A More Efficient Transportable and Scalable System for Real-Time Activities and Exercises Recognition

Chapron, Kévin; Plantevin, Valère; Thullier, Florentin; Bouchard, Kévin; Duchesne, Élise; Gaboury, Sébastien

doi:10.3390/s18010268

Cited by 21 publications

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is one of the leading causes of disability and death worldwide. The majority of survivors have varying degrees of motor dysfunction 3 . It seriously affects the activities of stroke patients' daily lives.…”

Section: Introductionmentioning

confidence: 99%

Automatic Rehabilitation Exercise Task Assessment of Stroke Patients Based on Wearable Sensors with a Lightweight Multichannel 1D-CNN Model

Wang,

Li,

Zhang

et al. 2024

Preprint

View full text Add to dashboard Cite

Approximately 75% of stroke survivors have movement dysfunction. Rehabilitation exercises are capable of improving physical coordination. They are mostly conducted in the home environment without guidance from therapists. It is impossible to provide timely feedback on exercises without suitable devices or therapists. Human action quality assessment in the home setting is a challenging topic for current research. In this paper, a low-cost HREA system in which wearable sensors are used to collect exercise data and a multichannel 1D-CNN framework is used to automatically assess action quality. The proposed 1D-CNN model is first pretrained on the UCI-HAR dataset, and it achieves a performance of 91.96%. Then, five typical actions were selected from the Fugl-Meyer Assessment Scale for the experiment, wearable sensors were used to collect the participants’ exercise data, and experienced therapists were employed to assess participants’ exercise at the same time. Following the above process, a dataset was built based on the Fugl-Meyer scale. Based on the 1D-CNN model, a multichannel 1D-CNN model was built, and the average accuracy of the model on the dataset was 97.23%. This shows that the HREA system can be used in the home environment and help patients receive timely assessment feedback.

show abstract

Section: Introductionmentioning

confidence: 99%

Automatic Rehabilitation Exercise Task Assessment of Stroke Patients Based on Wearable Sensors with a Lightweight Multichannel 1D-CNN Model

Wang,

Li,

Zhang

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…On the other end, wearable technology has been proving to produce convincing and useful results in evaluating motor impairments of subjects suffering from (among others) Parkinson disease [10][11][12], attention deficit hyperactivity disorder/developmental coordination disorder (ADHD/DCD) [13], neuro-degenerative diseases [14], or spinal cord injury [15], when measured in a clinical environment, and in evaluating motor (dis)abilities of subjects when doing daily chores in home environment too [16][17][18]. The effective sensitivity of instruments as accelerometers, gyroscopes [19,20], and electromyography (EMG) [21], supports and extends the naked-eye analysis of the medical doctors [22] for the balance and gait analysis: Chapron et al adopted wearable IMUs on patients during physical rehabilitation programs within domestic environments [23]. Storm et al found that IMUs applied to the six-minute walk trial can provide clinically meaningful information [24].…”

Section: Introductionmentioning

confidence: 99%

Objective Assessment of Walking Impairments in Myotonic Dystrophy by Means of a Wearable Technology and a Novel Severity Index

et al. 2021

View full text Add to dashboard Cite

Myotonic dystrophy type 1 (DM1) is a genetic inherited autosomal dominant disease characterized by multisystem involvement, including muscle, heart, brain, eye, and endocrine system. Although several methods are available to evaluate muscle strength, endurance, and dexterity, there are no validated outcome measures aimed at objectively evaluating qualitative and quantitative gait alterations. Advantageously, wearable sensing technology has been successfully adopted in objectifying the assessment of motor disabilities in different medical occurrences, so that here we consider the adoption of such technology specifically for DM1. In particular, we measured motor tasks through inertial measurement units on a cohort of 13 DM1 patients and 11 healthy control counterparts. The motor tasks consisted of 16 meters of walking both at a comfortable speed and fast pace. Measured data consisted of plantar-flexion and dorsi-flexion angles assumed by both ankles, so to objectively evidence the footdrop behavior of the DM1 disease, and to define a novel severity index, termed SI-Norm2, to rate the grade of walking impairments. According to the obtained results, our approach could be useful for a more precise stratification of DM1 patients, providing a new tool for a personalized rehabilitation approach.

show abstract

Hybrid Deep-Readout Echo State Network and Support Vector Machine with Feature Selection for Human Activity Recognition

Abudalfa

Bouchard

2021

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

A More Efficient Transportable and Scalable System for Real-Time Activities and Exercises Recognition

Cited by 21 publications

References 28 publications

Automatic Rehabilitation Exercise Task Assessment of Stroke Patients Based on Wearable Sensors with a Lightweight Multichannel 1D-CNN Model

Automatic Rehabilitation Exercise Task Assessment of Stroke Patients Based on Wearable Sensors with a Lightweight Multichannel 1D-CNN Model

Objective Assessment of Walking Impairments in Myotonic Dystrophy by Means of a Wearable Technology and a Novel Severity Index

Hybrid Deep-Readout Echo State Network and Support Vector Machine with Feature Selection for Human Activity Recognition

Contact Info

Product

Resources

About