Model Deep Learning untuk Mendeteksi dan Memprediksi Konsentrasi Manusia dalam Lingkungan Dinamis: Penelitian

Devi Fajar Wati; Lila Setiyani; Deden Moch Alfiansyah; M. Jembar Jomantara; Dedih Dedih; M. Ridho Darmawan

doi:10.31004/jerkin.v4i4.6336

Authors

Devi Fajar Wati Universitas Horizon Indonesia
Lila Setiyani Universitas Horizon Indonesia
Deden Moch Alfiansyah Universitas Horizon Indonesia
M. Jembar Jomantara Universitas Horizon Indonesia
Dedih Dedih Universitas Horizon Indonesia
M. Ridho Darmawan Universitas Horizon Indonesia

DOI:

https://doi.org/10.31004/jerkin.v4i4.6336

Keywords:

Deep Learning, Konsentrasi Manusia, EEG, Multimodal Learning, Monitoring Kognitif

Abstract

Konsentrasi manusia merupakan aspek kognitif penting yang memengaruhi efektivitas belajar, produktivitas kerja, dan keselamatan dalam aktivitas sehari-hari. Namun, meningkatnya distraksi digital dan lingkungan yang dinamis membuat individu semakin sulit mempertahankan fokus secara konsisten. Penelitian sebelumnya umumnya hanya berfokus pada deteksi tingkat konsentrasi dalam lingkungan laboratorium yang terkontrol dan belum banyak membahas prediksi perubahan konsentrasi secara real-time pada situasi dinamis. Penelitian ini bertujuan mengembangkan model deep learning multimodal untuk mendeteksi dan memprediksi tingkat konsentrasi manusia menggunakan data fisiologis dan perilaku. Pendekatan yang diusulkan mengintegrasikan sinyal electroencephalography (EEG), eye-tracking, dan perilaku interaksi digital untuk meningkatkan akurasi analisis konsentrasi. Arsitektur hybrid Convolutional Neural Network (CNN) dan Bidirectional Long Short-Term Memory (BiLSTM) digunakan untuk menangkap pola spasial dan temporal dari data multimodal. Model dirancang untuk melakukan deteksi konsentrasi secara real-time serta memprediksi perubahan fokus jangka pendek pada lingkungan dinamis seperti pembelajaran daring, aktivitas multitasking, dan simulasi mengemudi. Metode penelitian meliputi pengumpulan data, pra-pemrosesan, pengembangan model, dan evaluasi performa menggunakan metrik accuracy, precision, recall, F1-score, dan RMSE. Hasil akhir penelitian berupa model deep learning multimodal yang mampu mendeteksi dan memprediksi tingkat konsentrasi manusia secara lebih adaptif dibandingkan pendekatan unimodal. Penelitian ini diharapkan dapat memberikan kontribusi dalam pengembangan teknologi kecerdasan buatan pada bidang pendidikan, kesehatan digital, dan keselamatan kerja..

References

Alhagry, S., Fahmy, A. A., & El-Khoribi, R. A. (2017). Emotion recognition based on EEG using LSTM recurrent neural network. International Journal of Advanced Computer Science and Applications, 8(10), 355–358. https://doi.org/10.14569/IJACSA.2017.081046

Chueh, M. T. W., & Chang, K. M. (2019). Using eye tracking to assess gaze concentration in meditation. Sensors, 19(7), 1612. https://doi.org/10.3390/s19071612

Craik, A., He, Y., & Contreras-Vidal, J. L. (2019). Deep learning for electroencephalogram (EEG) classification tasks: A review. Journal of Neural Engineering, 16(3), 031001. https://doi.org/10.1088/1741-2552/ab0ab5

Cui, J., Lan, Z., Sourina, O., & Müller-Wittig, W. (2021). EEG-based cross-subject driver drowsiness recognition with an interpretable convolutional neural network. IEEE Transactions on Neural Networks and Learning Systems, 32(10), 4567–4578. https://doi.org/10.1109/TNNLS.2021.3054904

Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press. https://www.deeplearningbook.org

Hosseini, S., & Guo, X. (2019). Deep convolutional neural network for automated detection of mind wandering using EEG signals. arXiv preprint arXiv:1911.02437. https://arxiv.org/abs/1911.02437

Huang, X., Zhang, T., & Wang, Y. (2022). Multimodal deep learning for human cognitive state detection using EEG and eye-tracking data. Neural Computing and Applications, 34(18), 15643–15658. https://doi.org/10.1007/s00521-021-06745-2

Iwata, M., Hayashi, T., Kinoshita, M., Nakajima, A., & Yamamoto, T. (2023). Deep multimodal learning model for prediction of prognosis in central nervous system inflammation. NPJ Digital Medicine, 6(1), 118. https://doi.org/10.1038/s41746-023-00845-7

LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539

Li, G., Lee, C. H., & Jung, T. P. (2020). EEG-based attention recognition using deep learning neural network. Sensors, 20(14), 4007. https://doi.org/10.3390/s20144007

Roy, Y., Banville, H., Albuquerque, I., Gramfort, A., Falk, T. H., & Faubert, J. (2019). Deep learning-based electroencephalography analysis: A systematic review. Journal of Neural Engineering, 16(5), 051001. https://doi.org/10.1088/1741-2552/ab260c

Schirrmeister, R. T., Springenberg, J. T., Fiederer, L. D. J., Glasstetter, M., Eggensperger, K., Tangermann, M., Hutter, F., Burgard, W., & Ball, T. (2017). Deep learning with convolutional neural networks for EEG decoding and visualization. Human Brain Mapping, 38(11), 5391–5420. https://doi.org/10.1002/hbm.23730

Shah, S. M. H., & Saleem, S. (2022). Measuring the percentage of brain concentration levels using Bi-LSTM algorithm. Procedia Computer Science, 197, 534–541. https://doi.org/10.1016/j.procs.2021.12.169

Stiefelhagen, R., & Fugen, C. (2018). Tracking gaze and visual focus of attention in social interaction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(6), 1363–1377. https://doi.org/10.1109/TPAMI.2017.2713462

Velnath, R., Prabhu, V., & Krishnakumar, S. (2021). Analysis of EEG signal for the estimation of concentration level of humans. IOP Conference Series: Materials Science and Engineering, 1084(1), 012003. https://doi.org/10.1088/1757-899X/1084/1/012003

Xiang, J., Supakar, R., Satvaya, P., & Chakrabarti, P. (2024). Deep learning methods for EEG applications: Focusing on CNN and RNN. Highlights in Science, Engineering and Technology, 85, 162–168. https://doi.org/10.54097/hset.v85i.14563

Xu, L., Wang, S., & Xu,Y. (2020). The impact of focused attention on emotional evaluation: An eye-tracking investigation. Frontiers in Psychology, 11, 585047. https://doi.org/10.3389/fpsyg.2020.585047

Yang, Y., Wu, Q., Fu, Y., & Chen, X. (2021). Continuous EEG-based attention recognition using deep convolutional neural networks. IEEE Access, 9, 49689–49698. https://doi.org/10.1109/ACCESS.2021.3069738

Zhang, Y., Li, H., & Chen, X. (2022). Multimodal deep learning for cognitive state detection using EEG and behavioral data. Neural Computing and Applications, 34(15), 12541–12555. https://doi.org/10.1007/s00521-021-06789-4