Statistical Analysis of Window Sizes and Sampling Rates in Human Activity Recognition

Niazi, Anzah H.; Yazdansepas, Delaram; Maier, Frederick; Ramaswamy, Lakshmish; Rasheed, Khaled; Buman, Matthew P.

doi:10.5220/0006148503190325

Cited by 20 publications

(13 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Triaxial IMUs can capture more data, which may improve classification accuracy, particularly for limb-based movements. 27 Sampling frequency ranged from 16 to 1000 Hz in the reviewed studies, and sensor measurement range varied from 8 to 16 g for the accelerometer, and 500 to 2000 degrees per second for the gyroscope. Although studies have shown that accuracy can be high when using a low sampling rate IMU, 6,14,17,23 only one study compared the accuracy of a high versus low sampling rate, when detecting fast bowling events in cricket.…”

Section: Discussionmentioning

confidence: 99%

“…Data segmentation involves arranging data into windows (segments of data), so that features can be extracted. Despite the potentially large impact that different window types and sizes can have on classification accuracy, 26,27 the comparison of window techniques is rarely performed, 22,36 especially when classifying sporting events.…”

Section: Discussionmentioning

confidence: 99%

Section: Balanced Accuracy Sensitivity + Specificitymentioning

confidence: 99%

See 2 more Smart Citations

Upper body activity classification using an inertial measurement unit in court and field-based sports: A systematic review

McGrath

Neville

Cronin

2020

Proceedings of the Institution of Mechanical Engineers, Part P:

View full text Add to dashboard Cite

Inertial measurement units (IMUs) are becoming increasingly popular in activity classification and workload measurement in sport. This systematic literature review focuses on upper body activity classification in court or field-based sports. The aim of this paper is to provide sport scientists and coaches with an overview of the past research in this area, as well as the processes and challenges involved in activity classification. The SPORTDiscus, PubMed and Scopus databases were searched, resulting in 20 articles. Both manually defined algorithms and machine learning approaches have been used to classify IMU data with varying degrees of success. Manually defined algorithms may offer simplicity and reduced computational demand, whereas machine learning may be beneficial for complex classification problems. Inter-study results show that no one machine learning model is best for activity classification; differences in sensor placement, IMU specification and pre-processing decisions can all affect model performance. Accurate classification of sporting activities could benefit players, coaches and team medical personnel by providing an objective estimate of workload. This could help to prevent injuries, enhance performance and provide valuable data to coaching staff.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Balanced Accuracy Sensitivity + Specificitymentioning

confidence: 99%

See 1 more Smart Citation

Upper body activity classification using an inertial measurement unit in court and field-based sports: A systematic review

McGrath

Neville

Cronin

2020

Proceedings of the Institution of Mechanical Engineers, Part P:

View full text Add to dashboard Cite

show abstract

“…The main goal of HAR is to recognize human physical activities from sensing data. In this research area many approaches were presented in the last decade [74,96,103,81]. These approaches vary depending on the sensor technologies used to collect the data, the machine learning algorithm and the features created to train the model.…”

Section: Related Workmentioning

confidence: 99%

“…Other authors have also discussed window size. For example, [10,54,9,74] compare the predictive performance of classifiers over a set of window sizes. However, most studies do not consider the use of overlap factor and the impact of the user on the obtained accuracy.…”

Section: Related Workmentioning

confidence: 99%

Unsupervised learning approaches for non-stationary data streams

Kemilly

View full text Add to dashboard Cite

show abstract

A Study on Hyperparameter Configuration for Human Activity Recognition

Garcia

Carvalho

Mendes‐Moreira

et al. 2019

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Human Activity Recognition is a machine learning task for the classification of human physical activities. Applications for that task have been extensively researched in recent literature, specially due to the benefits of improving quality of life. Since wearable technologies and smartphones have become more ubiquitous, a large amount of information about a person's life has become available. However, since each person has a unique way of performing physical activities, a Human Activity Recognition system needs to be adapted to the characteristics of a person in order to maintain or improve accuracy. Additionally, when smartphones devices are used to collect data, it is necessary to manage its limited resources, so the system can efficiently work for long periods of time.In this paper, we present a semi-supervised ensemble algorithm and an extensive study of the influence of hyperparameter configuration in classification accuracy. We also investigate how the classification accuracy is affected by the person and the activities performed. Experimental results show that it is possible to maintain classification accuracy by adjusting hyperparameters, like window size and window overlap, depending on the person and activity performed. These results motivate the development of a system able to automatically adapt hyperparameter settings for the activity performed by each person.

show abstract

Statistical Analysis of Window Sizes and Sampling Rates in Human Activity Recognition

Cited by 20 publications

References 6 publications

Upper body activity classification using an inertial measurement unit in court and field-based sports: A systematic review

Upper body activity classification using an inertial measurement unit in court and field-based sports: A systematic review

Unsupervised learning approaches for non-stationary data streams

A Study on Hyperparameter Configuration for Human Activity Recognition

Contact Info

Product

Resources

About