cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
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)
Published by Universitas Muhammadiyah Semarang
ISSN : 27156923     EISSN : 27219186     DOI : https://doi.org/10.26714/jichi
Core Subject : Health, Science, Engineering,
Computer Science & IT Dentistry Electrical & Electronics Engineering Medicine & Pharmacology Public Health
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.
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 57 Documents
 2   3   4   5   6 
Topic Modelling using Latent Dirichlet Allocation (LDA) to Investigate the Latent Topics of Mathematical Creative Thinking Research in Indonesia Maulidiya, Della
Journal of Intelligent Computing & Health Informatics Vol 3, No 2 (2022): September
Publisher : Universitas Muhammadiyah Semarang Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jichi.v3i2.11428

Abstract

In mathematics education, there is increasing interest in Mathematical Creative Thinking (MCT), and numerous scientific documents on this topic have been published in Indonesia. The availability of publication databases has made it easier to access these documents and collect large amounts of data related to MCT. This data has the potential to uncover latent topics within MCT research articles published in Indonesian journals. This study analyzed a dataset of 102 articles obtained from Garuda (Digital Reference Garda) published between 2010 and 2022 in six proceedings and 49 journals. The study applied text processing techniques and used topic modeling with Latent Dirichlet Allocation (LDA) and variational expectation maximization algorithm (VEM) to produce 23 topics. Each topic consisted of general and special words from the beta probability value. The study found 30 unique words from topic modeling, including learning, abilities, problems, skills, mathematics, tests, levels, answers, approaches, assessments, basics, classes, developing, values, ideas, instruments, materials, mathematics, moderate, models, motivation, open-ended, processes, questions, reasons, solving, styles, subjects, teaching, and worksheets. The study also used LDA to classify documents into discovered themes and found that the five MCT research focuses were learning approaches, student competencies, teacher competencies, assessments, and learning resources. The study's findings revealed a research gap, specifically, the need for more MCT studies that concentrate on enhancing teacher competency.
The Role of EEG Signals: SVM Classification of Cognitive Load as a Support for UX Evaluation Iksan, Ennu Intan; Mardhia, Murein Miksa
Journal of Intelligent Computing & Health Informatics Vol 4, No 1 (2023): March
Publisher : Universitas Muhammadiyah Semarang Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jichi.v4i1.11198

Abstract

Cognitive load is the mental effort that needs to be applied to working memory to process information received over a period of time. Cognitive load can be viewed as the level of mental energy required to process a given amount of information. In user experience design, cognitive load is considered as the mental processing power required to use a product. If the amount of information processed exceeds the user's ability to process it, the overall performance will be disrupted. An EEG device is needed that is used to record electrical activity that occurs in the brain by channeling brain electrical waves to cables and modulators that are sensitive to electrical waves. The object of this research is the EEG Beta signal with the attention wave type from UX testing activities on students aged 21-24 years with a frequency level of 13-30 Hz. The EEG tool records the activity of the respondent's wave signal by collecting data on the activity of working on a questionnaire about evaluating the WhatsApp application using the Google Form application. The classification of cognitive load studied is unencumbered and burdened. Unencumbered represents the ease that is felt when interacting with the application, while burdened represents the difficulty or confusion that is felt when interacting with the application. Testing is done with the Confusion matrix. The best accuracy results among the kernel types in the SVM method are linear kernel types with an accuracy result of 89% consisting of 1 data that is categorized as an unencumbered label and 8 data labels that are loaded
Ordinal Logistic Regression Approach for Probability Analysis of Student Stress Levels Khikmah, Laelatul; Ratnasari, Elis Meida
Journal of Intelligent Computing & Health Informatics Vol 3, No 1 (2022): March
Publisher : Universitas Muhammadiyah Semarang Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jichi.v3i1.11793

Abstract

Stress is a condition or condition where a person feels pressured because of the many demands, both from within and from outside the individual that must be met. Stress is an uncomfortable stressful event for someone that can cause negative effects such as dizziness, emotional instability, irritability, loss of appetite, difficulty concentrating, and difficulty sleeping. One of the factors that cause stress is doing the Final Project. Someone who is experiencing stress can be seen from the level of stress, namely the level of mild, moderate and severe stress. To see a person's stress level, several variables can be used, namely physiological, emotional, cognitive, supervisory, and knowledge variables. This study aims to find out what variables affect stress levels in students. The analysis used is Ordinal Logistic Regression analysis which is one of the statistical analyzes used to determine the probability of events that are affected by the independent variable, where the response variable is a categorical scale. Variables that affect stress levels are emotional, cognitive and knowledge variables. The results showed that the higher a person's emotion, cognitive and knowledge, the smaller the chance for someone to experience severe levels of stress.
Time Optimization of Watermark Image Quality Using Run Length Encoding Compression Mahiruna, Adiyah; Rachmawanto, Eko Hari; Istiawan, Deden
Journal of Intelligent Computing & Health Informatics Vol 4, No 2 (2023): September
Publisher : Universitas Muhammadiyah Semarang Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jichi.v4i2.12058

Abstract

Internet technology continues to have a significant impact on digital media, such as text, images, audio, and video. One effect is the ease of exchange, distribution, and duplication of digital data; on the other hand, this ease raises the problem of digital data being protected by copyright or digital data confidentiality. Watermarking is a way to protect digital data rights. Extensive research on watermarking has been conducted, including a hybrid DWT-DCT-SVD approach. Several studies have found weaknesses in the message insertion process; for example, the time required to insert a watermark image is relatively long, particularly for large images. To address the problem of long message insertion times, this study applies a compression process to the original image before the watermark image insertion process. The original image to be inserted into the watermark image is compressed using the run-length encoding (RLE) algorithm. The results of RLE compression demonstrate that image file size is reduced significantly, which optimizes the watermarking process. The experimental results demonstrate that watermarked images with RLE compression preprocessing exhibit better imperceptibility and comparable or improved PSNR values. Specifically, the image "Elaine" showed a PSNR improvement from 28.7541 to 31.4502 with RLE compression. These findings demonstrate that combining DWT-DCT-SVD with RLE compression not only reduces watermarking time but also maintains or enhances image quality, providing a robust solution for digital copyright protection.
Modelling of Dengue Hemorrhagic Fever Disease in Semarang City Using Generalized Poisson Regression Model Septia, Siti Fajar; Hidayat, Muhamad Arif; Asyfani, Yusrisma; Haris, M. Al; Winaryati, Eny
Journal of Intelligent Computing & Health Informatics Vol 4, No 2 (2023): September
Publisher : Universitas Muhammadiyah Semarang Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jichi.v4i2.12769

Abstract

Dengue Hemorrhagic Fever (DHF) is an infectious disease that can be life- threatening within a relatively short period of time and can be fatal if not promptly treated. DHF in Indonesia ranks second as a dangerous seasonal disease. DHF remains a serious issue in the Central Java Province, particularly in Semarang City. The cases of DHF can be modeled using a Poisson regression model due to the characteristics of DHF cases, which involve count data with small occurrence probabilities. The Poisson regression model assumes equality between the mean and variance (equidispersion). However, the application of the Poisson regression model often encounters violations of the assumption of excessive variance (overdispersion), which necessitates addressing the violation, and one possible approach is to use the Generalized Poisson Regression model. Based on the analysis results, the Generalized Poisson Regression model could handle the overdispersion because the ratio of Pearson Chi-Square by degrees of freedom was 0.976, approaching a value of 1. It has also been proven to be more suitable for evaluating factors influencing the number of DHF cases, as it has a lower AIC value compared to Poisson models, with a value of 123.64. The variables that were found to have an impact on DHF cases in Semarang City based on the Generalized Poisson Regression model are the number of larval habitats (X1), the number of hospitals (X2), population density (X3), and the number of healthcare workers (X4).
Expert System for Diagnosis Pregnancy Disorders using Forward Chaining Method Based on Android Safitri, Dina; Safuan, Safuan; Assaffat, Luqman
Journal of Intelligent Computing & Health Informatics Vol 4, No 2 (2023): September
Publisher : Universitas Muhammadiyah Semarang Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jichi.v4i2.13013

Abstract

Technology's rapid evolution has extended its impact into the healthcare field, including the development of artificial intelligence-based expert systems designed to streamline the work processes of nurses and obstetricians. In this research, we use the forward chaining method to build an android-based expert system for diagnosing fetal disorders in pregnant women. This system is made for ease of use on mobile devices by targeting pregnant women where this application provides a self-detection mechanism for pregnancy abnormalities. The test results show a high level of respondent satisfaction with this expert system application, with an average score of 90.16%, indicating a strong acceptance of the quality and functionality of the application. It can be concluded that our proposed expert system application shows a positive response from respondents and is considered successful in providing pregnancy diagnosis services independently.
An Enhanced IS-LM Business Cycle Model for Increasing Income in a Dynamic Economy Diana, Arista Fitri; Rahmasari, Shafira Meiria; Mahardika, Dhimas
Journal of Intelligent Computing & Health Informatics Vol 4, No 2 (2023): September
Publisher : Universitas Muhammadiyah Semarang Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jichi.v4i2.13201

Abstract

This paper introduces an enhanced IS-LM business cycle model by integrating control parameters using the Pontiyagin Maximum Principle Method, aiming to maximize income within economic cycles. It develops a dynamic model incorporating import and consumption rates as controls, showcasing their impact on economic variables through simulations and analytical methodologies. The results exhibit a significant increase in income by up to 10% through the reduction of interest rates and capital stock. The efficiency of the proposed controls is visually demonstrated, providing a robust validation of the methodology used, aligning with prior research, and offering substantial insights into dynamic business cycle modelling for economic analysis and policy-making.
Enhancing Early Diagnosis of Heart Disease: A Comparative Study of K-NN and Naive Bayes Classifiers Using the UCI Heart Disease Dataset Permana, Angga Aditya; Arsanah, Arsanah
Journal of Intelligent Computing & Health Informatics Vol 5, No 1 (2024): March
Publisher : Universitas Muhammadiyah Semarang Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jichi.v5i1.11251

Abstract

Heart disease remains a leading cause of mortality globally, necessitating accurate predictive models for early detection and intervention. This study conducted a detailed comparative analysis of the K-nearest neighbor (KNN) and naive bayes classifiers using the UCI Repository Heart Disease dataset to determine the most effective algorithm for heart disease prediction. Our results demonstrate that the proposed KNN outperforms naive bayes in terms of several key metrics: KNN achieved an accuracy of 91.25%, which surpasses naive bayes' accuracy of 88.75%. Additionally, KNN exhibited superior precision (92%), recall (90%), and an F1 score (91%) compared to naive bayes, which demonstrated precision of 89%, recall of 87%, and an F1 score of 88%. The findings of this study have substantial practical implications for medical data analysis. The high accuracy and reliability of the KNN algorithm make it a valuable tool for healthcare professionals in the early diagnosis of heart disease. Implementing KNN-based predictive models can enhance patient outcomes by timely and accurate detection of heart disease, facilitating early intervention, and reducing the risk of severe cardiac events. Moreover, the user-friendly interface of the proposed system streamlines the classification process, making it accessible for clinical use. Future research should explore the integration of additional machine learning algorithms and ensemble methods to further improve prediction accuracy. Developing real-time prediction systems integrated with electronic health records (EHR) could revolutionize patient monitoring and proactive healthcare management, ultimately contributing to better patient outcomes and more efficient healthcare delivery.
Padang Cuisine Classification using Deep Convolutional Neural Networks and Transfer Learning Sulistya, Elvina; Tyasari, Fanni; Azahra, Anisa Ismi; Munsyarif, Muhammad
Journal of Intelligent Computing & Health Informatics Vol 5, No 1 (2024): March
Publisher : Universitas Muhammadiyah Semarang Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jichi.v5i1.13960

Abstract

Recent advances in artificial intelligence, particularly deep convolutional neural networks (DCNN), have revolutionized image classification tasks across various domains. However, the application of these techniques to culturally specific food classifications, such as Padang cuisine, remains underexplored. This study aimed to develop a robust model for accurately classifying Padang cuisine using a CNN architecture enhanced with Transfer Learning to address the challenge of distinguishing between visually and texturally similar dishes. The model was trained on a dataset comprising approximately 2500 images of nine distinct Padang dishes, including Rendang and Gulai. Images were preprocessed by resizing, normalizing, and augmented through techniques like rotation and zooming, to enhance model generalizability. A pretrained CNN model was fine-tuned using Transfer Learning to leverage the existing knowledge and improve classification accuracy. The enhanced CNN model achieved an overall accuracy of 92% in classifying Padang cuisine, which significantly outperformed traditional models. Despite this, misclassifications were noted in dishes with similar visual features, such as Sate and certain types of Gulai. The results demonstrate the effectiveness of combining CNNs and transfer learning to accurately classify culturally specific dishes. The findings not only advance the field of food image classification but also have practical implications for automated menu management and culinary education, particularly in preserving and promoting culinary heritage. The integration of AI into culinary heritage documentation represents a significant advancement in preserving cultural diversity and enhancement of technological applications in the culinary industry. Future research should explore larger and more diverse datasets to further refine model accuracy and broaden its applicability to other regional cuisines.
EfficientNet for Medical Image Classification: Performance vs. Efficiency in Skin Cancer Detection Purbandanu, Muhammad Wigig; Kurniawan, Arif; Yanuarta, Rizky; Munsarif, Muhammad; A. Awoseyi, Ayomikun
Journal of Intelligent Computing & Health Informatics Vol 5, No 2 (2024): September
Publisher : Universitas Muhammadiyah Semarang Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jichi.v5i2.14338

Abstract

This study applies EfficientNetB2, a computationally efficient convolutional neural network (CNN), to improve the accuracy of skin cancer detection using the heterogeneous HAM10000 dataset. Skin cancer classification poses challenges, including overfitting and class imbalance, which we address through data augmentation, class weighting, and SMOTE (Synthetic Minority Over-sampling Technique). Our model achieved accuracy of 86%, precision of 0.87, recall of 0.85, and an AUC of 0.90. These results outperform comparable architectures, such as ResNet50 and GoogleNet, while maintaining lower computational complexity. The proposed model demonstrates high precision in detecting actinic keratoses and basal cell carcinoma, which require timely treatment, but faces difficulties in differentiating melanoma from benign nevi because of their similar visual appearance. This study highlights the potential of EfficientNetB2 for real-world deployment in resource-limited settings, such as mobile health applications and telemedicine platforms. Future research will focus on integrating attention mechanisms and exploring cross-dataset validation to enhance model generalizability and performance.

Page 4 of 6 | Total Record : 57

 2   3   4   5   6 

Filter by Year

2020 2026


Reset
Filter By Issues
All Issue Vol 7, No 1 (2026): March Vol 6, No 2 (2025): September Vol 6, No 1 (2025): March Vol 5, No 2 (2024): September Vol 5, No 1 (2024): March Vol 4, No 2 (2023): September Vol 4, No 1 (2023): March Vol 3, No 2 (2022): September Vol 3, No 1 (2022): March Vol 2, No 2 (2021): September Vol 2, No 1 (2021): March Vol 1, No 2 (2020): September Vol 1, No 1 (2020): March More Issue