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

Abstract

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.

Motion and Object Recognition for Crime Prediction and Forecasting: A Review

“…Similarly, in Property Monitoring, motion detection can help monitor a property for any unauthorized activity, triggering an alert that notifies authorities to respond. This shows that motion detection is an excellent way to recognize crime [24].…”

“…The process of choosing and extracting the most pertinent and educational aspects from raw data transformation is the process of changing the shape or structure of data and altering it. It is a critical step in analysis and data processing that helps to clean, normalize, and prepare data for remaining analysis, MODEL TRAINING-Trains the chosen machine learning algorithm using the training data, EVALUATION AND RESULT -give a few testing datasets to test the model, will give the output if its violent or not [24]. Same is shown in Fig 1 . we can observe the process for detection of violence.…”

Machine Learning Methods for Fault Diagnosis in AC Microgrids: A Systematic Review

“…As a result, a preprocessing stage is necessary in which the collected data is subjected to activities such as labeling [59], data normalization, outlier removal, and missing data treatment [58]. Further, in some applications, preprocessing may include resampling, data compression, and data splitting [60]. Overall, preprocessing can improve assessment accuracy by making the input data comparable and easier to analyze.…”

“…The validation data is used during the training process to assess the performance of the trained model. This is often done using cross validation techniques such as k-fold and leave-k subjects out [60]. The crossvalidation technique used depends on the characteristics of the dataset [60].…”

“…This is often done using cross validation techniques such as k-fold and leave-k subjects out [60]. The crossvalidation technique used depends on the characteristics of the dataset [60]. After training the model, the testing data is fed to the trained model to evaluate its performance since testing data is not seen during training phase.…”