Optimisasi Fungsi Aktivasi pada Arsitektur LeNet untuk Meningkatkan Akurasi Klasifikasi Citra Tumor Otak
-
Harliana Harliana
*
Universitas Nahdlatul Ulama Blitar, Blitar,
Indonesia
- Indra Riyana Rahadjeng Universitas Bina Sarana Informatika, Jakarta, Indonesia
- Riki Winanjaya STIKOM Tunas Bangsa, Pematangsiantar, Indonesia (*) Corresponding Author
Abstract
Brain hemorrhage is a critical medical condition that requires early and accurate detection to improve patient recovery outcomes. However, conventional image classification methods for brain hemorrhage still face limitations in terms of accuracy and efficiency. To address this issue, this study proposes optimizing the LeNet model using various activation functions—ReLU, Sigmoid, Tanh, and Swish—to enhance classification performance. Several optimization strategies were applied, including data augmentation techniques (flipping, rotation, shearing, rescaling) and fine-tuning of hyperparameters, to improve model generalization. Experimental results indicate that the model utilizing the Swish activation function achieves the most stable overall performance, with an accuracy of 55%, recall of 54%, precision of 54%, F1-score of 54%, and a ROC AUC value of 0.45. Although this performance is still below clinical application standards, the findings serve as an initial step toward exploring activation function optimization in CNN architectures. Further research is needed to significantly enhance classification accuracy and enable clinical viability.
Downloads
References
H. T. Zaw, N. Maneerat, and K. Y. Win, “Brain tumor detection based on Naïve Bayes classification,” Proceeding - 5th Int. Conf. Eng. Appl. Sci. Technol. ICEAST 2019, pp. 1–4, 2019, doi: 10.1109/ICEAST.2019.8802562.
N. F. B. Ali, “Comparison Review on Brain Tumor Classification and Segmentation using Convolutional Neural Network (CNN) and Capsule Network,” Int. J. Adv. Comput. Sci. Appl., vol. 14, no. 4, pp. 723–731, 2023, doi: 10.14569/IJACSA.2023.0140479.
S. S. Dip, “Enhancing Brain Tumor Classification in MRI: Leveraging Deep Convolutional Neural Networks for Improved Accuracy,” Int. J. Inf. Technol. Comput. Sci., vol. 16, no. 3, pp. 12–21, 2024, doi: 10.5815/ijitcs.2024.03.02.
K. M. Sundaram, “EWPCO-enabled Shepard convolutional neural network for classification of brain tumour using MRI image,” Imaging Sci. J., vol. 72, no. 3, pp. 349–366, 2024, doi: 10.1080/13682199.2023.2206271.
B. L. Nandipati, “Hybrid deep learning model for detection and classification of lung cancer fusion images using MCNet,” J. Intell. Fuzzy Syst., vol. 45, no. 2, pp. 2235–2252, 2023, doi: 10.3233/JIFS-231145.
S. Kharya and S. Soni, “Weighted Naive Bayes Classifier: A Predictive Model for Breast Cancer Detection,” Int. J. Comput. Appl., vol. 133, no. 9, pp. 32–37, 2016, doi: 10.5120/ijca2016908023.
M. A. Lubis, D. G. S. Saragih, I. D. Anastasia, A. P. Windarto, and P. Alkhairi, “Application of the ANN Algorithm to Predict Access to Drinkable Water in North Sumatra Regency/City,” Int. J. Informatics Data Sci., vol. 1, no. 1, pp. 18–25, 2023.
A. P. Windarto, T. Herawan, and P. Alkhairi, “Prediction of Kidney Disease Progression Using K-Means Algorithm Approach on Histopathology Data,” in Artificial Intelligence, Data Science and Applications, Y. Farhaoui, A. Hussain, T. Saba, H. Taherdoost, and A. Verma, Eds., Cham: Springer Nature Switzerland, 2024, pp. 492–497. doi: 10.1007/978-3-031-48465-0_66.
W. El-Shafai, “Efficient classification of different medical image multimodalities based on simple CNN architecture and augmentation algorithms,” J. Opt., vol. 53, no. 2, pp. 775–787, 2024, doi: 10.1007/s12596-022-01089-3.
O. H. Kesav, “Enhancing Brain Tumor Detection and Classification with Reduced Complexity Spatial Fusion Convolutional Neural Networks,” Int. J. Intell. Eng. Syst., vol. 17, no. 1, pp. 263–277, 2024, doi: 10.22266/ijies2024.0229.25.
M. V. V Saradhi, “Prediction of Alzheimer’s Disease Using LeNet-CNN Model with Optimal Adaptive Bilateral Filtering,” Int. J. Commun. Networks Inf. Secur., vol. 15, no. 1, pp. 12–23, 2023, doi: 10.17762/ijcnis.v15i1.5706.
O. I. Berngardt, “Improving Classification Neural Networks by using Absolute activation function (MNIST/LeNET-5 example),” no. 2015, pp. 1–19, 2023, [Online]. Available: http://arxiv.org/abs/2304.11758
H. Pratiwi et al., “Sigmoid Activation Function in Selecting the Best Model of Artificial Neural Networks,” J. Phys. Conf. Ser., vol. 1471, no. 1, 2020, doi: 10.1088/1742-6596/1471/1/012010.
W. N. Ismail, H. A. Alsalamah, M. M. Hassan, and E. Mohamed, “AUTO-HAR: An adaptive human activity recognition framework using an automated CNN architecture design,” Heliyon, vol. 9, no. 2, p. e13636, 2023, doi: 10.1016/j.heliyon.2023.e13636.
P. Hu, “DReP: Deep ReLU pruning for fast private inference,” J. Syst. Archit., vol. 152, 2024, doi: 10.1016/j.sysarc.2024.103156.
C. Közkurt, “Trish: an efficient activation function for CNN models and analysis of its effectiveness with optimizers in diagnosing glaucoma,” J. Supercomput., vol. 80, no. 11, pp. 15485–15516, 2024, doi: 10.1007/s11227-024-06057-1.
N. G. Amit Gupta, Richa Gupta, “An efficient approach for classifying chest X-ray images using different embedder with different activation functions in CNN,” J. Interdiscip. Math., vol. 24, no. 2, pp. 285–297, 2021, doi: 10.1080/09720502.2020.1838060.
Z. Yin, “Assistant investigation of energy dissipation in non-obstructive particle damper based on a neural network using simulated annealing backpropagation,” JVC/Journal Vib. Control, vol. 29, no. 23, pp. 5387–5397, 2023, doi: 10.1177/10775463221135207.
G. Pan, J. Li, F. Lin, T. Sun, and Y. Sun, “A Combined Activation Function for Learning Performance Improvement of CNN Image Classification,” In Proceedings of 5th International Conference on Vehicle, Mechanical and Electrical Engineering (ICVMEE 2019), pp. 360–366, 2020, doi: 10.5220/0008851103600366.
Q. Hua, “Gaussian-type activation function for complex-valued CNN and its application in polar-SAR image classification,” J. Appl. Remote Sens., vol. 15, no. 2, 2021, doi: 10.1117/1.JRS.15.026510.
N. Leema, H. K. Nehemiah, and A. Kannan, “Neural network classifier optimization using Differential Evolution with Global Information and Back Propagation algorithm for clinical datasets,” Appl. Soft Comput. J., vol. 49, pp. 834–844, 2016, doi: 10.1016/j.asoc.2016.08.001.
M. R. Lubis, “Metode Hybrid Particle Swarm Optimization - Neural Network Backpropagation Untuk Prediksi Hasil Pertandingan Sepak Bola,” J-SAKTI (Jurnal Sains Komput. dan Inform., vol. 1, no. 1, p. 71, 2017, doi: 10.30645/j-sakti.v1i1.30.
S. Sarraf, D. D. Desouza, J. A. E. Anderson, and C. Saverino, “MCADNNet: Recognizing stages of cognitive impairment through efficient convolutional fMRI and MRI neural network topology models,” IEEE Access, vol. 7, no. Mci, pp. 155584–155600, 2019, doi: 10.1109/ACCESS.2019.2949577.
M. El Adoui, S. A. Mahmoudi, M. A. Larhmam, and M. Benjelloun, “MRI breast tumor segmentation using different encoder and decoder CNN architectures,” Computers, vol. 8, no. 3, 2019, doi: 10.3390/computers8030052.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Optimisasi Fungsi Aktivasi pada Arsitektur LeNet untuk Meningkatkan Akurasi Klasifikasi Citra Tumor Otak
Pages: 2690−2699
Copyright (c) 2025 Harliana Harliana, Indra Riyana Rahadjeng, Riki Winanjaya
This work is licensed under a Creative Commons Attribution 4.0 International 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 Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment 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 acknowledgment 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 (Refer to The Effect of Open Access).
