Convolutional Neural Network Activation Function Performance on Image Recognition of The Batak Script
DOI:
10.33395/sinkron.v9i1.13192Keywords:
Deep Learning, Convolutional Neural Network, Activation Function, tanH, ReLU.Abstract
Deep Learning is a sub-set of Machine learning, Deep Learning is widely used to solve problems in various fields. One of the popular deep learning architectures is The Convolutional Neural Network (CNN), CNN has a layer that transforms feature extraction automatically so it is widely used in image recognition. However, CNN's performance using the tanh function is still relatively low, therefore it is necessary to select the right activation function to improve accuracy performance. This study analyzes the use of the activation function in image recognition of the Batak script. The result of this study is that the CNN model using the ReLU and eLU functions produces the highest accuracy compared to the CNN model using the tanh function. The CNN model using eLU produces the best accuracy performance in the training process, which is 99.71% with an error value of 0.0108. Meanwhile, in the testing process, the highest accuracy value is generated by the CNN Model using the ReLU function with an accuracy of 94.11%, an error value of 0.3282, a precision value of 0.9411, a recall of 0.9411, and an f1-score of 0.9416.
Downloads
References
Abiodun, O. I., Jantan, A., Omolara, A. E., Dada, K. V., Mohamed, N. A., and Arshad, H. 2018. State-of-the-art in artificial neural network applications: A survey. Heliyon, 4(11), e00938. https://doi.org/10.1016/j.heliyon.2018.e00938
Afakh, M. L., Risnumawan, A., Anggraeni, M. E., Tamara, M. N., & Ningrum, E. S. 2017. Aksara jawa text detection in scene images using convolutional neural network. 2017 International Electronics Symposium on Knowledge Creation and Intelligent Computing (IES-KCIC). doi:10.1109/kcic.2017.8228567
Ahmed, W. and Karim, A. 2020. The Impact of Filter Size and Number of Filters on Classification Accuracy in CNN. 88-93. 10.1109/CSASE48920.2020.9142089.
Albawi, S., Mohammed, T. A., & Al-Zawi, S. (2017). Understanding of a convolutional neural network. 2017 International Conference on Engineering and Technology (ICET), 1–6. https://doi.org/10.1109/ICEngTechnol.2017.8308186
Batak Pustaha [Magic Book] https://digital.soas.ac.uk/LOAA005798/00004
Bertrand, H., Ardon, R., Perrot, M., & Bloch, I. 2017. Hyperparameter optimization of deep neural networks: combining Hperband with Bayesian model selection.
Bezdan, T., & Bačanin D., N. 2019. Convolutional neural network layers and architectures. Proceedings of the International Scientific Conference - Sinteza 2019, 445–451. https://doi.org/10.15308/Sinteza-2019-445-451
Book in the Balta [sic] language of Sumatra, on bark https://digital.soas.ac.uk/AA00001360/00001
Clevert, D.-A., Unterthiner, T., & Hochreiter, S. 2016. Fast and accurate deep network learning by exponential linear units(Elus). ArXiv:1511.07289 [Cs]. http://arxiv.org/abs/1511.07289
Duchi, J., Haza, E., & Singer, Y. 2011. Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research (JMLR) 12: 2121-2159.
Faza, S. 2018. Peningkatan Kinerja Dalam Pengklasifikasian Menggunakan Deep Learning. [Tesis]. Medan: Universitas Sumatera Utara, Program Pasca Sarjana.
Goodfellow, I., Bengio, Y., and Courville, A.(2016). 6.2.2.3 Softmax Units for Multinoulli Output Distributions. Deep Learning. MIT Press. pp. 180–184. ISBN 978-0-26203561-3.
Hasugian, M. J. 2017. Feature Extraction Comparison in Handwriting Recognition of Batak Toba Alphabet. International Journal of Information Technology and Electrical Engineering.
Hasugian, M. J. dan Pasaribu, N. T. B. 2015. Perbandingan Ekstraksi Ciri Statistik dan EFD dalam Pengenalan Tulisan Tangan Aksara Batak Toba, Seminar Nasional Teknologi Terapan, Sekolah Vokasi Universitas Gadjah Mada.
Hidayat, A., Nurtanio, I., and Tahir, Z. 2019. Segmentation and Recognition of Handwritten Lontara Characters Using Convolutional Neural Network. 2019 International Conference on Information and Communications Technology (ICOIACT). doi:10.1109/icoiact46704.2019.8938445
Hinton, G. 2012. Neural Networks for Machine Learning. (Online)
.https://www.coursera.org/learn/neural-networks (02 Januari 2018).
Julpan, J., Nababan, E. B., dan Zarlis, M. 2018. Analisis Fungsi Aktivasi Sigmoid Biner dan Sigmoid Bipolar dalam Algoritma Backpropagation pada Prediksi Kemampuan Siswa. Jurnal Teknovasi: Jurnal Teknik dan Inovasi, 2(1), 103-116.
Khadijah, R., & Nurhadiyatna, A. 2017. Deep learning for handwritten Javanese character recognition. 2017 1st International Conference on Informatics and Computational Sciences (ICICoS), 59-64.
Kingma, D. P., & Ba, J. 2017. Adam: A method for stochastic optimization. ArXiv:1412.6980 [Cs]. http://arxiv.org/abs/1412.6980
Kozok, Uli. 2009. Surat Batak: Sejarah Perkembangan Tulisan Batak, Berikut Pedoman Menulis Aksara Batak dan Cap Sisimangaraja XII. KPG (Kepustakaan Populer Gramedia) & EFEO
Krizhevsky, A., Sutskever, I., & Hinton, G. E. 2017. ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84–90. https://doi.org/10.1145/3065386
LeCun, Y., Bengio, Y., and Hinton, G. 2015. Deep learning. Nature, vol. 521, no.7553, pp. 436–444.
LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. 1998. Gradient-based learning ap-plied to document recognition. Proceedings of the IEEE,86(11), 2278–2324. doi: 10.1109/5.726791.
Lorentius, C. A.; Gunadi, K.; Tjondrowiguno, A. N. 2019. Pengenalan Aksara Jawa dengan Menggunakan Metode Convolutional Neural Network. Jurnal Infra Vol 7, No 1.
Lumbangaol, S. K. 2021. Peningkatan Kinerja Backpropagation Dengan Kombinasi Algoritma Genetika Pada Pengenalan Pola Aksara Batak Karo. [Tesis]. Medan: Program Studi Magister Teknik Informatika, Universitas Sumatera Utara.
Miranda, N. D., Novamizanti, L., & Rizal, S. 2020. Convolutional neural network pada klasifikasi sidik jari menggunakan resnet-50. Jurnal Teknik Informatika (Jutif), 1(2), 61–68. https://doi.org/10.20884/1.jutif.2020.1.2.18
Modi, A. S. 2018. Review Article on Deep Learning Approaches. 2018 Second International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India, pp. 1635-1639. doi:10.1109/iccons.2018.8663057
Nair, V. & Hinton, G. E. 2010. Rectified Linear Units Improve Restricted Boltzmann Machines.. In J. Fürnkranz & T. Joachims (eds.), ICML (p./pp. 807-814), : Omnipress.
Nasoichah. C. 2015. Faktor Yang Mempengaruhi Perbedaan Bentuk Aksara Batak Pada Pustaha Laklak Dan Naskah Bambu Di Mandailing Natal. Forum Arkeologi Volume 28, Nomor 3, November 2015 (145 - 154)
Nasoichah, C., Susilowati R, N., Oetomo, W., Setiawan, T., Soedewo, E. 2017. 31 Sumber-Sumber Tertulis Beraksara Angkola-Mandailing Di Kab. Mandailing Natal, Kab. Tapanuli Selatan Dan Kab. Padang Lawas Utara. Berita Penelitian Arkeologi. http://repositori.kemdikbud.go.id/20018/1/BPA%2031%20tahun%202017.pdf
Nugroho, O. 2012. Batak Karo Alphabet Pattern Recognition. Media Aplikom, 2(2), 11–16. https://doi.org/10.33488/1.ma.2012.2.85
Onwujekwegn, G and Yoon, V. Y. 2020 . Analyzing the Impacts of Activation Functions on the Performance of Convolutional Neural Network Models. AMCIS 2020 Proceedings. 4
Panggabean, M. dan Rønningen, L. 2009. Character Recognition of the Batak Toba Alphabet Using Signatures and Simplified Chain Code. Signal and Image Processing Applications (ICSIPA), IEEE, pp. 215 – 220. doi:10.1109/icsipa.2009.5478614.
Pasaribu, N. T. B., & Hasugian, M. J. 2015. Pengenalan Tulisan Tangan Ina ni surat Aksara Batak Toba,” Seminar Nasional Teknologi Terapan, Sekolah Vokasi Universitas Gadjah Mada.
Pasaribu, N. T. B., & Hasugian, M. J. 2016. Noise removal on Batak Toba handwritten script using Artificial Neural Network. 2016 3rd International Conference on Information Technology, Computer, and Electrical Engineering (ICITACEE). doi:10.1109/icitacee.2016.7892474
Patterson, J. and Gibson, A. 2017. Deep Learning: A Practitioner’s Approach. O’Reilly Media, Inc.: Sebastopol
Putri, A. R. 2017. Pengenalan Pola Aksara Batak Karo menggunakan Metode Backprogation. Yogyakarta: Universitas Sanata Dharma.
Radiuk, P. M. 2017. Impact of training set batch size on the performance of convolutional neural networks for diverse datasets. Information Technology and Management Science, 20(1). https://doi.org/10.1515/itms-2017-0003
Romulus, P., Maraden, Y., Purnamasari, P. D., & Ratna, A. A. P. 2015. An analysis of optical character recognition implementation for ancient Batak characters using K-nearest neighbors principle. 2015 International Conference on Quality in Research (QiR). doi:10.1109/qir.2015.7374893
Septianto, T., Setyati, E., & Santoso, J. 2018. Model CNN LeNet dalam Rekognisi Angka Tahun pada Prasasti Peninggalan Kerajaan Majapahit. Jurnal Teknologi dan Sistem Komputer, 6(3), 106 109. https://doi.org/10.14710/jtsiskom.6.3.2018.106-109
Shrestha, A.K., and Mahmood, A. 2019. Review of Deep Learning Algorithms and Architectures. IEEE Access, 7, 53040-53065.
Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. ArXiv:1409.1556 [Cs]. http://arxiv.org/abs/1409.1556
Sitinjak, S. 2012. Pengenalan Tulisan Tangan Aksara Batak Toba Menggunakan Backpropagation. TESIS Program Studi Magister Teknik Informatika, Univ. Atmajaya, Yogyakarta.
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R. 2014. Dropout: A Simple Way to Prevent Neural Networks from Overfitting. Journal of Machine Learning Research. 15. 1929-1958.
Susilawati, S., & Muhathir, M. 2019. Analisis Pengaruh Fungsi Aktivasi, Learning Rate Dan Momentum Dalam Menentukan Mean Square Error (MSE) Pada Jaringan Saraf Restricted Boltzmann Machines (RBM). JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING, 2(2), 77-91. doi:https://doi.org/10.31289/jite.v2i2.2162
Tambunan, F. 2019. Pengenalan Aksara Batak Dengan Metode Perceptron. Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika), 4(1), 160-170. doi:http://dx.doi.org/10.30645/jurasik.v4i1.129
Tambunan, F., Ginting, E., Victor Haryanto, E., & Fauzi, M. 2020. Pattern recognition of batak script using habbian method. 2020 8th International Conference on Cyber and IT Service Management (CITSM), 1–4. https://doi.org/10.1109/CITSM50537.2020.9268839
Wibawa, M. S. 2017. Pengaruh Fungsi Aktivasi, Optimisasi dan Jumlah Epoch Terhadap Performa Jaringan Saraf Tiruan. Jurnal Sistem Dan Informatika (JSI), 11(2), 167-174. Retrieved from https://jsi.stikom-bali.ac.id/index.php/jsi/article/view/129
Widyastuti, W. 2018. Kinerja Deep Convolutional Network untuk Pengenalan Aksara Pallawa. Media Teknika, 12(2). doi:https://doi.org/10.24071/mt.v12i2.1085
Yaqub, M., Jinchao, F., Zia, M. S., Arshid, K., Jia, K., Rehman, Z. U., & Mehmood, A. 2020. State-of-the-Art CNN Optimizer for Brain Tumor Segmentation in Magnetic Resonance Images. Brain sciences, 10(7), 427. https://doi.org/10.3390/brainsci10070427
Yoon, H.-J., Gounley, J., Gao, S., Alawad, M., Ramanathan, A., & Tourassi, G. 2019. Model-based hyperparameter optimization of convolutional neural networks for information extraction from cancer pathology reports on hpc. 2019 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), 1–4. https://doi.org/10.1109/BHI.2019.8834674
Yu, T., & Zhu, H. 2020. Hyper-parameter optimization: A review of algorithms and applications. ArXiv:2003.05689 [Cs, Stat]. http://arxiv.org/abs/2003.05689
Zamzami, E. M., Hayanti, S., & Nababan, E. B. 2021. Diagonal Based Feature Extraction and Backpropagation Neural Network in Handwritten Batak Toba Characters Recognition. Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, 6(2). https://doi.org/10.22219/kinetik.v6i2.1212.
Downloads
|
How to Cite
Issue
Section
License
Copyright (c) 2023 Abdul Muis, Elviawaty Muisa Zamzami, Erna Budhiarti Nababan
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Muhammad Khoiruddin harahap
Google Scholar 
Moraref
PKP Index
Garuda Kemdikbud
Indonesia OneSearch
OCLC Worldcat
Dimensions
Index Copernicus
Scilit
