Article
Computer Science, Information Systems
Cristeta U. Jamilla, Renier G. Mendoza, Victoria May P. Mendoza
Summary: In this study, parameter estimation in neutral delay differential equations (NDDEs) is treated as an optimization problem, and Genetic Algorithm with Multi-Parent Crossover (GA-MPC) is applied to obtain parameter estimates. The results show that GA-MPC is capable of consistently identifying model parameters that provide a good fit of the model to the data.
Article
Computer Science, Artificial Intelligence
Karam M. Sallam, Amr A. Abohany, Rizk M. Rizk-Allahi
Summary: This paper presents a binary multi-operator differential evolution (BMODE) approach to solve the 0-1 knapsack problem. The method uses multiple differential evolution mutation strategies with complementary characteristics, selecting the best mutation operator based on the quality of solutions and population diversity. Two types of transfer functions are used to convert continuous solutions to binary ones, and a feasibility rule is applied to handle capacity constraints. Experimental results demonstrate that BMODE outperforms other state-of-the-art algorithms in most cases.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Junfeng Liu, Xinggao Liu, Yun Wu, Zhe Yang, Jian Xu
Summary: Harris hawks optimization (HHO) algorithm, inspired by the cooperative behavior and chasing style of harris' hawks, is a relatively novel swarm intelligent optimization algorithm. To address concerns regarding exploration and exploitation capabilities and premature convergence, this paper proposes a dynamic multi-swarm differential learning Harris hawks optimizer (DMSDLHHO). The algorithm maintains population diversity through the division of the whole population into small sub-swarms, which are periodically regrouped and exchange information. Differential evolution operators and the Quasi-Newton method are used to enhance exploration and exploitation capabilities, while the differential mutation operator candidate pool strategy is introduced to prevent falling into local optima. Experimental results demonstrate the superior performance of the proposed algorithm on classic test functions and real-world optimization problems.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Zhengkang Zuo
Summary: This research proposes an enhanced empirical distribution-based framework (ABCF) to address the limitation of the original EDBF. By adaptively changing the boundary of weight assigned to each parent chromosome according to the constraint law, ABCF outperforms compared algorithms on 20 benchmark functions in terms of convergence, efficiency, and accuracy.
Article
Green & Sustainable Science & Technology
Iman Ahmadianfar, Ali Kheyrandish, Mehdi Jamei, Bahram Gharabaghi
Summary: An adaptive differential evolution with particle swarm optimization (A-DEPSO) algorithm is developed to derive optimal operating rules for multi-reservoir systems in hydropower generation, showing improved performance compared to other well-known optimizers in the literature.
Article
Computer Science, Artificial Intelligence
Lixin Wei, Yexian Wang, Rui Fan, Ziyu Hu
Summary: To address the premature convergence issue in multi-objective evolutionary algorithms, a two-stage diversity enhancement differential evolution algorithm (TSDE) is proposed. The algorithm uses an improved cell density method and Principal Component Analysis operator to select high-quality parents and perturb non-dominated solutions, respectively. Results show that TSDE outperforms other advanced methods on 19 test functions.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Zhengkang Zuo, Lei Yan, Sana Ullah, Yiyuan Sun, Ruihua Zhang, Hongying Zhao
Summary: The paper discusses a real-coded schema to support genetic optimization process, using linear combination of coefficients for hybridizing parent chromosomes. An empirical distribution-based framework (EDBF) is proposed to optimize multiple-parent crossover algorithms.
Article
Computer Science, Information Systems
Xiaolong Zheng, Deyun Zhou, Na Li, Tao Wu, Yu Lei, Jiao Shi
Summary: This paper investigates the solution method for multi-task optimization problems, proposes an evolutionary multi-task optimization algorithm based on differential evolution, and enhances efficiency through a new knowledge transfer strategy. Experimental results demonstrate that the new algorithm shows promise in solving weapon-target assignment problems.
Article
Computer Science, Interdisciplinary Applications
Lue Tao, Yun Dong, Weihua Chen, Yang Yang, Lijie Su, Qingxin Guo, Gongshu Wang
Summary: This study addresses a new variant of the assembly line feeding problem in automobile manufacturing, proposing a novel mathematical model and algorithm that achieve superior cost savings, solution quality, and convergence efficiency while providing decision support for managers.
COMPUTERS & INDUSTRIAL ENGINEERING
(2022)
Article
Engineering, Chemical
Bruno Leite, Esly Ferreira da Costa Jr
Summary: This study optimizes industrial styrene reactors using the multi-objective algorithm GDE3 to maximize conversion and selectivity. The use of an intrinsic heterogeneous reaction model in modeling produces realistic results and explores the impact of different operational conditions on reactor performance.
CHEMICAL ENGINEERING SCIENCE
(2023)
Article
Computer Science, Artificial Intelligence
Surendra Tripathi, K. K. Mishra, Shailesh Tiwari
Summary: Differential evolution algorithm (DE) is a popular algorithm for solving numerical optimization problems, but it may get stuck in local optimal solutions. To address this issue, we propose a Modified Differential Evolution Algorithm (MDE) by updating the mutation and crossover operators, which improves the convergence rate and maintains the diversity among solutions. The performance of MDE is compared with other state-of-the-art algorithms, and it shows better results.
JOURNAL OF MULTIPLE-VALUED LOGIC AND SOFT COMPUTING
(2022)
Article
Management
Carlos E. Andrade, Rodrigo F. Toso, Jose F. Goncalves, Mauricio G. C. Resende
Summary: This paper introduces a variant of the Biased Random-Key Genetic Algorithm that employs multiple parents and implicit path-relinking, providing complete independence between local search and problem definition. Computational experiments demonstrate performance benefits over traditional BRKGA and BRKGA with multiple parents, making intensification/diversification more natural and simplifying development efforts.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2021)
Article
Computer Science, Information Systems
Yongkuan Yang, Jianchang Liu, Shubin Tan, Yuanchao Liu
Summary: Many domination-based multi-objective evolutionary algorithms are designed for constrained multi-objective optimization problems, but balancing feasibility, convergence, and distribution remains a challenge. The proposed MODE-CHS algorithm addresses this issue by using constraint-handling switching to enhance population convergence and obtain feasible solutions, while also involving an external archive and offspring in the evolution process to improve distribution. Experimental results demonstrate that MODE-CHS is competitive in solving CMOPs compared to other state-of-the-art algorithms.
INFORMATION SCIENCES
(2021)
Article
Chemistry, Multidisciplinary
Karn Moonsri, Kanchana Sethanan, Kongkidakhon Worasan, Krisanarach Nitisiri
Summary: This paper presents the Hybrid and Self-Adaptive Differential Evolution algorithms (HSADE) to solve an egg distribution problem in Thailand. It introduces a model for a multi-product, multi-depot vehicle routing problem and proposes corresponding strategies. The computational results show that the algorithm can effectively reduce costs compared to the current practice and can be applied to similar agriculture logistics globally.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Artificial Intelligence
Rongjuan Luo, Shoufeng Ji, Tingting Ji
Summary: This paper focuses on a special multi-objective unbalanced transportation problem considering fuel consumption, establishes a mathematical model and proposes a solution method. Numerical results and comparisons on 100 random instances and a real-life case study validate the effectiveness and practical value of the proposed method.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Information Systems
Rahul Sharma, Tripti Goel, M. Tanveer, P. N. Suganthan, Imran Razzak, R. Murugan
Summary: As per the latest statistics, Alzheimer's disease has become a global burden. This paper proposes a novel fusion approach using MRI and PET scans for identifying Alzheimer's disease at an early stage. The approach utilizes a trained CNN and RVFL models to extract features and make the final decision. Experimental results prove the effectiveness of the fusion-based ensemble approach.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Computer Science, Artificial Intelligence
Xuan He, Quan-Ke Pan, Liang Gao, Ling Wang, Ponnuthurai Nagaratnam Suganthan
Summary: This article addresses the flowshop sequence-dependent group scheduling problem (FSDGSP) by considering both production efficiency measures and energy efficiency indicators. A mixed-integer linear programming model and a critical path-based accelerated evaluation method are proposed. A greedy cooperative co-evolutionary algorithm (GCCEA) is designed to explore the solution space, and a random mutation operator and a greedy energy-saving strategy are employed.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2023)
Article
Automation & Control Systems
Parul Arora, Seyed Mohammad Jafar Jalali, Sajad Ahmadian, B. K. Panigrahi, P. N. Suganthan, Abbas Khosravi
Summary: Wind power forecasting is crucial for power system planning and scheduling. Optimizing the hyperparameters of deep neural networks (DNNs) using evolutionary algorithms is an effective approach. In this article, a novel evolutionary algorithm based on the grasshopper optimization algorithm is proposed to optimize the hyperparameters of a wind power forecasting model. The proposed model outperforms benchmark DNNs and other neuroevolutionary models in terms of learning speed and prediction accuracy.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Computer Science, Information Systems
Ruilin Li, Ruobin Gao, Ponnuthurai Nagaratnam Suganthan
Summary: In this study, a novel decomposition-based hybrid ensemble convolutional neural network (CNN) framework is proposed to enhance the capability of decoding EEG signals. Four decomposition methods are employed to disassemble the EEG signals into components of different complexity. The CNNs in this framework directly learn from the decomposed components, and a component-specific batch normalization layer is employed to reduce subject variability. The models under the framework showed better performance than the strong baselines in the challenging cross-subject driver fatigue recognition task.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Zhongqiang Ma, Guohua Wu, Ponnuthurai Nagaratnam Suganthan, Aijuan Song, Qizhang Luo
Summary: Metaheuristics are widely used and have gained much attention in various fields. Many new algorithms are inspired by biology, human behaviors, physics, or other phenomena, and show competitive performances compared to other metaheuristics. However, these new metaheuristics are often not rigorously tested on challenging benchmarks and not compared with state-of-the-art variants. This study exhaustively tabulates over 500 metaheuristics and compares them on benchmark suites, finding that some recent algorithms are less efficient and robust than state-of-the-art ones.
SWARM AND EVOLUTIONARY COMPUTATION
(2023)
Article
Computer Science, Artificial Intelligence
Kenneth Price, Abhishek Kumar, P. N. Suganthan
Summary: This paper presents a method for determining the better of two stochastic optimization algorithms by using trial-based dominance to order the outcomes. Traditional non-parametric methods can be used when the benchmarking results are ordinal-like, but when a trial can terminate once it reaches a prespecified target value, both the time taken to reach the target value and the final fitness value are important. The effectiveness of the method is demonstrated through simulations and validation in a numerical optimization competition.
SWARM AND EVOLUTIONARY COMPUTATION
(2023)
Article
Engineering, Multidisciplinary
Yulin He, Xuan Ye, Laizhong Cui, Philippe Fournier-Viger, Chengwen Luo, Joshua Zhexue Huang, Ponnuthurai Nagaratnam Suganthan
Summary: This paper presents an artificial intelligence-assisted network slice prediction method, which utilizes a novel incremental random vector functional link (IRVFL) network for the wireless network slice assignment (WNSA) problem. The IRVFL network gradually updates output layer weights as new data arrive, improving the performance of wireless network slice prediction. Extensive experiments validate the feasibility and effectiveness of using the IRVFL network for WNSA, showing that it consumes less time compared to other classification algorithms while maintaining equivalent performance.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2023)
Article
Robotics
Jiaying Chen, Han Wang, Minghui Hu, Ponnuthurai Nagaratnam Suganthan
Summary: In this paper, a hybrid LiDAR-inertial SLAM framework is proposed to improve the localization performance by leveraging both the on-board perception system and prior information such as motion dynamics. The proposed method achieves superior performance in accuracy and robustness.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Automation & Control Systems
Sreenivasan Shiva, Minghui Hu, Ponnuthurai Nagaratnam Suganthan
Summary: In this work, we propose the use of ensemble deep Random Vector Functional Link (edRVFL) to address the time-consuming training process and catastrophic forgetting issues in backpropagation-based deep neural networks during online learning. Unlike backpropagation-based networks, RVFL uses a closed-form solution method without iterative parameter learning and allows incremental growth of the model. Our proposed online learning models outperformed other randomization-based models in 72% of classification datasets and 80% of regression datasets. Statistical comparisons also confirmed the stability of our network.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Ruilin Li, Ruobin Gao, Ponnuthurai N. Suganthan, Jian Cui, Olga Sourina, Lipo Wang
Summary: This study proposes a spectral-ensemble deep random vector functional link (SedRVFL) network for feature learning in the frequency domain. It introduces an unsupervised feature-refining (FR) block and a dynamic direct link (DDL) to improve classification performance of EEG-based brain-computer interface tasks.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Aijuan Song, Guohua Wu, Ponnuthurai Nagaratnam Suganthan, Witold Pedrycz
Summary: A variable reduction strategy is an effective method to speed up the optimization process of evolutionary algorithms by simplifying the optimization problems. However, the current manual implementation of the strategy is trial-and-error-based. To improve its efficiency and applicability, we propose a variable reduction optimization problem to represent decision spaces with the smallest sets of variables. Then, we design an automatic variable reduction algorithm based on heuristic rules to address this problem.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2023)
Article
Engineering, Civil
Huan Liu, Guohua Wu, Ling Zhou, Witold Pedrycz, Ponnuthurai Nagaratnam Suganthan
Summary: Unmanned aerial vehicles (UAVs) face challenges in path planning in 3-D urban environments. This paper introduces a tangent-based (3D-TG) method that constructs a tangent graph to generate sub-paths for UAVs to bypass obstacles efficiently. The experimental results demonstrate the effectiveness of 3D-TG in both static and dynamic environments, as well as its ability to generate collision-free paths through simple mazes.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Information Systems
Jinlong Zhou, Yinggui Zhang, P. N. Suganthan
Summary: This paper proposes a novel dual population algorithm to approximate the constrained Pareto front (CPF) from both sides of the constraint boundaries. The algorithm uses the constrained-domination principle and an improved c-constrained method to approximate the feasible and infeasible regions respectively. Experimental results show that the algorithm achieves superior performance, especially for CMOPs with CPF located at constraint boundaries.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Information Systems
Lingping Kong, Varun Ojha, Ruobin Gao, Ponnuthurai Nagaratnam Suganthan, Vaclav Snasel
Summary: This study proposes a Global Representation (GR) based attention mechanism to alleviate the heterophily and over-smoothing issues. The model integrates geometric information and uses GR to construct the Key, discovering the relation between nodes and the structural representation of the graph. Experimental tests validate the performance of the proposed method and provide insights for future improvements.
INFORMATION SCIENCES
(2023)
Editorial Material
Computer Science, Artificial Intelligence
Rui Wang, Lining Xing, Maoguo Gong, Ponnuthurai Nagaratnam Suganthan, Hisao Ishibuchi
Summary: Optimization is an important research topic in engineering and various methods, including evolutionary algorithms, have been proposed. Evolutionary algorithms have gained attention for their robustness, but their iterative nature results in high computational effort, making them unsuitable for online or real-time optimization.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Rui Lv, Dingheng Wang, Jiangbin Zheng, Zhao-Xu Yang
Summary: In this paper, the authors investigate tensor decomposition for neural network compression. They analyze the convergence and precision of tensor mapping theory, validate the rationality of tensor mapping and its superiority over traditional tensor approximation based on the Lottery Ticket Hypothesis. They propose an efficient method called 3D-KCPNet to compress 3D convolutional neural networks using the Kronecker canonical polyadic (KCP) tensor decomposition. Experimental results show that 3D-KCPNet achieves higher accuracy compared to the original baseline model and the corresponding tensor approximation model.
Article
Computer Science, Artificial Intelligence
Xiangkun He, Zhongxu Hu, Haohan Yang, Chen Lv
Summary: In this paper, a novel constrained multi-objective reinforcement learning algorithm is proposed for personalized end-to-end robotic control with continuous actions. The approach trains a single model using constraint design and a comprehensive index to achieve optimal policies based on user-specified preferences.
Article
Computer Science, Artificial Intelligence
Zhijian Zhuo, Bilian Chen, Shenbao Yu, Langcai Cao
Summary: In this paper, a novel method called Expansion with Contraction Method for Overlapping Community Detection (ECOCD) is proposed, which utilizes non-negative matrix factorization to obtain disjoint communities and applies expansion and contraction processes to adjust the degree of overlap. ECOCD is applicable to various networks with different properties and achieves high-quality overlapping community detection.
Article
Computer Science, Artificial Intelligence
Yizhe Zhu, Chunhui Zhang, Jialin Gao, Xin Sun, Zihan Rui, Xi Zhou
Summary: In this work, the authors propose a Contrastive Spatio-Temporal Distilling (CSTD) approach to improve the detection of high-compressed deepfake videos. The approach leverages spatial-frequency cues and temporal-contrastive alignment to fully exploit spatiotemporal inconsistency information.
Review
Computer Science, Artificial Intelligence
Laijin Meng, Xinghao Jiang, Tanfeng Sun
Summary: This paper provides a review of coverless steganographic algorithms, including the development process, known contributions, and general issues in image and video algorithms. It also discusses the security of coverless steganography from theoretical analysis to actual investigation for the first time.
Article
Computer Science, Artificial Intelligence
Yajie Bao, Tianwei Xing, Xun Chen
Summary: Visual question answering requires processing multi-modal information and effective reasoning. Neural-symbolic learning is a promising method, but current approaches lack uncertainty handling and can only provide a single answer. To address this, we propose a confidence based neural-symbolic approach that evaluates NN inferences and conducts reasoning based on confidence.
Article
Computer Science, Artificial Intelligence
Anh H. Vo, Bao T. Nguyen
Summary: Interior style classification is an interesting problem with potential applications in both commercial and academic domains. This project proposes a method named ISC-DeIT, which combines data-efficient image transformer architectures and knowledge distillation, to address the interior style classification problem. Experimental results demonstrate a significant improvement in predictive accuracy compared to other state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Shashank Kotyan, Danilo Vasconcellos Vargas
Summary: This article introduces a novel augmentation technique called Dynamic Scanning Augmentation to improve the accuracy and robustness of Vision Transformer (ViT). The technique leverages dynamic input sequences to adaptively focus on different patches, resulting in significant changes in ViT's attention mechanism. Experimental results demonstrate that Dynamic Scanning Augmentation outperforms ViT in terms of both robustness to adversarial attacks and accuracy against natural images.
Article
Computer Science, Artificial Intelligence
Hiba Alqasir, Damien Muselet, Christophe Ducottet
Summary: The article proposes a solution to improve the learning process of a classification network by providing shape priors, reducing the need for annotated data. The solution is tested on cross-domain digit classification tasks and a video surveillance application.
Article
Computer Science, Artificial Intelligence
Dexiu Ma, Mei Liu, Mingsheng Shang
Summary: This paper proposes a method using neural dynamics solvers to solve infinity-norm optimization problems. Two improved solvers are constructed and their effectiveness and superiority are demonstrated through theoretical analysis and simulation experiments.
Article
Computer Science, Artificial Intelligence
Francesco Gregoretti, Giovanni Pezzulo, Domenico Maisto
Summary: Active Inference is a computational framework that uses probabilistic inference and variational free energy minimization to describe perception, planning, and action. cpp-AIF is a header-only C++ library that provides a powerful tool for implementing Active Inference for Partially Observable Markov Decision Processes through multi-core computing. It is cross-platform and improves performance, memory management, and usability compared to existing software.
Article
Computer Science, Artificial Intelligence
Zelin Ying, Dawei Cheng, Cen Chen, Xiang Li, Peng Zhu, Yifeng Luo, Yuqi Liang
Summary: This paper proposes a novel stock market trends prediction framework called SMART, which includes a self-supervised stock technical data sequence embedding model S3E. By training with multiple self-supervised auxiliary tasks, the model encodes stock technical data sequences into embeddings and uses the learned sequence embeddings for predicting stock market trends. Extensive experiments on China A-Shares market and NASDAQ market prove the high effectiveness of our model in stock market trends prediction, and its effectiveness is further validated in real-world applications in a leading financial service provider in China.
Article
Computer Science, Artificial Intelligence
Hao Li, Hao Jiang, Dongsheng Ye, Qiang Wang, Liang Du, Yuanyuan Zeng, Liu Yuan, Yingxue Wang, C. Chen
Summary: DHGAT1, a dynamic hyperbolic graph attention network, utilizes hyperbolic metric properties to embed dynamic graphs. It employs a spatiotemporal self-attention mechanism and weighted node representations, resulting in excellent performance in link prediction tasks.
Article
Computer Science, Artificial Intelligence
Jiehui Huang, Zhenchao Tang, Xuedong He, Jun Zhou, Defeng Zhou, Calvin Yu-Chian Chen
Summary: This study proposes a progressive learning multi-scale feature blending model for image deraining tasks. The model utilizes detail dilation and texture extraction to improve the restoration of rainy images. Experimental results show that the model achieves near state-of-the-art performance in rain removal tasks and exhibits better rain removal realism.
Article
Computer Science, Artificial Intelligence
Lizhi Liu, Zilin Gao, Yinhe Wang, Yongfu Li
Summary: This paper proposes a novel discrete-time interconnected model for depicting complex dynamical networks. The model consists of nodes and edges subsystems, which consider the dynamic characteristic of both nodes and edges. By designing control strategies and coupling modes, the stabilization and synchronization of the network are achieved. Simulation results demonstrate the effectiveness of the proposed methods.