A Low-Cost System Using a Big-Data Deep-Learning Framework for Assessing Physical Telerehabilitation: A Proof-of-Concept

Abstract

The consolidation of telerehabilitation for the treatment of many diseases over the last decades is a consequence of its cost-effective results and its ability to offer access to rehabilitation in remote areas. Telerehabilitation operates over a distance, so vulnerable patients are never exposed to unnecessary risks. Despite its low cost, the need for a professional to assess therapeutic exercises and proper corporal movements online should also be mentioned. The focus of this paper is on a telerehabilitation system for patients suffering from Parkinson’s disease in remote villages and other less accessible locations. A full-stack is presented using big data frameworks that facilitate communication between the patient and the occupational therapist, the recording of each session, and real-time skeleton identification using artificial intelligence techniques. Big data technologies are used to process the numerous videos that are generated during the course of treating simultaneous patients. Moreover, the skeleton of each patient can be estimated using deep neural networks for automated evaluation of corporal exercises, which is of immense help to the therapists in charge of the treatment programs.

A Novel Deep Neural Network to Analyze and Monitoring the Physical Training Relation to Sports Activities

“…Exercise monitoring systems have been a topic of interest in the field of computer vision and machine learning for several years [10][11][12]. Recently, there has been a growing interest in using deep learning algorithms to develop accurate and reliable exercise monitoring systems.…”

“…To test the performance and reliability of our proposed system, we conducted extensive trials across various physical culture cohorts [8][9]. Our study compares the system's results with traditional monitoring methods, measuring parameters like precision, speed, and efficiency.…”

Fault diagnosis method for imbalanced and unlabeled data based on bayesian graph balanced learning

“…Despite advancements, a key challenge in practical scenarios is the simultaneous presence of imbalanced and unlabeled data [3,4]. This concurrent issue of imbalance and lack of labels compromises both the accuracy and the training process of diagnostic models [5][6][7][8]. Current research often addresses data imbalance and label scarcity separately, overlooking their coexistence in real-world applications.…”

Semi-supervised adaptive anti-noise meta-learning for few-shot industrial gearbox fault diagnosis

“…A series of semi-supervised methods [25][26][27] have been used to detect and diagnose industrial faults, achieving better diagnostic results. Semi-supervised learning [28,29] improves model performance by exploiting the information extracted from pseudo-labels in unlabeled samples.…”