Deteksi Delayed Onset Muscle Soreness (DOMS) pada Latihan Interval Intensitas Tinggi dengan Metode Neural Network

Agustina, Florence Fedora (2022) Deteksi Delayed Onset Muscle Soreness (DOMS) pada Latihan Interval Intensitas Tinggi dengan Metode Neural Network. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 07311840000056_Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2024. Download (2MB) | Request a copy

Abstract

Latihan eksentrik yang umumnya digunakan oleh atlet untuk meningkatkan kinerja dengan delayed onset muscle soreness (DOMS) yang terjadi sebagai konsekuensi umum dari jenis latihan ini. DOMS merupakan sensasi ketidaknyamanan otot dan nyeri selama kontraksi aktif yang terjadi secara tertunda setelah latihan berat. DOMS juga merupakan efek samping dari proses perbaikan sebagai respon kerusakan otot mikroskopis, sehingga ketika selesai melakukan olahraga intensif akan terjadi kerusakan pada jaringan otot dan membran sel yang kemudian berkembang menimbulkan respon inflamasi. Umumnya, DOMS akan terjadi apabila seseorang yang tidak pernah atau sudah lama tidak melakukan latihan interval intensitas tinggi. Pada penelitian ini akan dirancang sebuah sistem deteksi yang bertujuan untuk mengintegrasikan sensor elektromiografi (EMG Click) dengan menggunakan Mikromedia 4 for STM32F4 Capacitive yang didalamnya sudah terdapat chipset mikrokontroler STM32F407ZG untuk membandingkan serta mengklasifikasikan nilai amplitudo dan frekuensi dari sinyal elektromiogram yang berhasil diekstraksi setelah melakukan latihan interval intensitas tinggi. Kemudian dengan metode klasifikasi Multilayer Perceptron Neural Network (MLPNN) dengan input berasal dari empat nilai fitur EMG yang berhasil diekstraksi yaitu Mean Power Frequency (MPF), Root Mean Square (RMS), Variance dan Energy yang dijadikan sebagai data training sehingga nantinya ketika desain MLPNN telah berhasil mendapatkan weight dan bias yang sesuai, maka algoritma MLPNN akan diunggah ke dalam mikrokontroler (embedded system). Setelah pengujian dan proses deteksi dilakukan maka didapatkan akurasi deteksi DOMS sebesar 83,76% dengan akurasi model sebesar 82,17%.
======================================================================================================
Athletes commonly use eccentric exercise to improve performance with delayed
onset muscle soreness (DOMS), a common consequence of this type of exercise.
DOMS is the sensation of muscle discomfort and pain during active contractions
that occur delayed after strenuous exercise. DOMS is also a side effect of the
repair process response to microscopic muscle damage. When finished doing
intensive training, there will be damage to muscle tissue and cell membranes,
causing an inflammatory response. Generally, DOMS will occur if someone has
never done high-intensity interval training for a long time. In this study, a
detection system will be designed that aims to integrate an electromyography
sensor (EMG Click) using Mikromedia 4 for STM32F4 Capacitive in which there
is already an STM32F407ZG microcontroller chipset to compare and classify the
amplitude and frequency values of the electromyogram signals that were
successfully extracted after high-intensity interval training. Then with the
Multilayer Perceptron Neural Network (MLPNN) classification method where
the input comes from four EMG feature values that have been successfully
extracted, namely Mean Power Frequency (MPF), Root Mean Square (RMS),
Variance and Energy which are used as training data so that later when design
MLPNN has succeeded in getting the appropriate weight and bias, then the
MLPNN algorithm will be uploaded to the microcontroller (embedded system).
After testing and the detection process is carried out, the DOMS detection
accuracy is 83.76%, with a model accuracy of 82.17%.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Delayed Onset Muscle Soreness, Latihan Interval Intensitas Tinggi, Multilayer Perceptron Neural Network (MLPNN), Otot Quadriceps, Sensor Elektromiografi. Delayed Onset Muscle Soreness, High Intensity Interval Training, Multilayer Perceptron Neural Network (MLPNN), Quadriceps Muscles, EMG Sensor
Subjects:	Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5102.9 Signal processing. T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7878 Electronic instruments
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Biomedical Engineering > 11410-(S1) Undergraduate Thesis
Depositing User:	Florence Fedora Agustina
Date Deposited:	08 Feb 2022 03:23
Last Modified:	31 Oct 2022 01:36
URI:	http://repository.its.ac.id/id/eprint/93003

Actions (login required)

View Item