Deep Learning Approaches to Automated Video Classification of Upper Limb Tension Test

Choi, Wan-Suk; Heo, Seoyoon

doi:10.3390/healthcare9111579

Cited by 7 publications

(7 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, although the format is meticulously structured, some scopes of subjectivity are there. Yang et al (2007), [10] and Cui et al (2010), [11] on the other hand, have used digital 'Classifiers' for web video categorization. These are specifically designed software for classifying videos based on possible video features (training data set).…”

Section: Resultsmentioning

confidence: 99%

Categorization Format for YouTube Medical Educational Videos: An Experience with Embryology

Khan¹,

Yesmin²,

Shamim³

2023

AIMDR

View full text Add to dashboard Cite

Background: Users of YouTube videos face considerable difficulty in handling the rapidly growing uploaded material. Videos can fall into various genres, and a single video can possess a number of characteristics. Rationale- Customized selection of the most appropriate videos for learning, teaching or research is hard to achieve. Appropriate tagging of videos for different characteristics by the uploaders for helping audience in their selection warrant meticulously designed structured format for categorizing the videos based on multiple characteristics. But no complete structured format is available for such categorization. Material & Methods: A cross-sectional analysis of 120 YouTube medical educational videos on Embryology selected through a multiphase systematic method using search terms chosen from selected focus areas of Embryology was done. This was aimed at identifying video characteristics of four functional natures: basic, academic, technical and esthetic. Using the ‘identified’ and related ‘identifiable’ characteristics, a “Proposed categorization format” was developed. Feedback on this document was obtained from five stakeholder groups i.e., anatomists, medical educationists, medical video creators, film/video/graphics experts and postgraduate students of Anatomy through a multiple-group discussion session. Results: Consensuses built on their opinions and lone voices were incorporated to develop the “Final version” of the format that possesses 38 Broad Characteristics, 179 Options, 59 Suboptions and fourteen Sub-suboptions. Conclusion: This format should be helpful in establishing a comprehensive database of medical educational videos on Embryology and with slight customization, on other anatomical subdivisions and other disciplines. But before that validation of the format by putting them into use should be justified.

show abstract

Section: Resultsmentioning

confidence: 99%

Categorization Format for YouTube Medical Educational Videos: An Experience with Embryology

Khan¹,

Yesmin²,

Shamim³

2023

AIMDR

View full text Add to dashboard Cite

show abstract

“…The notable impact of our study on the field of health and physical education deserves mention. By critically evaluating these algorithms, we contribute to more precise and efficient data analyses, thereby enhancing the comprehension and prediction of health and physical activities [ 2 ].…”

Section: Discussionmentioning

confidence: 99%

“…Wearable sensor technology has been employed in studies of gait, balance, and range of motion. Recently, the use of high-performance automatic machine learning (AutoML) technology or deep learning methods has increased for posture estimation and kinematic analysis of human body motion [ 2 ]. Human posture estimation (HPE) is a longstanding research area in computer vision that involves estimation of the body [ 3 , 4 ].…”

Section: Introductionmentioning

confidence: 99%

A Comparative Study of Automated Machine Learning Platforms for Exercise Anthropometry-Based Typology Analysis: Performance Evaluation of AWS SageMaker, GCP VertexAI, and MS Azure

Choi

Choi²,

Heo

2023

Bioengineering

Self Cite

View full text Add to dashboard Cite

The increasing prevalence of machine learning (ML) and automated machine learning (AutoML) applications across diverse industries necessitates rigorous comparative evaluations of their predictive accuracies under various computational environments. The purpose of this research was to compare and analyze the predictive accuracy of several machine learning algorithms, including RNNs, LSTMs, GRUs, XGBoost, and LightGBM, when implemented on different platforms such as Google Colab Pro, AWS SageMaker, GCP Vertex AI, and MS Azure. The predictive performance of each model within its respective environment was assessed using performance metrics such as accuracy, precision, recall, F1-score, and log loss. All algorithms were trained on the same dataset and implemented on their specified platforms to ensure consistent comparisons. The dataset used in this study comprised fitness images, encompassing 41 exercise types and totaling 6 million samples. These images were acquired from AI-hub, and joint coordinate values (x, y, z) were extracted utilizing the Mediapipe library. The extracted values were then stored in a CSV format. Among the ML algorithms, LSTM demonstrated the highest performance, achieving an accuracy of 73.75%, precision of 74.55%, recall of 73.68%, F1-score of 73.11%, and a log loss of 0.71. Conversely, among the AutoML algorithms, XGBoost performed exceptionally well on AWS SageMaker, boasting an accuracy of 99.6%, precision of 99.8%, recall of 99.2%, F1-score of 99.5%, and a log loss of 0.014. On the other hand, LightGBM exhibited the poorest performance on MS Azure, achieving an accuracy of 84.2%, precision of 82.2%, recall of 81.8%, F1-score of 81.5%, and a log loss of 1.176. The unnamed algorithm implemented on GCP Vertex AI showcased relatively favorable results, with an accuracy of 89.9%, precision of 94.2%, recall of 88.4%, F1-score of 91.2%, and a log loss of 0.268. Despite LightGBM’s lackluster performance on MS Azure, the GRU implemented in Google Colab Pro displayed encouraging results, yielding an accuracy of 88.2%, precision of 88.5%, recall of 88.1%, F1-score of 88.4%, and a log loss of 0.44. Overall, this study revealed significant variations in performance across different algorithms and platforms. Particularly, AWS SageMaker’s implementation of XGBoost outperformed other configurations, highlighting the importance of carefully considering the choice of algorithm and computational environment in predictive tasks. To gain a comprehensive understanding of the factors contributing to these performance discrepancies, further investigations are recommended.

show abstract

“…In an approach similar to ours, several studies have trained time series machine learning models on single-camera pose keypoint data to predict gait parameters such as walking speed [ 31 , 32 ]. Other studies have used the transfer learning of pre-trained image classification models to classify videos of upper-limb tension tests on a single-frame basis [ 44 ]. Ref.…”

Section: Discussionmentioning

confidence: 99%

Physiotherapy Exercise Classification with Single-Camera Pose Detection and Machine Learning

Arrowsmith

Burns

Mak³

et al. 2022

Sensors

View full text Add to dashboard Cite

Access to healthcare, including physiotherapy, is increasingly occurring through virtual formats. At-home adherence to physical therapy programs is often poor and few tools exist to objectively measure participation. The aim of this study was to develop and evaluate the potential for performing automatic, unsupervised video-based monitoring of at-home low-back and shoulder physiotherapy exercises using a mobile phone camera. Joint locations were extracted from the videos of healthy subjects performing low-back and shoulder physiotherapy exercises using an open source pose detection framework. A convolutional neural network was trained to classify physiotherapy exercises based on the segments of keypoint time series data. The model’s performance as a function of input keypoint combinations was studied in addition to its robustness to variation in the camera angle. The CNN model achieved optimal performance using a total of 12 pose estimation landmarks from the upper and lower body (low-back exercise classification: 0.995 ± 0.009; shoulder exercise classification: 0.963 ± 0.020). Training the CNN on a variety of angles was found to be effective in making the model robust to variations in video filming angle. This study demonstrates the feasibility of using a smartphone camera and a supervised machine learning model to effectively classify at-home physiotherapy participation and could provide a low-cost, scalable method for tracking adherence to physical therapy exercise programs in a variety of settings.

show abstract

Deep Learning Approaches to Automated Video Classification of Upper Limb Tension Test

Cited by 7 publications

References 37 publications

Categorization Format for YouTube Medical Educational Videos: An Experience with Embryology

Categorization Format for YouTube Medical Educational Videos: An Experience with Embryology

A Comparative Study of Automated Machine Learning Platforms for Exercise Anthropometry-Based Typology Analysis: Performance Evaluation of AWS SageMaker, GCP VertexAI, and MS Azure

Physiotherapy Exercise Classification with Single-Camera Pose Detection and Machine Learning

Contact Info

Product

Resources

About