Physical Workout Classification Using Wrist Accelerometer Data by Deep Convolutional Neural Networks
Recently, the deep learning algorithm has received considerable attention and is influencing different fields including human-computer interaction (HCI). The purpose of this study is to maximize accuracy by applying deep learning to the classification of body movements. An experiment was performed t...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8932483/ |
| id |
doaj-96e8472a2e894c7abb25112c18bb1d9d |
|---|---|
| record_format |
Article |
| spelling |
doaj-96e8472a2e894c7abb25112c18bb1d9d2021-03-30T00:39:39ZengIEEEIEEE Access2169-35362019-01-01718240618241410.1109/ACCESS.2019.29593988932483Physical Workout Classification Using Wrist Accelerometer Data by Deep Convolutional Neural NetworksPilyeong Jeong0https://orcid.org/0000-0002-5314-9605Mungyeong Choe1https://orcid.org/0000-0003-4964-1987Nahyeong Kim2https://orcid.org/0000-0001-5438-3359Jaehyun Park3https://orcid.org/0000-0002-5264-6941Jaeyong Chung4https://orcid.org/0000-0001-5819-1995Department of Electronics Engineering, Incheon National University (INU), Incheon, South KoreaDepartment of Industrial and Management Engineering, Incheon National University (INU), Incheon, South KoreaDepartment of Industrial and Management Engineering, Incheon National University (INU), Incheon, South KoreaDepartment of Industrial and Management Engineering, Incheon National University (INU), Incheon, South KoreaDepartment of Electronics Engineering, Incheon National University (INU), Incheon, South KoreaRecently, the deep learning algorithm has received considerable attention and is influencing different fields including human-computer interaction (HCI). The purpose of this study is to maximize accuracy by applying deep learning to the classification of body movements. An experiment was performed to collect acceleration information on the wrist while performing seven workouts: pull up, row-barbell, bench press, dips, squat, deadlift, and military press. Participants were asked to perform each workout for ten sets repeated ten times per set. Experimental results confirm that one-dimensional convolutional neural network was the best among different algorithms including support vector machine, multi-layer perceptron, long short-term memory, and other deep convolutional neural networks. The accuracy was extremely high, 96%. The results of this experiment are applicable not only to the classification of fitness activities but also to the classification of different motions in numerous sporting events.https://ieeexplore.ieee.org/document/8932483/Deep convolutional neural networksfitness workoutsphysical movementsaccelerometersmartwatches |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Pilyeong Jeong Mungyeong Choe Nahyeong Kim Jaehyun Park Jaeyong Chung |
| spellingShingle |
Pilyeong Jeong Mungyeong Choe Nahyeong Kim Jaehyun Park Jaeyong Chung Physical Workout Classification Using Wrist Accelerometer Data by Deep Convolutional Neural Networks IEEE Access Deep convolutional neural networks fitness workouts physical movements accelerometer smartwatches |
| author_facet |
Pilyeong Jeong Mungyeong Choe Nahyeong Kim Jaehyun Park Jaeyong Chung |
| author_sort |
Pilyeong Jeong |
| title |
Physical Workout Classification Using Wrist Accelerometer Data by Deep Convolutional Neural Networks |
| title_short |
Physical Workout Classification Using Wrist Accelerometer Data by Deep Convolutional Neural Networks |
| title_full |
Physical Workout Classification Using Wrist Accelerometer Data by Deep Convolutional Neural Networks |
| title_fullStr |
Physical Workout Classification Using Wrist Accelerometer Data by Deep Convolutional Neural Networks |
| title_full_unstemmed |
Physical Workout Classification Using Wrist Accelerometer Data by Deep Convolutional Neural Networks |
| title_sort |
physical workout classification using wrist accelerometer data by deep convolutional neural networks |
| publisher |
IEEE |
| series |
IEEE Access |
| issn |
2169-3536 |
| publishDate |
2019-01-01 |
| description |
Recently, the deep learning algorithm has received considerable attention and is influencing different fields including human-computer interaction (HCI). The purpose of this study is to maximize accuracy by applying deep learning to the classification of body movements. An experiment was performed to collect acceleration information on the wrist while performing seven workouts: pull up, row-barbell, bench press, dips, squat, deadlift, and military press. Participants were asked to perform each workout for ten sets repeated ten times per set. Experimental results confirm that one-dimensional convolutional neural network was the best among different algorithms including support vector machine, multi-layer perceptron, long short-term memory, and other deep convolutional neural networks. The accuracy was extremely high, 96%. The results of this experiment are applicable not only to the classification of fitness activities but also to the classification of different motions in numerous sporting events. |
| topic |
Deep convolutional neural networks fitness workouts physical movements accelerometer smartwatches |
| url |
https://ieeexplore.ieee.org/document/8932483/ |
| work_keys_str_mv |
AT pilyeongjeong physicalworkoutclassificationusingwristaccelerometerdatabydeepconvolutionalneuralnetworks AT mungyeongchoe physicalworkoutclassificationusingwristaccelerometerdatabydeepconvolutionalneuralnetworks AT nahyeongkim physicalworkoutclassificationusingwristaccelerometerdatabydeepconvolutionalneuralnetworks AT jaehyunpark physicalworkoutclassificationusingwristaccelerometerdatabydeepconvolutionalneuralnetworks AT jaeyongchung physicalworkoutclassificationusingwristaccelerometerdatabydeepconvolutionalneuralnetworks |
| _version_ |
1724188041868738560 |