Related references
Note: Only part of the references are listed.
Article
Dipanwita Thakur et al.
International Journal of Information Technology (Singapore)
(2021)
Article
Computer Science, Theory & Methods
Nidhi Dua et al.
Summary: Human Activity Recognition (HAR), an important research area, has seen a surge in interest due to the development of a deep neural network model that automates feature extraction and activity classification, achieving high accuracy without requiring manual feature extraction.
Review
Engineering, Electrical & Electronic
Sharmin Majumder et al.
Summary: This article provides a survey of papers where vision and inertial sensing are used together in a fusion framework for human action recognition. The surveyed papers are categorized based on fusion approaches, features, classifiers, and multimodality datasets. Challenges and possible future directions for deploying the fusion of these two sensing modalities under realistic conditions are also discussed.
IEEE SENSORS JOURNAL
(2021)
Article
Chemistry, Analytical
Sakorn Mekruksavanich et al.
Summary: Human Activity Recognition (HAR) using inertial motion data has been increasingly utilized in various applications due to the acceleration of building intelligent environments and systems. Deep learning methods are found to be more effective than traditional machine learning techniques in feature extraction from raw sensor data. A generic HAR framework based on LSTM networks for smartphone sensor data is proposed in this study, with experiments showing improved recognition performance using a 4-layer CNN-LSTM network.
Article
Chemistry, Analytical
Zhongzheng Fu et al.
Summary: Human activity recognition based on wearable devices has gained more attention from researchers, with a focus on personalized recognition and high accuracy while maintaining model generalization. A new transfer learning algorithm with improved pseudo-labels was proposed to address personalized recognition challenges and achieved a high average recognition accuracy of 93.2% for different subjects.
Article
Computer Science, Information Systems
Sakorn Mekruksavanich et al.
Summary: Currently, there is significant interest in research on Human Activity Recognition (HAR) for practical applications like biometric user identification, elderly health monitoring, and surveillance. Deep learning is the most commonly used approach in HAR systems. A novel framework for multi-class wearable user identification based on deep learning models has been proposed and validated with sensory data from wearable devices. The accuracy of 91.77% and 92.43% for basic models CNN and LSTM, respectively, shows promising results for biometric user identification.
Article
Chemistry, Analytical
Ohoud Nafea et al.
Summary: Human activity recognition (HAR) poses a challenging yet crucial problem in computer vision, with the development of deep learning offering automatic high-level feature extraction to optimize performance. This study introduces a new methodology utilizing convolution neural networks (CNN) and bi-directional long short-term memory (BiLSTM) to effectively capture features at various resolutions. Through traditional CNN and BiLSTM, spatial and temporal features are efficiently extracted from sensor data to improve HAR, as demonstrated by higher accuracy achieved in the WISDM dataset compared to the UCI dataset.
Article
Computer Science, Theory & Methods
Kaixuan Chen et al.
Summary: This study explores the impact of sensor devices and the Internet of Things on sensor-based activity recognition, discusses the role of deep learning methods in addressing recognition challenges, and provides an overview of current research progress and future directions.
ACM COMPUTING SURVEYS
(2021)
Review
Engineering, Electrical & Electronic
E. Ramanujam et al.
Summary: Human Activity Recognition (HAR) is the field of inferring human activities from signals acquired through sensors of smartphones and wearable devices, mainly for smart home and elderly care. Current techniques mostly use Deep Learning for feature extraction and classification efficiency, but there are challenges and issues that require future research and improvements.
IEEE SENSORS JOURNAL
(2021)
Article
Computer Science, Artificial Intelligence
Xue Yang et al.
Summary: Currently, part of the population is in a sub-health state, and dance, as a simple and popular activity, has attracted increasing attention. In order to improve the recognition of dance actions, an improved residual dense neural network method was used, with the addition of ELU activation function, BN, Dropout technology, and DenseNet to enhance the model's performance and generalization ability.
FRONTIERS IN NEUROROBOTICS
(2021)
Article
Computer Science, Information Systems
Jiahui Huang et al.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2020)
Article
Chemistry, Analytical
Saedeh Abbaspour et al.
Article
Computer Science, Information Systems
Chih-Ta Yen et al.
Article
Computer Science, Information Systems
Kun Xia et al.
Article
Chemistry, Analytical
Carlos Aviles-Cruz et al.
Article
Computer Science, Information Systems
Cheng Xu et al.
Article
Computer Science, Information Systems
Sen Qiu et al.
Article
Computer Science, Information Systems
Igor Bisio et al.
IEEE INTERNET OF THINGS JOURNAL
(2017)
Article
Chemistry, Analytical
Ahmet Turan Ozdemir
