cover
Contact Name
Hairani
Contact Email
ijecsa@universitasbumigora.ac.id
Phone
+6287839793970
Journal Mail Official
ijecsa@universitasbumigora.ac.id
Editorial Address
Universitas Bumigora Jl. Ismail Marzuki-Cilinaya-Cakranegara-Mataram 83127
Location
Kota mataram,
Nusa tenggara barat
INDONESIA
Jurnal: International Journal of Engineering and Computer Science Applications (IJECSA)
Published by Universitas Bumigora
ISSN : -     EISSN : 28285611     DOI : https://doi.org/10.30812/ijecsa.v1i2
Core Subject : Science,
Description of Journal : The International Journal of Engineering and Computer Science Applications (IJECSA) is a scientific journal that was born as a forum to facilitate scientists, especially in the field of computer science, to publish their research papers. The 12th of the 12th month of 2021 is the historic day of the establishment of the IJECSA International Journal. The initial idea of ​​forming the IJECSA Journal was based on the thoughts and suggestions of Experts and Lecturers of Computer Science at Bumigora University Mataram-Lombok. This journal covers all areas of computer science research, and studies literature including hardware, software, computer systems organization, computational theory, information systems, computational mathematics, data mining and data science, computational methodology, computer applications, machine learning, and learning technologies. computer. The initial publication of the IJECSA journal is 2 editions in one year, and this will continue to be reviewed based on the number of submitted papers and will increase the number of editions based on the number of submitted papers. Incoming papers will be reviewed by experts in the field of computer science from various countries. We, on behalf of the Editors, ask researchers from all fields of computer science to contribute to the publication of the IJECSA Journal. Topics covered include Computational Mathematics Data Science Computer Applications Information Systems Learning Science And Technology Network Architectures And Protocols Computer Network Education Computer Distance Learning Cloud Computing Cluster Computing Distributed Computing E-Commerce Protocols Automata Theory Game Theory. E-Health Biometric Security And Artificial Intelligence Cryptography And Security Protocols Authentication And Identification Modulation/Coding/Signal Processing Network Measurement And Management Bayesian Networks, Fuzzy And Rough Set Biometric Security And Artificial Intelligence Cryptography And Security Protocols Image Processing And Computer Vision Authentication And Identification Bayesian Networks Fuzzy And Rough Set Mobile System Security Ubiquitous Computing Security Sensor And Mobile Ad Hoc Network Security Security In Social Networks Security For Web Services Security In Wireless Network Security For Grid Computing Security For Web Services Security For Personal Data And Databases Management Of Computing Security Intelligent Multimedia Security Service Computer Applications In Engineering And Technology Computer Control System Design Cad/Cam, Cae, Cim And Robotics Computer Applications In Knowledge-Based And Expert Systems Computer Applications In Information Technology And Communication Computer-Integrated Material Processing (Cimp) Computer-Aided Learning (Cal) Computer Modelling And Simulation Man-Machine Interface Software Engineering And Management Management Techniques And Methods Human Computer InteractionTopics covered include Computational Mathematics Data Science Computer Applications Information Systems Learning Science And Technology Network Architectures And Protocols Computer Network Education Computer Distance Learning Cloud Computing Cluster Computing Distributed Computing E-Commerce Protocols Automata Theory Game Theory. E-Health Biometric Security And Artificial Intelligence Cryptography And Security Protocols Authentication And Identification Modulation/Coding/Signal Processing Network Measurement And Management Bayesian Networks, Fuzzy And Rough Set Biometric Security And Artificial Intelligence Cryptography And Security Protocols Image Processing And Computer Vision Authentication And Identification Bayesian Networks Fuzzy And Rough Set Mobile System Security Ubiquitous Computing Security Sensor And Mobile Ad Hoc Network Security Security In Social Networks Security For Web Services Security In Wireless Network Security For Grid Computing Security For Web Services Security For Personal Data And Databases Management Of Computing Security Intelligent Multimedia Security Service Computer Applications In Engineering And Technology Computer Control System Design Cad/Cam, Cae, Cim And Robotics Computer Applications In Knowledge-Based And Expert Systems Computer Applications In Information Technology And Communication Computer-Integrated Material Processing (Cimp) Computer-Aided Learning (Cal) Computer Modelling And Simulation Man-Machine Interface Software Engineering And Management Management Techniques And Methods Human Computer Interaction
Articles 78 Documents
Assessing Twitter User Sentiment Regarding Divorce Issues Using the Random Forest Method Muhamad Azwar; I Putu Hariyadi; Raisul Azhar
International Journal of Engineering and Computer Science Applications (IJECSA) Vol. 4 No. 2 (2025): September 2025
Publisher : Universitas Bumigora Mataram-Lombok

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/ijecsa.v4i2.4980

Abstract

The issue of divorce remains a complex and sensitive topic within Indonesian society, influenced by various factors such as repeated disputes, domestic violence, lack of harmony, financial difficulties, and other socio-cultural aspects. With the rise of social media, particularly Twitter, public discussions regarding divorce have become more widespread, allowing individuals to express their opinions and sentiments on the subject. These diverse perspectives create a wealth of sentiment data that can be analyzed to understand public perception and societal trends related to divorce. This study aims to classify public sentiment on divorce-related discussions using the Random Forest algorithm, providing insight into how people perceive and react to divorce issues. The research adopts a quantitative approach with a case study framework. The methodology involves data collection through web scraping techniques to gather approximately 1500 tweets containing discussions on divorce. The collected data is then preprocessed, including text cleaning, tokenization, and feature extraction, before being used to train and evaluate the Random Forest model. Sentiments are classified into three categories: negative, neutral, and positive. The classification model's performance is assessed using accuracy and F1-score metrics derived from the confusion matrix to determine its effectiveness in categorizing sentiments. Experimental results indicate that the Random Forest algorithm achieves an accuracy of 70%. The relatively low accuracy is attributed to the imbalance in sentiment class distribution, where negative sentiments dominate while positive sentiments are underrepresented. This imbalance affects the model's ability to predict positive sentiments effectively. The implications of this research contribute to a better understanding of public sentiment dynamics regarding divorce, which can be beneficial for policymakers, psychologists, and social researchers in analyzing societal attitudes towards marital dissolution.
Feature Extraction in Eye Images Using Convolutional Neural Network to Determine Cataract Disease Fitra Rizki Ramdhani; Khasnur Hidjah; Muhammad Zulfikri; Hairani Hairani; Mayadi Mayadi; Ni Gusti ayu Dasriani; Juvinal Ximenes Guterres
International Journal of Engineering and Computer Science Applications (IJECSA) Vol. 4 No. 2 (2025): September 2025
Publisher : Universitas Bumigora Mataram-Lombok

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/ijecsa.v4i2.5064

Abstract

The eye is one of the vital human senses and serves as the main organ for vision. One of the visual impairments that requires special attention is blindness, and cataracts are a major cause of it. A cataract is a condition in which the eye’s lens becomes cloudy due to changes in the lens fibers or materials inside the capsule. This cloudiness blocks light from entering the eye and reaching the retina, significantly interfering with vision. Early detection of cataracts is essential to prevent blindness. An efficient image-based classification model is needed for cataract detection. This study aims to test the Convolutional Neural Network (CNN) model for early cataract detection by exploring the use of several optimization algorithms: Adaptive Moment Estimation (Adam), Root Mean Square Propagation (RMSprop), Adaptive Gradient Algorithm (AdaGrad), and Stochastic Gradient Descent (SGD). The research method follows an experimental approach, where eye image datasets are trained using the same CNN architecture but with different parameter configurations. The results show that the Adam optimizer, with a data split of 70% for training, 15% for validation, and 15% for testing over 50 epochs, produced the best results, achieving accuracies of 94%, 93%, and 93%, respectively. Other optimizers performed reasonably well but could not match Adam's stability and accuracy. The implication of this research is that the choice of optimizer and hyperparameter configuration plays a crucial role in improving the performance of image-based cataract detection models.
Handling Imbalanced Data in K-Nearest Neighbor Algorithm using Synthetic Minority Oversampling Technique-Nominal Continuous Anjani Anjani; Hayati, Memi Nor; Surya Prangga
International Journal of Engineering and Computer Science Applications (IJECSA) Vol. 4 No. 2 (2025): September 2025
Publisher : Universitas Bumigora Mataram-Lombok

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/ijecsa.v4i2.5142

Abstract

Classification is a part of data mining that aims to predict the class of data using a trained machine learning model. K-Nearest Neighbor (K-NN) is one of the classification methods that uses the concept of distance to the nearest neighbor in creating classification models. However, K-NN has limitations in handling imbalanced class distributions. This core problem can be addressed by applying a class balancing technique. One such technique is the Synthetic Minority Oversampling Technique for Nominal and Continuous (SMOTE-NC), which is suitable for datasets containing both nominal and continuous variables. The aim of this research is to classify Honda motorcycle loan customer data at Company Z using the K-NN method combined with SMOTE-NC to address data imbalance. This research method is experimental, using a 10-fold cross-validation approach to partition training and testing data. The input variables include gender, occupation, length of installment, income, installment amount, motorcycle price, and down payment, while the output variable is payment status (current or non-current). The results of this research are: the optimal K value for classification using K-NN with SMOTE-NC is K = 1, with an average APER (Average Probability of Error Rate) of 0.143. The best result is found in subset 8 with an APER value of 0.033. In this subset, out of 61 data points, 34 current-status customers are correctly classified as current, and 25 non-current-status customers are correctly classified as non-current, with only one misclassification in each class. The conclusion of this study is that the combination of SMOTE-NC and K-NN (K=1) provides high classification accuracy for imbalanced data, and can be effectively used to support credit risk assessment in motorcycle financing.  
Computational Aesthetics in Improving Regional Election Mascot Branding Using Hue Saturation Value Method Hasbullah, Hasbullah; Swandi, I Wayan; Udayana, Anak Agung Gde Bagus; Dewi, Alit Kumala
International Journal of Engineering and Computer Science Applications (IJECSA) Vol. 4 No. 2 (2025): September 2025
Publisher : Universitas Bumigora Mataram-Lombok

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/ijecsa.v4i2.5159

Abstract

The digital era has a visual appeal that plays a crucial role in strengthening identity and public involvement in political campaigns, particularly in the election of the regional head of Mataram City. The role of visual mascots is important in attracting public attention. Through the intensity of color in digital media, it can attract attention and persuade the public to like it, thus building trust in the branding of the Mataram city election. However, the deviation value from the dominant color intensity in the Mataram City election mascot on the computer screen remains unclear. The core issue lies in identifying the exact value of the color intensity in the mascot design, which serves as a digital aesthetic element in strengthening the branding identity of the Mataram City election. This study aims to analyze the color intensity of the mascot design as a reflective attraction in the regional political campaign in Mataram City. The method used is Hue, Saturation, Value (HSV), with cultural and psychological color analysis image processing techniques to attract public participation and perception. The results of the study indicate that the color intensity based on HSV segmentation increases. The average color Hue has a deviation of 0.0319, Saturation has a deviation of 0.0255, and Value has a deviation of 0.9409, all of which are attributed to the dominant color in the mascot design on the computer screen. The HSV color intensity in the design of the Mataram city election mascot, especially on the screen, has an average value that intersects with each other, resulting in unity and forming an aesthetically pleasing visual. In conclusion, the brightness of the dominant color is a crucial aspect of creating aesthetic elements that capture the audience's attention. The implications of the study's results serve as a basic reference for creating graphic designs using computer technology. 
Animation Design Stage in Merarik as a Medium for Introducing Culture and Customs Satria, Christofer; Raharja, I Gede Mugi; Suteja, I Kt; Swandi, I Wayan
International Journal of Engineering and Computer Science Applications (IJECSA) Vol. 4 No. 2 (2025): September 2025
Publisher : Universitas Bumigora Mataram-Lombok

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/ijecsa.v4i2.5161

Abstract

The creative industry today, animation is one of the popular media used by many entertainment industries and to introduce the customs and culture of a region. Animation is a process in which an image or object is manipulated to create a predetermined movement flow. Merarik is the escape or kidnapping of a girl from the supervision of her guardian and her social environment has been formed as a cultural heritage that is passed down from generation to generation for the Sasak people in general and merarik has several stages that must be passed through to run it. The purpose of this design is where the designer wants to provide information about the meaning and stages in the design. The methodology used in this design is the pipeline method, which is a method that includes several stages (pre-production, production and post-production). The results of this design are in the form of animations of the stages in merarik which are designed with 2D techniques as a medium that explains the process of elopement (merarik) in Sasak culture. Animation is made with the limited animation genre which is usually done in Japanese animated films. The implications of the results of this study as a medium for learning and preserving the Merarik culture which has recently been rarely found among the Sasak people
Clustering Regency in Kalimantan Island Based on People's Welfare Indicators Using Ward's Algorithm with Principal Component Analysis Optimization Ningsih, Eva Lestari; Mahmuda, Siti; Hayati, Memi Nor
International Journal of Engineering and Computer Science Applications (IJECSA) Vol. 4 No. 2 (2025): September 2025
Publisher : Universitas Bumigora Mataram-Lombok

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/ijecsa.v4i2.5363

Abstract

Cluster analysis is used to group objects based on similar characteristics, so that objects in one cluster are more homogeneous than objects in other clusters. One method that is widely used in hierarchical clustering is Ward's algorithm. This method works by minimizing the sum of squared distances between objects in one cluster (within-cluster variance) to produce optimal clustering. However, one important assumption in using this method is that there is no high correlation between variables, or in other words, the data must be free from multicollinearity. Multicollinearity can cause distortion in distance calculation, resulting in less accurate clustering results. To overcome this problem, a Principal Component Analysis (PCA) approach is used to reduce the dimension and eliminate the correlation between variables by forming several mutually independent principal components. This research aims to cluster 56 districts/cities in Kalimantan Island based on 19 indicators of people's welfare in 2023, using Ward's algorithm optimized through PCA. Validation of clustering results is done using the Silhouette Coefficient value to assess the quality of clustering. This research method is a combination of Principal Component Analysis (PCA) and hierarchical clustering using Ward’s algorithm. PCA was applied to reduce 19 welfare-related indicators into four principal components that retained most of the essential information in the dataset. The clustering process based on these components resulted in two optimal clusters, as determined by a Silhouette Coefficient value of 0.651, which indicates a moderately strong cluster structure. The results of this research are that the first cluster consists of 47 districts/cities characterized by relatively low welfare levels, while the second cluster comprises 9 districts/cities with comparatively higher welfare conditions. These findings imply the existence of considerable disparities in welfare among regions on Kalimantan Island. The results can be used as a reference for policymakers in formulating more targeted and equitable development strategies
A Gaussian Mixture Model Approach to Profiling Stunting Risk Across Indonesian Provinces Rochayani, Masithoh Yessi; Utami, Iut Tri
International Journal of Engineering and Computer Science Applications (IJECSA) Vol. 4 No. 2 (2025): September 2025
Publisher : Universitas Bumigora Mataram-Lombok

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/ijecsa.v4i2.5395

Abstract

Stunting is still a major health problem in Indonesia, with notable differences between provinces. Although the national rate has decreased over time, regional gaps continue, emphasizing the role of data in helping to explain what contributes to the issue. This study aims to segment 38 provinces in Indonesia based on maternal and child health indicators associated with stunting prevalence. The variables used include the percentage of low birth weight (LBW) infants, the percentage of infants born short, the percentage of pregnant women with chronic energy deficiency (CED), exclusive breastfeeding (EBF) coverage, prevalence of diarrhea in toddlers, and prevalence of acute respiratory infections (ARI) in toddlers. The clustering analysis was performed using the Gaussian Mixture Model (GMM) with the number of clusters varied from 2 to 7. Model selection was based on the Bayesian Information Criterion (BIC), where the lowest value indicated the optimal model. The results show that the model with two clusters was selected, with a BIC value of 1358.24, which indicates the best balance between model fit and complexity. This clustering reveals that provinces are grouped based on similarities in maternal and child health profiles, not on geographic proximity, meaning that the GMM method does not rely on spatial location to form clusters.
Designing A Web-Based Content-Based Filtering Method for A Culinary Marketplace Shiddiq, Zulfikar; Suendri, Suendri; Sibarani, Fathiya Hasyifah
International Journal of Engineering and Computer Science Applications (IJECSA) Vol. 4 No. 2 (2025): September 2025
Publisher : Universitas Bumigora Mataram-Lombok

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/ijecsa.v4i2.5652

Abstract

The development of information technology has made various aspects of life easier, including product marketing through marketplace applications. In Pasar Bengkel Village, known as a culinary center, vendors have experienced a decline in the number of customers due to the operation of the Medan–Tebing Tinggi toll road, which has reduced visitor traffic. The purpose of this study is to design a marketplace application with a recommendation system that can help vendors increase product visibility and attract customers back. The research method is the application of a Content-Based Filtering-based recommendation system with the Term Frequency–Inverse Document Frequency (TF-IDF) algorithm to process product description data and generate relevant recommendations for users. The result of this study is a marketplace application that is able to provide personalized product recommendations based on the frequency of word occurrences in product descriptions using the TF-IDF technique. In conclusion, this application is expected to be an innovative solution in increasing the competitiveness of local culinary vendors by expanding their marketing reach and maintaining the sustainability of their businesses..