cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Siti Nurmaini
Contact Email
comengappjournal@unsri.ac.id
Phone
+6285268048092
Journal Mail Official
comengappjournal@unsri.ac.id
Editorial Address
Jurusan Sistem Komputer, Fakultas Ilmu Komputer, Universtas Sriwijaya, KampusUnsri Bukit Besar, Palembang
Location
Kab. ogan ilir,
Sumatera selatan
INDONESIA
ComEngApp : Computer Engineering and Applications Journal
Published by Universitas Sriwijaya
ISSN : 22524274     EISSN : 22525459     DOI : 10.18495
Core Subject : Science, Engineering,
Computer Science & IT Engineering
ComEngApp-Journal (Collaboration between University of Sriwijaya, Kirklareli University and IAES) is an international forum for scientists and engineers involved in all aspects of computer engineering and technology to publish high quality and refereed papers. This Journal is an open access journal that provides online publication (three times a year) of articles in all areas of the subject in computer engineering and application. ComEngApp-Journal wishes to provide good chances for academic and industry professionals to discuss recent progress in various areas of computer science and computer engineering.
Arjuna Subject : Teknik (semua kategori) - Teknik (Lain-Lain)
Articles 10 Documents
 1 
Search results for , issue "vol. 15 no. 2 (2026)" : 10 Documents clear
An Information Security Maturity Evaluation of the BKO District Court Based on the KAMI Index Version 5.0 Muhammad Tulus Akbar
Computer Engineering and Applications Journal Vol. 15 No. 2 (2026)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18495/comengapp.v15i2.1329

Abstract

Information security is a vital component in institutional IT operations, especially for Electronic System Operators (ESO). Effective governance is essential to ensure data protection, integrity, and availability. The readiness evaluation of the BKO District Court, conducted using the KAMI Index version 5.0 based on ISO/IEC 27001:2022, assessed seven areas: information security governance, risk management, information security framework, asset and technology management, personal data protection, and supplementary controls involving third parties. The assessment applied five implementation levels and maturity levels I–V. The Court scored 14 in the electronic system category (low dependency) and achieved an overall score of 913 with a “Good” rating. The highest maturity levels were recorded in risk management and the information security framework (Level V), while other areas ranged from Levels III to IV. Overall, the results show that the BKO District Court has a well-developed and consistently implemented information security governance structure, though enhancements in asset management and personal data protection are still required to achieve optimal maturity under SNI ISO/IEC 27001:2022.
A Comprehensive Survey of Audio-Visual Fusion with Attention Mechanisms: Trends, Challenges, and Future Directions Rexcharles Enyinna Donatus
Computer Engineering and Applications Journal Vol. 15 No. 2 (2026)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18495/comengapp.v15i2.1332

Abstract

Advances in multimodal deep learning have driven growing interest in attention mechanisms that enhance audio and visual integration for tasks such as emotion recognition, event localization, and human computer interaction. This comprehensive survey synthesizes recent progress in attention based fusion methods and highlights the evolution from early fusion strategies to more advanced architectures, including self-attention, cross modal attention, co attention, and hierarchical attention. Transformer based models, in particular, now play a central role in state of the art audio visual systems because they capture long range temporal and semantic relationships across modalities. This survey examines how these mechanisms improve contextual understanding and task performance, while also identifying persistent challenges related to interpretability, robustness to noisy or missing modalities, modality imbalance, and computational efficiency. Limitations associated with dataset bias and the lack of standardized evaluation metrics are also discussed. Finally, the survey presents future research directions, including the development of cross modal transformer architectures, hierarchical attention models, and comprehensive attention diagnostics frameworks to support trustworthy and effective multimodal artificial intelligence systems
RPLR -ASBO- A novel model of risk communication and risk perception in financial decision making Bingxu Hou; Yuzhou Liu; Shiyuan Huang
Computer Engineering and Applications Journal Vol. 15 No. 2 (2026)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18495/comengapp.v15i2.1342

Abstract

The interaction between risk communication and risk perception plays a pivotal role in shaping financial decision-making, particularly in complex investment environments. Traditional financial advice often emphasizes assessing clients' risk tolerance while overlooking how the communication of risk information influences clients' perception of potential losses and uncertainties. The analysis examines the effectiveness of conveying financial risks in the perception of risk by investors and thus their decisions to invest. This analyzed on the direct and indirect effects of risk education on allocation to risky assets based on risk perception based on survey respondents of 465 financial adviser clients. The respondents were asked to complete structured questionnaires on risk communication quality (RCQ), risk perception (RP), investment choice (IC), Emotional Response to Risk (ERR) and Information Seeking Behavior (ISB). SPSS version 27 was used to analyze the data, and regression, correlation, and descriptive statistics were used to investigate associations between the variables. The results indicate that the Clear risk communication (b = 0.420, r = 0.52) contributes to the financial decision-making, the most help of risk perception (b = 0.310) and investment choices (b = 0.365) and moderate effects of emotional response (b = 0.180) and information seeking behavior (b = 0.250). In addition to this, the study proposed Risk Perception using Logistic Regression (RPLR) based Adaptive Satin Bowerbird optimization (ASBO) model for analyzing the risk communication and risk perception. Risk communication significantly impacts financial decisions, with clarity of communication boosting decision quality. The relationship between communication and perception is confirmed in direct and indirect effects. Development and implementation of proper strategies enhance the informed decision making, risk management and investment returns.
Progressive Ordinates GAN with Centroid Fuzzy Ray-Tracing for Scene Image Detection from Thermal Imaging R. Rajeswari; Dr. S. Kannan
Computer Engineering and Applications Journal Vol. 15 No. 2 (2026)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18495/comengapp.v15i2.1343

Abstract

The security threats from terrorism and illegal migration raised security concerns, insisting the use of thermal cameras in surveillance systems due to their night vision and all-weather capability. However, thermal images suffer from variations in surface roughness, texture, and radiation, hindering accurate object detection. To address this, a Progressive Ordinates GAN with Centroid Fuzzy Ray-Tracing model is proposed for the efficient object detection using thermal images. The existing object detection algorithms struggle in detecting thermal signatures, as they depend only on temperature while neglecting emissivity differences from diverse surface characteristics of thermal images. To overcome this problem, a novel Progressive Ordinates Generative Adversarial Network (POGAN) is introduced, for more accurate detection and characterization of objects with diverse surface characteristics having varying emissivity, mitigating the challenges of inconsistent thermal signatures. Moreover, the shadow casting of objects from thermal image hinders identifying the object boundaries. The existing algorithms struggle to determine the shadow casting as they are not aware of the related parameters such as geometric properties, spatial relationships and the angle of incidence, as they operate on fixed-size image patches or regions. Hence, Centroid Ray-Tracing Fuzzy Clustering (CRFC) is introduced, which effectively acclimates to varying scene complexity by dynamically adjusting cluster centroids, thus enables a better understanding of geometric properties, spatial relationships, and angle of incidence within the scene. The analysis on this work validates that the proposed model achieves better performance with improved accuracy, sensitivity, mean Average Precision (mAP) and recall, with minimized Mean Average Error (MAE).
Hybrid CNN–Transformer Architecture for Multivariate Behavioral Time-Series Modeling in Precision Livestock Pregnancy Prediction: An Intelligent Data-Driven Approach for Early Pregnancy Prediction in Precision Livestock Farming Swagatika Devi; Senthilkumar V; Geetha M; Nithya K; Shailendra Madansing Pardeshi; Sumithra M; Tatiraju.V.Rajani Kanth; Prince Sahaya Brighty S
Computer Engineering and Applications Journal Vol. 15 No. 2 (2026)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18495/comengapp.v15i2.1347

Abstract

This work presents CNN–Transformer, a new hybrid deep learning model based on CNN and Transformer for predicting the pregnancy of a cow with multivariate sequential behavioral data extracted from CowView sensors. The percentage features were divided into three cow states – ALLEY (motion), BOOST (eating) & LOGETTE (sleeping) – and summarized into 30 minutes, resulting in daily sequences comprised of 48 time points. To mitigate the limitation of scarce data and facilitate generalization, simulation-based augmentation is performed by utilizing activity frequency matrix and transition probability matrix learned from the real data. Among these, Logistic Regression, SVM, Random Forest, LSTM and CNN-LSTM are chosen and a comparative analysis of the five models is presented. Traditional machine learning algorithms had moderate performance: Logistic Regression and SVM obtained an accuracy of 71% and 73%, respectively; Random Forest obtained 66%. The results are improved by deep learning methods, where LSTM obtains 77% (ROC-AUC: 0.82), and CNN-LSTM achieves 82% (Precision: 0.86, F1-score: 0.81, ROC-AUC: 0.87). Our CNN–Transformer model beats all the baselines at the accuracy of 86%, precision of 0.90, F1-score of 0.86, and ROC-AUC of 0.92. Models trained on the real data, on average, had an accuracy of 73.8%, significantly better than that with the simulated data (53.8%). It was robust, holding 78% accuracy at 20% noise, and early prediction accuracy was 81% at 24 hours before diagnosis. Statistical validation demonstrated significant improvement (p < 0.01), thus confirming hybrid temporal models for precision livestock farming.
Hybrid Interpretable and Deep Learning Models for Intrusion Detection in Large-Scale Network Traffic: An Intelligent and Scalable Approach for Detecting Complex and Evolving Network Threats Chintureena Thingom; Harikeerthan MK; Cloudin S; Lokeshwaran K; Praveena K; Prasanna Kumar K.R; Deepa P; Kishore Chandra Dev Nakka
Computer Engineering and Applications Journal Vol. 15 No. 2 (2026)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18495/comengapp.v15i2.1348

Abstract

The fast growth of cyber-attacks and network traffic, have put forward the requirement of autonomous and scalable IDSs that can accurately discern among normal and malicious activities. In this paper, a hybrid machine learning (ML)-based IDS model, DTCNN-IDS, is presented by combining Decision Tree (DT), Convolutional Neural Network (CNN), and TabTransformer. The framework is tested against the KDD99 data set, containing 4,898,431 network records with continuous and categorical fields. A uniform pipeline with preprocessing, encoding, normalization, and multi-class supervised learning (M2A approach) allows for robust model evaluation. DT produces high accuracy (99.99%) but biased results on minority attacks (U2R recall = 0.72, R2L recall = 0.76) as a result of class imbalance. CNN enhances the nonlinear feature learning and achieves an accuracy of 99.7% with the precision, recall and F1-score of 0.996. The best-performing model is TabTransformer, achieving accuracy of 99.8%, precision of 0.997, recall of 0.998 and F1-score of 0.997, which also significantly improves detection of minority attacks. The improved sensitivity and stability are further confirmed by the Precision–Recall, scalability analyses and statistical testing (p < 0.05) validates the significance of results.
A Lightweight Dual-Stage Conv2D–UNet Framework for Real-Time Chili Leaf Disease Detection and Severity Estimation: A Computationally Efficient Framework for Real-Time Plant Disease Identification and Localization Prabhu D; Golda Dilip
Computer Engineering and Applications Journal Vol. 15 No. 2 (2026)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18495/comengapp.v15i2.1349

Abstract

Timely crop disease detection is important to increase the productivity and reduce the economic loss in farming. For automated chilli leaf disease diagnosis, a Conv2D-based classification model and a UNet based segmentation model are combined for lightweight dual-stage deep learning framework in the proposed study. The severity of the disease was estimated at the pixel level by the Segmentation model, which was able to transgress the disease area from the sensors. The training set was augmented to improve the generalization, and the training, validation, and testing sets were divided into 80:10:10: The dataset contains 3,780 chilli leaf images. Results: Our Conv2D classifier attains an accuracy of 96.5% with F1-score of 0.96 and recall of 0.95, obtaining superior results over popular models like VGG16 and EfficientNet-B0 and is also lightweight with only 28 MB size and 2.4 million parameters. Results:The UNet model obtains a mean mIoU of 0.89 with the maximal IoU of 0.92 and the dice coefficient is 0.91, corresponding to a pixel accuracy of 94.8% for the Bacterial Spot lesions. The framework is lightweight, allowing on-line disease classification and severity prediction in precision agriculture
LoTQA: Local Benchmarking of Large Language Models for Table Question Answering Muhammad Arya All Fajri; Muhammad Ikhsan Rizki Pratama; Firdaus Firdaus; Abdiansah Abdiansah
Computer Engineering and Applications Journal Vol. 15 No. 2 (2026)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18495/comengapp.v15i2.1350

Abstract

TableQA memainkan peran penting dalam mendukung pengambilan keputusan berbasis data dan meningkatkan efisiensi pencarian informasi. Penggunaan Large Language Models (LLM) melalui layanan cloud atau API eksternal memungkinkan sistem untuk secara otomatis memahami struktur tabel dan konteks pertanyaan, melakukan generalisasi, penalaran kontekstual, dan memahami hubungan semantik antar entitas dalam tabel untuk menghasilkan jawaban yang lebih relevan dan akurat. Pendekatan ini mengakibatkan peningkatan signifikan dalam biaya komputasi, potensi risiko keamanan data, dan keterbatasan dalam pengembangan, kustomisasi, dan pengujian model. Penelitian ini mengusulkan LoTQA untuk tugas TableQA. LoTQA adalah pendekatan yang memanfaatkan eksekusi lokal untuk mengevaluasi dan membandingkan metode LLM dalam menghasilkan jawaban dari data tabel terstruktur. Evaluasi kinerja pada LoTQA (Qwen3:4b, LoRA Fine-tuned) memperoleh nilai SacreBLUE sebesar 8,613, BLEU-1 sebesar 35,623, BLEU-2 sebesar 26,592, BLEU-3 sebesar 22,723, ROUGE-1 sebesar 0,364, ROUGE-2 sebesar 0,177, ROUGE-L sebesar 0,311, dan METEOR sebesar 0,317. Hasil ini menunjukkan bahwa metode LoTQA cukup baik dalam menyediakan kalimat yang bermakna secara semantik untuk prediksi, bahkan dengan sumber daya yang rendah. Hasil evaluasi kinerja untuk setiap model LLM yang digunakan menunjukkan bahwa model Qwen3:4b mencapai skor tertinggi untuk SacreBLEU, ROUGE-1, ROUGE-2, ROUGE-L, dan METEOR. Studi ini menunjukkan bahwa LoTQA berkinerja cukup baik pada tugas TableQA, meskipun dengan sumber daya yang rendah.
A real-time intruder detection and notification system using the LBPH facial recognition method via the LINE application Nitit WangNo
Computer Engineering and Applications Journal Vol. 15 No. 2 (2026)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18495/comengapp.v15i2.1360

Abstract

Face detection and recognition in images and videos is a widely studied topic in the field of biometrics, with increasing importance in security and surveillance applications. This paper presents the development of a real-time face recognition system designed to enhance security and automation. The system utilizes a Haar-cascade classifier for initial face detection and the Local Binary Pattern Histogram (LBPH) algorithm for face recognition, based on a locally generated training dataset. It operates in two main stages: detecting human faces and identifying individuals. In cases where an unrecognized face is detected, the system sends an immediate alert via the LINE application. Key components of the system include real-time processing, identity verification, and access control. The proposed system shows strong potential for practical deployment in areas such as crowd monitoring and personal security in sensitive environments like airports. Experimental results demonstrate a recognition accuracy ranging from 90% to 93.45%, validating the effectiveness of the approach.
Implementation and Training of Linux-Based Network Administration to Enhance Network Infrastructure Izulhak Algi Fahrizal; Andi Rakhmat Baharuddin
Computer Engineering and Applications Journal Vol. 15 No. 2 (2026)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18495/comengapp.v15i2.1370

Abstract

This article aims to comprehensively synthesize the relationship between Linux server implementation, network administration training, and their impact on network infrastructure improvement. Linux servers are becoming increasingly important in modern network management because they support service flexibility, resource efficiency, security, automation, and high availability, while network administration training is a key factor in building the technical competencies of network administrators. This study employs a systematic review method on 35 scientific articles classified into three main topics: Linux server implementation, network administration training, and the impact on network infrastructure. The review results indicate that Linux server implementation contributes to improved performance, stability, efficiency, and reliability of network services, whereas hands-on training plays a role in enhancing administrators’ operational skills and readiness. These findings confirm that improvements in Linux server-based network infrastructure depend on the integration of the quality of technical implementation and the competencies of the personnel managing it.

Page 1 of 1 | Total Record : 10

 1 

Filter by Year

2026 2026


Reset
Filter By Issues
All Issue Vol. 15 No. 2 (2026) Vol. 15 No. 1 (2026) Vol. 14 No. 2 (2025) Vol. 14 No. 1 (2025) Vol 14 No 1 (2025) Vol 13 No 03 (2024) Vol. 13 No. 3 (2024) Vol 13 No 2 (2024) Vol. 13 No. 2 (2024) Vol 13 No 1 (2024) Vol. 13 No. 1 (2024) Vol. 12 No. 3 (2023) Vol 12 No 3 (2023) Vol 12 No 2 (2023) Vol. 12 No. 2 (2023) Vol. 12 No. 1 (2023) Vol 12 No 1 (2023) Vol. 11 No. 3 (2022) Vol 11 No 3 (2022) Vol 11 No 2 (2022) Vol. 11 No. 2 (2022) Vol. 11 No. 1 (2022) Vol 11 No 1 (2022) Vol 10 No 3 (2021) Vol 10 No 2 (2021) Vol 10 No 1 (2021) Vol 9 No 3 (2020) Vol 9 No 2 (2020) Vol 9 No 1 (2020) Vol 8 No 3 (2019) Vol 8 No 2 (2019) Vol 8 No 1 (2019) Vol 7 No 3 (2018) Vol 7 No 2 (2018) Vol 7 No 1 (2018) Vol 6 No 3 (2017) Vol. 6 No. 2 (2017) Vol 6 No 2 (2017) Vol 6 No 1 (2017) Vol. 6 No. 1 (2017) Vol. 5 No. 3 (2016) Vol 5 No 3 (2016) Vol 5 No 2 (2016) Vol 5 No 1 (2016) Vol 4 No 3 (2015) Vol 4 No 2 (2015) Vol 4 No 1 (2015) Vol 3 No 3 (2014) Vol 3 No 2 (2014) Vol 3 No 1 (2014) Vol 2 No 3 (2013) Vol. 2 No. 3 (2013) Vol 2 No 2 (2013) Vol. 2 No. 2 (2013) Vol 2 No 1 (2013) Vol. 2 No. 1 (2013) Vol. 1 No. 2 (2012) Vol 1 No 2 (2012) Vol 1 No 1 (2012) More Issue