Fatigue Detection System Based on Heart Rate and Eye Blink Equipped with Email and Buzzer Alerts to Increase Health Workers Productivity

Abstract:

During COVID-19 pandemic, health workers have a crucial role in promotion, prevention, communication, and education to the public. Limited human resources, longer working hours, high risk of infection, and negative stigma from the community are challenges for health workers in treating COVID-19 patients. If there is no change in the near future, then health workers are threatened with excessive fatigue. A heart rate and eye blink fatigue detection system equipped with email and buzzer alerts is developed as an effort to increase the productivity of health workers in the midst of a pandemic. For heart rate based fatigue detection system, the placement of the sensor on the wrist is chosen with 82% accuracy. Two of five battery bars left for five hours of operation. For eye blink based fatigue detection system, EAR 0.32 is chosen because health workers use mask and glasses while working. The potential benefits of this fatigue detection system are buzzer alert for user, email alert for supervisor, track record, increase service quality, time and workload management. All these potential advantages are expected to prevent fatigue which can increase the productivity of health workers.

• Periodical: Advances in Science and Technology (Volume 125)
• Pages: 29-35
• DOI: https://doi.org/10.4028/p-m2u945
• Online since: March 2023
• Authors: Vivi Bella Callista*, Mochammad Fadhel Firnanda, Rewila Fajar Anugraheni, Alief Wikarta
• Keywords: Eye Blink, Fatigue Detection System, Heart Rate

References

[1] Information on https://www.kemenkopmk.go.id.

[2] L. Ran, X. Chen, Y. Wang, W. Wu, L. Zhang, X. Tan, Risk Factors of Healthcare Workers with Coronavirus Disease 2019: A Retrospective Cohort Study in a Designated Hospital of Wuhan in China. Clinical infectious diseases: an official publication of the Infectious Diseases Society of America 71(2020): 2218-2221.

DOI: 10.1093/cid/ciaa287

[3] S.S. Bharambe, P. Mahajan, Implementation of Real Time Driver Drowsiness Detection System. International Journal of Science and Research (IJSR) 4(2015): 2202–2206.

[4] Z. Hu, C. Lv, Y. Zhou, Y. Zhang, W. Huang, Marker-free Head Tracker Using Vision-based Head Pose Estimation with Adaptive Kalman Filter. Electrical Engineering and Systems Science (2021).

[5] Y. Ming, D. Wu, Y.K. Wang, Y. Shi, C.T. Lin, EEG-Based Drowsiness Estimation for Driving Safety Using Deep Q-Learning. IEEE Transactions on Emerging Topics in Computational Intelligence 5(2021): 583-594.

DOI: 10.1109/tetci.2020.2997031

[6] S. Hwang, J.O. Soe, H. Jebelli, S.H. Lee, Feasibility analysis of heart rate monitoring of construction workers using a photoplethysmography (PPG) sensor embedded in a wristband-type activity tracker. Automation in Construction 71(2016): 372-381.

DOI: 10.1016/j.autcon.2016.08.029

[7] E. Pino, L. Ohno-Machado, E. Wiechmann, D. Curtis, Real-time ECG algorithms for ambulatory patient monitoring, American Medical Informatics Association Annual Symposium proceedings, 2005, pp.604-608.

[8] I.K.R. Arthana, I.M.A. Pradnyana, Perancangan Alat Pendeteksi Detak Jantung dan Notifikasi Melalui SMS, 5th Seminar Nasional Riset Inovatif, 2017, p.889–895.

[9] D.N. Meivita, S.B. Utomo, B. Supeno, Rancang Bangun Alat Ukur Kondisi Kesehatan Pada Pendaki Gunung Berbasis Fuzzy Logic, Seminar Nasional Aplikasi Teknologi Informasi (SNATi), 2016, pp.13-18.

[10] J. Allen, Photoplethysmography and Its Application in Clinical Physiological Measurement. Physiological Measurement 28(2007): 1-39.

DOI: 10.1088/0967-3334/28/3/r01

[11] P.D. Purnamasari, A.Z. Hazmi, Heart Beat Based Drowsiness Detection System for Driver, International Seminar on Application for Technology of Information and Communication (iSemantic), 2018, pp.585-590.

DOI: 10.1109/isemantic.2018.8549786

[12] S. Ramadass, H.A. Bazar, O.A. Abouabdalla, A. M. Manasrah, El-Taj, H., Active E-Mail System SMTP Protocol Monitoring Algorithm, Broadband Network & Multimedia Technology, 2009, pp.257-260.

DOI: 10.1109/icbnmt.2009.5348490

[13] C.A. Saputra, D. Erwanto, P.N. Rahayu, Deteksi Kantuk Pengendara Roda Empat Menggunakan Haar Cascade Classifier dan Convolutional Neural Network.  Journal of Electrical Engineering and Computer 3(2021): 1-7.

DOI: 10.33650/jeecom.v3i1.1510

[14] A. Rosebrock, Raspberry Pi for Computer Vision, first ed., PyImageSearch, (2019).

[15] T. Soukupová, J. Čech, Real-Time Eye Blink Detection using Facial Landmarks. 21ST COMPUTER VISION WINTER WORKSHOP, (2016).

[16] M.R. Arma, Pengaruh Pelatihan Kolaborasi pada Perawat yang Mengalami Konflik Peran Terhadap Kepatuhan dalam Pelaksanaan Standar Operasional Prosedur (Pemasangan Infus) di Ruangan Interne Rsup Dr.M.Djamil Padang Tahun 2012, (2012).

DOI: 10.33006/ji-kes.v6i1.307

[17] S.P. Hastono, Basic data analysis for health research training, Fakultas Kesehatan Masyarakat Universitas Indonesia, Depok, Indonesia, (2007).

DOI: 10.7454/jki.v18i2.412

[18] N. D. Saroinsong, G.D. Kandou, J. Posangi, Kebutuhan Tenaga Perawat Berdasarkan Beban Kerja dengan Metode Time and Motion Study di Ruang Perawatan Penyakit Dalam RSUD DR. Sam Ratulangi Tondano. Paradigma Sehat 5(2017): 16-31.