Article
Automation & Control Systems
Tse-Yu Pan, Wan-Lun Tsai, Chen-Yuan Chang, Chung-Wei Yeh, Min-Chun Hu
Summary: This study proposes a training system for sports referees that utilizes deep belief networks to learn gesture features and achieve robust recognition results by combining them with selective handcrafted features. It also introduces a hierarchical recognition scheme and fusion of multimodality data to improve recognition accuracy.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Chemistry, Analytical
Aiguo Wang, Shenghui Zhao, Huan-Chao Keh, Guilin Chen, Diptendu Sinha Roy
Summary: This study proposes a clustering guided hierarchical framework for discriminating human activities. By introducing an activity confusion index based on clustering, the confusion between activities is quantitatively measured automatically, leading to the design of a hierarchical activity recognition framework to reduce recognition errors between similar activities.
Article
Engineering, Electrical & Electronic
Yves Luduvico Coelho, Francisco de Assis Souza dos Santos, Anselmo Frizera-Neto, Teodiano Freire Bastos-Filho
Summary: Human Activity Recognition (HAR) has gained increasing attention from researchers and industry, requiring the design of small, lightweight, powerful, and low-cost smart sensors for practical HAR systems on wearable devices. Edge computing presents an energy-efficient solution that offers real-time response and privacy requirements for HAR applications.
IEEE SENSORS JOURNAL
(2021)
Article
Computer Science, Artificial Intelligence
Sen Qiu, Hongkai Zhao, Nan Jiang, Zhelong Wang, Long Liu, Yi An, Hongyu Zhao, Xin Miao, Ruichen Liu, Giancarlo Fortino
Summary: This paper introduces common wearable sensors, smart wearable devices, and key application areas, proposing fusion methods for multi-modality and multi-location sensors. It comprehensively surveys important aspects of wearable sensor fusion methods in human activity recognition, including new technologies in unsupervised learning and transfer learning, while also discussing open research issues that need further investigation and improvement.
INFORMATION FUSION
(2022)
Article
Computer Science, Information Systems
Nguyen Thi Hoai Thu, Dong Seog Han
Summary: The paper introduces a hierarchical deep learning-based HAR model (HiHAR) that extracts features and performs activity classification in two stages: local and global. Experimental results show that the proposed hybrid model achieves competitive performance in accuracy compared to other state-of-the-art HAR models.
Article
Chemistry, Analytical
Yiming Tian, Jie Zhang, Qi Chen, Shuping Hou, Li Xiao
Summary: This paper proposes a selective ensemble approach with group decision-making for decision-level fusion in human activity recognition. Experimental results demonstrate that the proposed approach outperforms traditional ensemble methods in terms of accuracy and diversity.
Article
Chemistry, Analytical
Ang Ji, Yongzhen Wang, Xin Miao, Tianqi Fan, Bo Ru, Long Liu, Ruicheng Nie, Sen Qiu
Summary: This study proposes a low-cost data glove solution that utilizes multiple inertial sensors to achieve efficient and accurate sign language recognition, enabling seamless communication between deaf and able-bodied individuals. Four machine learning models and an attention-based mechanism of long and short-term memory neural networks were employed to recognize 20 different types of dynamic sign language data. The results show that the proposed Attention-BiLSTM and RF algorithms have the highest performance in recognizing the twenty dynamic sign language gestures, with accuracies of 98.85% and 97.58% respectively, providing evidence for the feasibility of the proposed data glove and recognition methods. This study serves as a valuable reference for the development of wearable sign language recognition devices and promotes easier communication between deaf and able-bodied individuals.
Article
Environmental Sciences
Ting Zhao, Haibao Chen, Yuchen Bai, Yuyan Zhao, Shenghui Zhao
Summary: In this paper, a hierarchical ensemble deep learning activity recognition approach with wearable sensors based on focal loss is proposed for predicting and monitoring chronic diseases in the elderly. Experimental results demonstrate that the method achieves high accuracy and performance in identifying daily activities of the elderly.
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
(2022)
Article
Chemistry, Analytical
Chih-Ta Yen, Jia-Xian Liao, Yi-Kai Huang
Summary: This study introduces a wearable device that can recognize six activities of daily living using a deep-learning algorithm and six-axis sensors. Experimental results demonstrate the effectiveness of the device in accurately identifying human activities.
Article
Engineering, Electrical & Electronic
Rebeen Ali Hamad, Longzhi Yang, Wai Lok Woo, Bo Wei
Summary: Existing models for human activity recognition based on sensor data have achieved state-of-the-art performances. However, training separate models for each domain is time-consuming and computationally expensive. To address this issue, we propose a multi-domain learning network that transfers knowledge across related domains and mitigates isolated learning paradigms using a shared representation.
IEEE SENSORS JOURNAL
(2022)
Article
Chemistry, Analytical
Mohamed Elshafei, Diego Elias Costa, Emad Shihab
Summary: This research investigates the impact of muscle fatigue on Human Activity Recognition (HAR) systems, using biceps concentration curls as an example. Findings show that fatigue prolongs completion time of later sets and decreases muscular endurance, leading to changes in data patterns and affecting the performance of subject-specific and cross-subject models. Feedforward Neural Network (FNN) exhibits the best performance in both types of models.
Article
Computer Science, Information Systems
Thien Huynh-The, Cam-Hao Hua, Nguyen Anh Tu, Dong-Seong Kim
Summary: This study proposes a fusion model for activity recognition by combining deep convolutional neural networks with traditional handcrafted features, achieving high accuracy in activity recognition in multisensor systems, outperforming other state-of-the-art approaches.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Artificial Intelligence
Zhiwen Xiao, Xin Xu, Huanlai Xing, Fuhong Song, Xinhan Wang, Bowen Zhao
Summary: This paper presents a federated learning system for human activity recognition, HARFLS, which includes a perceptive extraction network (PEN) that extracts features through a feature network and a relation network. Compared to other systems, it achieves higher recognition accuracy, especially on the WISDM and PAMAP2 datasets.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Ayokunle Olalekan Ige, Mohd Halim Mohd Noor
Summary: With the development of deep learning, numerous models have been proposed for human activity recognition. However, activity recognition remains challenging due to the complexity of specific activity patterns. Existing models that address this challenge are often bulky and complex, making them unsuitable for resource-constrained embedded systems. This research proposes an efficient and lightweight deep learning model that achieves high recognition accuracy while minimizing resource consumption.
COMPUTATIONAL INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Sunder Ali Khowaja, Parus Khuwaja, Fayaz Ali Dharejo, Saleem Raza, Ik Hyun Lee, Rizwan Ali Naqvi, Kapal Dev
Summary: In this paper, a framework called ReFuSeAct is proposed for activity recognition using self-supervised learning. The method utilizes modality-specific encoders, attention encoders, and decision-level fusion strategies to accurately classify human activities while reducing the dependence on annotated data. Experimental results show significant improvements in performance.
INFORMATION FUSION
(2024)
