Prediksi Jumlah Kalori Yang Terbakar Saat Berolahraga Skipping Berbasis Kamera Menggunakan Long-Short Term Memory (LSTM)

Setiawan, Felix Titus (2023) Prediksi Jumlah Kalori Yang Terbakar Saat Berolahraga Skipping Berbasis Kamera Menggunakan Long-Short Term Memory (LSTM). Other thesis, Institut Teknologi Sepuluh Nopember.

Text 07211940000081-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2025. Download (13MB) | Request a copy

Abstract

Skipping merupakan salah satu jenis olahraga kardio yang efektif untuk meningkatkan kondisi fisik dan mengontrol berat badan. Skipping adalah olahraga yang tinggi intensitas yang dapat membantu meningkatkan kondisi kardiovaskular dan membakar kalori dengan cepat.Kalori adalah unit energi yang digunakan untuk mengukur jumlah energi yang diperlukan tubuh untuk berbagai keperluan, termasuk kegiatan fisik. Namun, jumlah kalori yang terbakar dari olahraga skipping tergantung pada berbagai faktor, seperti intensitas, durasi olahraga, dan berat badan seseorang. Menghitung kalori berguna bagi orang yang mencoba menurunkan berat badan, menambah berat badan, atau mempertahankan berat badan karena mereka dapat memonitor kalori yang mereka bakar. Namun sebagian besar alat skipping yang dilengkapi dengan fitur penghitung kalori cenderung memiliki harga yang lebih tinggi dibandingkan dengan alat skipping biasa. Penelitian ini membuat sistem yang dapat memprediksi kalori yang terbakar saat berolahraga skipping menggunakan citra video dengan kamera. Metode yang digunakan dengan melakukan akuisisi data citra yang kemudian dideteksi dan segmentasi pose ,Hasil deteksi dilakukan ekstrak fitur untuk menjadi dataset yang akan dilakukan training menghasilkan model machine learning yang dapat mendeteksi lompatan. Prediksi kalori dilakukan menggunakan metode regresi linear berdasarkan jumlah lompatan yang didapat pada hasil deteksi.dari hasil model yang ditraining menggunakan 49 sequence dengan 3 kelas dan 17 epoch, didapatkan akurasi sebesar 96.67% dan loss sebesar 1.3%.
================================================================================================================================
Jumping rope is a type of cardio exercise that is effective for improving physical condition and controlling weight. Jumping rope is high-intensity exercise that can help improve cardiovascular conditions and burn calories quickly. Calories are energy units used to measure the amount of energy the body needs for various purposes, including physical activity. However, the number of calories burned from jumping rope exercise depends on various factors, such as intensity, duration of exercise, and one's body weight. Calorie counting is useful for people trying to lose weight, gain weight, or maintain weight because they can monitor the calories they burn. However, most of the Jumping rope tools that are equipped with a calorie counter feature tend to have a higher price than with the usual jumping rope tool. This research creates a system that can predict calories burned while exercising jumping rope using video images with a camera. The method used is to acquire image data which is then detected and segmented poses. The results of the detection are extracted from features to become a dataset that will be trained to produce a machine learning model that can detect jumps. Calorie prediction was carried out using the linear regression method based on the number of jumps obtained on the detection results.From the results of the model trained using 49 sequences with 3 classes and 17 epochs, an accuracy of 96.67% and a loss of 1.3% were obtained.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Lompat Tali, Kalori, Prediksi Jumping Rope,Calories,Prediction
Subjects:	Q Science > Q Science (General) > Q325.5 Machine learning. Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Computer Engineering > 90243-(S1) Undergraduate Thesis
Depositing User:	Setiawan Felix Titus
Date Deposited:	10 Oct 2023 02:46
Last Modified:	10 Oct 2023 02:46
URI:	http://repository.its.ac.id/id/eprint/102262

Actions (login required)

View Item