Search

This paper is concerned with two generalized inverse eigenvalue problems for a kind of pseudo‐Jacobi matrix. From a non‐Hermite matrix, an r × r Jacobi matrix, two distinct real eigenvalues, and part of the corresponding eigenvectors, an n × n pseudo‐Jacobi matrix is constructed. Furthermore, an n × n pseudo‐Jacobi matrix can be made by two different eigenpairs and a positive definite diagonal matrix. It is shown that a unique pseudo‐Jacobi matrix can be recovered from partial eigenpairs and certain special mixed eigendata. Two algorithms are provided for the reconstruction of such a pseudo‐Jacobi matrix, and illustrative numerical examples are presented to verify the proposed algorithms. [ABSTRACT FROM AUTHOR]

This paper extends our previous method for COVID-19 diagnosis, proposing an enhanced solution for detecting COVID-19 from computed tomography (CT) images using a lean transfer learning-based model. To decrease model misclassifications, two key steps of image processing were employed. Firstly, the uppermost and lowermost slices were removed, preserving sixty percent of each patient's slices. Secondly, all slices underwent manual cropping to emphasize the lung areas. Subsequently, resized CT scans (224 × 224) were input into an Xception transfer learning model with a modified output. Both Xception's architecture and pretrained weights were leveraged in the method. A big and rigorously annotated database of CT images was used to verify the method. The number of patients/subjects in the dataset is more than 5000, and the number and shape of the slices in each CT scan varies greatly. Verification was made both on the validation partition and on the test partition of unseen images. Results on the COV19-CT database showcased not only improvement from our previous solution and the baseline but also comparable performance to the highest-achieving methods on the same dataset. Further validation studies could explore the scalability and adaptability of the developed methodologies across diverse healthcare settings and patient populations. Additionally, investigating the integration of advanced image processing techniques, such as automated region of interest detection and segmentation algorithms, could enhance the efficiency and accuracy of COVID-19 diagnosis. [ABSTRACT FROM AUTHOR]

In this paper, we develop the theoretical provisions of symmetric cryptographic algorithms based on the polynomial residue number system for the first time. The main feature of the proposed approach is that when reconstructing the polynomial based on the method of undetermined coefficients, multiplication is performed not on the found base numbers but on arbitrarily selected polynomials. The latter, together with pairwise coprime residues of the residue class system, serve as the keys of the cryptographic algorithm. Schemes and examples of the implementation of the developed polynomial symmetric encryption algorithm are presented. The analytical expressions of the cryptographic strength estimation are constructed, and their graphical dependence on the number of modules and polynomial powers is presented. Our studies show that the cryptanalysis of the proposed algorithm requires combinatorial complexity, which leads to an NP-complete problem. [ABSTRACT FROM AUTHOR]

Despite the extensive research on developing robust image inpainting algorithms in recent years, there are almost no objective metrics for the quality assessment of inpainted images currently. Inspired by the feature coherence in the inpainted image and the human visual perception mechanism, this paper proposes an image inpainting quality assessment (IIQA) that takes into account both visual saliency and structural features. First, the quality issues associated with image inpainting are categorized into three aspects: incoherent structure, unreasonable texture, and other results that are inconsistent with human visual perception. These quality problems are further expressed as "regions of interest" and extracted by the visual saliency method using the natural statistics model. Subsequently, the structural features are computed based on the nonlinear diffusion of the horizontal and vertical gradient field of the inpainted image. Finally, the IIQA metric incorporates brightness, gradient similarity, structural similarity, and visual saliency is established. The quality evaluation process is conducted by comparing each patch within the inpainted region with its best match from the known region. The quantitative experimental results demonstrate the effectiveness of the proposed method, especially for images with structural discontinuity. A comparative study also shows that the Spearman rank order correlation coefficient of our method achieves 0.875 on certain databases, which outperforms existing IIQA metrics. [ABSTRACT FROM AUTHOR]

In this paper, a novel UAV path planning algorithm based on improved cellular ant colony algorithm and dynamic window algorithm (ICACO-IDWA) is proposed to solve the problem of dynamically changing threat during actual flight. The main innovations of this paper are as follows. (a) The hexagon grid method is proposed to model the UAV flight space, which solves the problem of inconsistent simulation time step. (b) A novel ICACO-IDWA algorithm is proposed. In the first stage, the optimal path is obtained by the improved cellular ant colony algorithm (ICACO). In the second stage, the improved dynamic window algorithm (IDWA) is used to optimize the optimal path considering dynamic threat. Through the algorithm, the UAV path planning with dynamic threat change is realized. Finally, simulation results verify the effectiveness of the proposed model and algorithm. [ABSTRACT FROM AUTHOR]

The identification of disruptive technologies is intended to focus on training and incubation in advance and is an important means to accelerate the upgrading of industrial structure and the transformation of developmental mode and seize the commanding heights of future development. Based on summarizing the existing major identification methods of disruptive technologies, this paper concludes the rule that "disruptive technologies are always at the root node of a certain classification in the deeply classified technology development network". It also proposes a new algorithm to use term frequency-inverse document frequency technology and a patented Subject-Action-Object structure to extract technical features, develop networks based on similarity matrix generation technology, and identify subversive technologies based on the depth classification model. Using patent data, it is found that the technology development network generated by the algorithm proposed in this paper can effectively show the trajectory of technology development by fitting the patent citation relationship. Through this algorithm, we have successfully identified technologies that have had disruptive effects in the field and verified the effectiveness of this algorithm. [ABSTRACT FROM AUTHOR]

Due to its large network scale, open communication environment, unstable wireless network, and other characteristics, it is extremely vulnerable to attacks and causes security problems, resulting in the collapse of the Internet of Vehicles system. The application of the Internet of Vehicles is becoming more and more extensive, but there are still problems such as information security and privacy leakage in the Internet of Vehicles. Through the analysis of the security threats and privacy protection requirements faced by the Internet of Vehicles system, this paper mainly studies information security, vehicle identity privacy, and location privacy in the process of Internet of Vehicles wireless communication. Therefore, it is urgent to conduct research on the information security and privacy protection issues of the Internet of Vehicles. This paper discusses the research on the security and privacy protection of the consensus algorithm for the Internet of Vehicles based on wireless sensors, compares and analyzes the wireless sensor data privacy protection protocols based on sharding technology, Tongtai encryption technology, and perturbation technology, and selects an optimized Kalman consensus filter. The algorithm is applied to the node information exchange of the sensor network, and two filters (low pass and band pass) are used to unify the observations and covariance of the network. Estimation of the sensor network state with and without data packet loss, the effect of system estimation error under different packet loss rates, data privacy protection algorithm performance, vehicle network data communication volume, and confusion factors on algorithm efficiency and the node energy consumption was compared and analyzed. Based on the application of wireless sensors, the estimation error and inconsistency estimation error of the algorithm in this paper finally converge to about 0.5, and both can maintain good stability and have good robustness. In addition, the communication volume of the algorithm in this paper is about 30% of the SCPDA algorithm. The Kalman consensus filtering algorithm reduces the amount of confusing data sent, improves privacy protection, and also achieves lower communication overhead. [ABSTRACT FROM AUTHOR]

To address the problems of less semantic information and low measurement accuracy when the SSD (single shot multibox detector) algorithm detects small targets, an MPH-SSD (multiscale pyramid hybrid SSD) algorithm that integrates the attention mechanism and multiscale double pyramid feature enhancement is proposed in this paper. In this algorithm, firstly, the SSD algorithm is used to extract the feature map of small targets, and the shallow feature enhancement module is added to expand the receptive field of the shallow feature layer so as to enrich the semantic information in the feature layer for small targets and improve the expression ability of shallow features. The processed shallow feature layer and deep feature layer are fused at multiple scales, and the semantic information and location information are fused together to obtain a feature map with rich information. Secondly, the cascaded double pyramid structure is used to transfer from the deep layer to the shallow layer so that the context information between different feature layers can be effectively transferred and the feature information can be further strengthened. The hybrid attention mechanism can retain more context information in the network, adaptively adjust the feature map after addition and fusion, and reduce the background interference. The experimental analysis of MPH-SSD algorithm on Pascal VOC and MS COCO datasets shows that the map of this algorithm is 87.7% and 51.1%, respectively. The results show that the MPH-SSD algorithm can make better use of the feature information in the shallow feature layer in the process of small target detection and has better detection performance for small targets. [ABSTRACT FROM AUTHOR]

High-resolution logging images with glaring detail information are useful for analysing geological features in the field of ultrasonic logging. The resolution of logging images is, however, severely constrained by the complexity of the borehole and the frequency restriction of the ultrasonic transducer. In order to improve the image superresolution reconstruction algorithm, this paper proposes a type of ultrasonic logging based on high-frequency characteristics, with multiscale dilated convolution to feature as the basis of network-learning blocks, training in the fusion of different scale texture feature. The outcomes of other superresolution reconstruction algorithms are then compared to the outcomes of the two-, four-, and eightfold reconstruction. The proposed algorithm enhances subjective vision while also enhancing PSNR and SSIM evaluation indexes, according to a large number of experiments. [ABSTRACT FROM AUTHOR]

With the development of artificial intelligence technology and information technology, the posture of volleyball training is becoming increasingly strict. By analyzing the dynamic training posture monitoring algorithm, the posture information of the human body can be directly obtained, which enables more efficient management of volleyball sports training. This paper aims to study how to monitor volleyball training posture and give suggestions based on machine learning in the context of artificial intelligence. The traditional method of manually detecting volleyball training postures is too subjective and cannot be used to judge the movements. Therefore, this paper proposes an algorithm for human posture monitoring and studies human posture recognition. Human gesture recognition has been widely used in many fields. The experimental results in this paper show that the corrected serve deviation rate of five volleyball players is 13.1% at the highest and 11.3% at the lowest after the traditional manual visual monitoring. The highest error is 0.70 m and the lowest is 0.63 m. The overall error is high. The corrected service deviation rate of the machine learning-based attitude monitoring algorithm is 3.5% at the highest and 2.7% at the lowest. The highest error is 0.24 m and the lowest is 0.19 m. The overall error is much lower than the former. This also shows that the posture monitoring algorithm based on machine learning can effectively detect the movement of volleyball players. This enables athletes to correct their mistakes in a timely manner, improve training efficiency, and improve their own strength. [ABSTRACT FROM AUTHOR]

The incidence of liver cancer is increasing year by year, and how to effectively diagnose early-stage liver cancer and improve the survival rate of liver cancer patients has become one of the current research topics of concern. Aiming at this problem, it is of great significance for the diagnosis of early liver cancer. With the in-depth research on the diagnosis of early-stage liver cancer, the research on growth differentiation factor 15 is gradually carried out, and its performance advantages are of great significance to solve the problem of detection and diagnosis of early-stage liver cancer. This study can improve the accuracy of early diagnosis of liver cancer. The purpose of this paper is to study the application of data mining in the study of clinical value of growth and differentiation factor 15 detection and diagnosis of early liver cancer. In this paper, the data mining algorithm is analyzed, the performance of the algorithm is experimentally analyzed, and the relevant theoretical formulas are used to explain. The results showed that the expression level of GDF-15 was significant in early primary liver cancer (tumor diameter <2.5 cm). Different from normal liver tissue (P < 0.01), there was a significant difference (P < 0.01) compared with adjacent tissue (P < 0.01). Serum GDF-15 can be used as a tumor marker for predicting early stage liver cancer. The high expression of GDF-15 in early stage liver cancer is an independent risk factor affecting the prognosis of liver cancer patients. [ABSTRACT FROM AUTHOR]

Improved SVM algorithm improves the efficiency of College English teaching effect evaluation and meets the requirements of College English teaching evaluation. Based on the relevant theories, this paper constructs the evaluation index system with teachers and students as the main body and takes the questionnaire survey results as the input samples of the LSSVM algorithm. Compared with the evaluation accuracy of an optimized BP neural network and the category weighted gray target decision-making method, the results show that the evaluation accuracy of optimized LSSVM algorithm is 96.26%. Taking SIT as an example, this paper uses the optimized LSSVM algorithm to evaluate its teaching effect and obtains that teachers' literature and teaching contents are important factors to improve the effect of English teaching. Therefore, this paper introduces the intelligent voice system to optimize the English teaching design of SIT. The teaching design is optimized from the dimensions of teaching objectives, learning situation, teaching content, teaching media and curriculum materials, and teaching procedures. [ABSTRACT FROM AUTHOR]

This paper studies the processing of digital media images using a diffusion equation to increase the contrast of the image by stretching or extending the distribution of luminance data of the image to obtain clearer information of digital media images. In this paper, the image enhancement algorithm of nonlinear diffusion filtering is used to add a velocity term to the diffusion function using a coupled denoising model, which makes the diffusion of the original model smooth, and the interferogram is solved numerically with the help of numerical simulation to verify the denoising processing effect before and after the model correction. To meet the real-time applications in the field of video surveillance, this paper focuses on the optimization of the algorithm program, including software pipeline optimization, operation unit balancing, single instruction multiple data optimization, arithmetic operation optimization, and onchip storage optimization. These optimizations enable the nonlinear diffusion filter-based image enhancement algorithm to achieve high processing efficiency on the C674xDSP, with a processing speed of 25 posts per second for 640 × 480 size video images. Finally, the significance means a value of super pixel blocks is calculated in superpixel units, and the image is segmented into objects and backgrounds by combining with the Otsu threshold segmentation algorithm to mention the image. In this paper, the proposed algorithm experiments with several sets of Kor Kor resolution remote sensing images, respectively, and the Markov random field model and fully convolutional network (FCN) algorithm are used as the comparison algorithm. By comparing the experimental results qualitatively and quantitatively, it is shown that the algorithm in this paper has an obvious practical effect on contrast enhancement of digital media images and has certain practicality and superiority. [ABSTRACT FROM AUTHOR]

The pedestrian detection model has a high requirement on the quality of the dataset. Concerning this problem, this paper uses data cleaning technology to improve the quality of the dataset, so as to improve the performance of the pedestrian detection model. The dataset used in this paper is obtained from subway stations in Beijing and Nanjing. The data images' quality is subject to motion blur, uneven illumination, and other noisy factors. Therefore, data cleaning is very important for this paper. The data cleaning process in this paper is divided into two parts: detection and correction. First, the whole dataset goes through blur detection, and the severely blurred images are filtered as the difficult samples. Then, the image is sent to DeblurGAN for deblur processing. 2D gamma function adaptive illumination correction algorithm is used to correct the subway pedestrian image. Then, the processed data is sent to the pedestrian detection model. Under different data cleaning datasets, through the analysis of the detection results, it is proved that the data cleaning process significantly improves the detection model's performance. [ABSTRACT FROM AUTHOR]

This paper presents an in-depth study of face detection, face feature extraction, and face classification from three important components of a high-capacity face recognition system for the treatment area of hospital and a study of a high-capacity real-time face retrieval and recognition algorithm for the treatment area of hospital based on a task scheduling model. Considering the real-time nature of our system, our face feature extraction network is modeled by DeepID, and the network is slightly improved by introducing a central loss verification signal to train a DeepID-like network model using central loss and use it to extract face features. To further investigate and optimize the schedulability analysis problem of the directed graph real-time task model, this paper proposes a rigorous and approximate response time analysis method for the directed graph real-time task model with an arbitrary time frame. Based on the theoretical results of the greatly additive algebra, it is shown that the coherent qualifying function is linearly periodic, i.e., the function can be represented by a finite nonperiodic part and an infinitely repeated periodic part, thus calculating the coherent qualifying function independent of the magnitude of the interval time. The algorithm for high-capacity real-time face retrieval and recognition in the treatment area of hospital based on the task scheduling model is further investigated, and a face database is established by using the PCA dimensionality reduction technique. Based on the internal architecture of the processor, image preprocessing and IP core packaging are implemented, and the hardware engineering of the high-capacity real-time face recognition system for hospital visits is built using the IP-based design concept. The performance tests of the face detection model and feature extraction network show that the face detection model has a significant reduction in false-positive rate, better fitting of border regression, and improved time performance. The face feature extraction network has no overfitting, and the features are highly discriminative with small feature extraction time consumption. The high-capacity real-time face recognition system for the treatment area of hospital combined with the optimized directed graph task scheduling model can approach 25 fps, which meets the real-time requirements, and the face recognition rate surpasses that of real people. It realizes the intelligence, self-help, and autonomy of medical services and satisfies the medical needs of users in all aspects. [ABSTRACT FROM AUTHOR]

Musical choreography is usually completed by professional choreographers, which is very professional and time-consuming. In order to realize the intelligent choreography of musical, based on the mixed density network (MDN), this paper generates the dance matching with the target music through three steps: motion generation, motion screening, and feature matching. The choreography results in this paper have a high degree of matching with music, which makes it possible for the development of motion capture technology and artificial intelligence and computer automatic choreography based on music. In the process of motion generation, the average value of Gaussian model output by MDN is used as the bone position and the consistency of motion is measured according to the change rate of joint velocity in adjacent frames in the process of motion selection. Compared with the existing studies, the dance generated in this paper has improved in motion coherence and realism. In this paper, a multilevel music and action feature matching algorithm combining global feature matching and local feature matching is proposed. The algorithm improves the unity and coherence of music and action. The algorithm proposed in this paper improves the consistency and novelty of movement, the compatibility with music, and the controllability of dance characteristics. Therefore, the algorithm in this paper technically changes the way of artistic creation and provides the possibility for the development of motion capture technology and artificial intelligence. [ABSTRACT FROM AUTHOR]

The use of neural machine algorithms for English translation is a hot topic in the current research. English translation using the traditional sequential neural framework, which is too poor at capturing long-distance information, has its own major limitations. However, the current improved frameworks, such as recurrent neural network translation, are not satisfactory either. In this paper, we establish an attention coding and decoding model to address the shortcomings of traditional machine translation algorithms, combine the attention mechanism with a neural network framework, and implement the whole English translation system based on TensorFlow, thus improving the translation accuracy. The experimental test results show that the BLUE values of the algorithm model built in this paper are improved to different degrees compared with the traditional machine learning algorithms, which proves that the performance of the proposed algorithm model is significantly improved compared with the traditional model. [ABSTRACT FROM AUTHOR]

Web page classification is critical for information retrieval. Most web page classification methods have the following two faults: (1) need to analyze based on the overall web page and (2) do not pay enough attention to the existence of noise information inside the web page, which will thus decrease the efficiency and classification performance, especially when classifying the contaminated web page. To solve these problems, this paper proposes a denoising disposal algorithm. We choose the top-down method for hierarchical classification to improve the prediction efficiency. The experimental results demonstrate that our method is about 7 times faster than the full-page method and achieves good classification results in most categories. The precision of 7 parent categories is all above 88% and is 24% higher than the other meta tag-based method on average. [ABSTRACT FROM AUTHOR]

To study the classification and evolution of key technologies in the transportation field, the data of 36 authoritative SCI journals in the transportation field were collected from the Web of Science core collection database from 2001 to 2020. Based on the bibliometric method, this study used Python to process and visualize data, combined with bibliometric software VOSviewer to assist data visualization. Firstly, a preprocessing data algorithm was designed to deduplicate the collected data, merge synonyms, and extract key technologies. Then the paper records that contained the key technology lexicon were filtered out. Next, the annual number of publications and the distribution of key technologies over time were counted. The least squares method was used to fit the distribution of the annual proportion of the publications, and the slope k1 of the fitted linear regression equation was used to determine the research interest trend of key technologies. The key technologies were divided into "hot technology," "cold technology," and "other technologies," according to the research heat trend. In order to further explore the research hotspots, the least squares method was also used to fit the citations of all technologies to obtain the slope k2. We use the Gaussian mixture model (GMM) algorithm to cluster k1 and k2 of each technology. As a result, the 144 technologies were divided into 13 super-key technologies, 60 key technologies, 59 relative key technologies, and 12 lower-key technologies. Then, the evolution of key technologies was analyzed from two perspectives of weighted evolution and cumulative evolution. And the technology evolution trend in the transportation field in the past 20 years was explored. Finally, the cooccurrence clustering method was adopted to divide key transportation technologies into five categories: vehicle technology and control, optimization algorithms and simulation techniques, artificial intelligence and big data, Internet of Things and computing, and communication technology. The research results can provide references for different people in the transportation field, including but not limited to researchers, journal editors, and funding agencies. [ABSTRACT FROM AUTHOR]

This paper does some research and discussion on the finite element analysis of a building structure, especially the computer graphics simulation method in building structure simulation. Moreover, with the support of BIM technology and computer finite element simulation technology, this paper constructs a building structure simulation system and analyzes the building structure simulation system based on actual conditions such as building structure and stress load. In addition, this paper improves the traditional structural analysis algorithm and designs experiments to evaluate the effect of the method proposed in this paper and analyze the data in the form of simulation to compare the validity of the test results. Finally, an experiment is designed to evaluate the data processing capability of the test system in this paper. The experimental analysis results verify the effectiveness of the method in this paper, which can provide relevant theoretical references for subsequent building structure simulation. [ABSTRACT FROM AUTHOR]

Segmentation of pulmonary vessels in CT/CTA images can help physicians better determine the patient's condition and treatment. However, due to the complexity of CT images, existing methods have limitations in the segmentation of pulmonary vessels. In this paper, a method based on the separation of pulmonary vessels in CT/CTA images is investigated. The method is divided into two steps: in the first step, the lung parenchyma is extracted using the Unet++ algorithm, which can effectively reduce the oversegmentation rate; in the second step, the pulmonary vessels in the lung parenchyma are extracted using nnUnet. According to the obtained lung parenchyma segmentation results, the "AND" operation is performed on the original image and the lung parenchyma segmentation results, and only the blood vessels within the lung parenchyma are segmented, which reduces the interference of external tissues and improves the segmentation accuracy. The experimental data source used CT/CTA images acquired from the partner hospital. After the experiments were performed on a total of 67 sets of images, the accuracy of CT and CTA images reached 85.1% and 87.7%, respectively. The comparison of whether to segment the lung parenchyma and with other conventional methods was also performed, and the experimental results showed that the algorithm in this paper has high accuracy. [ABSTRACT FROM AUTHOR]

Faced with massive amounts of online news, it is often difficult for the public to quickly locate the news they are interested in. The personalized recommendation technology can dig out the user's interest points according to the user's behavior habits, thereby recommending the news that may be of interest to the user. In this paper, improvements are made to the data preprocessing stage and the nearest neighbor collection stage of the collaborative filtering algorithm. In the data preprocessing stage, the user-item rating matrix is filled to alleviate its sparsity. The label factor and time factor are introduced to make the constructed user preference model have a better expression effect. In the stage of finding the nearest neighbor set, the collaborative filtering algorithm is combined with the dichotomous K-means algorithm, the user cluster matching the target user is selected as the search range of the nearest neighbor set, and the similarity measurement formula is improved. In order to verify the effectiveness of the algorithm proposed in this paper, this paper selects a simulated data set to test the performance of the proposed algorithm in terms of the average absolute error of recommendation, recommendation accuracy, and recall rate and compares it with the user-based collaborative filtering recommendation algorithm. In the simulation data set, the algorithm in this paper is superior to the traditional algorithm in most users. The algorithm in this paper decomposes the sparse matrix to reduce the impact of data sparsity on the traditional recommendation algorithm, thereby improving the recommendation accuracy and recall rate of the recommendation algorithm and reducing the recommendation error. [ABSTRACT FROM AUTHOR]

In this paper, through the improved decision tree algorithm, the handles in multimedia English assistance are parsed and simulated. In order to better perceive the sense of language in English composition and improve the rationality of intelligent evaluation, an N element based on association analysis is proposed. Sense value quantification calculates its support in the corpus by obtaining N-tuples of the composition. If the degree of support is lower than the threshold, the part where the language sense problem occurs is analyzed, and the type of language sense problem is judged for the students to provide assistance in modifying the composition. In addition, this paper also extracts word features, sentence features, and text structure features in the composition to fit the English handles analytical score. By testing the test set, the experiment shows that, by extracting the language sense features of the candidate's English composition, it can not only judge whether there is a problem with the language sense of the candidate, but also provide a basis for the overall evaluation of the composition. [ABSTRACT FROM AUTHOR]

Context. The improvements made in the last couple of decades in the requirements engineering (RE) processes and methods have witnessed a rapid rise in effectively using diverse machine learning (ML) techniques to resolve several multifaceted RE issues. One such challenging issue is the effective identification and classification of the software requirements on Stack Overflow (SO) for building quality systems. The appropriateness of ML-based techniques to tackle this issue has revealed quite substantial results, much effective than those produced by the usual available natural language processing (NLP) techniques. Nonetheless, a complete, systematic, and detailed comprehension of these ML based techniques is considerably scarce. Objective. To identify or recognize and classify the kinds of ML algorithms used for software requirements identification primarily on SO. Method. This paper reports a systematic literature review (SLR) collecting empirical evidence published up to May 2020. Results. This SLR study found 2,484 published papers related to RE and SO. The data extraction process of the SLR showed that (1) Latent Dirichlet Allocation (LDA) topic modeling is among the widely used ML algorithm in the selected studies and (2) precision and recall are amongst the most commonly utilized evaluation methods for measuring the performance of these ML algorithms. Conclusion. Our SLR study revealed that while ML algorithms have phenomenal capabilities of identifying the software requirements on SO, they still are confronted with various open problems/issues that will eventually limit their practical applications and performances. Our SLR study calls for the need of close collaboration venture between the RE and ML communities/researchers to handle the open issues confronted in the development of some real world machine learning-based quality systems. [ABSTRACT FROM AUTHOR]

Human action recognition is an important part for computers to understand the behavior of people in pictures or videos. In a single image, there is no context information for recognition, so its accuracy still needs to be greatly improved. In this paper, a single-image human action recognition method based on improved ResNet and skeletal keypoints is proposed, and the accuracy is improved by several methods. We improved the backbone network ResNet-50 and CPN to a certain extent and constructed a multitask network to suit the human action recognition task, which not only improves the accuracy but also balances the total number of parameters and solves the problem of large network and slow operation. In this paper, the improvement methods of ResNet-50, CPN, and whole network are tested, respectively. The results show that the single-image human action recognition based on improved ResNet and skeletal keypoints can accurately identify human action in the case of different human movements, different background light, and occlusion. Compared with the original network and the main human action recognition algorithms, the accuracy of our method has its certain advantages. [ABSTRACT FROM AUTHOR]

This paper presents an indepth analysis and research on the quantitative design of fine art images through artificial intelligence algorithms. A CycleGAN-based network model for automatic generation of sketches of fine art images is constructed to extract the edge and contour features of fine art images. The network uses 512 × 1024 high-resolution art images as input and Pitchman as a discriminator. To further enhance the sketch generation effect, a bilateral filtering algorithm is added to the generator model for noise reduction, and then a K -means algorithm is used for color quantization to solve the problem of cluttered lines in the generated sketches. The experimental results show that the network model can effectively realize the automatic generation of art image sketches and can retain the detailed part of the costume information well. A rendering platform is built to realize the application of art image generation algorithms and coloring algorithms. The platform integrates the functions of image preprocessing, sketch generation, and sketch coloring, demonstrates the results of the main research content of this paper, and finally increases the interest of the system through the rendering function of the art image grid, which further improves the practicality of the platform. [ABSTRACT FROM AUTHOR]

With the development of computer science, especially the application of 3D scanning technology in garment design, intelligent modeling is realized, which is impossible to achieve in traditional design methods. In this paper, we propose the 3D model construction of human garments based on the motion recovery structure method. The eigenmatrix is obtained from the camera parameters, and the transformation matrix is calculated by matching the image feature points with the help of scale-invariant feature conversion algorithm to realize the 3D reconstruction technology of human garments based on multiview image sequences. The effectiveness of this method is verified through experiments, and it has good robustness and accuracy. Through the form of style modeling, the design thinking and method can be extended to form a more reasonable garment structure and guide the innovation of garment production mode. [ABSTRACT FROM AUTHOR]

This paper presents an in-depth study and analysis of X-ray inspection of basin insulators by wireless sensing technology. Aiming at the characteristics of low contrast and many kinds of noise in the basin insulator ray image, this paper proposes an X-ray basin insulator image denoising method based on improved 3D block matching. Using the RF microcontroller CC2530 chip as the core hardware and networked by ZigBee protocol, the sensor senses and collects various parameters and transmits this information to the monitoring end in real time through wireless. The method proposes an improved wavelet thresholding denoising method to overcome the pseudo-Gibbs phenomenon caused by the wavelet hard thresholding method in the 3D block matching algorithm cofiltering and retain more details of the image. Aiming at the ringing effect caused by the Wiener filtering method used in the three-dimensional block matching algorithm collaborative filtering, an improved Kalman filtering method based on anisotropic diffusion is proposed, which avoids the ringing effect, and has clear edges and complete details. An improved Kalman filtering method based on anisotropic diffusion is proposed to avoid the ringing effect, and the edges are clear, and the details are complete. The proposed method is a safe, efficient, accurate, and feasible method for detecting defects in basin insulators by combining X-ray and improved wireless image sensing technology to detect the internal equipment without disassembling or touching the GIS equipment. [ABSTRACT FROM AUTHOR]

In order to detect and correct node localization anomalies in wireless sensor networks, a hierarchical nonuniform clustering algorithm is proposed. This paper designs a centroid iterative maximum likelihood estimation location algorithm based on nonuniformity analysis, selects the nonuniformity analysis algorithm, gives the flowchart of node location algorithm, and simulates the distribution of nodes with MATLAB. Firstly, the algorithm divides the nodes in the network into different network levels according to the number of hops required to reach the sink node. According to the average residual energy of nodes in each layer, the sink node selects the nodes with higher residual energy in each layer of the network as candidate cluster heads and selects a certain number of nodes with lower residual energy as additional candidate cluster heads. Then, at each level, the candidate cluster heads are elected to produce the final cluster heads. Finally, by controlling the communication range between cluster head and cluster members, clusters of different sizes are formed, and clusters at the level closer to the sink node have a smaller scale. By simulating the improved centroid iterative algorithm, the values of the optimal iteration parameters α and η are obtained. Based on the analysis of the positioning errors of the improved centroid iterative algorithm and the maximum likelihood estimation algorithm, the value of the algorithm conversion factor is selected. Aiming at the problem of abnormal nodes that may occur in the process of ranging, a hybrid node location algorithm is further proposed. The algorithm uses the ℓ 2 , 1 norm to smooth the structured anomalies in the ranging information and realizes accurate positioning while detecting node anomalies. Experimental results show that the algorithm can accurately determine the uniformity of distribution, achieve good positioning effect in complex environment, and detect abnormal nodes well. In this paper, the hybrid node location algorithm is extended to the node location problem in large-scale scenes, and a good location effect is achieved. [ABSTRACT FROM AUTHOR]

With the rapid development of deep learning, computer vision has also become a rapidly developing field in the field of artificial intelligence. Combining the physical training of deep learning will bring good practical value. Physical training has different effects on people's body shape, physical function, and physical quality. It is mainly reflected in the changes of relevant physical indicators after physical training. Therefore, the purpose of this article is to study the method of evaluating the impact of sports training on physical indicators based on deep learning. This paper mainly uses the convolutional neural network in deep learning to design sports training, then constructs the evaluation system of physical index impact, and finally uses the deep learning algorithm to evaluate the impact of physical index. The experimental results show that the accuracy of the algorithm proposed in this paper is significantly higher than that of the other three algorithms. Firstly, in the angular motion, the accuracy of the mean algorithm is 0.4, the accuracy of the variance algorithm is 0.2, the accuracy of the RFE algorithm is 0.4, and the accuracy of the DLA algorithm is 0.6. Similarly, in foot racing and skill sports, the accuracy of the algorithm proposed in this paper is significantly higher than that of other algorithms. Therefore, the method proposed in this paper is more effective in the evaluation of the impact of physical training on physical indicators. [ABSTRACT FROM AUTHOR]

The signal corresponding to English speech contains a lot of redundant information and environmental interference information, which will produce a lot of distortion in the process of English speech translation signal recognition. Based on this, a large number of studies focus on encoding and processing English speech, so as to achieve high-precision speech recognition. The traditional wavelet denoising algorithm plays an obvious role in the recognition of English speech translation signals, which mainly depends on the excellent local time-frequency domain characteristics of the wavelet signal algorithm, but the traditional wavelet signal algorithm is still difficult to select the recognition threshold, and the recognition accuracy is easy to be affected. Based on this, this paper will improve the traditional wavelet denoising algorithm, abandon the single-threshold judgment of the original traditional algorithm, innovatively adopt the combination of soft threshold and hard threshold, further solve the distortion problem of the denoising algorithm in the process of English speech translation signal recognition, improve the signal-to-noise ratio of English speech recognition, and further reduce the root mean square error of the signal. Good noise reduction effect is realized, and the accuracy of speech recognition is improved. In the experiment, the algorithm is compared with the traditional algorithm based on MATLAB simulation software. The simulation results are consistent with the actual theoretical results. At the same time, the algorithm proposed in this paper has obvious advantages in the recognition accuracy of English speech translation signals, which reflects the superiority and practical value of the algorithm. [ABSTRACT FROM AUTHOR]

The saliency calculation model based on the principle of partial differential equations sometimes highlights areas with high contrast in the background, and the salient targets obtained occasionally have holes. The above problems can be solved by combining the improved convex hull calculation center saliency map. This paper designs a single-target color image segmentation algorithm based on partial differential equations. First, we calculate the basic saliency map according to the uniqueness of the color and the spatial distribution of the color; second, we then use the superpixel to improve the convex hull and calculate the central saliency map according to the principle; finally, the basic saliency map and the central saliency map are calculated. The weighted fusion is used to obtain the comprehensive saliency map, and the threshold method is used to segment the comprehensive saliency map to obtain the final target image. This paper designs an evaluation standard suitable for the segmentation of the illuminated highlight area of the effect image. It compares the experimental results of the segmentation method in this paper with the SLIC (Simple Linear Iterative Clustering) method and the traditional superpixel method to segment the illuminated highlight area. The segmentation method is applied to the image enhancement experiment. Based on the fuzzy means clustering algorithm, a fuzzy clustering objective function including brightness, color, and distance parameters is designed, which improves the weight of the brightness value in the clustering and improves the edge fit of the segmentation of the lighting highlight area of the rendering. The segmentation method produced by combining the clustering method with the superpixel biased clustering method can improve the output effect of the illuminated highlight area of the effect image after segmentation. We perform color equalization processing on the image to be segmented to reduce the impact of light, then set the closed value of the brightness information component, perform segmentation judgment, and expand the long and short axes of the ellipse model in the high-brightness area to further reduce the impact of light. The experimental results prove that the above method has a better segmentation effect than the traditional ellipse model and can accurately segment the gesture image. Compared with the existing mainstream saliency calculation models, this algorithm is closer to the true value image in terms of visual effects and has obvious advantages in terms of accuracy. [ABSTRACT FROM AUTHOR]

The advancement in technology is taking place with an accelerating pace across the globe. With the increasing expansion and technological advancement, a vast volume of text data are generated everyday, in the form of social media platform, websites, company data, healthcare data, and news. Indeed, it is a difficult task to extract intriguing patterns from the text data, such as opinions, summaries, and facts, having varying length. Because of the problems of the length of text data and the difficulty of feature value extraction in news, this paper proposes a news text classification method based on the combination of deep learning (DL) algorithms. In order to classify the text data, the earlier approaches use a single word vector to express text information and only the information of the relationship between words were considered, but the relationship between words and categories was ignored which indeed is an important factor for the classification of news text. This paper follows the idea of a customized algorithm which is the combination of DL algorithms such as CNN, LSTM, and MLP and proposes a customized DCLSTM-MLP model for the classification of news text data. The proposed model is expressed in parallel with word vector and word dispersion. The relationship among words is represented by the word vector as an input of the CNN module, and the relationship between words and categories is represented by a discrete vector as an input of the MLP module in order to realize comprehensive learning of spatial feature information, time-series feature information, and relationship between words and categories of news text. To check the stability and performance of the proposed method, multiple experiments were performed. The experimental results showed that the proposed method solves the problems of text length, difficulty of feature extraction in the news text, and classification of news text in an effective way and attained better accuracy, recall rate, and comprehensive value as compared to the other models. [ABSTRACT FROM AUTHOR]

Aiming at the optimal path and planning efficiency of global path planning for intelligent driving, this paper proposes a global dynamic path planning method based on improved A ∗ algorithm. First, this method improves the heuristic function of the traditional A ∗ algorithm to improve the efficiency of global path planning. Second, this method uses a path optimization strategy to make the global path smoother. Third, this method is combined with the dynamic window method to improve the real-time performance of the dynamic obstacle avoidance of the intelligent vehicle. Finally, the global dynamic path planning method of the proposed improved A ∗ algorithm is verified through simulation experiments and real vehicle tests. In the simulation analysis, compared with the modified A ∗ algorithm and the traditional A ∗ algorithm, the method in this paper shortens the path distance by 2.5%∼3.0%, increases the efficiency by 10.3%∼13.6% and generates a smoother path. In the actual vehicle test, the vehicle can avoid dynamic obstacles in real time. Therefore, the method proposed in this paper can be applied on the intelligent vehicle platform. The path planning efficiency is high, and the dynamic obstacle avoidance is good in real time. [ABSTRACT FROM AUTHOR]

In order to improve the effect of college English classroom teaching, this paper combines optical recognition to improve machine vision algorithms and uses computer optical vision technology to process teaching images. The system designed in this paper can be applied to philosophical teaching in college English classrooms. Moreover, the system can optimize teaching resources, manage teaching classrooms through the improved machine vision algorithm in this paper, and have a formative evaluation effect. In addition, taking into account the psychological activities of students in the classroom, this paper integrates the emotional recognition of college students in the construction of the system. Furthermore, it combines the actual teaching process to build a college English classroom teaching system based on constructivism. Finally, this paper designs an experiment to analyze the effect of the teaching model. From the research results, it can be known that the teaching system meets the demands of teaching. [ABSTRACT FROM AUTHOR]

Traditional Chinese medicine (TCM) is a summary of the diagnosis and treatment experience formed by the working people in the long-term struggle against diseases, so it is very important to protect the intangible cultural heritage of TCM. How to extract valuable knowledge accurately and conveniently from the massive medical records of TCM is one of the important issues in the current research on the development of TCM. Due to the large amount of data of TCM medical records, many feature attributes, and diverse patterns, the existing classification technology has high computational complexity, low mining efficiency, and poor universality. Therefore, this paper proposed to quantify the medical records of TCM and obtained the main symptoms according to the improved hierarchical clustering feature selection algorithm. This paper also proposed a support vector machine (SVM) classification method using improved particle swarm algorithm to classify TCM information, which not only improves the efficiency and accuracy of TCM information classification but also discovers the potential dialectical and symptom patterns in diagnosis and treatment, so that the intangible cultural heritage protection of TCM can be developed sustainably. This paper showed that the information acquisition accuracy of the improved algorithm was very high. Before the improved algorithm was used, the accuracy of information mining for TCM was 67.90% at the highest and 65.53% at the lowest, but after using the improved algorithm, the accuracy rate of information mining for TCM was 88.02% at the highest and 82.45% at the lowest. It can be seen that using the improved algorithm to mine TCM information can quickly process effective information. [ABSTRACT FROM AUTHOR]

The existing interpretation models for the time spectrum of impulse neutron oxygen activation require interpreters to select the peak range or background range manually from the time spectrum curve, and there is no adaptive interpretation model that can determine the peak range or background range. In this paper, an adaptive selection rule for background segment is proposed, and a semiautomatic interpretation model is constructed by combining background segment interpretation model. Firstly, the interpretation operator selects the time spectrum curve, then the algorithm program adaptively determines the background segment according to the rules, and then calculates and displays the transit time and volume flow according to the background segment interpretation model. The processing results of the measured data show that the interpretation model in this paper not only retains the interpretation precision of the background interpretation model, but also reduces the labor intensity of the interpretation operator, realizing the semiautomatic interpretation of the time spectrum. [ABSTRACT FROM AUTHOR]

The more frequent occurrence of network security incidents has an impact on network security. Through the research on network security situational awareness, this paper constructs a multilevel network security situation evaluation index system from various aspects and uses the Elman neural network optimized by the genetic algorithm to evaluate network security situation. Aiming at the disadvantage of subjective dependence in the traditional assignment method of basic probability assignment function, Elman neural network is used to obtain the basic probability assignment function to increase its objectivity, and it is optimized with the PSD algorithm. In addition, the neural network is further improved by the genetic algorithm. In the traditional D-S evidence theory, an evidence correction step is added to optimize the situation that the final judgment result is incorrect due to evidence conflict. Finally, the fusion rules of the D-S evidence theory are used to fuse the support degrees of the four first-level situations to different security levels to obtain the final network security situation assessment result. The results show that the prediction accuracy of the GA-Elman neural network model is as high as 80%, which is significantly higher than that of the traditional D-S model, indicating that the model proposed in this paper has improved the accuracy of the assessment and prediction results. In conclusion, this study provides feasible theoretical prediction guidance for the accurate assessment of network security posture, reveals the improvement ideas for network security development, and is of great significance for the maintenance of network environment security. [ABSTRACT FROM AUTHOR]

Exploring the improvement of classroom teaching effect under the background of sports education integration in China has important practical significance and theoretical value. Integration of yard sports education and classroom course education in the school is a novel concept put forward by China's sports and education circles to deepen the combination of sports and education. Although it is only a word different from the combination of sports and education to integrating sports and course education in the school, it is a groundbreaking theoretical and practical innovation for China in terms of changing the competitive sports development model and cultivating exceptional athletes. It is a new way to promote the sustainable development of sports and education according to the scientific outlook on development. Its fundamental significance is to change the closed state of sports and education departments, put sports and education in the background of economic and social development in a certain region, and fundamentally reform the content and mode of education. Therefore, this paper proposes a comprehensive rating model of classroom teaching effects based on deep learning (DL) and machine learning (ML) techniques. In this paper, the Jaffe expression dataset is used to train and test the utilized ML and DL models such as ResNet50, random forest (RF), logistic regression (LR), K-nearest neighbor (k-NN), and decision tree (DT). Further, with the help of artificial intelligence (AI) techniques, the algorithms can objectively evaluate the classroom teaching effect after the integration of physical education with classroom education and provide important guidance for the modernization and intellectualization of China's educational methods in the future. [ABSTRACT FROM AUTHOR]

Since there is a close relationship between network information security attack events and time complexity, it is necessary to count the degree of correlation between the current connection record and the connection record within a certain period of time before. Only in this way can the relationship between network connection data and network information security attack events be better reflected. In this paper, a rough Fourier fast algorithm based on rough set theory is proposed. Based on the characteristic attributes of the intrusion detection data set with the most value of character attributes as the data division basis, the computer network intrusion anomaly detection data set is intelligently divided into small data sets, so as to carry out attribute reduction. The network intrusion detection rule update experiment adopts the misuse detection method, extracts some samples from the KDD99 data set for training, obtains the computer network intrusion detection rules in the hierarchical decision table, and uses the incremental learning algorithm to update the rules, compared with the intrusion detection rules expressed by the decision table to test the feasibility and effectiveness of the rule update, and compared with the improved RSDB, RE-RFE algorithm, and KNN algorithm to evaluate the effect of the rough Fourier fast detection model applied to the problem of network intrusion anomaly detection. Using the attribute subset reduced by the rough Fourier algorithm to perform classification and modeling of computer network intrusion anomaly detection is significantly reduced, and the average time is reduced by 0.09 seconds, and this paper lays a good foundation for the application of network security intrusion detection algorithm. [ABSTRACT FROM AUTHOR]

In this paper, the existing scenic spot recommendation algorithms ignore the implicit trust and trust transmission of users when dealing with user relationships, and the lack of historical browsing behavior data of users in new city scenes leads to an inaccurate recommendation. In this paper, a personalized scenic spot recommendation method combining user trust relationship and tag preference is proposed. Firstly, the trust degree is introduced when the recommendation quality is poor only considering the similarity of users. By mining the implicit trust relationship of users, the problem that the existing research cannot make recommendations when the direct trust is difficult to obtain is solved, and the data sparsity and cold start problems are effectively alleviated. Secondly, in the process of user interest analysis, the relationship between scenic spots and tags is extended to the relationship among users, scenic spots and tags, and users' interest preferences are decomposed into long-term preferences for different scenic spots tags, which effectively alleviates the problem of poor recommendation quality when users' historical tour records are lacking. The personalized tourism recommendation method proposed in this paper effectively integrates many features of social networks and effectively alleviates the problems of data sparseness and feature learning in tourism recommendation based on social networks by using vectorization and deep learning technology. Its research has very important usage scenarios and commercial value in the tourism industry. This model can efficiently mine the association rules between scenic spots in multisource information data. The experimental results show that mining the correlation between the scenic spots selected by tourists can provide effective information for tourism decision-making. [ABSTRACT FROM AUTHOR]

The analysis of ancient literary works in the era of digital intelligence needs to keep pace with the times. In order to improve the analysis effect of ancient literary works, this paper combines the intelligent image text recognition algorithm to extract the features of ancient literary works and proposes an intelligent algorithm that can be used for the analysis of ancient literary works. Moreover, this paper combines the analysis needs of literary works to improve the algorithm. In order to verify the role of the intelligent image text recognition algorithm proposed in this paper in the analysis of ancient literary works, this paper scans a large number of pictures of ancient literary works in the library by scanning to construct the experimental database of this paper. Finally, this paper combines experimental research to verify the algorithm proposed in this paper. From the experimental results, it can be seen that the method proposed in this paper has a certain effect, and it can be used as a reference for the digital processing and digital preservation of subsequent literary works, and it can also be used as a reference for the management of digital libraries. [ABSTRACT FROM AUTHOR]

In the era of advanced information technology, new media represented by mobile phones have the characteristics of fast information dissemination, unlimited time, and place, and they are loved by people. Just like this, many businesses and enterprises use new media tools to promote and sell product information, and they have achieved positive results. In this context, this paper mainly studies the impact of new media communication on consumer behavior. By combining the characteristics of the industrial edge cloud deployment algorithm, an analysis model of behavior influencing factors is constructed, and relevant analysis is carried out. This paper mainly obtains experimental data by means of questionnaires and conducts experimental demonstrations for the proposed hypotheses. Before the experiment, the algorithm is compared and analyzed, and it is concluded that when the production line is 50, the algorithm in this paper is 0.6% and 0.32% lower than other algorithms under the SER index. When the production line is 100, the algorithm in this paper is 9.9% and 6.3% lower than other algorithms under the ELDR index. When the production line is 150, the algorithm in this paper is 2.2% and 2.4% lower than other algorithms under the ACR index, indicating that the performance of the algorithm in this paper is better than other algorithms under the SER, ELDR, and ACR indexes. In the correlation and regression analysis of variables, the results show that there is a positive relationship between consumer behavior and consumer willingness. At the same time, there is a positive relationship between consumer willingness and perceived novelty, perceived value, perceived interactivity, and perceived usefulness of new media. The coefficients of its functional expression are 0.411, 0.378, 0.241, and 0.216, respectively, verifying the assumptions 3, 5, 7, and 8 hold. It shows that consumer behavior is affected by consumer willingness, and consumer willingness is most affected by the perceived novelty of new media, followed by new media perceived value, perceived interactivity, and perceived usefulness. [ABSTRACT FROM AUTHOR]

In recent years, with the rapid economic development, the development speed of all walks of life has entered a new level, and the power industry has also developed rapidly. Driven by market demand, China's power transmission range and power transmission capacity will enter a new level. At the same time, the problems brought about by the development of the power system are equally severe. Due to the large load density in individual areas, the detection of short-circuit current must be improved as an important issue. The purpose of this paper is to study how to improve the practical model of short-circuit current calculation of photovoltaic power plants, so that it can be well applied to the current high-density current detection in China. Therefore, this paper improves the recursive least squares (RLS) algorithm and applies it to the practical model of short-circuit current calculation of photovoltaic power plants and describes the improvement process of the algorithm in detail. At the same time, this paper designs relevant experiments and analysis to count the data of the improved RLS algorithm in the short-circuit current calculation of the actual photovoltaic power station and combines the data of this part to test and analyze the ability of the algorithm. The experimental results in this paper show that the improved RLS algorithm has a very good improvement in the calculation accuracy of the short-circuit current calculation of photovoltaic power plants in the actual model calculation. At the same time, the calculation efficiency is also improved, and the current tracking effect is also improved by 7%. [ABSTRACT FROM AUTHOR]

In recent years, an increasing number of population-based metaheuristic algorithms have been proposed to solve the flexible job-shop scheduling problem (FJSP) according to its practicality and complexity. Most of these algorithms are single-population-based and hence are very susceptible to becoming trapped in local optimal values. Thus, multipopulation methods are widely used to improve these algorithms, resulting in multipopulation algorithms. These multipopulation algorithms have been widely studied in the context of single-layer complex networks recently. However, coupled networks used to control two (or more) algorithms simultaneously to get a better algorithm are always ignored in literature. Therefore, in this paper, using coupled scale-free networks (with different scaling exponents) to control the genetic algorithm (GA) and the invasive weed optimization (IWO) simultaneously, a multipopulation GA/IWO with coupled scale-free networks (MPGAIWO-SF) is proposed to solve FJSP. Then, we study how some parameters (e.g., subpopulation size, subpopulation number, and scaling exponent) of MPGAIWO-SF affect its performance, which is also ignored in literature. The simulation results illustrate that (1) the performance of MPGAIWO-SF is significantly improved compared with that of GA and IWO; (2) as the subpopulation size increases, the performance of MPGAIWO-SF first becomes better and then remains almost unchanged; (3) as the subpopulation number increases, the performance of MPGAIWO-SF first becomes better and then decreases rapidly; and (4) the performance of MPGAIWO-SF becomes worse slightly as the scaling exponent decreases. Finally, solving more FJSP instances, the MPGAIWO-SF with optimized parameters is compared with other related algorithms to verify its effectiveness. [ABSTRACT FROM AUTHOR]

(Purpose/Significance). This paper aims at the problems of inaccurate recommendation effect caused by data sparseness and cold start in the traditional collaborative filtering-based book personalized recommendation algorithm. So this paper proposes a collaborative filtering recommendation algorithm which improves the similarity solution method and the filling method of missing data. (Method/Process). By considering the influence of the user's common rating book collection on the similarity calculation, the average rating value of all books is used as the threshold, and the user's common rating weight is introduced into the user's similarity calculation. As for data filling, according to the user's average rating, the basic attributes such as the age and gender of users are coded, and then Euclidean distance is initially calculated, making hierarchical clustering on users. What's more, Shope-one algorithm is used to calculate the filling value of the former m similar users，and add the weight value of the degree simultaneously to get the final filling value, so as to improve the data filling method. (Result/Conclusion). Experiments were carried out with the data set of Book-Crossing Data set through Python. The experimental results show that the improved collaborative filtering algorithm has a significantly improvement in the accuracy and quality of book recommendation. [ABSTRACT FROM AUTHOR]

Effective perception of the surrounding environment and the balance between accuracy and processing speed are crucial for the successful application of real-time semantic segmentation algorithm in the fields of autonomous driving, drones, and smart security. In this paper, a lightweight feature reuse network MHANet for real-time semantic segmentation is proposed. The main novelties of our method are improved ResNet and attention-based fusion mechanism. And the effectiveness of our method is verified by a large number of experiments. Without any pre-training process, the performance of real-time segmentation is improved by using deep fusion of segmentation maps with different resolutions. At the same time, our network converges faster than other networks using pre-training when trained from scratch. Compared with existing methods, the results obtained with our method on the Camvid dataset improve in accuracy (mIoU) ranging from 2% to 6% and in efficiency (FPS) ranging from 15% to 18%. The results achieved 71.87% mIoU of accuracy in the Cityscapes test set, processing images at 203 FPS. Experiments show that manual designed MHANet is effective in improving the performance of real-time semantic segmentation without any pre-training. [ABSTRACT FROM AUTHOR]

Undercarriage device is one of the essential parts of an aeroplane, and accurate detection of whether the aeroplane undercarriage is operating normally can effectively avoid aeroplane accidents. To address the problems of low automation and low accuracy of small target detection in existing aeroplane undercarriage detection methods, an improved algorithm for aeroplane undercarriage detection YOLO V4 is proposed. Firstly, the convolutional network structure of Inception-ResNet is integrated into the CSPDarkNet53 framework to improve the algorithm's ability to extract semantic information of target features; then an attention mechanism is added to the path aggregation network algorithm structure to improve the importance and relevance of different features after conceptual operations. In addition, aeroplane and undercarriage datasets were constructed, and finally, the generated partitioned test sets were tested to evaluate the test performance of Faster R-CNN, YOLO V3, and YOLO V4 target detection algorithms. The experimental results show that the improved algorithm has significantly improved the recall rate and the mean accuracy of detection for small targets in our dataset compared with the YOLO V4 algorithm. The reasonableness and advancedness of the improved algorithm in this paper are effectively verified. [ABSTRACT FROM AUTHOR]

It is very important for power grid development research and related technical improvement to obtain the disaster situation of fine-scale distribution network, such as the transportation condition evaluation of distribution network and the wind waterlogging disaster prediction of distribution network. Among them, the wind waterlogging disaster prediction of distribution network is the main one, and the prediction of its disaster degree often determines whether the distribution network can be prevented before and rescued after the disaster. Therefore, in view of the above problems, combined with the actual transmission situation of the distribution network, after collecting the measured disaster data of the distribution network in relevant areas, combined with the multi-source data fusion technology and neural network modeling technology, this paper analyzes the disaster degree indicators of different distribution networks and constructs the relevant fuzzy matrix through the fuzzy theory to evaluate the disaster degree, which is verified by the measured data. This distribution network disaster loss prediction model can effectively implement the disaster loss prediction of distribution network and compare its prediction results with the other two different common models. The comparison results show that the prediction accuracy of the multi-source data fusion prediction model constructed in this paper is more than 0.95 compared with the other two models, while the prediction accuracy of the other two models is not more than 0.9, which proves that the model constructed in this paper has smaller errors. It has the advantages of higher accuracy and faster convergence speed. [ABSTRACT FROM AUTHOR]

Lack of trust, lack of standards, and low efficiency are the three biggest problems in China's trade financing at present. With the development and application of new generation technologies such as big data, cloud computing, artificial intelligence, and blockchain technology, China is in the stage of financial technology 3.0 under the deep integration of finance and technology. In the field of financial technology, the most concerned is the application of blockchain technology in trade finance business. With the successive construction of various blockchain platforms and the acceleration of the internationalization process, the international trade credit risk behind it is also increasing. Among many financial services, trade finance is the most closely integrated field with blockchain technology. In this context, preventing the risks in the business process of international trade enterprises, so as to reduce the cost of financial transactions, improve the effectiveness of financial services, and better serve the real economy is not only the internal development needs of enterprises, but also the national financial strategy needs. In view of the above problems, this paper analyzes the risk factors faced by multinational trading enterprises in the transaction process through the transaction data of some multinational enterprises on mobile phones, and constructs a credit evaluation system of international trading enterprises based on blockchain, in order to enhance the trade risk resistance ability of international trading companies. [ABSTRACT FROM AUTHOR]