Gated Recurrent Unit for Fall Detection on Motorcycle Smart Helmet with Accelerometer Sensor

  • Aji Gautama Putrada Telkom University
Abstract views: 216 , 672 downloads: 104
Keywords: gates recurrent unit, fall detection, smart helmet, accelerometer sensor, motorcycle

Abstract

Smart motorcycle helmets are an emerging topic that can provide convenience to motorcyclists, such as providing information about the gas tank and tire pressure through the sound on the helmet. However, extracting important features of sequential data from accelerometer sensors becomes challenging when attempting to add a fall detection function to the helmet. This study proposes a gated recurrent unit (GRU) for fall detection using an accelerometer mounted on a smart motorcycle helmet. The first step is to get the x-axis, y-axis, and z-axis data from the accelerometer for the fallen human condition and the non-falling human condition. The data preparation involves the autocorrelation function (ACF), the partial autocorrelation function (PACF), normalization, standardization, random oversampling, and one hot encoder. The last is to train the GRU model. We use long short-term memory (LSTM) and convolutional neural network (CNN) as benchmarks. Accuracy, Loss, Precision, Recall, and F1−Score are the metrics we use to measure model performance. The test results show that GRU has Accuracy that is better than LSTM and CNN, which are 0.98, 0.97, and 0.96, respectively. Then other GRU performances in fall detection using the accelerometer sensor are 0.99, 0.97, and 0.98 for Precision, Recall, and F1−Score, respectively.

Downloads

Download data is not yet available.

References

[1] Mochammad Ikbal Tawakal, Maman Abdurohman, and Aji Gautama Putrada. Wireless monitoring system for motorcycle tire air pressure with pressure sensor and voice warning on helmet using fuzzy logic. In 2021 International Conference on Software Engineering & Computer Systems and 4th International Conference on Computational Science and Information Management (ICSECS-ICOCSIM), pages 47–52. IEEE, 2021.
[2] Arif Rahman, Maman Abdurohman, and Aji Gautama Putrada. Indicator warning refined fuel oil in a motorcycle with fuzzy logic and sound navigaiotn through smart helmet. In 2019 International Symposium on Electronics and Smart Devices (ISESD), pages 1–5. IEEE, 2019.
[3] Fakhri Akbar Pratama, Aji Gautama Putrada, and Sidik Prabowo. Smart crash detector untuk sepeda motor berbasis iot. eProceedings of Engineering, 6(2), 2019.
[4] Daniel Arga Amallo, Dodi Wisaksono Sudiharto, and Aji Gautama Putrada. Penerapan algoritma fall detection pada inflatable smart helmet menggunakan accelerometer. eProceedings of Engineering, 5(3), 2018.
[5] Hui Xing Tan, Nway Nway Aung, Jing Tian, Matthew Chin Heng Chua, and Youheng Ou Yang. Time series classification using a modified lstm approach from accelerometer-based data: A comparative study for gait cycle detection. Gait & posture, 74:128–134, 2019.
[6] Feng Zou, Wenlong Fu, Ping Fang, Dongzhen Xiong, and Renming Wang. A hybrid model based on multi-stage principal component extraction, gru network and kelm for multi-step short-term wind speed forecasting. IEEE Access, 8:222931– 222943, 2020.
[7] Qi Nie, Yun Li, Wen Ying Xiong, and Wei Xu. Health recognition algorithm for sports training based on bi-gru neural networks. Journal of Healthcare Engineering, 2021, 2021.
[8] Phesto Peter Namayala. Development of smart helmet motor cycles’ embedded system. Int. J. Eng. Res. Adv. Technol, 5(7):75–84, 2019.
[9] Md Atiqur Rahman, SM Ahsanuzzaman, Ishman Rahman, Toufiq Ahmed, and Abid Ahsan. Iot based smart helmet and accident identification system. In 2020 IEEE Region 10 Symposium (TENSYMP), pages 14–17. IEEE, 2020.
[10] Gaojing Wang, Qingquan Li, Lei Wang, Yuanshi Zhang, and Zheng Liu. Elderly fall detection with an accelerometer using lightweight neural networks. Electronics, 8(11):1354, 2019.
[11] Angela Sucerquia, José David López, and Jesús Francisco Vargas-Bonilla. Real-life/real-time elderly fall detection with a triaxial accelerometer. Sensors, 18(4):1101, 2018.
[12] Guto Leoni Santos, Patricia Takako Endo, Kayo Henrique de Carvalho Monteiro, Elisson da Silva Rocha, Ivanovitch Silva, and Theo Lynn. Accelerometer-based human fall detection using convolutional neural networks. Sensors, 19(7):1644, 2019.
[13] Yves M Galvão, Janderson Ferreira, Vinícius A Albuquerque, Pablo Barros, and Bruno JT Fernandes. A multimodal approach using deep learning for fall detection. Expert Systems with Applications, 168:114226, 2021.
[14] Tamam Alsarhan, Luay Alawneh, Mohammad Al-Zinati, and Mahmoud Al-Ayyoub. Bidirectional gated recurrent units for human activity recognition using accelerometer data. In 2019 IEEE SENSORS, pages 1–4. IEEE, 2019.
[15] Md Siraj, Omar Shahid, Md Atiqur Rahman Ahad, et al. Cooking activity recognition with varying sampling rates using deep convolutional gru framework. In Human Activity Recognition Challenge, pages 115–126. Springer, 2021.
[16] MN Mohammed, Halim Syamsudin, S Al-Zubaidi, Ramli R AKS, and Eddy Yusuf. Novel covid-19 detection and diagnosis system using iot based smart helmet. International Journal of Psychosocial Rehabilitation, 24(7):2296–2303, 2020.
[17] Aji Gautama Putrada and Maman Abdurohman. Anomaly detection on an iot-based vaccine storage refrigerator temperature monitoring system. In 2021 International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA), pages 75–80. IEEE, 2021.
[18] Maya Ameliasari, Aji Gautama Putrada, and Rizka Reza Pahlevi. An evaluation of svm in hand gesture detection using imu-based smartwatches for smart lighting control. Jurnal Infotel, 13(2):47–53, 2021.
[19] Fairus Zuhair Azizy Atoir, Aji Gautama Putrada, and Rizka Reza Pahlevi. An evaluation of complementary filter method in increasing the performance of motion tracking gloves for virtual reality games. Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, 2021.
[20] Baginda Achmad Fadillah, Aji Gautama Putrada, and Maman Abdurohman. A wearable device for enhancing basketball shooting correctness with mpu6050 sensors and support vector machine classification. Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, 2022.
[21] Hui Liu and Lei Shen. Forecasting carbon price using empirical wavelet transform and gated recurrent unit neural network. Carbon Management, 11(1):25–37, 2020.
[22] Raza Haider, Chul Hwan Kim, Teymoor Ghanbari, Syed Basit Ali Bukhari, Muhammad Saeed uz Zaman, Shazia Baloch, and Yun Sik Oh. Passive islanding detection scheme based on autocorrelation function of modal current envelope for photovoltaic units. IET Generation, Transmission & Distribution, 12(3):726–736, 2018.
[23] Huan He, Haomiao Wang, Hongliang Ma, Xuesong Liu, Yilin Jia, and Gangjun Gong. Research on short-term power load forecasting based on bi-gru. In Journal of Physics: Conference Series, volume 1639, page 012017. IOP Publishing, 2020. [24] Jiaju Miao and Wei Zhu. Precision–recall curve (prc) classification trees. Evolutionary intelligence, 15(3):1545–1569, 2022.
[25] Aji Gautama Putrada, Irfan Dwi Wijaya, and Dita Oktaria. Overcoming data imbalance problems in sexual harassment classification with smote. International Journal on Information and Communication Technology (IJoICT), 8(1):20–29, 2022.
[26] Haw-minn Lu. Quasi-orthonormal encoding for machine learning applications. arXiv preprint arXiv:2006.00038, 2020.
[27] Muhammad Zulqarnain, Rozaida Ghazali, Muhammad Ghulam Ghouse, and Muhammad Faheem Mushtaq. Efficient processing of gru based on word embedding for text classification. JOIV: International Journal on Informatics Visualization, 3(4):377–383, 2019.
[28] Htet Myet Lynn, Sung Bum Pan, and Pankoo Kim. A deep bidirectional gru network model for biometric electrocardiogram classification based on recurrent neural networks. IEEE Access, 7:145395–145405, 2019. [29] Huahui Yang, Chen Meng, and Cheng Wang. Data-driven feature extraction for analog circuit fault diagnosis using 1-d convolutional neural network. IEEE Access, 8:18305–18315, 2020.
[30] Ali Jaber Almalki and Pawel Wocjan. Forecasting method based upon gru-based deep learning model. In 2020 International Conference on Computational Science and Computational Intelligence (CSCI), pages 534–538. IEEE, 2020.
[31] Nur Ghaniaviyanto Ramadhan, Aji Gautama Putrada, and Maman Abdurohman. Improving smart lighting with activity recognition using hierarchical hidden markov model. Indonesia Journal on Computing (Indo-JC), 4(2):43–54, 2019.
[32] Minglu Ma and Zhuangzhuang Wang. Prediction of the energy consumption variation trend in south africa based on arima, ngm and ngm-arima models. Energies, 13(1):10, 2019.
[33] Muhammad Bagus Satrio, Aji Gautama Putrada, and Maman Abdurohman. Evaluation of face detection and recognition methods in smart mirror implementation. In Proceedings of Sixth International Congress on Information and Communication Technology, pages 449–457. Springer, 2022.
[34] Ka Io Wong, Yi-Chung Chen, Tzu-Chang Lee, and Sheng-Min Wang. Head motion recognition using a smart helmet for motorcycle riders. In 2019 International Conference on Machine Learning and Cybernetics (ICMLC), pages 1–7. IEEE, 2019.
[35] Purwono Prasetyawan, Slamet Samsugi, Agus Mulyanto, Muhammad Iqbal, Rizky Prabowo, et al. A prototype of iot-based smart system to support motorcyclists safety. In Journal of Physics: Conference Series, volume 1810, page 012005. IOP Publishing, 2021.
Published
2022-12-31
How to Cite
Putrada, A. G. (2022). Gated Recurrent Unit for Fall Detection on Motorcycle Smart Helmet with Accelerometer Sensor. Indonesia Journal on Computing (Indo-JC), 7(3), 21-32. https://doi.org/10.34818/INDOJC.2022.7.3.672
Section
Computer Science