A Wearable Device based on IMU and EMG Sensors for Remote Monitoring of Elbow Rehabilitation

Lavado, Diego; Vela, Emir A.

doi:10.1109/ehb55594.2022.9991526

Cited by 2 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of the studies (n = 26, 84% of clinical population studies) exploited IMU sensors in their wearable platform (usually containing a 3-axis accelerometer, 3-axis gyroscope, and 3-axis magnetometer) to obtain joint angles, accelerations, angular velocities, and posture. While only five studies have included EMG sensors in their wearable platform to obtain muscle activity [30,[38][39][40][41]. Some of the studies have also used other instruments and sensors to obtain measurements or treat an MSK condition, such as using high-power LEDs [42] and thermal flexible printed circuit boards for treatment [32] or using piezoresistive or strain sensors for measurements [35][36][37]43].…”

Section: Clinical Population Studiesmentioning

confidence: 99%

“…One of the critical aspects is finding the rate of studies aimed to use wearable sensor platforms for either rehabilitation or treatment applications or increasing the quality of remote treatment sessions. In this regard, 11 studies in the clinical population studies category (35% of studies in the category) [26,27,29,32,33,36,37,40,[42][43][44], three studies in the workers' population studies category (10% of studies in the category) [62,80,85], and two studies in the general wearable studies category (11% of studies in the category) have focused on treatment applications [87,98].…”

Section: General Wearable Design/performance Studiesmentioning

confidence: 99%

See 1 more Smart Citation

Applications of wearable sensors in upper extremity MSK conditions: a scoping review

Zadeh,

MacDermid,

Johnson

et al. 2023

J NeuroEngineering Rehabil

View full text Add to dashboard Cite

Purpose This scoping review uniquely aims to map the current state of the literature on the applications of wearable sensors in people with or at risk of developing upper extremity musculoskeletal (UE-MSK) conditions, considering that MSK conditions or disorders have the highest rate of prevalence among other types of conditions or disorders that contribute to the need for rehabilitation services. Materials and methods The preferred reporting items for systematic reviews and meta-analysis (PRISMA) extension for scoping reviews guideline was followed in this scoping review. Two independent authors conducted a systematic search of four databases, including PubMed, Embase, Scopus, and IEEEXplore. We included studies that have applied wearable sensors on people with or at risk of developing UE-MSK condition published after 2010. We extracted study designs, aims, number of participants, sensor placement locations, sensor types, and number, and outcome(s) of interest from the included studies. The overall findings of our scoping review are presented in tables and diagrams to map an overview of the existing applications. Results The final review encompassed 80 studies categorized into clinical population (31 studies), workers’ population (31 studies), and general wearable design/performance studies (18 studies). Most were observational, with 2 RCTs in workers’ studies. Clinical studies focused on UE-MSK conditions like rotator cuff tear and arthritis. Workers’ studies involved industrial workers, surgeons, farmers, and at-risk healthy individuals. Wearable sensors were utilized for objective motion assessment, home-based rehabilitation monitoring, daily activity recording, physical risk characterization, and ergonomic assessments. IMU sensors were prevalent in designs (84%), with a minority including sEMG sensors (16%). Assessment applications dominated (80%), while treatment-focused studies constituted 20%. Home-based applicability was noted in 21% of the studies. Conclusion Wearable sensor technologies have been increasingly applied to the health care field. These applications include clinical assessments, home-based treatments of MSK disorders, and monitoring of workers’ population in non-standardized areas such as work environments. Assessment-focused studies predominate over treatment studies. Additionally, wearable sensor designs predominantly use IMU sensors, with a subset of studies incorporating sEMG and other sensor types in wearable platforms to capture muscle activity and inertial data for the assessment or rehabilitation of MSK conditions.

show abstract

Section: Clinical Population Studiesmentioning

confidence: 99%

Section: General Wearable Design/performance Studiesmentioning

confidence: 99%

Applications of wearable sensors in upper extremity MSK conditions: a scoping review

Zadeh,

MacDermid,

Johnson

et al. 2023

J NeuroEngineering Rehabil

View full text Add to dashboard Cite

show abstract

Real-Time Gait Anomaly Detection Using 1D-CNN and LSTM

Rostovski,

Ahmadilivani,

Krivošei

et al. 2024

Communications in Computer and Information Science

View full text Add to dashboard Cite

Anomaly detection and fall prevention represent one of the key research areas within gait analysis for patients suffering from neurological disorders. Deep Learning has penetrated into healthcare applications, encompassing disease diagnosis and anomaly prediction. Connected wearable medical sensors are emerging due to computationally expensive machine learning tasks, which traditionally require use of remote PC or cloud computing. However, to reduce needs for wireless communication channel throughput, for data processing latency, and increase service reliability and safety, on device machine learning is gaining attention. This paper presents an innovative approach that leverages one dimensional convolutional neural network (1D-CNN) and long-short term memory (LSTM) neural network for the real-time detection of abnormal gait patterns during the step. Real-time anomaly detection pertains to the algorithm’s ability to promptly detect true gait abnormality occurrence during the swing phase of an ongoing step.For the experiments, we have collected eight different common gait anomalies, simulated by 22 persons, using motion sensors containing multidimensional inertial measurement units (IMUs).Results have demonstrated that the proposed 1D-CNN-AD algorithm achieves an average accuracy of 95% and an average F1-score of 88% for all gait types and can run in true real-time. Average earliness for 1D-CNN-AD algorithm was 0.6 s, which is mid-swing phase of the step. Proposed LSTM-AD algorithm achieved average accuracy of 87% and average F1-score of 70% for all gait types.

show abstract

A Wearable Device based on IMU and EMG Sensors for Remote Monitoring of Elbow Rehabilitation

Cited by 2 publications

References 12 publications

Applications of wearable sensors in upper extremity MSK conditions: a scoping review

Applications of wearable sensors in upper extremity MSK conditions: a scoping review

Real-Time Gait Anomaly Detection Using 1D-CNN and LSTM

Contact Info

Product

Resources

About