Search

Splicing the shredded paper means the technology that, according the paper, which has been shredded to design a particular algorithm to splice and recover the original paper. This paper introduced the algorithm of splicing the shredded paper based on the matching to texture feature. By means of this algorithm, we modeled for the problem of splicing the shredded paper and solved it. And, we used the algorithm to splice both pieces of English shredded paper and Chinese shredded paper. The recovered paper had proved the accuracy of the algorithm.

This paper presents a new method for calculating the insulation health index (HI) of oil-paper transformers rated under 110 kV to provide a snapshot of health condition using binary logistic regression. Oil breakdown voltage (BDV), total acidity of oil, 2-Furfuraldehyde content, and dissolved gas analysis (DGA) are singled out in this method as the input data for determining HI. A sample of transformers is used to test the proposed method. The results are compared with the results calculated for the same set of transformers using fuzzy logic. The comparison results show that the proposed method is reliable and effective in evaluating transformer health condition.

We consider a one-dimensional cutting stock problem (CSP) in which the stock widths are not used to fulfill the order but kept for use in the future for the industrial-use paper production. We present a new model based on the flexible stock allocation and trim loss control to determine the production quantity. We evaluate our approach using a real data and show that we are able to solve industrial-size problems, while also addressing common cutting considerations such as aggregation of orders, multiple stock widths, and cutting different patterns on the same machine. In addition, we compare our model with others, including trim loss minimization problem (TLMP) and cutting stock problem (CSP). The results show that the proposed model outperforms the other two models regarding total flexibility and trim loss ratio.

This paper analyzed the drying process of the household gas clothes dryer (GCD) based on the principle of heat and mass transfer. The drying models in three scenarios were established: natural gas burned in combustion chamber, ambient air mixed with exhausted gas in hot gas duct, and clothes were dried in the drying drum. The simulation of the drying process was performed on MATLAB software. And the effectiveness of the drying model was verified by comparison with experiment results. The effects of gas flow rate, dry mass of clothes, ambient temperature, ambient humidity, textile type, and moisture extraction rate (MER) on the performance of dryers were studied. This paper provided a theoretical basis for the design and optimization of GCDs. It was found that the drying time of the gas clothes dryer was mostly affected by the gas flow and dry mass of clothes, and the specific moisture extraction rate (SMER) was mostly affected by the ambient temperature and relative humidity. The nylon clothes have the fastest MER and the smallest SMER. Moreover, reducing operating time in falling-rate drying period can improve energy efficiency.

In recent years, modeling and recognizing driver behavior have become crucial to understanding intelligence transport systems, human-vehicle systems, and intelligent vehicle systems. A wide range of both mathematical identification methods and modeling methods of driver behavior are presented from the control point of view in this paper based on the driving data, such as the brake/throttle pedal position and the steering wheel angle, among others. Subsequently, the driver’s characteristics derived from the driver model are embedded into the advanced driver assistance systems, and the evaluation and verification of vehicle systems based on the driver model are described.

In order to explore the impact of different decision-making methods on the profits of various entities in the supply chain of the community e-commerce platform, this paper adopts the method of the Stackelberg game. For the community e-commerce platform supply chain composed of suppliers, community e-commerce platforms, and grid station service providers, considering the degree of supplier value cocreation efforts, this paper studies the optimal decisions under centralized decision-making, supplier-led decentralized decision-making, and community e-commerce platform-led decentralized decision-making, respectively. The results show that the supply chain obtains the highest profit in centralized decision-making; under decentralized decision-making, the dominant party will get higher profits; and the supplier value cocreation sensitivity coefficient is positively correlated with sales price, value cocreation effort level, and total supply chain value. The results are helpful to improve the competitiveness of the community e-commerce platform supply chain in the market and are of great significance to the long-term development of the community e-commerce industry.

From the time dimension, this paper analyzes the characteristics of the scale, industrial structure, employment flexibility, and comprehensive employment effects of regional tourism employment based on the three-level criteria of the scope of tourism employment based on the regional Internet of Things. From the spatial dimension, we take the regional city as the basic research unit, adopt multiple indicators, and conduct a comprehensive evaluation of the regional development of regional tourism employment through horizontal and vertical comparisons. This paper uses multiple linear regression analysis to establish the relationship between the development level of the county tourism economy and the influencing factors; in order of magnitude of influence, they are tourism resource endowment, location traffic conditions, and economic development. Using a combination of a single indicator and multiple indicators, the county tourism economy is evaluated and analyzed for differences in time and space. We select the total tourism revenue as an indicator and use methods such as range, standard deviation, coefficient of variation, and coefficient to analyze the time difference of the tourism economy in each county. We adopt the Granger causality test and other methods to analyze the factors affecting tourism employment in the area and the growth mode. Through the establishment of a structural model of the tourism employment growth dynamics system, causality test and other methods are adopted to analyze the regional tourism employment influencing factors and growth methods, and the results show that the regional tourism employment growth mode is an investment-driven tourism employment growth mode.

In this paper, we address the issues of the trade-off between QoS and QoE with an analytical analysis based on mathematical modeling under a unified normalization measurement. We model through computation the awareness of QoS and QoE with a strategy of quality-aware QoE-QoS coordination. A balanced coordination is proposed using modeling correlations between user experience and service performance. The main contributions of this paper include three main parts. First, a comprehensive mapping is modeled in a close form to illustrate the analytic correlations between QoS, QoE, and data communication. Second, an analytical method to analyze and coordinate the nonlinear trade-off between QoE and QoS is proposed based on the theoretical proof with discussions on necessary-sufficient conditions. Third, an algorithmic framework is provided to perform QoE-QoS coordination based on quality-awareness computing with a test proof. An assessment model for user experience quantification is built with the mean opinion score (MOS) test. Quality-aware QoE and QoS models are built based on the subspace learning strategy. Simulations are given to prove the feasibility and effectiveness of the proposed method. The results show that the operations with the proposed solution can be obtained analytically with balanced efficiency in both user experience performance and network performance.

With the accelerated pace of urbanization, green buildings and green smart buildings gradually come into people’s vision and are highly valued by all sectors of society on the premise of meeting sustainable development strategy. Firstly, this paper selects 7 first-level index factors and 20 second-level index factors to establish the green smart building evaluation system. Secondly, this paper uses the analytic hierarchy process-fuzzy comprehensive evaluation (AHP-FCE) method to determine the weight of each secondary index. Finally, the feasibility of the evaluation system is verified by case analysis, and some suggestions on green smart building are put forward.

The precision of traditional deformation resistance model is limited, which leads to the inaccuracy of the existing rolling force model. In this paper, the back propagation (BP) neural network model was established according to the industrial big data to accurately predict the deformation resistance. Then, a new rolling force model was established by using the BP neural network model. During the establishment of the neural network model, the data set of deformation resistance was established, which was calculated back from the actual rolling force data. Based on the data set after normalization, the BP neural network model of deformation resistance was established through the optimization of algorithm and network structure. It is shown that both the prediction accuracy of the neural network model on the training set and the test set are high, indicating that the generalization ability of the model is strong. The neural network model of the deformation resistance is compared with the theoretical one, and the maximum error is only 3.96%. Furthermore, by comparison with the traditional rolling force model, it is found that the prediction accuracy of the rolling force model imbedding with the present neural network model is improved obviously. The maximum error of the present rolling force model is just 3.86%. The research in this paper provides a new way to improve the prediction accuracy of rolling force model.

Hand gesture recognition is a challenging topic in the field of computer vision. Multimodal hand gesture recognition based on RGB-D is with higher accuracy than that of only RGB or depth. It is not difficult to conclude that the gain originates from the complementary information existing in the two modalities. However, in reality, multimodal data are not always easy to acquire simultaneously, while unimodal RGB or depth hand gesture data are more general. Therefore, one hand gesture system is expected, in which only unimordal RGB or Depth data is supported for testing, while multimodal RGB-D data is available for training so as to attain the complementary information. Fortunately, a kind of method via multimodal training and unimodal testing has been proposed. However, unimodal feature representation and cross-modality transfer still need to be further improved. To this end, this paper proposes a new 3D-Ghost and Spatial Attention Inflated 3D ConvNet (3DGSAI) to extract high-quality features for each modality. The baseline of 3DGSAI network is Inflated 3D ConvNet (I3D), and two main improvements are proposed. One is 3D-Ghost module, and the other is the spatial attention mechanism. The 3D-Ghost module can extract richer features for hand gesture representation, and the spatial attention mechanism makes the network pay more attention to hand region. This paper also proposes an adaptive parameter for positive knowledge transfer, which ensures that the transfer always occurs from the strong modality network to the weak one. Extensive experiments on SKIG, VIVA, and NVGesture datasets demonstrate that our method is competitive with the state of the art. Especially, the performance of our method reaches 97.87% on the SKIG dataset using only RGB, which is the current best result.

With the rapid development of economy and society and the continuous optimization of industrial structure, the demand for high skilled talents is increasing. Education plays an irreplaceable role in China’s economic growth. Therefore, it is of great significance to study the impact of talent supply of vocational education on economic growth from the perspective of human capital and comprehensively consider the spatial interaction of economic growth. Taking intelligent image recognition technology as the main research technology, this paper discusses the contribution of educational human capital to regional green economic growth. This paper expounds the content of intelligent image recognition technology, constructs an image recognition system based on neural network, and studies the relationship between human resource utilization efficiency and regional economy under intelligent image recognition technology based on the empirical analysis of intelligent image recognition technology. Finally, it makes an empirical study on the spatial effect in the image recognition system and expounds the relationship between feature space and economic growth. It verifies the relationship between educational human capital and green economic growth. The results show that the intelligent image recognition technology has a good effect in the research of spatial effect.

As the essential content of intelligent animal husbandry, identifying each livestock is the only way to achieve modern and refined scientific husbandry. This paper proposes a sheep face recognition method based on European spatial metrics and realizes noncontact sheep identity recognition by training the network using sheep face image samples in the natural environment. The SheepBase data set was first proposed in this process, which contains 6559 images of Inner Mongolia fine-wool sheep and Sunite sheep. To enhance the diversity of the data, the sheep face images were data-enhanced. Secondly, to solve the problems of more redundant information in the sheep face image and the poor posture and angle of the sheep face, we propose the sheep face detection and correction (SheepFaceRepair) method. This method aims to detect the sheep face area in the image to be recognized and align the sheep face area. On this basis, we offer an open sheep facial recognition network (SheepFaceNet) based on the European spatial metric. This method incorporates the biological identity information features of the sheep face to achieve sheep identity. We also tested the effectiveness of this method in the SheepBase data set. The experimental results show that the method proposed in this paper is much higher than the other methods, and the precision of recognition reaches 89.12%. In addition, we found that integrating the biometrics of the sheep face can effectively improve the network’s recognition capacity.

Logistics distribution is the terminal link that connects the manufacturer and product user and determines the efficiency of the manufacturer’s service. Therefore, the disruption risk of the joint system is an essential factor affecting the product user experience. In this paper, while considering the product user’s supply disruption risk preference (PUSDRP), a biobjective integer nonlinear programming (INLP) model with subjective cost-utility is proposed to solve the manufacturer’s combined location routing inventory problem (CLRIP). According to the user’s time satisfaction requirement, a routing change selection framework (RCSF) is designed based on the bounded rational behavior of the user. Additionally, the Lagrange Relaxation and Modified Genetic Algorithm (LR-MGA) is proposed. The LR method relaxes the model, and the MGA finds a compromise solution. The experimental results show that the biobjective cost-utility model proposed in this paper is effective and efficient. The RCSF based on user behavior is superior to the traditional expected utility theory model. The compromise solution provides a better solution for the manufacturer order allocation delivery combinatorial optimization problem. The compromise solution not only reduces the manufacturer’s total operating cost but also improves the user's subjective utility. To improve the stability of cooperation between manufacturers and users, the behavior decision-making method urges manufacturers to consider product users’ supply disruption risk preferences (PUSDRPs) in attempting to optimize economic benefits for the long term. This paper uses behavior decision-making methods to expand the ideas of the CLRIP joint system.

Diabetic retinopathy (DR) is a diabetic complication affecting the eyes, which is the main cause of blindness in young and middle-aged people. In order to speed up the diagnosis of DR, a mass of deep learning methods have been used for the detection of this disease, but they failed to attain excellent results due to unbalanced training data, i.e., the lack of DR fundus images. To address the problem of data imbalance, this paper proposes a method dubbed retinal fundus images generative adversarial networks (RF-GANs), which is based on generative adversarial network, to synthesize retinal fundus images. RF-GANs is composed of two generation models, RF-GAN1 and RF-GAN2. Firstly, RF-GAN1 is employed to translate retinal fundus images from source domain (the domain of semantic segmentation datasets) to target domain (the domain of EyePACS dataset connected to Kaggle (EyePACS)). Then, we train the semantic segmentation models with the translated images, and employ the trained models to extract the structural and lesion masks (hereafter, we refer to it as Masks) of EyePACS. Finally, we employ RF-GAN2 to synthesize retinal fundus images using the Masks and DR grading labels. This paper verifies the effectiveness of the method: RF-GAN1 can narrow down the domain gap between different datasets to improve the performance of the segmentation models. RF-GAN2 can synthesize realistic retinal fundus images. Adopting the synthesized images for data augmentation, the accuracy and quadratic weighted kappa of the state-of-the-art DR grading model on the testing set of EyePACS increase by 1.53% and 1.70%, respectively.

In-depth mining and analysis of electricity data in low-voltage area are essential for the further intelligent development of power grids. However, in the actual data collection and measurement of low-voltage area, there will be missing data, and complete electricity data cannot be obtained. To obtain complete power data, this paper proposes a low-voltage station area missing data complement model based on joint matrix decomposition. First, we analyse the characteristics of the low-pressure station data. Then, a model that comprehensively considers the characteristics of the low-voltage station area data is proposed, which includes three parts: the construction of a low-voltage station area data tensor, the joint matrix decomposition, and the completion of the missing data, and it is named LPZ. After that, the CIM learning algorithm proposed in this paper is used to iteratively solve the model to obtain the completed data. Finally, the method proposed in this paper is used to complement the two situations of random loss and all-day loss of real current data in a low-voltage station area and compared with the traditional complement method. The experimental results show that this method is not only effective but also that the completion effect is better than that of other completion methods.

Scale and standardization are essential to the prosperity of the breeding industry. During large-scale, standardized breeding, the selective breeding of good livestock breeds hinges on the accurate measurement of body parameters for live animals. However, the complex shooting environment brings several urgent problems, such as the missing of many local data in the point cloud and the difficulty in the automatic acquisition of body data. To solve these problems, this paper proposes a method for parameter measurement of live animals based on the mirror of multiview point cloud. Firstly, the acquisition and stitching principles were given for the multiview point cloud data on body parameters of live animals. Next, the authors presented a way to make up for the data missing areas in the point cloud. Finally, this paper acquires the body mirror data of live animals and scientifically calculates the body parameters. The proposed measurement method was proved effective through experiments.

As a special type of enterprises with high risks, Chinese commercial banks’ risk management plays an important role in banks’ business process. Measuring and improving the risk management efficiency of the Chinese commercial banking system has recently attracted increasing interest. Previous studies analyze the business performance of commercial banks from the perspective of the overall management level of banks, and few articles focus on the risk management ability of banks. This paper evaluates the technical efficiencies of Chinese commercial banks’ risk management by the DEA-BCC model with window analysis to come up with some recommendations for policy makers. The technical efficiency is then decomposed into pure technology efficiency and scale efficiency. According to the banking risk supervision indicators released by the China Banking Regulatory Commission, we choose the indicators of 26 commercial banks’ risk management during the period of 2011 to 2019. Principal component analysis (PCA) is applied to delete redundant input indicators. The paper gives a dynamic evaluation of technology efficiency, pure technology efficiency, and scale efficiency. The main empirical results are as follows: (1) the technical efficiency of Chinese commercial banks’ risk management is low, and the differences among three different types of banks are large. (2) The pure technology inefficiency of Chinese commercial banks’ risk management has become a key factor restricting the improvement of the risk management of the Chinese banking industry. (3) The Chinese commercial banks’ risk management faces a serious problem which is economies of scale. (4) The technical efficiencies of Chinese commercial banks’ risk management fluctuate greatly, and management capabilities need to be enhanced urgently.

With the advent of the information age, human demand for information is increasing day by day. The emergence of the concept of big data has triggered a new round of technological revolution, and visual information plays an important role in information. In order to obtain a better 3D model, this paper studies the reconstruction model of training motion 3D images based on a graphical neural network algorithm. This paper studies the problem of Sanda from the following two aspects. First, we try to apply two deep learning algorithms, graphical neural network and recurrent neural network, to the boxing movement recognition task and compare the effects with quadratic discriminant analysis and support vector machine. By comparing and analyzing the influence of different network structures on the deep learning algorithm, it is concluded that recurrent neural network has more practical application advantages than graph neural network in network structure parameter tuning.

It is difficult for the autonomous underwater vehicle (AUV) to recognize targets similar to the environment in lacking data labels. Moreover, the complex underwater environment and the refraction of light cause the AUV to be unable to extract the complete significant features of the target. In response to the above problems, this paper proposes an underwater distortion target recognition network (UDTRNet) that can enhance image features. Firstly, this paper extracts the significant features of the image by minimizing the info noise contrastive estimation (InfoNCE) loss. Secondly, this paper constructs the dynamic correlation matrix to capture the spatial semantic relationship of the target and uses the matrix to extract spatial semantic features. Finally, this paper fuses the significant features and spatial semantic features of the target and trains the target recognition model through cross-entropy loss. The experimental results show that the mean average precision (mAP) of the algorithm in this paper increases by 1.52% in recognizing underwater blurred images.

The governments need beforehand to perceive the innovative relationship risk because they are one of the innovation subjects in those industry collaborative innovation alliances. However, it is difficult for innovation subjects to quantify the risks for industry collaborative innovation alliances due to the complexity, nonlinear, and dynamic condition. This paper firstly constructs an ordered logistic model, uses the following as independent variables: the collaborative degree, the ratio of science technology expenditure to GDP, the ratio of education expenditure to GDP, the ratio of finances to GDP, and uses the levels of risk as the dependent variable. Then, this paper uses the panel data of 30 provinces in China (Hainan is not included) from 2010 to 2018 to fit the model. Based on the fitting results, the research has gained the relationship risk prewarning model in industry collaborative innovation alliances by using the collaborative degree as an independent variable. The governments at all levels can use this relationship risk prewarning model to percept risk levels and reckon the corresponding probability which exists in industry collaborative innovation alliances. Furthermore, there are regional influences existing in the prewarning relationship risk levels in industry collaborative alliances. The east and middle areas have significant regional influence, but it does not exist among west areas and others. The governments at all levels may consider the regional differences.

This paper mainly studies the influence of dynamic cognitive diagnosis on personalized learning. Considering the influence of knowledge correlation factors and human brain memory factors on learning activities, a knowledge tracing model integrating learning factors is proposed. Firstly, based on the exercise-knowledge association information, the model maps learners and exercises to the knowledge space with clear meaning. Then, the evolution process of learners’ knowledge learning is quantitatively modeled in the knowledge space by integrating the classical learning curve and forgetting curve theory of pedagogy. On the other hand, considering the influence of topic semantics in the learning process, a knowledge tracing model integrating topic semantics is proposed in this paper. Firstly, the model designs a dynamic enhanced memory network to store the common information of knowledge and describes the learners’ dynamic mastery of knowledge. Secondly, the depth representation method of exercise resources is proposed to mine the text personality information and integrate it into the process of learners’ knowledge change modeling. Through a large number of experiments on exercise records, it is verified that the proposed model has accurate prediction performance and knowledge tracing interpretability.

This paper proposes a new method to make short-term predictions for the three kinds of primary energy consumption of power, lighting, and ventilated air conditioning in the metro station. First, the paper extracts the five main factors influencing metro station energy consumption through the kernel principal component analysis (KPCA). Second, improved genetic-ant colony optimization (G-ACO) was fused into the BP neural network to train and optimize the connection weights and thresholds between each BP neural network layer. The paper then builds a G-ACO-BP neural model to make short-term predictions about different energy consumption in the metro station to predict the energy consumed by power, lighting, and ventilated air conditioning. The experimental results showed that the G-ACO-BP neural model could give a more accurate and effective prediction for the main energy consumption in a metro station.

China is gradually transitioning from the “tunnel construction era” to the “tunnel maintenance era,” and more and more operating tunnels need to be inspected for diseases. With the continuous development of computer vision, the automatic identification of tunnel lining cracks with computers has gradually been applied in engineering. On the basis of summarizing the weaknesses and strengths of previous studies, this paper first uses the improved multiscale Retinex algorithm to filter the collected tunnel crack images and introduces the eight-direction Sobel edge detection operator to extract the edges of the cracks. Perform mathematical morphological operations on the image after edge extraction, and use the principle of the smallest enclosing rectangle to remove the isolated points of the image. Finally, the performance of the algorithm is judged by the objective evaluation index of the image, the accuracy of crack recognition, and the running time of the algorithm. The image filtering algorithm proposed in this paper can better preserve the edges of the image while enhancing the image. The objective evaluation indexes of the image have been improved significantly, and the main body of the crack can be accurately identified. The overall crack recognition accuracy rate can reach 97.5%, which is higher than the existing tunnel lining crack recognition algorithm, and the average calculation time for each image is shorter. This algorithm has high research significance and engineering application value.

Extreme value theory (EVT) is useful for modeling the impact of crashes or situations of extreme stress on investor portfolios. EVT is mostly utilized in financial modeling, risk management, insurance, and hydrology. The price of gold fluctuates considerably over time, and this introduces a risk on its own. The goal of this study is to analyze the risk of gold investment by applying the EVT to historical daily data for extreme daily losses and gains in the price of gold. We used daily gold prices in the Pakistan Bullion Market from August 1, 2011 to July 30, 2021. This paper covers two methods such as Block Maxima (BM) and Peak Over Threshold (POT) modeling. The risk measures which are adopted in this paper are Value at Risk (VaR) and Expected Shortfall (ES). The point and interval estimates of VaR and ES are obtained by fitting the Generalized Pareto (GPA) distribution. Moreover, in this paper, return-level forecasting is also included for the next 5 and 10 years by analyzing the Generalized Extreme Value (GEV) distribution.

With the rapid development of artificial intelligence in recent years, the research on image processing, text mining, and genome informatics has gradually deepened, and the mining of large-scale databases has begun to receive more and more attention. The objects of data mining have also become more complex, and the data dimensions of mining objects have become higher and higher. Compared with the ultra-high data dimensions, the number of samples available for analysis is too small, resulting in the production of high-dimensional small sample data. High-dimensional small sample data will bring serious dimensional disasters to the mining process. Through feature selection, redundancy and noise features in high-dimensional small sample data can be effectively eliminated, avoiding dimensional disasters and improving the actual efficiency of mining algorithms. However, the existing feature selection methods emphasize the classification or clustering performance of the feature selection results and ignore the stability of the feature selection results, which will lead to unstable feature selection results, and it is difficult to obtain real and understandable features. Based on the traditional feature selection method, this paper proposes an ensemble feature selection method, Random Bits Forest Recursive Clustering Eliminate (RBF-RCE) feature selection method, combined with multiple sets of basic classifiers to carry out parallel learning and screen out the best feature classification results, optimizes the classification performance of traditional feature selection methods, and can also improve the stability of feature selection. Then, this paper analyzes the reasons for the instability of feature selection and introduces a feature selection stability measurement method, the Intersection Measurement (IM), to evaluate whether the feature selection process is stable. The effectiveness of the proposed method is verified by experiments on several groups of high-dimensional small sample data sets.

Today, the global exchange market has been the world’s largest trading market, whose volume could reach nearly 5.345 trillion US dollars, attracting a large number of investors. Based on the perspective of investors and investment institutions, this paper combines theory with practice and creatively puts forward an innovative model of double objective optimization measurement of exchange forecast analysis portfolio. To be more specific, this paper proposes two algorithms to predict the volatility of exchange, which are deep learning and NSGA-II-based dual-objective measurement optimization algorithms for the exchange investment portfolio. Compared with typical traditional exchange rate prediction algorithms, the deep learning model has more accurate results and the NSGA-II-based model further optimizes the selection of investment portfolios and finally gives investors a more reasonable investment portfolio plan. In summary, the proposal of this article can effectively help investors make better investments and decision-making in the exchange market.

Sea ice disasters are already one of the most serious marine disasters in the Bohai Sea region of our country, which have seriously affected the coastal economic development and residents’ lives. Sea ice classification is an important part of sea ice detection. Hyperspectral imagery and multispectral imagery contain rich spectral information and spatial information and provide important data support for sea ice classification. At present, most sea ice classification methods mainly focus on shallow learning based on spectral features, and the good performance of the deep learning method in remote sensing image classification provides a new idea for sea ice classification. However, the level of deep learning is limited due to the influence of input size in sea ice image classification, and the deep features in the image cannot be fully mined, which affects the further improvement of sea ice classification accuracy. Therefore, this paper proposes an image classification method based on multilevel feature fusion using residual network. First, the PCA method is used to extract the first principal component of the original image, and the residual network is used to deepen the number of network layers. The FPN, PAN, and SPP modules increase the mining between layer and layer features and merge the features between different layers to further improve the accuracy of sea ice classification. In order to verify the effectiveness of the method in this paper, sea ice classification experiments were performed on the hyperspectral image of Bohai Bay in 2008 and the multispectral image of Bohai Bay in 2020. The experimental results show that compared with the algorithm with fewer layers of deep learning network, the method proposed in this paper utilizes the idea of residual network to deepen the number of network layers and carries out multilevel feature fusion through FPN, PAN, and SPP modules, which effectively solves the problem of insufficient deep feature extraction and obtains better classification performance.

This paper considers the principle-agent conflict problem in a continuous-time delegated asset management model when the investor and the fund manager are all risk-averse with risk sensitivity coefficients γ f and γ m , respectively. Suppose that the investor entrusts his money to the fund manager. The return of the investment is determined by the manager’s effort level and incentive strategy, but the benefit belongs to the investor. In order to encourage the manager to work hard, the investor will determine the manager’s salary according to the terminal income. This is a stochastic differential game problem, and the distribution of income between the manager and the investor is a key point to be solved in the custody model. The uncertain form of the incentive strategy implies that the problem is different from the classical stochastic optimal control problem. In this paper, we first express the investor’s incentive strategy in term of two auxiliary processes and turn this problem into a classical one. Then, we employ the dynamic programming principle to solve the problem.

With the advent of the new types of electrical systems that attach more importance to the renewability of the energy resource, issues arising out of the randomness and volatility of the renewable energy resource, such as the safety, reliability, and economic operation of the underlying power generation system, are expected to be challenging. Generally speaking, the power generation company can do a reasonable dispatch of each unit according to weather forecast and load demand information. Focusing on concentrating solar power (CSP) plants (wind power, photovoltaic, battery energy storage, and thermal power plants), this paper proposes a day-ahead scheduling model for renewable energy generation systems. The model also considers demand response and related generator set constraints. The problem is described as a mixed-integer nonlinear programming (MINLP) problem, which can be solved by the CPLEX solver to obtain an optimal solution. At the same time, the paper compares and analyzes the impact of concentrating solar power plants on other renewable energy generation and thermal power operation systems. The results show that the renewable energy generation system can lower power generation costs, reduce load fluctuation, and enhance the energy storage rate.

Alzheimer’s disease (AD) is an irreversible neurodegenerative disease, and, at present, once it has been diagnosed, there is no effective curative treatment. Accurate and early diagnosis of Alzheimer’s disease is crucial for improving the condition of patients since effective preventive measures can be taken in advance to delay the onset time of the disease. 18F-Fluorodeoxyglucose positron emission tomography (18F-FDG PET : PET) is an effective biomarker of the symptom of AD and has been used as medical imaging data for diagnosing AD. Mild cognitive impairment (MCI) is regarded as an early symptom of AD, and it has been shown that MCI also has a certain biomedical correlation with PET. In this paper, we explore how to use 3D PET images to realize the effective recognition of MCI and thus achieve the early prediction of AD. This problem is then taken as the classification of three categories of PET images, including MCI, AD, and NC (normal controls). In order to get better classification performance, a novel network model is proposed in the paper based on 3D convolution neural networks (CNN) and support vector machines (SVM) by utilizing both the excellent abilities of CNN in feature extraction and SVM in classification. In order to make full use of the optimal property of SVM in solving binary classification problems, the three-category classification problem is divided into three binary classifications, and each binary classification is being realized with a CNN + SVM network. Then, the outputs of the three CNN + SVM networks are fused into a final three-category classification result. An end-to-end learning algorithm is developed to train the CNN + SVM networks, and a decision fusion algorithm is exploited to realize the fusion of the outputs of three CNN + SVM networks. Experimental results obtained in the work with comparative analyses confirm the effectiveness of the proposed method.

This paper identifies the system composition of the life cycle of retreaded tires and constructs the energy consumption model, carbon emission model, and economic model of retreaded tires based on the life cycle theory. Moreover, the theoretical calculation model and method for the energy consumption, carbon emission, and economy at the production phase, transportation phase, usage phase, and reuse phase of retreaded tires are proposed. After that, this paper puts forward the energy substitution model, carbon reduction model, and cost profit model of five reuse methods of retreaded tires, namely, secondary retreading, mechanical pulverization, low-temperature pulverization, combustion decomposition, and combustion power generation. Finally, this paper proposes the evaluation index for the energy consumption, carbon emission, and economy in the life cycle of retreaded tires and quantitatively analyzes the energy consumption, carbon emission, and cost profit list in each phase of the life cycle of retreaded tires, obtaining the energy recovery rate, carbon reduction rate, and profit-to-cost ratio of the five reuse methods of retreaded tires. The main conclusions of this paper are as follows: the energy consumption and carbon emission of retreaded tires are the largest at the production phase, while the energy consumption and carbon emission are the lowest at the transportation phase. Among the five reuse methods, the energy recovery effect, carbon reduction rate, and economy of secondary retreading are the optimal ones, and the quantitative results show that retreading is the most effective way for the reuse of waste tires.

A convolutional neural network’s weight sharing feature can significantly reduce the cumbersome degree of the network structure and reduce the number of weights that need to be trained. The model can directly input the original image, without the process of feature extraction and data reconstruction in common classification algorithms. This kind of network structure has got a good performance in image processing and recognition. Based on the color objective evaluation method of the convolutional neural network, this paper proposes a convolutional neural network model based on multicolor space and builds a convolutional neural network based on VGGNet (Visual Geometry Group Net) in three different color spaces, namely, RGB (Red Green Blue), LAB (Luminosity a b), and HSV (Hue Saturation Value) color spaces. We carry out research on data input processing and model output selection and perform feature extraction and prediction of color images. After a model output selection judger, the prediction results of different color spaces are merged and the final prediction category is output. This article starts with the multidimensional correlation for visual art image processing and color objective evaluation. Considering the relationship between the evolution of artistic painting style and the color of artistic images, this article explores the characteristics of artistic image dimensions. In view of different factors, corresponding knowledge extraction strategies are designed to generate color label distribution, provide supplementary information of art history for input images, and train the model on a multitask learning framework. In this paper, experiments on multiple art painting data sets prove that this method is superior to single-color label classification methods.

Statistical analysis of Bactrocera grooming behavior is important for pest control and human health. Based on DeepLabCut, this study proposes a noninvasive and effective method to track the key points of Bactrocera minax and to detect and analyze its grooming behavior. The results are analyzed and calculated automatically by a computer program. Traditional movement tracking methods are invasive; for instance, the use of artificial pheromone may affect the behavior of Bactrocera minax, thus directly affecting the accuracy and reliability of experimental results. Traditional research studies mainly rely on manual work for behavior analysis and statistics. Researchers need to play the video frame by frame and record the time interval of each grooming behavior manually, which is time-consuming, laborious, and inaccurate. So the advantages of automated analysis are obvious. Using the method proposed in this paper, the image data of 94538 frames from 5 adult Bactrocera were analyzed and 14 key points were tracked. The overall tracking accuracy was as high as 96.7%. In the behavior analysis and statistics, the average accuracy rate of the five grooming behavior was all above 96%, and the accuracy rate of the remaining two grooming behavior was over 87%. The experimental results show that the automatic noninvasive method designed in this paper can track many key points of Bactrocera minax with high accuracy and ensure the accuracy of insect behavior recognition and analysis, which greatly reduces the manual observation time and provides a new method for key points tracking and behavior recognition of related insects.

In theory, the industrial agglomeration is a double-edged sword as there are both positive and negative externalities. China’s cities, with great disparities on degrees of the industrial agglomeration, often face different energy and carbon dioxide emission problems, which raise the question whether the industrial agglomeration promotes or inhibits energy efficiency and carbon dioxide emission. This paper explored the effects of the industrial agglomeration on carbon efficiency in China. Spatial econometric methods were implemented using panel data (2007–2016) of 285 cities above the prefecture level. The results revealed that industrial agglomerations have significant impacts on the urban carbon efficiency with significant spatial spillover effects. The agglomerations of the manufacturing and high-end productive service industries take positive effects on carbon efficiency while the low-end productive and living service industries take negative effects. As a comparison, we found that the agglomeration effects at the level of the megalopolis are greater than those at the national level, especially for the living services industry, in which the higher levels of agglomeration make the effects on carbon efficiency change from negative to positive. The divisions of labor for the central and common cities in the megalopolises are integrated into the industrial agglomeration. Furthermore, the fractional-order grey forecasting model is used in this paper. By the virtue of its advantage in dealing with small sample data which lack statistical rules, this paper makes an out-of-sample prediction of carbon efficiency and industrial agglomeration degree of Chinese cities. By adding the predicted results to the spatial correlation test, new evidence on the spatial correlation of carbon efficiency and spatial division of labor between cities is obtained. Based on the empirical results of the present study, we have proposed some policy recommendations.

Nowadays, rich quantity of information is offered on the Net which makes it hard for the clients to detect necessary information. Programmed techniques are desirable to effectively filter and search useful data from the Net. The purpose of purported text summarization is to get satisfied content handling with information variety. The main factor of document summarization is to extract benefit feature. In this paper, we extract word feature in three group called important words. Also, we extract sentence feature depending on the extracted words. With increasing knowledge on the Internet, it turns out to be an extremely time-consuming, exhausting, and boring mission to read the whole content and papers and get the relevant information on precise topics

Logistics and economic development complement each other. The comprehensive competitiveness of Guangdong provincial economy ranks first in China. Under the influence of COVID-19, the freight development of Guangdong Province has been affected, but there is still lack of quantitative research. It is significant to explore the trend of economic development through the freight development of Guangdong Province. Based on the grey theory model, this paper uses six freight indexes to research freight development of Guangdong Province. Under the assumption that COVID-19 did not happen, we predicted the development value of freight index of Guangdong Province from January to December in 2020 and studied the influence based on the comparison between the predicted value and actual value. The empirical study shows three impact characteristics: stage characteristics, structural characteristics, and entity transmission characteristics. COVID-19 has a negative impact on the development of total freight volume, highway freight volume, waterway freight volume, and air freight volume in Guangdong Province. The influence values were −23.001%, −29.344%, −11.296%, and −3.838%. But, the freight volumes of railway and pipeline were positively affected by 14.343% and 13.057%, respectively, due to their continuity and substitution to other transportation modes. To further explore the abate measures of COVID-19 impact on Guangdong's freight development, the grey correlation model is introduced to study the correlation factors of freight development of Guangdong Province. Through the research of the related factors, this paper puts forward some measures to promote the freight development of Guangdong Province in the postepidemic era. [ABSTRACT FROM AUTHOR] Copyright of Mathematical Problems in Engineering is the property of Hindawi Limited and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Convolution neural network has become a hot research topic in the field of computer vision because of its superior performance in image classification. Based on the above background, the purpose of this paper is to analyze sports sequence images based on convolutional neural network. In view of the low detection rate of single-frame and the complexity of multiframe detection algorithms, this paper proposes a new algorithm combining single-frame detection and multiframe detection, so as to improve the detection rate of small targets and reduce the detection time. Based on the traditional residual network, an improved, multiscale, residual network is proposed in this paper. The network structure enables the convolution layer to “observe” data from different scales and obtain more abundant input features. Moreover, the depth of the network is reduced, the gradient vanishing problem is effectively suppressed, and the training difficulty is reduced. Finally, the ensemble learning method of relative majority voting is used to reduce the classification error rate of the network to 3.99% on CIFAR-10, and the error rate is reduced by 3% compared with the original residual neural network.

China’s regional economic competition is intensifying; in particular, the cluster development of air transport, high-end manufacturing, and modern service industries is closely related to the construction of regional airports. Local governments have listed aviation hubs as the hardcore advantage of high-quality growth in the new era, but it may also lead to excessive convergence and preferential system competition. Based on the “GDP competition” of local governments in China, this paper uses panel data of 78 airports in mainland China from 2001 to 2018 and tries to explore the causes of airport preferential policies. The Synthetic Control Method is used to study the influence of preferential policies on airport passenger and cargo flow, and then the Spatial Durbin Model is used to verify the spatial spillover effect of aviation hubs, which may be magnified by the preferential policies. This paper finds that the impact of preferential policies on airports in central and western China is mainly reflected in the increase of cargo throughput, and there is a spatial siphon effect on cargo throughput between airports. The implementation of the preferential policy enhances this spatial siphon effect, which in turn leads to more fierce competition. The research results show that the preferential policies, issued in central and western aviation economy, have shown a trend of evolving in the direction of vicious competition. Before the airport preferential system produces more negative effects, it should be corrected in time, and each aviation economic zone in the central and western regions should be scientifically coordinated and reasonably planned.

WOS:000672427400001 In today's complex and ever-changing world, concerns about the lack of enough data have been replaced by concerns about too much data for supply chain management (SCM). The volume of data generated from all parts of the supply chain has changed the nature of SCM analysis. By increasing the volume of data, the efficiency and effectiveness of the traditional methods have decreased. Limitations of these methods in analyzing and interpreting a large amount of data have led scholars to generate some methods that have high capability to analyze and interpret big data. Therefore, the main purpose of this paper is to identify the applications of machine learning (ML) in SCM as one of the most well-known artificial intelligence (AI) techniques. By developing a conceptual framework, this paper identifies the contributions of ML techniques in selecting and segmenting suppliers, predicting supply chain risks, and estimating demand and sales, production, inventory management, transportation and distribution, sustainable development (SD), and circular economy (CE). Finally, the implications of the study on the main limitations and challenges are discussed, and then managerial insights and future research directions are given. WOS:000672427400001 Q3

Microscope vision analysis is applied in many fields. The traditional way is to use the human eye to observe and manually focus to obtain the image of the observed object. However, with the observation object becoming more and more subtle, the magnification of the microscope is required to be larger and larger. The method of manual focusing cannot guarantee the best focusing position of the microscope in use. Therefore, in this paper, we are studying the existing autofocusing technology and the autofocusing method of microscope based on image processing, which is different from the traditional manual focusing method. The autofocusing method of microscope based on image processing does not need the information such as the target position and the focal length of optical system, to directly focus the collected image. First of all, in order to solve the problem of large computation and difficult real time of traditional wavelet based image sharpness evaluation algorithm, this paper proposes an improved wavelet based image sharpness evaluation algorithm; secondly, in view of the situation that the window selected by traditional focusing window selection method is fixed, this paper adopts an adaptive focusing window selection method to increase the focusing window. Finally, this paper studies the extremum search strategy. In order to avoid the interference of the local extremum in the focusing curve, this paper proposes an improved hill-climbing algorithm to achieve the accuracy of focusing search. The simulation results show that the improved wavelet transform image definition evaluation algorithm can improve the definition evaluation performance, and the improved mountain climbing algorithm can reduce the impact of local extremum and improve the accuracy of the search algorithm. All in all, it can be concluded that the method based on image processing proposed in this paper has a good focusing effect, which can meet the needs of anti-interference and extreme value search of microscope autofocus.

To push forward the development of electric vehicles while improving the economy and environment of virtual power plants (VPPs), research on the optimization of VPP capacity considering electric vehicles is carried out. In this paper, based on this, this paper first analyzes the framework of the VPP with electric vehicles and models each unit of the VPP. Secondly, the typical scenarios of wind power, photovoltaic, electric vehicle charging and discharging, and load are formed by the Monte Carlo method to reduce the output deviation of each unit. Then, taking the maximization of the net income and clean energy consumption of the VPP as the objective function, the capacity optimal allocation model of the VPP considering multiobjective is constructed, and the conditional value-at-risk (CVaR) is introduced to represent the investment uncertainty faced by the VPP. Finally, a VPP in a certain area of Shanxi Province is used to analyze a calculation example and solve it with CPLEX. The results of the calculation example show that, on the one hand, reasonable selection of the optimal scale of EV connected to the VPP is able to improve the economy and environment of the VPP. On the other hand, the introduction of CVaR is available for the improvement of the scientific nature of VPP capacity allocation decisions.

Sports video is loved by the audience because of its unique charm, so it has high research value and application value to analyze and study the video data of competition. Based on the background of football match, this paper studies the football detection and tracking algorithm in football game video and analyzes the real-time image of real-time mobile devices in sports video augmented reality. Firstly, the image is preprocessed by image graying, image denoising, image binarization, and so on. Secondly, Hough transform is used to locate and detect football, and according to the characteristics of football, Hough transform is improved. Based on the good performance of SIFT algorithm in feature matching, a football tracking algorithm based on SIFT feature matching is proposed, which matches the detected football with the sample football. The simulation results show that the improved Hough transform can effectively detect football and has good antijamming performance. And the designed football tracking algorithm based on SIFT feature matching can accurately track the football trajectory; therefore, the football detection and tracking algorithm designed in this paper is suitable for real-time football monitoring and tracking.

Recent years have witnessed the use of metaheuristic algorithms to solve the optimization problems that usually require extensive computations and time. Among others, scatter search is the widely used evolutionary metaheuristic algorithm. It uses the information of global optima, which is stored in a different and unique set of solutions. In this paper, an updated review of scatter search (SS) is given. SS has been successfully applied in a variety of research problems, namely, data mining, bioinformatics, and engineering design. This paper presents the modified and hybrid versions of SS with their applications. The control strategies are discussed to show their impact on the performance of SS. various issues and future directions related to SS are also discussed. It inspires innovative researchers to use this algorithm for their research domains.

Language and vision are the two most essential parts of human intelligence for interpreting the real world around us. How to make connections between language and vision is the key point in current research. Multimodality methods like visual semantic embedding have been widely studied recently, which unify images and corresponding texts into the same feature space. Inspired by the recent development of text data augmentation and a simple but powerful technique proposed called EDA (easy data augmentation), we can expand the information with given data using EDA to improve the performance of models. In this paper, we take advantage of the text data augmentation technique and word embedding initialization for multimodality retrieval. We utilize EDA for text data augmentation, word embedding initialization for text encoder based on recurrent neural networks, and minimizing the gap between the two spaces by triplet ranking loss with hard negative mining. On two Flickr-based datasets, we achieve the same recall with only 60% of the training dataset as the normal training with full available data. Experiment results show the improvement of our proposed model; and, on all datasets in this paper (Flickr8k, Flickr30k, and MS-COCO), our model performs better on image annotation and image retrieval tasks; the experiments also demonstrate that text data augmentation is more suitable for smaller datasets, while word embedding initialization is suitable for larger ones.

In this paper, an improved bidirectional RRT ∗ vehicle path planning method for smart vehicle is proposed. In this method, the resultant force of the artificial potential field is used to determine the search direction to improve the search efficiency. Different kinds of constraints are considered in the method, including the vehicle constraints and the vehicle driving environment constraints. The collision detection based on separating axis theorem is used to detect the collision between the vehicle and the obstacles to improve the planning efficiency. The cubic B-spline curve is used to optimize the path to make the path’s curvature continuous. Both simulation and experiment are implemented to verify the proposed improved bidirectional RRT ∗ method. In the simulation analysis, this paper’s method can generate the smoothest path and takes the shortest time compared with the other two methods and it can be adaptive to the complicated environment. In the real vehicle experiment, we can see from the test results that this paper’s method can be applied in practice on the smart electric vehicle platform; compared with others’ algorithm, this paper’s algorithm can generate shortest and smoothest path.

This paper examines how investment in intellectual capital (IC) elements by textile and apparel companies improves firm performance measured in terms of profitability, market value, and productivity. The modified value-added intellectual coefficient (MVAIC) model is applied to measure IC. Using a panel of 35 Chinese textile and apparel companies for a six-year period (2013–2018), the results show that physical and human capitals are the strong factors that contribute to firm performance. In addition, relational capital negatively influences profitability and market value, and structural capital and innovation capital have a negative impact on employee productivity. We also find that the MVAIC model performs better in measuring IC than the original value-added intellectual coefficient (VAIC) model. This paper can provide some insights for corporate managers to enhance firm performance and gain competitive advantage by proper utilization of IC in traditional industries.

Promoting economic development and improving people’s quality of life have a lot to do with the continuous improvement of cloud computing technology and the rapid expansion of applications. Emotions play an important role in all aspects of human life. It is difficult to avoid the influence of inner emotions in people’s behavior and deduction. This article mainly studies the personalized emotion recognition and emotion prediction system based on cloud computing. This paper proposes a method of intelligently identifying users’ emotional states through the use of cloud computing. First, an emotional induction experiment is designed to induce the testers’ positive, neutral, and negative three basic emotional states and collect cloud data and EEG under different emotional states. Then, the cloud data is processed and analyzed to extract emotional features. After that, this paper constructs a facial emotion prediction system based on cloud computing data model, which consists of face detection and facial emotion recognition. The system uses the SVM algorithm for face detection, uses the temporal feature algorithm for facial emotion analysis, and finally uses the classification method of machine learning to classify emotions, so as to realize the purpose of identifying the user’s emotional state through cloud computing technology. Experimental data shows that the EEG signal emotion recognition method based on time domain features performs best has better generalization ability and is improved by 6.3% on the basis of traditional methods. The experimental results show that the personalized emotion recognition method based on cloud computing is more effective than traditional methods.

To solve the problem of real-time arrhythmia classification, this paper proposes a real-time arrhythmia classification algorithm using deep learning with low latency, high practicality, and high reliability, which can be easily applied to a real-time arrhythmia classification system. In the algorithm, a classifier detects the QRS complex position in real time for heartbeat segmentation. Then, the ECG_RRR feature is constructed according to the heartbeat segmentation result. Finally, another classifier classifies the arrhythmia in real time using the ECG_RRR feature. This article uses the MIT-BIH arrhythmia database and divides the 44 qualified records into two groups (DS1 and DS2) for training and evaluation, respectively. The result shows that the recall rate, precision rate, and overall accuracy of the algorithm’s interpatient QRS complex position prediction are 98.0%, 99.5%, and 97.6%, respectively. The overall accuracy for 5-class and 13-class interpatient arrhythmia classification is 91.5% and 75.6%, respectively. Furthermore, the real-time arrhythmia classification algorithm proposed in this paper has the advantages of practicability and low latency. It is easy to deploy the algorithm since the input is the original ECG signal with no feature processing required. And, the latency of the arrhythmia classification is only the duration of one heartbeat cycle.