IoT-Driven Posture and Eye Strain Monitoring Systems for Students: A Comprehensive Review

Abstract

Health issues have expanded as a result of the global increase in digital device utilize, especially as a result of extended exposure to and utilize of digital screens. The developing significance of IoT-enabled ergonomic monitoring system is brought to light by the truth that this tendency has resulted in an increment in occasions of poor posture and eye strain among students. In order to distinguish and reduce the physical strain brought on by prolonged screen time in educational settings, this review article examines a number of intelligent, sensor-based Internet of Things (IoT), Artificial Intelligence (AI), and Machine Learning (ML) advancements. In order to improve ergonomic wellbeing, AI-powered versatile systems are able to analyse user behaviour and make changes in real time. Through theintegration of several sensor sorts, cloud computing, and AI that works straightforwardly on the device, modern systems are advancing from fundamental screens to intelligent companions that actively contribute to our well-being. These progressed strategies for detecting eye strain are helping students who spend a lot of time before screens to stop feeling uncomfortable. Their concentration and scholastic achievement subsequently increase. For this reason, it\'s becoming more significant than ever for educational educate to implement these intelligent monitoring and evaluation systems in order to set up advanced learning environments that are healthier and more encouraging.

Introduction

The Internet of Things (IoT) refers to interconnected devices that collect and exchange real-time data. In healthcare, IoT and Artificial Intelligence (AI)/Machine Learning (ML) are revolutionizing patient monitoring by reducing human errors, enabling remote care, and improving personalized treatment.

By 2025, over 75 billion IoT devices are expected to be in use globally, with healthcare being a major beneficiary. Smart surveillance and health-monitoring systems are particularly important.

2. Student Health and Technology Use

Globally, students increasingly use smartphones, tablets, and laptops for learning, communication, and entertainment. While these tools offer educational benefits, prolonged screen time leads to health issues such as:

• Eye strain

• Poor posture

• Fatigue

• Back, neck, and musculoskeletal pain

• Reduced concentration and academic performance

Sitting for more than 10 hours per day is now common and linked to "sedentary disorder," which includes cardiovascular and metabolic risks, physical fatigue, and reduced mobility.

3. Smart Systems to Address Health Issues

AI and IoT-enabled systems can help detect and prevent these health problems by:

• Monitoring posture and eye movement using sensors (e.g., gyroscopes, flex sensors, accelerometers, and cameras)

• Using AI algorithms for real-time feedback, anomaly detection, and behavior prediction

• Sending personalized alerts via apps or web platforms to encourage better habits

• Recommending breaks, posture corrections, and simple exercises

These systems use Arduino, ESP32, and cloud computing to process and store data. Dashboards and visual feedback tools help users (students/parents/teachers) access and respond to insights.

4. Problem Statement

While technology supports education, students often lack awareness of the physical toll of prolonged device use. Poor ergonomic practices lead to:

• Eye fatigue and dry eyes

• Chronic musculoskeletal disorders

• Headaches and cognitive decline

General wearables (e.g., fitness bands) are not tailored for educational use. There's a need for real-time, low-cost, AI-powered systems that provide meaningful, personalized feedback for students in learning environments.

5. Health Issues and Their Causes

6. Gaps in Existing Solutions

Current tech:

• Does not give context-specific feedback suitable for classrooms

• Offers generic health data, not focused on academic environments

• Lacks real-time alerts for poor posture or visual strain

7. Literature Review: Smart Sensing Chairs

Studies on smart chairs equipped with sensors (e.g., FSRs, flex sensors, load cells) show promise in posture detection using ML algorithms like SVM, KNN, RF, and CNN. However, most studies:

• Use small datasets with limited demographic diversity

• Lack comprehensive user feedback mechanisms

• Do not consider people with existing musculoskeletal issues

Feedback modes (e.g., haptic vibrations or visual alerts) improve posture but require better usability testing. IoT integration allows remote monitoring and alerts via mobile apps, increasing healthcare efficiency.

Systems that detect 5–7 postures perform well (>90% accuracy) using models like ANN or LightGBM. But as the number of detected postures increases, accuracy drops due to system complexity.

Conclusion

The blending of Artificial Intelligence and Machine Learning innovations with the Internet of Things has the capability to revolutionize change checking and handling issues related to the abuse of innovation. Gadgets such as computers and tablets have ended up commonplace in classroom settings, declining pupils’ pose and eye-strain. These wellbeing concerns may adversely affect learners’ instructive results and by and large wellness. This review looks for arrangements requiring innovative approaches with dynamic input systems that proficiently address the depicted issues counting real-time checking.A promising improvement in reparative advancement may be the proposed Web of Things (IoT) based micro-posture and eye strain monitoring systems. In expansion to teaching students around the significance of legitimate pose and eye wellbeing, this proactive approach instructs students to develop the determination of more profitable inclinations that will lead to moved forward scholarly accomplishment. The literature survey in this research illustrates the adequacy of different IoT and AI-enabled observing systems in recognizing and treating eye strain and poor posture. For occasion, it has been illustrated that force-sensitive resistors and machine learning calculations empower savvy detecting chairs to recognize and adjust sitting positions in genuine time. At the same time, intelligent eye blinking checking gadgets have appeared guarantee in recognizing diminished.

References

[1] G. Yang et al., \"A Health-IoT Platform Based on the Integration of Intelligent Packaging, Unobtrusive Bio-Sensor, and Intelligent Medicine Box,\" in IEEE Transactions on Industrial Informatics, vol. 10 (4), pp. 2180-2191, Nov. 2014, https://doi.org/10.1109/TII.2014.2307795 [2] A. Al-Fuqaha, M. Guizani, M. Mohammadi, M. Aledhari and M. Ayyash, \"Internet of Things: A Survey on Enabling Technologies, Protocols, and Applications,\" in IEEE Communications Surveys & Tutorials, vol. 17 (4), pp. 2347-2376, Fourthquarter(2015) https://doi.org/10.1109/COMST.2015.2444095 [3] Charalampos Doukas and Ilias Maglogiannis. 2012. Bringing IoT and Cloud Computing towards Pervasive Healthcare. In Proceedings of the 2012 Sixth International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing (IMIS \'12). IEEE Computer Society, USA,922–926. https://doi.org/10.1109/IMIS.2012.26 [4] A. Esteva et al., \"A guide to deep learning in healthcare,\" Nat. Med., vol. 25(1), pp. 24–29, Jan. 2019. https://doi.org/10.1038/s41591-018-0316-z [5] L. Chen, J. Hoey, C. Nugent, D. J. Cook, and Z. Yu, \"Sensor-Based Activity Recognition,\" IEEE Trans. Syst., Man, Cybern. C, vol. 42(6), pp. 790–808,Nov(2012). https://doi.org/1109/TSMCC.2012.2198883 [6] M. Mohammadi, A. Al-Fuqaha, S. Sorour, and M. Guizani, \"Deep Learning for IoT Big Data and Streaming Analytics: A Survey,\" IEEE Commun. Surveys Tuts., vol. 20(4), pp. 2923–2960, 2018. https://doi.org/10.1109/COMST.2018.2844341 [7] Sheppard, Amy & Wolffsohn, James. (2018). Digital eye strain: Prevalence, measurement and amelioration. BMJ Open Ophthalmology. 3. e000146.https://doi.org/10.1136/bmjophth-2018-000146 [8] Loh, K. Y., & Reddy, S. C. (2008). Understanding and preventing computer vision syndrome. Malaysian Family Physician, 3(3), 128–130.https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4170366/. [9] Straker, Leon & Pollock, Clare & Maslen, B. (2009). Principles for the wise use of computers by children. Ergonomics. 52. 1386-401. https://doi.org/10.1080/00140130903067789. [10] American Optometric Association, “Computer Vision Syndrome (CVS) and digital screens,” AOA Fact Sheet, 2020. [Online]. Available: https://www.aoa.org [11] Rosenfield, Mark. (2016). Computer vision syndrome (a.k.a. digital eye strain). Optometry in practice. 17. 1-10. [12] Peper, Erik & Lin, I-Mei & Harvey, Richard & Perez, Jacob. (2017). How Posture Affects Memory Recall and Mood. Biofeedback. 45. 36-41. https://doi.org/10.5298/1081-5937-45.2.01 [13] [N. Krause et al., \"Physical workload, ergonomic problems, and incidence of low back injury,\" Am. J. Ind. Med., vol. 46(6), pp. 570–585, 2004. https://doi.org/10.1002/ajim.20094 [14] J.Y. Chau et al., \"Are workplace interventions to reduce sitting effective? A systematic review,\" Prev. Med., vol. 51(5), pp. 352–356, 2010.https://doi.org/10.1016/j.ypmed.2010.08.012 [15] U. Ekelund et al., \"Does physical activity attenuate or eliminate the detrimental association of sitting time with mortality?\" Lancet, vol. 388(10051), pp. 1302–1310, 2016.https://doi.org/10.1016/S0140-6736(16)30370-1 [16] Biswas, Avi & Oh, Paul & Faulkner, Guy & Bajaj, R. & Silver, MA & Mitchell, Marc. (2015). Sedentary Time and Its Association With Risk for Disease Incidence, Mortality, and Hospitalization in Adults (vol 162, pg 123, 2015). Annals of internal medicine. 163. 400-400.https://doi.org/10.7326/L15-5134 [17] Ranasinghe, P et al. “Computer vision syndrome among computer office workers in a developing country: an evaluation of prevalence and risk factors.” BMC research notes vol. 9 150. 9 Mar. 2016,https://doi.org/10.1186/s13104-016-1962-1 [18] Reddy, S. C., Low, C., Lim, Y., Low, L., Mardina, F., & Nursaleha, M. (2013). Computer vision syndrome: a study of knowledge and practices in university students. Nepalese Journal of Ophthalmology, 5(2), 161–168. https://doi.org/10.3126/nepjoph.v5i2.8707 [19] Aggarwal, D., Sharma, D., & Saxena, A. B. (2022). Detection of eye strain due to usage of electronic devices: A machine learning based approach. International Journal of Health Sciences, 6(S1),11197–11207. https://doi.org/10.53730/ijhs.v6nS1.7707 [20] S. Patel et al., \"A review of wearable sensors and systems with application in rehabilitation,\" J. NeuroEng. Rehabil., vol. 9(1), p. 21, Apr. 2012. https://doi.org/10.1186/1743-0003-9-21 [21] Faritha Banu, Jahir Hussain & R, Revathi & M, Suganya & N.R, Gladiss. (2020). IoT based Cloud Integrated Smart Classroom for smart and a sustainable Campus. Procedia Computer Science. 172.77-81 https://doi.org/10.1016/j.procs.2020.05.012 [22] M. A. Khan and K. Salah, \"IoT security: Review, blockchain solutions, and open challenges,\" Future Generation Computer Systems, vol. 82, pp. 395–411, 2018. https://doi.org/10.1016/j.future.2017.11.022 [23] S. Alam, M. M. Rathore, and A. Paul, \"Data fusion and IoT for smart ubiquitous environments: A survey,\" IEEE Access, vol. 5, pp. 9533–9554, 2017.https://doi.org/10.1109/ACCESS.2017.2708727 [24] American Optometric Association, \"Computer Vision Syndrome,\" 2019. [Online]. Available: https://www.aoa.org [25] J. Gubbi et al., \"Internet of Things (IoT): A vision, architectural elements, and future directions,\" Future Generation Computer Systems, vol. 29(7), pp. 1645–1660, 2013. https://doi.org/10.1016/j.future.2013.01.010 [26] H. Alemdar and C. Ersoy, \"Wireless sensor networks for healthcare: A survey,\" Computer Networks, vol. 54(15), pp. 2688–2710, Oct. 2010. https://doi.org/10.1016/j.comnet.2010.05.003 [27] L. Catarinucci et al., \"An IoT-aware architecture for smart healthcare systems,\" IEEE Internet of Things Journal, vol. 2(6), pp. 515–526, Dec.2015. https://doi.org/1109/JIOT.2015.2417684 [28] Rosenfield M. (2011). Computer vision syndrome: a review of ocular causes and potential treatments. Ophthalmic & physiological optics: the journal of the British College of Ophthalmic Opticians (Optometrists), 31(5), 502–515. https://doi.org/10.1111/j.1475-1313.2011.00834.x [29] Hasan, Dler. (2025). IoT-Based Smart Education: A Systematic Review of the State of the Art. Journal of Intelligent Systems and Information Technology.2.1-16. https://doi.org/10.61971/jisit.v2i1.106 [30] R. Coles-Brennan, J. Sulley, and D. Young, \"Management of digital eye strain,\" Clin. Exp. Optom., vol. 102(1), pp. 18–29, 2019.https://doi.org/10.1111/cxo.12798 [31] S. C. Mukhopadhyay, \"Wearable sensors for human activity monitoring: A review,\" IEEE Sensors Journal, vol. 15(3), pp. 1321–1330, 2015. https://doi.org/10.1109/JSEN.2014.2370945 [32] Nadeem, M., Elbasi, E., Zreikat, A. I., & Sharsheer, M. (2024). Sitting Posture Recognition Systems: Comprehensive Literature Review and Analysis. Applied Sciences, 14(18), 8557. https://doi.org/10.3390/app14188557 [33] Gupta, M.; Sharma, S.; Bhatia, M.; Gupta, N. Similarity index retrieval for school kids’ sitting posture identification. In Predictive Data Modelling for Biomedical Data and Imaging; River Publishers: Aalborg, Denmark, 2024; pp. 231–247. [34] Ordean, M.-N., Oarcea, A., Stan, S.-D., Dumitru, D.-M., Cobîlean, V., & Bîrz?, M.-C. (2022). Analysis of Available Solutions for the Improvement of Body Posture in Chairs. Applied Sciences, 12(13), 6489. https://doi.org/10.3390/app12136489 [35] Manlove, David & Milne, Duncan & Olaosebikan, Sofiat. (2020). Student-project allocation with preferences over projects: Algorithmic and experimental results. Discrete Applied Mathematics. 308. http://dx.doi.org/10.1016/j.dam.2020.08.015 [36] JDahlhamer, J., Lucas, J., Zelaya, C., Nahin, R., Mackey, S., DeBar, L., Kerns, R., Von Korff, M., Porter, L., & Helmick, C. (2018). Prevalence of Chronic Pain and High-Impact Chronic Pain Among Adults - United States, 2016. MMWR. Morbidity and mortality weekly report, 67(36), 1001–1006. https://doi.org/10.15585/mmwr.mm6736a2 [37] N.M. Daraiseh, S.N. Cronin, L.S. Davis, R.L. Shell, W. Karwowski, Low back symptoms among hospital nurses, associations to individual factors and pain in multiple body regions, International Journal of Industrial Ergonomics, Vol 40(1), 2010, Pages 19-24, ISSN 0169-8141,https://doi.org/10.1016/j.ergon.2009.11.004 [38] Dunstan, D.W., Dogra, S., Carter, S.E. et al. Sit less and move more for cardiovascular health: emerging insights and opportunities. Nat Rev Cardiol 18, 637–648 (2021). https://doi.org/10.1038/s41569-021-00547-y [39] English C, Janssen H, Crowfoot G, et al. Breaking up sitting time after stroke (BUST-stroke). International Journal of Stroke. 2018;13(9):921-931. https://doi.org/10.1177/1747493018801222 [40] Y. Tomita et al., \"Effects of sitting posture and jaw clenching on neck and trunk muscle activities during typing,\" J. Oral. Rehabil., vol. 48, pp. 568–574, 2021.https://doi.org/10.1111/joor.13152 [41] International Labour Organization (ILO), \"Teleworking arrangements during the COVID-19 crisis and beyond,\" 2021. [42] D. F. Odesola et al., \"Smart Sensing Chairs for Sitting Posture Detection, Classification, and Monitoring: A Comprehensive Review,\" Sensors, vol. 24(9) p. 2940, 2024. https://doi.org/10.3390/s24092940 [43] A. A. Jiman et al., \"Intelligent Standalone Eye Blinking Monitoring System for Computer Users,\" J. Eye Mov. Res., vol. 17(5), pp. 1–17, 2024. https://doi.org/10.16910/jemr.17.5.1 [44] X. He et al., “Flexible wearable sensors for human motion monitoring,” Sensors, vol.?25(5), p. 1377, 2025. https://doi.org/10.3390/s25051377 [45] Patel, S.; Park, H.; Bonato, P.; Chan, L.; Rodgers, M. \"A Review of Wearable Sensors and Systems with Application in Rehabilitation.\" J. NeuroEngineering Rehabil., vol. 9, p. 21, 2012. https://doi.org/10.1186/1743-0003-9-21 [46] Brownlee, J. Deep Learning for Time Series Forecasting: Predict the Future with MLPs, CNNs and LSTMs in Python; Machine Learning Mastery: 2018. Available online: https://machinelearningmastery.com/deep-learning-for-time-series-forecasting/ [47] International Organization for Standardization. ISO 13482:2014 Robots and Robotic Devices — Safety Requirements for Personal Care Robots; ISO: Geneva, Switzerland, 2018. Available online: https://www.iso.org/standard/53820.html [48] World Health Organization. Global Action Plan on Physical Activity 2018–2030: More Active People for a Healthier World; WHO Press: Geneva, Switzerland, 2019. Available online: https://www.who.int/publications/i/item/9789241514187 [49] Occupational Safety and Health Administration. Ergonomics: The Study of Work; OSHA: Washington, DC, USA, 2021. Available online: https://www.osha.gov/ergonomics [50] Tihomir, Opetuk; Dukic, Goran; Cajner, Hrvoje; Trstenjak, Maja. \"Use of Artificial Intelligence (AI) in the Workplace Ergonomics of Industry 5.0.\" Tehni?ki glasnik, vol. 19, pp. 335–340, 2025.https://doi.org/10.31803/tg-20250105140152

Copyright

Copyright © 2025 Pragadeesh M. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.