ANALISIS PERBANDINGAN PENGARUH NORMALISASI DAN STANDARDISASI TERHADAP AKURASI MODEL CNN PADA KLASIFIKASI EKSPRESI WAJAH

Gilang Isnan Fiyoriirly; Dian Ade Kurnia; Yudhistira Arie Wijaya; Mulyawan .

Authors

Gilang Isnan Fiyoriirly STMIK IKMI Cirebon, Indonesia
Dian Ade Kurnia STMIK IKMI Cirebon, Indonesia
Yudhistira Arie Wijaya STMIK IKMI Cirebon, Indonesia
Mulyawan . STMIK IKMI Cirebon, Indonesia

Keywords:

K-Means; Pengelompokan Saham; Bank BNI; Akuntansi Investasi; KDD

Abstract

Penelitian ini bertujuan membandingkan pengaruh normalisasi [0,1] dan standardisasi (Z-Score) terhadap akurasi model CNN pada klasifikasi ekspresi wajah senyum dan tidak senyum. Penelitian dilakukan menggunakan dataset Smiling or Not Face Data dari Kaggle yang terdiri dari 9.200 citra wajah grayscale berukuran 64x64 piksel. Citra-citra ini kemudian diproses melalui teknik augmentasi serta dua pendekatan preprocessing berbeda sebelum dilatih menggunakan arsitektur CNN yang sama.Keunikan penelitian ini terletak pada pembandingan langsung antara dua metode preprocessing dalam satu eksperimen yang terkontrol, guna mengidentifikasi teknik mana yang memberikan hasil klasifikasi paling optimal.Model dengan preprocessing normalisasi [0,1] menghasilkan akurasi 87,08%, precision 87,07%, recall 87,07%, dan f1-score 87,06%. Sementara itu, model dengan preprocessing standardisasi Z-Score menghasilkan akurasi 86,30%, precision 86,28%, recall 86,29%, dan f1-score 86,27%.Hasil ini menunjukkan bahwa teknik normalisasi lebih unggul dalam konteks klasifikasi biner ekspresi wajah pada dataset dengan ukuran menengah dan format grayscale. Oleh karena itu, normalisasi direkomendasikan sebagai metode preprocessing yang lebih efektif dalam membangun model CNN untuk tugas serupa.

Kata kunci: CNN, normalisasi, standardisasi, preprocessig, ekspresi wajah, klasifikasi

References

Agung, S., E., Rifai, P., A., Wijayanto, & T. (2024). Image-based facial emotion recognition using convolutional neural network on emognition dataset. Scientific Reports, 14. https://doi.org/https://doi.org/10.1038/s41598-024-65276-x

Ahsan, M., M., Mahmud, P., M. A., Saha, K., P., Gupta, D., K., Siddique, & Z. (2021). Effect of data scaling methods on machine learning algorithms and model performance. Technologies, 9(3). https://doi.org/https://doi.org/10.3390/technologies903005

Albert, S., Wichtmann, B.-D., Wember, F., Zimmer, F.-G., & al., et. (2023). Comparison of image normalization methods for multi-site and multimodal deep learning. Applied Sciences, 13(15). https://doi.org/https://doi.org/10.3390/app1315892

Allgaier, & J. (2024). Cross-Validation Visualized: A Narrative Guide to Cross-Validation Techniques. MDPI Proceedings, 6(2). https://doi.org/https://doi.org/10.3390/proceedings6020065

Alzubaidi, L., Zeadally, S., Kbhbeib, O., Samuel, M., Jaradat, & M. (2021). Review of deep learning: Concepts, CNN architectures, challenges and applications. Journal of Big Data, 8(1). https://doi.org/https://doi.org/10.1186/s40537-021-00444-8

Alzubaidi, L., Zhang, J., Humaidi, J., A., & al., et. (2021). Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data, 8. https://doi.org/https://doi.org/10.1186/s40537-021-00444-8

Apicella, A., Isgrò, F., Pollastro, A., Prevete, & R. (2023). On the effects of data normalisation for domain adaptation on EEG data. Engineering Applications of Artificial Intelligence, 128. https://doi.org/https://doi.org/10.1016/j.engappai.2023.106205

Archana, R., Sharma, R., Gupta, S., Mehrotra, & R. (2024). Deep learning models for digital image processing: A review. Artificial Intelligence Review, 57. https://doi.org/https://doi.org/10.1007/s10462-023-10631-z

Castaldo, N., & al., et. (2023). The effect of feature normalization methods in radiomics. Insights into Imaging, 14. https://doi.org/https://doi.org/10.1186/s13244-023-01575-7

Cè, M., & al., et. (2024). Decoding Radiomics: A Step-by-Step Guide to Machine-Learning in Medical Imaging. Diagnostics, 14(22). https://doi.org/https://doi.org/10.3390/diagnostics14222473

Chen, L., Li, S., Bai, Q., Yang, J., Jiang, S., Miao, & Y. (2021). Review of image classification algorithms based on convolutional neural networks. Remote Sensing, 13(22). https://doi.org/https://doi.org/10.3390/rs13224712

Collins, S., G., Reitsma, B., J., Altman, G., D., Moons, M., K. G., & al., et. (2024). TRIPOD+AI statement: Updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ, 385. https://doi.org/https://doi.org/10.1136/bmj-2023-078378

Dhaka, S., V., Meena, V., S., Rani, G., Sinwar, D., & al., et. (2021). A survey of deep convolutional neural networks applied for prediction of plant leaf diseases. Sensors, 21(14). https://doi.org/https://doi.org/10.3390/s21144749

Ekundayo, O., & Viriri, S. (2021). Facial Expression Recognition: A Review of Trends and Techniques. Ieee Access, 9, 136944–136973. https://doi.org/10.1109/access.2021.3113464

Elsheikh, A., R., & al., et. (2024). Improved facial emotion recognition model based on a deep convolutional neural network. Scientific Reports, 14. https://doi.org/https://doi.org/10.1038/s41598-024-79167-8

Hao, X., Gao, M., Li, C., Xu, J., Wang, & B. (2023). A review of data augmentation methods of remote sensing target detection. Remote Sensing, 15(3). https://doi.org/https://doi.org/10.3390/rs15030827

Hu, F., Liu, Y., Wang, & Y. (2023). Image harmonization: A review of statistical and deep learning methods. Image and Vision Computing, 118. https://doi.org/https://doi.org/10.1016/j.imavis.2023.104648

Iwana, K., B., Uchida, & S. (2021). An empirical survey of data augmentation for time series classification with neural networks. PLOS ONE, 16(7). https://doi.org/https://doi.org/10.1371/journal.pone.0254841

Kopalidis, T., & al., et. (2024). Advances in facial expression recognition: A survey of methods, datasets and opportunities. Information, 15(3). https://doi.org/https://doi.org/10.3390/info15030135

Kopalidis, T., Solachidis, V., Vretos, N., Daras, & P. (2024). Advances in facial expression recognition: A survey of methods, benchmarks, models and datasets. Information, 15(3). https://doi.org/https://doi.org/10.3390/info15030135

Krichen, & M. (2023). Convolutional neural networks: A survey. Computers, 12(8). https://doi.org/https://doi.org/10.3390/computers12080151

Li, J., Duan, Q., Sun, J., Lu, & H. (2020). Attention mechanism‑based convolutional neural network for facial expression recognition. Pattern Recognition Letters, 135. https://doi.org/https://doi.org/10.1016/j.patrec.2020.07.010

Li, M., Hu, Z., Wang, Y., & al., et. (2023). Medical image analysis using deep learning algorithms. Frontiers in Public Health, 11. https://doi.org/https://doi.org/10.3389/fpubh.2023.1273253

Liang, C., Dong, & J. (2023). A survey of deep learning-based facial expression recognition research. Frontiers in Computing and Intelligent Systems, 5(2). https://doi.org/https://doi.org/10.54097/fcis.v5i2.12445

Liu, Y., T., Zhang, Q., H., Long, X., H., Shi, M., J., Yao, H., Y., & al., et. (2022). Convolution neural network with batch normalization and inception-residual modules for Android malware classification. Scientific Reports, 12. https://doi.org/https://doi.org/10.1038/s41598-022-18402-6

Ma, J., Chen, H., Zhang, P., Jia, F., Wang, & X. (2023). Review of image augmentation used in deep learning-based material microscopic image segmentation. Applied Sciences, 13(11). https://doi.org/https://doi.org/10.3390/app13116478

Madusanka, N., Jayalath, P., Fernando, D., Yasakethu, L., Lee, & B.-I. (2023). Impact of H&E stain normalization on deep learning models in cancer image classification: Performance, complexity, and trade-offs. Cancers, 15(16). https://doi.org/https://doi.org/10.3390/cancers15164144

Maharana, K., Behera, S., H., Panigrahi, & K., B. (2022). Data pre-processing and data augmentation techniques. Heliyon, 8(6). https://doi.org/https://doi.org/10.1016/j.heliyon.2022.e09406

Novac, O.-C., & al., et. (2022). Analysis of the Application Efficiency of TensorFlow and PyTorch in Convolutional Neural Network. Sensors, 22(22). https://doi.org/https://doi.org/10.3390/s22228872

Nowozin, S., Smith, T., Brown, & G. (2022). Challenges in in-the-wild facial expression recognition: dataset bias, annotation noise, and domain adaptation issues. Journal of Visual Communication and Image Representation, 89. https://doi.org/https://doi.org/10.1016/j.jvcir.2022.103677

Osman, I., A. F., & al., et. (2022). Deep learning–based convolutional neural network for automatic detection of radiation-induced lung damage. Journal of Applied Clinical Medical Physics, 23(10). https://doi.org/https://doi.org/10.1002/acm2.13530

Pham, T.-D., Duong, M.-T., Ho, Q.-T., Lee, S., Hong, & M.-C. (2023). CNN-Based Facial Expression Recognition with Simultaneous Consideration of Inter-Class and Intra-Class Variations. Sensors, 23(24). https://doi.org/https://doi.org/10.3390/s23249658

Pires, M., I., Hussain, F., Garcia, M., N., Lameski, P., Zdravevski, & E. (2020). Homogeneous data normalization and deep learning: A case study in human activity classification. Future Internet, 12(11). https://doi.org/https://doi.org/10.3390/fi12110194

Qi, H., Zhou, J., Wang, & H. (2022). A note on factor normalization for deep neural network models. Scientific Reports, 12. https://doi.org/https://doi.org/10.1038/s41598-022-09910-6

Rana, P., Balasubramanian, S., Muthusamy, R., Suganthan, & N., P. (2022). Data augmentation with improved regularisation and sampling for imbalanced blood cell image classification. Scientific Reports, 12. https://doi.org/https://doi.org/10.1038/s41598-022-22882-x

Sajjad, M., Ullah, M., F. U., Ullah, M., Christodoulou, G., Cheikh, A., F., Hijji, M., Muhammad, K., Rodrigues, & C., J. J. P. (2023). A comprehensive survey on deep facial expression recognition: Challenges, applications, and future guidelines. Alexandria Engineering Journal, 68. https://doi.org/https://doi.org/10.1016/j.aej.2023.01.017

Salehi, W., A., Khan, S., Gupta, G., Alabduallah, I., B., Almjally, A., Alsolai, H., Siddiqui, T., Mellit, & A. (2023). A study of CNN and transfer learning in medical imaging: Advantages, challenges, future scope. Sustainability, 15(7). https://doi.org/https://doi.org/10.3390/su15075930

Shahrabadi, S., Adão, T., Peres, E., Morais, R., Magalhães, G., L., Alves, & V. (2024). Automatic Optimization of Deep Learning Training through Feature-Aware-Based Dataset Splitting. Algorithms, 17(3). https://doi.org/https://doi.org/10.3390/a17030106

Swiderska-Chadaj, Z., Bel, de, T., Blanchet, L., Baidoshvili, A., Vossen, D., derLaak, van, J., Litjens, & G. (2020). Impact of rescanning and normalization on convolutional neural network performance in multi-center, whole-slide classification of prostate cancer. Scientific Reports, 10. https://doi.org/https://doi.org/10.1038/s41598-020-71420-0

Ullah, S., Ou, J., Xie, Y., Tian, & W. (2024). Facial expression recognition (FER) survey: A vision, architectural elements, and future directions. PeerJ Computer Science, 10. https://doi.org/https://doi.org/10.7717/peerj-cs.13456

Varoquaux, G., Cheplygina, V., Karrer, & B. (2022). Machine learning for medical imaging: Methodological failures and recommendations. NPJ Digital Medicine, 5. https://doi.org/https://doi.org/10.1038/s41746-022-00592-y

Yalçin, & N. (2024). Introducing a novel dataset for facial emotion recognition and benchmarking. Heliyon, 10. https://doi.org/https://doi.org/10.1016/j.heliyon.2024.e14944

Yu, & J. (2023). Normalization effects on deep neural networks. Fractional Order Dynamical Systems, 8(4). https://doi.org/https://doi.org/10.3934/fods.2023004

Zhao, X., & al., et. (2024). A review of convolutional neural networks in computer vision. Artificial Intelligence Review, 57. https://doi.org/https://doi.org/10.1007/s10462-024-10721-6