Article
Public, Environmental & Occupational Health
Youming Zhang, Xingchen Hou
Summary: This paper mainly studies the optimization process of the particle swarm optimization algorithm and discusses its development. Secondly, through methods such as video decoding, image noise removal, and video enhancement, the complete video image processing is performed and the structure of the manikin is established to achieve the collection of target key points. The results show that the motion recognition system proposed in this paper can effectively detect the changes of athletes' sampling point path and has a good auxiliary role.
PREVENTIVE MEDICINE
(2023)
Article
Computer Science, Artificial Intelligence
Y. L. Chang, C. S. Chan, P. Remagnino
Summary: The paper proposes a novel framework called LVAR for generic action classification in videos, which introduces a partial recurrence connection for propagating information within each layer. This framework improves action recognition performance by accessing long-term information in videos of different lengths.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Chemistry, Multidisciplinary
Ziyang Ji, Jie Zhang, Yi Liu, Tao Zhou
Summary: With the continuous and large-scale development of renewable energy, the level of inertia in new power systems decreases, weakening its capability for inertia support and frequency regulation during disturbance events. This paper presents an improved combined inertial intelligent control strategy for wind turbines, using contractive autoencoder and deep neural network, to efficiently cope with disturbance in different scenarios and achieve optimal frequency regulation.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Artificial Intelligence
Xinghan Xu, Weijie Ren
Summary: This paper proposes a hybrid model using stacked autoencoder and modified particle swarm optimization for multivariate chaotic time series forecasting. Experimental results show that the hybrid model performs well on multiple datasets.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Information Systems
Ibomoiye Domor Mienye, Yanxia Sun
Summary: This study proposes a deep learning approach to improve the prediction of heart disease. An enhanced stacked sparse autoencoder network (SSAE) is used for efficient feature learning. The authors also introduce a particle swarm optimization (PSO) based technique to optimize the parameters of the autoencoder network, resulting in improved feature learning and classification performance. Experimental results demonstrate that the proposed method achieves a classification accuracy of 0.973 and 0.961 on the Framingham and Cleveland heart disease datasets, outperforming other machine learning methods and similar studies.
Article
Engineering, Electrical & Electronic
Yatong Chen, Hongwei Ge, Yuxuan Liu, Xinye Cai, Liang Sun
Summary: This paper proposes an Action Granularity Pyramid Network (AGPN) for action recognition, which can be flexibly integrated into 2D backbone networks. The core module is the Action Granularity Pyramid Module (AGPM), a hierarchical pyramid structure with residual connections, which is established to fuse multi-granularity action spatio-temporal information.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2023)
Article
Green & Sustainable Science & Technology
Nida Khalid, Munkhjargal Gochoo, Ahmad Jalal, Kibum Kim
Summary: This study proposes a stereoscopic Human Action Recognition (HAR) system based on the fusion of RGB and depth sensors. Through optimized feature representation and a neuro-fuzzy classifier, accurate tracking and recognition of human activities are achieved, demonstrating promising results.
Article
Computer Science, Artificial Intelligence
Xu Chen, Yahong Han, Xiaohan Wang, Yifan Sun, Yi Yang
Summary: This paper proposes an Action Keypoint Network (AK-Net) that integrates temporal and spatial selection to improve the efficiency of video recognition models. AK-Net selects informative keypoints from arbitrary-shaped regions and transforms the video recognition into point cloud classification, providing two-fold benefits for efficiency. Experimental results demonstrate that AK-Net consistently improves the efficiency and performance of baseline methods on several video recognition benchmarks.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2022)
Article
Automation & Control Systems
John Kingsley Arthur, Conghua Zhou, Jeremiah Osei-Kwakye, Eric Appiah Mantey, Yaru Chen
Summary: This research proposes a Heterogeneous Coupling and Persuasive User/Item Information Model (HCPIM) to improve the performance of session-based recommenders. The HCPIM learns both intra-basket and inter-basket associations to predict the next items a user could purchase during their next shop visit.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Reza Jafari Ziarani, Reza Ravanmehr
Summary: Most recommender systems focus on accuracy of recommendations, but recent studies show accuracy alone does not guarantee user satisfaction. Serendipity, with relevant and unexpected recommendations, is a key factor beyond accuracy for improving user experience. The proposed approach using CNN and PSO algorithm outperforms other methods in achieving serendipitous recommendations.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Xiaodong Liu, Huating Xu, Miao Wang
Summary: This paper proposes a joint spatial-temporal reasoning (JSTR) framework to recognize action from videos by modeling the relation between joints. The experiment results demonstrate the good performance of our method in video action recognition.
FRONTIERS IN NEUROROBOTICS
(2022)
Article
Chemistry, Analytical
Tom Lawrence, Li Zhang, Kay Rogage, Chee Peng Lim
Summary: The study introduces a novel particle swarm optimization-based deep architecture generation algorithm that designs deep networks with residual connections and optimizes important design choices through thorough search. The proposed encoding scheme describes convolutional neural network architecture configurations with residual connections and outperforms existing methods. The final residual architectures generated by the model show improved capabilities in handling vanishing gradients, with a 4.34% increase in mean accuracy compared to existing studies.
Article
Computer Science, Artificial Intelligence
Shanshan Tu, Sadaqat Ur Rehman, Muhammad Waqas, Obaid Ur Rehman, Zubair Shah, Zhongliang Yang, Anis Koubaa
Summary: Training optimization is crucial for the development of convolutional neural networks (CNNs). The proposed evolutionary CNN algorithm, ModPSO-CNN, combines modified particle swarm optimization with backpropagation and CNN to improve performance by preventing premature convergence and local minima. Adaptable and dynamic parameters of ModPSO maintain global and local search balance, while an enhanced parameter preserves swarm diversity. The algorithm's effectiveness is validated on standard mathematical test functions and compared with benchmark PSO variants, showing promising results.
Article
Engineering, Multidisciplinary
Jinggeng Gao, Xinggui Wang, Weiman Yang
Summary: This paper proposes a new algorithm to address electric energy metering issues in micro-grids, optimizing deep belief networks for accurate metering. Verification results demonstrate significant improvements in accuracy compared to traditional methods.
ALEXANDRIA ENGINEERING JOURNAL
(2022)
Article
Environmental Sciences
Bahareh Kalantar, Naonori Ueda, Vahideh Saeidi, Saeid Janizadeh, Fariborz Shabani, Kourosh Ahmadi, Farzin Shabani
Summary: The study utilized artificial neural networks (ANN), deep learning neural networks (DLNN), and optimized DLNN using particle swarm optimization (PSO) to predict flood-prone areas in the Brisbane river catchment. The analysis identified altitude, distance from river, sediment transport index (STI), and slope as the most important factors, while stream power index (SPI) did not contribute significantly. The PSO-DLNN model demonstrated superior performance compared to the ANN and DLNN models, with the highest values of sensitivity, specificity, and true skill statistic.
Article
Engineering, Electrical & Electronic
Selvakumar Raja, Mala John
IETE JOURNAL OF RESEARCH
(2013)
Article
Engineering, Electrical & Electronic
S. Selvakumar Raja, Mala John
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY
(2009)
Article
Computer Science, Information Systems
Jeffin Gracewell, Mala John
MULTIMEDIA TOOLS AND APPLICATIONS
(2020)
Article
Computer Science, Artificial Intelligence
S. Jeba Berlin, Mala John
APPLIED ARTIFICIAL INTELLIGENCE
(2020)
Article
Computer Science, Artificial Intelligence
S. Jeba Berlin, Mala John
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2020)
Article
Computer Science, Software Engineering
S. Jeba Berlin, Mala John
Summary: In this paper, an efficient technique for human action recognition in automated video surveillance systems is proposed. The technique utilizes optical flow features and joint entropy to model human actions, and incorporates a spiking neural network to aggregate information across frames. Experimental results demonstrate the effectiveness of the proposed method.
Article
Computer Science, Artificial Intelligence
S. Jeba Berlin, Mala John
Summary: The study introduces a method for human fall detection using Siamese network and one shot classification, learning to differentiate video sequences by computing similarity scores. Experimental results demonstrate the effectiveness of the proposed method compared to existing methods.
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING
(2021)
Proceedings Paper
Computer Science, Theory & Methods
S. Jeba Berlin, Mala John
2016 IEEE INTERNATIONAL CARNAHAN CONFERENCE ON SECURITY TECHNOLOGY (ICCST)
(2016)
Proceedings Paper
Computer Science, Theory & Methods
S. Santhosh Kumar, Mala John
2016 IEEE INTERNATIONAL CARNAHAN CONFERENCE ON SECURITY TECHNOLOGY (ICCST)
(2016)
Proceedings Paper
Computer Science, Artificial Intelligence
Prashanth Chandran, Mala John, Santhosh S. Kumar, N. S. R. Mithilesh
2014 IEEE 17TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC)
(2014)