Inertial Measurement Unit-Based Wearable Computers for Assisted Living Applications: A signal processing perspective

Bennett, Terrell R.; Wu, Jian; Kehtarnavaz, Nasser; Jafari, Roozbeh

doi:10.1109/msp.2015.2499314

Cited by 130 publications

(132 citation statements)

References 28 publications

Supporting

Mentioning

132

Contrasting

Order By: Relevance

“…As presented in this table, our approach performs well in terms of accuracy in comparison with the literature methods. As shown in the confusion matrix presented in Figure 4, it Algorithm Accuracy (% ) Seidenari et al [20] 82.00 Anirudh et al [25] 89.67 Devanne et al [6] 87.04 Cippitelli et al [15] 76.10 Vemulapalli et al [23] 90.88 Ours 90.32 can be observed that the classes (5,6,7,9) are perfectly classified, while the classes 2 and 3 (drink from a bottle versus answer phone), present a high confusion rate. We can explain it because both classes involve human-object interaction which is not captured by the skeleton data.…”

Section: ) Human Action Recognitionmentioning

confidence: 76%

“…For elderly people, a fall may cause injury and induce a long hospitalization. Early recognition of fall before the person hits the ground is necessary to prevent injuries, by triggering the inflation of a wearable airbag for example [5]. In video games applications, latency is important [6] and the prior knowledge of the action is necessary to improve the response time.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Human Action Recognition from Body-Part Directional Velocity Using Hidden Markov Models

Talha

Fleury

Ambellouis³

2017

2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA)

View full text Add to dashboard Cite

This paper introduces a novel approach for early recognition of human actions using 3D skeleton joints extracted from 3D depth data. We propose a novel, frame-by-frame and real-time descriptor called Body-part Directional Velocity (BDV) calculated by considering the algebraic velocity produced by different body-parts. A real-time Hidden Markov Models algorithm with Gaussian Mixture Models state-output distributions is used to carry out the classification. We show that our method outperforms various state-of-the-art skeleton-based human action recognition approaches on MSRAction3D and Florence3D datasets. We also proved the suitability of our approach for early human action recognition by deducing the decision from a partial analysis of the sequence.

show abstract

Section: ) Human Action Recognitionmentioning

confidence: 76%

Section: Introductionmentioning

confidence: 99%

Human Action Recognition from Body-Part Directional Velocity Using Hidden Markov Models

Talha

Fleury

Ambellouis³

2017

2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA)

View full text Add to dashboard Cite

show abstract

“…the T-test or the mutual information) and then select the best N features [25]- [27]. It should be noted that similar processing steps are followed also for different types of sensors, such as wearable inertial measurement units (IMUs) as detailed in [13]. In the remainder of this section, details about the proposed techniques, their experimental validation, and their advantages and disadvantages will be discussed.…”

Section: Literature Review On Radar Systemsmentioning

confidence: 99%

Radar and RGB-Depth Sensors for Fall Detection: A Review

et al. 2017

View full text Add to dashboard Cite

Abstract-This paper reviews recent works in the literature on the use of systems based on Radar and RGB-Depth sensors for fall detection, and discusses outstanding research challenges and trends related to this research field. Systems to detect reliably fall events and promptly alert carers and first responders have gained significant interest in the past few years in order to address the societal issue of an increasing number of elderly people living alone, with the associated risk of them falling and the consequences in terms of health treatments, reduced well-being, and costs. The interest in radar and RGB-D sensors is related to their capability to enable contactless and non-intrusive monitoring, which is an advantage for practical deployment and users' acceptance and compliance, compared with other sensor technologies such as video-cameras, or wearables. Furthermore, the possibility of combining and fusing information from heterogeneous types of sensors is expected to improve the overall performance of practical fall detection systems. Researchers from different fields can benefit from multidisciplinary knowledge and awareness of the latest developments in radar and RGB-D sensors that this paper is discussing.

show abstract

“…The authors acknowledge support of EPSRC under grant "INSHEP" EP/R041679/1 and Doctoral Training Award supporting A. Shrestha in his PhD at the School of Engineering, University of Glasgow. active or passive radar principles [11][12][13][14][15]. Each sensing technology presents advantages and disadvantages inherent to its implementation and in aspects related to the required users' compliance or perception.…”

Section: Introductionmentioning

confidence: 99%

A Multisensory Approach for Remote Health Monitoring of Older People

Shrestha

Heidari

et al. 2018

IEEE J. Electromagn. RF Microw. Med. Biol.

View full text Add to dashboard Cite

Growing life expectancy and increasing incidence of multiple chronic health conditions are significant societal challenges. Different technologies have been proposed to address these issues, to detect critical events such as stroke or falls, and to monitor automatically human activities for health condition inference and anomalies detection. This paper aims to investigate two types of sensing technologies proposed for assisted living: wearable and radar sensors. First, different feature selection methods are validated and compared in terms of accuracy and computational loads. Then, information fusion is applied to enhance activity classification accuracy combining the two sensors. Improvements in classification accuracy of approximately 12% using feature level fusion is achieved with both Support Vector Machine and K Nearest Neighbor classifiers. Decision-level fusion schemes are also investigated, yielding classification accuracy in the order of 97-98%.

show abstract

Inertial Measurement Unit-Based Wearable Computers for Assisted Living Applications: A signal processing perspective

Cited by 130 publications

References 28 publications

Human Action Recognition from Body-Part Directional Velocity Using Hidden Markov Models

Human Action Recognition from Body-Part Directional Velocity Using Hidden Markov Models

Radar and RGB-Depth Sensors for Fall Detection: A Review

A Multisensory Approach for Remote Health Monitoring of Older People

Contact Info

Product

Resources

About