Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI)
Raj, Bill
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Engineering

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

Found 2 Documents
Search

 1 
Pendekatan Explainable Deep Learning pada Klasifikasi Citra Sampah Menggunakan MobileNetV2 dan Teknik Grad-CAM serta SHAP Al Adib, Muhammad; Siregar, Andri Armaginda; Raj, Bill; Hasibuan, Rahmat Humala Putra; Nasution, Jalaluddin; Parapat, Andreas Jorghy; Rosnelly, Rika
Jurnal Komputer Teknologi Informasi Sistem Informasi (JUKTISI) Vol. 4 No. 3 (2026): Februari 2026
Publisher : LKP KARYA PRIMA KURSUS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62712/juktisi.v4i3.739

Abstract

The increasing volume of waste resulting from urbanization and population growth poses significant challenges to waste management systems, particularly in the sorting stage. Deep learning approaches, especially Convolutional Neural Networks (CNNs), have been widely employed for waste image classification due to their ability to automatically extract complex visual features. However, a major limitation of these approaches lies in their limited interpretability, which may hinder user trust and real-world adoption. This study proposes an Explainable Deep Learning Framework for organic and inorganic waste image classification by integrating the MobileNetV2 architecture with Explainable Artificial Intelligence (XAI) methods, namely Gradient-weighted Class Activation Mapping (Grad-CAM) and SHapley Additive exPlanations (SHAP). MobileNetV2 is utilized as a feature extractor due to its computational efficiency and suitability for deployment on resource-constrained devices. The dataset used in this study consists of a combination of a public benchmark dataset and field-acquired waste images, processed using a transfer learning approach. Model performance is evaluated using accuracy, precision, recall, and f1-score metrics. Experimental results demonstrate that the proposed model achieves a validation accuracy of 90.25% with balanced performance across both classes. Furthermore, interpretability analysis using Grad-CAM and SHAP reveals that the model focuses on semantically relevant visual features and provides explainable feature contributions. These findings confirm that integrating lightweight CNN architectures with XAI techniques can produce waste classification systems that are accurate, transparent, and accountable.
Optimasi Strategi Promosi Sekolah SMK melalui Segmentasi Data Siswa Baru dengan Clustering Metode K-Means menggunakan Differential Evolution (DE) Hutabarat, Pebruarianto; Setiawan, Adil; Raj, Bill; Prasetyo, M; Irnanda, M. Agung; Gea, Empiter; Johan; Parapat, Andreas
Jurnal Komputer Teknologi Informasi Sistem Informasi (JUKTISI) Vol. 4 No. 3 (2026): Februari 2026
Publisher : LKP KARYA PRIMA KURSUS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62712/juktisi.v4i3.779

Abstract

SMK XYZ faces challenges in developing effective and efficient promotional strategies to attract prospective new students. Previously, promotional approaches have been general and failed to address the specific needs of different prospective student segments. This research aims to optimize school promotional strategies by analyzing patterns in new student characteristics through data segmentation techniques. The proposed method is K-Means Clustering optimized with the Differential Evolution (DE) algorithm. DE optimization addresses K-Means' sensitivity to initial cluster center initialization, aiming for more stable and optimal segmentation. The data used includes demographic attributes, major interests, registration pathways, and prior school origins of new students from the 2023/2024 cohort. Research results show that the DE-K-Means combination produces more compact clusters (lower within-cluster sum of squares values) compared to standard K-Means. Based on the resulting cluster analysis, three distinct promotional strategies are formulated for each prospective student segment: digital-intensive approaches, partnerships with feeder schools, and highlighting specific major advantages. Implementing these strategies is expected to significantly increase the quality and quantity of new student admissions.
Co-Authors Al Adib, Muhammad Gea, Empiter Hasibuan, Rahmat Humala Putra Hutabarat, Pebruarianto Irnanda, M. Agung Johan Johan Nasution, Jalaluddin Parapat, Andreas Parapat, Andreas Jorghy Prasetyo, M Rika Rosnelly, Rika Setiawan, Adil Siregar, Andri Armaginda