Review
Automation & Control Systems
Jun Tang, Gang Liu, Qingtao Pan
Summary: Swarm intelligence algorithms are a subset of artificial intelligence that has gained popularity for solving optimization problems and has been widely utilized in various applications. This review summarizes the most representative swarm intelligence algorithms and their successful applications in engineering fields, providing insights into future trends and prospects for development.
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
(2021)
Article
Computer Science, Artificial Intelligence
Rehna Kalam, Ciza Thomas, M. Abdul Rahiman
Summary: Brain tumor detection in MRI images was proposed utilizing an optimized ANFIS classifier, including preprocessing, segmentation, feature extraction, and classification. Performance of the proposed system was compared to existing systems in terms of various metrics.
INTERNATIONAL JOURNAL OF UNCERTAINTY FUZZINESS AND KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Engineering, Electrical & Electronic
Jingwei Yang, Xiaolong Yin, Yuwen Sun
Summary: The feedrate has a significant impact on contour error in five-axis machining. Therefore, it is important to plan a time-optimal feedrate curve considering the contour error constraint to achieve high-accuracy and high-efficiency machining. This paper proposes a PSO-based feedrate optimization algorithm for five-axis machining with the constraint of contour error, aiming to improve the error control accuracy and optimize the machining time. The effectiveness of the algorithm is validated through experiments on an open double-turntable five-axis machine tool, demonstrating accurate control of contour error while fully utilizing the potential of the machine tools.
Article
Mathematics
Omer Ali, Qamar Abbas, Khalid Mahmood, Ernesto Bautista Thompson, Jon Arambarri, Imran Ashraf
Summary: This study introduces a competitive coevolution process to enhance the capability of Phasor PSO (PPSO) for global optimization problems. Experimental results show that the improved competitive multi-swarm PPSO (ICPPSO) algorithm achieves a dominating performance, with average improvements of 15%, 20%, 30%, and 35% over PPSO and FMPSO.
Article
Mathematics
Martin Montes Rivera, Carlos Guerrero-Mendez, Daniela Lopez-Betancur, Tonatiuh Saucedo-Anaya
Summary: Optimizing large-scale numerical problems is challenging, but our proposed improved PSO algorithm (DSRegPSO) has achieved significant success in reducing stagnation in local optimal regions.
Article
Environmental Sciences
Rana Muhammad Adnan Ikram, Abolfazl Jaafari, Sami Ghordoyee Milan, Ozgur Kisi, Salim Heddam, Mohammad Zounemat-Kermani
Summary: This study investigated the capability of three hybridized models in modeling monthly pan evaporation at three stations in the Dongting lake basin, China. The results showed that the ANFIS-WOA and ANFIS-HHO models outperformed the other models, with ANFIS-WOA performing better between these two models. This study demonstrates the effectiveness of hybrid models in predicting evaporation, especially in data-scare regions.
Review
Computer Science, Interdisciplinary Applications
Janmenjoy Nayak, H. Swapnarekha, Bighnaraj Naik, Gaurav Dhiman, S. Vimal
Summary: This article presents an in-depth analysis of the Particle Swarm Optimization (PSO) algorithm and its developments in different application domains. PSO is highly popular due to its simple structure and few algorithmic parameters, and it has shown excellent performance in areas such as networking, robotics, and image segmentation. The paper discusses the evolution of PSO and its improved variants, providing a scope for further development and inspiring researchers and practitioners to find innovative solutions for complex problems in various domains using PSO.
ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Parminder Singh, Avinash Kaur, Ranbir Singh Batth, Sukhpreet Kaur, Gabriele Gianini
Summary: This paper proposes a BSO-ANFIS model for heart disease and multi-disease diagnosis, achieving high accuracy and precision by optimizing parameters and analyzing feature extraction. The results demonstrate the superiority of this algorithm over competitor models.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Ankita, Sudip Kumar Sahana
Summary: This paper proposes a new balanced PSO algorithm to solve the scheduling problem of computational grid. The algorithm is evaluated using a standard dataset, and its results outperform other considered deterministic and heuristic approaches.
APPLIED INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Feng Zhao, Lulu Cao, Hanqiang Liu, Zihan Tang, Jiulun Fan
Summary: The rough clustering algorithm optimizes nonlocal spatial information to improve noise robustness, simultaneously optimizing cluster centers to adapt to different segmentation requirements. It introduces an adaptive threshold determination mechanism to enhance the accuracy of rough cluster upper and lower approximations.
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2022)
Article
Chemistry, Analytical
Suganya Selvaraj, Eunmi Choi
Summary: This paper proposes an improved PSO algorithm, called dynamic sub-swarm PSO, for text document clustering problems. The experimental results show that this algorithm outperforms standard PSO and K-means algorithms in terms of purity and execution time.
Article
Computer Science, Artificial Intelligence
Kishore Balasubramanian, N. P. Ananthamoorthy
Summary: This study presents a predictive model for detecting neurodegenerative diseases and cancer, focusing on enhancing the efficiency of the adaptive neuro-fuzzy inference system. Experimental results demonstrate the superior performance of the DE-GSO-ANFIS in predicting medical disorders.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Mathematics
Do Ngoc Tuyen, Tran Manh Tuan, Le Hoang Son, Tran Thi Ngan, Nguyen Long Giang, Pham Huy Thong, Vu Van Hieu, Vassilis C. Gerogiannis, Dimitrios Tzimos, Andreas Kanavos
Summary: Flood is one of the deadliest natural hazards globally, and timely warning is crucial. The paper proposes a new deep learning architecture PSO-UNET, which combines particle swarm optimization with UNET to improve the performance of flash flood segmentation from satellite images.
Article
Computer Science, Interdisciplinary Applications
Davoud Sedighizadeh, Ellips Masehian, Mostafa Sedighizadeh, Hossein Akbaripour
Summary: The Particle Swarm Optimization (PSO) algorithm, a nature-inspired meta-heuristic, has evolved into various variants due to its flexibility in parameters and concepts. The Generalized Particle Swarm Optimization (GEPSO) algorithm enriches the original PSO by incorporating new terms and dynamic inertia weight updates, leading to improved performance in continuous space optimization.
MATHEMATICS AND COMPUTERS IN SIMULATION
(2021)
Article
Thermodynamics
Chiazor Faustina Jisieike, Niyi Babatunde Ishola, Lekan M. Latinwo, Eriola Betiku
Summary: This study evaluated the modeling effectiveness of response surface methodology (RSM) and adaptive neuro-fuzzy inference system (ANFIS) in esterifying crude rubber seed oil (CRSO) with high free fatty acid (FFA). The ANFIS-PSO hybrid provided the best optimal conditions, resulting in the lowest FFA of 0.56%.
Article
Energy & Fuels
Parthasarathy Velusamy, Santhosh Rajendran, Rakesh Kumar Mahendran, Salman Naseer, Muhammad Shafiq, Jin-Ghoo Choi
Summary: Agriculture is the primary source of income in developing countries like India. The monitoring and early detection of crop diseases and pest infestations are still challenging, but unmanned aerial vehicles (UAVs) have proven to be effective tools for precision-based crop monitoring and pest management.
Article
Physics, Multidisciplinary
S. Sivasaravanababu, V Prabhu, V Parthasarathy, Rakesh Kumar Mahendran
Summary: The EEG technology plays a critical role in the analysis of neural ailments, especially in the diagnosis and monitoring of epilepsy. This study proposes a fully automatic seizure indication structure based on deep learning, which significantly improves the accuracy and sensitivity of epileptic seizure detection.
EUROPEAN PHYSICAL JOURNAL-SPECIAL TOPICS
(2022)
Article
Automation & Control Systems
Navod Neranjan Thilakarathne, G. Muneeswari, V Parthasarathy, Fawaz Alassery, Habib Hamam, Rakesh Kumar Mahendran, Muhammad Shafiq
Summary: Healthcare is being revolutionized by the Medical IoT (MIoT) which integrates the Internet of Things. The use of MIoT generates a large amount of data that requires analysis for meaningful information, leading to the deployment of artificial intelligence technologies like machine learning and deep learning. Federated learning (FL) is gaining attention as a method to learn on devices without migrating private data to the cloud.
INTELLIGENT AUTOMATION AND SOFT COMPUTING
(2022)
Article
Engineering, Multidisciplinary
Rakesh Kumar Mahendran, V Prabhu, V Parthasarathy, Usharani Thirunavukkarasu, Mary A. Judith, S. Jagadeesan
Summary: In IoT systems used for monitoring patients, the conservation of energy in sensor nodes is crucial. Factors causing power consumption in IoHT networks include network interference, resource allocation, and idle time of body sensors. A novel MAC resource allocation protocol called CDTS is designed to reduce network congestion, energy consumption, and bit errors.
Article
Engineering, Biomedical
A. Mary Judith, S. Baghavathi Priya, Rakesh Kumar Mahendran
Summary: This study presents a method that combines Regenerative Multi-Dimensional Singular Value Decomposition (RMD-SVD) with Independent Component Analysis (ICA) to eliminate artifacts in EEG signals. By mapping the signals into multivariate data and applying ICA, accurate separation of artifacts can be achieved. Experimental results demonstrate that the proposed RMD-SVD method significantly improves noise removal efficiency.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Computer Science, Information Systems
Kiruthiga Devi Murugavel, Parthasarathy Ramadass, Rakesh Kumar Mahendran, Arfat Ahmad Khan, Mohd Anul Haq, Sultan Alharby, Ahmed Alhussen
Summary: Mobile Ad hoc Networks are networks that work without a fixed infrastructure and enable continuous communication even when nodes are disabled or removed. This paper proposes a method that switches communication mode based on the connectivity of adjacent nodes, and validates the results through simulation work.
Article
Chemistry, Analytical
Mary Judith Antony, Baghavathi Priya Sankaralingam, Rakesh Kumar Mahendran, Akber Abid Gardezi, Muhammad Shafiq, Jin-Ghoo Choi, Habib Hamam
Summary: In this paper, a feature extraction method based on ORICA-CSP is proposed for two classes of EEG experiments. The experimental results show that the ORICA-CSP method with A-SVM classifier has good performance.
Article
Automation & Control Systems
A. Mary Judith, S. Baghavathi Priya, Rakesh Kumar Mahendran, Thippa Reddy Gadekallu, Loknath Sai Ambati
Summary: This article introduces Brain-Computer Interfaces based on Electroencephalograms and some improvements in classification and performance. Experimental results show that the proposed method performs better on MI data.
ASIAN JOURNAL OF CONTROL
(2023)
Review
Chemistry, Analytical
Delshi Howsalya Devi, Kumutha Duraisamy, Ammar Armghan, Meshari Alsharari, Khaled Aliqab, Vishal Sorathiya, Sudipta Das, Nasr Rashid
Summary: The use of 5G technology in wearable devices and healthcare can reduce the cost of diagnosing and preventing diseases, and save patient lives. It has the potential to directly impact clinical decision making, improve patient rehabilitation, and continuously monitor human physical activity. The widespread adoption of 5G technology by healthcare systems enables sick people to access specialists and receive correct care more conveniently.
Article
Green & Sustainable Science & Technology
Parthasarathy Velusamy, Jagadeesan Srinivasan, Nithyaselvakumari Subramanian, Rakesh Kumar Mahendran, Muhammad Qaiser Saleem, Maqbool Ahmad, Muhammad Shafiq, Jin-Ghoo Choi
Summary: Municipal solid waste (MSW) management is crucial for modern society's health, safety, and environmental performance. Directly converting MSW into conventional energy is a strategy to solve the energy demand and waste disposal problems. This study used a machine learning model to predict the properties of fuel hydrochar and achieved excellent performance.
Article
Medicine, General & Internal
Mary Judith Antony, Baghavathi Priya Sankaralingam, Shakir Khan, Abrar Almjally, Nouf Abdullah Almujally, Rakesh Kumar Mahendran
Summary: An efficient processing approach is needed to deal with the nonlinear, nonstationary, and time-varying EEG signals produced by BCI apparatus. This study proposes a method using Singular Spectrum Analysis and Independent Component Analysis to preprocess the EEG data and effectively remove artifacts such as EOG, ECG, and EMG while preserving essential brain activity.
Article
Computer Science, Artificial Intelligence
Arfat Ahmad Khan, Rakesh Kumar Madendran, Usharani Thirunavukkarasu, Muhammad Faheem
Summary: Epilepsy is a serious brain disorder characterized by frequent seizures caused by unexpected electrical changes in brain neural activity. Existing research on predicting epileptic seizures has faced challenges in obtaining patients' characteristics, affecting the reliability of the models. To address these issues, a deep learning approach called D(2)PAM is proposed for classifying pre-ictal signals of epilepsy patients based on brain signals. Integrating deep neural networks with D(2)PAM reduces the impact of patient differences and improves the generalizability and stability of the trained model. The proposed model transforms brain signals into data blocks suitable for pre-ictal classification, providing early warning and auxiliary diagnosis.
CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Nehru Veerabatheran, Prabhu Venkatesan, Rakesh Kumar Mahendran
Summary: Brain tumor is a life-threatening disease that requires early diagnosis and localization through image processing techniques. This study proposes an efficient image processing method by processing MRI images to detect and localize the tumor-affected region in the human brain through image denoising and image segmentation.
COMPUTATIONAL INTELLIGENCE
(2022)
Article
Environmental Studies
Kun Gao, Prathik Anandhan, Rakesh Kumar
Summary: This paper proposes a web-text analysis based method for developing and evaluating air quality index monitoring and pollution research. The added value of web-text analysis has been demonstrated by comparing traditional monitoring approaches with immersive techniques.
ENVIRONMENTAL IMPACT ASSESSMENT REVIEW
(2021)