Klasifikasi Coronary Heart Disease (CHD) Berbasis Optimasi DNN dan Inisialisasi Kaiming He
DOI:
https://doi.org/10.30865/mib.v5i1.2559Keywords:
CHD, Kaiming He, DNN, Accuracy, Sensitivity, SpecificityAbstract
CHD is chest pain or discomfort that occurs if the area of the heart muscle does not get enough oxygen-rich blood. CHD is also known as coronary artery disease. CHD is increasing every year with a significant number of deaths. A learning algorithm is proposed to get better performance in accuracy, sensitivity, and specificity in CHD interpretation. Accuracy can be improved by adding a Kaiming He (2015) weight initialization optimization technique to the DNN structure. Therefore we propose that DNN is optimized with a Kaiming He weight initialization technique so that it can overcome weaknesses in the data variant. This is evidenced by the results of the accuracy performance of 98.73%. Initialization of kaiming he weights is proven to improve accuracy and overcome the problem of large data variants between classesReferences
A. Darmawahyuni, S. Nurmaini, and F. Firdaus, “Coronary Heart Disease Interpretation Based on Deep Neural Network,†Comput. Eng. Appl. J., vol. 8, no. 1, pp. 1–12, 2019.
G. S. M. Tech, “Decision Support in Heart Disease Prediction System using Naive Bayes,†vol. 2, no. 2, pp. 170–176, 2011.
P. Gayathri and N. Jaisankar, “Comprehensive study of heart disease diagnosis using data mining and soft computing techniques,†Int. J. Eng. Technol., vol. 5, no. 3, pp. 2947–2958, 2013.
Shinde, “Heart Disease Prediction System using Multilayered Feed Forward Neural Network and Back Propagation,†pp. 1–2, 2017.
D. R. Chowdhury, M. Chatterjee, and R. K. Samanta, “An Artificial Neural Network Model for Neonatal Disease Diagnosis,†Int. J. Artif. Intell. Expert Syst., vol. 2, no. 3, pp. 96–106, 2011.
J. Nahar, T. Imam, K. S. Tickle, and Y. P. P. Chen, “Computational intelligence for heart disease diagnosis: A medical knowledge driven approach,†Expert Syst. Appl., vol. 40, no. 1, pp. 96–104, 2013.
E. O. Olaniyi, O. K. Oyedotun, A. Helwan, and K. Adnan, “Neural network diagnosis of heart disease,†2015 Int. Conf. Adv. Biomed. Eng. ICABME 2015, pp. 21–24, 2015.
K. H. Miao and J. H. Miao, “Coronary heart disease diagnosis using deep neural networks,†Int. J. Adv. Comput. Sci. Appl., vol. 9, no. 10, pp. 1–8, 2018.
K. He, X. Zhang, S. Ren, and J. Sun, “Delving deep into rectifiers: Surpassing human-level performance on imagenet classification,†Proc. IEEE Int. Conf. Comput. Vis., vol. 2015 Inter, pp. 1026–1034, 2015.
N. A. Sundar, P. P. Latha, and M. R. Chandra, “Performance Analysis of Classification Data Mining Techniques Over Heart Disease Data Base,†Int. J. Eng. Sci. Adv. Technol., vol. 2, no. 3, pp. 470–478, 2012.
X. Deng, Q. Liu, Y. Deng, and S. Mahadevan, “An improved method to construct basic probability assignment based on the confusion matrix for classification problem,†Inf. Sci. (Ny)., vol. 340–341, pp. 250–261, 2016.
G. Dahl, T. Sainath, and G. Hinton, “Improving Deep Neural Networks for LVCSR Using Recitified Linear Units and Dropout, Department of Computer Science , University of Toronto,†Acoust. Speech Signal Process. (ICASSP), 2013 IEEE Int. Conf. Acoust. Speech Signal Process. - Proc., pp. 8609–8613, 2013.
S. K. Kumar, “On weight initialization in deep neural networks,†pp. 1–9, 2017.
Y. Kwon, Y. Kwon, D. Chung, and M. Lim, “Initialization Weight Malware,†no. 4, pp. 57–62, 2019.
J. jiao Xie et al., “The Th17/Treg functional imbalance during atherogenesis in ApoE-/- mice,†Cytokine, vol. 49, no. 2, pp. 185–193, 2010.
Downloads
Published
Issue
Section
License
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).
