TY - GEN
T1 - Cluster Dominance Analysis of Strength Training Motion Characteristics
AU - Toba, Hapnes
AU - Wianto, Elizabeth
AU - Malinda, Maya
AU - Al Halim, Agung Wijaya
AU - Chen, Chien Hsu
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - This paper presents an approach to analyze clusters as a means to determine the characteristics of strength training motion patterns. The proposed method emphasizes the observation of dominance sequences within clusters and is reinforced by the formation of specific characteristics within each cluster. Data collection is performed using video-guided strength training exercises equipped with 1 kg dumbbells and recorded by a sensor embedded in smartwatches. The analysis method involves applying the concept of density affinity, which calculates the density ratio of clusters to the recognized motions. Subsequently, the dominance sequence is observed to identify which clusters exhibit distinct characteristics, ultimately determining the intended motions. The research findings demonstrate the potential for further investigation into a more comprehensive understanding of motion patterns, leading to the development of models that can be integrated into mobile devices or smartwatches.
AB - This paper presents an approach to analyze clusters as a means to determine the characteristics of strength training motion patterns. The proposed method emphasizes the observation of dominance sequences within clusters and is reinforced by the formation of specific characteristics within each cluster. Data collection is performed using video-guided strength training exercises equipped with 1 kg dumbbells and recorded by a sensor embedded in smartwatches. The analysis method involves applying the concept of density affinity, which calculates the density ratio of clusters to the recognized motions. Subsequently, the dominance sequence is observed to identify which clusters exhibit distinct characteristics, ultimately determining the intended motions. The research findings demonstrate the potential for further investigation into a more comprehensive understanding of motion patterns, leading to the development of models that can be integrated into mobile devices or smartwatches.
UR - http://www.scopus.com/inward/record.url?scp=85179761234&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85179761234&partnerID=8YFLogxK
U2 - 10.1109/GCCE59613.2023.10315252
DO - 10.1109/GCCE59613.2023.10315252
M3 - Conference contribution
AN - SCOPUS:85179761234
T3 - GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics
SP - 1125
EP - 1128
BT - GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 12th IEEE Global Conference on Consumer Electronics, GCCE 2023
Y2 - 10 October 2023 through 13 October 2023
ER -