BACKPROPAGATION NEURAL NETWORK WITH ADAPTIVE LEARNING RATE FOR CLASSIFICATION OF IMBALANCED DATA
Keywords:
Classification, Neural Network, Adaptive Learning Rate, Backpropagation Learning Algorithm, Imbalanced DataAbstract
Currently there are several research studies solving classification with Backpropagation Neural Network (BPNN) due to its high capability to learn complex data. However, the drawback of this method is that if the learning data sets contain imbalanced data, the BPNN will learn more from the class that has more data than the class that has few data; as a result, it will always predict the class that has more data. Thus, the overall classification accuracy is low. This research aims to solve the imbalanced data problem by presenting the Backpropagation Neural Network with Adaptive Learning Rate (BPNN-ALR) which is improved over the traditional BPNN. To test the efficiency of the proposed method, the researchers used two imbalanced medical data sets. The results showed that the accuracy of the traditional BPNN on Breast Tissue data set is 47.62%, while that of BPNN-ALR is 77.14%. On Vertebral Column data set, the accuracy of the traditional BPNN is 48.39%, while that of BPNN-ALR is 60.97%. In summary, the preliminary test results showed that the proposed algorithm is more accurate than the traditional BPNN.
References
นพมาศ อัครจันทโชติ, และดิเรก พนิตสุภากมล. (2562). การเปรียบเทียบวิธีการแก้ปัญหาข้อมูลไม่สมดุลสำหรับการจำแนกกลุ่มรายได้ของผู้ประกอบการร้านยาประเภท ข.ย. 1. In The 9th STOU National Research Conference. สืบค้นจาก http://sci-database.hcu.ac.th/science/file/rsID292_F1_20200122213859.pdf.
วิชญ์วิสิฐ เกษรสิทธิ์, จิราวัลย์ จิตรถเวช, และวิชิต หล่อจีระชุณห์กล. (2563). การลดจำนวนกลุ่มในการจำแนกแบบหลายกลุ่มเป็นสองกลุ่มสำหรับการจำแนกการกลับมารักษาซ้ำในโรงพยาบาลของผู้ป่วยโรคเบาหวาน. Thai Science and Technology Journal, 28(1), 41-51.
อาริกา ธรรมโน, มุทิตา หวังคิด, และอาริต ธรรมโน. (2563). การพยากรณ์โรคมะเร็งเต้านมด้วยอัลกอริทึมการจำแนกประเภทแบบเคมีร่วมกับค่าถ่วงน้ำหนักแบบปรับตัวเอง. Journal of Information Science and Technology, 10(2), 1-9.
Berthonnaud, E., Dimnet, J., Roussouly, P., & Labelle, H. (2005). Analysis of the sagittal balance of the spine and pelvis using shape and orientation parameters. Journal of Spinal Disorders & Techniques, 18(1), 40-47.
Blackard, J. A., & Dean, D. J. (1999). Comparative accuracies of artificial neural networks and discriminant analysis in predicting forest cover types from cartographic variables. Computers and Electronics in Agriculture, 24, 131-151.
Dreiseitl, S., & Ohno-Machado, L. (2002). Logistic regression and artificial neural network classification models: a methodology review. Journal of Biomedical Informatics, 35, 352–359.
Dua, D., & Graff, C. (2019). UCI machine learning repository. Retrieved from https://archive.ics.uci.edu/ml/index.php.
Feng, J., Xu, H., Mannor, S., & Yan, S. (2014). Robust logistic regression and classification. Proceedings of the 27th International Conference on Neural Information Processing Systems (NIPS 2014), Montreal, Quebec, Canada.
Geisser, S. (1975). The predictive sample reuse method with applications. Journal of the American Statistical Association, 70(350), 320-328.
Jia, W., Deng, Y., Xin, C., Liu, X., & Pedrycz, W. (2019). A classification algorithm with linear discriminant analysis and axiomatic fuzzy sets. Mathematical Foundations of Computing, 2(1), 73-81.
Jossinet, J. (1996). Variability of impedivity in normal and pathological breast tissue. Medical & Biological Engineering & Computing, 34, 346-350.
Rocha Neto, A. R., & Barreto, G. A. (2009). On the application of ensembles of classifiers to the diagnosis of pathologies of the vertebral column: A comparative analysis. IEEE Latin America Transactions, 7(4), 487-496.
Rocha Neto, A. R., Sousa, R., Barreto, G. A., & Cardoso, J. S. (2011). Diagnostic of pathology on the vertebral column with embedded reject option. In Proceedings of the 5th Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA'2011), Gran Canaria, Spain, 588-595.
Silva, J. E., Marques de Sá, J. P., & Jossinet, J. (2000). Classification of breast tissue by electrical impedance spectroscopy. Medical & Biological Engineering & Computing, 38, 26-30.
Zhang, H., Huang, L., Wu, C. Q., & Li, Z. (2020). An effective convolutional neural network based on SMOTE and gaussian mixture model for intrusion detection in imbalanced dataset. Computer Networks, 177.
Downloads
Published
How to Cite
Issue
Section
License
Content and information of the article published at Suthiparithat Journal are based on the sole opinions and responsibility of author(s) only. Neither the editorial board involve in......
