Claim Missing Document
Check
Articles

Found 12 Documents
Search

A Grid-search Method Approach for Hyperparameter Evaluation and Optimization on Teachable Machine Accuracy: A Case Study of Sample Size Variation Edwin Ariesto Umbu Malahina; Gregorius Rinduh Iriane; Yohanes Suban Belutowe; Petrus Katemba; Jimi Asmara
Journal of Applied Data Sciences Vol 5, No 3: SEPTEMBER 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i3.290

Abstract

This study aims to evaluate the effectiveness of the grid-search method in hyperparameter optimization on Teachable Machine (TM) using a varying number of image samples. The hyperparameters studied include epoch (e), batch size (b), and learning rate (l). A structured grid-search method approach will be applied to test 216 hyperparameter combinations across 6 categories of sample size per class, namely 10, 25, 50, 100, 250, and 500. The results showed that the optimal combination findings were obtained based on variations in the number of samples as follows: 10 samples using e:100, b:256, l:0.001 get an accuracy range of ≥ 90%; for 25 samples using e:500, b:16, l:0.001 get an accuracy range ≥ 97%; for 50 samples using e:100, b:512, l:0.001 get an accuracy range ≥ 88%; for 100 samples using e:500, b:32, l:0.001 get an accuracy range ≥ 88%; for 250 samples using e:50, b:16, l:0.001 get an accuracy range ≥ 92%, and finally 500 samples using e:500, b:256, l:0.001 get an accuracy range ≥ 96% and on average are able to achieve 100% accuracy from the detection test results of the best value performed for each sample variation of the image object. This research provides significant contributions or benefits in finding the optimal hyperparameter configuration, minimizing overfitting, and shortening the search time for TM accuracy in image classification, particularly in human face recognition. The findings support the development of more efficient and accurate TMs and provide practical guidance for finding better hyperparameter optimization using the grid-search method approach. The results of this study have implications for improving the effectiveness and accuracy of TM models and their development in mobile web applications
Digitalisasi Layanan Perlindungan Korban Kekerasan Seksual dan KDRT: Pelatihan dan Implementasi Aplikasi Web bagi Masyarakat Gregorius Rinduh Iriane; Petrus Katemba; Egidius Dewa
Jurnal Pengabdian Masyarakat Vol. 5 No. 1 (2026): April: Jurnal Pengabdian Masyarakat
Publisher : Universitas 45 Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30640/abdimas45.v5i1.5375

Abstract

Sexual violence and domestic violence remain serious community problems, including in Ende Regency, East Nusa Tenggara. Many cases remain unreported because victims may feel afraid, ashamed, or unaware of available reporting channels. This community service program developed a web-based reporting application to enable victims and witnesses to report violence safely, quickly, and confidentially. The program was implemented in collaboration with the Pedulih Kasih Association, an organization concerned with the protection of women and children in Ende Regency. The application was designed not only as a reporting tool but also as an educational medium to increase public awareness of violence prevention and victim protection. The implementation consisted of five stages: needs identification and field surveys, application design and development, training and mentoring, application testing and evaluation, and implementation and monitoring. The activities were conducted collaboratively with partners. The outputs included a web-based violence reporting application, a user training module, digital educational materials, scientific publications and documentation, and improved partner capacity in handling violence reports. The implementation achieved approximately 80% of the planned targets, including completion of the application prototype, dissemination to partners, and increased community understanding of the importance of reporting and victim protection. The program demonstrates potential for broader adoption as a digital and integrated mechanism for addressing gender-based violence.