Toward classification of swimming style by using underwater wireless accelerometer data

Kon, Yoshihisa; Omae, Yuto; Sakai, Kazuki; Takahashi, Hideya; Akiduki, Takuma; Miyaji, Chikara; Sakurai, Yoshihisa; Ezaki, Nobuo; Nakai, Kenta

doi:10.1145/2800835.2800875

Cited by 7 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Practically, however, it is often difficult to collect long-term data from a large number of subjects, both because subjects must be experienced at specific skills and because of concerns regarding fatigue and injuries. Therefore, many studies have constructed human body motion classifiers using training data collected from a small number of subjects [1][2][3][4][5][6]. In contrast, training data from a small number of subjects is susceptible to generalization errors caused by individual and trial differences.…”

Section: Resultsmentioning

confidence: 99%

“…We represent trial differences by adding variance to the obtained barycentric coordinates and spreading them (i.e., the variance added to the barycentric coor- 14is constructed by Eqs. (6) and (12). dinates, which represent individual differences, represents trial differences.)…”

Section: Probability Distributions Of Trial Differencesmentioning

confidence: 96%

“…For instance, Khan et al [1] used a neural network (NN) to classify such motions as walking, running, sitting down, and standing up using sensor data acquired from six subjects; Lester et al [2] used a hidden Markov model (HMM) to classify such motions as walking, running, brushing teeth, and riding an elevator using sensor data acquired from 12 subjects; He et al [3] used a support vector machine (SVM) to classify such motions as walking, running, and jumping using sensor data acquired from 11 subjects; Ward et al [4] used HMM to classify such motions as assembly work (using drills and vises) using sensor data acquired from five subjects; Siirtola et al [5] classified motions such as swimming strokes (backstroke, crawl, turn, etc.) using sensor data acquired from 11 subjects; Kon et al [6] using a decision tree (DT) with sensor data acquired from one subject. Classifiers constructed with data acquired from a limited number of subjects may experience problems due to individual and trial differences.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Feature Selection Algorithm Considering Trial and Individual Differences for Machine Learning of Human Activity Recognition

Omae¹,

Takahashi²

2017

JACIII

Self Cite

View full text Add to dashboard Cite

In recent years, many studies have been performed on the automatic classification of human body motions based on inertia sensor data using a combination of inertia sensors and machine learning; training data is necessary where sensor data and human body motions correspond to one another. It can be difficult to conduct experiments involving a large number of subjects over an extended time period, because of concern for the fatigue or injury of subjects. Many studies, therefore, allow a small number of subjects to perform repeated body motions subject to classification, to acquire data on which to build training data. Any classifiers constructed using such training data will have some problems associated with generalization errors caused by individual and trial differences. In order to suppress such generalization errors, feature spaces must be obtained that are less likely to generate generalization errors due to individual and trial differences. To obtain such feature spaces, we require indices to evaluate the likelihood of the feature spaces generating generalization errors due to individual and trial errors. This paper, therefore, aims to devise such evaluation indices from the perspectives. The evaluation indices we propose in this paper can be obtained by first constructing acquired data probability distributions that represent individual and trial differences, and then using such probability distributions to calculate any risks of generating generalization errors. We have verified the effectiveness of the proposed evaluation method by applying it to sensor data for butterfly and breaststroke swimming. For the purpose of comparison, we have also applied a few available existing evaluation methods. We have constructed classifiers for butterfly and breaststroke swimming by applying a support vector machine to the feature spaces obtained by the proposed and existing methods. Based on the accuracy verification we conducted with test data, we found that the proposed method produced significantly higher F-measure than the existing methods. This proves that the use of the proposed evaluation indices enables us to obtain a feature space that is less likely to generate generalization errors due to individual and trial differences.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Probability Distributions Of Trial Differencesmentioning

confidence: 96%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Feature Selection Algorithm Considering Trial and Individual Differences for Machine Learning of Human Activity Recognition

Omae¹,

Takahashi²

2017

JACIII

Self Cite

View full text Add to dashboard Cite

show abstract

“…Swimming is a good activity workout because the body needs to be moved as a whole against the resistance of water [16]. Coaching the swimmers with the innovative technologies is aiding to avoid injuries that happened during swimming [4,6,11,12]. The British journal of sports medicine stated that 91% out of 80 young elite swimmers 13-25 years old are reported as cases of shoulder pain due to wrong hand and arm movements [18].…”

Section: Introductionmentioning

confidence: 99%

ISwimCoach: A Smart Coach guiding System for Assisting Swimmers Free Style Strokes

Ehab

Mohamed

Ahmed

et al. 2020

Companion Publication of the 2020 International Conference on Multimodal Interaction

View full text Add to dashboard Cite

“…Research work of [4] presents only breaststroke phase identification using inertialsensor worn on the arm and other on the leg. Android phoneworn on the arm was used in [5] to perform stroke recognition.Back worn IMU sensor was used to perform kinematic analysis [6] of a swimmer and tracking of swimming styles [7] as well as classification of them [8]. A chest-worn accelerometer was used in [9] to classify swimming stroke styles.…”

mentioning

confidence: 99%

Uni-Directional and Bi-Directional LSTM Comparison on Sensor Based Swimming Data

Tarasevičius¹

2020

IJAR

View full text Add to dashboard Cite

This paper aim is to present the deep learning model comparison for swimming style recognition using publicly available sensor data and provide a comparison of Uni-directional LSTM(Long-Short Term Memory) and Bi-directional LSTM. Both neural networks were constructed using MATLAB neural network toolbox. Data for the neural networks was prepared by segmenting data into fixed size windows with overlap. To reduce the computational cost five features from time domain signal were extracted: Signal Magnitude Area (SMA), median absolute deviation (MAD), interquartile range (IQR), mean and standart deviation. And five features from frequency domain signal: entropy, energy, kurtosis, skewness and index of frequency domain signal. These features were extracted from every window. The Uni-directional LSTM was able to perform with F1-score of 87.66 % and Bi-directional LSTM with F1-score of 90.35 %.

show abstract

Toward classification of swimming style by using underwater wireless accelerometer data

Cited by 7 publications

References 5 publications

Feature Selection Algorithm Considering Trial and Individual Differences for Machine Learning of Human Activity Recognition

Feature Selection Algorithm Considering Trial and Individual Differences for Machine Learning of Human Activity Recognition

ISwimCoach: A Smart Coach guiding System for Assisting Swimmers Free Style Strokes

Uni-Directional and Bi-Directional LSTM Comparison on Sensor Based Swimming Data

Contact Info

Product

Resources

About