Automatic Exercise Recognition with Machine Learning

Mendiola, Victor; Doss, Abnob; Adams, Will; Ramos, J. Humberto; Bruns, Matthew; Cherian, Josh; Kohli, Puneet; Goldberg, Daniel W.; Hammond, Tracy

doi:10.1007/978-3-030-24409-5_4

Cited by 5 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, commercially available devices are more practical for daily wear, are more likely to be worn by eventual users as they ofer other functionality, and do not have the social stigma that may be associated with the use of a prototype system [21]. These studies have focused on recognizing a wide range of mostly health-related activities [10,18,27] such as meal tracking [25,33,35], monitoring cleanliness (e.g., brushing teeth, showering) [11,14,21,30], and exercise encouragement [5,23,24,28]. This work builds upon this body of work and uses smartwatch accelerometer data and machine learning techniques to detect the action of putting on a seatbelt, an activity which, to our knowledge, has not yet been recognized in literature.…”

Section: Related Workmentioning

confidence: 99%

Recognizing Seatbelt-Fastening Behavior with Wearable Technology and Machine Learning

Leland

Stanfill

Cherian

et al. 2021

Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems

Self Cite

View full text Add to dashboard Cite

Nearly 1.35 million people are killed in automobile accidents every year, and nearly half of all individuals involved in these accidents were not wearing their seatbelt at the time of the crash. This lack of safety precaution occurs in spite of the numerous safety sensors and warning indicators embedded within modern vehicles. This presents a clear need for more efective methods of encouraging consistent seatbelt use. To that end, this work leverages wearable technology and activity recognition techniques to detect when individuals have buckled their seatbelt. To develop such a system, we collected smartwatch data from 26 diferent users. From this data, we identifed trends which inspired the development of novel features. Using these features, we trained models to identify the motion of fastening a seatbelt in real-time. This model serves as the basis for future work in which systems can provide personalized and efective interventions to ensure seatbelt use. CCS CONCEPTS• Computing methodologies → Machine learning algorithms; • Human-centered computing → Smartphones; Mobile devices; Mobile computing.

show abstract

Section: Related Workmentioning

confidence: 99%

Recognizing Seatbelt-Fastening Behavior with Wearable Technology and Machine Learning

Leland

Stanfill

Cherian

et al. 2021

Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…This recognition has been powered by a combination of sensors, located either on the body or in the environment, and machine learning techniques that have become increasingly adept at distinguishing among a variety of human behaviors and activities. Researchers have applied human activity recognition techniques to a diverse range of applications, including healthcare and well-being [ 1 , 2 , 3 , 4 ], weightlifting and sports [ 5 , 6 , 7 , 8 ], sign language translation [ 9 ], and car manufacturing and safety [ 10 , 11 ]. Within the area of healthcare and well-being, researchers have devoted particular attention to the recognition of activities of daily living (ADLs), as ADL performance is a key indicator of day-to-day health and wellness [ 12 , 13 , 14 ].…”

Section: Introductionmentioning

confidence: 99%

Exploring the Impact of the NULL Class on In-the-Wild Human Activity Recognition

Cherian,

Ray,

Taele

et al. 2024

Sensors

Self Cite

View full text Add to dashboard Cite

Monitoring activities of daily living (ADLs) plays an important role in measuring and responding to a person’s ability to manage their basic physical needs. Effective recognition systems for monitoring ADLs must successfully recognize naturalistic activities that also realistically occur at infrequent intervals. However, existing systems primarily focus on either recognizing more separable, controlled activity types or are trained on balanced datasets where activities occur more frequently. In our work, we investigate the challenges associated with applying machine learning to an imbalanced dataset collected from a fully in-the-wild environment. This analysis shows that the combination of preprocessing techniques to increase recall and postprocessing techniques to increase precision can result in more desirable models for tasks such as ADL monitoring. In a user-independent evaluation using in-the-wild data, these techniques resulted in a model that achieved an event-based F1-score of over 0.9 for brushing teeth, combing hair, walking, and washing hands. This work tackles fundamental challenges in machine learning that will need to be addressed in order for these systems to be deployed and reliably work in the real world.

show abstract

“…A naive solution is to simply hard code the major dimension for each exercise [ 19 ]. However, a better approach is to dynamically select the dimension with the highest variance [ 20 ]. This dimension is most likely the predominant exercise direction and will produce the most accurate results when counting peaks or troughs.…”

Section: Introductionmentioning

confidence: 99%

LEAN: Real-Time Analysis of Resistance Training Using Wearable Computing

Coates

Wahlström

2023

Sensors

View full text Add to dashboard Cite

The use of fitness apps to track physical exercise has been proven to promote weight loss and increase physical activity. The most popular forms of exercise are cardiovascular training and resistance training. The overwhelming majority of cardio tracking apps automatically track and analyse outdoor activity with relative ease. In contrast, nearly all commercially available resistance tracking apps only record trivial data, such as the exercise weight and repetition number via manual user input, a level of functionality not far from that of a pen and paper. This paper presents LEAN, a resistance training app and exercise analysis (EA) system for both the iPhone and Apple Watch. The app provides form analysis using machine learning, automatic repetition counting in real time, and other important but seldom studied exercise metrics, such as range of motion on a per-repetition level and average repetition time. All features are implemented using lightweight inference methods that enable real-time feedback on resource-constrained devices. The performance evaluation includes a user survey and benchmarking of all data science features using both ground-truth data from complementary modalities and comparisons with commercial apps.

show abstract

Automatic Exercise Recognition with Machine Learning

Cited by 5 publications

References 21 publications

Recognizing Seatbelt-Fastening Behavior with Wearable Technology and Machine Learning

Recognizing Seatbelt-Fastening Behavior with Wearable Technology and Machine Learning

Exploring the Impact of the NULL Class on In-the-Wild Human Activity Recognition

LEAN: Real-Time Analysis of Resistance Training Using Wearable Computing

Contact Info

Product

Resources

About