MiLift: Efficient Smartwatch-Based Workout Tracking Using Automatic Segmentation

Shen, Chenguang; Ho, Bo-Jhang; Srivastava, Mani

doi:10.1109/tmc.2017.2775641

Cited by 56 publications

(31 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Human activity recognition (HAR) is an important sub-field of human-computer interaction (HCI), with a rich body of work. HAR covers a broad range of tasks, including distinguishing activity from non-activity [5,6], activity classification [7] and repetition counting [5,6,8,9,10]. These tasks are interesting by themselves from a research perspective, but also have a wide range of potential real world applications, especially in the fields of healthcare and personal fitness.…”

Section: Related Workmentioning

confidence: 99%

Recognition and Repetition Counting for Complex Physical Exercises with Deep Learning

Soro

Brunner

Tanner

et al. 2019

Sensors

View full text Add to dashboard Cite

Activity recognition using off-the-shelf smartwatches is an important problem in humanactivity recognition. In this paper, we present an end-to-end deep learning approach, able to provideprobability distributions over activities from raw sensor data. We apply our methods to 10 complexfull-body exercises typical in CrossFit, and achieve a classification accuracy of 99.96%. We additionallyshow that the same neural network used for exercise recognition can also be used in repetitioncounting. To the best of our knowledge, our approach to repetition counting is novel and performswell, counting correctly within an error of 1 repetitions in 91% of the performed sets.

show abstract

Section: Related Workmentioning

confidence: 99%

Recognition and Repetition Counting for Complex Physical Exercises with Deep Learning

Soro

Brunner

Tanner

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…For example, type A reflectors (111A) reflect more light than type B reflectors (111B). Nevertheless, 3 Journal of Sensors both types of reflectors (A and B) reflect light to such an extent that it is possible to differentiate between such reflectors and the weight plate as well as between situations where there is an empty space and between weight plates, in front of a receiver (103).…”

Section: A Description Of the System Elementsmentioning

confidence: 99%

“…There are many devices on the market that allow one to, e.g., count the number of steps taken during a day or measure the heart rate while running (which is often combined with route-tracking capabilities). In most cases, these are wirelessly connected to mobile devices such as a smartphone, a smart armband, or a smartwatch [3]. Data gathered by such devices can be later used to calculate training statistics, which can be useful in determining what the subsequent stages of training should be, contributing to the achievement of one's personal development goals.…”

Section: Introductionmentioning

confidence: 99%

Sensor-Based Weightlifting Workout Assisting System Design and Its Practical Implementation

et al. 2019

View full text Add to dashboard Cite

The paper is devoted to the problem of counting repetitions and automatic weight stack detection in a weightlifting machine used for weight training. Some weightlifting machines include a weight stack that can be adjusted by a user. For example, the user can choose to increase or reduce the weight load using the weight stack, thus changing the difficulty level of a particular exercise. Users may want to perform a desired number of repetitions of an exercise or to perform an exercise with a desired range of motion when using such weightlifting machines. From a medical point of view, it is often required that an exact number of repetitions of a given load are performed in order to aid in a prompt recovery. This paper describes a complete design of the system and the algorithm that allows one to collect data from such a machine. Data can then be used for various purposes: in overviews and statistical analysis of a number of workouts. The approach presented in this paper is part of an application for European patent number 18461537.5-1126.

show abstract

“…and analyze them in real-time, while providing direct feedback and store data for further analysis. Compared to self-reports, sensor-captured data provide more accurate summaries of both cardiorespiratory and resistance exercise [ 27 ]. The smartphone's built-in inertial sensors ( i .…”

Section: Introductionmentioning

confidence: 99%

Using smartphone accelerometer data to obtain scientific mechanical-biological descriptors of resistance exercise training

Viecelli

Graf

Aguayo³

et al. 2020

PLoS ONE

View full text Add to dashboard Cite

Background Single repetition, contraction-phase specific and total time-under-tension (TUT) are crucial mechano-biological descriptors associated with distinct morphological, molecular and metabolic muscular adaptations in response to exercise, rehabilitation and/or fighting sarcopenia. However, to date, no simple, reliable and valid method has been developed to measure these descriptors. Objective In this study we aimed to test whether accelerometer data obtained from a standard smartphone placed on the weight stack can be used to extract single repetition, contraction-phase specific and total TUT. Methods Twenty-two participants performed two sets of ten repetitions of their 60% one repetition maximum with a self-paced velocity on nine commonly used resistance exercise machines. Two identical smartphones were attached on the resistance exercise weight stacks and recorded all user-exerted accelerations. An algorithm extracted the number of repetitions, single repetition, contraction-phase specific and total TUT. All exercises were videorecorded. The TUT determined from the algorithmically-derived mechano-biological descriptors was compared with the video recordings that served as the gold standard. The agreement between the methods was examined using Limits of Agreement (LoA). The association was calculated using the Pearson correlation coefficients and interrater reliability was determined using the intraclass correlation coefficient (ICC 2.1). Results The error rate of the algorithmic detection of single repetitions derived from two smartphones accelerometers was 0.16%. Comparing algorithmically-derived, contraction-phase

show abstract

MiLift: Efficient Smartwatch-Based Workout Tracking Using Automatic Segmentation

Cited by 56 publications

References 33 publications

Recognition and Repetition Counting for Complex Physical Exercises with Deep Learning

Recognition and Repetition Counting for Complex Physical Exercises with Deep Learning

Sensor-Based Weightlifting Workout Assisting System Design and Its Practical Implementation

Using smartphone accelerometer data to obtain scientific mechanical-biological descriptors of resistance exercise training

Contact Info

Product

Resources

About