cover
Contact Name
Ahmad Ilham
Contact Email
ahmadilham@unimus.ac.id
Phone
+6282225426654
Journal Mail Official
jichi.informatika@unimus.ac.id
Editorial Address
Jl. Kedungmundu Raya No. 18 Semarang, Jawa Tengah - Indonesia 50273
Location
Kota semarang,
Jawa tengah
INDONESIA
Journal of Intelligent Computing and Health Informatics (JICHI)
ISSN : 27156923     EISSN : 27219186     DOI : https://doi.org/10.26714/jichi
Journal of Intelligent Computing & Health Informatics (JICHI) was printed in March 2020. JICHI is a scientific review journal publishing that focus on exchanging information relating to intelligent computing and health informatics applied in industry, hospitals, government, and universities. All articles should include a validation of the idea presented, e.g. through case studies, experiments, or systematic comparisons with other approaches already in practice. Two types of papers are accepted: (1) A short paper that discusses a single contribution to a specific new trend or a new idea, and; (2) A long paper that provides a survey of a specific research trend using a systematic literature review (SLR) method, as well as a traditional review method. Topics of interest include, but are not limited to: Intelligent Computing Include Machine Learning; Reinforcement Learning; Computer Vision; Image Processing; Scheduling and Optimization; Bio-inspired Algorithms; Business Intelligence; Chaos theory and intelligent control systems; Robotic Intelligent; Multimedia & Application; Web and mobile Intelligence and Big Data, etc.) Health Informatics Include Electronic health record; E-Health Information; Medical Image Processing & Techniques; Data Mining in Healthcare; Bioinformatics & Biostatistics; Mobile applications for patient care; Medical Image Processing & Techniques; Hospital information systems; Document handling systems; Electronic medical record systems; standardization, and systems integration; ICT in health promotion programmes e-health Guidelines and protocols; E-learning & education in healthcare; Telemedicine Software- Portals-Devices & Telehealth; Public health & consumer informatics; Data Mining & Knowledge Discovery in Medicine; ICT for Patient empowerment; ICT for Patient safety; Medical Databanks-Databases & Knowledge Bases; Healthcare Quality assurance; Nursing Informatics; Evaluation & Technology Assessment; Home-based eHealth; Health Management Issues; Health Research; Health Economics Issues; Statistical Method for Computer Medical Decision Support Systems; Medical Informatics or medicine in general; Organizational, economic, social, clinical impact, ethical and cost-benefit aspects of IT applications in health care.
Articles 63 Documents
The Hybrid Residual–BiLSTM Model for Mitigating the Vanishing Gradient Problem in Synthetic Image Detection Kafitra Marna Ibrahim; Brian Halubanza; AHMAD SHUKRI MOHD NOOR; Muhammad Sam'an; Muhammad Munsyarif; Azyan Yusra Kapi
Journal of Intelligent Computing & Health Informatics Vol 7, No 2 (2026): September
Publisher : Universitas Muhammadiyah Semarang Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jichi.v7i2.22744

Abstract

The rapid advancement of generative artificial intelligence has enabled the creation of highly realistic synthetic images, raising concerns regarding the authenticity of digital media. While convolutional neural network (CNN)-based methods have shown promising results for synthetic image detection, deep architectures often suffer from training instability caused by the vanishing gradient problem and limited representation learning. This study proposes a Deep Residual BiLSTM Fusion model that integrates residual-based CNN feature extraction with bidirectional long short-term memory (BiLSTM) modeling to enhance training stability and contextual representation learning. The proposed model is evaluated on the CIFAKE dataset, a challenging low-resolution benchmark for synthetic image detection. Experimental results demonstrate competitive performance with an accuracy of 97.27% and balanced precision and recall across both real and synthetic classes. Gradient flow analysis further confirms stable optimization behavior, highlighting the effectiveness of the proposed hybrid architecture for robust synthetic image detection.
Grey Wolf Optimization-Based Feature Selection for Improved Stunting Malnutrition Classification Santosa Santosa; Zailani Bin Abdullah
Journal of Intelligent Computing & Health Informatics Vol 7, No 2 (2026): September
Publisher : Universitas Muhammadiyah Semarang Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jichi.v7i2.22743

Abstract

This study investigates the impact of Synthetic Minority Oversampling Technique (SMOTE) and feature selection on ten machine learning models hybridized with Grey Wolf Optimization (GWO) for stunting malnutrition classification. The models, including Support Vector Classifier (GWO+SVC), KNearest Neighbors (GWO+KNN), Decision Tree (GWO+DT), Gradient Boosting Decision Trees (GWO+GBDT), Random Forest (GWO+RF), XGBoost (GWO+XGBoost), LightGBM (GA+LightGBM), Adaboost (GWO+Adaboost), CatBoost (GWO+CatBoost), and Stacking Classifier (GWO+Stacking), are evaluated. The findings reveal that SMOTE significantly enhances most models, particularly in terms of accuracy, precision, and F1-score, effectively addressing data imbalance. Notably, GWO+GBDT consistently outperforms other models, achieving the highest accuracy after SMOTE application. Feature selection further boosts model performance, with GBDT reaching 86.84% accuracy after attribute selection. Future research avenues may explore alternative machine learning models, feature selection methods, additional data sources, external validation, parameter optimization, and the integration of clinical information for more effective stunting malnutrition combat strategies.
Longitudinal KAP Analysis for Measuring the Robustness of Community Nurses’ Digital Health Adoption Ahmed D. Salman Abed
Journal of Intelligent Computing & Health Informatics Vol 7, No 2 (2026): September
Publisher : Universitas Muhammadiyah Semarang Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jichi.v7i2.21037

Abstract

The rapid integration of digital health architectures demands specialized digital health literacy among frontlineclinicians. However, in resource-constrained healthcare environments, professional readiness and technologicalacceptance remain limited. This study evaluates a structured training intervention designed to optimize theKnowledge, Attitude, and Practice (KAP) trajectories of community health nurses, leveraging the causal pathwaysof the Technology Acceptance Model (TAM). Using an explanatory sequential mixed-methods design, a cohort of60 community health nurses underwent a four-session simulator-based training. Metrics were quantified acrossmulti-temporal checkpoints: Baseline Spre, 1 month Spost1, and 3 months Spost2. Hypothesis testing confirmedstatistically significant and robust competency transitions (p < 0.001). Cognitive Knowledge (K) scores escalatedfrom a baseline of 12.4 ± 3.1 to 24.2 ± 1.8 at 1 month, and stabilized at 23.5 ± 2.1 at 3 months, reflecting an eliteeffect size (Cohen’s d = 2.61). Behavioral Attitude (A) scores advanced from 3.2 ± 0.8 to 4.6 ± 0.4 (p < 0.001),while Clinical Practice (P) shifted from 2.1 ± 1.2 to 4.1 ± 0.7, revealing an exceptional overall technology adoptionefficiency of 93% and a low degradation rate ( = 0.046). Qualitative insights from interviews (n = 15) highlightedinfrastructural constraints ( ) limiting the theoretical performance ceiling.