Sistem Peringatan Tersemat untuk Pengemudi Mengantuk
DOI:
https://doi.org/10.30595/jrre.v5i1.17922Abstract
Pendeteksian Driver Drowsiness (DDD) merupakan teknologi keselamatan kendaraan penting yang dirancang untuk mencegah kecelakaan akibat kantuk pengemudi. Dalam penelitian ini, pendekatan baru diajukan menggunakan model jaringan saraf konvolusi (CNN) ringan yang terdiri dari 44.853 parameter. Berkat ke ringanannya, model ini bekerja secara efisien bahkan pada perangkat dengan sumber daya terbatas. Hasil percobaan menunjukkan kinerja kompetitif model ini dibandingkan dengan model yang ada dengan ukuran input dan jumlah parameter yang lebih besar. Dalam hal akurasi, metode ini mencapai akurasi sebesar 92,06% pada dataset Curtin Emotion Wheels (CEW) yang mengesankan. Bahkan dalam kondisi pencahayaan yang sulit, performa model ini tetap luar biasa jika digabungkan dengan kamera termal. Secara khusus, model ini mencapai akurasi yang luar biasa sebesar 95,10% pada jarak kamera 0,3-meter dari wajah pengemudi. Selain itu, metode ini memiliki karakteristik kecepatan yang sangat baik, sehingga cocok digunakan pada perangkat tertanam. Kecepatan rata-rata perangkat Raspberry Pi 4 diperkirakan mencapai 5 frames per detik (FPS). Hal ini menunjukkan kepraktisan dan kelayakan penerapan pendekatan ini dalam skenario waktu nyata, yang semakin meningkatkan keselamatan pengemudi.
References
[1] K. Ashwini, R. Amutha, and S. Aswin Raj, “Skeletal Data based Activity Recognition System,” Proc. 2020 IEEE Int. Conf. Commun. Signal Process. ICCSP 2020, pp. 444–447, 2020, doi: 10.1109/ICCSP48568.2020.9182132.
[2] C. Changhong and G. Zongliang, “Action recognition from a different view,” China Commun., vol. 10, no. 12, pp. 139–148, 2013, doi: 10.1109/CC.2013.6723886.
[3] N. Dawar and N. Kehtarnavaz, “Continuous detection and recognition of actions of interest among actions of non-interest using a depth camera,” Proc. - Int. Conf. Image Process. ICIP, vol. 2017-Septe, pp. 4227–4231, 2018, doi: 10.1109/ICIP.2017.8297079.
[4] E. P. Ijjina and C. K. Mohan, “Human action recognition based on recognition of linear patterns in action bank features using convolutional neural networks,” Proc. - 2014 13th Int. Conf. Mach. Learn. Appl. ICMLA 2014, pp. 178–182, 2014, doi: 10.1109/ICMLA.2014.33.
[5] O. C. Ann and L. B. Theng, “Human activity recognition: A review,” Proc. - 4th IEEE Int. Conf. Control Syst. Comput. Eng. ICCSCE 2014, no. March, pp. 389–393, 2014, doi: 10.1109/ICCSCE.2014.7072750.
[6] J. Liu, J. Yang, Y. Zhang, and X. He, “Action recognition by multiple features and hyper-sphere multi-class SVM,” Proc. - Int. Conf. Pattern Recognit., pp. 3744–3747, 2010, doi: 10.1109/ICPR.2010.912.
[7] M. Mobark, S. Chuprat, and T. Mantoro, “Improving the accuracy of complex activities recognition using accelerometer-embedded mobile phone classifiers,” Proc. 2nd Int. Conf. Informatics Comput. ICIC 2017, vol. 2018-Janua, pp. 1–5, 2018, doi: 10.1109/IAC.2017.8280606.
[8] S. Park and D. Kim, “Study on 3D action recognition based on deep neural network,” ICEIC 2019 - Int. Conf. Electron. Information, Commun., pp. 1–3, 2019, doi: 10.23919/ELINFOCOM.2019.8706490.
[9] T. Perumal, Y. L. Chui, M. A. Bin Ahmadon, and S. Yamaguchi, “IoT based activity recognition among smart home residents,” 2017 IEEE 6th Glob. Conf. Consum. Electron. GCCE 2017, vol. 2017-Janua, no. Gcce, pp. 1–2, 2017, doi: 10.1109/GCCE.2017.8229478.
[10] P. M. D. Alex, A. Ravikumar, J. Selvaraj, and A. Sahayadhas, “Research on human activity identification based on image processing and artificial intelligence,” Int. J. Eng. Technol., vol. 7, no. 3.27 Special Issue 27, pp. 174–178, 2018, doi: 10.14419/ijet.v7i3.27.17754.
[11] H. Wang and L. Wang, “Cross-Agent Action Recognition,” IEEE Trans. Circuits Syst. Video Technol., vol. 28, no. 10, pp. 2908–2919, 2018, doi: 10.1109/TCSVT.2017.2746092.
[12] P. Mishra, S. Dey, S. S. Ghosh, D. B. Seal, and S. Goswami, “Human Activity Recognition using Deep Neural Network,” 2019 Int. Conf. Data Sci. Eng. ICDSE 2019, pp. 77–83, 2019, doi: 10.1109/ICDSE47409.2019.8971476.
[13] M. M. Hossain Shuvo, N. Ahmed, K. Nouduri, and K. Palaniappan, “A hybrid approach for human activity recognition with support vector machine and 1d convolutional neural network,” Proc. - Appl. Imag. Pattern Recognit. Work., vol. 2020-Octob, pp. 6–10, 2020, doi: 10.1109/AIPR50011.2020.9425332.
[14] Y. Chen, K. Zhong, J. Zhang, Q. Sun, and X. Zhao, “LSTM Networks for Mobile Human Activity Recognition,” no. January 2016, 2016, doi: 10.2991/icaita-16.2016.13.
[15] S. Yu, L. Qin, and Q. Yin, “A C-LSTM Neural Network for Human Activity Recognition Using Wearables,” 2018 Int. Symp. Sens. Instrum. IoT Era, ISSI 2018, no. 6140017010001, pp. 1–6, 2018, doi: 10.1109/ISSI.2018.8538129.
[16] S. K. Yadav, K. Tiwari, H. M. Pandey, and S. A. Akbar, “Skeleton-based human activity recognition using ConvLSTM and guided feature learning,” Soft Comput., vol. 26, no. 2, pp. 877–890, 2022, doi: 10.1007/s00500-021-06238-7.
[17] W. Zhu et al., “Co-Occurrence feature learning for skeleton based action recognition using regularized deep LSTM networks,” 30th AAAI Conf. Artif. Intell. AAAI 2016, no. September 2017, pp. 3697–3703, 2016.
[18] E. Cippitelli, S. Gasparrini, E. Gambi, and S. Spinsante, “A Human Activity Recognition System Using Skeleton Data from RGBD Sensors,” Comput. Intell. Neurosci., vol. 2016, 2016, doi: 10.1155/2016/4351435.
[19] S. Gaglio, G. Lo Re, and M. Morana, “Human Activity Recognition Process Using 3-D Posture Data,” IEEE Trans. Human-Machine Syst., vol. 45, no. 5, pp. 586–597, 2015, doi: 10.1109/THMS.2014.2377111.
[20] H. Pham, L. Khoudour, A. Crouzil, P. Zegers, and S. A. Velastin, “Learning and recognizing human action from skeleton movement with deep residual neural networks,” pp. 25 (6 .)-25 (6 .), 2017, doi: 10.1049/cp.2017.0154.
[21] B. Jiang, J. Yu, L. Zhou, K. Wu, and Y. Yang, “Two-Pathway Transformer Network for Video Action Recognition,” pp. 1089–1093, 2021, doi: 10.1109/icip42928.2021.9506453.
[22] J. He and S. Gao, “TBSN: Sparse-Transformer Based Siamese Network for Few-Shot Action Recognition,” 2021 2nd Inf. Commun. Technol. Conf. ICTC 2021, pp. 47–53, 2021, doi: 10.1109/ICTC51749.2021.9441568.
H. Seong, J. Hyun, and E. Kim, “Video multitask transformer network,” Proc. - 2019 Int. Conf. Comput. Vis. Work. ICCVW 2019, no. 1, pp. 1553–1561, 2019, doi: 10.1109/ICCVW.2019.00194.
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish with this journal agree to the following terms:
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
Jurnal Riset Rekayasa Elektro is licensed under a Creative Commons Attribution 4.0 International License.
Login
Peer Review Process
Author Guidelines
Indexing
