Search

Group Recommendation Systems (GRS) is an emerging area in both research and practice and has been successfully developed in many domains as a type of information filter to overcome the information overload problem. With the growth of Scientific Social Networks (SSNs), the need for article recommendation is emerging. Considering that researchers can be grouped according to their research interests, and article recommendation to a group of users has not been addressed in the literature, this paper aims to develop and test an inferential model to accurately recommend articles for group researchers in SSNs. In this paper, a novel approach for group article recommendation, referred to as GPRAH_ER, is proposed to improve the processes of both individual prediction and group aggregation. In the stage of individual prediction, the Probabilistic Matrix Factorization method is adopted and is further unified by using articles’ contents and group information. In the stage of group aggregation, the ER rule is introduced in the aggregation process, since it possesses the advantages of identifying group members’ impacts based on the group member’s weight and reliability. To verify the performance of the proposed method, experiments are conducted on a real dataset CiteULike. The experimental results show that the proposed GPRAH_ER method outperforms other benchmark methods, and provides a more effective recommendation of articles to researchers in SSNs.

When ambulances’ turnaround time (TT) in emergency departments is prolonged, it not only affects the victim severely but also causes unavailability of resources in emergency medical services (EMSs) and, consequently, leaves a locality unprotected. This problem may worsen with abnormal situations, e.g., the current coronavirus disease 2019 (COVID-19) pandemic. Taking this into consideration, this paper presents a first study on the COVID-19 impact on ambulances’ TT by analyzing historical data from the Departmental Fire and Rescue Service of the Doubs (SDIS 25), in France, for three hospitals. Because the TTs of SDIS 25 ambulances increased, this paper also calculated and analyzed the number of breakdowns in services, which augmented due to shortage of ambulances that return on service in time. It is, therefore, vital to have a decision-support tool to better reallocate resources by knowing the time EMSs ambulances and personnel will be in use. Thus, this paper proposes a novel two-stage methodology based on machine learning (ML) models to forecast the TT of each ambulance in a given time and hospital. The first stage uses a multivariate model of regularly spaced time series to predict the average TT (AvTT) per hour, which considers temporal variables and external ones (e.g., COVID-19 statistics, weather data). The second stage utilizes a multivariate irregularly spaced time series model, which considers temporal variables of each ambulance departure, type of intervention, external variables, and the previously predicted AvTT as inputs. Four state-of-the-art ML models were considered in this paper, namely, Light Gradient Boosted Machine, Multilayer Perceptron, Long Short-Term Memory, and Prophet. As shown in the results, the proposed methodology provided remarkable results for practical purposes. The AvTT accuracies obtained for the three hospitals were 90.16%, 97.02%, and 93.09%. And the TT accuracies were 74.42%, 86.63%, and 76.67%, all with an error margin of ± 10 min.

DC arc fault is difficult to be detected, which brings great challenge to the safety of DC distribution system. The investigation of arc fault detection based on simulation method is able to reduce the cost and contributes to the research in the system where it is not suitable to carry out experiments. Accurate arc model is the foundation of simulation research. To address the gaps existing in arc models and corresponding parameter identification methods, two novel arc models and a new optimization algorithm are presented in this paper. First of all, hook static model was proposed to describe the nonlinearity near the transition point in static curve of arc. Then, segmented noise model was developed to flexibly fit the diversiform shape of arc noise’s frequency spectrum (FS). Finally, in order to improve the accuracy of parameter identification of arc models, this paper introduced chaos mechanism into quantum cuckoo search (CQCS): using chaotic map to initialize the population and generate the random parameter p; using lifespan based chaotic local search to further update the position of best solution. Based on the data obtained from established experimental platform, the effectiveness of the proposed models and optimization algorithm is verified. Meanwhile, compared with the existing methodologies, the proposed models and optimization algorithm are of better performance.

Time-dependent reliability and sensitivity analysis, in which the nature of demand, capacity and the limit state function varies over the life cycle of the structural system, is a challenging task. Meta-models are a suitable tool to construct inexpensive-to-evaluate and accurate surrogates in analysis of modern engineering problems. The paper’s contribution is threefold: First, the superiority of polynomial chaos Kriging (PCK) meta-model in terms of efficiency and accuracy is depicted in comparison to two other state-of-the-art methods in an explicit representation of a pilot gravity dam. Second, the problem of aging dams is analytically studied. Adaptive reliability approaches which benefit from Kriging and PCK meta-models are also investigated in a comparative analysis with classical reliability methods. Third, the importance of considering nonlinear dependency between random variables by copula theory is investigated under the reliability and sensitivity concepts. The results show that PCK meta-model can be used as an effective technique in uncertainty quantification (UQ) of dams. Furthermore, Kriging and PCK-assisted reliability methods can establish fairly accurate meta-models to perform reliability analysis in structural UQ with low computational efforts. Finally, the concept of UQ is propagated to ”dam class” in which the dam shape and its age are assumed to be variable. A generalized program is developed to assist dam owners and decision-makers in approximate failure probability estimation of gravity dams. This paper paves the road for global risk assessment of dams.

The use of optimization algorithms for designing Infinite Impulse Response (IIR) filters has been considered in many studies. The concern in this area is the multimodal error surface of such filters and their fitting with filter coefficients. The order of the modeled system has a direct effect on the number of coefficients, complexities of the error surface, and the filter’s stability. This paper proposes an efficient approach based on a variable length particle swarm optimization algorithm with a weighted sum fitness function (WS-VLPSO). The proposed WS-VLPSO is utilized as an effective adaptive algorithm for designing optimal IIR filters. The approach is based on the inclusion of the order as a discrete variable in the particle vector, which is done with the goal of intelligent minimizing of order and thereby reducing the design complexity of IIR filters. To ensure the optimality of the systems, the objective function is considered as a weighted sum. Also, a new criterion called Optimum Modeling Indicator (OMI) is introduced, a measure to determine the percentage reduction of order and the success rate of the proposed approach. The proposed algorithm is also applied for solving the sensor coverage problem as another real-world variable length engineering optimization application. Evaluation of simulation results, with Monte-Carlo simulation, indicates the acceptable improvement of identified structures and the significant performance of the proposed approaches. Note that the source codes of the paper will be publicly available at https://github.com/ali-ece .

Harris Hawks Optimizer (HHO) is one of the many recent algorithms in the field of metaheuristics. The HHO algorithm mimics the cooperative behavior of Harris Hawks and their foraging behavior in nature called surprise pounce. HHO benefits from a small number of controlling parameters setting, simplicity of implementation, and a high level of exploration and exploitation. To alleviate the drawbacks of this algorithm, a modified version called Nonlinear based Chaotic Harris Hawks Optimization (NCHHO) is proposed in this paper. NCHHO uses chaotic and nonlinear control parameters to improve HHO’s optimization performance. The main goal of using the chaotic maps in the proposed method is to improve the exploratory behavior of HHO. In addition, this paper introduces a nonlinear control parameter to adjust HHO’s exploratory and exploitative behaviors. The proposed NCHHO algorithm shows an improved performance using a variety of chaotic maps that were implemented to identify the most effective one, and tested on several well-known benchmark functions. The paper also considers solving an Internet of Vehicles (IoV) optimization problem that showcases the applicability of NCHHO in solving large-scale, real-world problems. The results demonstrate that the NCHHO algorithm is very competitive, and often superior, compared to the other algorithms. In particular, NCHHO provides 92% better results in average to solve the uni-modal and multi-modal functions with problem dimension sizes of D = 30 and 50, whereas, with respect to the higher dimension problem, our proposed algorithm shows 100% consistent improvement with D = 100 and 1000 compared to other algorithms. In solving the IoV problem, the success rate was 62.5%, which is substantially better in comparison with the state-of-the-art algorithms. To this end, the proposed NCHHO algorithm in this paper demonstrates a promising method to be widely used by different applications, which brings benefits to industries and businesses in solving their optimization problems experienced daily , such as resource allocation, information retrieval, finding the optimal path for sending data over networks, path planning, and so many other applications.

Large-scale optimization is the key to many practical decision processes. To deal with the dimensional issue in such problems, many approaches incorporate a divide-and-conquer strategy. Among them, cooperative coevolution approaches have recently gained popularity. Depending on the problem’s structure, the decomposition of any large problem, into a number of smaller sub-problems, may leave some variables common in more than one sub-problem. Such a decomposition may have a negative effect on the quality of the final solution of an optimization problem. In this paper, we have proposed an algorithm that incorporates a novel decomposition method, where the objective of decomposition is to minimize the number of common variables between sub-problems, achieved by exploiting a variable interaction matrix developed from the problem. So the algorithm works as a two-stage approach, where the first stage is the problem decomposition, and the second stage is to find the solutions of the problem. The performance of our proposed algorithm is assessed by solving different sets of large-scale non-separable benchmark functions with up to 2,905 variables. The experimental results provide important insights into the efficiency of the proposed decomposition method, which in turn improves the performance of the optimization process.

Ransomware is a form of malicious software which when deployed encrypts or locks the files and demands a ransom to have the files decrypted and accessible. In today’s digital world, devices connected to the network are vulnerable to ransomwares. Signature based methods are used to detect known ransomwares at an early stage to minimize the damage. This type of detection involves a predefined repository of static signatures which block the ransomwares based on the signatures in the repository. Fuzzy hashing method and Clam Av method for signature based ransomware detection have been proposed in literature. However, these methods raised false negatives and false positives respectively. Also, the speed of comparison in fuzzy hashing method was a limitation. In this paper an Ant Colony Optimization (ACO) based approach for filtering ransomwares by matching the incoming signature hash value with the signature database is proposed. Termed Ant Colony Optimization based Light weight Binary Search for Signature based Ransomware detection (ACOLBSR) algorithm, the ant agent finds the search space in the signature database. If a search space does not exist in the signature database, the incoming file is logged. If the search space exists in the database, the ant agent employs a binary search to match the incoming signature hash value with the signatures in the search space. If a match is found, the file is accepted or blocked if it is a goodware or ransomware respectively. If the incoming signature does not match with the signatures in the search space, the file is logged. The advantage of ACOLBSR algorithm is that the ransomwares are strictly filtered based on the signatures in the database. The computational complexity of ACOLBSR algorithm is less compared to binary search and sequential search. Also, it is shown that ACOLBSR algorithm do not generate false positives when compared to ClamAV, SplitScreen, fuzzy hashing and classification based approaches. Experimental results comparing the performance of the ACOLBSR scheme with the binary search scheme, sequential search scheme and classification based approaches are presented.

We discuss a planning model with load-dependent lead times for making order acceptance decisions in multi-product, multi-stage manufacturing systems. Semiconductor wafer fabrication facilities (wafer fabs) belong to this class of manufacturing systems. A profit-based objective function is considered. Clearing functions are used in the planning formulation to correctly represent the lead time behavior in the case of a congested system. Order acceptance decisions are made with respect to flexible due dates, i.e., it is possible to reject certain orders if there is not enough capacity. Such acceptance decisions are important, for instance, in short-term demand supply matching algorithms that are crucial for demand fulfillment and available to promise decisions in semiconductor manufacturing. The resulting planning problem is formulated as a mixed integer linear program. We first show that the resulting planning problem is NP-hard. Hence, computationally tractable approaches must be designed. Therefore, variable neighborhood search is hybridized with linear programming to solve large-sized problem instances in reasonable amount of computing time in the present paper. Results of computational experiments for problem instances that are derived from a scaled-down wafer fab simulation model are provided and analyzed. The computational results demonstrate that the proposed matheuristic outperforms time-based decomposition approaches from the literature.

Proper management and treatment of food waste have become a key concern due to its significant environmental, social, and economic ramifications. The selection of the most appropriate food waste treatment method among a set of alternative methods can be regarded as a multi-criteria decision-making problem because of the association of numerous qualitative and quantitative attributes. In this paper, we offer a novel integrated framework by combining criteria interaction through inter-criteria correlation (CRITIC) and multi-objective optimization based on ratio analysis with the full multiplicative form (MULTIMOORA) methods with single-valued neutrosophic sets (SVNSs) for assessing the multi-criteria food waste treatment methods selection. In this methodology, the CRITIC technique is applied for computing the attribute weights, and the MULTIMOORA model is employed for estimating the ranking of the options within SVNSs context. To examine the introduced methodology’s efficiency and achievability, a case study of food waste treatment method (FWTM) assessment is discussed in the SVNSs setting. Further, comparative study and sensitivity investigation are offered to certify the presented framework for prioritizing FWTMs. The final results indicate that the proposed approach achieves better solutions than the extant models.

Although the existing steganography methods can successfully embed secret information into the carrier image without introducing distortion into the appearance of the carrier image, the difference in distribution between the carrier image and stego image still cannot resist the detection by statistics-based steganalysis algorithms. To improve the capability of resisting steganalysis algorithms, an image steganography scheme based on style transfer and quaternion exponent moments is proposed in this paper. First, the geometric invariance of quaternion exponent moments is combined to accomplish the task of embedding secret information. Next, the style transfer is performed on a stego image embedded with the secret information, and the stylized image is used to transmit through the common channel. Then, the receiver attempts to remove the style from the stylized image and to restore the stylized image back to its original appearance. For this purpose, a de-stylized network is designed to reconstruct the stego image from the stylized image. Finally, an extracting algorithm is used to extract the transmitted secret image from the reconstructed stego image. In the steganography process, the main goal is to achieve that even when the appearance and distribution of the carrier image have been changed, that should also look like an independent and normal behavior to an eavesdropper. Extensive experiments are conducted to verify the feasibility of the proposed scheme. Experimental and analysis results indicate that the proposed scheme can generate an independent and meaningful image and successfully transmit a secret image and has the ability to extract a secret image at a low bit error rate. In addition, the proposed scheme provides high security.

Signaling in the control charts is usually followed by a substantial amount of delay, in which precise identification of the time when a change has occurred in a process simplifies the removal of change causes. This problem is referred to as change point (CP) estimation in the literature. This paper proposes a novel ensemble model to estimate CP under different processes’ changes in the phase II applications, known as ANNCP. It uses an evolutionary artificial neural network (ANN) as an underlying reasoning scheme to combine the predictions of multiple techniques and make the final decision. Specifically, a hybrid model of genetic algorithm (GA) and simulated annealing (SAN) with a new loss function is used to optimize the weights of ANN. The experimental results indicate that ANNCP can produce promising results under different conditions as compared with other state-of-the-art methods reported in the literature.

In this paper, we address a problem of vision-based 3D robotic navigation using deep reinforcement learning for an Autonomous Underwater Vehicle (AUV). Our research offers conclusions from the experimental study based on one of the RoboSub 2018 competition tasks. However, it can be generalized to any navigation task consisting of movement from a starting point to the front of the next station. The presented reinforcement learning-based model predicts the robot’s steering settings using the data acquired from the robot’s sensors. Its Vision Module may be based on a built-in convolutional network or a pre-trained TinyYOLO network so that a comparison of various levels of features’ complexity is possible. To enable evaluation of the proposed solution, we prepared a test environment imitating the real conditions. It provides the ability to steer the agent simulating the AUV and calculate values of rewards, used for training the model by evaluating its decisions. We study the solution in terms of the reward function form, the model’s hyperparameters and the exploited camera images processing method, and provide an analysis of the correctness and speed of the model’s functioning. As a result, we obtain a valid model able to steer the robot from the starting point to the destination based on visual cues and inputs from other sensors.

This paper proposes a novel competition-guided multi-neighborhood local search (CMLS) algorithm for solving the curriculum-based course timetabling problem. In comparison with the classical metaheuristic methods in the literature, the proposed algorithm includes three main contributions. Firstly, a new way of combining multiple neighborhoods is presented, according to which, only one neighborhood is selected at each iteration to make a trade-off between large search space and high computational efficiency. Secondly, two heuristic rules are proposed to determine the probabilities of selecting the neighborhood. Thirdly, a competition-based restart strategy is proposed, i.e., two SA-based multi-neighborhood local search procedures are implemented during the search process, and the elite one is selected from the two results obtained by the two procedures as the initial solution for the next round of search. The proposed algorithm is evaluated on the well-known benchmark instances, and the computational results show that the proposed algorithm is highly competitive compared with 6 state-of-the-art algorithms in the literature. Analysis of the essential ingredients of the proposed algorithm is also presented.

Label Distribution Learning (LDL) is a new learning paradigm with numerous applications in various domains. It is a generalization of both standard multiclass classification and multilabel classification. Instead of a binary value, in LDL, each label is assigned a real number which corresponds to a degree of membership of the object being classified to a given class. In this paper a new neural network approach to Label Distribution Learning (Duo-LDL), which considers pairwise class dependencies, is introduced. The method is extensively tested on 15 well-established benchmark sets, against 6 evaluation measures, proving its competitiveness to state-of-the-art non-neural LDL approaches. Additional experimental results on artificially generated data demonstrate that Duo-LDL is especially effective in the case of most challenging benchmarks, with extensive input feature representations and numerous output classes.

In this paper, we propose an online support vector quantile regression approach with an ɛ -insensitive pinball loss function, called Online-SVQR, for dynamic time series with heavy-tailed noise. Online-SVQR is robust to heavy-tailed noise, as it can control the negative influence of heavy-tailed noise by using a quantile parameter. By using an incremental learning algorithm to update the new samples, the coefficients of Online-SVQR reflect the dynamic information in the examined time series. During each incremental training process, the nonsupport vector is ignored while the support vector continues training with new updated samples. Online-SVQR can select useful training samples and discard irrelevant samples. As a result, the training speed of Online-SVQR is accelerated. Experimental results on one artificial dataset and three real-world datasets indicate that Online-SVQR outperforms ɛ -support vector quantile regression in terms of both sample selection ability and training speed.

Logic minimization is one of the most crucial steps in combinational logic synthesis. The minimization for ternary fixed polarity Reed–Muller (FPRM) expressions aims to find a polarity that produces a ternary FPRM expression with as few operation terms as possible. However, the size of the ternary FPRM optimization space is much larger than that of binary FPRM optimization space, and the minimization for ternary FPRM expressions is a computationally hard problem. In this paper, we first propose a ternary quantum shuffled frog leaping algorithm (TQSFL) to solve the three-valued combinatorial optimization problem. The TQSFL divides frog individuals into three subpopulations: a subpopulation with a global updating strategy, a subpopulation with a local updating strategy, and a subpopulation with a random updating strategy, and performs local depth search on the three subpopulations based on the proposed ternary quantum rotation gate, ternary quantum correction mechanism, and ternary quantum crossover operator. Moreover, based on the TQSFL, we propose a minimization algorithm (MA) for ternary FPRM expressions, which searches for a polarity that produces a ternary FPRM expression with as few operation terms as possible by using the TQSFL. Experimental results demonstrated the effectiveness of the MA in minimizing ternary FPRM expressions.

A support vector regression (SVR)-based method is presented in this paper, which aims to reconstruct the uncertain dynamic load using heterogeneous responses. Essentially, the technology of load identification can be regarded as an issue of nonlinear regression. Considering the incomplete limitation of the single response signal, the complicated relationship between the dynamic load and heterogeneous responses for a specific structure may be determined through some support vectors in simulated training samples based on the SVR algorithm. In view of multi-source uncertainties, an interval dimension-by-dimension (D–D) method is investigated, which can approximate the load changing concerning the each-dimensional uncertain parameter by Legendre orthogonal polynomials. Then, the dynamic load boundaries can be calculated through the maxima/minima of the approximation polynomial in the time history. The validity and specificity of the proposed methodology are clarified by 3 numerical examples. In addition, the results indicate that the proposed method can be utilized to identify the interval of dynamic load with outstanding accuracy and efficiency.

Regression testing is an essential aspect of the software development lifecycle. As the software evolves, the test suite grows, hence the cost and effort to retest the software. Test case prioritization is one of the mitigation techniques for regression testing. It ranks the test cases to maximize the desired properties, e.g., detecting faults early. The efficiency and effectiveness of test case prioritization techniques can be enhanced using optimization algorithms. Nature-inspired algorithms are gaining more attention due to their easy implementation and quality of the solutions. This paper proposes the discrete cuckoo search algorithm for test case prioritization. The prioritization problem deals with ordering the test cases. Therefore, a new adaptation strategy using asexual genetic reproduction is introduced to convert real numbers into permutation sequences. Furthermore, the cuckoo search algorithm’s effectiveness is extended with the genetic algorithm’s mutation operator to balance the trade-off between exploration and exploitation. An in-depth comparative study on four case studies is conducted between the proposed algorithms, existing state-of-the-art algorithms and baseline approach. Statistical investigation confirms that the proposed hybrid cuckoo search algorithm outperforms the genetic algorithm, particle swarm optimization, ant colony optimization, tree seed algorithm and random search by 4.29%, 5.52%, 8.38%, 2.74% and 10.80%, respectively.

The adaptability of multi-robot systems in complex environments is a hot topic. Aiming at static and dynamic obstacles in complex environments, this paper presents dynamic proximal meta policy optimization with covariance matrix adaptation evolutionary strategies (dynamic-PMPO-CMA) to avoid obstacles and realize autonomous navigation. Firstly, we propose dynamic proximal policy optimization with covariance matrix adaptation evolutionary strategies (dynamic-PPO-CMA) based on original proximal policy optimization (PPO) to obtain a valid policy of obstacles avoidance. The simulation results show that the proposed dynamic-PPO-CMA can avoid obstacles and reach the designated target position successfully. Secondly, in order to improve the adaptability of multi-robot systems in different environments, we integrate meta-learning with dynamic-PPO-CMA to form the dynamic-PMPO-CMA algorithm. In training process, we use the proposed dynamic-PMPO-CMA to train robots to learn multi-task policy. Finally, in testing process, transfer learning is introduced to the proposed dynamic-PMPO-CMA algorithm. The trained parameters of meta policy are transferred to new environments and regarded as the initial parameters. The simulation results show that the proposed algorithm can have faster convergence rate and arrive the destination more quickly than PPO, PMPO and dynamic-PPO-CMA.

Deep Neural Networks (DNNs) have achieved remarkable success in many computer vision tasks recently, but the huge number of parameters and the high computation overhead hinder their deployments on resource-constrained edge devices. It is worth noting that channel pruning is an effective approach for compressing DNN models. A critical challenge is to determine which channels are to be removed, so that the model accuracy will not be negatively affected. In this paper, we first propose Spatial and Channel Attention (SCA), a new attention module combining both spatial and channel attention that respectively focuses on “where” and “what” are the most informative parts. Guided by the scale values generated by SCA for measuring channel importance, we further propose a new channel pruning approach called Channel Pruning guided by Spatial and Channel Attention (CPSCA). Experimental results indicate that SCA achieves the best inference accuracy, while incurring negligibly extra resource consumption, compared to other state-of-the-art attention modules. Our evaluation on two benchmark datasets shows that, with the guidance of SCA, our CPSCA approach achieves higher inference accuracy than other state-of-the-art pruning methods under the same pruning ratios.

Large volumes of data have been accumulated in identical or very similar contexts of decision making. To generate accurate and explanatory decision recommendations by using these data, this paper proposes a data-driven multi-criteria decision making (MCDM) method based on machine learning (ML) algorithms and the evidential reasoning (ER) approach. In the method, based on the assessments of all historical alternatives, a comparison framework is designed to determine the most appropriate ML algorithm with the highest predictive accuracy. An optimization model is then constructed to connect the appropriate ML algorithm with the ER approach. Through the optimization model, the difference between overall assessments derived from the ER approach and the predicted results derived from the appropriate ML algorithm is minimized to learn criterion weights. The learned criterion weights are used to generate accurate and explanatory decisions. Such a combination takes advantage of high predictability of ML algorithms and favorable interpretability of the ER approach simultaneously. To demonstrate the validity and applicability of the proposed method, it is used to aid the diagnosis of thyroid nodules for a tertiary hospital located in Hefei, Anhui, China. Its merits are further highlighted by its comparison with two traditional ER approaches and the appropriate ML algorithm.

There are some practical optimization problems that can be only optimized using historical data, which is known as offline data-driven optimization problems. Since the real function evaluations are not available in the optimization process, surrogate models must replace the real fitness evaluations to guide the search. The key issue in offline data-driven optimization is how to make full use of offline data for building robust and accurate surrogate models. However, the existing offline algorithms do not consider optimization problems with constraints. Since the predicted values of the surrogate models for constraints are inaccurate, it becomes difficult to balance the objective function and the constraints during the optimization process. In this paper, we discuss a number of commonly used constraint handling techniques and combine them with an offline data-driven evolutionary algorithm. Also, four different test functions are designed with various constraints and difficulties. The results on the test function show that the multi-objective-based constraint handling technique is more likely to obtain feasible solutions, while stochastic ranking has better quality of feasible solutions.

This paper considers a variant of the classical capacitated vehicle routing problem called clustered vehicle routing problem (CluVRP). In CluVRP, customers are grouped into different clusters. A vehicle visiting a cluster cannot leave the cluster until all customers in the same cluster have been served. Each cluster and customer have to be served only once. A new hybrid metaheuristic, combining the particle swarm optimization (PSO) and variable neighborhood search (VNS) for the specific problem, is proposed to solve the CluVRP. In the hybrid PSO, the basic PSO principle ensures the solution diversity and VNS ensures solution intensity to bring the solution to the local optima. Extensive computational experiments have been performed on numerous benchmark instances with various sizes obtained from the CluVRP literature to evaluate the performance of the proposed hybrid PSO. The obtained results of the proposed algorithm are compared with the results found in the literature to validate the effectiveness of the proposed hybrid PSO. The proposed algorithm is proven to be superior to the state-of-the-art algorithms on the CluVRP. The proposed algorithm obtains 138 new best-known solutions among the 293 benchmark instances.

Transportation problem is one of the most common real life optimization problems seeking to minimize the total transportation cost while delivering a product from a number of sources to a number of destinations. In this paper, the transportation costs have been considered as generalized trapezoidal fuzzy numbers representing the uncertainty therein whereas the supply and the demand levels are crisp numbers. Particle Swarm Optimization has been extended to solve this fuzzy transportation problem. To illustrate the proposed extension of PSO, two numerical examples from existing literature have been solved and the results have been compared with those of the existing approaches. A few randomly generated problems of different dimensions have also been solved and the convergence rate of the proposed PSO has also been studied with respect to the variants of inertia weight, population size and the number of iterations. It has been observed that the proposed PSO works efficiently to obtain the optimal solutions and also removes the barricades of the traditional solution techniques.

Most research on robot manipulation focuses on objects that are light enough for the robot to pick them up. However, in our daily life, some objects are too big or too heavy to be picked up or carried, so that dragging them is necessary. Although bipedal humanoid robots have nowadays good mobility on level ground, dragging unfamiliar objects including large and heavy objects on various surfaces is an interesting research area with many applications, which will provide insights into human manipulation and will encourage the development of novel algorithms for robot motion planning and control. This is a challenging problem, not only because of the unknown and potentially variable friction of the foot, but also because the feet of the robot may slip during unbalanced poses. In this paper, we propose a novel hierarchical deep learning algorithm that learns how to drag heavy objects with an adult-sized humanoid robot for the first time. First, we present a Three-layered Convolution Volumetric Network (TCVN) for 3D object classification with point clouds volumetric occupancy grid integration. Second, we propose a lightweight real-time instance segmentation method named Tiny-YOLACT for the detection and classification of the floor surface. Third, we propose a deep Q-learning algorithm to learn the policy control of the Center of Mass of the robot (DQL-COM). The DQL-COM algorithm learning is bootstrapped using the ROS Gazebo simulator. After initial training, we complete training on the THORMANG-Wolf, a 1.4 m tall adult-sized humanoid robot with 27 degrees of freedom and weighing 48 kg, on three distinct types of surfaces. We evaluate the performance of our approach by dragging eight different types of objects (e.g., a small suitcase, a large suitcase, a chair). The extensive experiments (480 times on the real robot) included dragging a heavy object with a mass of 84.6 kg (two times greater than the robot’s weight) and showed remarkable success rates of 92.92% when combined with the force–torque sensors, and 83.75% without force–torque sensors.

For decades, breast cancer is the leading cause of cancer-related deaths among women. Early detection and diagnosis of breast cancer can effectively reduce the mortality rate. Masses are one of the manifestations of imperceptible breast cancer visible in mammograms whose detection and diagnosis is a challenging task due to its subtle nature. In this paper, a unified computer-aided detection/diagnosis scheme is proposed for the automatic detection and diagnosis of mammographic masses. Being simple and effective, multilevel image thresholding based on Otsu’s method is considered for localization of suspicious mass lesions, but its performance is compromised while defining the precise threshold value especially when the intensity profile in and around the anomalies does not vary much. To mitigate the issue, a nature-inspired optimization algorithm, wind driven optimization, is proposed which in combination with Otsu’s multilevel thresholding identifies the potential candidates of mass lesions. To reduce the false positives and diagnose the malignant masses, a texture-based multi-gradient local quinary pattern (M-GQP) feature is introduced which renders higher consistency in computing gradient information from the uniform and near-uniform areas. Due to eight distinct Sobel masks, it offers a better resolution in edge regions in addition to the micro information at different orientations. Four popular classifiers (support vector machine, Fisher’s linear discriminant, K-nearest neighbor, and an ensemble classifier) are also investigated to discriminate malignant tumors from benign lesions and normal tissues. The proposed integrated approach for the detection and characterization of mammographic masses is evaluated on two benchmark databases — mini-MIAS and DDSM comprising of 68 and 500 mammograms, respectively and achieved a sensitivity of 96.9% and 96.2% with 0.09 and 0.17 false positives per image after false positive reduction for the respective datasets. The diagnosis of malignant masses prior to and following false-positive reduction observes an A z value of 0.98 and 0.94 with an accuracy of 99.04% and 92.65%, respectively for the mini-MIAS dataset while the same for the DDSM are 0.99 and 0.92 with an accuracy of 98.33% and 78.50%, respectively. In a three-class classification (normal, benign and malignant), an accuracy of 99.04% and 97.76% with an F 1 score of 0.98 and 0.97 for malignancy is obtained for the mini-MIAS and DDSM images, respectively which are promising in nature when compared to other competing schemes in the state-of-the-art.

Social media platforms have radically transformed the creation and dissemination of news. Users can easily access this news in a fast and efficient manner. However, some users might post negative and fraudulent content in the form of comments or posts. Such content can constitute a threat to an individual or an organization. Therefore, the identification of fake news has become a major research field in natural language processing (NLP). The main challenge is to determine whether the news is real or fake. In this paper, we propose an attention-based convolutional bidirectional long short-term memory (AC-BiLSTM) approach for detecting fake news and classifying them into six categories. The evaluation of our proposed approach on a benchmarked dataset shows a significant improvement in accuracy rate in comparison with other existing classification models. In particular, this work contributes to the progress in the field of detecting fake news and confirms the feasibility of our proposed approach in classifying fake news on social media.

The Whale Optimization Algorithm (WOA) is a recently developed algorithm that is based on the chasing mechanism of humpback whales. Benefiting from the unique structure, WOA has virtuous global search capability. One of the drawbacks of this algorithm is the slow convergence rate that limits its real-world application. In resolving complicated global optimization problems, without any exertion for adequate fine-tuning preliminary constraints, Teaching-learning-based optimization (TLBO) is smooth to plunge into local optimal, but it has a fast convergence speed. By given the features of WOA and TLBO, an active hybrid WOA-TLBO algorithm is proposed for resolving optimization difficulties. To explore the enactment of the proposed WOA-TLBO algorithm, several experimentations are accompanied by regular benchmark test functions and compared with six other algorithms. The investigational outcomes indicate the more magnificent concert of the proposed WOA-TLBO algorithm for the benchmark function results. The proposed method has also been applied to the Facial Emotion Recognition (FER) functional problem. FER is the thought-provoking investigation zone that empowers us to classify the expression of the human face in everyday life. Centered on the portions’ actions in the human face, the maximum of the standard approaches fail to distinguish the expressions precisely as the expressions. In this paper, we have proposed FER’s productive process using WOA-TLBO based MultiSVNN (Multi-Support Vector Neural Network). Investigational outcomes deliver an indication of the virtuous enactment of the proposed technique resolutions in terms of accurateness.

The agile earth observation satellite scheduling problem (AEOSSP) consists of selecting and scheduling a number of tasks from a set of user requests in order to optimize one or multiple criteria. In this paper, we consider a multi-objective version of AEOSSP (called MO-AEOSSP) where the failure rate and the timeliness of scheduled requests are optimized simultaneously. Due to its NP-hardness, traditional iterative problem-tailored heuristic methods are sensitive to problem instances and require massive computational overhead. We thus propose a deep reinforcement learning and parameter transfer based approach (RLPT) to tackle the MO-AEOSSP in a non-iterative manner. RLPT first decomposes the MO-AEOSSP into a number of scalarized sub-problems by a weight sum approach where each sub-problem can be formulated as a Markov Decision Process (MDP). RLPT then applies an encoder–decoder structure neural network (NN) trained by a deep reinforcement learning procedure to producing a high-quality schedule for each sub-problem. The resulting schedules of all scalarized sub-problems form an approximate pareto front for the MO-AEOSSP. Once a NN of a subproblem is trained, RLPT applies a parameter transfer strategy to reducing the training expenses for its neighboring sub-problems. Experimental results on a large set of randomly generated instances show that RLPT outperforms three classical multi-objective evolutionary algorithms (MOEAs) in terms of solution quality, solution distribution and computational efficiency. Results on various-size instances also show that RLPT is highly general and scalable. To the best of our knowledge, this study is the first attempt that applies deep reinforcement learning to a satellite scheduling problem considering multiple objectives.

This paper addresses the problem of minimizing the makespan on unrelated parallel machines with sequence-dependent setup times. The term unrelated machines is used in the sense that there is no correlation between the processing times for jobs between different machines. Due to the NP-hardness of this problem, a wide range of metaheuristics has been developed to find near-optimal solutions. Out of such methods, the ones based on constructive greedy algorithms like the Greedy Randomized Adaptive Search Procedure (GRASP), Ant Colony Optimization (ACO) and Worm Optimization (WO) proved to be most efficient. The Fixed Set Search (FSS) is a novel population-based metaheuristic of this type that adds a learning mechanism to the GRASP. The basic concept of FSS is to avoid focusing on specific high quality solutions but on parts or elements that such solutions have. This is done through fixing a set of elements that exist in such solutions and dedicating computational effort to finding near-optimal solutions for the underlying subproblem. In this work, the FSS is applied to the problem of interest. Computational experiments show that the FSS manages to significantly outperform the GRASP, ACO and WO on the standard benchmark instances when the quality of found solutions is considered without an increase in computational cost. This application of the FSS is significant as it shows that it can also be applied to scheduling type problems, in addition to covering and routing ones.

Ensemble feature selection has attracted much attention of scholars because of its good robustness. However, existing methods on dealing with high-dimensional or large-scale data still have some shortcomings, such as high computational cost or high feature redundancy. In view of it, this paper proposes a new ensemble feature selection algorithm for large-scale data, called Multi-surrogate-assisted Dual-layer Ensemble Feature Selection (MDEFS). In MDEFS, a filter ensemble feature selection method with fast search ability is firstly developed to remove irrelevant or weakly-relevant features in the first layer. In the second layer, a particle swarm-based ensemble method with global search ability is proposed to select optimal feature subset from those remaining features. Furthermore, a multi-surrogate-assisted search mechanism of swarm is developed to reduce the cost of MDEFS on processing large-scale data, where the whole original dataset is replaced by multiple types of representative samples. Finally, the proposed algorithm is applied to 13 datasets and compared with 7 feature selection algorithms. Experimental results show that the multi-surrogate-assisted search mechanism can obviously reduce the running time of MDEFS, and the proposed ensemble approach can make MDEFS obtain better feature subsets, whose average accuracy is 0.72% higher than the best comparison algorithm on each data set. All results indicate that MDEFS is a robust and competitive feature selection algorithm.

The development of optimisation algorithms heavily relies on comparing performance across benchmark problem suites. In continuous unconstrained multi-objective optimisation, the most popular suites are ZDT, DTLZ and WFG. For each problem in these suites, there are construction parameters that control characteristics such as the degree of multimodality or deceptiveness. Despite encouragement from the suites’ authors to do otherwise, experiments are largely performed using only the original values of these parameters. It is important to understand the robustness of these test problems, and their potential to create a diversity of challenging problem landscapes to guide future algorithm testing and development. In this paper we propose a methodology for evaluating robustness of the benchmark test problems by strategically varying construction parameters and exploring how problem difficulty and landscape characteristics are affected. Our methodology adopts both Latin Hyper-cube Sampling and a design and analysis of experiments model to construct more diverse problem instances within the benchmark problem classes. These problem variants are evaluated for eight diverse multi-objective optimisation algorithms to contribute to our understanding of problem robustness. We measure robustness of problems indirectly in terms of impacts on algorithm performance and rankings, and directly in terms of Exploratory landscape Analysis (ELA) metrics that are used to establish problem robustness from a landscape characteristics perspective. Our results show that only eleven of the 21 benchmark problems are robust for algorithms in absolute terms, nine in relative terms, and seven which provide evidence of both types of algorithm robustness. There are also nine problems which satisfy requirements for landscape robustness. Of these, only four of the 21 benchmark problem classes are robust across all measures. These results highlight the importance of diversity in selecting benchmark problems, as the majority of the test suite problems, if only default construction parameters are considered, do not support robust conclusions to be drawn in general about how algorithms perform in the presence of various constructed characteristics intended to challenge algorithms. The existing benchmark test problems are currently insufficient for understanding algorithm performance, certainly with the popularly used default parameters, and more efforts in generating diverse problem instances would serve the research community well.

Measuring the similarity between images is of paramount importance in computer vision. However, the commonly used pixelwise similarity metrics do not match well with perceptual similarity. The purpose of this paper is to propose a visual similarity measurement method, which can be effectively used for plagiarism detection in graphic design. Plagiarism detection of designs refers to the identification and determination of major similarities. It is difficult to carry out the similarity learning process in traditional deep neural network due to the insufficient of training samples. To overcome this problem, a novel scheme is proposed for measuring perceptual similarity of graphics by using a constraint Generative Adversarial Network (GAN) model. The generator of GAN is used to create similar graphics following the common plagiarism features of logo design. Unlike the traditional discriminator which judges the authenticity of the generated image and the original image, the modified discriminator is used to calculate the perceptual similarity of the graphics pair. In graphics design, plagiarism mainly focuses on the changes of shape, color and style, which has certain cognitive subjectivity. Therefore, design experts were invited to participate in a group of cognitive analysis experiments. A perceptual constraint model is established to limit the generation of plagiarized graphics according to “design and visual rationality”. Promising results demonstrate that the proposed method can be used for plagiarism detection of logo design. Given its effectiveness and conceptual simplicity, I hope it can serve as a baseline and contribute to the future research on plagiarism detection of artworks.

Fake news has become a major concern over the Internet. It influences people directly and should be identified. In the recent years, various Machine Learning (ML) and Deep Learning (DL) based data-driven approaches have been suggested for fake news classification. Most of the ML based approaches use hand-crafted features extracted from input textual content. Moreover, in DL based approaches, an efficient word embedding representation of input data is also a major concern. This paper presents a deep learning framework, BerConvoNet, to classify the given news text into fake or real with minimal error. The presented framework has two main building blocks: a news embedding block (NEB) and a multi-scale feature block (MSFB). NEB uses Bidirectional Encoder Representations from Transformers (BERT) for extracting word embeddings from a news article. Next, these embeddings are fed as an input to MSFB. The MSFB consists of multiple kernels (filters) of varying sizes. It extracts various features from news word embedding. The output of MSFB is fed as an input to a fully connected layer for classification. To validate the performance of BerConvoNet, several experiments have been performed on four benchmark datasets and various performance measures are used to evaluate the results. Furthermore, the ablative experiments with respect to news article embedding, kernel size, and batch size have been carried out to ensure the quality of prediction. Comparative analysis of the presented model is done with other state of the art models. It shows that BerConvoNet outplays other models on various performance metrics.

This paper proposes a modified marine predators algorithm based on quantum theory to handle the multilevel image segmentation problem. The main aims of using quantum theory is to enhance the ability of marine predators algorithm to find the optimal threshold levels to enhance the segmentation process. The proposed quantum marine predators algorithm gets the idea of finding a particle in the space based on a possible function borrowed from the Schrodinger wave function that determines the position of each particle at any time. This rectification in the search mechanism of the marine predators algorithm contributes to strengthening of exploration and exploitation of the algorithm. To analyze the performance of the proposed algorithm, we conduct a set of experiments. In the first experiment, the results of the developed quantum marine predators algorithm are compared with eight well-known meta-heuristics based on benchmark test functions. The second experiment demonstrates the applicability of the algorithm, in addressing multilevel threshold image segmentation. A set of ten gray-scale images assess the quality of the quantum marine predators algorithm and its performance is compared with other meta-heuristic algorithms. The experimental results show that the proposed algorithm performs well compared with other algorithms in terms of convergence and the quality of segmentation.

As generalizations of single-valued information systems, interval-valued information systems (IVISs) can better express the real data with uncertainty in some applications. Attribute reduction methods for complete IVISs or complete interval-valued decision systems (IVDSs) have been developed. However, there are few researches on attribute reduction for incomplete interval-valued information systems (IIVISs). The paper aims to investigate the attribute reduction issue in IIVISs. Firstly, the maximal and minimal distances, which characterize the difference between two interval values, are defined, and the maximal and minimal similarity degrees are given. Secondly, the fuzzy α -similarity relation is defined based on similarity between interval values, and the concept of α -equivalence relation is raised. Thirdly, entropy measures are investigated for IIVISs in view of α -equivalence relations. Fourthly, a new attribute reduction approach for IIVISs is proposed by using conditional entropy, and its corresponding algorithm is given. Finally, experiments to verify the effectiveness and feasibility of the newly proposed approach for attribute reduction in IIVISs are presented. These results will be helpful to perfect the uncertainty measurement model, and provide an approach for attribute reduction in IIVISs.

The capacitated vehicle routing problem (CVRP) is a classical combinatorial optimization problem, which has received much attention due to its main challenges as distribution, logistics, and transportation. This proposed attempts to find the vehicle routes with minimizing traveling distance, in which the excellent solution delivers a set of customers in one visit by capacitated vehicle. For solving the CVRP problem, a cooperative hybrid firefly algorithm (CVRP-CHFA) is proposed in this paper with multiple firefly algorithm (FA) populations. Each FA is hybridized with two types of local search (i.e., Improved 2-opt as a local search and 2-h-opt as a mutation operator) and genetic operators. The proposed algorithms (FAs) communicate from time to time for exchanging some solutions (fireflies). The main aim of the hybridization and communication strategies is to maintain the diversity of populations to prevent the proposed algorithm from falling into local optima and overcome the drawbacks of a single swarm FA. The experiments are conducted on 108 instances from eight standard benchmarks. The results revealed that the proposed CVRP-CHFA got promising results compared to other well-known methods. Moreover, the proposed CVRP-CHFA significantly outperformed the recent three hybrid firefly algorithms.

Detection of eye state can assist the related work in the field of computer vision such as face recognition, expression recognition, pose estimation and human–computer interaction. This paper proposes an Weight Binarization Convolution Neural Network and Transfer Learning (WBCNNTL) based eye state detection method, in which the WBCNNTL is composed of deep convolution neural network and the weight is binarized. The human eye state features can be extracted by Convolutional Neural Network (CNN) effectively, and binary network not only speeds up the computation, but also helps to reduce the storage space and fewer parameters of the model. Transfer learning applies the knowledge or patterns learned from the source domain to different but related fields or problems, which improves the training efficiency of the new model. Experiments on eye state detection are performed using Closed Eyes in the wild (CEW), FER2013 and Zhejiang University Eyeblink (ZJU) Databases, from which the experiment results show the average accuracy obtained by our method are 97.41% on CEW and are 97.15% on ZJU, the computing speed of binary network is faster than non-binary network. Moreover, our method requires less storage space due to lightweight binary model, which maintains better detection capability on CEW compared with some state-of-the-art works.

In Electronic commerce, customer reviews play a significant role in purchase making decision. Most of the existing recommendation systems consider the customer reviews, user purchase history and product rating for predicting the recommended product. Since the users interest are varying over time, the existing recommendation systems lack in finding the current relevant items to the customers. To overcome this problem, this article proposes a new fuzzy logic-based product recommendation system which dynamically predicts the most relevant products to the customers in online shopping according to the users’ current interests. A novel algorithm has been proposed in this paper for computing the sentimental score of the product with associated end user target category. Finally, the proposed fuzzy rules and ontology-based recommendation system uses ontology alignment for making decisions that are more accurate and predict dynamically based on the search context. The experimental results of the proposed recommendation system show better performance than the existing product recommendation systems in terms of prediction accuracy of the relevant products for target users and in the time taken to provide such recommendations.

In recent years, sustainable development and green manufacturing have attracted widespread attention to environmental problems becoming increasingly serious. Meanwhile, affected by the intensification of market competition and economic globalization, distributed manufacturing systems have become increasingly common. This paper addresses the energy-efficient scheduling of the distributed permutation flowshop (EEDPFSP) with the criteria of minimizing both total flow time and total energy consumption. Considering the distributed and multi-objective optimization complexity, an improved NSGAII algorithm (INSGAII) is proposed. First, we analyze the problem-specific characteristics and designed new operators based on the knowledge of the problem. Second, four constructive heuristic algorithms are proposed to produce high-quality initial solutions. Third, inspired by the artificial bee colony algorithm, we propose a new colony generation method using the operators designed. Fourth, a local intensification is designed for exploiting better non-dominated solutions. The influence of parameter settings is investigated by experiments to determine the optimal parameter configuration of the INSGAII. Finally, a large number of computational tests and comparisons have been carried out to verify the effectiveness of the proposed INSGAII in solving EEDPFSP.

Clustering has always been a powerful tool in knowledge discovery. Traditionally unsupervised, it received renewed attention when it was shown to produce better results when provided with new types of information, thus leading to a new kind of semi-supervised learning: constrained clustering. This technique is a generalization of traditional clustering that considers additional information encoded by constraints. Constraints can be given in the form of instance-level must-link and cannot-link constraints, which this paper focuses on. We propose the first application of Differential Evolution to the constrained clustering problem, which has proven to produce a better exploration–exploitation trade-off when comparing with previous approaches. We will compare the results obtained by this proposal to those obtained by previous nature-inspired techniques and by some of the state-of-the-art algorithms on 25 datasets with incremental levels of constraint-based information, supporting our conclusions with the aid of Bayesian statistical tests.

The purpose of this paper is to establish a new mathematical framework for knowledge measure (KM) from fuzzy sets (FSs) through interval-valued intuitionistic fuzzy sets (IVIFSs). A novel KM is developed first in the context of intuitionistic fuzzy sets (IFSs) based on the normalized Hamming distance combined with the technique for order preference by similarity to ideal solution (TOPSIS), complying with the latest axiomatic definition. More efforts are made to investigate this new kind of axiomatic system and measuring model in the contexts of IVIFSs and FSs, respectively. This allows us to further recognize the nature of knowledge and present a unified framework for KM from FSs through IVIFSs. The developed technique is then used for image thresholding as a brand-new KM application, in which a new classification rule of pixels and a more efficient method for (interval-valued) intuitionistic fuzzification of images are proposed, thus leading to a knowledge-driven thresholding methodology. Experimental results show the outperformance of the developed technique with application. This is the first attempt to apply the latest KM theory to image processing, with which we undoubtedly create a new instance for the potential application areas of this theory.

Safety risk assessment of metro construction is necessary to prevent catastrophic accidents that may cause heavy financial losses and casualties. In this paper, we introduce a comprehensive risk assessment framework that incorporates credal networks (CNs) and an improved evaluation based on distance from average solution (EDAS) method. First, the CN model can intuitively demonstrate dependencies between risk factors, capture the epistemic uncertainty of expert judgement in the form of imprecise probability, and propagate the uncertainty quickly and accurately with advanced inference algorithms. In addition, the improved EDAS method can be used to comprehensively identify critical risk factors with multiple indicators, including the nature of the risk itself and company capabilities, being taken into account. Moreover, to effectively aggregate expert opinions, a weighting method that integrates subjective weights and similarity-based objective weights is provided. A case study on the safety risk analysis of metro construction in China verified the feasibility of the framework. The proposed approach can be extended to other similar projects to help engineers systematically assess risks during the life cycle of the project to ensure the safety of metro construction.

Today’s arena of global village organizations, social applications, and commercial websites provides huge information about products, individuals, and activities. This is leading to a plethora of content that requires effective handling to obtain the desired information. A recommendation system (RS) suggests relevant items to the user according to his/her desired preference. It processes various information related to users and items. However, RSs suffer from data sparsity. Generally, deep learning techniques are used in RSs for deep analysis of item contents to create precise recommendations. However, the effective handling of user reviews in parallel with item reviews is still an open research domain that can be further explored. In this paper, a hybrid model that handles both user and item metadata concurrently is proposed with the aim of solving the sparsity problem. To demonstrate the viability of the proposed methodology, a series of experiments was performed on three real-world datasets. The results show that the proposed model outperforms other state-of-the-art approaches to the best of our knowledge.

This paper proposes a maiden application of a two dimensional Sine Logistic map based chaotic sine cosine algorithm (2D-SLCSCA) optimized classical PID controller for load frequency control (LFC) of an islanded microgrid (MG). In comparison to random variables and 1D chaotic sequences, the 2D chaotic sequences are more ergodic and possess a wider chaotic range, thereby enhancing the global convergence speed and search capability of an algorithm. Initially, the proposed 2D-SLCSCA is tested on eight classical benchmark test functions and its performance is compared with 1D Logistic map based chaotic SCA (1D-LCSCA), 1D Sine map based chaotic SCA (1D-SCSCA), and the SCA incorporating random variables. Test results reveal that the proposed algorithm exhibits better convergence characteristics, statistics, and execution time. Finally, the proposed 2D-SLCSCA is implemented for the LFC analysis of the islanded MG. To establish the competence of the proposed algorithm in this regard, its performance is compared with 2D Henon map based chaotic SCA, 2D Lozi map based chaotic SCA, improved salp swarm algorithm (ISSA), SCA, grey wolf optimizer (GWO), and particle swarm optimization (PSO) algorithm considering diverse load disturbance patterns in the MG. Simulation results affirm that the proposed control scheme augments the frequency response of the MG exhibiting a maximum percentage improvement of 78.89%, 78.86%, and 96.51% in peak overshoot ( O S p e a k ), peak undershoot ( U S p e a k ) and objective function ( O F I T S E ) value, respectively as compared to the other algorithms. Furthermore, sensitivity of the proposed 2D-SLCSCA is validated considering ± 30% variation in the MG parameters.

Deep neural networks (DNNs) have achieved excellent performance in image classification research, part of which is due to the large-scale training data with accurate annotations. However, it is expensive and time-consuming to collect such clean data. In contrast, when collecting a dataset by crawling from websites, noisy labels are ubiquitous, which makes it easy for deep neural networks (DNNs) to overfit noisy labels and cause performance degradation. Most recent efforts have been focused on defending noisy labels by roughly ignoring some samples with high losses, which are treated as noise or reweight the training data in the loss function. Both strategies inevitably have priori conditions, such as a clean validation set or a ground-truth noise transition matrix, which are impractical in real-world datasets. In this paper, we propose a novel end-to-end framework for noise correction, called End-to-end Correction with Mixup and Balance terms (ECMB). ECMB can completely correct noisy labels to true labels and keep the number of each class more balanced. This framework uses a backbone network that is pre-trained by using an improved Mixup entropy instead of the traditional cross entropy, and does not need any extra conditions. In addition, we introduce a new balance term that can update noisy labels more accurately. Compared with other state-of-the-art methods, the experimental results on publicly available CIFAR-10, CIFAR-100 and Clothing1M datasets demonstrate that our method has superior performance.

Industrial enterprises are the main body of national scientific and technological innovation activities, and the improvement of their research and development (R&D) output capacity plays a pivotal role in the enhancement of national innovation capabilities. The R&D process is an input–output process, and its results have various forms. In this study, we construct a multi-objective R&D investment allocation optimization model from three dimensions representing China’s innovation capability, and propose a novel multi-objective mutation flower pollination algorithm (MOMFPA) to solve the model. We employ a two paired-sample T-tests to test the difference hypothesis of the model, and the test results show that the model is effective and reasonable. The MOMFPA and the weighting algorithm are respectively used for empirical analysis, and the optimized results obtained by the MOMFPA are found to be better than those obtained by the weighting algorithm, thereby demonstrating the validity and application value of the MOMFPA. Moreover, the multi-objective model is used to predictively optimize China’s future R&D investment. The forecasting results indicate that China should focus on increasing the proportions of R&D investment in high-tech equipment manufacturing and electronic information technology, while reducing the proportions of R&D investment in traditional industries, such as mining, food, paper, and metallurgy.

Many specialized numerical techniques have been developed on interval uncertainty optimization. However, the conventional nested optimization strategy is time-consuming. The improved Taylor-based interval optimization avoids the laborious inner optimization, nonetheless, it is intrusive and presents significant computational challenges in the large-level uncertain optimization problems. To end these, this paper proposes a Legendre polynomial expansion method combined with the subinterval technique to evaluate the range enclosure of an interval function, where the expansion coefficients are computed through the collocation method. The detailed comparisons demonstrate that such Legendre-based polynomial expansion provides much more confidence in interval bounds evaluation than the Taylor expansion, and is capable of maintaining very sharp solution enclosures even when the uncertainty level is increased. More exciting, it is highly efficient. Subsequent application of the Legendre polynomial expansion in the interval bound estimation of the uncertain objective function and constraints, and combining an appropriate outer optimizer, result in a novel nonlinear interval uncertain optimization method for complicated engineering systems, whereby the time-consuming optimization nesting is avoided. A beam design example and an electromagnetic buffer optimization example illustrate that the proposed interval optimization method has fine computational precision and high computational efficiency, especially is capable of attacking the increase of uncertainty level. Moreover, the new method does not require the derivative information of the uncertain objective and constraints, such that applies to any engineering uncertain optimization problems, including the complex engineering problems which are usually referred to as “black-box”.

Simultaneous Heat Transfer Search (SHTS) is a novel meta-heuristic algorithm proposed recently and it can solve some optimization problems. However, it still has some deficiencies, such as weak search ability owing to poor information exploitation so that it cannot solve complicated problems well. So an Information Guiding and Sharing enhanced SHTS (IGS-SHTS) is proposed in this paper. Firstly, Grey wolf optimizer is embedded into SHTS to enhance information sharing through the two different search methods. Secondly, an information sharing way through different agents is added. Thirdly, a sinusoidal crossover is utilized to fulfill information guiding through the historical individual-best population guiding the current one. Finally, an information guiding way, the global best agent guiding the worst one, is embedded to strengthen the worst agent. A large number of experimental results on the complex functions from CEC2017 test set and clustering optimization show that IGS-SHTS has stronger search ability compared with SHTS and quite a few state-of-the-art algorithms.