Klasifikasi Teknik Squat Pound Fitness Amatir Menggunakan Deep Learning Berdasarkan Estimasi Pose Manusia

Rubiagatra, Doni (2024) Klasifikasi Teknik Squat Pound Fitness Amatir Menggunakan Deep Learning Berdasarkan Estimasi Pose Manusia. Masters thesis, Institut Teknologi Sepuluh Nopember.

Text 6022221031-Master_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (1MB) | Request a copy

Abstract

Aplikasi olahraga yang didukung AI, seperti pelacak kebugaran, olahraga virtual, dan pelatih AI, telah menjadi semakin populer selama dan setelah pandemi. Pelatih AI dapat menyediakan program latihan yang disesuaikan dengan kebutuhan individu, sementara aplikasi olahraga virtual memungkink- an orang untuk berolahraga di rumah. Pound Fitness adalah olahraga yang menggabungkan gerakan tari dengan latihan beban tubuh menggunakan stik drum, yang semakin populer di kalangan masyarakat. Tujuan dari penelitian ini adalah untuk menunjukkan bahwa teknologi estimasi pose manusia dapat digunakan untuk mengukur kinerja atlet dalam gerakan Pound Fitness secara akurat. Dalam penelitian ini, kami mengumpulkan data melalui rekaman video dari depan sesi Pound Fitness, melibatkan dua kelompok, masing- masing terdiri dari lima individu selama empat minggu, untuk mengevaluasi perkembangan akurasi dan kinerja gerakan mereka. Kelompok A terdiri dari 5 individu yang berpartisipasi dalam latihan Pound Fitness sekali seminggu, dan Kelompok B terdiri dari 5 individu berbeda yang berpartisipasi dalam latihan Pound Fitness dua kali seminggu. Temuan kami mengungkapkan peningkatan nyata dalam kedua kelompok, menunjukkan korelasi positif antara latihan rutin dan peningkatan kinerja. Secara khusus, latihan yang lebih sering menghasilkan kemajuan yang konsisten, sementara sesi intensitas tinggi yang kurang sering menghasilkan lonjakan kinerja signifikan untuk beberapa individu. Hasil ini menunjukkan potensi keuntungan dalam mendiversifikasi frekuensi dan intensitas latihan untuk mengoptimalkan hasil kebugaran.
===================================================================================================================================
AI-supported sports applications, such as fitness trackers, virtual sports, and AI coaches, have become increasingly popular during and after the pandemic. AI coaches can provide customized workout programs tailored to individual needs, while virtual sports applications enable people to exercise at home. Pound Fitness is a sport that combines dance movements with bodyweight exercises using drumsticks, which has gained pop- ularity among the community. The aim of this research is to demonstrate that human pose estimation technology can be used to accurately measure the performance of athletes in Pound Fitness movements. For this study, we collected data through front-facing video recordings of Pound Fitness sessions, involving two groups, each with five individuals over four weeks, to evaluate the progression in their movement accuracy and performance. Group A consisted of 5 individuals who participated in a Pound Fitness exercise once a week, and Group B consisted of 5 different individuals who participated in a Pound Fitness exercise twice a week. Our findings reveal tangible improvements in both groups, indicating a positive correlation between regular training and enhanced performance. Notably, more frequent training yielded consistent progress, whereas less frequent, high-intensity sessions resulted in significant performance leaps for certain individuals. These outcomes suggest a potential advantage in diversifying training frequency and intensity to optimize fitness results

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Human Pose Estimation, Pound Fitness, Deep Learning, Biomechanics,Pose Estimasi Manusia, Pound Fitness, Deep Learning, Biomekanika
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science. EDP Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) Q Science > QA Mathematics > QA9.58 Algorithms T Technology > T Technology (General) > T59.7 Human-machine systems. T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5105.888 Web sites--Design. Web site development.
Divisions:	Faculty of Electrical Technology > Electrical Engineering > 20101-(S2) Master Thesis
Depositing User:	Doni Rubiagatra
Date Deposited:	24 Jul 2024 04:22
Last Modified:	24 Jul 2024 04:22
URI:	http://repository.its.ac.id/id/eprint/108753

Actions (login required)

View Item