Article Per Year (5 Year)
p-Index From 2020 - 2025
0.408
P-Index
This Author published in this journals
All Journal Prosiding Seminar Nasional Teknoka
Widya Kurniawan
Unknown Affiliation
Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Analisis Klasifikasi Tingkat Kesehatan Mental pada Mahasiswi Akhir dalam Menempuh Tugas Akhir Menggunakan Algoritma Support Vector Machine Studi Kasus: Universitas Darussalam Gontor Widya Kurniawan; Aziz Musthafa; Anisa Kirani
Prosiding Seminar Nasional Teknoka Vol 9 (2024): Proceeding of TEKNOKA National Seminar - 9
Publisher : Fakultas Teknik, Universitas Muhammadiyah Prof. Dr. Hamka, Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22236/teknoka.v9i1.17524

Abstract

Overall health depends on mental health or psychological well-being. Mental and physical well being are equally vital. One in two young people under the age of 25 will experience mental health issues at some point, and 75% of mental illnesses begin before the age of 25. Female university students are among those at the highest risk for mental health issues. Typically, students in their early and final semesters experience a high level of academic anxiety. One of the main factors causing psychological distress in students is the final project or thesis. This study aims to classify mental health levels, namely stress and anxiety, by training a classification model that makes use of the Support Vector Machine algorithm. The dataset used in this study is derived from a questionnaire distributed to final-year female students working on their thesis. The dataset consists of 249 records and is divided into two datasets for stress and anxiety classification. The results of this study show the highest accuracy in the stress classification dataset using the RBF and polynomial kernels, reaching 68% with the RBF kernel at gamma 1 and C 100. Meanwhile, the highest accuracy in the anxiety classification dataset reached 50% achieved with the polynomial kernel at degree 3 and C 100. The application of the best model indicates that the most influential features in the Stress and Anxiety datasets are Literature Review, Support System, and Analysis Method.  The obtained accuracy can be used as a standard for upcoming studies using more complex data.
Analisis Clustering Kasus Bunuh Diri di Jawa Tengah dengan Menerapkan Algoritma K-Means Widya Kurniawan; Faisal Reza Pradhana; Khusna Amalia Zen
Prosiding Seminar Nasional Teknoka Vol 9 (2024): Proceeding of TEKNOKA National Seminar - 9
Publisher : Fakultas Teknik, Universitas Muhammadiyah Prof. Dr. Hamka, Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22236/teknoka.v9i1.17559

Abstract

Suicide is a deliberate act intended to end one’s life. In Indonesia, this phenomenon remains prevalent and is influenced by various factors, such as psychological conditions, economic pressures, social issues, and environmental factors. This study aims to identify patterns of suicide cases using Clustering techniques, with data sourced from the Semarang and Boyolali Police Departments. The three main variables analyzed are age range, suicide method, and location of the incident. The CRISP-DM approach is applied for data processing, and the K-Means algorithm is used to group relevant data based on these variables. A Silhouette score of 84% indicates a good separation between clusters. Visualization with Principal Component Analysis (PCA) is used to map the clusters more comprehensively. The most vulnerable group to commit suicide is individuals in the productive age range, who tend to use hanging as the method and do so in private homes. This study is expected further insights into the suicide phenomenon in Indonesia.
Co-Authors Anisa Kirani Aziz Musthafa Faisal Reza Pradhana Khusna Amalia Zen