Article Per Year (5 Year)
p-Index From 2020 - 2025
0.92
P-Index
This Author published in this journals
All Journal Jurnal Pengabdian Masyarakat Nusantara International Journal of Management Science and Information Technology (IJMSIT)
Widowati, Fika Ulfa
Unknown Affiliation
Humanities Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Social Sciences

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Application of C4.5 algorithm with PSO Feature Selection and Bagging Technique on Breast Cancer Classification Widowati, Fika Ulfa
International Journal of Management Science and Information Technology Vol. 4 No. 2 (2024): July - December 2024
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijmsit.v4i2.3061

Abstract

The second greatest cause of death for women worldwide is breast cancer. When abnormal cells in the body proliferate out of control, cancer is the result. The diagnosis of breast cancer was established using anthropometric data obtained from standard blood tests. From the UCI Machine Learning Repository, the Breast Cancer Coimbra Data Set was obtained and put to use. One popular classification decision tree method is the C4.5 approach. By selecting the appropriate features and applying the appropriate strategy to address class imbalance throughout the classification process, the performance of the C4.5 algorithm may be enhanced. To determine the accuracy of the classification, tests are conducted using a confusion matrix. Accuracy in this study is anticipated to increase with the application of the C4.5 Algorithm, the Bagging approach to address class imbalance, and the PSO feature selection method. The C4.5 Algorithm, PSO, Bagging Technique produce the best accuracy results, with an average of 86.36 percent. The C4.5 classification method has the second highest accuracy, with a PSO accuracy of 79.39 percent. Utilizing the Bagging Technique in conjunction with the C4.5 Algorithm, the accuracy of 75.0% is the third highest. Furthermore, it has a 65.71 percent accuracy with the C4.5 categorization. As a result, the increase in accuracy from before adding PSO and Bagging Technique was 20.65%, indicating that the inclusion of PSO and Bagging Technique had a substantial impact on the calculation process.
Cybersecurity Mesh and Edge Computing on the Analytics Platform of the Indonesian Telecommunications Industry Widowati, Fika Ulfa
International Journal of Management Science and Information Technology Vol. 5 No. 1 (2025): January - June 2025
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijmsit.v5i1.3845

Abstract

This research analyzes the implementation of cybersecurity mesh and edge computing on analytics platforms in the Indonesian telecommunications industry. The geographical complexity and disparity of Indonesia's telecommunications infrastructure create unique challenges in securing and optimizing analytics platforms using a mixed-method approach with a sequential explanatory design. The research involves 15 national telecommunications operators representing 85% of the market share. Data were collected through structured surveys, in-depth interviews, and field observations during the period from January to June 2024. The research results show that the integration of cybersecurity mesh with edge computing increases operational efficiency by 45% and reduces latency by up to 75% compared to conventional architecture. The developed integration model successfully accommodates Indonesia's geographical characteristics and complies with national regulations. The implementation of a cybersecurity mesh increased the effectiveness of cyber threat detection by 89%, while edge computing optimization resulted in bandwidth savings of up to 60%. This research contributes to the development of a national blueprint for optimizing telecommunications analytics platforms that are adaptive to Indonesia's conditions. These findings provide practical implications for telecommunications operators in optimizing digital infrastructure. This can enrich the literature by considering integration models from geographical and regulatory aspects.
Application of C4.5 algorithm with PSO Feature Selection and Bagging Technique on Breast Cancer Classification Widowati, Fika Ulfa
International Journal of Management Science and Information Technology Vol. 4 No. 2 (2024): July - December 2024
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijmsit.v4i2.3061

Abstract

The second greatest cause of death for women worldwide is breast cancer. When abnormal cells in the body proliferate out of control, cancer is the result. The diagnosis of breast cancer was established using anthropometric data obtained from standard blood tests. From the UCI Machine Learning Repository, the Breast Cancer Coimbra Data Set was obtained and put to use. One popular classification decision tree method is the C4.5 approach. By selecting the appropriate features and applying the appropriate strategy to address class imbalance throughout the classification process, the performance of the C4.5 algorithm may be enhanced. To determine the accuracy of the classification, tests are conducted using a confusion matrix. Accuracy in this study is anticipated to increase with the application of the C4.5 Algorithm, the Bagging approach to address class imbalance, and the PSO feature selection method. The C4.5 Algorithm, PSO, Bagging Technique produce the best accuracy results, with an average of 86.36 percent. The C4.5 classification method has the second highest accuracy, with a PSO accuracy of 79.39 percent. Utilizing the Bagging Technique in conjunction with the C4.5 Algorithm, the accuracy of 75.0% is the third highest. Furthermore, it has a 65.71 percent accuracy with the C4.5 categorization. As a result, the increase in accuracy from before adding PSO and Bagging Technique was 20.65%, indicating that the inclusion of PSO and Bagging Technique had a substantial impact on the calculation process.
Penguatan Daya Saing UMKM Agroindustri Singkong Melalui Implementasi Inovasi Kemasan Ramah Lingkungan dan Pemberdayaan Masyarakat Widowati, Fika Ulfa
Jurnal Pengabdian Masyarakat Nusantara (JPMN) Vol. 5 No. 2 (2025): Agustus 2025 - Januari 2026
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/jpmn.v5i2.5370

Abstract

Micro, Small, and Medium Enterprises (MSMEs) in the cassava agro-industry have strategic potential to support the rural economy, but face challenges in product competitiveness and environmental sustainability. This research aims to enhance the competitiveness of cassava agro-industry MSMEs thru eco-friendly packaging innovation and community empowerment. The method uses a participatory approach with the stages of socialization, training, mentoring, and evaluation. The program was implemented in Kaliwungu District, Kendal Regency, over a period of 6 months, involving 25 MSMEs. The results show an average increase in turnover of 35% and a substantial improvement in packaging quality. Environmental impacts include an 80% reduction in plastic thru cassava flour and recycled paper packaging, and a 65% decrease in packaging waste. Measurable social impacts include: increasing the capacity of 120 family members in digital business (85% able to operate e-commerce), forming 5 joint business groups, creating 15 new jobs, and improving financial literacy (78% able to prepare simple financial statements). The program creates a multiplier effect by increasing the adoption of digital technology from 20% to 85%. Evaluation shows sustainability thru a system of local partnerships and an integrated distribution network. This research contributes to the development of a green innovation-based MSME empowerment model that can be replicated in other agro-industrial regions, supporting the achievement of SDGs goals 8, 12, and 17.
Deep Learning for HIV Screening Using Laboratory and Demographic Data Widowati, Fika Ulfa
International Journal of Management Science and Information Technology Vol. 5 No. 2 (2025): July - December 2025
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijmsit.v5i2.5371

Abstract

In this work, laboratory and demographic data were integrated to create a deep learning model for HIV screening. The rising incidence of HIV in Indonesia necessitates the development of more effective and precise screening techniques for early identification. The created methodology improves the accuracy of HIV status prediction by integrating many laboratory indicators, including total blood count, viral load, CD4 count, and patient demographic information. For the years 2020–2024, 5,847 patient samples from different Indonesian hospitals made up the dataset. A Deep Neural Network (DNN) architecture with Grid Search hyperparameter optimization was employed in this investigation. According to the evaluation results, the model obtained an F1 score of 93.5%, a sensitivity of 92.8%, a specificity of 95.1%, and an accuracy of 94.2%. When compared to using only laboratory data, the model's performance increased by 3.7% when demographic data was included. This methodology can lessen laboratory burden while assisting medical staff in doing HIV screening more quickly and accurately. An external validation plan has been created with a testing strategy using a separate dataset from ten referral hospitals that were not part of the model training process in order to guarantee the model's dependability in clinical application. To boost the confidence of medical staff, a workable implementation has been created in the form of an API and web application that can be included into the hospital's current information systems and provide an explanation of the prediction results. To help healthcare facilities with different resource levels embrace this technology, technical and clinical implementation recommendations are offered. In order to assess how well the model works to increase HIV detection rates and clinical workflow efficiency, a post-implementation impact evaluation is planned. The efficiency of HIV prevention and control initiatives in Indonesia might be greatly increased by incorporating this paradigm into the healthcare system.
Co-Authors