cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Rian Ferdian
Contact Email
rian.ferdian@fti.unand.ac.id
Phone
-
Journal Mail Official
jitce@fti.unand.ac.id
Editorial Address
-
Location
Kota padang,
Sumatera barat
INDONESIA
Journal of Information Technology and Computer Engineering
Published by Universitas Andalas
ISSN : 25991663     EISSN : -     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering
Journal of Information Technology and Computer Engineering (JITCE) is a scholarly periodical. JITCE will publish research papers, technical papers, conceptual papers, and case study reports. This journal is organized by Computer System Department at Universitas Andalas, Padang, West Sumatra, Indonesia.
Arjuna Subject : -
Articles 4 Documents
 1 
Search results for , issue "Vol. 9 No. 2 (2025): Journal of Information Technology and Computer Engineering" : 4 Documents clear
Evaluating IndoGPT for Legal Queries: A Benchmark Against GPT-4 Models Palupi, Ade Cahyaning; irawan, ade
JITCE (Journal of Information Technology and Computer Engineering) Vol. 9 No. 2 (2025): Journal of Information Technology and Computer Engineering
Publisher : Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study evaluates a chatbot developed with the Large Language Model (LLM) IndoGPT, focusing on its use of Retrieval-Augmented Generation (RAG) to answer questions about university regulations from legal PDF documents in the Indonesian Language. IndoGPT's performance is benchmarked against the more advanced models, GPT-4 and GPT-4o. The chatbot combines RAG techniques with the LangChain framework, and its effectiveness is assessed using the Retrieval-Augmented Generation Assessment (RAGAS) framework. The dataset includes publicly available legal documents from Universitas Pertamina, with test data created by the authors. IndoGPT consistently underperforms compared to GPT-4 and GPT-4o. GPT-4 achieves superior metrics with Context Precision at 0.9027, Context Recall at 0.8693, Faithfulness at 0.8486, and Answer Relevancy at 0.8142. Similarly, GPT-4o delivers strong results with Context Precision at 0.8896, Context Recall at 0.8594, Faithfulness at 0.8804, and Answer Relevancy at 0.8773. In contrast, IndoGPT shows significant deficiencies, with much lower scores: Context Precision at 0.6687, Context Recall at 0.5711, Faithfulness at 0.0738, and Answer Relevancy at 0.1628. These findings highlight IndoGPT's substantial limitations, especially when compared to GPT-4 and GPT-4o, which excel in providing accurate, contextually relevant answers. The GPT-4-based chatbot demonstrates strong capabilities in understanding user queries and delivering accurate responses while effectively reducing hallucinations through the RAG technique.
Development of a Multi-Task Learning CNN Model for Pneumonia Detection and Pathogen Classification Based on Medical Images Harahap, Aris Munandar; Samosir, Khairunnisa
JITCE (Journal of Information Technology and Computer Engineering) Vol. 9 No. 2 (2025): Journal of Information Technology and Computer Engineering
Publisher : Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Pneumonia is one of the leading causes of death from respiratory tract infections worldwide. Early detection and identification of the causative pathogen are crucial for determining appropriate treatment. This study aims to develop a Convolutional Neural Network (CNN) model based on Multi-Task Learning (MTL) to simultaneously detect pneumonia and classify the type of pathogen through chest X-ray images. The model architecture uses a shared convolutional layer for feature extraction, which then branches into two classification paths. The model was trained using a dataset of X-ray images labeled with disease status and pathogen type, with two loss functions optimized simultaneously. Based on the training process and model architecture design, the estimated accuracy achieved is approximately 92% for pneumonia detection and 89% for pathogen type classification. These results indicate that the CNN-MTL approach is effective and efficient in simultaneously addressing two clinical tasks. The proposed model has the potential to be applied as a clinical decision support system, particularly in healthcare facilities with limited resources.
Low-complexity Automatic Modulation Classification of Higher-order QAM Based on Square Modulus Extraction Bello, Olalekan
JITCE (Journal of Information Technology and Computer Engineering) Vol. 9 No. 2 (2025): Journal of Information Technology and Computer Engineering
Publisher : Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Modulation classification plays a key role in decoding cognitive radio, signal identification, menace assessment, spectrum senses, and management, efficient use of available spectrum and increase in the speed of data transfer. Quadrature Amplitude Modulation (QAM) has become an important modulation scheme used in most civilian and military applications. However, algorithms developed so far for these purposes have been limited in classifying higher-order QAM and are also extremely complex. Applications which need to take real-time critical decision based upon modulation types information require that an automatic modulation classification (AMC) algorithm is necessarily simple both in cost and in implementation. This paper, therefore, proposes a novel low-complexity feature-based (FB) method based on evaluating the square modulus of the baseband demodulated received signal, as the only discriminating feature, to classify QAM of any modulation order. Results show, in the presence of combined effects of the carrier phase deviations, timing offset, multipath interference and AWGN, that all QAM modulation types up to 2048-QAM achieve 100% classification accuracy at lower than 10 dB of SNR. The classification algorithm is thus robust in accurately classifying any QAM modulation type even in the presence of combined effects of the common distortions on the received modulated signal.
Begal-Detector: A Real-Time Street Crime Detection Framework Combining Human Activity Recognition and Object Detection on Raspberry Pi Prastyo, Pulung Hendro; Agung, Ismi Batari; Ikram, Ahmad Fadahil; Pratama, Muhammad Herlan; Mandasari, Nia
JITCE (Journal of Information Technology and Computer Engineering) Vol. 9 No. 2 (2025): Journal of Information Technology and Computer Engineering
Publisher : Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Currently, street crime remains a serious challenge in Indonesia, while conventional CCTV systems still function passively as recorders. One of the most concerning types of crime is robbery with violence, commonly known in Indonesia as begal, which remains among the most frequently reported cases. This study proposes the Begal-Detector, a YOLOv8-based system that integrates Human Activity Recognition (HAR) and Object Detection to identify suspicious activities in real time on edge devices. The experiments were conducted on Raspberry Pi 4, Raspberry Pi 5, and Raspberry Pi 5 with Hailo AI Kit, with variations in distance, camera angle, and lighting conditions. The test dataset consisted of 72 video samples, including both street crime and non-street crime scenarios, recorded using the EZVIZ H8C Outdoor CCTV camera. Experimental results show that the Begal-Detector performs very well, achieving a 100% detection accuracy at a distance of 2 meters, 94% at 3 meters, and 94% at a 45° camera angle. Under low-light conditions supported by infrared light, the system maintained an accuracy of up to 79%, making it feasible for real-world deployment. In terms of hardware performance, the Raspberry Pi 5 with Hailo AI Kit provided the most optimal results, achieving an average of 52.71 FPS with a stable temperature of 63 °C, significantly outperforming the Raspberry Pi 4 and Raspberry Pi 5 without an accelerator, both of which failed to operate the system in real time. The findings confirm that utilizing Raspberry Pi 5 with Hailo AI Kit is an effective solution to ensure that the Begal-Detector operates quickly, stably, and reliably.

Page 1 of 1 | Total Record : 4

 1 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol. 9 No. 2 (2025): Journal of Information Technology and Computer Engineering Vol. 9 No. 1 (2025) Vol. 8 No. 2 (2024) Vol 8 No 2 (2024): Journal of Information Technology and Computer Engineering Vol. 8 No. 1 (2024) Vol 7 No 01 (2023): Journal of Information Technology and Computer Engineering Vol. 7 No. 01 (2023) Vol. 7 No. 2 (2023) Vol 6 No 02 (2022): Journal of Information Technology and Computer Engineering Vol. 6 No. 02 (2022) Vol. 6 No. 01 (2022) Vol 6 No 01 (2022): Journal of Information Technology and Computer Engineering Vol 5 No 02 (2021): Journal of Information Technology and Computer Engineering Vol. 5 No. 02 (2021) Vol. 5 No. 01 (2021) Vol 5 No 01 (2021): Journal of Information Technology and Computer Engineering Vol 4 No 02 (2020): Journal of Information Technology and Computer Engineering Vol. 4 No. 02 (2020) Vol. 4 No. 01 (2020) Vol 4 No 01 (2020): Journal of Information Technology and Computer Engineering Vol 3 No 02 (2019): Journal of Information Technology and Computer Engineering Vol. 3 No. 02 (2019) Vol 3 No 01 (2019): Journal of Information Technology and Computer Engineering Vol. 3 No. 01 (2019) Vol 2 No 02 (2018): Journal of Information Technology and Computer Engineering Vol. 2 No. 02 (2018) Vol 2 No 01 (2018): Journal of Information Technology and Computer Engineering Vol. 2 No. 01 (2018) Vol 1 No 01 (2017): Journal of Information Technology and Computer Engineering Vol. 1 No. 01 (2017) More Issue