Detection of Accidents Related to Fall by Using IoT and Deep Learning Methods

Abstract

Work accidents in many businesses pose many dangers for employees. Examples of these work accidents include slippery floors, falling materials, harmful substances/gas leaks, protective clothing and equipment not being used in improper ways or not used at all. It is very important to identify these hazards and take the necessary measures for both worker safety and the employer. Among these dangerous situations, the easiest and most frequent accident to prevent is accidents that occur as a result of slipping or falling. Many employees are injured as a result of these accidents that occur due to problems such as a foreign liquid/substance on the working surface, the inability of the worker to establish his own balance or surface inequalities etc. In this study, such situations such as falling, slipping and balance disorders will be determined by IoT and a deep learning-based system in order to recognize such accidents and make necessary arrangements. Deep learning methods that detect movement such as sliding etc. will be evaluated according to the performance evaluation criteria and the method with the most accurate result will be determined. With the results to be obtained from this study, it is aimed to make improvements to prevent these accidents.

Keywords

• Deep Learning
• Internet of Things (IoT)
• Sensors
• Fall detection

Nesnelerin İnterneti ve Derin Öğrenme Yöntemleri Kullanılarak Düşmeye Bağlı Kazaların Tespiti

Abstract

Birçok işletmede iş kazaları çalışanlar için birçok tehlike oluşturmaktadır. Kaygan zeminler, düşen malzemeler, zararlı maddeler/gaz kaçakları, koruyucu giysi ve ekipmanların uygunsuz kullanılmaması veya hiç kullanılmaması bu iş kazalarına örnek olarak gösterilebilir. Bu tehlikelerin belirlenmesi ve gerekli önlemlerin alınması hem işçi güvenliği hem de işveren açısından oldukça önemlidir. Bu tehlikeli durumlar arasında en kolay ve en sık karşılaşılan kaza, kayma veya düşme sonucu meydana gelen kazalardır. Çalışma yüzeyindeki yabancı bir sıvı/madde, işçinin kendi dengesini kuramaması veya yüzey eşitsizlikleri vb. problemler nedeniyle oluşan bu kazalar sonucunda birçok çalışan yaralanmaktadır. Düşme, kayma ve denge bozuklukları, bu tür kazaların tanınması ve gerekli düzenlemelerin yapılması için IoT ve derin öğrenme tabanlı bir sistem tarafından belirlenecektir. Kayma vb. hareketleri algılayan derin öğrenme yöntemleri performans değerlendirme kriterlerine göre değerlendirilecek ve en doğru sonuca sahip yöntem belirlenecektir. Bu çalışmadan elde edilecek sonuçlar ile bu kazaların önlenmesine yönelik iyileştirmeler yapılması hedeflenmektedir.

Keywords

• Derin Öğrenme
• Sensörler
• Düşme Tespiti
• Nesnelerin İnterneti

References

1. SGK, “SGK İstatistik Yıllıkları”, sgk.gov.tr, SGK 2009, 01.01.2018. [Online]. Available: http://www.sgk.gov.tr/wps/portal/sgk/tr/kurumsal/istatistik/sgk_istatistik_yilliklari. [Accessed: May. 31, 2020].
2. A. Palali and J.C. van Ours, “Workplace accidents and workplace safety: on under-reporting and temporary jobs,” Labour, vol. 31, no. 1, pp. 1-14, 2017. Doi:10.1111/labr.12088
3. K. Jilcha, D. Kitaw and B. Beshah, “Workplace innovation influence on occupational safety and health,” African Journal of Science Technology Innovation and Development. vol. 8, no. 1, pp. 33-42, 2016. Doi:10.1080/20421338.2015.1128044
4. Who.int. “Falls”, who.int, falls, 16.01.2018. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/falls. [Accessed: June 03, 2020].
5. I. Tcarenko, T. Nguyen Gia, A.M. Rahmani, T. Westerlund, P. Liljeberg and H. Tenhunen, “Energy-efficient IoT-enabled fall detection system with messenger-based notification,” Social Informatics and Telecommunications Engineering. vol. 192, pp. 19-26, 2017. Doi:10.1007/978-3-319-58877-3_3
6. A.V. Dastjerdi and R. Buyya, “Fog computing: helping the internet of things realize its potential,” Computer, vol. 49, no. 8, pp. 112-116, 2016. Doi:10.1109/mc.2016.245
7. L.W.F. Chaves and Z. Nochta, Breakthrough towards the internet of things. D. Ranasinghe, Q. Sheng, S. Zeadally, Eds. Unique Radio Innovation for the 21st Century. Berlin, Germany: Springer, 2010. Doi:10.1007/978-3-642-03462-6_2
8. J. ah Lee and M.H. Kim, “Work type classification of gas safety workers and interaction function design for IoT-based app development,” Journal of the Korea Convergence Society, vol. 8, no. 5, pp. 45–52, 2017. Doi:10.15207/JKCS.2017.8.5.045

9. Z.Yinghua, F. Guanghua, Z. Zhigang, H. Zhian, L. Hongchen and Y. Jixing, “Discussion on application of IoT technology in coal mine safety supervision,” Procedia Engineering, vol. 43, pp. 233-237, 2012. Doi:10.1016/j.proeng.2012.08.040
10. MPU-6000 and MPU-6050 Product Specification Revision 3.4 MPU-6000/MPU-6050 “Product Specification”, invensense.tdk.com, 01.01.2013. [Online]. Available: https://invensense.tdk.com/wp-content/uploads/2015/02/MPU-6000-Datasheet1.pdf. [Accessed May 31, 2020].
11. P. Zhang and Z. Liu, “Gesture recognition method based on inertial sensor MPU6050,” Transducer and Microsystem Technologies, vol. 37, no. 1, pp. 46-53, 2018.
12. D.A. Fitriani, W. Andhyka, D. Risqiwati, “Design of monitoring system step walking with MPU6050 sensor based android,” Journal of Informatics, Network, and Computer Science, vol. 1, no. 1, pp. 1, 2017. doi:10.21070/joincs.v1i1.799
13. A. Yudhana, J. Rahmawan and C.U.P. Negara. “Flex sensors and MPU6050 sensors responses on smart glove for sign language translation,” Materials Science and Engineering, vol. 403, no. 1, pp. 12-32, 2018. doi:10.1088/1757-899x/403/1/012032
14. Y. Chakravarthy, K. Sowjanya, A. Srinath, R.P. Paladugu, “Determination of angle measurement using mems based sensor MPU6050 in the development process of a prosthetic leg,” International Journal of Pure and Applied Mathematics, vol. 116, no. 5, pp. 57-61, 2017.
15. J. Han, X. Li and Q. Qin. “Design of two-wheeled self-balancing robot based on sensor fusion algorithm,” International Journal of Automation Technology, vol. 8, no. 2, pp. 216-221, 2014. Doi:10.20965/ijat.2014.p0216
16. U - blox. “NEO-6 u-Blox 6 GPS Modules”, u-blox.com,05.04.2011.[Online]. Available: https://www.u-blox.com/sites/default/files/products/documents/NEO-6_DataSheet_(GPS.G6-HW-09005).pdf. [Accessed May 31, 2020].
17. H.Gjoreski, M. Lustrek and M. Gams. “Accelerometer placement for posture recognition and fall detection,” In: 2011 Seventh International Conference on Intelligent Environments, Nottingham, United Kingdom, July 25–28, 2011, IEEE, 2011. pp. 47-54. doi:10.1109/ie.2011.11
18. W. Wang, M. Zhu, J. Wang, X. Zeng, Z. Yang, “End-to-end encrypted traffic classification with one-dimensional convolution neural networks,” In: 2017 IEEE International Conference on Intelligence and Security Informatics, ISI 2017, Beijing, China, July 22-24, 2017, IEEE, 2017. pp. 43-48. doi:10.1109/isi.2017.8004872
19. S. Kiranyaz, O. Avcı, O. Abdeljaber, T. İnce, M. Gabbouj, D.J. Inman. “1D convolutional neural networks and applications: a survey,” Mechanical Systems And Signal Processing, vol. 151, no. 107398, 2021.
20. S. Kianoush, S. Savazzi, F. Vicentini, V. Rampa, M. Giussani, “Device-Free RF Human Body Fall Detection and Localization in Industrial Workplaces,” IEEE Internet of Things Journal, vol. 4, no. 2, pp. 351-362, 2017. doi:10.1109/jiot.2016.2624800
21. A. Hayat and M. Shan, “Fall Detection System for Labour Safety,” In: 2018 International Conference on Engineering, ICE 2018, London, United Kingdom, July 4-6, 2018 Applied Sciences, and Technology, IEEE, 2018, pp. 1-4. doi:10.1109/iceast.2018.8434476
22. D. Lee, J.Y. Lee, K.D. Jung. “The design of the Fall detection algorithm using the smartphone accelerometer sensor,” International Journal of Advanced Culture Technology, vol. 5, no. 2, pp. 54–62, 2017. doi:10.17703/IJACT.2017.5.2.54
23. K.Yang, C.R. Ahn, M.C. Vuran, S.S. Aria. “Semi-supervised near-miss fall detection for ironworkers with a wearable inertial measurement unit,” Automation in Construction. Vol. 68, pp.194-202, 2016. doi:10.1016/j.autcon.2016.04.007