Human activity recognition on raw sensor data via sparse approximation

Dohnálek, Pavel; Gajdoš, Petr; Peterek, Tomáš

doi:10.1109/tsp.2013.6614027

Cited by 12 publications

(10 citation statements)

References 9 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Intuitive control can be developed by extracting the user's intention from signals recorded in a non-invasive way [through surface EMG electrodes (sEMG; Dohnalek et al, 2013 ), ultrasound imaging (Gonzales and Castellini, 2013 ), force myography (FMG; Wininger et al, 2008 )] or else in an invasive way [by means of Implantable Myoelectric Sensors (IMES; Pasquina et al, 2015 ), neural interfaces (Dhillon et al, 2004 )] from the Peripheral or Central Nervous System. Invasive surgical procedures, such as Targeted Muscle Reinnervation (TMR), have been applied in some cases of very proximal limb loss to allow an intuitive prosthesis control through myoelectric interfaces.…”

Section: Introductionmentioning

confidence: 99%

“…In order to overcome these limitations, several approaches have been proposed, such as ultrasound imaging (Gonzales and Castellini, 2013 ), FMG (Wininger et al, 2008 ), TMR (Hijjawi et al, 2006 ; Miller et al, 2008 ), pattern recognition techniques (Cloutier and Yang, 2013 ) applied to EMG signals acquired through implantable (IMES; Pasquina et al, 2015 ) or surface electrodes (Dohnalek et al, 2013 ), and neural signals acquired through implantable neural interfaces (Dhillon et al, 2004 ; Polasek et al, 2009 ; Rossini et al, 2010 ).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Literature Review on Needs of Upper Limb Prosthesis Users

et al. 2016

View full text Add to dashboard Cite

The loss of one hand can significantly affect the level of autonomy and the capability of performing daily living, working and social activities. The current prosthetic solutions contribute in a poor way to overcome these problems due to limitations in the interfaces adopted for controlling the prosthesis and to the lack of force or tactile feedback, thus limiting hand grasp capabilities. This paper presents a literature review on needs analysis of upper limb prosthesis users, and points out the main critical aspects of the current prosthetic solutions, in terms of users satisfaction and activities of daily living they would like to perform with the prosthetic device. The ultimate goal is to provide design inputs in the prosthetic field and, contemporary, increase user satisfaction rates and reduce device abandonment. A list of requirements for upper limb prostheses is proposed, grounded on the performed analysis on user needs. It wants to (i) provide guidelines for improving the level of acceptability and usefulness of the prosthesis, by accounting for hand functional and technical aspects; (ii) propose a control architecture of PNS-based prosthetic systems able to satisfy the analyzed user wishes; (iii) provide hints for improving the quality of the methods (e.g., questionnaires) adopted for understanding the user satisfaction with their prostheses.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Literature Review on Needs of Upper Limb Prosthesis Users

et al. 2016

View full text Add to dashboard Cite

show abstract

“…The scaled “raw” sEMG data were directly used as input for the NLR model, without performing any features extraction. The use of only “raw” sEMG signals allowed a significant reduction of the classification time and of the response time without loss of system performance (Nazarpour, 2005; Dohnalek et al, 2013; Benatti et al, 2014). Moreover, the use of “raw” scaled sEMG signals (Figure 3) as input features approximated the class evaluation time and system readiness to the sampling time (Bellingegni et al, 2017).…”

Section: Methodsmentioning

confidence: 99%

Simultaneous sEMG Classification of Hand/Wrist Gestures and Forces

et al. 2019

View full text Add to dashboard Cite

Surface electromyography (sEMG) signals represent a promising approach for decoding the motor intention of amputees to control a multifunctional prosthetic hand in a non-invasive way. Several approaches based on proportional amplitude methods or simple thresholds on sEMG signals have been proposed to control a single degree of freedom at time, without the possibility of increasing the number of controllable multiple DoFs in a natural manner. Myoelectric control based on PR techniques have been introduced to add multiple DoFs by keeping low the number of electrodes and allowing the discrimination of different muscular patterns for each class of motion. However, the use of PR algorithms to simultaneously decode both gestures and forces has never been studied deeply. This paper introduces a hierarchical classification approach with the aim to assess the desired hand/wrist gestures, as well as the desired force levels to exert during grasping tasks. A Finite State Machine was introduced to manage and coordinate three classifiers based on the Non-Linear Logistic Regression algorithm. The classification architecture was evaluated across 31 healthy subjects. The “hand/wrist gestures classifier,” introduced for the discrimination of seven hand/wrist gestures, presented a mean classification accuracy of 98.78%, while the “Spherical and Tip force classifier,” created for the identification of three force levels, reached an average accuracy of 98.80 and 96.09%, respectively. These results were confirmed by Linear Discriminant Analysis (LDA) with time domain features extraction, considered as ground truth for the final validation of the performed analysis. A Wilcoxon Signed-Rank test was carried out for the statistical analysis of comparison between NLR and LDA and statistical significance was considered at p < 0.05. The comparative analysis reports not statistically significant differences in terms of F1Score performance between NLR and LDA. Thus, this study reveals that the use of non-linear classification algorithm, as NLR, is as much suitable as the benchmark LDA classifier for implementing an EMG pattern recognition system, able both to decode hand/wrist gestures and to associate different performed force levels to grasping actions.

show abstract

“…In Hargrove et al ( 2007 ) the effects of the choice of feature sets over classifier performance are in-depth investigated. Moreover, methods based on “raw” filtered EMG signals have been recently proposed; they allow considerably decreasing the time for feature extraction and skipping the feature reduction step without significant loss of system performance (Nazarpour, 2005 ; Dohnalek et al, 2013 ).…”

Section: Prosthetic Hand Controlmentioning

confidence: 99%

Control of Prosthetic Hands via the Peripheral Nervous System

et al. 2016

View full text Add to dashboard Cite

This paper intends to provide a critical review of the literature on the technological issues on control and sensorization of hand prostheses interfacing with the Peripheral Nervous System (i.e., PNS), and their experimental validation on amputees. The study opens with an in-depth analysis of control solutions and sensorization features of research and commercially available prosthetic hands. Pros and cons of adopted technologies, signal processing techniques and motion control solutions are investigated. Special emphasis is then dedicated to the recent studies on the restoration of tactile perception in amputees through neural interfaces. The paper finally proposes a number of suggestions for designing the prosthetic system able to re-establish a bidirectional communication with the PNS and foster the prosthesis natural control.

show abstract

Human activity recognition on raw sensor data via sparse approximation

Cited by 12 publications

References 9 publications

Literature Review on Needs of Upper Limb Prosthesis Users

Literature Review on Needs of Upper Limb Prosthesis Users

Simultaneous sEMG Classification of Hand/Wrist Gestures and Forces

Control of Prosthetic Hands via the Peripheral Nervous System

Contact Info

Product

Resources

About