Search

Recommender system plays a supporting role in the process of information filtering. It plays a remarkable role in large-scale online shopping and product suggestions. This paper discusses various trends of recommender system such as content-based, collaborative-based and hybrid personalization techniques proposed for recommendations. It provides better insight and future directions of recommender systems. We have reviewed 142 articles from several journals and conference papers which were published from 1992 to 2019. We have used statistical descriptions to show the progression and drawbacks of the various notions of recommendation approaches. We have also discussed growing research demand in the area of recommender systems as well as the pros and cons of the currently available classifications. We have created a classification of recommender techniques, including various user inputs, knowledge from the database, the ways in which the recommendation will be presented to the user and the technologies which are used to create the recommendations. [ABSTRACT FROM AUTHOR]

Logistics refers to the process of moving goods or materials from the point of origin to the point of destination, with the utilization of various resources including personnel, vehicles, facilities and equipment. In the paper entitled "Robust multi-product inventory optimization under support vector clustering-based data-driven demand uncertainty set", a robust multi-product inventory optimization approach is developed with an uncertainty set constructed from the available data using support vector clustering. Product sales forecasting would directly impact inventory management and customer service level and thus plays an important role in logistics systems. [Extracted from the article]

In the paper, I Traffic flow guidance algorithm in intelligent transportation systems considering the effect of non i - I floating vehicle i , Chen et al. ([4]) present the method of estimating non-floating vehicles' driving information according to floating vehicles' information. The authors presented the estimation method, a new traffic flow guidance algorithm, Estimated Weighted Vehicle Density Feedback Strategy (EWVDFS) based on Weighted Vehicle Density Feedback Strategy (WVDFS). In the paper, A I robust lane detection method based on hyperbolic model i , Li et al. ([9]) investigated a robust lane detection method under structured roads. The paper I Road network i - I based region of interest mining and social relationship recommendation i by Tan and Zhang ([17]) proposed road context-based active region extraction algorithm (RAREA) which explores the method to extract the specific regions within the road network. [Extracted from the article]

The paper by Ma et al. ([20]) investigates the supply chain coordination issues arising out of a green supply chain consisting of a manufacturer and a retailer under a cost-sharing contract with uncertain information. 20 Ma N, Gao R, Wang X, Li P. Green supply chain analysis under cost sharing contract with uncertain information based on confidence level. 30 Yang S, Ding P, Wang G, Wu X. Green investment in a supply chain based on price and quality competition. 33 Zhang P, Liu Y, Yang G, Zhang G. A distributionally robust optimization model for designing humanitarian relief network with resource reallocation. [Extracted from the article]

Paper " B Combinatorial design of the MAUT and PAMSSEM II methods for multiple attributes group decision making with probabilistic linguistic information b " looks at the use of probabilistic linguistic term sets in multiple attribute group decision making when the weights are unknown. The special issue focuses on various fuzzy summability techniques that are used in a variety of scientific, engineering, and technological fields. The guest editor wishes to express his heartfelt appreciation to Editors-in-Chief, Special Issue Editor, and other editorial staff members of "Soft Computing" for providing and supporting the opportunity to publish this special issue. Paper " B Cold start aware hybrid recommender system approach for E-commerce users b " proposes a methodological approach called sparsity and cold start aware hybrid recommended system (SCSHRS) to suppress data sparsity and cold start problems in the recommendation system. [Extracted from the article]

We have encouraged our authors to present multidisciplinary research papers in this special issue and present papers which are directly or indirectly related to pattern recognition and computer vision. This special issue is on topics of pattern recognition and computer vision, along with their applications in different domains and systems in different environments. [Extracted from the article]

This paper develops an integrated framework to forecast the volatility of crude oil prices by considering the impacts of extreme events (structural breaks). The impacts of extreme events are vital to improving prediction accuracy. Aiming to demonstrate the crude oil price fluctuation and the impacts of external events, this paper employs the complementary ensemble empirical mode decomposition (CEEMD). It decomposes the crude oil price into some constituents at various frequencies to extract a market fluctuation, a shock from extreme events and a long-term trend. The shock from extreme events is found to be the most crucial element in deciding the crude oil prices. Then we combine the iterative cumulative sum of squares (ICSS) test with the Chow test to get the structural breaks and analyze the extreme event impacts. Finally, this paper combines the structural breaks, the autoregressive integrated moving average (ARIMA) model, and the support vector machine (SVM) to make a forecast of the crude oil prices. The empirical process proves that the CEEMD-ARIMA-SVM model with structural breaks performs the best when compared with the other ARIMA-type models and SVM-type models. The framework offers an insightful view to help decision-makers and can be used in many areas. [ABSTRACT FROM AUTHOR]

With the rapid development of communication technology, the optimization of communication protocol, as a new generation of intelligent traffic system technology, has attracted more and more attention, in particular, the communication technology in traffic. In the authentication protocol of this paper, the symmetric cipher algorithm ZUC and the asymmetric cryptographic algorithm RSA are used as the cryptographic algorithms of the protocol. RSA is used to decrypt digital signatures for messages. In the current communication scheme, node communication does not have scalability and communication requirements in different scenarios, and a population key negotiation communication protocol was proposed in this paper. Employing the kana and random key parameters of the nodes in the roadside cell group, 3 communication protocols for group broadcasting, group to vehicle communication, and RSU communication between groups were designed. The results show that the protocol can meet the security requirements of network communication. The results show that the communication protocol in this paper is safe and reliable. At last, the communication efficiency of communication protocol is analyzed using communication overhead and average delay. The proposed protocol is an efficient communication protocol and the scheme is superior to other schemes in terms of communication overhead and average delay. [ABSTRACT FROM AUTHOR]

This paper presents a new hybrid genetic-particle swarm optimization (GPSO) algorithm for solving multi-constrained optimization problems. This algorithm is different from the traditional GPSO algorithm, which adopts genetic algorithm (GA) and particle swarm optimization (PSO) in series, and it combines PSO and GA through parallel architecture, so as to make full use of the high efficiency of PSO and the global optimization ability of GA. The algorithm takes PSO as the main body and runs PSO at the initial stage of optimization, while GA does not participate in operation. When the global best value (gbest) does not change for successive generations, it is assumed that it falls into local optimum. At this time, GA is used to replace PSO for particle selection, crossover and mutation operations to update particles and help particles jump out of local optimum. In addition, the GPSO adopts adaptive inertia weight, adaptive mutation parameters and multi-point crossover operation between particles and personal best value (pbest) to improve the optimization ability of the algorithm. Finally, this paper uses a nonlinear constraint problem (Himmelblau's nonlinear optimization problem) and three structural optimization problems (pressure vessel design problem, the welded beam design problem and the gear train design problem) as test functions and compares the proposed GPSO with the traditional GPSO, dingo optimization algorithm, whale optimization algorithm and grey wolf optimizer. The performance evaluation of the proposed algorithm is carried out by using the evaluation indexes such as best value, mean value, median value, worst value, standard deviation, operation time and convergence speed. The comparison results show that the proposed GPSO has obvious advantages in finding the optimal value, convergence speed and time overhead. [ABSTRACT FROM AUTHOR]

Under the continuous development of China's social economy, the Internet and multimedia technology have been developed and innovated and are widely used in all walks of life and all fields. Because of their powerful interactivity, effectiveness, and dynamism, combining them with colleges and universities' English teaching plays an essential role in enriching teaching resources and improving teaching efficiency and quality. This paper proposes an improved LSTM model based on the web and multimedia environment, which improves the prediction effect of neural networks by adding an attention mechanism to the LSTM layer. The attention mechanism is based on a decision support system that automates the availability of various teaching resources to ensure an interactive teaching and learning environment in the colleges and universities. The decision support system of attention mechanism enhances the model's generalization ability by tuning the model parameters with the genetic algorithm (GA). Finally, this paper proposes some suggestions on improving the effectiveness of teaching English as a foreign language in the online and multimedia environment, taking into account the popular MU teaching format and English APP. The results show that the improved LSTM model outperforms the existing models in terms of various performance metrics. [ABSTRACT FROM AUTHOR]

Big data technology has undoubtedly accelerated the efficiency of data processing, made data become an important reference basis in enterprise operation, and changed the mode of enterprise operation as well as the existing business model. With the development of computer technology and related equipment, more and more enterprises and organizations can begin to use big data processing technology. However, many small and medium-sized enterprises, because they cannot afford the high cost of research and development and leasing, are gradually eliminated in the information-based business competition, so it is necessary to adopt certain strategies to help small and medium-sized enterprises out of this crisis. For fragmented big data obtained from different data sources, this paper adopts load-balancing technology to provide horizontal service cluster scalability and designs a separate system module for routine testing. The experimental results show that the improved big data processing system based on genetic algorithm in this paper can better meet the business needs of small and medium-sized enterprises and meet the application needs of small and medium-sized enterprises. The simulation results also show the advantages of the system in this paper, which is faster, higher accuracy, less energy consumption, lower requirements for equipment, and more suitable for small and medium-sized enterprises. This paper designs a kind of effective big data processing system by studying genetic algorithm and computer technology. [ABSTRACT FROM AUTHOR]

When constructing the algorithm model of sports training action classification, the accuracy of action classification has an important impact on the algorithm model. How to improve the algorithm model to improve the accuracy of sports training action classification needs further research. Based on BP neural network algorithm, this paper carries out the modeling of BP neural network signal classification algorithm and the construction of BP neural network, and deduces the BP algorithm in detail. Firstly, this paper applies genetic algorithm to the initial parameter selection of BP algorithm to avoid the local optimization problem. When carrying out chromosome coding, binary coding is easy to cause the problem of too long coding string, which also needs to be restored and decoded. The algorithm runs too long and the learning accuracy is not high. Therefore, this paper uses real coding. Through simulation analysis, it can be seen that the classification accuracy of the improved algorithm model is significantly higher than that of the simple BP algorithm. In addition, this paper analyzes the requirements of the sports training management visualization system, introduces the system structure framework and network topology, describes in detail the functions of the user information management module, the training plan management module, the training test management module, the competition information management module and the scientific research information management module, and tests the visualization function of the system. Finally, this paper analyzes the problems existing in the current sports training management, and puts forward the development strategy of sports training management based on this, which lays a theoretical foundation for the scientific development of sports training. [ABSTRACT FROM AUTHOR]

At present, wearable devices have some problems, such as poor adaptability to human motion behavior, and the recognition accuracy required for different wearers cannot be achieved. Based on the principle of deep learning algorithm, this paper realizes the development of intelligent rope skipping movement data monitoring system. Through the universal human body analysis model, the attention mechanism is introduced and embedded into the decoding network. The data set of rope skipping is classified by multiple labels, and the convolution of spatial graph is constructed, which is extended to the time series dynamics of moving human skeleton data. Aiming at the problem of complex information data in the process of moving human body recognition, we use pose estimation to calculate the key points of moving human body, extract the dynamic structure information of human skeleton sequence. Due to the problems of line of sight occlusion in the process of moving human target tracking, a target tracking algorithm based on multi domain convolution neural network is adopted to improve the feature extraction ability of the algorithm by segmenting the target to be tracked and identifying the area around the target. The data set of rope skipping is collected by wearable sensors, and the difference in the numerical range may be large, so the data is normalized. Finally, through the loss function, the fitting effect of neural network can be evaluated, and the gradient optimization model parameters can be calculated, and coping with different data changes. Through the final system performance test, it is verified that the accuracy rate of the system designed in this paper is above 90%, which can effectively monitor the data of skipping rope and be used in the actual operation of skipping rope. [ABSTRACT FROM AUTHOR]

In March 2018, the State Council issued a reform plan for institutions. Through the establishment of the Ministry of natural resources, the planning of the national space system was carried out, and the historical division phenomenon within the administrative institutions was solved by using the transformation of fragmentation. Subsequently, relevant functional departments began to design the land spatial planning system and coordinate the mechanism. From the policy guidance, it can be seen that land use spatial planning has risen to the central position in the national management system. From the current situation of planning control, planning control becomes more and more important in the management process. At the same time, the construction of ecological civilization requires us to examine the regulatory mechanism from a new perspective. Therefore, based on machine vision technology, this paper develops a land use spatial planning method system. The sub-pixel edge detection algorithm used in the system design can obtain the point coordinates on the edge of the gauge block with high accuracy. After testing, we can see that in terms of storage space, the octree map used in this paper can save more space than the point cloud map under the same resolution. The data results obtained from the test are also better than the existing system, indicating that the machine vision spatial planning system studied in this paper can better serve the field of land and resources planning. [ABSTRACT FROM AUTHOR]

Textual emotion recognition is an increasingly popular research area, which recognizes human emotions by capturing textual information posted by people, and the recognition results depend on the composition of the system framework. In this paper, we propose a textual emotion recognition method based on ALBERT-BiLSTM model and SVM-NB classification. Firstly, the text is pre-processed based on ALBERT pre-training model. Then, the word vector-related features are obtained by BiLSTM Recurrent Neural Network for machine learning to make them have a specific form for classification in order to improve the accuracy of emotion recognition. In the link of emotion classification, this paper innovatively proposes a classification method SVM-NB to obtain more emotional polarities. Finally, the classifier is used to obtain the emotional polarities of the text, including positive and negative categories. The negative emotions are divided into three sub-categories of anger, sad and disgust. The experiments show that the proposed emotion recognition method has better robustness and higher accuracy than the general modal recognition method. [ABSTRACT FROM AUTHOR]

In recent years, the cuckoo search (CS) algorithm has been successfully applied to single-objective optimization problems. But in real life, most optimization problems are multi-objective optimization problems (MOPs). In order to enable CS to better solve MOPs, this paper proposes an elite-guided multi-objective cuckoo search algorithm based on cross-operation and information enhancement (CIE-MOCS). This algorithm first enhances its population diversity through crossover operation, then adds elite individuals to guide its update process to speed up the algorithm convergence speed. Finally, the method of information enhancement is adopted in the abandonment process, so that the algorithm is not easy to fall into the local optimum. In order to verify the performance of the algorithm, this paper uses a variety of benchmark functions and performance evaluation indicators to evaluate it, and provides a case to verify the effectiveness of the algorithm in practical applications. The experimental results show that CIE-MOCS has good performance compared with the contrasting algorithms. [ABSTRACT FROM AUTHOR]

The main purpose of this paper is to solve the deadlock problem encountered by the algorithm in robot path planning, so as to improve the efficiency of the algorithm. Therefore, two strategies are proposed in this paper to help the algorithm solve the common deadlock problem. First, a deadlock prediction strategy based on connectivity detection is proposed to preprocess the map. The deadlock region is filled by the image processing method. Second, a dynamic backtracking strategy is proposed to help the algorithm exit quickly in the deadlock region to complete the task. With these two strategies, even if the deadlock region is large, the algorithm can get the result quickly. This paper takes the ant colony algorithm as an example to demonstrate the deadlock strategy. By comparing with other algorithms, it can be found that the optimization rate of the proposed strategy is up to 5.96% and 88.5% for the optimal path and the number of iterations, respectively. [ABSTRACT FROM AUTHOR]

At present, the COVID-19 epidemic is still spreading at home and abroad, and the foreign exchange market is highly volatile. From financial institutions to individual investors, foreign exchange asset allocation has become important contents worthy of attention. However, most intelligent optimization algorithms (hereinafter IOAS) adopt the existing data and ignore the forecasted one in the foreign exchange portfolio allocation, which will result in a huge difference between portfolio allocation and actual demand; at the same time, many IOAS are less adaptable and have lower optimization ability in portfolio problems. To solve the aforementioned problems, this paper first proposed a DETS based on hybrid tabu search and differential evolution algorithms (DEAs), which has excellent optimization ability. Subsequently, the DETS algorithm was applied to support vector machine (SVM) model. Experiments show that, compared with other algorithms, the MAE and RMSE obtained by using DETS optimization parameters are reduced by at least 3.79 and 1.47%, while the CTR is improved by at least 2.19%. Then combined with the DETS algorithm and Pareto sorting theory, an algorithm suitable for multi-objective optimization was further proposed, named NSDE-TS. Finally, by applying NSDE-TS algorithm, the optimal foreign exchange portfolio is acquired. The empirical analysis shows that the Pareto front obtained by this algorithm is better than that of NSGA-II. Since the lower the uniformity index and convergence index, the stronger the optimization performance of the corresponding algorithm, compared with NSGA-II, its uniformity and convergence index decreased by 15.7 and 39.6%. [ABSTRACT FROM AUTHOR]

The growing concern about the influences of anthropogenic pollutions has forced researchers and scholars to study the environmental concerns. This paper addresses a joint daily route and speed optimization problem in home health care (HHC) with the constraints of synchronized visits and carbon emissions. In this work, the aim is to design a reasonable logistics route with the objective of minimizing the carbon emissions, which has a linear relationship with fuel consumption. This goal can reduce environmental pollution while optimizing operating costs for the HHC company. This paper formulated the problem as a mixed-integer programming (MIP) model and used the Gurobi solver to solve the MIP model with a time limit of 1 h. However, the method based on the MIP model is difficult to solve large-scale instances. Therefore, this paper proposed an ant colony optimization (ACO)-based heuristic approach improved by local search for this problem with large-scale instances. The minimal carbon emissions of each route is calculated by a dynamic programming (DM) algorithm. We designed three kinds of experiments to test the proposed approach, including the basic vehicle routing problem with time window (VRPTW), the studied problem with one speed and the studied problem with two speeds. The experimental results highlight the effectiveness and efficiency of the proposed approach. [ABSTRACT FROM AUTHOR]

As the main carrier of Chinese civilization, the importance of ancient Chinese documents cannot be overstated. However, the phenomenon of "Heavy storage and light use" is serious in modern society. In order to improve the utilization of its content, and to improve the difficult recognition problem caused by the complex character glyphs and diverse styles of Chinese characters in ancient books, as well as the single and double column mismatch and the different sizes of Chinese characters, in this paper, we propose an adaptive receptive field-based image recognition network for Chinese ancient characters. The network fully considers the high sensitivity of residual dense network to data fluctuation and uses selective convolution kernel to construct residual dense blocks to provide a dynamic selection mechanism for the receptive fields of different images, so that it can focus on the fine structure of Chinese characters and thus realize cross-channel information interaction and integration. The experimental results show that the accuracy and precision of recognition using this paper's network can reach 93.48% and 95.37%, which is a significant improvement compared with other recognition methods, and proves that SKRDN has good advantages in dealing with the recognition problem of ancient Chinese characters. [ABSTRACT FROM AUTHOR]

In the lung computer-aided detection (Lung CAD) system, the region of interest (ROI) of lung nodules has more false positives, making the imbalance between positive and negative (true positive and false positive) samples more likely to lead to misclassification of true positive nodules, a cost-sensitive multikernel learning support vector machine (CS-MKL-SVM) algorithm is proposed. Different penalty coefficients are assigned to positive and negative samples, so that the model can better learn the features of true positive nodules and improve the classification effect. To further improve the detection rate of pulmonary nodules and overall recognition accuracy, a score function named F-new based on the harmonic mean of accuracy (ACC) and sensitivity (SEN) is proposed as a fitness function for subsequent particle swarm optimization (PSO) parameter optimization, and a feasibility analysis of this function is performed. Compared with the fitness function that considers only accuracy or sensitivity, both the detection rate and the recognition accuracy of pulmonary nodules can be improved by this new algorithm. Compared with the grid search algorithm, using PSO for parameter search can reduce the model training time by nearly 20 times and achieve rapid parameter optimization. The maximum F-new obtained on the test set is 0.9357 for the proposed algorithm. When the maximum value of F-new is achieved, the corresponding recognition ACC is 91%, and SEN is 96.3%. Compared with the radial basis function in the single kernel, the F-new of the algorithm in this paper is 2.16% higher, ACC is 1.00% higher and SEN is equal. Compared with the polynomial kernel function in the single kernel, the F-new of the algorithm is 3.64% higher, ACC is 1.00% higher and SEN is 7.41% higher. The experimental results show that the F-new, ACC and SEN of the proposed algorithm is the best among them, and the results obtained by using multikernel function combined with F-new index are better than the single kernel function. Compared with the MKL-SVM algorithm of grid search, the ACC of the algorithm in this paper is reduced by 1%, and the results are equal to those of the MKL-SVM algorithm based on PSO only. Compared with the above two algorithms, SEN is increased by 3.71% and 7.41%, respectively. Therefore, it can be seen that the cost sensitive method can effectively reduce the missed detection of nodules, and the availability of the new algorithm can be further verified. [ABSTRACT FROM AUTHOR]

In the paper Crucial and unsolved problems on Atanassov’s intuitionistic fuzzy sets, D.-F. Li pointed out that some kind of definitions of operations over Atanassov’s intuitionistic fuzzy sets are incorrect. We can see that, near 30 years after the first Atanassov’s papers, there exist some misunderstandings related not only on the name, but also on the basic operations on IFSs. Those misunderstandings concern, this time, on the operations of the sum and product. Li also casts doubt the equivalence of the intuitionistic fuzzy sets and the interval-valued fuzzy sets. In this paper, the Li’s reasoning is presented and commented. [ABSTRACT FROM AUTHOR]

In order to improve the stock price prediction effect, based on the improved PSO algorithm, this paper constructs a stock price prediction model through neural network. Based on the idea of avoiding particles falling into the same local solution as much as possible and always keeping the particles with a certain diversity, in order to improve the global search ability of the algorithm in the early stage of evolution and the local search ability in the later stage of the evolution, the adaptive adjustment of inertial weight is proposed, and the algorithm is improved by combining with neural network. In addition, on the basis of the improved algorithm, this paper constructs a stock price prediction system based on neural network. Finally, this paper designs experiments to verify the function of the model from the perspectives of stock data collection and processing, and stock price prediction accuracy, and draw statistical graphs based on the statistical research results. The results of the research show that the system constructed in this paper has a certain practical effect. [ABSTRACT FROM AUTHOR]

We describe in this paper an approach for predicting the COVID-19 time series in the world using a hybrid ensemble modular neural network, which combines nonlinear autoregressive neural networks. At the level of the modular neural network, which is formed with several modules (ensembles in this case), the modules are designed to be efficient predictors for each country. In this case, an integrator is used to combine the outputs of the modules, in this way achieving the goal of predicting a set of countries. At the level of the ensembles, forming a part of the modular network, these are constituted by a set of modules, which are nonlinear autoregressive neural networks that are designed to be efficient predictors under particular conditions for each country. In each ensemble, the results of the modules are combined with an aggregator to achieve a better and improved result for the ensemble. Publicly available datasets of coronavirus cases around the globe from the last months have been used in the analysis. Interesting conclusions have been obtained that could be helpful in deciding the best strategies in dealing with this virus for countries in their fight against the coronavirus pandemic. In addition, the proposed approach could be helpful in proposing strategies for similar countries. [ABSTRACT FROM AUTHOR]

With the gradual advancement of image sensor technology and the gradual complexity of the application environment, single-source imaging sensors have been difficult to meet practical application requirements. Therefore, the registration and fusion techniques of infrared images and visible images are hot topics in recent years. This article aims to study the fusion of two images. Based on the traditional image fusion algorithm, the color space IHS transform and the lifting wavelet transform are combined according to the characteristics of infrared image and visible light image captured by the UAV imaging device. The experimental results show that the algorithm can not only retain the brightness information of the infrared target. Among them, some details of the visible light image are retained. In this paper, the four objective criteria of information entropy, standard deviation, image mean and average gradient are used to evaluate the fusion effect of the proposed algorithm. The obtained values are 7.285, 29.487, 122.2739, and 4.5678, respectively, which are higher than other algorithms. It can be seen that the algorithm proposed in this paper has important practical significance. [ABSTRACT FROM AUTHOR]

The objective of this paper is to provide an insight on effect of stringency in Covid-19 spread in India especially in Chennai, a city were more lockdown, and restrictions was imposed to control the infection. Even though the restriction was imposed in the country by the end of March 2020, the growth reduction was seen in the mid of June as the awareness was increased. The average Covid-19 case growth was got reduce from 3.43 to 2.62% by July mid. To analysis the impact of stringency, a detailed analysis was done on Chennai city which was imposed with more repeated lockdowns to flatten the curve. We tried to fit a regression line with three difference scenario of data. The results show a promising R-squared and p value, with a right skewed distribution normal probability plot. The impact of lockdown in people's lives in different sectors were also discussed in this paper. [ABSTRACT FROM AUTHOR]

In recent years, the amount of Internet information data has exploded, and the problem of "information overload" has become a huge challenge for Internet development. Through the prior knowledge of the known data distribution, combined with sample training data to estimate the mathematical model of the overall data. Intelligent recommendation methods based on knowledge graphs and Bayesian networks are a hot spot in the current Internet research, and they are of great significance to search engines and e-commerce. This paper studies the fusion of knowledge graph and Bayesian belief network and its application in personalized recommendation and designs a Bayesian network that describes the purchase behavior of users based on the purchase records of customers across the network. User recommendation is the process of fusing knowledge graphs and Bayesian network reasoning. For the design of the recommendation network, a random reasoning algorithm with approximate reasoning is selected in consideration of calculation scale and accuracy. This paper uses the content filtering technology of KNN algorithm to supplement the sparse matrix, which can improve the quality of collaborative filtering recommendation, thereby improving the quality of final recommendation. In this paper, based on the knowledge graph, the EPCA algorithm and the robust recommendation algorithm are merged to form a robust collaborative recommendation model based on Bayesian probability matrix decomposition. The robust recommendation algorithm further improves the robustness of the recommendation algorithm by introducing the suspected users and target items detected by the EPCA algorithm. Research shows that the PS value of the VarSelect SVD algorithm used in this paper is approximately between 0.36 and 1.04. Compared with the first two algorithms, the PS value of VarSelect SVD has been significantly reduced, and the algorithm robustness has been significantly improved. [ABSTRACT FROM AUTHOR]

Multi-attribute decision-making (MADM) is a cognitive process for evaluating data under various attributes in order to find the best option in terms of the preferences of decision makers. Handling uncertainty and vagueness in most real-world decision-making problems involves the application of mathematical tools dealing with uncertainty, such as soft set (SS) theory in decision-making processes. In recent years, different approaches have been suggested for demonstrating the effectiveness and efficiency of soft set theory in MADM. To date, no systematic literature review has been presented in this area. However, a review paper on existing SS-based methods can help future researchers to find the gaps and missing MADM approaches in current studies. In this paper, we review the methodologies and applications of 71 research papers published in 30 academic journals (extracted from online databases including ScienceDirect, Scopus, Springer, World of Scientific, and Hindawi) between January 2000 and December 2017. These papers have been categorized into two main groups: single and hybrid approaches. In addition, they have been classified with respect to MADM techniques, country of origin, journal, and publication year. The statistical analysis shows that "SSAW" method which has been employed by various authors is the most common technique. Moreover, the number of research publications by academics was highest in 2017. In addition, the "Applied Mathematical Modelling" journal and China are ranked as the academic journal and country that have presented the most major contributions in this domain, respectively. [ABSTRACT FROM AUTHOR]

With the improvement of people's requirements for the accuracy of disease detection, increasing researchers apply image recognition to the detection and diagnosis of gastrointestinal diseases. In addition, the evaluation of detection and diagnostic accuracy is also an important factor in the diagnosis and treatment of gastrointestinal diseases. Referring to the QoS and QoE evaluation scheme in 5G network communication, this paper proposes a secondary quality experience evaluation model for gastrointestinal diseases. Firstly, three mandatory detection implementation nodes of 5G network communication are created in the image recognition model, and the first node detects the detected points (images of intestinal diseases) in 5G network communication in the form of interactive information. Then, take the above detection results as the first level to obtain the quality detection strategy results, and the second node uses the policy detection server to evaluate the measurement results as the results of the second level quality evaluation strategy. Finally, the third node is used to evaluate the results of the secondary quality evaluation, and the evaluation results of gastrointestinal disease detection are returned to the output of the whole model. In this paper, 200 CT images of the gastrointestinal tract in the CT colonography dataset were used to evaluate the performance of the model. The study shows that after 200 gastrointestinal CT images are imported into the model, 173 samples have a score of more than 85% for the output of other nodes at the end of the enforcement node, accounting for 86.5% of the sample size. After 24 samples were evaluated by the second level, the output result was the first level scoring error, accounting for 12% of the sample size. Three samples were judged as abnormal images by the first level enforcement node, accounting for 1.5% of the sample size. From the results, the secondary quality experience evaluation model can improve the image recognition accuracy of gastrointestinal disease detection and diagnosis from 86.5% to 98.5%, which greatly improves the accuracy of image recognition. [ABSTRACT FROM AUTHOR]

As one of the indirect causality, cascaded causality can be used to construct the event knowledge graph, causal inference, scenario analysis, etc. The existing GCN methods lack the mining of context information and relevant entity information, resulting in the poor ability of causality inference, which inevitably affects the extraction accuracy of cascade causality. To solve this problem, this paper proposes a causality extraction model based on a two-stage GCN to improve the extraction accuracy. To obtain rich features of entities, this work combines sentiment polarity and knowledge base to get the causality candidate entity library. Firstly, the BERT model is pre-trained using context information and relevant entity information extracted from the entity library to obtain the final entity nodes. Secondly, using the semantic dependency graph, each possible edge between any two entity nodes can be obtained, which are input into the first stage GCN to get a preliminary directed graph of causality. Finally, the directed graph of causality is input into the second stage GCN to achieve deep causality multi-hop inference. Thus, the cascade causality is inferred and extracted by the two-stage GCN model. Experiments show that the extraction accuracy of cascade causality has been further improved. [ABSTRACT FROM AUTHOR]

Two goals of multi-objective evolutionary algorithms are effectively improving their convergence and diversity and making the Pareto set evenly distributed and close to the real Pareto front. At present, the challenges to be solved by the multi-objective evolutionary algorithm are to improve the convergence and diversity of the algorithm, and how to better solve functions with complex PF and/or PS shapes. Therefore, this paper proposes a gray wolf optimization-based self-organizing fuzzy multi-objective evolutionary algorithm. Gray wolf optimization algorithm is used to optimize the initial weights of the self-organizing map network. New neighborhood relationships for individuals are built by self-organizing map, which can maintain the invariance of feature distribution and map the structural information of the current population into Pareto sets. Based on this neighborhood relationship, this paper uses the fuzzy differential evolution operator, which constructs a fuzzy inference system to dynamically adjust the weighting parameter in the differential operator, to generate a new initial solution, and the polynomial mutation operator to refine them. Boundary processing is then conducted. Experiments on 15 problems of GLT1-6 and WFG1-9 and the algorithm proposed in this paper achieve the best on 18 values. And the result shows that the convergence and diversity of the proposed algorithm are better than several state-of-the-art multi-objective evolutionary algorithms. [ABSTRACT FROM AUTHOR]

Fuzzy neural networks have seen an increasing presence in state-owned enterprise performance evaluation. Fuzzy-based financial and non-financial indicators are combined to evaluate state-owned enterprise performance. In this paper, a combination model is proposed for enterprise performance evaluation. This model is built using fuzzy neural network and uses the fuzzy method along with the neural network's self-learning ability to reduce the impact of subjective factors on the evaluation results while realizing intelligent enterprise performance evaluation. First, this paper proposes construction ideas and principles for the state-owned enterprise' performance evaluation index system and then examines its efficiency. There are two types of indicators in the system: financial and non-financial. The Takagi-Sugeno fuzzy neural network is used to build a financial indicator model. The BP neural network is used to construct a non-financial indicator model for a state-owned enterprise performance evaluation portfolio model based on fuzzy neural networks. Both these networks use a decision support system during the process of building the model. Finally, a comparison is made between the results from Takagi-Sugeno fuzzy neural network and those from the BP neural network performance evaluation model after sample data have been selected, standardization processing has been applied, and a simulation of the network model has been trained. The experiments show that the combined model can be used to evaluate the performance of state-owned enterprises which opens a new direction for evaluating enterprise performance. [ABSTRACT FROM AUTHOR]

High-resolution remote sensing images have the characteristics of complex background environment, clustering of objects, etc., the complex background makes the remote sensing image contain a large number of irrelevant ground objects with a high similarity or overlap, which makes the edge and texture of the objects not clear enough, and this leads to low recognition accuracy of ground objects such as airports, dams, and golf field, although the size of this object is large. Based on this problem, this paper proposes a remote sensing image object detection method based on the YOLOv5 network. By improving the backbone extraction network, the network structure can be deepened to get more information about large objects, and the detection effect can be improved by adding an attention mechanism and adding an output layer to enhance feature extraction and feature fusion. The pre-training weight is obtained by transfer learning and used as the training weight of the improved YOLOv5 to speed up the network convergence. The experiment is carried out on the DIOR dataset, the results show that the improved YOLOv5 network can significantly improve the accuracy of large object recognition compared with the YOLO series network and the EfficientDet model on DIOR dataset, and the mAP of the improved YOLOv5 network is 80.5%, which is 2% higher than the original YOLOv5 network. [ABSTRACT FROM AUTHOR]

The identification of germ integrity is very important for the study of germ rice grains. However, the traditional algorithms lack to achieve better recognition results. This article proposes a specific germ integrity detection model that improves the inception-resnet v1 model and adopts topological structure branch of inception-v4. The proposed model dilates the convolution based on the original model that gives an explicit description of image features for germ rice. The proposed scheme achieves the better approximation of abstract representations for potential space. Simultaneously, this paper is based on color image features for germ rice to identify its image location. Afterward, the rice germ gathered in the training will be unified its location by image rotation in accordance with the location information of germ. The proposed model is increasing the identification precision of rice germ integrity. It further strengthens the training of germ detail features. The experiment result shows that comprehensive recognition accuracy in this paper is up to 90.43%, compared with other traditional recognition methods, the algorithm accuracy has highly improved. [ABSTRACT FROM AUTHOR]

Efficient resource scheduling is one of the most critical issues for big data centers in clouds to provide continuous services for users. Many existing scheduling schemes based on tasks on virtual machine (VM), pursued either load balancing or migration cost under certain response time or energy efficiency, which cannot meet the true balance of the supply and demand between users and cloud providers. The paper focuses on the following multi-objective optimization problem: how to pay little migration cost as much as possible to keep system load balancing under meeting certain quality of service (QoS) via dynamic VM scheduling between limited physical nodes in a heterogeneous cloud cluster. To make these conflicting objectives coexist, a joint optimization function is designed for an overall evaluation on the basis of a load balancing estimation method, a migration cost estimation method and a QoS estimation method. To optimize the consolidation score, an array mapping and a tree crossover model are introduced, and an improved genetic algorithm (GA) based on them is proposed. Finally, empirical results based on Eucalyptus platform demonstrate the proposed scheme outperforms exiting VM scheduling models. [ABSTRACT FROM AUTHOR]

Focusing on non-iterative approaches in training feed-forward neural networks, this special issue includes 12 papers to share the latest progress, current challenges, and potential applications of this topic. This editorial presents a background of the special issue and a brief introduction to the 12 contributions. [ABSTRACT FROM AUTHOR]

The physical movement of the human hand produces gestures, and hand gesture recognition leads to the advancement in automated vehicle movement system. In this paper, the human hand gestures are detected and recognized using convolutional neural networks (CNN) classification approach. This process flow consists of hand region of interest segmentation using mask image, fingers segmentation, normalization of segmented finger image and finger recognition using CNN classifier. The hand region of the image is segmented from the whole image using mask images. The adaptive histogram equalization method is used as enhancement method for improving the contrast of each pixel in an image. In this paper, connected component analysis algorithm is used in order to segment the finger tips from hand image. The segmented finger regions from hand image are given to the CNN classification algorithm which classifies the image into various classes. The proposed hand gesture detection and recognition methodology using CNN classification approach with enhancement technique stated in this paper achieves high performance with state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Nontraditional manufacturing processes (NTMPs) bring the processing capabilities such as machining high strength and hard materials with desired accuracies and surface finish to the manufacturing companies. Therefore, there has been a significant increase in the use and number of NTMPs. Hence, choosing a particular NTMP for a specific application turns out to be a complex decision-making problem, which involves conflicting qualitative and quantitative ranking criteria. In recent NTMP ranking literature, it is noted that fuzzy approaches are better suited for handling uncertainties and incomplete information that exist within the NTMP ranking environment. This paper introduces such a fuzzy approach using the hesitant fuzzy preference selection index (PSI) method for the assessment of the criteria weights and the hesitant fuzzy correlation coefficient principle for ranking and recommending the most appropriate NTMP for a specific application. The proposed methodology and its efficiency in dealing with incomplete information under the fuzzy decision-making environment are explored with a case study. As a result of the study, the proposed model preferred the electron beam machining (EBM) as the most suitable nontraditional manufacturing process. On the other hand, triangular fuzzy TOPSIS methods offered the electrochemical machining (ECM) as the best choice among the alternatives. The differences among the ranking decisions are also analyzed in the paper. It can be concluded from the authors' various applications of the proposed hesitant fuzzy PSI method that it is extremely effective in representing fuzzy decision-making environments in NTMP ranking decisions. [ABSTRACT FROM AUTHOR]

In this current era, the field of robotics has made much advancement and has also produced novelties than any other advanced research areas. The usage of robots has become an imperative part of the defense-oriented applications. The missions which are difficult to be performed by human beings can certainly be accomplished by the robots nowadays. The most crucial part for an industrial- and defense-based robot is to perform pose movements accurately for optimal usage of robotics as a replacement of human beings. This paper proposes a comprehensive introduction to the proposed hybrid approach PSO–RL which uses reinforcement learning (RL) and Particle swarm optimization (PSO). It summarizes the usage of proposed PSO-RL for pose measurement of robots in defense and industrial manufacturing systems. The hybrid PSO–RL is a promising technique for measuring poses in robots with accuracy and for optimizing obstacle avoidance error. In this paper, robot's core movements are analyzed; speed of movements is given importance, and an attempt is made to provide more accurate moves with high precision. In order to optimize the efficiency of robotic operations, a full freedom pose measurement method based on PSO–RL is proposed. By using the characteristics of two-wheel independent driving industrial robot, the performance of the robot in three moving modes is evaluated. The experimental results show that the proposed PSO-RL method has the advantages of high accuracy, high measurement efficiency, high success rate of grabbing and avoiding obstacles. It outperforms the existing methods such as least square method and micro-displacement cyclic correction method with respect to maximum error, RMSE score and time complexity. [ABSTRACT FROM AUTHOR]

An equity warrant allows warrant holders to buy stocks of listed companies at a certain price on a promissory day. Classified by the time of exercise right, there are two types of equity warrant, namely European equity warrants and American equity warrants. The European equity warrants allow the buyers to exercise their rights only on the expiring date. In contrast, American warrants enable the buyers to exercise their rights before or on the expiring date. Based on the assumption that the firm's value follows an uncertain exponential Ornstein–Uhlenbeck process instead of a stochastic process, this paper mainly solves the pricing problems of European and American equity warrants. The most significant advantage of this paper is offering the corresponding formulas to calculate equity warrants, which are not complicated compared with the classical stochastic financial theory. Besides, the minimum cover estimation method is applied to estimate the parameters in an uncertain exponential Ornstein–Uhlenbeck equation, and a simulation example is provided to show the effectiveness of the proposed pricing formulae. [ABSTRACT FROM AUTHOR]

Fuzzing is an important technique in software and security testing that involves continuously generating a large number of test cases against target programs to discover unexpected behaviors such as bugs, crashes, and vulnerabilities. Recently, fuzzing has advanced considerably owing to the emergence of new methods and corresponding tools. However, it still suffers from low coverage, ineffective detection of specific vulnerabilities, and difficulty in deploying complex applications. Therefore, to comprehensively survey the development of fuzzing techniques and analyze their advantages and existing challenges, this paper provides a comprehensive survey of the development of fuzzing techniques, summarizes the main research issues, and provides a categorized overview of the latest research advances and applications. The paper first introduces the background and related work on fuzzing. Research issues are subsequently addressed and summarized, along with the latest research developments. Furthermore, various customized fuzzing techniques in different applications are presented. Finally, the paper discusses future research directions. [ABSTRACT FROM AUTHOR]

Mobile manipulator robots that combine mobile platforms and robotic arms have been attracting considerable attention in recent years. In this paper, the motion control problem of the mobile manipulator system is considered with the following proposed control strategy. Firstly, a decoupled dynamic model is created to increase operation safety and to reduce complexity such that the independent controllers can be designed for the mobile system and the manipulator system. Subsequently, an effective reference trajectory generator is proposed to guide the mobile manipulator systems to the proper position for the manipulation being able to grip the target. Thereafter, the fuzzy controllers are designed for the mobile system to eliminate the tracking error and for the manipulator system to accomplish the gripping mission. The stability of the mobile manipulator control system can be guaranteed by the Lyapunov theory. Finally, the numerical simulations are given to demonstrate the effectiveness of the proposed approach. From the simulation results, it can be seen that this paper as well as other compared methods have good control response in case of small controller gain, in which the convergence time are about 4–5 s. However, by increasing the controller gain to improve the control response, the other methods will make the system unstable or the controller output will produce a large amount of chattering. The proposed controller in this paper can not only decrease the convergence time, from 5 to 3 s, but also provide a smooth control response. [ABSTRACT FROM AUTHOR]

In a competitive online retail market, orders for assembled products such as refrigerators, air conditioners, smart televisions, etc., attract significant attention due to their high gross merchandise value. Unlike other regular products, product delivery has a two-stage process—delivery of product components and assembly and installation of the final product—involving multiple parties that may be internal or external to the organization. Coordination of the above activities is essential to reduce customer dissatisfaction and to curb the various waiting or demurrage costs due to delayed arrivals of goods vehicles and traveling salesman. This paper attempts to model and solve such a realistic synchronized goods delivery and service problem against the online booking. In this model, one goods vehicle starts from the company's storehouse with all the goods to be delivered and moves continually, dropping the goods at the specified locations. For service, a traveling salesman separately moves and uses the appropriate conveyances among the available ones at each node to reach the customers. This paper poses some interesting research questions to understand the requirements of separate tour paths for goods vehicles and traveling salesman along with appropriate conveyance for traveling salesman's arrival. This is an NP-hard traveling salesman problem. For solving, a varied offspring memetic algorithm (VOMA) with modified probabilistic selection, varied offspring three-parent (i.e., surro-embryos) crossover and Fibo-generation-dependent mutation is developed and tested on some standard test functions to establish its superiority over the standard ones. VOMA implementation on the above proposed problem reveals the influence of unloading and service times, halt time and third-party outsourcing charges on the final optimum route design. Finally, the paper provides a structured decision-making framework for practitioners and showcases a case study by implementing VOMA in a similar problem context. [ABSTRACT FROM AUTHOR]

In this paper, an Economic Order Quantity (EOQ) model of a fractional order with time-varying holding cost is discussed in detail with the help of numerical computations. As is well known, financial variables possess memories, which makes it appropriate for developing fractional modeling to describe the effect of memory in the financial system. This paper is concerned with the issues of deterioration of the items of the inventory system where the importance of time-varying holding cost on the memory-dependent inventory model has been studied. For the inclusion of the memory effect, fractional order derivative and fractional order integration have been used. Illustrative numerical examples and graphical presentations are exploited to verify the efficiency of the effect of fractional rate of change of inventory model and memory-affected costs. The numerical result shows that the output of memory-affected systems is different from the output of memory-less and low-memory-affected systems. Sensitivity analysis has been carried out in long memory effect as well as low memory effect to highlight the critical parameters of the two different systems. Sensitivity analysis clears that in the long memory effect, a small change in deterioration rate can disturb the system but in the low memory effect, such type of disturbances does not arises. At last, some conclusions are recommended. [ABSTRACT FROM AUTHOR]

This paper focuses on the problem of motorcyclist helmet detection in single images. Although some previous works have been developed to deal with this problem, yet most of them are designed for videos and not suitable for single-image helmet detection. In view of this, in this paper, we propose a novel dual-detection framework for single-image motorcyclist helmet detection with multi-head self-attention. Particularly, two types of detectors are first trained, namely the rider detector and the head-shoulder detector, which are jointly leveraged in the dual-detection scheme. To take advantage of the contextual relevance information, the multi-head self-attention mechanism is incorporated, where multiple self-attention layers are integrated to capture the complex relationships among the input features so as to further enhance the detection accuracy. A new benchmark dataset, termed the SCAU helmet detection on motorcyclists (SCAU-HDM) dataset, is presented, which consists of 8000 training images and 2000 test images. Extensive experiments on the benchmark dataset demonstrate the effectiveness of the proposed framework. The code is available at https://github.com/LiChunHong2020/SCAUHDM. [ABSTRACT FROM AUTHOR]

The rapid advancement of IoT technology presents transformative opportunities across various sectors, with education being a prominent beneficiary. Smart classrooms, a product of IoT integration, are being widely adopted to create technology-enhanced, student-centric learning environments that cater to students' information literacy needs, particularly during events like pandemics. This widespread adoption generates substantial amounts of educational data, commonly known as big data, necessitating innovative solutions for analysis and utilization. To solve these challenges, this paper proposes utilizing the Apriori algorithm—a data mining technique renowned for uncovering valuable patterns and associations within extensive datasets. This paper evaluates the impact of various information resources with differing quality, considering individuals' information literacy skills. Utilizing data mining techniques, it delves into university students' information literacy data, integrating it with the university library resources to establish a data-driven information literacy education model. It then focuses on criteria, components, and effective methods for instructing college students in information literacy. Finally, a diverse group of students, from first-year undergraduates to doctoral candidates at a specific university, is studied for their engagement in information literacy instruction. Based on the experimental findings, sophomore students exhibited the highest level of participation at 75.9% accuracy, while postgraduate students received more information literacy training than undergraduates and Ph.D. students. When comparing this method to others, such as SVM, KNN, LR, RF, and DT, it achieved superior performance. Additionally, the quality of information literacy training in university libraries was assessed through three dimensions: student learning, behavior, and achievements. Only junior, senior, and first-year graduate students scored above 4, with scores of 4.18, 4.15, and 4.26, respectively. [ABSTRACT FROM AUTHOR]