Evaluasi 1D-CNN untuk Klasifikasi Gerakan Tolak Peluru Berbasis MediaPipe
DOI:
https://doi.org/10.29407/6ydsgw58Abstract
Penelitian ini bertujuan untuk mengevaluasi kinerja model CNN satu dimensi dalam mengklasifikasikan kualitas gerakan tolak peluru berdasarkan landmark tubuh. Data yang digunakan berasal dari kategori Shotput pada dataset UCF101 yang diperoleh melalui Kaggle. Data terdiri dari 150 klip video yang dibagi ke dalam tiga fase gerakan, yaitu awalan, dorongan, dan sikap akhir, serta dua kategori kualitas gerakan, yaitu sempurna dan tidak sempurna. Tahapan penelitian meliputi preprocessing video menggunakan OpenCV, ekstraksi landmark tubuh menggunakan MediaPipe Pose, pelatihan model CNN satu dimensi, dan evaluasi model. Hasil ekstraksi menghasilkan dataset fitur berukuran 150 × 30 × 99. Model memperoleh training accuracy sebesar 88,54%, validation accuracy sebesar 70,83%, dan accuracy pengujian sebesar 60%. Hasil evaluasi menunjukkan bahwa model mampu mengenali kedua kelas, meskipun masih terdapat kesalahan klasifikasi. Dengan demikian, pendekatan MediaPipe Pose dan 1D-CNN memiliki potensi untuk digunakan dalam klasifikasi gerakan tolak peluru, tetapi masih memerlukan peningkatan variasi data dan perbaikan model.
Keywords:
1D-CNN, gerakan tolak peluru, klasifikasi gerakan, MediaPipe Pose##plugins.themes.default.displayStats.downloads##
References
[1] A. Akkase, U. N. Makassar, J. A. P. Pettarani, K. Rappocini, K. Makassar, and S. Selatan,
“Analisis Gerak Biomekanika Pada Tolak Peluru Gaya 0’brien,” Journal Physical
Health Recreation (JPHR), vol. 4, no. 1, pp. 171–178, Nov. 2023, doi:
https://doi.org/10.55081/jphr.v4i1.1668.
[2] M. T. Mubayyin, E. M. A. Anantacia, C. Salsabila, and M. F. Hidayattullah, “Klasifikasi
dan deteksi pose pilates menggunakan mediapipe dan random forest classifier,”
Teknosains: Media Informasi Sains dan Teknologi, vol. 19, no. 1, pp. 56–63, Jun. 2025,
doi: 10.24252/teknosains.v19i1.53698.
[3] F. Daniel Tanugraha, H. Pratikno, M. Musayanah, and W. Indah Kusumawati,
“Pengenalan Gerakan Olahraga Berbasis (Long Short- Term Memory) Menggunakan
Mediapipe,” Journal of Advances in Information and Industrial Technology, vol. 4, no.
1, pp. 37–45, May 2022, doi: 10.52435/jaiit.v4i1.182.
[4] V. Jericho and T. H. Rochadiani, “Implementasi CNN dan MediaPipe dalam
Peningkatan Efektivitas Stretching pada Olahraga Futsal,” Technomedia Journal, vol. 9,
no. 3, pp. 387–398, Feb. 2025, doi: 10.33050/tmj.v9i3.2294.
[5] F. H. Adiba, P. Kasih, and M. A. D. W. Dara, “Implementation and Evaluation of the K
– Nearest Neighbors Algorithm in Badminton Movement Classification,” Jurnal
Sisfokom (Sistem Informasi dan Komputer), vol. 14, no. 4, pp. 489–498, Oct. 2025, doi:
10.32736/sisfokom.v14i4.2441.
[6] R. Andriawan, P. Kasih, and D. P. Pamungkas, “Implementasi Teknik Ekstraksi Pose
dengan MediaPipe dan Klasifikasi Random Forest untuk Penentuan Kualitas Gerakan
Push-Up,” Prosiding SEMNAS INOTEK (Seminar Nasional Inovasi Teknologi), vol. 9,
pp. 1723–1732, 2025, doi: https://doi.org/10.29407/zf3hpm03.
[7] L. A. Sindhikara, A. Sanjaya, and A. Bagus, “Deteksi Gerakan Servis Bulutangkis
Menggunakan Metode K-Nearest Neighbors (KNN) Berbasis Komputer Vision,”
Prosiding SEMNAS INOTEK (Seminar Nasional Inovasi Teknologi), vol. 9, pp. 2111–
2118, 2025, doi: https://doi.org/10.29407/ygyvja37.
[8] Muhammad Rizaldi, Rudi Heriansyah, and Nazori Suhandi, “Pengenalan Gerakan
Tangan untuk Kontrol Slide Presentasi Menggunakan Framework Mediapipe, OpenCV,
dan Model LSTM,” Jurnal Publikasi Teknik Informatika, vol. 4, no. 3, pp. 98–111, Sep.
2025, doi: 10.55606/jupti.v4i3.5332.
[9] Y. Effendi, Y. Kristian, L. Zaman, H. Yutanto, and A. History, “Jurnal Teknologi dan
Manajemen Informatika Pemanfaatan Mediapipe Body Pose Estimation dan Dynamic
Time Warping untuk Pembelajaran Tari Remo Article Info ABSTRACT,” Jurnal
Teknologi dan Manajemen Informatika, vol. 9, no. 2, pp. 183–190, 2023, doi:
https://doi.org/10.26905/jtmi.v9i2.10408.
[10] B. C. Santoso, H. Santoso, and J. Sandjaya, “DEVELOPMENT OF INDEPENDENT
TAEKWONDO TRAINING MACHINE LEARNING WITH 3D POSE MODEL MEDIAPIPE,” Sinkron : Jurnal dan Penelitian Teknik Informatika, vol. 8, no. 3, pp.
1427–1434, Jul. 2023, doi: 10.33395/sinkron.v8i3.12571.
[11] M. A. B. Prasetya, Harits Ar Rosyid, and M. Zainal Arifin, “Accuracy Evaluation of 2D
MediaPipe-Based Pose Estimation for Archery Posture Detection Using N-MPJPE,”
JURNAL TEKNIK INFORMATIKA, vol. 19, no. 1, pp. 109–121, Apr. 2026, doi:
10.15408/jti.v19i1.49778.
[12] B. Sobari, M. Moedjiono, and M. A. Rizkiawan, “Pose Analysis and Classification in
Shooting Sport Using Convolutional Neural Network and Long Short-Term Memory,”
Jurnal Informatika, vol. 12, no. 2, pp. 122–130, Oct. 2025, doi:
10.31294/inf.v12i2.25566.
[13] A. Bera, M. Nasipuri, O. Krejcar, and D. Bhattacharjee, “Fine-Grained Sports, Yoga,
and Dance Postures Recognition: A Benchmark Analysis,” Aug. 2023, doi:
10.1109/TIM.2023.3293564.
[14] G. T. Tendra, D. J. Jollyta, and Sumijan, “Development of an Attention-Based
Convolutional Neural Network-Long Short-Term Memory Model for Real-Time
Ergonomic Analysis of Sitting Posture,” MATRIK : Jurnal Manajemen, Teknik
Informatika dan Rekayasa Komputer, vol. 25, no. 2, pp. 287–298, Mar. 2026, doi:
10.30812/matrik.v25i2.5678.
[15] C. Z. Noorta, M. F. Rais, M. I. Alfatrah, U. D. Fatmawati, and H. A. Danang Rimbawa,
“Machine learning-based approach for evaluating physical fitness through motion
detection,” vol. 14, no. 1, pp. 2809–1884, 2025, [Online]. Available:
www.ejournal.isha.or.id/index.php/Mandiri
[16] K. Swee Sim, S. Wei Wong, A. Low, A. Prademon Yunus, and C. Peng Lim, “RealTime Digital Assistance for Exercise: Exercise Tracking System with MediaPipe Angle
Directive Rules,” International Journal on Informatics Visualization, vol. 8, no. 4, pp.
2380–2387, Dec. 2024, doi: 10.62527/joiv.8.4.2993.
[17] V. Suhandi and H. Santoso, “Personal Training with Tai Chi: Classifying Movement
using Mediapipe Pose Estimation and LSTM,” Building of Informatics, Technology and
Science (BITS), vol. 6, no. 2, pp. 767–775, Sep. 2024, doi: 10.47065/bits.v6i2.5536.
[18] R. Krisna Pambudi and N. Wijaya, “Sistem Finding Choreography HipHop Basic
Menggunakan MediaPipe Body Pose Estimation untuk Dancer,” Jutisi: Jurnal Ilmiah
Teknik Informatika dan Sistem Informasi, vol. 15, no. 1, pp. 1–11, 2026, doi:
10.35889/jutisi.v15i1.3404.
[19] L. Fitriani and I. Nurhakim, “Sistem Deteksi Gerakan Tangan Untuk Pengendalian
Kursor Pada Presentasi Berbasis Opencv dan Mediapipe,” Jurnal Algoritma, vol. 22, no.
2, Nov. 2025, doi: 10.33364/algoritma/v.22-2.2485.
[20] M. Abdul muthalib, I. Irfan, K. Kartika, and S. M. Selamat Meliala, “PENGIRAAN
POSE MODEL MANUSIA PADA REPETISI KEBUGARAN AI PEMOGRAMAN
PYTHON BERBASIS KOMPUTERISASI,” INFOTECH journal, vol. 9, no. 1, pp. 11–
19, Jan. 2023, doi: 10.31949/infotech.v9i1.4233.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
