Klasifikasi Kemampuan Perawatan Diri Anak dengan Disabilitas Menggunakan SMOTE Berbasis Neural Network

Sari Susanti

Sari


Abstrak

Penyandang disabilitas merupakan kelompok minoritas terbesar didunia, dengan anak-anak menempati  sepertiga dari jumlah keseluruhan penyandang disabilitas. Pada penerapannya proses diagnosis dan klasifikasi dimensi disabilitas membutuhkan ahli terapis okupasi. Jumlah terapis okupasi yang terbatas mengakibatkan penanganan penyandang disabilitas menjadi tertunda. Teknik data mining digunakan untuk membantu proses diagnosis yang bertujuan untuk menghindari kesalahan dalam diagnosis. Penelitian ini menggunakan dataset Scadi yang merepresentasikan masalah kemampuan perawatan diri anak dengan disabilitas. Dataset Scadi merupakan dataset baru yang belum banyak diteliti. Pada dataset Scadi terdapat permasalahan yaitu, ketidakseimbangan kelas (imbalanced class). Masalah tersebut menyebabkan rendahnya nilai akurasi klasifikasi. Algoritma yang diusulkan yaitu neural network untuk klasifikasi kemampuan perawatan diri anak dengan disabilitas, Selain neural network digunakan algoritma Smote untuk mengatasi masalah ketidakseimbangan kelas (imbalanced class) pada level data. Hasil penelitian menunjukan bahwa metode yang diusulkan telah meningkatan kinerja algoritma klasifikasi neural network, dengan meningkatkan nilai akurasi secara signifikan sebesar 90.4762 % dibandingkan hasil yang dilaporkan pada penelitian sebelumnya yaitu 83,1%.

 

Kata kunci: Perawatan Diri, Disabilitas, ICF-CY, Neural network, Smote, Ketidakseimbangan Kelas.

Abstract

Persons with disabilities are the majority group in the world, with children determined one third of the total number of persons with disabilities. In its application, the process of diagnosis and classification of occupational therapist needs. The number of occupational therapists who are limited to handling persons with disabilities is delayed. Data mining techniques are used to help the diagnosis process that helps to avoid errors in diagnosis. This study uses the Scadi dataset which presents the problem of self-care ability of children with disabilities. Dataset Scadi is a new dataset that has not yet been collected. The Scadi dataset is related, that is, class imbalances (unbalanced classes). This problem causes a low value. The proposed algorithm is a neural network for the classification of self-care abilities of children with disabilities. In addition to the neural network, the Smote algorithm is used to overcome the problem of class imbalances (unbalanced levels) at the data level. The results showed that the proposed method had improved the results of neural network classification analysis, by increasing the assessment value by 90.4762% compared to the results obtained in the previous study, namely 83.1%.

 

Keywords: Self-care, Disability, ICF-CY, Neural network, Smote, imbalanced class. 

 


Teks Lengkap:

PDF

Referensi


Barro, R. A., Sulvianti, I. D., & Afendi, F. M. (2013). Penerapan Synthetic Minority Oversampling Technique (Smote) Terhadap Data Tidak Seimbang Pada Pembuatan Model Komposisi Jamu. Xplore, 1(1). Retrieved from journal.ipb.ac.id/index.php/xplore/article/download/12424/9491

Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16(2), 321–357. https://doi.org/10.1613/jair.953

Cost, S., & Salzberg, S. (2013). A Weighted Nearest Neighbor Algorithm for Learning with Symbolic Features. Journal of Chemical Information and Modeling, 53(9), 1689–1699. https://doi.org/10.1017/CBO9781107415324.004

Deepa, T., & Punithavalli, M. (2013). An Innovative Optimization Algorithm for Feature Selection – A Comparative Study. International Journal of Computer Science and Information Technology & Security (IJCSITS), 3(1), 20–24.

Han, J., & Kamber, M. (2006). Data Mining Concepts and Techniques Second Edition. San Francisco: Diane Cerra.

Kemenkes. (2014). Penyandang Disabilitas Pada Anak. Pusat Data dan Informasi Kementrian Kesehatan RI.

Khoshgoftaar, T. M., Gao, K., Napolitano, A., & Wald, R. (2014). A comparative study of iterative and non-iterative feature selection techniques for software defect prediction. Information Systems Frontiers, 16(5), 801–822. https://doi.org/10.1007/s10796-013-9430-0

Korada, Kumar, & Deekshitulu. (2012). Implementatioan Of Naive Bayesian Classifier and Ada-Boost Algoritm Using Maiz Expert System. International Journal Of Information Sciences And Techniques (IJIST) Vol.2, No.3, 63-75, 2(3), 63–75.

Kusrini, & Luthfi, E. T. (2009). Algoritma Data Mining. Yogyakarta: Penerbit Andi.

Kusumadewi, S. (2004). Membangun Jaringan Syaraf Tiruan Menggunakan Matlab & Excel Link. Yogyakarta: Graha Ilmu.

Larose, D. T. (2006). Discovering Knowledge in Data: An Introduction to Data Mining. New Jersey: John Wiley & Sons, Inc.

Myatt, G. J. (2007). Making Sense of Data: A Practical Guide to Exploratory Data Analysis and Data Mining. New Jersey: John Wiley & Sons, Inc.

Praveena, S., & Singh, S. P. (2014). Hybrid Clustering Algorithm and Feed-Forward Neural Network for Satellite Image Classification. In 2015 International Conference on Industrial Instrumentation and Control (ICIC) (pp. 1378–1383). Pune: IEEE.

Putri, S. A., & Wahono, R. S. (2015). Integrasi SMOTE dan Information Gain pada Naive Bayes untuk Prediksi Cacat Software. Journal of Software Engineering, 2(1).

Radhimeenakshi, S. (2016). Classification and prediction of heart disease risk using data mining techniques of Support Vector Machine and Artificial Neural Network. In 2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom) (pp. 3107–3111). New Delhi.

Riquelme, J. C., Ruiz, R., Rodriguez, D., & Moreno, J. (2008). Finding defective modules from highly unbalanced datasets. In Actas de los Talleres de las Jornadas de Ingeniería del Software y Bases de Datos (Vol. 2, pp. 67–74). gijon, espana: Sistedes.

Tiwari, D. (2014). Handling Class Imbalance Problem Using Feature Selection. International Journal of Advanced Research in Computer Science & Technology, 516–520.

Unal, Y., & Kocer, E. (2013). Diagnosis of Pathology on the Vertebral Column with Backpropagation and Naive Bayes Classifier. Technological Advances in Electrical, Electronics and Computer Engineering, 278–281.

WHO. (2007). ICF-CY (International Classification of Functioning, Disability and Health for Children and Youth). Switzerland: World Health Organization.

WHO. (2018). Disabilities. Retrieved May 4, 2018, from http://www.who.int/news-room/facts-in-pictures/detail/disabilities

Yeh, Y., Hou, T., & Chang, W. (2012). Expert Systems with Applications An intelligent model for the classification of children ’ s occupational therapy problems. Expert Systems With Applications, 39(5), 5233–5242. https://doi.org/10.1016/j.eswa.2011.11.016

Zarchi, M. S., Bushehri, F., & Dehghanizadeh, M. (2018). SCADI: International Journal of Medical Informatics, 114(2), 1–28. https://doi.org/10.1016/j.ijmedinf.2018.03.003

Zhang, D., Liu, W., Gong, X., & Jin, H. (2011). A Novel Improved SMOTE Resampling Algorithm Based on Fractal. Journal of Computational Information Systems, 6, 2204–2211.

Zhang, Z.-Z., Chen, Q., Ke, S.-F., Wu, Y.-J., Qi, F., & Zhang, Y.-P. (2008). Ranking Potential Customers Based on Group-Ensemble. International Journal of Data Warehousing and Mining, 4(2), 79–89. https://doi.org/10.4018/jdwm.2008040109




DOI: https://doi.org/10.31311/ji.v6i2.5798

##submission.license.cc.by4.footer##

 dipublikasikan oleh LPPM UBSI
Jl. Kamal Raya No. 18 Cengkareng, Jakarta Barat