Self-Organizing Maps to Assess Rehabilitation Progress of Post-Stroke Patients

Sarwat, Hussein; Awad, Mohammed I.; Maged, Shady A.; Sarwat, Hassan

doi:10.1109/niles50944.2020.9257927

Cited by 2 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jerkiness is the derivative of acceleration and describes a motion's smoothness. Event-related features were used in 12 publications and characterize exercise-specific events [29], [31], [48], [50], [59], [60], [61], [62], [65], [84], [87], [91]. These can include the duration of an exercise or a sub-phase of an exercise (e.g., during the loading and release phases of a serve in tennis [31]).…”

Section: ) Feature Extraction Engineering and Selectionmentioning

confidence: 99%

“…The most commonly used subcategory was ensemble techniques, which combine multiple learning algorithms (primarily decision trees), with 17/51 publications using them [29], [46], [49], [52], [57], [60], [61], [64], [68], [73], [76], [79], [104], [112], [113], [119]. RF was used in 10/17 publications using ensemble techniques [29], [46], [52], [60], [61], [73], [76], [79], [112], [113], and eXtreme Gradient Boosting (XGBoost) was used in three publications [34], [65], [104]. Support Vector Machines (SVM) were also widely used, with 14/51 publications applying them, for both classification [3], [21], [31], [32], [33], [36], [63], [88], [89], [90], [100], [108], [111] and regression [3], [47].…”

Section: ) Model Trainingmentioning

confidence: 99%

“…Finally, four publications used generative DL algorithms. The algorithms used were Generative Adversarial Network (GAN) [70], Self-Organizing Map (SOM) [65], Transformer [82], and a combination of a Feed-forward neural network, SOM, and Nonlinear AutoRegressive Neural Network (NAR) [50]. Moreover, two publications used RL algorithms for their assessment, using a combination of Deep Q-network with Double Q-Learning (DQ), Markov Decision Process (MDP), and Artificial Neural Network [93], [94].…”

Section: ) Model Trainingmentioning

confidence: 99%

“…10 shows the type of assessment used in the publications. Of the ones that used classification, most (21/88) used binary classification [36], [39], [49], [55], [59], [60], [61], [65], [66], [71], [72], [79], [84], [101], [102], [105], [106], [111], [114], [117], [120]; that is, datasets were assessed using a dichotomous variable (e.g., normal or abnormal motion). Other often-used types of assessments were using 3-point ordinal scale values evaluated from rank-based classification approaches [35], [48], [54], [62], [63], [64], [68], [77], [83], [86], [87], [97], [98], [99], [103], [107], [108], [109], and score-based assessments evaluated using regression methods [31], [40], [44], [45], [46],…”

Section: ) Model Trainingmentioning

confidence: 99%

See 3 more Smart Citations

Assessing Human Motion During Exercise Using Machine Learning: A Literature Review

et al. 2022

View full text Add to dashboard Cite

The World Health Organization promotes healthy living through regular physical activities, such as exercise and sports, as well as access to healthcare and rehabilitation services for people with motor dysfunctions. However, there is a lack of specialized personnel and increased costs associated with such activities. These have led to the increased use of machine learning for the analysis and evaluation of human motion during exercise. To study the latest advancements in this area, a systematic literature review focusing on publications from 2017 to 2021 was performed. As a result, 88 relevant publications were identified, which developed both shallow machine learning and deep learning algorithms. The results indicated that algorithms for human motion assessment should provide personalized and informative assessments, with explainable and interpretable outcomes, that can be computed in real-time or concurrently with the execution of an exercise. Furthermore, they should be easy to adapt based on the needs of applications and should be able to perform with different motion capture systems. This has been challenging because of the usually small amount of collected data, the lack of large open datasets, and the unique characteristics of exercise motions. Based on the above findings, guidelines for the development of such algorithms are proposed and discussed. They relate to the selection of the type of assessment, handling data imbalances, selecting of motion capture technologies, balancing between accuracy and speed, selecting the right algorithm, performing concurrent assessment during an exercise, personalization and scalability, and evaluation.

show abstract