A survey on wearable sensor modality centred human activity recognition in health care

Wang, Yan; Cang, Shuang; Yu, Hongnian

doi:10.1016/j.eswa.2019.04.057

Cited by 299 publications

(156 citation statements)

References 207 publications

(355 reference statements)

Supporting

Mentioning

156

Contrasting

Order By: Relevance

“…In this study, an inertial motion capture system collected the motion data from five patients to create rehabilitation plans, validating the motion capture system for this rehabilitation application. On the other hand, the study of Wang and his team [22] compiles several works that focus their development on active monitoring systems for daily activities. It highlights a wide selection of Sensor-based human activity recognition (HAR) devices for the field of rehabilitation.…”

Section: Motion Capture Based On Inertial-magnetic Systemsmentioning

confidence: 99%

Proposal for Gait Analysis Using Fusion of Inertial-Magnetic and Optical Sensors

Callejas-Cuervo

Vélez-Guerrero

Alarcón-Aldana

2020

reveia

View full text Add to dashboard Cite

A proposed measurement protocol for the lower limbs movement analysis during walking is presented, with the use of a measurement system based on inertial-magnetic motion processing units and an optical system. Initially, the state of the art in terms of methods and tools for the biomechanical capture of movements is shown, to finally explore the protocols used in the health sciences for the gait analysis. The measurement proposal made in this document uses robust features of inertial-magnetic and optical technology that can be used in medical diagnosis. The application of this proposal can generate tools that have a positive impact in the fields of health and medicine.

show abstract

Section: Motion Capture Based On Inertial-magnetic Systemsmentioning

confidence: 99%

Proposal for Gait Analysis Using Fusion of Inertial-Magnetic and Optical Sensors

Callejas-Cuervo

Vélez-Guerrero

Alarcón-Aldana

2020

reveia

View full text Add to dashboard Cite

show abstract

“…In this regard, it would be critical to use a sensing technology that can accurately record the heart rate of workers. Advancements in embedded biosensor systems (e.g., heart rate and skin temperature sensors) have led to the development of wearable devices that can measure the impact of physical workload [ 22 , 23 ]. These wearable health devices are commercially available at an affordable price in the form of lightweight wristbands.…”

Section: Introductionmentioning

confidence: 99%

Practical Judgment of Workload Based on Physical Activity, Work Conditions, and Worker’s Age in Construction Site

Hashiguchi

Kodama

Lim

et al. 2020

Sensors

View full text Add to dashboard Cite

It is important for construction companies to sustain a productive workforce without sacrificing its health and safety. This study aims to develop a practical judgement method to estimate the workload risk of individual construction workers. Based on studies, we developed a workload model comprising a hygrothermal environment, behavioral information, and the physical characteristics of workers). The construction workers’ heart rate and physical activity were measured using the data collected from a wearable device equipped with a biosensor and an acceleration sensor. This study is the first report to use worker physical activity, age, and the wet bulb globe temperature (WBGT) to determine a worker’s physical workload. The accuracy of this health risk judgment result was 89.2%, indicating that it is possible to easily judge the health risk of workers even in an environment where it is difficult to measure the subject in advance. The proposed model and its findings can aid in monitoring the health impacts of working conditions during construction activities, and thereby contribute toward determining workers’ health damage. However, the sampled construction workers are 12 workers, further studies in other working conditions are required to accumulate more evidence and assure the accuracy of the models.

show abstract

“…There are two primary ways to extract features from sensor-based data. One employs hand-crafted features based on the statistical knowledge, while the other automatically extracts features using neural networks [8]. The extraction of meaningful hand-crafted features from the time and frequency domains relies heavily on human experience and domain knowledge.…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Network Based on Dense Connection and Weighted Feature Aggregation for Human Activity Recognition

Wang

Jin

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Human activity recognition (HAR) using body-worn sensors is an active research area in human-computer interaction and human activity analysis. The traditional methods use hand-crafted features to classify multiple activities, which is both heavily dependent on human domain knowledge and results in shallow feature extraction. Rapid developments in deep learning have caused most researchers to switch to deep learning methods, which extract features from raw data automatically. Most of the existing works on human activity recognition tasks involve multimodal sensor data, and these networks mainly focus on the top representation extracted from bottom-up feedforward process without reusing other features from bottom layers. In this paper, we present a novel hybrid deep learning network for human activity recognition that also employs multimodal sensor data; however, our proposed model is a ConvLSTM pipeline that makes full use of the information in each layer extracted along the temporal domain. Thus, we propose a dense connection module (DCM) to ensure maximum information flow between the network layers. Furthermore, we employ a multilayer feature aggregation module (MFAM) to extract features along the spatial domain, and we aggregate the features obtained from every convolutional layer according to the importance of features in different spatial locations. The output of the MFAM is input into two LSTM layers to further model the temporal dependencies. Finally, a fully connected layer and a softmax function are used to compute the probability of each class. We demonstrate the effectiveness of our proposed model on two benchmark datasets: Opportunity and UniMiB-SHAR. The results illustrate that our designed network outperforms the state-of-the-art models. We also conduct experiments on efficiency, multimodal fusion and different hyperparameters to analyze our proposed network. Finally, we carry out ablation and visualization experiments to reveal the effectiveness of the two proposed modules. INDEX TERMS Human activity recognition, deep learning, dense connection, multilayer feature aggregation, multimodal sensor data.

show abstract

A survey on wearable sensor modality centred human activity recognition in health care

Cited by 299 publications

References 207 publications

Proposal for Gait Analysis Using Fusion of Inertial-Magnetic and Optical Sensors

Proposal for Gait Analysis Using Fusion of Inertial-Magnetic and Optical Sensors

Practical Judgment of Workload Based on Physical Activity, Work Conditions, and Worker’s Age in Construction Site

A Hybrid Network Based on Dense Connection and Weighted Feature Aggregation for Human Activity Recognition

Contact Info

Product

Resources

About