Motion artifact synthesis for research in biomedical signal quality analysis

Farago, Emma; Chan, Adrian D. C.

doi:10.1016/j.bspc.2021.102611

Cited by 6 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A summary of key research contributions in the field of AI-enhanced bioelectric signal processing in sports is presented in Table I: In the field of motion artifact data processing, Emma Farago et al delved into the application of three distinct AIbased methods: autoregressive models, Markov chain models, and recurrent neural network (RNN) models [129], Autoregressive models employ a linear combination of past observations to predict future values, offering simplicity and computational efficiency. Markov chain models, on the other hand, rely on the principle of 'memorylessness,' where the future state depends solely on the current state, making them suitable for systems with short-term dependencies.…”

Section: Ai Methods For Processing Bioelectric Signalsmentioning

confidence: 99%

A Review of Intelligent Garment System for Bioelectric Monitoring During Long-Lasting Intensive Sports

Shen,

Tao,

Koncar

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Bioelectric signals are significant indicators of the state of health of the human body, especially in sports monitoring, where athletes' fatigue state and performance need to be monitored in realtime to develop a proper training plan. Due to the characteristics of sports, it is difficult to obtain the dynamic bioelectrical signals of the human body during exercise. This paper provides a comprehensive overview of the current knowledge on Intelligent Garment Systems (IGS) for long-lasting bioelectric monitoring in sports. This review includes a detailed examination of human bioelectric signals, focusing on ECG, EMG, and GSR signals and their applications in intelligent wearable technologies. The definition and development history of IGS is also discussed, along with a review of the primary research components of IGS, including dry textile electrodes, methods for connecting sensors to IGS, and processing methods for bioelectric signals. The paper concludes by highlighting the current challenges faced by IGS in terms of real-time dynamic monitoring and connection problems and outlining the future directions for this field, including the need for further advancements in bioelectric signal processing and analysis, the development of new materials and connection technologies, and the integration of artificial intelligence and machine learning into IGS.

show abstract

Section: Ai Methods For Processing Bioelectric Signalsmentioning

confidence: 99%

A Review of Intelligent Garment System for Bioelectric Monitoring During Long-Lasting Intensive Sports

Shen,

Tao,

Koncar

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…This chapter details the development of a generative model to simulate diverse motion artifact for cyclic motions. This research has been published in Biomedical Signal Processing and Control [36].…”

Section: Chapter 9: Motion Artifact Synthesis For Research In Biomedi...mentioning

confidence: 99%

Biomedical Signal Quality Analysis for Electromyography

Farago

View full text Add to dashboard Cite

Electromyogram (EMG) signals can provide valuable insights into muscle activation and health;however, achieving high-quality signals is challenging. EMG signals are susceptible to contamination, and the acquisition of high-quality EMG signals often requires lengthy setup times and experienced technicians. EMG signal quality analysis is an important domain of research to increase EMG integration into clinical practice, wearable devices, and long-term monitoring. This thesis develops techniques to assess EMG signal quality to improve the ease of EMG acquisition.A literature review of methods for EMG signal quality analysis was conducted. Key areas for further research were identified, including improved selection of high-quality channels within EMG arrays.A process for establishing a ground truth of EMG signal quality based on expert human ratings was developed and used to label an EMG dataset. The intra-rater reliability ranged from 0.76-0.90, and the inter-rater agreement was 0.83, indicating good reliability and that the human rated datasets could be used for future assessments.An automated method of quantifying EMG signal quality was developed in two stages. In Stage I, poor-quality EMG channels were detected and reconstructed. An interpolation-based method of detecting and reconstructing poor-quality channels in high-density EMG (HD-EMG) was developed. Compared with two other detection methods (root mean square and normalized mutual information), the interpolation-based method was most effective for identifying poor iii channels in HD-EMG (precision 95.0%, recall 100%). Reconstruction of poor-quality channels was best performed with a 2-dimensional spline interpolation (correlation = 0.99).In Stage II, machine learning was explored to distinguish between adequate, good, and excellent channels. A random forest regression model provided the best overall result with Spearman correlations of 0.90, 0.91, 0.74, and 0.73 for inter-electrode distances of 10, 20, 30, and 40 mm, respectively. The recommended EMG feature set was an amplitude-based feature (e.g., root mean square) combined with frequency-based feature(s) (e.g., mean frequency). In single channel EMG, the Spearman correlation dropped to 0.55; however, there was potential to distinguish between adequate and excellent quality channels.The automated methods for quantifying EMG signal quality developed in this thesis will lead to improved efficiencies and lower costs for EMG acquisition. Ph.D. journey. I truly could not have asked for a more knowledgeable, dedicated, and supportive supervisor. I would like to extend my sincere thanks to Dr. Dawn MacIsaac for lending her immense expertise and insight to my research. I am immensely grateful to the entire team at the UNB Institute of Biomedical Engineering, and the members of the MacIsaac lab for extending their insights and support. I was also fortunate to have the opportunity to work with Dr. Andrew Law and Dr. Sujoy Ghosh Hajra. Their insights and research outlook inspired me to become a better researcher.Many...

show abstract

A deep learning approach to cardiovascular disease classification using empirical mode decomposition for ECG feature extraction

Luo

Dai

et al. 2023

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

Motion artifact synthesis for research in biomedical signal quality analysis

Cited by 6 publications

References 22 publications

A Review of Intelligent Garment System for Bioelectric Monitoring During Long-Lasting Intensive Sports

A Review of Intelligent Garment System for Bioelectric Monitoring During Long-Lasting Intensive Sports

Biomedical Signal Quality Analysis for Electromyography

A deep learning approach to cardiovascular disease classification using empirical mode decomposition for ECG feature extraction

Contact Info

Product

Resources

About