Human Activity Recognition
Recently Published Documents


TOTAL DOCUMENTS

2103
(FIVE YEARS 1518)

H-INDEX

58
(FIVE YEARS 28)

Sensor Review ◽  
2022 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Gomathi V. ◽  
Kalaiselvi S. ◽  
Thamarai Selvi D

Purpose This work aims to develop a novel fuzzy associator rule-based fuzzified deep convolutional neural network (FDCNN) architecture for the classification of smartphone sensor-based human activity recognition. This work mainly focuses on fusing the λmax method for weight initialization, as a data normalization technique, to achieve high accuracy of classification. Design/methodology/approach The major contributions of this work are modeled as FDCNN architecture, which is initially fused with a fuzzy logic based data aggregator. This work significantly focuses on normalizing the University of California, Irvine data set’s statistical parameters before feeding that to convolutional neural network layers. This FDCNN model with λmax method is instrumental in ensuring the faster convergence with improved performance accuracy in sensor based human activity recognition. Impact analysis is carried out to validate the appropriateness of the results with hyper-parameter tuning on the proposed FDCNN model with λmax method. Findings The effectiveness of the proposed FDCNN model with λmax method was outperformed than state-of-the-art models and attained with overall accuracy of 97.89% with overall F1 score as 0.9795. Practical implications The proposed fuzzy associate rule layer (FAL) layer is responsible for feature association based on fuzzy rules and regulates the uncertainty in the sensor data because of signal inferences and noises. Also, the normalized data is subjectively grouped based on the FAL kernel structure weights assigned with the λmax method. Social implications Contributed a novel FDCNN architecture that can support those who are keen in advancing human activity recognition (HAR) recognition. Originality/value A novel FDCNN architecture is implemented with appropriate FAL kernel structures.


Author(s):  
Anna Ferrari ◽  
Daniela Micucci ◽  
Marco Mobilio ◽  
Paolo Napoletano

AbstractHuman activity recognition (HAR) is a line of research whose goal is to design and develop automatic techniques for recognizing activities of daily living (ADLs) using signals from sensors. HAR is an active research filed in response to the ever-increasing need to collect information remotely related to ADLs for diagnostic and therapeutic purposes. Traditionally, HAR used environmental or wearable sensors to acquire signals and relied on traditional machine-learning techniques to classify ADLs. In recent years, HAR is moving towards the use of both wearable devices (such as smartphones or fitness trackers, since they are daily used by people and they include reliable inertial sensors), and deep learning techniques (given the encouraging results obtained in the area of computer vision). One of the major challenges related to HAR is population diversity, which makes difficult traditional machine-learning algorithms to generalize. Recently, researchers successfully attempted to address the problem by proposing techniques based on personalization combined with traditional machine learning. To date, no effort has been directed at investigating the benefits that personalization can bring in deep learning techniques in the HAR domain. The goal of our research is to verify if personalization applied to both traditional and deep learning techniques can lead to better performance than classical approaches (i.e., without personalization). The experiments were conducted on three datasets that are extensively used in the literature and that contain metadata related to the subjects. AdaBoost is the technique chosen for traditional machine learning, while convolutional neural network is the one chosen for deep learning. These techniques have shown to offer good performance. Personalization considers both the physical characteristics of the subjects and the inertial signals generated by the subjects. Results suggest that personalization is most effective when applied to traditional machine-learning techniques rather than to deep learning ones. Moreover, results show that deep learning without personalization performs better than any other methods experimented in the paper in those cases where the number of training samples is high and samples are heterogeneous (i.e., they represent a wider spectrum of the population). This suggests that traditional deep learning can be more effective, provided you have a large and heterogeneous dataset, intrinsically modeling the population diversity in the training process.


PLoS ONE ◽  
2022 ◽  
Vol 17 (1) ◽  
pp. e0262181
Author(s):  
Prasetia Utama Putra ◽  
Keisuke Shima ◽  
Koji Shimatani

Multiple cameras are used to resolve occlusion problem that often occur in single-view human activity recognition. Based on the success of learning representation with deep neural networks (DNNs), recent works have proposed DNNs models to estimate human activity from multi-view inputs. However, currently available datasets are inadequate in training DNNs model to obtain high accuracy rate. Against such an issue, this study presents a DNNs model, trained by employing transfer learning and shared-weight techniques, to classify human activity from multiple cameras. The model comprised pre-trained convolutional neural networks (CNNs), attention layers, long short-term memory networks with residual learning (LSTMRes), and Softmax layers. The experimental results suggested that the proposed model could achieve a promising performance on challenging MVHAR datasets: IXMAS (97.27%) and i3DPost (96.87%). A competitive recognition rate was also observed in online classification.


Sensors ◽  
2022 ◽  
Vol 22 (1) ◽  
pp. 323
Author(s):  
Imran Ullah Khan ◽  
Sitara Afzal ◽  
Jong Weon Lee

In recent years, Human Activity Recognition (HAR) has become one of the most important research topics in the domains of health and human-machine interaction. Many Artificial intelligence-based models are developed for activity recognition; however, these algorithms fail to extract spatial and temporal features due to which they show poor performance on real-world long-term HAR. Furthermore, in literature, a limited number of datasets are publicly available for physical activities recognition that contains less number of activities. Considering these limitations, we develop a hybrid model by incorporating Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) for activity recognition where CNN is used for spatial features extraction and LSTM network is utilized for learning temporal information. Additionally, a new challenging dataset is generated that is collected from 20 participants using the Kinect V2 sensor and contains 12 different classes of human physical activities. An extensive ablation study is performed over different traditional machine learning and deep learning models to obtain the optimum solution for HAR. The accuracy of 90.89% is achieved via the CNN-LSTM technique, which shows that the proposed model is suitable for HAR applications.


2021 ◽  
Vol 5 (6) ◽  
pp. 1193-1206
Author(s):  
Humaira Nur Pradani ◽  
Faizal Mahananto

Human activity recognition (HAR) is one of the topics that is being widely researched because of its diverse implementation in various fields such as health, construction, and UI / UX. As MEMS (Micro Electro Mechanical Systems) evolves, HAR data acquisition can be done more easily and efficiently using inertial sensors. Inertial sensor data processing for HAR requires a series of processes and a variety of techniques. This literature study aims to summarize the various approaches that have been used in existing research in building the HAR model. Published articles are collected from ScienceDirect, IEEE Xplore, and MDPI over the past five years (2017-2021). From the 38 studies identified, information extracted are the overview of the areas of HAR implementation, data acquisition, public datasets, pre-process methods, feature extraction approaches, feature selection methods, classification models, training scenarios, model performance, and research challenges in this topic. The analysis showed that there is still room to improve the performance of the HAR model. Therefore, future research on the topic of HAR using inertial sensors can focus on extracting and selecting more optimal features, considering the robustness level of the model, increasing the complexity of classified activities, and balancing accuracy with computation time.  


Sign in / Sign up

Export Citation Format

Share Document