Intellekt: A Machine Learning Based Framework for Advanced Muscle Strain Severity Detection Using IoT Devices

Authors

DOI:

https://doi.org/10.61467/2007.1558.2026.v17i3.1395

Keywords:

Machine Learning, IoT Devices, Aprendizaje automático, dispositivos IoT

Abstract

As global populations grow and technology advances, daily life is increasingly shaped by digital tools like computers and smart devices. However, prolonged use has led to rising physical and mental health issues, particularly due to poor sitting posture. Posture-related strain, often overlooked, contributes significantly to musculoskeletal issues including back, neck, shoulder, and wrist pain, and may also be associated with sleep disturbances and elevated stress levels. To the best of our knowledge based on existing literature, this is the first study to introduce Intellekt, a machine learning–based framework for advanced muscle strain severity detection using IoT devices that integrates both posture and muscle strain detection into a unified, low-cost ($23 hardware) framework aimed at mitigating these risks. Specifically, this study makes four key contributions: (1) We created a novel real-time dataset by collecting electromyography (EMG) and posture data from participants in university, bank, and industrial environments, acquiring diverse muscle strain patterns validated against clinical assessment protocols; (2) We designed a two-part hardware framework consisting of Posture Detection (PD) and Strain Detection (SD) modules using Node MCU ESP8266, ultrasonic sensor HC SR04, EMG sensor, and buzzer for real-time user monitoring, featuring EMG-specific signal processing including band pass filtering, rectification, and RMS smoothing; (3) We proposed and evaluated a custom hybrid machine learning approach, referred to as the Intellekt model, that categorizes muscle strain severity into mild, moderate, and severe using EMG signals, with thresholds clinically correlated to tissue damage levels; (4) Our proposed model Intellekt achieved an accuracy of 99% (95% CI: 99.1-99.8%) with 15.2ms inference latency.

 

Spanish-language metadata / Metadatos en español

Título en español:

Intellekt: un marco basado en el aprendizaje automático para la detección avanzada de la gravedad de las distensiones musculares mediante dispositivos IoT


Resumen:

A medida que crece la población mundial y avanza la tecnología, la vida cotidiana se ve cada vez más marcada por herramientas digitales como las computadoras y los dispositivos inteligentes. Sin embargo, el uso prolongado ha dado lugar a un aumento de los problemas de salud física y mental, sobre todo debido a una mala postura al sentarse. La tensión relacionada con la postura, que a menudo se pasa por alto, contribuye de manera significativa a problemas musculoesqueléticos, como el dolor de espalda, cuello, hombros y muñecas, y también puede estar asociada con trastornos del sueño y niveles elevados de estrés. Según nuestro conocimiento, basándonos en la bibliografía existente, este es el primer estudio que presenta Intellekt, un marco basado en el aprendizaje automático para la detección avanzada de la gravedad de las tensiones musculares mediante dispositivos del Internet de las cosas (IoT), que integra tanto la detección de la postura como la de las tensiones musculares en un marco unificado y de bajo costo (hardware de 23 dólares) destinado a mitigar estos riesgos. En concreto, este estudio aporta cuatro contribuciones clave: (1) Creamos un novedoso conjunto de datos en tiempo real mediante la recopilación de datos de electromiografía (EMG) y de postura de participantes en entornos universitarios, bancarios e industriales, obteniendo diversos patrones de tensión muscular validados según protocolos de evaluación clínica; (2) Diseñamos un marco de hardware de dos partes compuesto por módulos de detección de postura (PD) y detección de tensión (SD) utilizando Node MCU ESP8266, un sensor ultrasónico HC-SR04, un sensor EMG y un zumbador para la monitorización en tiempo real del usuario, con un procesamiento de señales específico para EMG que incluye filtrado de paso de banda, rectificación y suavizado RMS; (3) Propusimos y evaluamos un enfoque híbrido de aprendizaje automático a medida, denominado «modelo Intellekt», que clasifica la gravedad de las distensiones musculares en leve, moderada y grave utilizando señales de EMG, con umbrales clínicamente correlacionados con los niveles de daño tisular; (4) Nuestro modelo Intellekt alcanzó una precisión del 99 % (IC del 95 %: 99,1-99,8 %) con una latencia de inferencia de 15,2 ms.

Palabras Claves:

Aprendizaje automático, dispositivos IoT

Smart citations:

https://scite.ai/reports/10.61467/2007.1558.2026.v17i3.1395
Dimensions.
Open Alex.

References

Akodu, A. K., Adedeji, A. R., Zibiri, R. A., & Bakre, A. T. (2024). Effect of telerehabilitation-based core-stability exercise on pain-related disability, pain self-efficacy, and psychological factors in individuals with non-specific chronic low back pain: A randomized controlled study. Bulletin of Faculty of Physical Therapy, 29, Article 28. https://doi.org/10.1186/s43161-024-00193-8

Alaca, N., Acar, A. Ö., & Öztürk, S. (2025). Low back pain and sitting time, posture and behavior in office workers: A scoping review. Journal of Back and Musculoskeletal Rehabilitation, 38(5). https://doi.org/10.1177/10538127251320320

Bourahmoune, K., Ishac, K., & Amagasa, T. (2022). Intelligent posture training: Machine-learning-powered human sitting posture recognition based on a pressure-sensing IoT cushion. Sensors, 22(14), Article 5337. https://doi.org/10.3390/s22145337

Calcaterra, V., Marin, L., Vandoni, M., Rossi, V., Pirazzi, A., Grazi, R., Patané, P., Silvestro, G. S., Carnevale Pellino, V., Albanese, I., Fabiano, V., Febbi, M., Silvestri, D., & Zuccotti, G. (2022). Childhood obesity and incorrect body posture: Impact on physical activity and the therapeutic role of exercise. International Journal of Environmental Research and Public Health, 19(24), Article 16728. https://doi.org/10.3390/ijerph192416728

Chan, O., Del Buono, A., Best, T. M., & Maffulli, N. (2012). Acute muscle strain injuries: A proposed new classification system. Knee Surgery, Sports Traumatology, Arthroscopy, 20(11), 2356–2362. https://doi.org/10.1007/s00167-012-2118-z

Chandra, M. A., & Bedi, S. S. (2021). Survey on SVM and their application in image classification. International Journal of Information Technology, 13, 1–11. https://doi.org/10.1007/s41870-017-0080-1

Dalangin, J. R. G. (2023). Fixtrate: An IoT-based posture detection and correction system [Manuscript/technical report]. Imposible completar institución/editorial sin metadatos verificables adicionales.

de Souza, J. M., Pinto, R. Z., Tebar, W. R., Gil, F. C. S., Delfino, L. D., Morelhão, P. K., da Silva, C. C. M., Oliveira, C. B. S., & Christofaro, D. G. D. (2020). Association of musculoskeletal pain with poor sleep quality in public school teachers. Work, 65(3), 599–606. https://doi.org/10.3233/WOR-203114

Feng, D., & Zhang, Y. (2023). College students’ knowledge, attitudes, and practices regarding body posture: A cross-sectional survey—Taking a university in Wuhu City as an example. Preventive Medicine Reports, 36, Article 102422. https://doi.org/10.1016/j.pmedr.2023.102422

Gadhvi, R., Desai, P., & Siddharth. (2025). PosePilot: An Edge-AI solution for posture correction in physical exercises. In Pattern Recognition and Image Analysis (pp. 208–219). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-99568-2_17

Gehlot, A., Singh, R., Siwach, S., Akram, S. V., Alsubhi, K., Singh, A., Delgado Noya, I., & Choudhury, S. (2022). Real time monitoring of muscle fatigue with IoT and wearable devices. Computers, Materials & Continua, 72(1), 999–1015. https://doi.org/10.32604/cmc.2022.023861

Hsu, C.-Y., Ke, D.-S., Lin, C.-L., & Kao, C.-H. (2020). Risk of herpes zoster in patients with adhesive capsulitis of the shoulder. International Journal of Environmental Research and Public Health, 17(10), Article 3592. https://doi.org/10.3390/ijerph17103592

Jiang, H., Qiu, X., Chen, J., Liu, X., Miao, X., & Zhuang, S. (2019). Insulator fault detection in aerial images based on ensemble learning with multi-level perception. IEEE Access, 7, 61797–61810. https://doi.org/10.1109/ACCESS.2019.2915985

Laidi, R., Khelladi, L., Kessaissia, M., & Ouandjli, L. (2023). Bad sitting posture detection and alerting system using EMG sensors and machine learning. In 2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) (pp. 324–329). IEEE. https://doi.org/10.1109/ICAIIC57133.2023.10067076

Lee, M. K., & Oh, J. (2022). The relationship between sleep quality, neck pain, shoulder pain and disability, physical activity, and health perception among middle-aged women: A cross-sectional study. BMC Women’s Health, 22, Article 186. https://doi.org/10.1186/s12905-022-01781-5

Li, X., Zhou, Z., Wu, J., & Xiong, Y. (2021). Human posture detection method based on wearable devices. Journal of Healthcare Engineering, 2021, Article 8879061. https://doi.org/10.1155/2021/8879061

Liaqat, S., Dashtipour, K., Arshad, K., Assaleh, K., & Ramzan, N. (2021). A hybrid posture detection framework: Integrating machine learning and deep neural networks. IEEE Sensors Journal, 21(7), 9515–9522. https://doi.org/10.1109/JSEN.2021.3055898

Lytras, D. E., Sykaras, E. I., Christoulas, K. I., Myrogiannis, I. S., & Kellis, E. (2020). Effects of exercise and an integrated neuromuscular inhibition technique program in the management of chronic mechanical neck pain: A randomized controlled trial. Journal of Manipulative and Physiological Therapeutics, 43(2), 100–113.

Manchikanti, L., Singh, V., Falco, F. J. E., Benyamin, R. M., & Hirsch, J. A. (2014). Epidemiology of low back pain in adults. Neuromodulation: Technology at the Neural Interface, 17(Suppl. 2), 3–10. https://doi.org/10.1111/ner.12018

Meng, Y., Xue, Y., Yang, S., Wu, F., Dong, Y., & colleagues. (2025). The associations between sedentary behavior and neck pain: A systematic review and meta-analysis. BMC Public Health, 25, Article 453. https://doi.org/10.1186/s12889-025-21685-9

Montuori, P., Cennamo, L. M., Sorrentino, M., Pennino, F., Ferrante, B., Nardo, A., Mazzei, G., Grasso, S., Salomone, M., Trama, U., Triassi, M., & Nardone, A. (2023). Assessment on practicing correct body posture and determinant analyses in a large population of a metropolitan area. Behavioral Sciences, 13(2), Article 144. https://doi.org/10.3390/bs13020144

Nadeem, M., Elbasi, E., Zreikat, A. I., & Sharsheer, M. (2024). Sitting posture recognition systems: Comprehensive literature review and analysis. Applied Sciences, 14(18), Article 8557. https://doi.org/10.3390/app14188557

Piersigilli, P., Citroni, R., Mangini, F., & Frezza, F. (2025). Electromagnetic techniques applied to cultural heritage diagnosis: State of the art and future prospective: A comprehensive review. Applied Sciences, 15(12), Article 6402. https://doi.org/10.3390/app15126402

Proske, U., & Gandevia, S. C. (2012). The proprioceptive senses: Their roles in signaling body shape, body position and movement, and muscle force. Physiological Reviews, 92(4), 1651–1697. https://doi.org/10.1152/physrev.00048.2011

Rafiq, K., Mehboob, S., Khalid, A., Nesar, S., Khan, Z., Saad, S. M., Arain, A. A., Ghafoor, B. A., Iftikhar, J., Laiq, S., & Bhutto, M. (2024). The ignorance of ergonomics: Digital lifestyle during the COVID-19 pandemic among university students in Pakistan. Pak-Euro Journal of Medical and Life Sciences, 7(2), 299–306. https://doi.org/10.31580/pjmls.v7i2.3037

Ren, Y., Ge, R., Yang, C., Tan, Y., Song, H., Liu, R., Huang, M., Niu, Z., Yang, L., & Liu, W. (2025). Efficacy of complex decongestive therapy in managing limb swelling, pain, and enhancing functional recovery after arthroscopic reconstruction of anterior cruciate ligament. Applied Nursing Research, 82, Article 151915. https://doi.org/10.1016/j.apnr.2025.151915

Rosario, J. L. (2017). What is posture? A review of the literature in search of a definition. EC Orthopaedics, 6(3), 111–133.

Wollesen, B., Gräf, J., Schumacher, N., Meyer, G., Wanstrath, M., Feldhaus, C., Luedtke, K., & Mattes, K. (2020). Influences of neck and/or wrist pain on hand grip strength of industrial quality proofing workers. Safety and Health at Work, 11(4), 458–465. https://doi.org/10.1016/j.shaw.2020.06.008

World Health Organization, & International Spinal Cord Society. (2013). International perspectives on spinal cord injury. World Health Organization.

World Health Organization. (2022). Global report on health equity for persons with disabilities. World Health Organization.

Yuan, S., & Zhou, L. (2025). GTA-Net: An IoT-integrated 3D human pose estimation system for real-time adolescent sports posture correction. Alexandria Engineering Journal, 112, 585–597. https://doi.org/10.1016/j.aej.2024.10.099

Downloads

Published

2026-06-12

How to Cite

Habiba, U., Ahmad, M., Ullah, F., Imran, M., Batyrshin, I., & Sidorov, G. (2026). Intellekt: A Machine Learning Based Framework for Advanced Muscle Strain Severity Detection Using IoT Devices. International Journal of Combinatorial Optimization Problems and Informatics, 17(3), 166–181. https://doi.org/10.61467/2007.1558.2026.v17i3.1395

Issue

Section

Articles

Most read articles by the same author(s)

1 2 > >>