Activity Recognition Using Complex Network Analysis

Jalloul, Nahed; Porée, Fabienne; Viardot, Geoffrey; Hostis, Phillipe L; Carrault, Guy

doi:10.1109/jbhi.2017.2762404

Cited by 27 publications

(15 citation statements)

References 51 publications

(36 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then Jain et al [19] used two classifiers, support vector machine and k-nearest neighbor (KNN), to recognize the activities of two public datasets. Jalloul et al [20] used six inertial measurement units to construct a monitoring system. After performing network analysis, a number of network measures that satisfy the statistical test were selected to form a feature set, and then the authors used the random forest (RF) classifier to classify the activities.…”

Section: Related Workmentioning

confidence: 99%

LSTM-CNN Architecture for Human Activity Recognition

2020

View full text Add to dashboard Cite

In the past years, traditional pattern recognition methods have made great progress. However, these methods rely heavily on manual feature extraction, which may hinder the generalization model performance. With the increasing popularity and success of deep learning methods, using these techniques to recognize human actions in mobile and wearable computing scenarios has attracted widespread attention. In this paper, a deep neural network that combines convolutional layers with long short-term memory (LSTM) was proposed. This model could extract activity features automatically and classify them with a few model parameters. LSTM is a variant of the recurrent neural network (RNN), which is more suitable for processing temporal sequences. In the proposed architecture, the raw data collected by mobile sensors was fed into a two-layer LSTM followed by convolutional layers. In addition, a global average pooling layer (GAP) was applied to replace the fully connected layer after convolution for reducing model parameters. Moreover, a batch normalization layer (BN) was added after the GAP layer to speed up the convergence, and obvious results were achieved. The model performance was evaluated on three public datasets (UCI, WISDM, and OPPORTUNITY). Finally, the overall accuracy of the model in the UCI-HAR dataset is 95.78%, in the WISDM dataset is 95.85%, and in the OPPORTUNITY dataset is 92.63%. The results show that the proposed model has higher robustness and better activity detection capability than some of the reported results. It can not only adaptively extract activity features, but also has fewer parameters and higher accuracy. INDEX TERMS Human activity recognition, convolution, long short-term memory, mobile sensors.

show abstract

Section: Related Workmentioning

confidence: 99%

LSTM-CNN Architecture for Human Activity Recognition

2020

View full text Add to dashboard Cite

show abstract

“…As regards the location, as Fig. 1 shows, the sensors can be placed at 17 different locations on a patient's body [6] [25] and can monitor 63 kinds of physical activity in a person's body.…”

Section: B Cross-analysis Between Characteristics and Functional Requirements Identifiedmentioning

confidence: 99%

New intelligent network approach for monitoring physiological parameters: the case of Benin

et al. 2020

View full text Add to dashboard Cite

Benin health system is facing many challenges as: (i) affordable high-quality health care to a growing population providing need, (ii) patients' hospitalization time reduction, (iii) and presence time of the nursing staff optimization. Such challenges can be solved by remote monitoring of patients. To achieve this, five steps were followed. 1) Identification of the Wireless Body Area Network (WBAN) systems' characteristics and the patient physiological parameters' monitoring. 2) The national Integrated Patient Monitoring Network (RIMP) architecture modeling in a cloud of Technocenters. 3) Cross-analysis between the characteristics and the functional requirements identified. 4) Each Technocenter's functionality simulation through: a) the design approach choice inspired by the life cycle of V systems; b) functional modeling through SysML Language; c) the communication technology and different architectures of sensor networks choice studying. 5) An estimate of the material resources of the national RIMP according to physiological parameters. A National Integrated Network for Patient Monitoring (RNIMP) remotely, ambulatory or not, was designed for Beninese health system. The implementation of the RNIMP will contribute to improve patients' care in Benin. The proposed network is supported by a repository that can be used for its implementation, monitoring and evaluation. It is a table of 36 characteristic elements each of which must satisfy 5 requirements relating to: medical application, design factors, safety, performance indicators and materiovigilance.

show abstract

“…In this section we briefly reviewed some of the existing approaches. A list of recent researches on activity detection using different types of sensors and classification methods, and under different data acquisition protocols have been provided in [16]. Mukhopadhyay [5] reviewed different technologies and systems available for human activity monitoring based on wearable sensors.…”

Section: A Related Work On Iot-based Healthcare Systemsmentioning

confidence: 99%

A Secure IoT-Based Modern Healthcare System With Fault-Tolerant Decision Making Process

Gope

Gheraibia

Kabir

et al. 2021

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

The advent of Internet of Things (IoT) has escalated the information sharing among various smart devices by many folds, irrespective of their geographical locations. Recently, applications like e-healthcare monitoring has attracted wide attention from the research community, where both the security and the effectiveness of the system are greatly imperative. However, to the best of our knowledge none of the existing literature can accomplish both these objectives (e.g., existing systems are not secure against physical attacks). This paper addresses the shortcomings in existing IoT-based healthcare system. We propose an enhanced system by introducing a Physical Unclonable Function (PUF)-based authentication scheme and a data driven fault-tolerant decision-making scheme for designing an IoT-based modern healthcare system. Analyses show that our proposed scheme is more secure and efficient than existing systems. Hence, it will be useful in designing an advanced IoT-based healthcare system.

show abstract

Activity Recognition Using Complex Network Analysis

Cited by 27 publications

References 51 publications

LSTM-CNN Architecture for Human Activity Recognition

LSTM-CNN Architecture for Human Activity Recognition

New intelligent network approach for monitoring physiological parameters: the case of Benin

A Secure IoT-Based Modern Healthcare System With Fault-Tolerant Decision Making Process

Contact Info

Product

Resources

About