Article
Computer Science, Artificial Intelligence
An-Da Li, Bing Xue, Mengjie Zhang
Summary: This paper proposes an improved sticky binary PSO algorithm for feature selection problems, which aims to enhance evolutionary performance through new mechanisms such as an initialization strategy, dynamic bits masking, and genetic operations. Experimental results show that ISBPSO achieves higher accuracy with fewer features and reduces computation time compared to benchmark PSO-based FS methods.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Information Systems
Emrah Hancer, Marina Bardamova, Ilya Hodashinsky, Konstantin Sarin, Artem Slezkin, Mikhail Svetlakov
Summary: This paper proposes modifications to the algorithm of particle swarm optimization (PSO) for feature selection. The modified binary PSO variations were tested on the dataset SVC2004 for user authentication based on dynamic signature features. The experiments demonstrate that the algorithm can effectively find the optimal subset of features.
Article
Computer Science, Artificial Intelligence
Saravanapriya Kumar, Bagyamani John
Summary: The GPSOGSA algorithm utilizes Gaussian based Particle Swarm Optimization Gravitational Search Algorithm for feature selection, effectively addressing the issues of local optima and local search ability. By limiting the use of excessive parameters, the algorithm shows promising results on benchmark functions and datasets.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Engineering, Multidisciplinary
Reya Sharma, Baijnath Kaushik
Summary: This research proposes an approach based on adaptive particle swarm optimization to automatically design the architecture of a convolutional neural network for the recognition of handwritten characters and digits in Indic scripts. Experimental results demonstrate that this method outperforms state-of-the-art approaches on three popular Indic scripts.
SADHANA-ACADEMY PROCEEDINGS IN ENGINEERING SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Jeremiah Osei-kwakye, Fei Han, Alfred Adutwum Amponsah, Qing-Hua Ling, Timothy Apasiba Abeo
Summary: In this study, a hybrid particle swarm optimization and crow search algorithm with a clustering initialization strategy (HPSOCSA-CIS) is proposed to enhance the exploration capability of feature selection. The clustering technique ensures an even distribution of the initial population over the feature space and includes more promising features. Additionally, the crow search algorithm helps in exploring unexplored regions within the search space. Experimental results on 15 standard UCI datasets demonstrate the superiority of the proposed method in feature selection tasks.
APPLIED INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Abdolreza Rashno, Milad Shafipour, Sadegh Fadaei
Summary: This paper introduces a novel multi-objective particle swarm optimization feature selection method. It decodes feature vectors as particles and ranks them in a two-dimensional optimization space. The proposed method incorporates feature ranks to update particle velocity and position during the optimization process. Experimental results demonstrate the effectiveness of the method in finding Pareto Fronts of the best particles in multi-objective optimization space.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Pei Hu, Jeng-Shyang Pan, Shu-Chuan Chu, Chaoli Sun
Summary: In this paper, a multi-surrogate assisted binary particle swarm optimization method is proposed for feature selection on large-scale datasets. Two surrogate models are trained to approximate the fitness values of individuals in two sub-populations, and a new population is generated through communication between the two sub-populations. Additionally, a dynamic transfer function is introduced to balance global and local search for finding optimal solutions with limited computational resources.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Xian-fang Song, Yong Zhang, Dun-wei Gong, Xiao-yan Sun
Summary: The paper proposes a novel feature selection algorithm based on bare bones PSO with mutual information, achieving better performance. The algorithm enhances exploitation performance through effective swarm initialization strategy and local search operators, while also designing an adaptive flip mutation operator.
PATTERN RECOGNITION
(2021)
Article
Engineering, Multidisciplinary
Jian Zhu, Jianhua Liu, Yuxiang Chen, Xingsi Xue, Shuihua Sun
Summary: The paper introduces the Binary Restructuring Particle Swarm Optimization (BRPSO) algorithm as an adaptation of the Restructuring Particle Swarm Optimization (RPSO) algorithm for solving discrete optimization problems. Unlike other binary metaheuristic algorithms, BRPSO does not use transfer functions, instead relying on comparison results and a novel perturbation term for the particle updating process. The algorithm requires fewer parameters and exhibits high exploration capability, as demonstrated by experiments on feature selection problems.
Article
Computer Science, Artificial Intelligence
Zhi Jiang, Yong Zhang, Jun Wang
Summary: The paper proposes a new ensemble feature selection algorithm, MDEFS, which can handle large-scale data, reduce computational costs, and improve the accuracy of feature selection results.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Milad Shafipour, Abdolreza Rashno, Sadegh Fadaei
Summary: This paper introduces a feature selection method based on particle distance and feature ranking, which is mathematically proven and experimentally supported to outperform existing methods in multiple evaluation metrics.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Litao Qu, Weibin He, Jianfei Li, Hua Zhang, Cheng Yang, Bo Xie
Summary: In this paper, a novel representation scheme called explicit representation is proposed for particle swarm optimization (PSO)-based feature selection, which effectively reduces computational complexity and memory occupation while improving classification performance. The proposed algorithm, ESAPSO, is validated through experiments on ten benchmark datasets, showing better classification performance with similar or smaller feature subsets.
SWARM AND EVOLUTIONARY COMPUTATION
(2023)
Article
Computer Science, Interdisciplinary Applications
Zhen He, Hao Hu, Min Zhang, Yang Zhang, An-Da Li
Summary: The paper proposes a data-driven method to effectively identify key quality characteristics in production processes, utilizing a multi-objective feature selection approach of maximizing geometric mean and minimizing the number of selected features. Experimental results show that the method exhibits good search performance on four production datasets.
COMPUTERS & INDUSTRIAL ENGINEERING
(2022)
Article
Physics, Multidisciplinary
Zhonghua Yang, Yuanli Cai, Ge Li
Summary: The gravitational search algorithm is a global optimization algorithm with the advantages of a swarm intelligence algorithm. In order to address the issues of accuracy and local optimal solutions, an improved gravitational search algorithm based on an adaptive strategy is proposed. By enhancing the information interaction between particles and improving the exploration and exploitation capacity, the algorithm shows significant improvements in solving local extrema and finding globally optimal solutions.
Article
Computer Science, Artificial Intelligence
Ying Hu, Yong Zhang, Xiaozhi Gao, Dunwei Gong, Xianfang Song, Yinan Guo, Jun Wang
Summary: Feature selection is an important preprocessing technique in data mining and machine learning. This paper proposes a federated feature selection framework that introduces a trusted third participant to process and integrate optimal feature subsets from multiple participants. A federated evolutionary feature selection algorithm based on particle swarm optimization is proposed to effectively solve feature selection problems with multiple participants under privacy protection. Experimental results show that the proposed algorithm can significantly improve the classification accuracy of the feature subset selected by each participant while protecting data privacy.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Information Systems
Soham Chattopadhyay, Arijit Dey, Pawan Kumar Singh, Ali Ahmadian, Ram Sarkar
Summary: Speech is crucial in human communication and human-computer interaction. In the field of AI and ML, it has been extensively studied to recognize human emotions from speech signals. To address the challenge of large feature dimension, a hybrid feature selection algorithm called CEOAS is proposed. By extracting LPC and LPCC features, the proposed model reduces feature dimension and improves classification accuracy. Impressive recognition accuracies have been achieved on four benchmark datasets, surpassing state-of-the-art algorithms.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Mainak Biswas, Saif Rahaman, Ali Ahmadian, Kamalularifin Subari, Pawan Kumar Singh
Summary: Spoken Language Identification (SLID) is a well-researched field and an important first step in multilingual speech recognition systems. This study proposes a model for Indian and foreign language recognition, which enhances data to make it robust against everyday life noise and selects relevant features through feature extraction and selection algorithms. The model achieves high accuracy on three standard datasets, indicating that these features capture language specific characteristics of speech and can be used as standard features for SLID task.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Business, Finance
Pawan Kumar Singh, Alok Kumar Pandey, Ravi Kiran, Rajiv Kumar Bhatt, Anushka Chouhan
Summary: This study collected information from 145 countries to predict the impact of COVID-19 cases, tests per million, and the proportion of people aged 65 and above on deaths per million at country and continent levels. It also evaluated the economic cost of these indicators in terms of reduction in GDP growth rate. The study found significant differences across continents and a negative association between tests per million and deaths per million. It provides valuable insights for assessing the impact of these indicators in the pandemic and informing policy formation and decision-making strategies.
INTERNATIONAL JOURNAL OF FINANCE & ECONOMICS
(2023)
Article
Environmental Sciences
Alok Kumar Pandey, Pawan Kumar Singh, Muhammad Nawaz, Amrendra Kumar Kushwaha
Summary: Renewable energy plays an important role in providing reliable power supplies and diversifying fuel sources, while also helping to conserve natural resources. Solar energy has become increasingly prominent in India. This study forecasts the development of renewable energy and finds that wind power is growing faster than hydropower, solar energy, and bioenergy.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)
Article
Computer Science, Artificial Intelligence
Erik Cuevas, Hector Escobar, Ram Sarkar, Heba F. Eid
Summary: This paper proposes a new population initialization method for metaheuristic algorithms, where the initial set of candidate solutions is obtained through the sampling of the objective function. The method aims to find initial solutions that are close to the prominent values of the objective function, and these initial points represent promising regions of the search space. The proposed approach shows faster convergence and improved quality of solutions compared to other similar approaches.
APPLIED INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Rishav Pramanik, Payel Pramanik, Ram Sarkar
Summary: Breast cancer is a leading cause of premature death among women globally, but early detection and diagnosis can save lives. Hence, computer scientists are working to develop reliable models to tackle this disease. A proposed lightweight model combines transfer learning-based deep learning (DL) with feature selection to detect abnormalities in breast thermograms. This model performs well in detecting and differentiating malignant and healthy breasts.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Automation & Control Systems
Debjit Sarkar, Sourodeep Roy, Samir Malakar, Ram Sarkar
Summary: Graph neural networks (GNN) maintain the essence of irregularly structured information in a graph through message passing and feature aggregation. A weighting scheme called VecGNN is proposed to incorporate inter-node feature-level correlational information, considering the relative position of nodes in the feature space. VecGNN outperforms baseline models GCN, GAT, and JKNets by 2%-4% on citation datasets.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Samriddha Majumdar, Payel Pramanik, Ram Sarkar
Summary: Breast cancer is the second deadliest disease among women globally. Histopathology image analysis is an effective method for detecting tumor malignancies. Computer-aided diagnosis (CAD) using convolutional neural network (CNN) models has shown potential in breast histopathological image classification, but there is room for improvement. This paper proposes a novel rank-based ensemble method that combines multiple CNN models to enhance classification accuracy.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Engineering, Manufacturing
Ritam Guha, Anirudh Suresh, Jared DeFrain, Kalyanmoy Deb
Summary: A long batch process involves recording sensor data with complicated non-linear dynamics, which are difficult to model. Predicting process outcomes before completion is important, and Virtual Metrology (VM) has been proposed as a solution. This paper introduces a generalized VM pipeline with a deep-learning model that can handle high-dimensional input sensors and outputs. The model can predict industrial process outcomes with less than 10% error after about one-fifth of the total process-time.
MATERIALS AND MANUFACTURING PROCESSES
(2023)
Article
Computer Science, Information Systems
S. k Mohiuddin, Samir Malakar, Ram Sarkar
Summary: Video forgery has become more common due to the easy availability of tools. This study proposes an ensemble based method to detect duplicate frames in a video. By extracting different types of features and applying lexicographical sorting, the method achieves high detection accuracy and outperforms state-of-the-art methods.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Sk Mohiuddin, Samir Malakar, Munish Kumar, Ram Sarkar
Summary: Video plays a critical role in conveying authenticity in various fields such as surveillance, medicine, journalism, and social media. However, the trust in videos is diminishing due to the ease of video forgery using accessible editing tools. This article comprehensively discusses the initiatives and recent trends in video forgery detection research worldwide.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Avirup Bhattacharyya, Avigyan Bhattacharya, Sourajit Maity, Pawan Kumar Singh, Ram Sarkar
Summary: Designing an automatic vehicle detection system that caters to the requirements of the traffic management system is important. This research develops a still image database, JUVDsi v1, for designing an automated traffic management system in India. The database addresses the shortcomings of existing databases and is evaluated using state-of-the-art deep learning architectures.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Interdisciplinary Applications
Ritam Guha, Kushal Kanti Ghosh, Suman Kumar Bera, Ram Sarkar, Seyedali Mirjalili
Summary: This paper proposes a binary adaptation of Equilibrium Optimizer (EO) called Discrete EO (DEO) for solving binary optimization problems. DEOSA algorithm, combining DEO with Simulated Annealing (SA) as a local search procedure, is applied to various datasets and outperforms other algorithms. The scalability and robustness of DEOSA are also tested on high-dimensional Microarray datasets and Knapsack problems, showing its superiority.
JOURNAL OF COMPUTATIONAL SCIENCE
(2023)
Article
Mathematics
Soumita Seth, Saurav Mallik, Atikul Islam, Tapas Bhadra, Arup Roy, Pawan Kumar Singh, Aimin Li, Zhongming Zhao
Summary: In this paper, a new framework is introduced to discover gene signatures from scRNA-seq data. The framework combines various strategies such as imputed matrix, MRMR feature selection, and shrinkage clustering. The results show that the proposed framework efficiently identifies differentially expressed stronger gene signatures and up-regulated markers in single-cell RNA sequencing data.