KLASIFIKASI PERILAKU PENGEMUDI MENGGUNAKAN BIDIRECTIONAL LONG SHORT-TERM MEMORY DENGAN ATTENTION LAYER

• ADE IRFAN EFENDI
• 14220009

---

ABSTRAK

Perilaku mengemudi memiliki dampak signifikan terhadap jumlah kecelakaan kendaraan, sehingga penting untuk mendeteksi perilaku ini secara dini guna memastikan perjalanan yang aman dengan mengkategorisasi berbagai pola perilaku mengemudi. Dalam penelitian ini, lapisan perhatian (attention layer) diterapkan pada dataset UAH Driver-set untuk meningkatkan kemampuan model dalam mendeteksi pola deret waktu dalam data tersebut. Untuk tujuan ini, digunakan jaringan saraf buatan RNN dengan beberapa algoritma, yaitu BiLSTM, LSTM, GRU, dan BiGRU yang diterapkan untuk klasifikasi perilaku mengemudi. Berdasarkan hasil penelitian, waktu pengamatan 120 detik dan 180 detik pada data GPS sudah cukup untuk mengidentifikasi perilaku mengemudi secara akurat. Hasilnya menunjukkan bahwa penerapan lapisan perhatian pada algoritma BiLSTM menghasilkan peningkatan signifikan dalam akurasi dan skor F1, menjadikannya lebih efektif dalam mengklasifikasikan perilaku mengemudi dibandingkan dengan algoritma tanpa lapisan perhatian.

KATA KUNCI

Pembelajaran mendalam,Perilaku pengemudi,Klasifikasi,RNN,Transportasi

---

DAFTAR PUSTAKA

[1] R. Ghandour, A. J. Potams, I. Boulkaibet, B. Neji, Z. Al Barakeh, and A. S. Karar, ‘Machine learning methods for driver behaviour classification’, in BioSMART 2021 - Proceedings: 4th International Conference on Bio Engineering for Smart Technologies, Institute of Electrical and Electronics Engineers Inc., 2021. doi: 10.1109/BioSMART54244.2021.9677801.

[2] N. Kadri, A. Ellouze, M. Ksantini, and S. H. Turki, ‘New LSTM Deep Learning Algorithm for Driving Behavior Classification’, Cybern Syst, vol. 54, no. 4, pp. 387–405, 2023, doi: 10.1080/01969722.2022.2059133.

[3] M. Maulidah and H. F. Pardede, ‘Prediction Of Myers-Briggs Type Indicator Personality Using Long Short-Term Memory’, Jurnal Elektronika dan Telekomunikasi, vol. 21, no. 2, p. 104, Dec. 2021, doi: 10.14203/jet.v21.104 111.

[4] I. Cojocaru, P. S. Popescu, and M. C. Miha?escu, ‘Driver Behaviour Analysis based on Deep Learning Algorithms’, in RoCHI - International Conference on Human-Computer Interaction, MATRIX ROM, 2022, pp. 108–114. doi: 10.37789/rochi.2022.1.1.18.

[5] A. M. Darsono, N. H. Mat Yazi, A. S. Ja’Afar, M. A. Othman, and M. I. Ahmad, ‘Utilizing LSTM Networks for the Prediction of Driver Behavior’, Przeglad Elektrotechniczny, vol. 2024, no. 4, pp. 182–185, 2024, doi: 10.15199/48.2024.04.34.

[6] M. A. Khodairy and G. Abosamra, ‘Driving Behavior Classification Based on Oversampled Signals of Smartphone Embedded Sensors Using an Optimized Stacked-LSTM Neural Networks’, IEEE Access, vol. 9, pp. 4957–4972, 2021, doi: 10.1109/ACCESS.2020.3048915.

[7] Y. Cai, R. Zhao, H. Wang, L. Chen, Y. Lian, and Y. Zhong, ‘CNN-LSTM Driving Style Classification Model Based on Driver Operation Time Series Data’, IEEE Access, vol. 11, pp. 16203–16212, 2023, doi: 10.1109/ACCESS.2023.3245146.

[8] R. Ghandour, A. J. Potams, I. Boulkaibet, B. Neji, and Z. Al Barakeh, ‘Driver behavior classification system analysis using machine learning methods’, Applied Sciences (Switzerland), vol. 11, no. 22, Nov. 2021, doi: 10.3390/app112210562.

[9] H. Farah, S. Zatmeh, T. Toledo, and P. Wagner, ‘Impact of distracting activities and drivers’ cognitive failures on driving performance’, 2016. [Online]. Available: https://www.researchgate.net/publication/306230450 59 “Program Studi Ilmu Komputer (S2) Universitas Nusa Mandiri”

[10] R. Ghandour, B. Neji, A. M. El-Rifaie, and Z. Al Barakeh, ‘Driver Distraction and Stress Detection Systems: A Review’, International Journal of Engineering and Applied Sciences (IJEAS), vol. 7, no. 4, Apr. 2020, doi: 10.31873/ijeas.7.04.10.

[11] A. Jami, M. Razzaghpour, H. Alnuweiri, and Y. P. Fallah, ‘Augmented driver behavior models for high-fidelity simulation study of crash detection algorithms’, IET Intelligent Transport Systems, Mar. 2023, doi: 10.1049/itr2.12373.

[12] R. Gupta, D. Srivastava, M. Sahu, S. Tiwari, R. K. Ambasta, and P. Kumar, ‘Artificial intelligence to deep learning: machine intelligence approach for drug discovery’, Mol Divers, vol. 25, no. 3, pp. 1315–1360, Aug. 2021, doi: 10.1007/s11030-021-10217-3.

[13] M. Totox and H. F. Pardede, ‘Exploring the Effectiveness of Deep Learning in Analyzing Review Sentiment’, JIKO (Jurnal Informatika dan Komputer), vol. 6, no. 2, Aug. 2023, doi: 10.33387/jiko.v6i2.6372.

[14] D. Dompu, H. Asih, A. Purwanto, D. Riana, and S. Hadianti, ‘Bacteria Classification using Image Processing andResidual Neural Network (ResNet)’, vol. 20, no. 1, pp. 62–69, 2022.

[15] Mahmud, Windu Gata, Hafifah Bella Novitasari, Sigit Kurniawan, and Dedi Dwi Saputra, ‘Indonesian Government Revenue Prediction Using Long Short Term Memory’, Inspiration: Jurnal Teknologi Informasi dan Komunikasi, vol. 14, no. 1, pp. 111–124, Jun. 2024, doi: 10.35585/inspir.v14i1.67.

[16] B. Bohara, R. I. Fernandez, V. Gollapudi, and X. Li, ‘Short-Term Aggregated Residential Load Forecasting using BiLSTM and CNN-BiLSTM’, in 2022 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies, 3ICT 2022, Institute of Electrical and Electronics Engineers Inc., 2022, pp. 37–43. doi: 10.1109/3ICT56508.2022.9990696.

[17] M. Obaidur Rahman, M. Sabir Hossain, M. Shafiul Alam Forhad, T.-S. Junaid, and M. Kamal Hossen, ‘Predicting Prices of Stock Market using Gated Recurrent Units (GRUs) Neural Networks’, 2019. [Online]. Available: https://www.researchgate.net/publication/331385031

[18] D. Andriyanto and Y. Rianto, ‘Optimization Of Recurrent Neural Network In Indonesia Stock Exchange Price Prediction Modeling’, Journal of Information Systems, Informatics and Computing Issue Period, vol. 6, no. 1, pp. 1–10, 2022, doi: 10.52362/jisicom.v6i1.744. 60 “Program Studi Ilmu Komputer (S2) Universitas Nusa Mandiri”

[19] L. Banchi, E. Grant, A. Rocchetto, and S. Severini, ‘Modelling non-markovian quantum processes with recurrent neural networks’, New J Phys, vol. 20, no. 12, Dec. 2018, doi: 10.1088/1367-2630/aaf749.

[20] Y. Duan, Y. Liu, Y. Wang, S. Ren, and Y. Wang, ‘Improved BILSTM Model and Its Application in Stock Price Forecasting’, Electronics (Switzerland), vol. 12, no. 12, Jun. 2023, doi: 10.3390/electronics12122718.

[21] R. A. Nugraha, H. F. Pardede, and A. Subekti, ‘Oversampling based on generative adversarial networks to overcome imbalance data in predicting fraud insurance claim’.

[22] R. Xiong et al., ‘On Layer Normalization in the Transformer Architecture’, 2020.

[23] Deviana Sely Wita and A. Subekti, ‘Mobilenet-based Transfer Learning for Detection of Eucalyptus Pellita Diseases’, Jurnal Nasional Pendidikan Teknik Informatika (JANAPATI), vol. 12, no. 1, pp. 1–7, Mar. 2023, doi: 10.23887/janapati.v12i1.53220.

[24] Y. Peerthum and M. Stamp, ‘An Empirical Analysis of the Shift and Scale Parameters in BatchNorm’, http://arxiv.org/abs/2303.12818 Mar. 2023, [Online]. Available:

[25] A. Zevana and D. Riana, ‘TEXT CLASSIFICATION USING INDOBERT FINE-TUNING MODELING WITH CONVOLUTIONAL NEURAL NETWORK AND BI-LSTM’, Jurnal Teknik Informatika (Jutif), vol. 4, no. 6, pp. 1605–1610, Jan. 2024, doi: 10.52436/1.jutif.2023.4.6.1650.

[26] B. Lengerich, E. P. Xing, and R. Caruana, ‘Dropout as a Regularizer of Interaction Effects’, http://arxiv.org/abs/2007.00823 Jul. 2020, [Online]. Available:

[27] A. Pardamean and H. F. Pardede, ‘Tuned bidirectional encoder representations from transformers for fake news detection’, Indonesian Journal of Electrical Engineering and Computer Science, vol. 22, no. 3, pp. 1667–1671, Jun. 2021, doi: 10.11591/ijeecs.v22.i3.pp1667-1671.

[28] A. M. Hafiz, S. A. Parah, and R. U. A. Bhat, ‘Attention mechanisms and deep learning for machine vision: A survey of the state of the art’, Jun. 2021, [Online]. Available: http://arxiv.org/abs/2106.07550

[29] S. Jha, A. Sudhakar, and A. K. Singh, ‘Neural Machine Translation based Word Transduction Mechanisms for Low-Resource Languages’. [Online]. Available: https://www.ling.helsinki.fi/~fkarlsso/genkau2.html 61 “Program Studi Ilmu Komputer (S2) Universitas Nusa Mandiri”

[30] S. L. Karri, L. C. De Silva, D. T. C. Lai, and S. Y. Yong, ‘Identification and Classification of Driving Behaviour at Signalized Intersections Using Support Vector Machine’, International Journal of Automation and Computing, vol. 18, no. 3, pp. 480–491, Jun. 2021, doi: 10.1007/s11633-021-1295-y.

[31] R. Aggarwal et al., ‘Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis’, Dec. 01, 2021, Nature Research. doi: 10.1038/s41746-021-00438-z.

[32] H. F. Pardede, P. Adhi, V. Zilvan, A. R. Yuliani, and A. Arisal, ‘A Generalization of Sigmoid Loss Function Using Tsallis Statistics for Binary Classification’, Neural Process Lett, vol. 55, no. 4, pp. 5193–5214, 2023, doi: 10.1007/s11063-022-11087-y.

[33] F. Talebloo, E. A. Mohammed, and B. Far, ‘Deep Learning Approach for Aggressive Driving Behaviour Detection DBA = Driving Behaviour Analysis DBC = Driving Behaviour Classification GPS = Global Positioning System ML = Machine Learning DL = Deep Learning RNN = Recurrent Neural Network GRU = Gated Recurrent Unit LSTM = Long Short-Term Memory’.

[34] K. Darwish and M. Ali, ‘Driving Behaviors Recognition Using Deep Neural Networks’, 2023.

[35] G. Mustafa, S. J. Cho, and Y. Hwang, ‘Hybrid ConvLSTM with Attention for Precise Driver Behavior Classification’, in Proceedings - 2023 IEEE 6th International Conference on Artificial Intelligence and Knowledge Engineering, AIKE 2023, Institute of Electrical and Electronics Engineers Inc., 2023, pp. 1 8. doi: 10.1109/AIKE59827.2023.00008.

[36] N. Kadri, A. Ellouze, M. Ksantini, and S. H. Turki, ‘New LSTM Deep Learning Algorithm for Driving Behavior Classification’, Cybern Syst, vol. 54, no. 4, pp. 387–405, 2023, doi: 10.1080/01969722.2022.2059133.

[37] J. Vyas, N. Bhardwaj, and D. Das, ‘TransDBC: Transformer for Multivariate Time-Series based Driver Behavior Classification’. [Online]. Available: https://github.com/vanetlabiitj/TransDBC

[38] J. Xie, K. Hu, G. Li, and Y. Guo, ‘CNN-based driving maneuver classification using multi-sliding window fusion’, Expert Syst Appl, vol. 169, May 2021, doi: 10.1016/j.eswa.2020.114442.

[39] M. Savelonas, I. Vernikos, D. Mantzekis, E. Spyrou, A. Tsakiri, and S. Karkanis, ‘Hybrid representation of sensor data for the classification of driving behaviour’, Applied Sciences (Switzerland), vol. 11, no. 18, Sep. 2021, doi: 10.3390/app11188574. 62 “Program Studi Ilmu Komputer (S2) Universitas Nusa Mandiri”

[40] P. Koprinkova-Hristova, Y?ld?z Teknik U?niversitesi, M. IEEE Systems, and Institute of Electrical and Electronics Engineers, IEEE INISTA 2019?: Sofia, Bulgaria?: proceedings.

[41] IEEE ITSS and Institute of Electrical and Electronics Engineers, IEEE ITSC 2017?: 20th International Conference on Intelligent Transportation Systems?: Mielparque Yokohama in Yokohama, Kanagawa, Japan, October 16-19, 2017.

[42] E. Romera, L. M. Bergasa, and R. Arroyo, ‘Need data for driver behaviour analysis? Presenting the public UAH-DriveSet’, in IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, Institute of Electrical and Electronics Engineers Inc., Dec. 2016, pp. 387–392. doi: 10.1109/ITSC.2016.7795584.