Search

Dynamic 3D mazes present more challenging environments for reinforcement learning due to their uncertainty and incomplete information. Conventional reward functions can lead to slow and ineffective task training. This paper proposed an event-triggered integrated rewards scheme to solve the problem of finding multiple targets in a dynamic maze using reinforcement learning. The scheme expressed the various behavioral states in the 3D maze as events, which in turn derived the rewards. This paper divided rewards into environmental rewards and internal rewards. Environmental rewards directly related to the 3D maze mission and included node rewards reflecting the mission objectives and constraint rewards reflecting the mission constraints. Internal rewards linked to the agent's emotional state during the learning process and encompassed both judgement and mood rewards. The average performance of the integrated reward shows a 54.66% improvement compared to the upgraded reward. The results suggest that the integrated reward scheme offers benefits by increasing satisfaction with task completion, promoting exploration, and boosting training efficiency. [ABSTRACT FROM AUTHOR]

This paper proposed a particle swarm algorithm based on pyramid layer topology to optimize energy consumption trajectories of industrial robots. The algorithm introduced a pyramid layer topology to sort and stratify the particles thus improving the competitive strategy of the algorithm and increasing the population diversity. The algorithm introduced a new cooperation strategy to update the speed and position of the particles. It introduced a victory percentage to adaptively adjust the weight coefficients of the particle swarm algorithm and improved the search efficiency of the particles. In order to verify the effectiveness of the algorithm, this paper tested it on the set of test functions and compared it with other eight variants of particle swarm algorithms. The results show that the performance of the proposed algorithm has significant advantages. Finally, it applied the algorithm to industrial robot trajectory planning. Simulation experiments show that the algorithm can effectively solve the optimal trajectory of the robot's energy consumption, and the energy consumption of the robot is significantly reduced, which meets the kinematics and dynamics constraints of industrial robots. [ABSTRACT FROM AUTHOR]

This paper aimed to optimize the node selection problem in existing oracle machine schemes in the blockchain environment in order to improve the accuracy and reliability of oracle machine node selection. This paper introduced ORLM, a deep reinforcement learning based middleware for blockchain prophecy machine node selection. This middleware considered the consumption of multiple nodes under different service demands and modeled the reputation value of the prophecy machine nodes to sick the reputation value of the oracle machine data-providing nodes, thus avoiding the selection of nodes with malicious history as much as possible. With the deep reinforcement learning DQN algorithm, the middleware is able to optimize the process of selecting nodes for better node selection with security. The experimental results show that the oracle middleware is able to better satisfy the service requests of users. And it has high scalability and availability. It proves that the introduction of deep reinforcement learning to optimize the oracle node selection is a feasible direction. [ABSTRACT FROM AUTHOR]

At present, it is a general trend to introduce intelligent detection and control into traffic signal control system, especially reinforcement learning and deep reinforcement learning methods show great technical advantages in scalability, stability and extensibility, and have become a research hotspot in this field. This paper studied traffic signal control tasks based on reinforcement learning, systematically sorted out the classification and application of reinforcement learning and deep reinforcement learning in the field of intelligent traffic signal control on the basis of extensive research results on traffic signal control methods, and summarized feasible solutions to large-scale traffic signal control problems by using multi-agent cooperation. This paper classified and summarized the factors affecting the traffic scene of large-scale traffic signal control, put forward the current challenges and potential research directions in this field from the perspective of improving the performance of traffic signal controllers. [ABSTRACT FROM AUTHOR]

Semantic segmentation plays a crucial role in various fields such as medical image analysis and battlefield situatio- nal awareness. However, a single client often cannot provide a sufficient quantity and diversity of training data for the model. Therefore, it is necessary to train semantic segmentation models from distributed data, which exhibits complex and diverse characteristics. To prevent data privacy breaches and safeguard data security, the application of federated learning in the col- laborative training of semantic segmentation models across multiple clients has become a hot research topic in the field. Buil- ding upon the definition of federated semantic segmentation, this paper conducted a comprehensive analysis around the key characteristics of data heterogeneity and label deficiency in distributed complex data samples. The study encompassed a review of issues, methods, and exemplary model instances in federated semantic segmentation, evaluating the applicability and cha- racteristics of different methods, summarizing current application outcomes. The paper also proposed potential research oppor- tunities to address the issues of data heterogeneity and label deficiency. The research provides insights and references for the development of federated semantic segmentation methods and related studies tailored for distributed complex data samples. [ABSTRACT FROM AUTHOR]

As a global research topic, leather artifacts have been studied even longer than other materials. And the archaeology and research on them is more abundant in foreign countries. The technology of leather manufacturing, an ancient craft, has a long history of development, and can be traced back to the Paleolithic Age, which is almost as long as the history of human civilization. Therefore, the study of leather artifacts and their historical development is of great significance to the restoration and protection of leather artifacts. After reviewing earlier literature and books, this paper had a preliminary understanding of the unearthed situation and status of ancient leather abroad. With further reading, it finally analyzed and summarized the unearthed leather artifacts from nearly 39 regions of five continents. The structure of this paper is composed of three aspects: the situation of foreign leather artifacts, the characteristics of cultural relics and the leather tanning techniques. Firstly, it analyzed and summarized typical archaeological sites with abundant resources such as the Austrian salt mine, Danish marsh, Rome leather factories in Europe, Asia, Africa and so on, to understand the time, burial environment and uses of unearthed leather artifacts, so as to analyze the tanning process. Europe is rich in unearthed artifacts dating back to prehistoric times, including Iron Age hide fragments from the Italian ice fields, prehistoric hide fragments of shoes from the Swiss ice fields, and more than 200 Iron Age hides from the Hallstatt salt mine in Austria. The Pazyryk tombs of the Iron Age in the Altai Mountains of Asia provide important information for understanding the natural beast art style of the Altai Mountain areas. Egyptian leather, affected by the Nubian culture in Africa, is rich in colors and materials. Through reviewing the history and development of ancient leather in many areas, this paper further analyzed the tanning process, which could provide clues and information for the protection of ancient leather artifacts. Secondly, the ages of leather artifacts were divided into Neolithic Age, Bronze and Iron Age, A.D. to the 5th century A.D., and Middle Ages, and the characteristics of leather artifacts in different ages were analyzed by taking study areas as examples. For instance, in the Neolithic period, people used the serrated edges of stones and cherts to cut animal skin, and stitched leather with bone needles, bone spurs or plant fibers. The leather that Otzi the icaman wore in the late Neolithic period was made of animal tendons sewn by plants as stitches, which confirmed the characteristics of this era. Finally, the ancient leather tanning techniques were mainly plant tanning, mineral tanning, smoke tanning and oil tanning. Through understanding the leather artifacts of 39 regions, the characteristics of ancient tanning process were analyzed and compared. The result of the tanning process depends on a number of factors, such as the type of hides (bull or cow hides), breeds (cow or sheep leather), living conditions (animals’ health condition), the quality of the raw hides, the properties of different parts of the same hide and the tannin. With the plant tanning as an example, the source of plant tannins and the differences in functional groups in tannins affect the efficiency of tanning and the properties of tanned leather. Based on the published literature on leather artifacts, this paper widely collects, collates and analyzes the distribution of foreign leather artifacts and their characteristics, and summarized four ancient leather tanning techniques. Sorting out the relevant data of leather artifacts in 39 regions and understanding the human living environment and cultural history can help further study the development of leather in the context of the times. The study of various uses of leather can enrich the development of leather tanning technology, and research on tanning technology and tannins used is of great significance for the restoration and protection of leather artifacts. The tanning process of many unearthed leather artifacts is hard to determine. Thus, the analysis of four ancient tanning processes summarized by predecessors is emphasized in this paper to compare the differences between tanning techniques. The aim is to determine the tanning method of unearthed leather artifacts with more advanced and non-destructive technology and methods and to fill the gap of tanning information of leather artifacts for the protection and restoration. And this paper clarifies the development characteristics of the world leather artifacts and provides a reference to enhance the international study level of leather artifacts in China. [ABSTRACT FROM AUTHOR]

Nisu and Muji of the Yi nationality and Tuliao of the Zhuang nationality are ethnic groups from the Mengzi area of Honghe Hani and Yi Autonomous Prefecture. These three settlements may overlap or become closely connected, showing a distribution state that “the ethnic groups live among each other, while some live in concentrated communities of their own”. Despite the different languages of each ethnic group, people in the three ethnic groups can all use the local dialect of Mengzi for communication and have long had intersections in production and life. Thus, the daily dresses of the three ethnic groups shows a unified trend that is difficult to distinguish from the outside world. Therefore, the analysis of the evolution of the three costumes is conductive to interpreting the phenomenon of costume acculturation and revealing the deep reasons for their cultural blending and symbiosis. Based on field research, this paper provides substantial evidence such as image data, clothing objects and ancient literature, and analyzes the evolution and causes of the daily dresses of the three ethnic groups. As shown by the research, the daily dresses of the three ethnic groups have experienced an evolutionary process from dissimilarity to convergence, as specifically reflected in three aspects. First, the daily dresses of the three ethnic groups in the Qing Dynasty are quite different from the current gradually convergent dresses. Due to the policy of bureaucratization of native officers and the influence of Han culture, their tops gradually evolve into the “Da Jin Yi” style, with lapels leaning towards the right side. The “Zhuiji” (a cone-shaped hair bun atop the head) is replaced by the “Baotou” (a headdress that wraps the head with a headscarf), but the separate style of upper and lower garments persists. Second, due to the geographical proximity of their respective settlements as well as frequent interactions such as intermarriage and economic exchanges in various forms, the customs of the three ethnic groups gradually merge, inducing to a closer resemblance in clothing. However, distinctive elements of each ethnic group are still retained in their clothing. On the one hand, the typical wear for females in the daily dress of the three ethnic groups includes wearing tops, pants, and Baotou, with a focus on apron adorned with distinctive patterns around the chest and abdomen. Nonetheless, there are differences in apron decorations, embroidered shoe styles, and headwear designs among them. On the other hand, paper-cutting embroidery is a common technique for the costume of the three ethnic groups. This decorative craft is most exquisite among the Nisu women, while Muji and Tuliao females have largely lost the paper-cutting skill. Furthermore, the disappearance of the Zhuang language has gradually detached females’ clothing from its ethnic system. The blending and mutual influence of cultures inevitably assimilates their clothing, ultimately presenting a distinct “Yi” style. Third, as a new cultural construction phenomenon, the current clothing image results from the interaction, integration, acceptance, and adaptation among the three ethnic groups. It not only maintains the aesthetic characteristics and regional features of each ethnic group in terms of patterns and styles, but also absorbs and draws upon elements of Han clothing culture. Thus, the clothing finally shows the acculturation characteristics of the blending of multiple cultures. This paper takes the integration and evolution of females’ daily dresses of the three ethnic groups as the starting point. Based on the field research, clothing data are collected from these groups. Besides, historical literature is combined with oral accounts from cultural inheritors. The study is aimed to clarify the characteristics, similarities, and differences of typical daily dresses since the Qing Dynasty. Additionally, the paper seeks to gain an insight into the reasons behind the three ethnic groups’ mutual integration, so as to shed light on exploring cultural identity and cultural blending among different ethnic groups. [ABSTRACT FROM AUTHOR]

Globally, design management and its related concepts have attracted much attention from experts and scholars in design, sociology, economics and other related industries, and the design policy research involved in design management is gradually becoming one of the core elements for countries to promote the development of the fashion industry, condense the characteristics of the regional fashion culture and build fashion centers. Looking back at history, economic development, capital accumulation and national development are all closely linked to the prosperity of the textile industry. The prosperity of the textile industry has undoubtedly provided a solid foundation for the rise of the fashion industry. Although there are differences in the development paths and methods of the fashion industry in various countries, the active intervention and guidance of the fashion industry at the national level is a common theme, which is manifested in design management and policies. Take Britain as an example, the country has introduced a series of policies driven by official design organizations, which include strategic planning at the national level as well as policy measures proposed by industry associations, all of which have helped the fashion industry to become an important pillar of its economic development. As modern industry attaches great importance to design innovation and economic development, governments are gradually realizing the industrial benefits and economic value brought by design, and are committed to promoting research on the formulation and implementation of design industry policies. However, the formulation and improvement of design policy do not happen overnight, but through years or even decades of gradual evolution and optimization, which is is particularly obvious specially in fashion design, a unique economic field and cross-disciplines. In this paper, through combing the development of design policy and fashion industry in Britain, interpreting typical cases from a historical perspective, analyzing the logic between design policy and fashion industry, and summing up the historical experience and value of the contribution of design policy to the development of the regional fashion industry, the paper aims to provide a clear picture of the development of the fashion industry in Britain. Firstly, the design policy was placed in the context of design management for the corresponding analysis of design policy and the fashion industry in Britain. Secondly, the British fashion process was divided into four phases: germination, development, transformation, and renewal, so as to compare and analyze how the driving factors behind the fashion phenomena presented by the British fashion industry under the guidance of design policy and its leadership interacted with each other and formed synergy. Finally, the paper summarized the three stages of transformation and development of the British fashion industry and analyze the impact of design policy on each stage of transformation. It is hoped that the reconfirmation of historical samples will inspire design management research in the process of China’s fashion development, promote the integration and development of China’s design policy and fashion industry, and provide a model for the transformation of China’s fashion brands and the construction of the fashion consumer market. [ABSTRACT FROM AUTHOR]

The Party Central Committee has placed a high priority on the preservation and transfer of cultural heritage in recent years. To this end, the Committee has released several significant documents, including Opinions on the Implementation of the Project for the Inheritance and Development of Excellent Traditional Chinese Culture, which clearly outline the goals and objectives of the preservation of intangible cultural heritage and are extremely significant both historically and practically. The national intangible cultural heritage list has gradually added many areas of the blue calico printing and dyeing procedures. It is discovered that there is some literature on blue calico, but there are not many in-depth discussions of the topic. The research angle on blue calico is primarily concentrated on its creative design and application, as well as its in a particular area. The term “comprehensive discussion” refers to the fact that all blue calico is included in the summary rather than being restricted to a specific area, and there is a dearth of literature that analyzes the data and text that have been transformed into pictures, graphs, charts, and diagrams from the standpoint of visualization. Therefore, it is very crucial to create a knowledge map and visualization analysis of the blue calico to comprehend the development state, identify research hotspots, and forecast the future development trend of the blue calico. Professor Chen Chaomei of the Drexel University in the United States created CiteSpace, a Java application for information visualization that has been widely used in a variety of fields. Its features include a good visualization effect, a large amount of information provided, simple operation, etc. To analyze the literature in the field of blue calico in terms of publications, authors and collaboration, source journals and institutions, keyword clustering mapping, and bursts, the paper chose journal articles and dissertations from the CNKI database. The paper then used CiteSpace visualization software to analyze the literature and provide a summary of the research content on China’s blue calico over the previous 23 years. Data support for the development of new research directions can be obtained through data visualization and analysis of the existing blue calico research literature from multiple dimensions scientifically and systematically, and understanding the current status and hot trends of blue calico research from a macroscopic point of view. It is discovered that: there are very few complete works on blue calico, and the research varies greatly by location; colleges and universities are the primary sources of literature research institutions, with the majority of them being collaborations between the same institution and department; the design of patterns or motifs, protection and inheritance, and innovation and development are the keywords that are concentrated in these areas; the literature research has undergone three phases: the period of exploration, the period of development, and the period of innovation and inheritance; and improving product design, cultural and creative products, printing, and dyeing direction is going to be a major trend in the future. The legacy of blue calico must adapt to the current circumstances while providing effective protection. Achieving a balance between inventive progress and inheritance requires the integration of current technology and digital communication while maintaining the use of natural raw materials, traditional techniques, and inherited pattern styles. [ABSTRACT FROM AUTHOR]

The high-quality natural luster of silk fabrics is its essential feature that distinguishes them from other natural fiber fabrics, making them stand out among many fabrics. In the evaluation of visual style of clothing, luster can give fabrics different image perceptions. Words such as “noble”, “gorgeous”, “advanced” and “classical” often appear in describing glossy silk, while they are rare in describing cotton and linen fabrics of the same color. In addition to fiber properties, yarn structure and fabric organization, fabric color is also an important factor affecting fabric gloss. Existing studies have found that there is a good linear relationship between luster and brightness of fabrics, while the relationship between brightness and luster of fabrics has not been discussed in detail. Specifically, the luster index belongs to the physical properties of the fabric, and it can not directly represent the quality of the luster of the fabric. The luster sensation of fabric is an index that connects the visual aesthetic needs of consumers. After visual stimulation of people through the surface luster of fabric, people’s brain can form feelings and cognition, which belongs to people’s subjective perception and evaluation of the visual style of fabric. To further explore the impact of brightness on the luster of silk fabrics and establish an evaluation system for the luster of silk fabrics, this paper explored the impact of brightness on the luster of silk fabrics based on eye tracking technology and subjective evaluation methods. With gaze time, number of gaze points, number of entry times and first entry time as indicators, the subjects’ visual preference for the luster of silk fabrics with different brightness values was analyzed from the perspective of visual perception, and the evaluation indexes of pleasure, arousal, luster warmth, luster softness and luster brightness were analyzed from the perspective of emotional perception. The results show that the brightness attribute of silk fabrics has a significant influence on the attention degree of fabric. The fabric with too high or too low brightness has a low attention degree, while the fabric with medium brightness has the highest attention degree. The brightness attribute has a significant impact on the fabric emotion and the perception evaluation of luster. The gray fabric with medium brightness has the softest luster and makes people feel the most pleasant, comfortable and relaxed; the white fabric with high brightness has the brightest luster and makes people feel the most awake. There is little difference in luster warmth between fabrics with different brightness values. There is a significant correlation between the visual attention of silk fabrics and the perception of fabric emotion and luster. The higher the fabric pleasure score is, the higher the visual attention of silk fabrics will be. The higher the arousal rating of the fabric, the more likely the subjects are to be attracted to the fabric. In this paper, the influence of brightness on the luster of silk fabrics is studied from the two dimensions of visual perception and emotional perception, so as to provide reference for silk design and inject new vitality into the development of the silk market. [ABSTRACT FROM AUTHOR]

From the founding of the People’s Republic of China to the early days of reform and opening-up, China printed and issued a great number of samples of silk samples for export by different compilation subjects, different versions of form, and different sales markets. However, of these silk samples collected from the collecting institutions and individual collectors, many scattered single-volume or single-page samples lack the annotation of relevant compilation and issuance time. This issue has brought difficulty and confusion to the collection and researchers on the examination and utilization, and even misunderstanding on the citation and research. It also leads to the the fact that it is difficult to properly reflect the collection value, historical value, cultural value, and social value of this part of the samples. Taking the series of exported silk samples compiled and issued by China Silk Company and other companies in the previous years as the main object, this paper clarified the compilation and form characteristics of the editions in different years from the physical form of the editions. Moreover, from the cultural form of the editions, the paper explored the relationship between socio-economics, foreign trade strategy, science and culture and the changes of the editions, as well as their value and contribution to the development of China’s modern silk design and silk foreign trade. The research results provide meaningful references for the collection and identification of exported silk samples of modern days, the study of the history of Chinese silk design, and the innovative design of modern silk. The paper clearly defined some conceptual problems of editions in the study of exported silk samples by drawing on the relevant research methods of edition studies, archival science, bibliography etc. The paper also carried out in-depth research, collection and sorting of the silk samples between 1957–1985, and examined and elaborated the compilation subjects, the form of editions, and the compilation characteristics of each period, providing detailed and accurate documentary evidence and graphic references for the screening of single-page silk samples compiled in different periods and by different subjects, and solving the confusion and problem that it is difficult to judge the specific age when confronting various single-page silk samples in the study of the history of modern silk design. Exported silk samples are one of the main transmission carriers of silk design culture and silk trade. The paper believes that, whether it is the study of exported silk samples or domestic silk samples, if it is only concerned about the silk sample or its general archival value, while ignores the identification and thorough examination of the subject, time and mode of dissemination of the samples from the perspective of editions, and ignores the discussion on the relationship between the formation and development of the samples and the driving forces such as politics, economy, culture and ideology, then there may be some limitations and deviations in the cognition, understanding and conclusion of the research, which will further affect the academic rigor of the research on satin varieties and colors and the development of silk design history. Therefore, the textual research and exploration of the issue subject, time and historical context of silk samples in different periods, and the compilation principle, as well as the overall analysis and demonstration of silk samples as a material form reflecting “historical presence”, should become the subject of full attention in the study of the history of modern silk design. [ABSTRACT FROM AUTHOR]

In the context of the rapid development of the digital economy information technologies represented by cloud computing Internet of Things and digital twins are fully embedded in the garment industry. The garment industry is rapidly reorganizing the entire industrial chain from design to after-sales. At present China's garment industry as a laborintensive industry is facing the dilemma of gradually weakening cost advantages market contraction weak high-end product development and manufacturing capabilities. Accelerating the pace of technology integration and improving the innovation ability of garment enterprises to cope with the development dilemma has increasingly become the consensus of the industry and academia and even the focus of government decision-making. By combing the literature it is found that there is little literature on the evaluation of innovation ability of textile and garment enterprises and there are problems of strong subjectivity in the evaluation process and insufficient sample size. At the same time driven by digital technologies such as big data artificial intelligence and industrial Internet the innovation process of garment enterprises is gradually integrated and a new index system needs to be constructed to evaluate their innovation ability. To promote the technological progress and innovation development of clothing enterprises this paper took China's listed clothing companies as the research object analyzed the main factors affecting the innovation ability measured the level of innovation ability and evaluated the innovation ability. The research time interval is from 2016 to 2022. Through the analysis of the relevant literature in the field of textile and garment this paper chose the listed companies in the textile and garment industry. After excluding the enterprises with delisting risk undisclosed annual report and termination of listing during the sample period this paper selected 25 sample enterprises that have survived. In terms of evaluation methods global factor analysis has the advantage of objective results in dealing with multi-dimensional and multi-index index system which meets the needs of research. Therefore this paper introduced the dimension of digital level and constructed the evaluation index system of innovation ability of listed clothing companies which contains 15 indicators in five dimensions innovation input innovation output business performance environmental factors and digital level. Based on the panel data of 25 listed Chinese clothing companies from 2016 to 2022 the global factor analysis method was used to aggregate 15 quantitative indicators into five common factors. The weights of these common factors were determined according to the corresponding variance contribution rate and then the scores of each common factor were weighted and averaged to obtain the innovation ability score. After obtaining the score of enterprise innovation ability the average scores of common factors and comprehensive factors of sample enterprises were calculated to explore the overall level of innovation ability. Three major conclusions were drawn. First R&D investment and patent output enterprise growth business environment and digital talents regional scientific research environment and equipment digitization level positively affected the innovation ability of listed clothing companies. Among them R&D investment and patent output had the highest variance contribution rate of 20. 32% which was the key factor affecting innovation ability. Second during the sample period the average score of innovation ability continued to decrease from 0. 003 to - 0. 011 indicating that the overall innovation ability of listed clothing companies was still at the middle and lower levels. Third the average score of business environment and digital talent factor decreased from 0. 024 to 0. 020 in fluctuation while the average score of regional scientific research environment and equipment digitization level factor continued to rise from - 0. 002 to 0. 013 indicating that the overall level of digitization of sample enterprises was good. Finally this paper put forward four major suggestions. First the core enterprises of the supply chain need to enable the enterprises on the chain to share the dividends of digital applications and also shoulder the burden of promoting the whole chain of digital technology. Second enterprises with weak innovation ability should increase investment in innovation resources and actively carry out digital cooperative innovation. Third the government should introduce diversified support policies improve the level of patent application services in the garment industry and accelerate the construction of information technology infrastructure. Fourth it is necessary to rely on industry associations and professional societies to build a digital innovation exchange platform and share digital innovation achievements. This paper evaluates the innovation ability of listed clothing companies from five aspects innovation input innovation output business performance environmental factors and digital level. It is found that innovation ability is affected by R&D investment patent output enterprise growth business environment and digital talents regional scientific research environment and equipment digital level. Follow-up research can measure the level of equipment digitization from more perspectives such as digital fixed assets plus digital intangible assets divided by total assets. [ABSTRACT FROM AUTHOR]

Weaving and embroidering are the craft of weaving knitting or embroidering with cotton linen silk wool and other textile materials. China is the starting point of the Silk Road the birthplace of sericulture silk reeling and silk weaving and the exquisite skills of the weaving and embroidery industry enjoy a high reputation in the world. The patterns of woven and embroidered artifacts present historical cultural and artistic values highlight the formal beauty of plastic arts in traditional Chinese culture and provide rich material resources for cultural and creative design. However the traditional weaving and embroidering design mainly relies on manual pattern extraction which has problems such as high cost complicated steps long cycle and low efficiency. To this end this paper proposed an algorithm based on genetic algorithm to adaptively determine the optimal threshold value of Canny operator to automatically extract the patterns in the images of woven and embroidered artifacts improve the extraction efficiency and effect make the artifacts "live" and promote the inheritance and protection of traditional Chinese culture. To realize the automatic extraction of patterns from images of woven and embroidered artifacts and solve the problem that traditional Canny operators need to manually determine the threshold for edge detection of images of woven and embroidered artifacts and that the extraction efficiency is not high the article took the images of woven and embroidered artifacts as the research object proposing a genetic algorithm to optimize the Canny operator for the extraction of patterns from woven and embroidered artifacts. Firstly the paper analyzed the characteristics of the images of the woven and embroidered artifacts and used bilateral filtering algorithm and mean drift algorithm to smooth the noisy original image for the gray scale of the smoothed graph it selected the genetic algorithm to solve the optimal threshold of Canny operator and input the optimal threshold into Canny operator for the edge detection of the gray scale graph. Then the paper expanded the morphology of the edge image and automatically filtered out noise and incomplete pattern samples based on the area length and width of each connectivity domain. Finally the algorithm was evaluated for the effect of extracting patterns and the algorithm's running time. Experiments show that the algorithm can accurately detect the real edges of the pattern in the image of the woven and embroidered artifacts and the edges detected are clearer and more continuous than those detected by the other five traditional operators. In terms of pattern extraction precision and pixel accuracy PA it is better than the existing methods such as traditional Canny operators hybrid frog jump adaptive Canny operator Otsu maximum optimized Canny operator and so on. The algorithm is robust to the presence of folds that lead to pattern deformation in the woven and embroidered artifacts and all the patterns are successfully extracted. The algorithm can effectively detect the real edges of the patterns in the image of woven and embroidered artifacts and complete the pattern extraction. Woven and embroidered artifacts contain deep cultural heritage and artistic value and through pattern extraction designers can integrate traditional cultural elements into modern design to create unique cultural and creative products. In this paper the algorithm solves the problem that the traditional Canny operators need to determine the threshold value for the edge detection of woven and embroidered artifacts and that the extraction efficiency is not high. In the process of cultural and creative design the digitization of cultural and creative materials is the first step. In addition the grasp and application of the knowledge of history and culture artistic connotations unique stories and symbolic meanings embedded in patterns can more accurately capture the essence of the culture and the emotional expression it represents. For this reason it is of deeper significance and value to carry out research on the integration and mining of multimodal information such as patterns and knowledge in the future. [ABSTRACT FROM AUTHOR]

During the period of the Republic of China, the traditional Chinese cheongsam successfully completed the modernization transformation with the methods of “Westernized Chinese style” and “integration of the East and the West”, and became the only “living fossil” of the successful transformation in the 5,000 years of traditional Chinese clothing history. In the context of “carrying forward the excellent traditional culture of China and enhancing cultural self-confidence”, in-depth research on the cheongsam of the Republic of China may point out the direction for today’s fashion designers in inheriting and innovating traditional clothing culture. The cheongsam of the Republic of China is a “transitional form” in the development sequence of the cheongsam. This paper used the methods of literature research, physical research and interviews with folk artists to sort out and summarize the development of cheongsams through four main periods: Manchu’s cheongsam, Shanghai style cheongsam, Taiwan and Hong Kong cheongsam and contemporary fashion cheongsam. Specifically, the development of the Shanghai style cheongsam of the Republic of China experienced the evolution of different shapes such as the inverted large-sleeve cheongsam, the tailored cheongsam and the “typical cheongsam of the Republic of China” in the mature stage. On this basis, the paper defined the “Shanghai style cheongsam of the Republic of China” as the typical cheongsam of the Republic of China in the mature stage after the revolution in the 1930s and 1940s. The Shanghai style cheongsam of the Republic of China is convenient, beautiful and economical, showing the characteristics of seeking novelty and difference. The overall style is simple and elegant, subtle and soft, and matches well with both Chinese and Western clothing. By observing and recording the cutting process of a typical Shanghai style cheongsam of the Republic of China, the paper tried to make a painstaking examination from the size and cutting method of traditional clothing philosophy, and explored the traditional creation concept and traditional Chinese aesthetic of the typical Shanghai style cheongsam through the phenomena. The study pointed out that the cutting method of the Shanghai style cheongsam in the Republic of China maintained the traditional Chinese plane cutting, did not make plates in advance, and was generally carried out by the way of laying materials on the board and cutting while sewing. The technical difficulty lies in how to solve the problem of “covering the front” caused by “digging the front”. This paper shows the most commonly used “off-warp cutting method” of the Shanghai style cheongsam of the Republic of China, and restores the traditional way of inch picking, the techniques of “front stealing”, the shrinking of “pleats”, blocking, ironing and collar making. This paper interprets the creative concepts of “applying art according to materials” and “carrying Tao with skills” and the costume-making ideals of “integrality, seamless clothing, and material saving”, and reveals the aesthetic characteristics of “beauty of shape”, “beauty of artisan” and “beauty of workmanship” of cheongsam craft from the aspects of structure, molding and techniques, in order to provide reference for further research on the excellent Chinese costume culture. [ABSTRACT FROM AUTHOR]

In Lhis paper, human embryonic sLcm cell line and iLs diffcrcnLiaLcd neural sLcm cell line nrc sclccLcd as Lhc objccLs Lo sLiidv Lhc rcgulaLorv cilccL of his Lone modificaLions on Lhc diffcrcnLiaLion of embryonic sLcm colls ・ The disLribuLion paLLcrns of 8 his Lone modificaLions and funcLional clusLcrs of his Lone modificaLions nrc obLaincd in Lhc flanking regions of LranscripLional iniLiaLion si Les of Lhc diffcrcnLially expressed genes in Lhc Lwo cell lines ・ The resnlLs show LhaL in Lhc Lwo cell lines, Lhc disLribuLion paLLerns of 8 hisLonc modificaLion profiles arc consisLcnL and show Lwo disLribuLion Lypcs; The fLincLional clusLei's compose of 113K27ac, 113K4mc3 and 113K9ac arc conscrvaLivc, while Lhc funcLional ckisLcrs compose of 1131<27mc3, 113K36mc3 and 113K79mcl and Lhc funcLional cl us Lei's composed of 113K9mc3 and 113K27mc3 disappear during Lhc diffcrcnLiaLion of embryonic sLcm cells inLo neural sLcm cells・ This paper reveals Lhc pailial rcgulaLory mechanism of hisLonc modificaLions on Lhc dillcrcnLiaLion of embryonic sLcm cell lines inLo neural sLcm cell lines and pro vids some imporLanL LhcorcLical basis for Lhc sLudv of molecular rcgulaLorv mechanism of Lhis diffcrcnLiaLion process. [ABSTRACT FROM AUTHOR]

This article examines Ziti xiaozhi 紫隄小志and Ziticun xiaozhi 紫隄村小志, compiled by Wang Yong’an 汪永安 in the early Qing Dynasty. Through the analysis of the genesis context and content changes of these local gazetteers, this paper shows how local social conditions and changes in the political environment affected the content of local gazetteers. In particular, I first demonstrate that Wang Yong';an's inclusion of a large number of good deeds of the Hou 侯 family of Shanggu 上谷 and the Wang 汪 family of Pingyang 平陽 in his gazetteers had two purposes. On one hand, it was an attempt to influence compilers of official gazetteers to include members of their own clans. On the other hand, it reflected his belief that narratives of loyalty and righteousness could change the declining moral standards of Ziti villagers. Second, this paper also points out that in Ziticun xiaozhi, Wang Yong'an deleted sensitive content that expressed nostalgia for the Ming Dynasty and that affirmed the legitimacy of the Southern Ming regime. This reflects the latent self-censorship that emerged among literati during the Yongzheng 雍正 period and illustrates the profound impact of political changes on how local elites wrote township gazetteers. [ABSTRACT FROM AUTHOR]

Underwater fish target recognition technology is an important technology in ocean exploration. However, the acquisition of underwater resources is very expensive and cannot meet the requirements of training large-scale deep neural networks. Aiming at the problem of small or even zero samples of underwater fish data, this paper proposed a Joint Deep Statistical Feature Alignment（JDSFA) method based on transfer learning to solve the problem of fish target identification in small samples. Using ResNet-50 as the backbone network, the mean square and covariance were incorporated into the weight selection algorithm to construct a joint domain adaptive loss function to align the feature distribution between the source domain and the target domain. In addition, we also designed a global loss function to combine the source domain loss with the inter-domain adaptive loss by using adaptive weights to realize the fish target recognition task. The published underwater fish data set QUT was used for experimental verification, and the results all showed that the effectiveness of JDSFA method in fish identification was 3.59%,4.96% and 5.91% higher than that of the current representative DADAN, PMTrans and DSAN methods, respectively. It is further demonstrated that the JDSFA method proposed in this paper has good application value in fish identification task. [ABSTRACT FROM AUTHOR]

In the process of detecting human respiration and heart rate using millimeter wave radar, the static clutter in the environment makes it extremely difficult for the radar to discriminate the information about the movement of the human chest cavity, which affects the separation of respiration and heart rate signals. At the same time, it is difficult to separate the harmonic components of the respiration signal in the high-frequency band and the heartbeat signal in the low-frequency band because the frequencies of the harmonic components in the high-frequency band are similar.To solve the above problems, this paper proposes a joint modal spatial domain estimation detection method, which mainly adopts an single ensemble empirical modal decomposition (SEEMD） algorithm to decompose the thoracic phase signal into each modal component to eliminate the influence of static noise on the respiratory heartbeat signal, and then uses a multiple signal classification (MUSIC) algorithm to convert the heartbeat modal component signals from the time domain to the spatial domain to estimate their frequencies to eliminate the influence of respiratory harmonics.The experimental results show that the accuracy of respiratory rate under the detection of this paper’s method is 95.76%,and the accuracy of heart rate is 98.76%.Compared with the traditional algorithms, the proposed method is more accurate in estimating respiratory rate and heart rate. [ABSTRACT FROM AUTHOR]

BACKGROUND: With the continuous improvement and progress of the magnetically controlled growing rod technology in the field of the treatment of spinal deformities, numerous studies have been put into this field, but the main research status, hot spots, and development trends are not clear enough. OBJECTIVE: Based on bibliometrics, this paper discusses the quality and quantity of articles in the field of using magnetically controlled growing rods to treat spinal deformities from different countries, aiming to clarify the global development trend of magnetically controlled growing rods and evaluate the research productivity, research trends, and research hotspots in the world. METHODS: The articles published from 1998 to 2023 were retrieved mainly based on the Web of Science database. CiteSpace 5.8 and VOSviewer 1.6.19 software were used to analyze the data and generate a visual knowledge map. The following parameters were evaluated for all studies: the total number of published papers, centrality, h index, the contribution of countries, authors, and journals, and the trend and hot spots were explored through the analysis of co-citation, highly cited literature, and literature keyword explosion. RESULTS AND CONCLUSION: (1) Finally, 138 articles were included. From 2009 to 2020, the number of published articles in this field gradually increased. The United States has the largest number of articles (53, 37.32%), and the United States has the highest h index and centrality of articles. (2) The results of keyword analysis showed that: the top ten keywords, such as early-onset scoliosis, surgery, complications, and so on, objectively and truly reflected the current situation and hot spots of magnetically controlled growing rod in the field of spinal deformity treatment. In recent years, the research focus in this field is the treatment failure caused by risk factors such as the pull-out of the magnetically controlled growing rod, implantation failure, and rod fracture, the accurate use of the corresponding medical classification, the monitoring and treatment of complications such as quality of life and cerebral palsy. (3) The co-citation results showed that: combined with the innovative and effective research of the magnetically controlled growing rod technology, the classification application of spinal deformity and the monitoring and treatment of related complications may be the research trend in this field. (4) Many highly cited articles further emphasized the therapeutic effect of magnetically controlled growing rod technology, providing an effective new idea and technical support for the field of spinal deformity correction. (5) The results of literature keyword explosion analysis demonstrate that the risk factors, medical classification, quality of life, and cerebral palsy of the application of magnetically controlled growing rods may become the research frontier in this field. (6) It can be seen that the application of magnetically controlled growing rod technology in the classification of spinal deformities and the in-depth study of related complications are the development trend in this field, but to further understand the effectiveness and safety of magnetically controlled growing rod technology in the treatment of spinal deformities, we still need long-term follow-up evidence. The overall research level of this field has steadily improved in recent years, but there are also problems such as the small number of high-quality articles and the unbalanced development of research in various regions. [ABSTRACT FROM AUTHOR]

Taking CNKI Full-text Database as the data source, the literatures on the study of Amorpha fruticosa L.published from 2012 to 2021 were retrieved, and the annual change trend of number of articles, literature types, research teams, research institutions, research high-fre- quency words, single citation frequency and literature research direction were analyzed systematically by Excel and VOSviewer softwares. The results showed that from 2012 to 2021, a total of 618 Chinese literatures related to A. fruticosa were included in the CNKI database, of which 261 papers (43.72%) were forestry literatures. Among all these literatures, 193 were supported by fund projects, and 167 (86.53%) were supported by national fund projects. The research institution with the largest number of papers was Northwest A & F University, with a total of 57 papers (25.68%). Journal of Northwest A & F University collected the most related literatures on Amorpha amorpha, number of which was 25 in total. Moreover, the ecology and environment, afforestation and cultivation, plant physiology of A. fruticosa were the research hotspots in recent years. China had achieved high level of scientific research results in these three research directions. Although the number of literatures on A. fruticosa showed a downward trend since 2014, it had increased in 2020, which indicated that the scientific research value of A. fruticosa had regained the attention of scholars. [ABSTRACT FROM AUTHOR]

Urban-rural integration is the only way for rural revitalization and the due meaning of new urbanization. Digital inclusive finance enables new fusion of industrial elements to promote urban-rural integration. Based on the inter provincial panel data from 2011 to 2020, this paper tests the impact of digital inclusive finance on urban-rural integration and its transmission mechanism. The study found that digital inclusive finance can effectively promote urban-rural integration. Further research found that digital inclusive finance promotes the optimization and upgrading of industrial structure and indirectly promotes urban-rural integration; digital inclusive finance and urban-rural integration show strong spatial relevance in space, but have not produced spatial spillover effect. The research of this paper provides evidence, experience and policy enlightenment for guiding the deep integration of digital technology and inclusive finance, optimizing industrial structure, strengthening interval links, breaking administrative barriers and realizing the deep integration of urban and rural areas. [ABSTRACT FROM AUTHOR]

Essential oils are expensive and have the name of "liquid gold". It has a strong aroma and is widely used in food, cosmetics and tobacco. Studying the extraction and application of rose essential oil will improve the economic efficiency of the essential oil industry. This paper reviews the extraction methods and advantages and disadvantages of rose essential oil in recent years, and introduces the antioxidant, antibacterial and anti-anxiety properties of rose essential oil, and summarizes the application of rose essential oil in daily life. This paper also presents an outlook on the subsequent development of essential oil applications in order to provide some theoretical support for the development and research of the extraction and application of rose essential oil. [ABSTRACT FROM AUTHOR]

BACKGROUND: In recent years, numerous studies have shown that long non-coding RNAs (lncRNAs) have an important role in the pathogenesis of periodontitis, including the immune response process and the biological activity and function of cells (periodontal stem cells and osteoblasts). Researchers attempt to regulate periodontal inflammation and periodontal regeneration by regulating lncRNA expression levels. OBJECTIVE: To review the progress of research on lncRNAs in periodontitis, thereby advancing the research of lncRNAs in periodontitis. METHODS: The first author searched PubMed, China National Knowledge Infrastructure (CNKI), Web of Science database, and WanFang Database for relevant literature published up to March 2023. “Long non-coding RNA, lncRNA, periodontitis, periodontium, immunity, inflammation, periodontal ligament stem cells, osteoclasts, osteogenic differentiation, bone resorption, bone formation, recurrence, hypoxia, oxidative stress, static mechanical strain”were used as the Chinese search terms. “lncRNA, periodontitis, periodontal, immunity, inflammation, periodontal membrane stem cells, osteoclasts, osteogenic differentiation, bone resorption, bone formation, recurrence, hypoxia, oxidative stress, static mechanical strain” were used as the English search terms. The title and abstract of each paper were read for initial screening, and 87 papers were finally selected for inductive analysis. RESULTS AND CONCLUSION: Periodontal pathogens stimulate the body, leading to immune imbalance that triggers inflammatory response and destroy periodontal tissue, and lncRNAs are involved in its regulatory mechanism. LncRNAs are involved in the pro-inflammatory regulation of periodontal ligament cells in an inflammatory environment, and their effects on osteoclast differentiation are regulated through ceRNA mechanism, which provides new clues for exploring the pathogenesis of periodontitis. For B cells and macrophages, lncRNAs can regulate the infiltration, cell activity and function of their subsets in periodontitis. LncRNAs participate in the immune response related to periodontitis mainly through two pattern recognition receptors, Toll-like receptors and NOD-like receptors, and nuclear factor-κB signaling pathway. To investigate whether lncRNAs can be used as a biomarker of periodontitis has great value in the diagnosis and prognosis of periodontitis. Animal experiments have demonstrated that the role of lncRNAs in periodontitis can be reversed by modulating the expression level of lncRNAs and thus lncRNAs act as an anti-inflammatory agent, which is of great value for the study of immunotherapy in periodontitis. The regulation of lncRNAs on periodontal ligament stem cells is mainly realized through endogenous competition mechanism and various signaling pathways, and its effects are influenced by various factors, such as inflammatory environment, mechanical strain, hypoxia and oxidative stress. Research on related mechanisms through these related factors provides new ideas for the treatment of periodontitis. [ABSTRACT FROM AUTHOR]

Plant extracts are natural active substances derived from plants, which have the functions of anti-oxidation, anti-inflammation, regulating flora. They are widely used in medicine, food and other fields. Many studies have showed that plant extracts have great beneficial effects in animal husbandry and are important green feed additives. In this paper, the research progress on application of plant extracts in laying hens was reviewed. The regulatory effects of plant polyphenols, plant polysaccharides, plant flavonoids and alkaloids on the productive performance, anti-oxidative, immune function, lipid metabolism and intestinal flora of layers were emphatically described. The purpose of this paper was to provide reference for the application in layer production. [ABSTRACT FROM AUTHOR]

In order to solve the problems of difficulty in obtaining paired data sets and poor quality of enhanced images in the process of low-light image enhancement, the implementation of unpaired low-light image enhancement was studied by improving the cycle generative adversarial network model. In the generator part, a U-NET model integrated with the Vision Transformer structure was used to replace the original generator model, so as to improve the cycle consistency and content retention of image transformation, and effectively deal with the problem of long-distance spatial correlation commonly existing in image research. In the discriminator part, PatchGAN was selected to replace the traditional discriminator according to the characteristics of image research to improve the discrimination ability of image details. At the same time, the identity consistency loss function was introduced to improve the image quality. The results show that compared with the traditional method, the improved model in this paper has better subjective visual effect, and also has a corresponding improvement in the objective evaluation index. It can be seen that the improved model in this paper is effective. [ABSTRACT FROM AUTHOR]

In order to explore the hotspots and research trends of domestic research on biochar in tobacco agriculture in recent years, bibliometric methods were used to analyze papers about biochar application in tobacco planting research included in the China National Knowledge Infrastructure (CNKI). The numbers, annual distribution, author information, publications and research content were statistically analyzed, and the CiteSpace V visualization software was used to predict and analyze research hotspots. The results showed that a total of 114 journal papers and 81 dissertations on the application of biochar to tobacco planting were retrieved, including 8 doctoral dissertations and 73 master’ s dissertations. The institution with the most research in China was Henan Agricultural University, and Liu Guoshun was the scholar with the most published papers. Domestic research on tobacco biochar still lacked a stable core author group, and the number of core authors was small. Tobacco biochar application hotspots focused on tobacco quality, chemical composition and tobacco-growing soil. In recent years, research hotspots tended to be on the effects of biochar on soil microbial communities and heavy metals in tobacco leaves. [ABSTRACT FROM AUTHOR]

Accurately identifying the spatial characteristics of “non-grain” cultivated land and proposing control measures have positive significance for accurate control of “non-grain” cultivated land. Taking Youjiang District as the research area, this paper identified the spatial characteristics of “non-grain” cultivated land in Youjiang District from the aspects of land type composition, slope distribution, landscape pattern, spatial adjacency, farming distance and transportation convenience. This paper proposed optimization and control measures for different types of “ non-grain” cultivated land to in order to guide cultivated land to grow food. The results show that: The total amount of “non-grain” cultivated land in Youjiang District has reached 308. 38 km², mainly dry land, followed by garden land and forest land. The slope of “non-grain” cultivated land is mainly greater than 6°, and when the terrain slope is less than 25°, the area of “non-grain” cultivated land increases with the increase of slope grade. “Non-grain” cultivated land is fragmented, with high spatial proximity to gardens and woodlands, and strong interaction. The closer to rural settlements (less than 800 m) and roads ( less than 1 200 m), the larger the proportion of “ non-grain” cultivated land, and the spatial distribution of “non-grain”cultivated land is affected by cultivation distance and transportation convenience. [ABSTRACT FROM AUTHOR]

Accelerating the citizenization of agricultural migrant population is an important task to realize urbanization, and the fundamental reason for the slow progress of citizens is the excessively high cost of urbanization of agricultural migrant population. At present, there are a considerable number of research findings concerning the cost of agricultural transfer of population urbanization. This paper adopts literature analysis method to review and sort the relevant research results of domestic scholars on the cost-sharing of urbanization for agricultural transfer populations. It elaborates on aspects such as the composition of cost-sharing for urbanization of migrant agricultural populations, precise calculation and quantitative methods of cost-sharing, and the construction of cost-sharing mechanisms. By combing and summarizing the existing research literature, the paper continuously promotes the in-depth study on the cost sharing of citizenization of the migrant agricultural population, so as to promote the development of new urbanization and rural revitalization. [ABSTRACT FROM AUTHOR]

Objective A bibliometric analysis of the literature related to stroke and the blood-brain barrier was conducted to obtain a research map, explore hotspots and trends, and provide references for clinical treatment and research. Methods The literature related to stroke and blood-brain barrier from 1 January 2001 to 28 February 2023 was explored in the Web of Science core database. Using bibliometrics, CiteSpace V6.1.R6 was used to analyze the distribution of years, countries/regions, research institutions/system, authors, publications, cited literature, keywords and research trends. Results A total of 5028 papers were included after screening, with an overall upward trend in the number of published papers. The United States had the most research on this topic, followed by China’s mainland and Germany. Most of the top 10 research institutions/system were from the United States, France and China, with strong collaboration between countries/regions and research institutions/system. Among the authors, Chopp Michael from the United States ranked first with 49 papers. Among the research trends, ischemic stroke, miR-126 in non-coding RNA, blood-brain barrier dysfunction and drug delivery were the hot spots in the last three years. Conclusions Blood-brain barrier and stroke are inextricably linked. The dysfunction and repair mechanism of blood-brain barrier during stroke, the circulation biomarkers released by blood brain barrier and the use of blood-brain barrier opening time to increase drug absorption are worthy of further study [ABSTRACT FROM AUTHOR]

A prediction model is a statistical model used to predict the probability of an individual with a target event or to predict the outcome value. Visualization of prediction model results is an essential part of the whole process of developing a prediction model. A good presentation of a prediction model can not only make the prediction results more readable and interpretable, but also determine its use and convenience to a large extent. This paper provided a detailed introduction to various forms of prediction model presentation and reported their advantages and disadvantages. Combining clinical prediction model research on cerebrovascular disease, this paper introduced the application of each presentation in cerebrovascular disease research through research examples. [ABSTRACT FROM AUTHOR]

The Whale Optimization Algorithm (WOA) is a novel swarm intelligence optimization algorithm that converges based on probability. It features simple and easily implementable algorithm principles, a small number of easily adjustable parameters, and a balance between global and local search control. This paper systematically analyzes the basic principles of WOA and factors influencing algorithm performance. It focuses on discussing the advantages and limitations of existing algorithm improvement strategies and hybrid strategies. Additionally, the paper elaborates on the applications and developments of WOA in support vector machines, artificial neural networks, combinatorial optimization, complex function optimization, and other areas. Finally, considering the characteristics of WOA and its research achievements in applications, the paper provides a prospective outlook on the research and development directions of WOA. [ABSTRACT FROM AUTHOR]

In order to ensure that the overall prefabricated underwater push-out final joint can control the safety risk during construction process under offshore conditions, and to meet the design requirements of centimeter-level installation and docking accuracy, this paper explores the issue of the closure width in the final joint construction of steel shell immersed tunnels. By analyzing the actual construction parameters of the installed pipes and the specific weather window conditions, this paper focuses on the entry method of the pipe into the closure, the longitudinal positioning ability of the pipe, and the cumulative length errors of the tunnel prefabrication and installation. The results show that controlling the closure width of the final joint at2.2 m is beneficial for providing space for post-welding operations, enhancing ventilation effects, satisfying large-scale welding operation conditions, facilitating the deployment of large -scale equipment, and improving work efficiency. Meanwhile, it provides an effective space for sinking and docking operations in the construction of immersed pipes, reducing operational risks. This study is of great significance to provide useful references for the final joint construction of steel shell immersed pipes. [ABSTRACT FROM AUTHOR]

Aiming at the problems of inaccurate semantic segmentation results and rough saliency maps of indoor scene images, this paper proposed a network architecture (feature regulator and dual-path guidance, FG-Net) based on multi-modal feature optimization extraction and dual-path guided decoding. Specifically, the feature regulator sequentially performed noise filtering, re-weighted representation, differential complementation and interactive fusion on the multi-modal features at each stage, and optimized multi-modal feature representation in the feature extraction process by strengthening RGB and depth feature aggregation. Then, the dual-path guidance component introduced rich cross-modal cues after feature interactive fusion in the decoding stage to further take advantage of multi-modal features. The dual-path cooperative guidance structure outputted a more detailed saliency map by integrating multi-scale and multi-level feature information in the decoding stage. This paper conducted experiments on the public datasets NYUD-v2 and SUN RGB-D, and achieved 48.5% in the main evaluation metric mIoU, which is better than other state-of-the-art algorithms. The results show that the algorithm achieves more refined semantic segmentation of indoor scene images, and has good generalization and robustness. [ABSTRACT FROM AUTHOR]

Emerging network architectures and technical service requirements for B5G and 6G will enable MEC with CF-mMIMO, helping to handle compute-intensive and latency-sensitive tasks in distributed IoT. For CF-mMIMO-assisted MEC systems, this paper aimed to minimize the delay in completing computational tasks of different task types under energy constraint. In order to solve the above goals, this paper designed a task offloading strategy based on UEs, multiple APs and CPU (central processing unit) for cloud-edge-end collaboration. Specifically, according to the different data types of each UE and AP service, this paper firstly used the convex optimization and graph matching methods to alternately iterate to optimize the offload association and task ratio. Then, under the limitation of the backhaul link, this paper used an improved binary whale optimization algorithm to further offload the tasks of unallocated terminals and associated access points to the cloud with efficient processing. Compared with other meta-heuristics such as ant colony optimization algorithm and hybrid gray wolf optimization algorithm, the proposed algorithm has better performance on discrete offload optimization problems, which can provide a good offload optimization strategy for distributed systems and greatly reduce the average delay of the whole network. [ABSTRACT FROM AUTHOR]

To address the issues of low efficiency and frequent security vulnerabilities in smart contract development, this paper proposed a smart contract auto-generation method based on code comment optimization. Firstly, it constructed a smart contract clustering analysis model based on the semantic information of smart contract code associated annotations to achieve fast and accurate clustering of functions similar to smart contracts. Then, it divided the smart contract knowledge base into different levels such as the contract layer, function layer, and interface layer associated with the annotation. And based on the clustered code and annotation information, it constructed a diversified Prompt feature prompt statement dataset. Finally, it achieved automatic generation of smart contracts with specific needs based on the large language model ChatGLM2-6B and with the help of P-Tuning v2 fine-tuning technology. In order to test the effectiveness of this method, this paper conducted comparative experiments with existing methods using the bilingual translation quality assessment assistant tool BLEU and the code security detection tools Mythril and VaaS. Experimental results show that the average BLEU of the code generated by this method is increased by about 13%, and the code security is improved by about 6%. This method integrates code annotation information into the automatic generation of smart contracts, effectively improves the quality of smart contracts, and provides a new method for the efficient development of safe and reliable smart contracts. [ABSTRACT FROM AUTHOR]

Currently, researchers are focusing on efficient applications and resource scheduling strategies in vehicular edge computing (VEC) environments, however, the real-world validation of these applications and strategies is often limited by cost and time and cannot be performed quickly and efficiently. The emergence of edge/fog computing simulators such as iFogSim2 reduces the cost of experiments. However, the connection switching and resource allocation requirements of high-speed moving vehicles pose challenges to the application of edge/fog computing simulators under VEC. Therefore, this paper improved iFogSim2 by designing VECSim, a VEC environment simulator that supported high-speed mobility. It integrated open-source base station data and constructed vehicle trajectory datasets so that researchers can focus on resource allocation strategies. Firstly, to simplify the experimental steps, this paper improved the mobile trajectory data parsing module and adapted the vehicle trajectory data generated by Simulation of Urban Mobility (SUMO), a microscopic transportation simulation software. Secondly, this paper modeled distributed applications under VEC based on the distributed data flow model and provided a service migration benchmark policy algorithm. In addition, VECSim introduced a time-performance optimization method to accelerate the simulation event processing by parallelizing the operation, which improved the time performance of the simulation tool. Experiments show that compared with similar service migration algorithms in iFogSim2, the proposed service migration algorithm exhibits good stability under the validation of large-scale motor vehicle trajectory dataset, and the time-performance optimization method achieves a 5.3% performance improvement in execution time. [ABSTRACT FROM AUTHOR]

In order to further optimize the overlapping community detection algorithm, this paper proposed a new definition of node importance based on degree and node clustering coefficient, and the nodes were updated in descending order of node importance, and the node update strategy was fixed to improve the stability of community detection. On this basis, this paper proposed an OCD-GEMPA. The algorithm combined the node2vec model to represent the nodes in a low-dimensional vector, constructed a matrix of weight values between nodes, calculated the label attribution coefficient according to the weight values, and selected labels accordingly, avoiding the problem of random selection. Experimental verification of the algorithm on real data sets and synthetic data sets shows that compared to other overlapping community detection algorithms, the OCD-GEMPA algorithm has significant improvements in both EQ and NMI indicators, with better accuracy and stability. [ABSTRACT FROM AUTHOR]

Knowledge tracing aims to model the state of knowledge and ultimately predict the future performance of learners by describing exercises through the representation of concepts. However, in terms of the representation of concepts, the current research doesn’t model the influence of historical knowledge concepts on the temporal relationship of the current concepts, nor does it describe the role of the spatial relationship between various concepts in the exercise. In order to solve these problems, this paper proposed a knowledge tracing model characterized by temporal and spatial correlation fusion. First of all, based on the degree of temporal correlation between concepts, it modelled the temporal effect of historical concepts from current concepts. Secondly, it modelled the spatial interaction between several concepts contained in the exercise to obtain the representation of knowledge points containing temporal and spatial information through the graph attention network. Finally, it used the above representation of concepts to derive the representation of the exercises, and generated the current state of knowledge through the self-attention mechanism. In the experimental stage, this paper compared the performance of the proposed model with the five relevant knowledge tracing models on four real datasets. The results show that the proposed model has better performance. In particular, compared to the five comparative models on the ASSISTments2017 dataset, the AUC and ACC are improved by 1.7%～7.7% and 7.3%～12.1%, respectively. At the same time, the ablation experiment proves the effectiveness of modeling the temporal and spatial correlation between concepts, and the training process experiment shows that the proposed model has certain advantages in the representation of concepts and the modeling of their interaction relationships. The application examples can also show that the model has better practical results than other knowledge tracing models. [ABSTRACT FROM AUTHOR]

Spatial co-location pattern mining aims to discover the association between spatial features and has been an important research direction in spatial data mining. Spatial co-location pattern mining method based on column calculation (CPM-Col algorithm) avoids the most time-consuming operation of generating table instances and directly searches for participating instances. This method has become one of the most efficient approaches. However, backtracking search for participating instances remains a bottleneck, especially in dense datasets and long pattern mining. To accelerate the search for participating instances, this paper proposed two improvements to the CPM-Col algorithm with less extra computations. Firstly, the row instances found by CPM-Col algorithm were stored as partial table instances, for avoiding backtracking calculations of many instances. Secondly, after successfully finding a row instance, some instances of the first feature were obtained by the sub-clique reaction of the row instance. Based on these improvements, this paper proposed a co-location pattern mining method based on improved column calculation (CPM-iCol algorithm) and discussed complexity, correctness, and completeness. Experiments were conducted on synthetic and real datasets. Comparing to a classical algorithm join-less and CPM-Col, the CPM-iCol algorithm significantly reduces mining time and backtracking times. The results show that the proposed algorithm has better performance and scalability than CPM-Col algorithm, especially in dense datasets. [ABSTRACT FROM AUTHOR]

In order to solve the problem that it is difficult for the model to perceive implicit information due to the lack of external knowledge in rumor detection, which limits the ability of the model to mine deep information, this paper proposed knowledge graph based multi-feature fusion rumor detection (KGMRD) method. Firstly, for each event, it constructed posts and comments together into a text sequence and used a classifier to extract the emotional features. This paper constructed a knowledge graph based on text using ConceptNet and aggregated the entity representation in the knowledge graph with the semantic features of text using the attention mechanism, so as to obtain the enhanced semantic feature representation. Secondly, in terms of communication structure, for each event, this paper built its communication structure diagram based on the propagation and forwarding relationship of the post, and used DropEdge to prune the communication structure diagram, so as to obtain more effective communication structure characteristics. Finally, it fused the obtained features to get a new representation and compared seven models including SVM-RBF on three real datasets of Weibo, Twitter15 and Twitter16. The experimental results show that compared with the current baseline with the best effect, the KGMRD method has the best ACC on the Weibo dataset and improves the ACC by 1.1%, and there is a 2.2% improvement on Twitter15 and Twitter16 dataset in ACC. The experiment proves that the KGMRD method is reasonable and effective. [ABSTRACT FROM AUTHOR]

Floating car GPS data serves as the foundation for processing traffic information, with the rapid increase in the number of monitored vehicles, a massive amount of GPS data is generated, posing great challenges to map matching. To address the shortcomings of traditional matching methods in terms of matching efficiency and accuracy, this paper proposed a real time parallel map matching algorithm for massive GPS data that ensured both high matching accuracy and computational efficiency. This paper firstly reconstructed an efficient and accurate real-time map matching algorithm for streaming data by introducing a comprehensive weight factor that considered velocity and direction to enhance the offline map matching algorithm that relied on historical trajectories. Then, it introduced the Spark Streaming distributed computing framework to achieve real-time and parallel computation of the map matching algorithm, significantly improving the efficiency of real-time map matching. Experimental results demonstrate that the proposed algorithm achieves more than a 10% increase in matching accuracy compared to conventional topological matching algorithms on complex road sections, with an overall matching accuracy of over 95%. In terms of matching efficiency, it achieves approximately a fourfold improvement compared to an equivalent number of standalone servers. The experimental results show that the proposed algorithm achieves real-time map matching of 80 million GPS data points on a computing cluster composed of 11 machines, proving that the proposed algorithm can achieve real-time vehicle matching in urban areas. [ABSTRACT FROM AUTHOR]

Blockchain technology has great potentiality in the secure sharing of electronic health records. However, current solutions face issues such as large storage space and low consensus efficiency. This paper proposed a novel scheme based on blockchain and friend and relative nodes. Firstly, this paper adopted a distributed file system to store users’ complete electronic health records on offline servers, and constructed a set of user’s friend and relative nodes. Each user’s data was stored redundantly by its friend and relative nodes, and only the block’s header information was stored on the chain, reducing storage space. Then, this paper designed a data access mechanism based on multi-signature technology, using Shamir secret sharing mechanism to distribute user’s private keys to their relatives and friends. More than half of the relatives and friends could use their own private keys to reconstruct users’ private keys, solving data access problems in emergency situations. Finally, this paper proposed a credit based Byzantine fault-tolerant consensus mechanism, which used the top 10% nodes with credit values as the leader node set and utilized a random algorithm to generate the master node in the leader node set. And it improved consensus security. The experimental results show that compared with existing methods, the proposed scheme reduces the on-chain storage space by 1/7, improves data access efficiency by 15 times, and has higher consensus security while ensuring good latency and throughput. The proposed scheme can achieve secure and efficient sharing of electronic health records, providing a case for the application of blockchain in the medical field. [ABSTRACT FROM AUTHOR]

This paper investigated the issue of covert network attacks on video surveillance systems in light of their networking and intelligent development, which brought about new risks. The primary objective of this research was to explore numerous cases of covert network attacks and summarize the specific characteristics of such attacks targeting video surveillance systems. Additionally, this paper examined the unique advantages of honeypot technology in detecting network attack behaviors and identifying attack clues, and outlined the honeypot defense methods against covert attacks on video surveillance systems. Furthermore, considering the shortcomings in the visual scene deployment of video surveillance honeypots, this paper introduced a deep scene fabrication defense framework that combined generative Al models with video surveillance honeypots. Finally, it proposed the development direction of honeypot defense technology for video surveillance systems. [ABSTRACT FROM AUTHOR]

The wide application of deep learning techniques has strongly promoted the development of the medical image analysis field. Most deep learning methods usually assume that the training and test sets are independent and identically distributed. However, the assumption is problematic to guarantee when the model. Resulting in the dilemma of model performance degradation and poor scene generalization ability. Deep learning-based domain adaptation techniques are the mainstream methods for improving model migration ability, which aims to enable the model trained on one dataset to obtain better results on another dataset with no or only a small amount of labels. Due to the difficulties in sample acquisition and labelling, unique image properties and modal differences in medical images, it brings many practical challenges to domain adaptive technology. This paper firstly introduced the definition and primary challenges of the domain adaptation and then classified and summarized related algorithms in recent years from a technical point of view, compared and analyzed their advantages and disadvantages, and then introduced the medical image datasets commonly used in domain adaptation and related algorithm results in detail. Finally, this paper prospected the future research direction of domain adaptation for medical image analysis regarding development bottlenecks, technical means, and cross-cutting areas. [ABSTRACT FROM AUTHOR]

In the field of deep learning, solving problems often requires combining multiple modal information for reasoning and decision-making, among which visual and language information are two important modalities in the interaction process. In many application scenarios, processing multi-modal tasks often faces problems such as complex model architecture organization and inefficient training methods. Based on the above problems, this paper reviewed the representative achievements in the field of multimodal image text in the past five years. This paper first started from the mainstream multi-modal tasks and introduced related text and image multi-modal datasets and pre-training targets. Secondly, considering the visual language model based on Transformer and the feature extraction method, this paper analyzed from the perspectives of multi-modal organization architecture and cross-modal fusion methods, and summarized and compared the commonalities and differences of different processing strategies. Then it introduced the lightweight method of the model from data input, structural components and other aspects. Finally, it prospected the future research direction of multimodal methods based on image text. [ABSTRACT FROM AUTHOR]

Data classification and grading is the foundation for ensuring the safe circulation of data and promoting the release of data value. This paper focuses on the key task of government data classification and grading in digital reform. Using a theoretical case study method and based on publicly released plans by various provincial governments and ministries, the implementation of government data classification and grading in China is systematically sorted and quantitatively analyzed. This paper summarizes four key processes and five characteristics of the implementation of government data classification and classification in China. Based on the special complexity of the classification and grading of government data, this paper puts forward four problems corresponding solutions in the implementation of the classification and grading of government data in China, such as unclear overall target positioning, different classification and grading objects, separated classification and grading relations, and different security grading standards. Based on the practice of classification and grading government data of a national ministry, this paper verifies the scientificity and effectiveness of the solutions, and provides a reference for constructing a unified national government data classification and grading system. [ABSTRACT FROM AUTHOR]

Building a high-quality big data resource platform for the government is an important basic project to realize the integration of government information across departments, regions and levels, accelerate the construction of digital government and improve the digital intelligence level of public services and social governance. Firstly, this paper reviews the development of China's E-government and summarizes the three construction mode and main problems of traditional big data platforms, i.e., low data freshness, poor data consistency, difficult business collaborative management, weak basic support and high overall investment. Secondly, this paper conducts a case study on the credit information resource management platform in Jiangsu and explains the reasons for using Jiangsu case as an example. This paper proposes corresponding solutions and overall architecture design for the problems existing in traditional construction models as well as four reference value of Jiangsu case. Finally, based on summarizing the research and practical experience in Jiangsu, five suggestions are summarized to provide a reference for various provinces to study and formulate policy documents, such as provincial government big data platform construction guidelines. [ABSTRACT FROM AUTHOR]

News recommendation system plays an important role in news dissemination of new media. This paper proposed a recommendation system based on deep reinforcement learning, which aimed to combine the representation ability of neural network and the strategy selection ability of reinforcement learning to improve the effect of news recommendation. This paper used dynamic action masks to enhance the ability of judging the short-term interests of users, used the optimization cache mechanism to improve the efficiency of experience cache use, and accelerated model training through the reward design of regional masking nature to improve the performance of the recommendation system in the field of news recommendation. Experimental results show that the accuracy of the proposed model in news data sets is comparable to the current mainstream neural network recommendation methods, and its ranking performance is better than others. [ABSTRACT FROM AUTHOR]

At present, the pollution of nitrogen and phosphorus in rural domestic sewage and farmland drainage has not been effectively controlled. The development of“ecological purification technology”, a representative measure to solve such pollution, has attracted wide attention. This paper analyzes the ecological purification technology of nitrogen and phosphorus pollution in rural domestic sewage and farmland drainage from three perspectives of technology development, technical standards and technical system. The development of technology starts with the analysis and introduction of the current research progress of popular ecological purification technologies. Through the investigation and collation of the promotion and application of these technologies in China, the development characteristics of these technologies in different regions of China are sorted out, and the difficulties faced by the application of current ecological purification technologies are summarized. At present, the relevant departments only pay attention to the compliance rate of effluent quality in the supervision of ecological purification projects, and lack effective post-maintenance and opinion survey feedback. In terms of technical standards, this paper sorts out a series of standards on ecological purification projects that have been issued and implemented, and believes that comprehensive benefit evaluation methods should be introduced to improve the evaluation system of ecological purification projects in China. In terms of technical system, the single technology is classified according to the interception and repairability of ecological purification technology, and the corresponding technical combination system is summarized for rural domestic sewage and farmland drainage. [ABSTRACT FROM AUTHOR]

Objectives: Individual driving destination prediction has important value in location-based services such as personalized services recommendation and intelligent transportation. However, most of the existing deep learning methods construct travel features on the basis of densely-sampled trajectory points, which generate data redundancy but only achieve limited information gain, and in turn introduce negative impacts on model training. Road intersection sequence can simplify the expression of driving trajectories restricted on the roads, and reduce the model training cost. Meanwhile, transfer preference between intersections and current movement mode imply the spatiotemporal correlation between road intersections and destinations, and are capable to represent individual travel intention to some extent, but few researches have applied them to destination prediction. Methods: This paper proposes a novel individual driving destination prediction method that takes intersection transfer preference (ITP) and current movement mode (CMM) into account, named ITPCMM. First, it constructs input features in units of each intersection, and adopts graph attention network to learn the individual-level transfer coefficients between intersections in different time slots. Then, it uses long short-term memory (LSTM) to capture the long-term dependence of transfer preferences. Second, ITP-CMM constructs time cyclic encoding features and driving features to learn current move mode by using two-layered LSTM. Third, intersection transfer preferences and current move mode are fused and weighted through feature intersection and attention mechanisms respectively. And the stacked residual networks are introduced to output prediction results. Results and Conclusions: Based on the trajectory data of twelve private car drivers in Shenzhen City, China for the whole year of 2019, this paper has conducted a group of experiments to verify the feasibility of the proposed method ITP-CMM. We verify the effectiveness of the proposed method by carrying out ablation experiments and comparing the prediction accuracy and stability of ITP-CMM with four baselines, including hidden Markov model, LSTM, distance neighboring dependencies model and attentionaware LSTM for real-time driving destination prediction by considering location semantics and location importance trajectory points. Besides, we demonstrate the value of transfer preference in capturing the spatial correlation between intersections through visual analytics, and explore the impact of the number of transfer intersections on the prediction accuracy. [ABSTRACT FROM AUTHOR]