Deteksi Delayed Onset Muscle Soreness (DOMS) Pada Latihan Sepeda Statis Menggunakan Multichannel EMG Dengan Machine Learning

Lincoln, Nathaniel Win (2023) Deteksi Delayed Onset Muscle Soreness (DOMS) Pada Latihan Sepeda Statis Menggunakan Multichannel EMG Dengan Machine Learning. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 07311940000042-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 September 2025. Download (2MB) | Request a copy

Abstract

Sepeda statis merupakan salah satu alat olahraga yang praktis, aman, dan mudah dilakukan. Salah satu bentuk latihan sepeda statis adalah Spinning, yaitu bentuk latihan di dalam ruangan di mana pengguna menggunakan sepeda statis khusus dengan roda yang diberi beban dengan interval intensitas tinggi. Spinning menjadi olahraga kelompok paling populer ketiga di dunia pada tahun 2020. Spinning menghasilkan risiko cedera berupa exertional rhabdomyolysis (ER), khususnya yang disebut sebagai spinning-induced ER (SIER), dimana dilaporkan terjadi 46 kasus. Rhabdomyolysis merupakan pembubaran otot dengan variasi gejala seperti kelelahan, mual, muntah, nyeri otot ringan, pembengkakan otot, dan disfungsi organ. Salah satu cara diagnosis dini SIER dapat dilakukan dengan deteksi Delayed Onset Muscle Soreness (DOMS), yang merupakan salah satu gejala dari rhabdomyolysis. Oleh karena itu, deteksi DOMS dilakukan. Penelitian ini menggunakan tiga sensor Electromyography (EMG) yang terhubung ke perangkat Mikromedia 7 FPI Capacitive dengan chipset STM32F746ZG, ditempatkan pada otot calves, otot quadriceps, dan otot hamstrings. Sinyal EMG dianalisis dalam domain waktu dan frekuensi untuk mengekstraksi parameter yang relevan. Pengujian melibatkan subjek laki-laki sehat berusia 20-22 tahun yang melakukan sprint interval cycling (SIC) sebagai modalitas latihan. Selain itu, pengujian subjektif dilakukan dengan menggunakan kuesioner Likert Scale of Muscle Soreness sebagai ground truth. Metode klasifikasi Multilayer Perceptron Neural Network (MLPNN) diusulkan untuk deteksi DOMS. Selama pengujian, MLPNN mencapai akurasi 94,2% dan nilai loss sebesar 6,7%. Hasil ini menunjukkan kinerja sistem yang objektif dan efektif dalam mengidentifikasi DOMS pada individu yang melakukan latihan sepeda statis.
====================================================================================================================================
Static cycling is one of the most practical, safe, and easily accessible exercise equipment. One form of static cycling exercise is Spinning, an indoor cycling workout using specially designed stationary bikes with weighted wheels and high-intensity interval training. Spinning became the third most popular group exercise worldwide in 2020. However, spinning carries the risk of injury, particularly exertional rhabdomyolysis (ER), known explicitly as spinning-induced ER (SIER). There have been reported 46 cases of SIER. Rhabdomyolysis involves the breakdown of muscle tissue and can present with symptoms such as fatigue, nausea, vomiting, mild muscle pain, swelling, and organ dysfunction. One way to diagnose SIER early is by detecting Delayed Onset Muscle Soreness (DOMS), one of the symptoms of rhabdomyolysis. Therefore, the detection of DOMS is conducted. This study uses three Electromyograph (EMG) sensors connected to a Mikromedia 7 FPI Capacitive device with an STM32F746ZG chipset, placed on the calves, quadriceps, and hamstrings muscles. EMG signals were analyzed in the time and frequency domains to extract pertinent parameters. The test involved healthy male subjects aged 20-22 years performing sprint interval cycling (SIC) as the exercise modality. Additionally, subjective testing was implemented utilizing the Likert Scale of Muscle Soreness questionnaire, serving as the ground truth. A Multilayer Perceptron Neural Network (MLPNN) classification method was proposed for DOMS detection. During testing, the MLPNN achieved an accuracy of 94.2% and a loss value of 6.7%. These results indicate the objective and effective functioning of the system for identifying DOMS in individuals engaging in static bicycle exercise.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Static Cycling Exercise, Latihan Sepeda Statis; Rhabdomyolysis, DOMS, EMG, MLPNN.
Subjects:	Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) Q Science > QC Physics > QC20.7.F67 Fourier transformations R Medicine > RC Internal medicine > RC1200 Sports Medicine T Technology > T Technology (General) > T58.62 Decision support systems T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5102.9 Signal processing. T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7871.674 Detectors. Sensors 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:	Nathaniel Win Lincoln
Date Deposited:	05 Oct 2023 04:19
Last Modified:	05 Oct 2023 04:19
URI:	http://repository.its.ac.id/id/eprint/101709

Actions (login required)

View Item