Abstract
Recently, motorcycle accidents have increased as the number of motorcycle drivers has increased. Although the head and neck are the body parts most frequently injured when a motorcycle accident occurs, there is a lack of research on the protection afforded to the neck by the safety equipment used by motorcycle drivers. This study presents an airbag system that uses artificial intelligence to prevent injury to the neck of a motorcycle driver. It uses a six-axis sensor, the MPU6050 sensor, which measures acceleration and angular velocity in real time as the user moves. The angles are obtained by using the measured acceleration and angular velocity, and the accident situation is judged by AI, which analyzes the acceleration and angle data. Because data is needed for AI to learn, data by type were collected through experiments. In this study, we compare the judgement performance of a parallel neural networks–convolutional neural network and a parallel neural network.
Similar content being viewed by others
References
Jo SH, Woo J, Jeong JH, Byun GS (2019) Safety air bag system for motorcycle using parallel neural networks. J Electric Eng Technol 14(5):2191–2203
Woo J, Jo SH, Jeong JH, Kim M, Byun GS (2020) A study on wearable airbag system applied with convolutional neural networks for safety of motorcycle. J Electric Eng Technol 15(2):883–897
Quick Service Two Wheeled Vehicle Delivery Safety Guide 2017. KOSHA. https://www.kosha.or.kr/kosha/data/business/transportBook.do?medSeq=37934&codeSeq=1150180&medForm=101&menuId=-1150180101&mode=view. Accessed 10 Apr 2017
Kiguchi K, Matsuo R (2017) Accident prediction based on motion data for perception-assist with a power-assist robot. In: 2017 IEEE symposium series on computational intelligence (SSCI), pp 1–5
Kawaguchi S, Takemura H, Mizoguchi H, Kusunoki F, Egusa R, Funaoi H et al (2017) Accuracy evaluation of hand motion measurement using 3D range image sensor. In: 2017 eleventh international conference on sensing technology (ICST), pp 1–4
Stone EE, Skubic M (2014) Fall detection in homes of older adults using the Microsoft Kinect. IEEE J Biomed Health Inform 19(1):290–301
Ryu JT (2013) The development of fall detection system using 3-axis acceleration sensor and tilt sensor. J Korea Ind Inform Syst Res 18(4):19–24
Kim SH, Park J, Kim DW, Kim NG (2011) The study of realtime fall detection system with accelerometer and tilt sensor. J Korean Soc Precision Eng 28(11):1330–1338
Kim HY, Min JK (2011) Implementation of a motion capture system using 3-axis accelerometer. J KIISE Comput Pract Lett (in Korean) 17(6):383–388
Jun C, Park JH, Zhao X, Karimi H, Cao J (2019) Quantized nonstationary filtering of network-based markov switching RSNSs: a multiple hierarchical structure strategy. IEEE Trans Autom Control. https://doi.org/10.1109/TAC.2019.2958824
Cheng J, Park JH, Cao J, Qi W (2020) A hidden mode observation approach to finite-time SOFC of Markovian switching systems with quantization. Nonlinear Dyn. https://doi.org/10.1007/s11071-020-05501-0
Lee SM, Jo HR, Yoon SM (2016) Machine learning analysis for human behavior recognition based on 3-axis acceleration sensor. J Korean Inst Commun Sci 33(11):65–70
Lee H, Lee S (2014) Real-time activity and posture recognition with combined acceleration sensor data from smartphone and wearable device. J KIISE Softw Appl 41(8):586–597
Kau LJ, Chen CS (2014) A smart phone-based pocket fall accident detection, positioning, and rescue system. IEEE J Biomed Health Inform 19(1):44–56
Yoo BH, Heo G (2017) Detection of rotations in jump rope using complementary filter. J Korea Inst Inform Commun Eng 21(1):8–16
Zhang Q, Li HQ, Ning YK, Liang D, Zhao GR (2014) Design and realization of a wearable hip-airbag system for fall protection. Appl Mech Mater 461:667–674 (Trans Tech Publications Ltd)
Sugomori Y (2017) Detailed deep learning-time series data processing by TensorFlow. Keras, Wikibook, chap. 3, part 3.1.2 Deep learning and neural networks
Sacko (2017) Deep learning that literary students can also understand(1)—perceptron. Sacko Tistory. https://sacko.tistory.com/10. Accessed 27 Sep 2017
Sacko (2017) Deep learning that literary students can also understand(2)—Neural Network. Sacko Tistory. https://sacko.tistory.com/17?category=632408. Accessed 18 Oct 2017
Saint Binary (2018) Role and type of activation function. Saint Binary Tistory. https://saintbinary.tistory.com/8. Accessed 5 Sept 2018
Ahn NH (2016) Neural Network. Machine Learning Blog. https://nmhkahn.github.io/NN. Accessed 30 Jan 2016
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980
Park HS (2018) Machine learning #4. Tensor ≈ Blog. https://tensorflow.blog/%ED%95%B4%EC%BB%A4%EC%97%90%EA%B2%8C-%EC%A0%84%ED%95%B4%EB%93%A4%EC%9D%80-%EB%A8%B8%EC%8B%A0%EB%9F%AC%EB%8B%9D-4/. Accessed Mar 2018
Lawrence S, Giles CL, Tsoi AC, Back AD (1997) Face recognition: a convolutional neural-network approach. IEEE Trans Neural Netw 8(1):98–113
LeCun Y, Bengio Y (1995) Convolutional networks for images, speech, and time series. Handb Brain Theory Neural Netw 3361(10):1995
Sun L, Jia K, Yeung DY, Shi BE (2015) Human action recognition using factorized spatio-temporal convolutional networks. In: Proceedings of the IEEE international conference on computer vision, pp 4597–4605
Avci D (2016) An automatic diagnosis system for hepatitis diseases based on genetic wavelet kernel extreme learning machine. J Electric Eng Technol 11(4):993–1002
Sacko (2017) Deep learning that literary students can also understand(3)—error back propagation, gradient descent. Sacko Tistory. https://sacko.tistory.com/19?category=632408. Accessed 25 Oct 2017
Heusel M, Ramsauer H, Unterthiner T, Nessler B, Hochreiter S (2017) Gans trained by a two time-scale update rule converge to a local Nash equilibrium. In: Advances in neural information processing systems, pp 6626–6637
Kim BS (2016) Gradient descent optimization algorithms theorem. Beomsu Kim’s Blog. https://shuuki4.github.io/deep%20learning/2016/05/20/Gradient-Descent-Algorithm-Overview.html. Accessed 20 May 2016
Tieleman T, Hinton G (2012) Lecture 6.5-rmsprop, coursera: neural networks for machine learning. University of Toronto, Technical report
Sutskever I, Martens J, Dahl G, Hinton G (2013) On the importance of initialization and momentum in deep learning. In: International conference on machine learning, pp 1139–1147
Clevert DA, Unterthiner T, Hochreiter S (2015) Fast and accurate deep network learning by exponential linear units (elus). arXiv preprint arXiv:1511.07289
Acknowledgements
This work was supported by a Research Grant of Pukyong National University (2019).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Jeong, JH., Jo, SH., Woo, J. et al. Parallel Neural Network–Convolutional Neural Networks for Wearable Motorcycle Airbag System. J. Electr. Eng. Technol. 15, 2721–2734 (2020). https://doi.org/10.1007/s42835-020-00507-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42835-020-00507-5