Sistem Deteksi Ekspresi Toileting Pada Anak Penyandang Multidisabilitas Berdasarkan Ekstraksi Fitur Menggunakan Support Vector Machine

Siregar, Salsabiela Khairunnisa (2024) Sistem Deteksi Ekspresi Toileting Pada Anak Penyandang Multidisabilitas Berdasarkan Ekstraksi Fitur Menggunakan Support Vector Machine. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5023201020-Undergraduates_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (3MB) | Request a copy

Abstract

Anak-anak dengan disabilitas sering menghadapi kesulitan dalam mengekspresikan keinginan mereka, termasuk saat ingin menggunakan fasilitas toilet. Hambatan ini dapat menyebabkan terjadinya masalah kesehatan ataupun masalah lainnya pada anak, seperti perilaku buang air tidak pada tempatnya. Melalui toilet training, anak akan belajar bagaimana mereka mengendalikan keinginan untuk buang air. Keberhasilan toilet training tergantung pada cara pengajaran bertahap sesuai dengan kemampuan anak. Oleh karena itu, penelitian ini bertujuan untuk menemukan parameter toileting berdasarkan ekspresi wajah anak disabilitas dengan menggunakan kamera. Kamera diposisikan di depan subjek selama kegiatan sekolah berlangsung untuk merekam perubahan ekspresi. Hasil citra akuisisi akan dipilih untuk dibuat dataset berdasarkan perubahan ekspresi yang muncul pada saat kondisi toileting. Ekstraksi fitur dilakukan dari 51 titik landmark wajah untuk mendapatkan nilai sudut, jarak, kemiringan antar titik landmark elemen wajah. Dataset TOP5 dan TOP10 dibuat menggunakan fitur-fitur dengan nilai korelasi pearson tertinggi. Proses klasifikasi menggunakan Support Vector Machine (SVM) menunjukkan bahwa model dengan dataset TOP5 mencapai akurasi tertinggi sebesar 96% dengan kombinasi parameter C=25 dan γ=0.001, menggunakan cross validation 5-folds. Model ini menunjukkan kinerja yang baik dengan nilai precision, recall, dan F1-score yang tinggi. Sistem deteksi ekspresi toileting ini memiliki beberapa kendala pada proses pengambilan data yang membutuhkan banyak pengondisian subjek. Selain itu, terdapat beberapa kesalahan klasifikasi yang perlu diatasi untuk mendapatkan hasil yang lebih baik. Untuk meningkatkan kemampuan dan generalisasi sistem dalam mendeteksi ekspresi toileting, diperlukan dilakukan penambahan jumlah dan variasi dataset dengan melibatkan subjek dari berbagai jenis disabilitas.
=========================================================================================
Children with disabilities often face challenges in expressing their needs, including when they wish to use toilet facilities. These barriers can lead to health issues or other problems, such as inappropriate toileting behaviors. Toilet training helps children learn to control their urges to urinate or defecate, and its success relies on gradual teaching methods tailored to the child`s abilities. Therefore, this study aims to identify toileting parameters based on the facial expressions of children with disabilities using a camera system. The camera is positioned in front of the subjects during school activities to capture expression changes. The acquired images are selected to create a dataset based on the expression changes observed during toileting events. Feature extraction is performed using 51 facial landmark points to obtain angles, distances, and inclinations between these points. TOP5 and TOP10 datasets are generated using features with the highest Pearson correlation values. The classification process using Support Vector Machine (SVM) demonstrated that the model with the TOP5 dataset achieved the highest accuracy of 96%, with parameter settings of C=25 and γ=0.001, utilizing 5-fold cross validation. This model exhibits robust performance with high precision, recall, and F1-score metrics. Despite this, the toileting expression detection system faces challenges in data collection, such as the extensive conditioning required for data collection and some misclassification errors that need to be addressed for improved results. To enhance the system`s capability and generalization in detecting toileting expressions, it is essential to increase the number and diversity of datasets by involving subjects with various types of disabilities.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Toileting Pada Disabilitas, Perilaku Disabilitas, Landmark Wajah, Klasifikasi Ekspresi Disabilitas, Computer Vision, dan Support Vector Machine ========================================================== Toileting for Disabilities, Disability Behavior, Facial Landmarks, Disability Expression Classification, Computer Vision, and Support Vector Machine
Subjects:	R Medicine > R Medicine (General) > R858 Deep Learning R Medicine > RJ Pediatrics T Technology > T Technology (General) > T57.5 Data Processing T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models. T Technology > T Technology (General) > T59.7 Human-machine systems.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Biomedical Engineering > 11410-(S1) Undergraduate Thesis
Depositing User:	Salsabiela Khairunnisa Siregar
Date Deposited:	12 Aug 2024 04:58
Last Modified:	12 Aug 2024 04:58
URI:	http://repository.its.ac.id/id/eprint/113488

Actions (login required)

View Item