SavedAdd your journal

Journals / Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi / 2026 / Cilt: 12 Sayı: 1

TinyML-based edge information system for recognizing the activities of parkinson patients

Parkinson hastalarının aktivitelerinin tanınmasında TinyML tabanlı uç bilişim sistemi

Mine Boz(TOKAT GAZİOSMANPAŞA ÜNİVERSİTESİ)0000-0002-0692-8809
Yeliz Durgun(GAZİOSMANPAŞA ÜNİVERSİTESİ, TURHAL MESLEK YÜKSEKOKULU)0000-0003-3834-5533
Pages
317–323
Publication Date
2023-01-15
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

It was found that the proposed system provides 85% recognition accuracy.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Parkinson's disease is a neurodegenerative disease in which tremor is the main symptom that threatens human health.
📊
Key Findings & Data:Reported results; While giving the impression that the problems are almost solved, serious questions arise about the representative capacity of the considered data and, accordingly, the reliability of the performance evaluation.
💡
Conclusion & Impact:It was found that the proposed system provides 85% recognition accuracy.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Edge impulse · İvme ölçer · Anormallik tespiti

Abstract

Parkinson's disease is a neurodegenerative disease in which tremor is the main symptom that threatens human health. Current research focuses on predicting, detecting or classifying Parkinson's Disease. In recent years, wearable motion detection systems have started to be created using various sensors. Reported results; While giving the impression that the problems are almost solved, serious questions arise about the representative capacity of the considered data and, accordingly, the reliability of the performance evaluation. In this research paper, the system for flicker detection is made with Edge Impulse and Arduino Nano 33 BLE LSM9DS1. It can distinguish between background flicker and an unwanted general signal. In this study, it is aimed to detect the disease early by using the Edge Impulse machine learning tools to detect motion with an acceleration sensor in combination with an advanced predictive system design, Internet of Things (IoT) and machine learning. Edge Impulse was used in this study to train a large dataset of various multiple samples for jitter and unwanted jitter. It was found that the proposed system provides 85% recognition accuracy.

Özet

Parkinson hastalığı, insan sağlığını tehdit eden titremenin ana semptom olduğu nörodejeneratif bir hastalıktır. Günümüzdeki araştırmalar, Parkinson Hastalığının önceden tahmin edilebilmesine, tespit edilebilmesine veya sınıflandırılabilmesine odaklanmaktadır. Son yıllarda çeşitli sensörler kullanılarak giyilebilir hareket algılama sistemleri oluşturulmaya başlanmıştır. Raporlanan sonuçlar; sorunların hemen hemen çözüldüğü izlenimini verirken, dikkate alınan verilerin temsil kapasitesi ve buna bağlı olarak performans değerlendirilmesinin güvenilirliği hakkında ciddi sorular ortaya çıkmaktadır. Bu araştırma makalesinde, Edge Impulse yazılımı, Arduino Nano 33 BLE mikrodenetleyicisi ve LSM9DS1 ivme sensörü ile titreme tespiti için sistem yapılmıştır. Arka planda titreme ile istenmeyen genel bir sinyali ayırt edebilmektedir. Bu çalışmada, Edge Impulse makine öğrenme araçlarını kullanarak gelişmiş bir tahmine dayalı sistem tasarımıyla Nesnelerin İnterneti (IoT) ve makine öğreniminin birlikteliğinde ivme sensörü ile hareket tespiti yapılarak hastalığın erken tespitinin yapılması amaçlanmıştır. Edge Impulse, bu çalışmada titreme ve istenmeyen titreme için çeşitli örneklerden oluşan geniş bir veri kümesini eğitmek için kullanılmıştır. Önerilen sistemin %85 tanıma doğruluğu sağladığı bulunmuştur.

🔖

Cite This Article

Boz, M., Durgun, Y. (2023). TinyML-based edge information system for recognizing the activities of parkinson patients. Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, Cilt: 12 Sayı: 1, 317–323. https://doi.org/10.28948/ngumuh.1144946

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (21)

  1. S. Tadse, M. Jain, P. Chandankhede, Parkinson’s detection using machine learning. Proceedings- 5th International Conference on Intelligent Computing and Control Systems ICICCS, 1081–1085, 2021. https://doi.org/10.1109/ICICCS51141.2021.9432340.
  2. M. Saleh, M. Abbas, R. B. Le Jeannes, FallAllD: An Open Dataset of Human Falls and Activities of Daily Living for Classical and Deep Learning Applications. IEEE Sensors Journal, 21(2), 1849–1858, 2021. https://doi.org/10.1109/JSEN.2020.3018335.
  3. M. T. Ehsan, M. S. R. Sajal, K. A. Mamun, An automated cloud-based tool for Screening of Parkinson’s disease in Bangladesh. International Conference on Robotics, Electrical and Signal Processing Techniques, 664–668, 2021. https://doi.org/10.1109/ICREST51555.2021.9331233.
  4. K. Rezaee, S. Savarkar, X. Yu, J. Zhang, A hybrid deep transfer learning-based approach for Parkinson’s disease classification in surface electromyography signals. Biomedical Signal Processing and Control, 71, 103161, 2022. https://doi.org/10.1016/J.BSPC. 2021.103161.
  5. L. Tao, X. Wang, X. Peng, P. Yang, J. Qi, Y. Yang, Activity Selection to Distinguish Healthy People from Parkinson’s Disease Patients Using I-DA. Proceedings - 2021 17th International Conference on Mobility, Sensing and Networking, MSN, 66–73, 2021. https://doi.org/10.1109/MSN53354.2021.00025.
  6. L. Tong, J. He, L. Peng, CNN-Based PD Hand Tremor Detection Using Inertial Sensors. IEEE Sensors Letters, 5(7), 2021. https://doi.org/10.1109/LSENS. 2021.3074958.
  7. A. Rana, Y. Dhiman, R. Anand, Cough Detection System using TinyML. Proceedings- International Conference on Computing, Communication and Power Technology, IC3P, 119–122, 2022. https://doi.org/10.1109/IC3P52835.2022.00032.
  8. J. Chen, X. Ran, Deep Learning With Edge Computing: A Review. Proceedings of the IEEE, 2019. https://doi.org/10.1109/JPROC.2019.2921977.
  9. P. P. Ray, A review on TinyML: State-of-the-art and prospects. Journal of King Saud University - Computer and Information Sciences, 34(4), 1595–1623, 2022. https://doi.org/10.1016/J.JKSUCI.2021.11.019).
  10. B. Wijgård and T. Eng, Power Consumption when using AIModels on microcontrollers. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-186026, 2022. https://doi.org/10.1515/CDBME-2020-3097/MACHINEREADABLECITATION/RIS.
  11. X. Pengfei, C. Shiwen, Y. Zhang, Design of Pose measurement and Display system based on STM32 and MPU6050. Proceedings - International Conference on Intelligent Computing, Automation and Systems, ICICAS, 71–74, 2021. https://doi.org/10.1109 /ICICAS53977.2021.00021.
  12. S. A. Hossein Tabatabaei, D. Pedrosa, C. Eggers, M. Wullstein, U. Kleinholdermann, P. Fischer, K. Sohrabi, Machine Learning Techniques for Parkinson’s Disease Detection using Wearables during a Timed-up-and-Go-Test. Current Directions in Biomedical Engineering, 6(3), 376–379, 2020.
  13. G. Pahuja, T. N. Nagabhushan, A Comparative Study of Existing Machine Learning Approaches for Parkinson’s Disease Detection. 67(1), 4–14, 2018. https://doi.org/10.1080/03772063.2018.1531730.
  14. H. W. Loh, W. Hong, C. P. Ooi, S. Chakraborty, P. D. Barua, R. C. Deo, J. Soar, E. E. Palmer, U. R. Acharya, Application of Deep Learning Models for Automated Identification of Parkinson’s Disease: A Review (2011–2021), 2021. https://doi.org/10.3390/ S21217034.
  15. J. Chatterjee, A. Saxena, G. Vyas, A. Mehra, A computer vision approach to diagnose Parkinson Disease using Brain CT Images. In 2018 Second International Conference on Computing Methodologies and Communication (ICCMC) (pp. 463-467), IEEE, 2018. https://doi.org/ 10.1109/ICCMC.2018.8488034.
  16. A. Picco, S. Morbelli, A. Piccardo, D. Arnaldi, N. Girtler, A. Brugnolo, I. Bossert, L. Marinelli, A. Castaldi, F. de Carli, C. Campus, G. Abbruzzese, F. Nobili, Brain 18F-DOPA PET and cognition in de novo Parkinson’s disease. European Journal of Nuclear Medicine and Molecular Imaging, 42(7), 1062–1070. 2015. https://doi.org/10.1007/S00259-015-3039-0/FIGURES/3.
  17. C. Thanawattano, C. Anan, R. Pongthornseri, S. Dumnin, R. Bhidayasiri, Temporal fluctuation analysis of tremor signal in Parkinson’s disease and Essential tremor subjects. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, 6054–6057, Milan, Italy, 25-29 August 2015. https://doi.org/10.1109/EMBC.2015.7319772.
  18. D. Wright, K. Nakamura, T. Maeda, K. Kutsuzawa, K. Miyawaki, K. Nagata, Research and development of a portable device to quantify muscle tone in patients with parkinsons disease. Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS’08- “Personalized Healthcare through Technology,” 2825–2827, Vancouver, BC, Canada, 20-25 August 2008. https://doi.org/10.1109/IEMBS.2008.4649790.
  19. L. Fraiwan, R. Khnouf, A. R. Mashagbeh, Parkinson’s disease hand tremor detection system for mobile application. Journal of Medical Engineering & Technology, 40(3), 127-134, 2016. https://doi.org/ 10.3109/03091902.2016.1148792.
  20. A. Zhang, A. Cebulla, S. Panev, J. Hodgins, & F. de La Torre, Weakly-supervised learning for Parkinson’s Disease tremor detection. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, 143–147, Jeju, Korea (South), 11-15 July 2017. https://doi.org/ 10.1109/EMBC.2017.8036782.
  21. J. Meng, Q. Niu, X. Huo, H. Zhao, L. Zhang, X. Wang, Y. Wang, A Detection Method for Parkinson’s Hand Tremor Based on Machine Learning. China Automation Congress, CAC, 4105–4109, Beijing, China, 22-24 October 2021. https://doi.org/ 10.1109/CAC53003.2021.9728408.