Search

Recommender systems are widely used in e-commerce, movies, music, social media, and other fields because of their personalized recommendation functions. The recommendation algorithm is used to capture user preferences, item characteristics, and the items that users are interested in are recommended to users. Matrix factorization is widely used in collaborative filtering algorithms because of its simplicity and efficiency. However, the simple dot-product method cannot establish a nonlinear relationship between user latent features and item latent features or make full use of their personalized information. The model of a neural network combined with an attention mechanism can effectively establish a nonlinear relationship between the potential features of users and items and improve the recommendation accuracy of the model. However, it is difficult for the general attention mechanism algorithm to solve the problem of attention interaction when the number of features between the users and items is not the same. To solve the above problems, this paper proposes an attention interaction matrix factorization (AIMF) model. The AIMF model adopts a symmetric structure using MLP calculation. This structure can simultaneously extract the nonlinear features of user latent features and item latent features, thus reducing the computation time of the model. In addition, an improved attention algorithm named slide-attention is included in the model. The algorithm uses the sliding query method to obtain the user's attention to the latent features of the item and solves the interaction problem among different dimensions of the user, and the latent features of the item. [ABSTRACT FROM AUTHOR]

The Constraint Satisfaction Problem (CSP) is a significant research area in artificial intelligence, and includes a large number of symmetric or asymmetric structures. A backtracking search combined with constraint propagation is considered to be the best CSP-solving algorithm, and the consistency algorithm is the main algorithm used in the process of constraint propagation, which is the key factor in constraint-solving efficiency. Max-restricted path consistency (maxRPC) is a well-known and efficient consistency algorithm, whereas the lmaxRPC3 r m algorithm is a classic lightweight algorithm for maxRPC. In this paper, we leverage the properties of symmetry to devise an improved pruning strategy aimed at efficiently diminishing the problem's search space, thus enhancing the overall solving efficiency. Firstly, we propose the maxRPC3 s i m algorithm, which abandons the two complex data structures used by lmaxRPC3 r m . We can render the algorithm to be more concise and competitive compared to the original algorithm while ensuring that it maintains the same average performance. Secondly, inspired by the RCP3 algorithm, we propose the maxRPC3 s i m R algorithm, which uses the idea of residual support to cut down the redundant operation of the lmaxRPC3 r m algorithm. Finally, combining the domain/weighted degree (dom/wdeg) heuristic with the activity-based search (ABS) heuristic, a new variable ordering heuristic, ADW, is proposed. Our heuristic prioritizes the selection of variables with symmetry for pruning, further enhancing the algorithm's pruning capabilities. Experiments were conducted on both random and structural problems separately. The results indicate that our two algorithms generally outperform other algorithms in terms of performance on both problem classes. Moreover, the new heuristic algorithm demonstrates enhanced robustness across different problem types when compared to various existing algorithms. [ABSTRACT FROM AUTHOR]

The quality of operation of neural networks in solving application problems is determined by the success of the stage of their training. The task of learning neural networks is a complex optimization task. Traditional learning algorithms have a number of disadvantages, such as «sticking» in local minimums and a low convergence rate. Modern approaches are based on solving the problems of adjusting the weights of neural networks using metaheuristic algorithms. Therefore, the problem of selecting the optimal set of values of algorithm parameters is important for solving application problems with symmetry properties. This paper studies the application of a new metaheuristic optimization algorithm for weights adjustment—the algorithm of the spiders-cycle, developed by the authors of this article. The approbation of the proposed approach is carried out to adjust the weights of recurrent neural networks used to solve the time series forecasting problem on the example of three different datasets. The results are compared with the results of neural networks trained by the algorithm of the reverse propagation of the error, as well as three other metaheuristic algorithms: particle swarm optimization, bats, and differential evolution. As performance criteria for the comparison of algorithms of global optimization, in this work, descriptive statistics for metrics of the estimation of quality of predictive models, as well as the number of calculations of the target function, are used. The values of the MSE and MAE metrics on the studied datasets were obtained by adjusting the weights of the neural networks using the cycling spider algorithm at 1.32, 25.48, 8.34 and 0.38, 2.18, 1.36, respectively. Compared to the inverse error propagation algorithm, the cycling spider algorithm reduced the value of the error metrics. According to the results of the study, it is concluded that the developed algorithm showed high results and, in the assessment of performance, was not inferior to the existing algorithm. [ABSTRACT FROM AUTHOR]

UAV trajectory planning is one of the research focuses in artificial intelligence and UAV technology. The asymmetric information, however, will lead to the uncertainty of the UAV trajectory planning; the probability theory as the most commonly used method to solve the trajectory planning problem in uncertain environment will lead to unrealistic conclusions under the condition of lacking samples, while the uncertainty theory based on uncertain measures is an efficient method to solve such problems. Firstly, the uncertainties in trajectory planning are sufficiently considered in this paper; the fuel consumption, concealment and threat degree with uncertain variables are taken as the objective functions; the constraints are analyzed according to the maneuverability; and the uncertain multi-objective trajectory planning (UMOTP) model is established. After that, this paper takes both the long-term benefits and its stability into account, and then, the expected-value and standard-deviation efficient trajectory model is established. What is more, this paper solves the Pareto front of the trajectory planning, satisfying various preferences, which avoids the defects of the trajectory obtained by traditional model only applicable to a certain specific situation. In order to obtain a better solution set, this paper proposes an improved backbones particle swarm optimization algorithm based on PSO and NSGA-II, which overcomes the shortcomings of the traditional algorithm such as premature convergence and poor robustness, and the efficiency of the algorithm is tested. Finally, the algorithm is applied to the UMOTP problem; then, the optimal trajectory set is obtained, and the effectiveness and reliability of the model is verified. [ABSTRACT FROM AUTHOR]

Ensemble learning of swarm intelligence evolutionary algorithm of artificial neural network (ANN) is one of the core research directions in the field of artificial intelligence (AI). As a representative member of swarm intelligence evolutionary algorithm, shuffled frog leaping algorithm (SFLA) has the advantages of simple structure, easy implementation, short operation time, and strong global optimization ability. However, SFLA is susceptible to fall into local optimas in the face of complex and multi-dimensional symmetric function optimization, which leads to the decline of convergence accuracy. This paper proposes an improved shuffled frog leaping algorithm of threshold oscillation based on simulated annealing (SA-TO-SFLA). In this algorithm, the threshold oscillation strategy and simulated annealing strategy are introduced into the SFLA, which makes the local search behavior more diversified and the ability to escape from the local optimas stronger. By using multi-dimensional symmetric function such as drop-wave function, Schaffer function N.2, Rastrigin function, and Griewank function, two groups (i: SFLA, SA-SFLA, TO-SFLA, and SA-TO-SFLA; ii: SFLA, ISFLA, MSFLA, DSFLA, and SA-TO-SFLA) of comparative experiments are designed to analyze the convergence accuracy and convergence time. The results show that the threshold oscillation strategy has strong robustness. Moreover, compared with SFLA, the convergence accuracy of SA-TO-SFLA algorithm is significantly improved, and the median of convergence time is greatly reduced as a whole. The convergence accuracy of SFLA algorithm on these four test functions are 90%, 100%, 78%, and 92.5%, respectively, and the median of convergence time is 63.67 s, 59.71 s, 12.93 s, and 8.74 s, respectively; The convergence accuracy of SA-TO-SFLA algorithm on these four test functions is 99%, 100%, 100%, and 97.5%, respectively, and the median of convergence time is 48.64 s, 32.07 s, 24.06 s, and 3.04 s, respectively. [ABSTRACT FROM AUTHOR]

The purpose of our bibliometric research was to capture and analyze the trends of two types of well-known classical artificial intelligence (AI) algorithms: neural networks (NNs) and genetic algorithms (GAs). Symmetry is a very popular international and interdisciplinary scientific journal that cover six major research subjects of mathematics, computer science, engineering science, physics, biology, and chemistry which are all related to our research on classical AI algorithms; therefore, we referred to the most innovative research articles of classical AI algorithms that have been published in Symmetry, which have also introduced new advanced applications for NNs and Gas. Furthermore, we used the keywords of "neural network algorithm" or "artificial neural network" to search the SSCI database from 2002 to 2021 and obtained 951 NN publications. For comparison purposes, we also analyzed GA trends by using the keywords "genetic algorithm" to search the SSCI database over the same period and we obtained 878 GA publications. All of the NN and GA publication results were categorized into eight groups for deep analyses so as to investigate their current trends and forecasts. Furthermore, we applied the Kolmogorov–Smirnov test (K–S test) to check whether our bibliometric research complied with Lotka's law. In summary, we found that the number of applications for both NNs and GAs are continuing to grow but the use of NNs is increasing more sharply than the use of GAs due to the boom in deep learning development. We hope that our research can serve as a roadmap for other NN and GA researchers to help them to save time and stay at the cutting edge of AI research trends. [ABSTRACT FROM AUTHOR]

In this paper, we advance the study of plithogenic hypersoft set (PHSS). We present four classifications of PHSS that are based on the number of attributes chosen for application and the nature of alternatives or that of attribute value degree of appurtenance. These four PHSS classifications cover most of the fuzzy and neutrosophic cases that can have neutrosophic applications in symmetry. We also make explanations with an illustrative example for demonstrating these four classifications. We then propose a novel multi-criteria decision making (MCDM) method that is based on PHSS, as an extension of the technique for order preference by similarity to an ideal solution (TOPSIS). A number of real MCDM problems are complicated with uncertainty that require each selection criteria or attribute to be further subdivided into attribute values and all alternatives to be evaluated separately against each attribute value. The proposed PHSS-based TOPSIS can be used in order to solve these real MCDM problems that are precisely modeled by the concept of PHSS, in which each attribute value has a neutrosophic degree of appurtenance corresponding to each alternative under consideration, in the light of some given criteria. For a real application, a parking spot choice problem is solved by the proposed PHSS-based TOPSIS under fuzzy neutrosophic environment and it is validated by considering two different sets of alternatives along with a comparison with fuzzy TOPSIS in each case. The results are highly encouraging and a MATLAB code of the algorithm of PHSS-based TOPSIS is also complied in order to extend the scope of the work to analyze time series and in developing algorithms for graph theory, machine learning, pattern recognition, and artificial intelligence. [ABSTRACT FROM AUTHOR]

Many existing scene-adaptive nonuniformity correction (NUC) methods suffer from slow convergence rate together with ghosting effects. In this paper, an improved NUC algorithm based on total variation penalized neural network regression is presented. Our work mainly focuses on solving the overfitting problem in least mean square (LMS) regression of traditional neural network NUC methods, which is realized by employing a total variation penalty in the cost function and redesigning the processing architecture. Moreover, an adaptive gated learning rate is presented to further reduce the ghosting artifacts and guarantee fast convergence. The performance of the proposed algorithm is comprehensively investigated with artificially corrupted test sequences and real infrared image sequences, respectively. Experimental results show that the proposed algorithm can effectively accelerate the convergence speed, suppress ghosting artifacts, and promote correction precision. [ABSTRACT FROM AUTHOR]

In this paper, we propose a particle-filter-based superpixel (PFS) segmentation method that extends the original tracking problem as a region clustering problem. The basic idea is to approximate superpixel centers by multiple particles to obtain high intra-region similarity. Specifically, we firstly use a density cluster to initialize single-group particles and introduce the association rule for mining other initial candidate particles. In propagation, particles are transferred to neighboring local regions by a moving step aiming to update local candidate particles with a lower energy cost. We evaluate all particles on the basis of their cluster similarity and estimate the largest particles as the final superpixel centers. The proposed method can locate cluster centers in diverse feature space, which alleviates the risk of a local optimum and produces better segmentation performance. Experimental results on the Berkeley segmentation 500 dataset (BSD500) demonstrate that our method outperforms seven state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) techniques in power grid control and energy management in building automation require both deep Q-networks (DQNs) and deep deterministic policy gradients (DDPGs) in deep reinforcement learning (DRL) as off-policy algorithms. Most studies on improving the stability of DRL have addressed these with replay buffers and a target network using a delayed temporal difference (TD) backup, which is known for minimizing a loss function at every iteration. The loss functions were developed for DQN and DDPG, and it is well-known that there have been few studies on improving the techniques of the loss functions used in both DQN and DDPG. Therefore, we modified the loss function based on a temporal consistency (TC) loss and adapted the proposed TC loss function for the target network update in both DQN and DDPG. The proposed TC loss function showed effective results, particularly in a critic network in DDPG. In this work, we demonstrate that, in OpenAI Gym, both "cart-pole" and "pendulum", the proposed TC loss function shows enormously improved convergence speed and performance, particularly in the critic network in DDPG. [ABSTRACT FROM AUTHOR]

In this study, a neural network-based approach is proposed for the identification of nonlinear static systems. A variant called ABCES (ABC Based on Effective Scout Bee Stage) is introduced for neural network training. Two important changes are carried out with ABCES. The first is an update of "limit" control parameters. In ABC algorithm, "limit" value is fixed. It is adaptively adjusted according to number of iterations in ABCES. In this way, the efficiency of the scout bee stage is increased. Secondly, a new solution-generating mechanism for the scout bee stage is proposed. In ABC algorithm, new solutions are created randomly. It is aimed at developing previous solutions in the scout bee stage of ABCES. The performance of ABCES is analyzed on two different problem groups. First, its performance is evaluated on 13 numerical benchmark test problems. The results are compared with ABC, GA, PSO and DE. Next, the neural network is trained by ABCES to identify nonlinear static systems. 6 nonlinear static test problems are used. The performance of ABCES in neural network training is compared with ABC, PSO and HS. The results show that ABCES is generally effective in the identification of nonlinear static systems based on neural networks. [ABSTRACT FROM AUTHOR]

Nowadays, video surveillance has become ubiquitous with the quick development of artificial intelligence. Multi-object detection (MOD) is a key step in video surveillance and has been widely studied for a long time. The majority of existing MOD algorithms follow the "divide and conquer" pipeline and utilize popular machine learning techniques to optimize algorithm parameters. However, this pipeline is usually suboptimal since it decomposes the MOD task into several sub-tasks and does not optimize them jointly. In addition, the frequently used supervised learning methods rely on the labeled data which are scarce and expensive to obtain. Thus, we propose an end-to-end Unsupervised Multi-Object Detection framework for video surveillance, where a neural model learns to detect objects from each video frame by minimizing the image reconstruction error. Moreover, we propose a Memory-Based Recurrent Attention Network to ease detection and training. The proposed model was evaluated on both synthetic and real datasets, exhibiting its potential. [ABSTRACT FROM AUTHOR]

This work tackles a recent challenge in digital image processing: how to identify the steganographic images from a steganographer, who is unknown among multiple innocent actors. The method does not need a large number of samples to train classification model, and thus it is significantly different from the traditional steganalysis. The proposed scheme consists of textural features and clustering ensembles. Local ternary patterns (LTP) are employed to design low-dimensional textural features which are considered to be more sensitive to steganographic changes in texture regions of image. Furthermore, we use the extracted low-dimensional textural features to train a number of hierarchical clustering results, which are integrated as an ensemble based on the majority voting strategy. Finally, the ensemble is used to make optimal decision for suspected image. Extensive experiments show that the proposed scheme is effective and efficient and outperforms the state-of-the-art steganalysis methods with an average gain from 4 % to 6 % . [ABSTRACT FROM AUTHOR]