The Level of Accuracy of the Expert System Training Data Uses the Naive Bayes Algorithm to Measure the Distance of A Ball Kick
Abstract
The importance of data accuracy in the implementation of long-distance kicking tests as basic data for coaches requires adequate facilities and requires large costs, so technology is needed for facility and budget efficiency. The purpose of this research is to determine the accuracy of expert system training data using the Naive Bayes algorithm to measure the distance of a ball kick. The research design used is a quantitative method with an experimental model. The type of experimental design is pre-experimental design. Participants amounted to 100 male soccer players with saturated sample technique. The instruments were question forms to obtain information on gender and age, while to measure leg muscle strength and leg muscle strength using a tape roll meter and leg dynamometer. Data validity uses calibrated tools. The data analysis technique uses probability (naive bayes) using data testing and evaluation. The results of the study obtained the accuracy level of the expert system training data using the naïve bayes algorithm with the best accuracy of 100%. There is a training data learning model used using the 99 scheme and test 1 and 98 and test 2. The conclusion is that the accuracy level of expert system training data using the naive bayes algorithm is declared to be accountable for use in classifying new data. The contribution for further research is testing using new data to determine the level of accuracy further to improve accuracy in learning training data.
Keywords
Expert system , Naïve Bayes , The length of the ball kick , Accuracy of training data
References
- Baker, B. S., Chen, Z., Larson, R. D., Bemben, M. G., & Bemben, D. A. (2022). Sex differences in bone density, geometry, and bone strength of competitive soccer players. Journal of Musculoskeletal and Neuronal Interactions. 20(1): 62–76. [CrossRef]
- Bonicalzi, S., Caro, M., & Giovanola, B. (2023). Artificial Intelligence and Autonomy : On the Ethical Dimension of Recommender Systems. Topoi, 0123456789. 42, 819-842. [CrossRef]
- Borror, A., Mazzoleni, M., Coppock, J., Jensen, B. C., Wood, W., & Battaglini, C. L. (2019). Predicting oxygen uptake responses during cycling at varied intensities using an artificial neural network. Biomedical Human Kinetics. 11, 60–68. [CrossRef]
- Burhaein, E., Fadjeri, A., & Widiyono, I. P. (2023). Application of Naive Bayes Algorithm for Physical Fitness Level Classification. Int J Disabil Sports Health Sci, 7(July 2023), 178–187. [CrossRef]
- Charntaweekhun, K., & Wangsiripitak, S. (2006). Visual programming using flowchart. 2006 International Symposium on Communications and Information Technologies, ISCIT, 200, 1062–1065. [CrossRef]
- Debelee, T. G., Schwenker, F., Rahimeto, S., & Yohannes, D. (2019). Evaluation of modified adaptive k -means segmentation algorithm. Biomedical Signal rocessing and Control. 5(4), 347–361. [CrossRef]
- Diseases, T. M., Device, D., Raspberry, U., Convolutional, D., Networks, N., Emebo, O., & Fori, B. (2018). The diagnose of oil palm disease using Naive Bayes Method based on Expert System Technology. Journal of Physics. 4(2), 236-252. [CrossRef]
- Fadjeri, A., Hidayat, K., & Handayani, D. R. (2021). Deteksi Emosi pada Teks menggunakan Algoritma Naïve Bayes. Jurnal Riset Teknologi Dan Komputer, 1(2), 1–4. [CrossRef]
- Fadjeri, A., Setyanto, A., & Kurniawan, M. P. (2020). Pengolahan Citra Digital Untuk Menghitung Ekstrasi Ciri Greenbean Kopi Robusta Dan Arabika (Studi Kasus: Kopi Temanggung). Jurnal Teknologi Informasi Dan Komunikasi (TIKomSiN), 8(1), 8–13. [CrossRef ]
- Jibriel, K. (2013). Hubungan Panjang Tungkai, Kekuatan Otot Tungkai, Dan Kelentukan Pergelangan Kaki Terhadap Tendangan Jarak Jauh Pemain U-15 SSB Tunas Muda Banyubiru Kab. Semarang Tahun 2012. Master’s Thesis, Universitas Negeri Semarang State University, Institute of Sport, Semarang, 154p (in Indonesia).