Sunno Fitness: A Fitness Coaching Platform Using Digital Skinfold Caliper Data and Isolation Forest Algorithm for Data-Driven Performance Monitoring

The integration of digital tools into fitness coaching has become increasingly important for delivering personalized and data-informed guidance. Despite this need, many practitioners continue to rely on manual tracking or costly body composition devices that lack seamless data integration. This study developed Sunno Fitness, a web-based coaching platform that combines a custom Bluetooth-enabled digital skinfold caliper with the Isolation Forest algorithm to support data-driven performance monitoring. The project employed a Developmental Research Design guided by Agile methodology. The hardware system incorporated an ESP32 microcontroller and an AS5047P magnetic rotary sensor to digitize skinfold measurements, while the software platform automated the Jackson–Pollock 3-site method and analyzed client progress. System validation was conducted through a two-phase testing procedure involving 31 participants. Results showed that the digital skinfold caliper achieved high precision, with a negligible mean difference of –0.01 mm and a percent error of 2.15% relative to a manual caliper. Automated body fat computation demonstrated strong agreement with manual calculations, reflected by a 0.01 percentage point mean difference and a 1.21% error rate. Higher variance observed when compared to Bioelectrical Impedance Analysis (21.87% error) was attributed to inherent methodological differences rather than hardware limitations. The machine learning component, validated using four health-related proxy datasets, effectively detected anomalies and distinguished long-term trends from data noise. Additionally, the web platform demonstrated reliable performance, achieving a 100% notification delivery rate with an average latency of under 1.5 seconds. Overall, Sunno Fitness offers a validated, cost-effective solution that integrates accurate body composition assessment with intelligent, real-time monitoring to enhance modern fitness coaching.

NA

1. Alslaity, A., Suruliraj, B., Oyebode, O., Fowles, J., Steeves, D., & Orji, R. (2022). Mobile Applications for Health and Wellness: A Systematic Review. Proceedings of the ACM on Human-Computer Interaction, 6(EICS), 1–29. https://doi.org/10.1145/3534525 [Google Scholar] [Crossref]

2. Amawi, A., AlKasasbeh, W., Jaradat, M., Almasri, A., Alobaidi, S., Hammad, A. A., & Ghazzawi, H. (2024). Athletes’ nutritional demands: a narrative review of nutritional requirements. Frontiers in Nutrition, 10, 1331854. https://doi.org/10.3389/fnut.2023.1331854 [Google Scholar] [Crossref]

3. Baglietto, N., Vaquero-Cristóbal, R., Albaladejo-Saura, M., Mecherques-Carini, M., & Esparza-Ros, F. (2024). Assessing skeletal muscle mass and lean body mass: an analysis of the agreement among dual X-ray absorptiometry, anthropometry, and bioelectrical impedance. Frontiers in Nutrition, 11. https://doi.org/10.3389/fnut.2024.1445892 [Google Scholar] [Crossref]

4. Baglietto, N., Vaquero-Cristóbal, R., Albaladejo-Saura, M., Mecherques-Carini, M., & Esparza-Ros, F. (2024). Assessing skeletal muscle mass and lean body mass: an analysis of the agreement among dual X-ray absorptiometry, anthropometry, and bioelectrical impedance. Frontiers in Nutrition, 11. https://doi.org/10.3389/fnut.2024.1445892 [Google Scholar] [Crossref]

5. Cintra-Andrade, M., Esparza-Ros, F., Albaladejo-Saura, M., & Vaquero-Cristóbal, R. (2023). Skinfold calipers: which instrument to use?. Journal of Nutritional Science, 12, e58. https://doi.org/10.1017/jns.2023.58 [Google Scholar] [Crossref]

6. Dingsøyr, T., Falessi, D., & Power, K. (2019). Agile development at scale: The next frontier [Preprint]. arXiv. https://arxiv.org/abs/1901.00324 [Google Scholar] [Crossref]

7. Edgemon, C. (2024). Body fat percentage vs. BMI: which is important. Baylor College of Medicine. https://www.bcm.edu/news/body-fat-percentage-vs-bmi-which-is-important [Google Scholar] [Crossref]

8. Elsey, A. M., Lowe, A. K., Cornell, A. N., Whitehead, P. N., & Conners, R. T. (2021). Comparison of the three-site and seven-site measurements in female collegiate athletes using BodyMetrix™. International Journal of Exercise Science, *14*(4), 230–238. https://www.intjexersci.com [Google Scholar] [Crossref]

9. Escamilla, R. F. et al. (2024). Comparison of four quick and reliable methods of assessing body fat. Journal of Physical Therapy Science, 36(9), 518–525. https://doi.org/10.14900/jpts.36.518 [Google Scholar] [Crossref]

10. Escamilla, R. F., Yamashiro, K., Asuncion, R., MacLean, D., Thompson, I. S., & McKeough, M. (2024). Comparison of four quick and reliable methods of assessing body fat appropriate for clinical settings among young, middle-age, and older healthy male and female adults. Journal of Physical Therapy Science, 36(9), 518–525. https://www.jstage.jst.go.jp/article/jpts/36/9/36_2024-038/_article [Google Scholar] [Crossref]

11. Fabbrizio, A., Fucarino, A., Cantoia, M., Iuliano, E., Reis, V. M., De Giorgio, A., Sausa, M., Vilaça-Alves, J., Garrido, N. D., Zimatore, G., Baldari, C., & Macaluso, F. (2023). Smart devices for health and wellness applied to tele-exercise: An overview of new trends and technologies such as IoT and AI. Healthcare, 11(12), 1805. https://doi.org/10.3390/healthcare11121805 [Google Scholar] [Crossref]

12. Fadul, A. M. A. (2023). *Anomaly Detection based on Isolation Forest and Local Outlier Factor* [Master’s thesis, African Institute for Mathematical Sciences]. ResearchGate. https://www.researchgate.net/publication/374332567 [Google Scholar] [Crossref]

13. Gaikwad, R. S. (2024). IoT-based smart meter using ESP32. International Journal of Research Publication and Reviews, *5*(5), 2360–2370. https://doi.org/10.55248/gengpi.5.0524.1204 [Google Scholar] [Crossref]

14. Garvey, W. T., Batterham, R. L., Bhatta, M., Buscemi, S., Christensen, R., Frias, J. P., & Rubino, D. (2022). Two-year effects of semaglutide in adults with overweight or obesity: the STEP 5 trial. Nature Medicine, 28(10), 2083–2091. https://doi.org/10.1038/s41591-022-02026-4 [Google Scholar] [Crossref]

15. Gejl, K. D., & Nybo, L. (2021). Performance effects of periodized carbohydrate restriction in endurance trained athletes – a systematic review and meta-analysis. Journal of the International Society of Sports Nutrition, 18(1). https://doi.org/10.1186/s12970-021-00435-3 [Google Scholar] [Crossref]

16. Hariri, S., Carrasco Kind, M., & Brunner, R. J. (2020). Extended Isolation Forest. arXiv preprint arXiv:1811.02141v3. https://arxiv.org/abs/1811.02141 [Google Scholar] [Crossref]

17. Heymsfield, S. B., Gonzalez, M. C., Lu, J., Jia, G., & Zheng, J. (2015). Skeletal muscle mass and quality: Evolution of modern measurement concepts in the context of sarcopenia. Proceedings of the Nutrition Society, 74(4), 355–366. https://doi.org/10.1017/S0029665115000129 [Google Scholar] [Crossref]

18. Heyward, V. H., & Pietrobelli, A. (2022). Criterion‐related validity of field‐based methods and equations for body composition estimation in adults: A systematic review. Current Obesity Reports, 11(4), 336–349. https://doi.org/10.1007/s13679-022-00488-8 [Google Scholar] [Crossref]

19. Jackson, A. S., & Pollock, M. L. (1985). Practical assessment of body composition. The Physician and Sportsmedicine, 13(5), 76-90. https://doi.org/10.1080/00913847.1985.11708790 [Google Scholar] [Crossref]

20. Jagim, A. R., Tinsley, G. M., Merfeld, B. R., et al. (2023). Validation of skinfold equations and alternative methods for the determination of fat-free mass in young athletes. Frontiers in Sports and Active Living, 5, 1240252. https://doi.org/10.3389/fspor.2023.1240252 [Google Scholar] [Crossref]

21. Katch, F. I., & McArdle, W. D. (1973). Nutrition and energy expenditure. Journal of Applied Physiology, 35(5), 523–528. https://www.researchgate.net/publication/320931917_Exercise_Physiology_Nutrition_Energy_and_Human_Performance [Google Scholar] [Crossref]

22. Leão, C., Clemente, F. M., Silva, B., Pereira, J., Badicu, G., Camões, M., & Cancela, J. M. (2023). Testing the concurrent validity and reliability of a Lipowise digital skinfold caliper to assess muscle mass in healthy young adults. Heliyon, 9, e17569. https://doi.org/10.1016/j.heliyon.2023.e17569 [Google Scholar] [Crossref]

23. Liu, F. T., Ting, K. M., & Zhou, Z.-H. (2008). Isolation forest. 2008 Eighth IEEE International Conference on Data Mining, 413–422. https://doi.org/10.1109/ICDM.2008.17 [Google Scholar] [Crossref]

24. Machado, D. R. L., Lopes da Silva, L. S., Vaquero-Cristóbal, R., Rosa, V. C., Tasinafo Júnior, M. F., dos Santos, A. P., Abdalla, P. P., Mazzonetto, L. F., Oliveira, A. S., Mota, J., & Marcos-Pardo, P. J. (2024). Reliability of skinfold measurements and body fat prediction depends on the rater's experience: A cross-sectional analysis comparing expert and novice anthropometrists [Preprint]. Research Square. https://doi.org/10.21203/rs.3.rs-4540605/v1 [Google Scholar] [Crossref]

25. McKenney, S., & Reeves, T. C. (2021). Educational design research: Portraying, conducting, and enhancing productive scholarship. Medical Education, 55(1), 82–92. https://doi.org/10.1111/medu.14280 [Google Scholar] [Crossref]

26. Millward, D. J., & Jackson, A. A. (2004). Protein/energy ratios of current diets in developed and developing countries compared with a safe protein/energy ratio: implications for recommended protein and amino acid intakes. Public Health Nutrition, 7(3), 387–405. https://doi.org/10.1079/PHN2003545 [Google Scholar] [Crossref]

27. Morton, R. W., Murphy, K. T., McKellar, S. R., Schoenfeld, B. J., Henselmans, M., Helms, E., Aragon, A. A., Devries, M. C., Banfield, L., Krieger, J. W., & Phillips, S. M. (2019). A systematic review, meta-analysis, and meta-regression of the effect of protein supplementation on resistance training–induced gains in muscle mass and strength in healthy adults. British Journal of Sports Medicine, 52(6), 376–384. https://doi.org/10.1136/bjsports-2019-097608 [Google Scholar] [Crossref]

28. Muntean, P., Mielos-Balica, M., Macavei, G. A., et al. (2024). Anthropometric formulas repurposed to predict body fat content from ultrasound measurements of subcutaneous fat thickness. Symmetry, *16*(8), 962. https://doi.org/10.3390/sym16080962 [Google Scholar] [Crossref]

29. Oresko, J. J., Jin, Z., Cheng, J., Huang, S., Sun, Y., Duschl, H., & Cheng, A. C. (2010). A wearable smartphone-based platform for real-time cardiovascular disease detection via electrocardiogram processing. IEEE Transactions on Information Technology in Biomedicine, 14(3), 734–740. https://doi.org/10.1109/TITB.2010.2047865 [Google Scholar] [Crossref]

30. Pahlevi, M. F. I., Fitrianto, E. J., Ihsani, S. I., & Yuliasih. (2025). The Association Between Body Fat Percentage and Physical Activity and the Physical Fitness Level of Students at SMA IT Al-Madinah Cibinong. Jurnal Segar, 13(2), 46–53. https://doi.org/10.21009/segar/1302.06 [Google Scholar] [Crossref]

31. Phillips, S. M., & Van Loon, L. J. (2011). Dietary protein for athletes: From requirements to optimum adaptation. Journal of Sports Sciences, 29(S1), S29–S38. https://doi.org/10.1080/02640414.2011.619204 [Google Scholar] [Crossref]

32. Prado-Nóvoa, O., Howard, K. R., Laskaridou, E., Zorrilla-Revilla, G., Reid, G. R., Marinik, E. L., Davy, B. M., Stamatiou, M., Hambly, C., Speakman, J. R., & Davy, K. P. (2024). Validity of predictive equations for total energy expenditure against doubly labeled water. Scientific Reports, 14, 15754. https://doi.org/10.1038/s41598-024-66767-7 [Google Scholar] [Crossref]

33. Saeed, A., & Mohammed, R. (2022). Anomaly detection in fitness tracking data using unsupervised machine learning. Journal of Biomedical Informatics, 127, 104013. (cannot find link) [Google Scholar] [Crossref]

34. Saunders, K. H., Umashanker, D., Igel, L. I., Kumar, R. B., & Aronne, L. J. (2018). Obesity pharmacotherapy. Medical Clinics of North America, 102(1), 135–148. https://doi.org/10.1016/j.mcna.2017.08.010 [Google Scholar] [Crossref]

35. Stults-Kolehmainen, M. A., Stanforth, P. R., Bartholomew, J. B., Lu, T., Abolt, C. J., & Sinha, R. (2020). DXA estimates of fat-free mass in relation to calculated and self-reported activity in middle-aged adults. Physiology & Behavior, 215, 112774. https://doi.org/10.1016/j.physbeh.2019.112774 [Google Scholar] [Crossref]

36. Van den Akker, J. J. H., Gravemeijer, K., McKenney, S., & Nieveen, N. (Eds.). (2006). Educational design research. Routledge. https://www.taylorfrancis.com/books/edit/10.4324/9780203088364/educational-design-research-jan-van-den-akker-koeno-gravemeijer-susan-mckenney-nienke-nieveen [Google Scholar] [Crossref]

37. We, S. (1956). Body composition from fruid spaces and density: analysis of method. Techniques for measuring body composition. National Academy of Sciences National Research Council, 223-244 https://escholarship.org/uc/item/6mh9f4nf [Google Scholar] [Crossref]

• Assessment of the Role of Artificial Intelligence in Repositioning TVET for Economic Development in Nigeria
• Teachers’ Use of Assure Model Instructional Design on Learners’ Problem Solving Efficacy in Secondary Schools in Bungoma County, Kenya
• “E-Booksan Ang Kaalaman”: Development, Validation, and Utilization of Electronic Book in Academic Performance of Grade 9 Students in Social Studies
• Analyzing EFL University Students’ Academic Speaking Skills Through Self-Recorded Video Presentation
• Major Findings of The Study on Total Quality Management in Teachers’ Education Institutions (TEIs) In Assam – An Evaluative Study