cover
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
sji@mail.unnes.ac.id
Editorial Address
-
Location
Kota semarang,
Jawa tengah
INDONESIA
Scientific Journal of Informatics
ISSN : 24077658     EISSN : 24600040     DOI : -
Core Subject : Science,
Scientific Journal of Informatics published by the Department of Computer Science, Semarang State University, a scientific journal of Information Systems and Information Technology which includes scholarly writings on pure research and applied research in the field of information systems and information technology as well as a review-general review of the development of the theory, methods, and related applied sciences.
Arjuna Subject : -
Articles 564 Documents
Zachman Enterprise Architecture Planning (Study Case: E –Government’s General Election Services on Karadenan Sub-District in Bogor Regency Armada Rizki; Elisa Susanti; Wina Erwina
Scientific Journal of Informatics Vol 10, No 4 (2023): November 2023
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v10i4.47691

Abstract

Purpose: This study examines enterprise architecture planning using the Zachman Framework as an effort to automate citizen administration in Bogor Regency. Furthermore, this planning is a solution in the simultaneous step of preparing voter lists down in general election commission data, especially connected to the Citizen Administration Bureau in Karadenan Sub District as a pilot plant project. This study aims to analyze enterprise architecture planning for citizen administration involved in the General Election Commission on collection, updating, and changing citizen data in Karadenan Sub District in Bogor Regency.Methods: Data analysis was carried out from 122 heads of neighborhood units and 19 heads of residential units in Karadenan Subdistrict Bogor Regency. After that, using a qualitative method using the Zachman Framework, an Enterprise Architecture Planning of Citizen Administration was designed.Result: According to the results, this study provides a new role model-based service scheme for citizen administration, especially in election conditions.Novelty: The results of this study are valuable for the government in implementing new digital citizen administration services, especially empowering general elections by providing high-quality data on voters.
Voting Classifier Technique and Count Vectorizer with N-gram to Identifying Hate Speech and Abusive Tweets in Indonesian Riza Arifudin; Dandi Indra Wijaya; Budi Warsito; Adi Wibowo
Scientific Journal of Informatics Vol 10, No 4 (2023): November 2023
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v10i4.46633

Abstract

Purpose: The objective of this study is to identify hate speech and abusive tweets in Indonesian using a Voting Classifier technique and Count Vectorizer with N-grams. Voting Classifier technique involves combining multiple classifiers like Random Forest and Support Vector Machines to improve classification accuracy.Methods: This research begins by preprocessing the data. Voting classifier uses Support Vector Machine algorithm and Random Forest algorithm. Support Vector Machine and Random Forest serve as the estimators for the voting classifier. As for feature extraction, N-gram and count vectorizer were employed. The effectiveness of the suggested procedures is the desired outcome.Result: Combining the Voting Classifier approach with Count Vectorizer feature extraction and using 1 gram of N-grams, or 82.50%, resulted in the best accuracy. From this study, it can be inferred that the approach employed to identify hate speech and abusive tweets is extremely practical.Novelty: Combining multiple classifiers and using feature extraction techniques like count vectorizer and N-gram with machine learning algorithms can be used for sentiment analysis to differentiate between hate speech and abusive tweets.
Revolutionizing Healthcare: Comprehensive Evaluation and Optimization of SVM Kernels for Precise General Health Diagnosis Wardatus Sholihah; Ade Silvia Handayani; Sarjana Sarjana
Scientific Journal of Informatics Vol 10, No 4 (2023): November 2023
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v10i4.46430

Abstract

Purpose: This study is driven by a two-fold objective. Firstly, it seeks to optimize the Support Vector Machine (SVM) algorithms in machine learning, comprehensively evaluating diverse SVM kernel variants to enhance their versatility and applicability across various domains, which is beyond the healthcare sector. Secondly, in the context of general health diagnosis, it aims to assess the suitability of SVM kernels for achieving precision in predictive modeling. The choice of SVM is rooted in its effectiveness, proven in classification and regression within data mining. SVMs excel in high-dimensional problem classification, demonstrating superior accuracy, making them invaluable in refining machine learning methodologies and advancing diagnostic systems, promising implications for healthcare and beyond. The chosen SVM model, distinguished by its exceptional performance, is then implemented in real-world applications, particularly in wireless, non-invasive healthcare devices. This deployment signifies a substantial stride toward advancing healthcare practices and holds promising implications for various fields.Methods: Data for this study was collected from publicly accessible datasets on Kaggle, encompassing a comprehensive array of general health-related information. This dataset, comprised of clinical data and vital signs data, underwent meticulous preprocessing, such as data cleaning, feature extraction, and categorization of health status into ‘healthy’ and ‘requiring further attention’. Subsequently, predictive models were constructed employing Support Vector Machine (SVM) algorithms with various kernel functions, such as Linear, RBF, Polynomial, and Sigmoid. They were trained and tested on the preprocessed dataset to assess their efficacy in general health diagnosis. Model performance was rigorously evaluated using established metrics, including accuracy, precision, recall, F-1 score, Area Under the Curve (AUC), Receiver Operating Characteristic (ROC) curve, and cross-validation. The selection of the most efficacious SVM kernel was governed by stringent adherence to industry standards and best practices, ensuring optimal integration into health diagnostic systems. The chosen model was tested using new datasets obtained from wireless non-invasive healthcare devices and the pre-existing AHD application. Hyperparameter tuning was meticulously executed to maximize accuracy, ensuring the effectiveness of the evaluation process.Results: The results demonstrate that the Polynomial kernel was selected as the body health diagnostic model instead of the Linear, RBF, and Sigmoid kernels. This kernel has a training time of 0.8 seconds, a testing time of 0.1 seconds, accuracy scores of 97%, precision of 97%, recall of 97%, F-1 score of 97% for training metrics, and accuracy scores of 99%, precision of 99%, recall of 99%, and F-1 score of 99% for testing metrics. The accuracy of the polynomial kernel model decreased to 0.88 on new datasets; adjusting the hyperparameter C to C = 100 resulted in the highest accuracy of 0.945.Novelty: This study introduces a pioneering approach by rigorously optimizing Support Vector Machine (SVM) algorithms, notably the innovative application of the Polynomial kernel in general health diagnosis. Unlike traditional kernels, the Polynomial kernel exhibited exceptional accuracy (up to 99%) and precision. Furthermore, the study’s unique methodology, combining industry standards and meticulous hyperparameter tuning, ensures seamless integration into real-world healthcare systems. The deployment of this optimized model in wireless non-invasive healthcare devices signifies a groundbreaking advancement, highlighting a novel synthesis of theoretical innovation and practical implementation in machine learning for healthcare.
UI/UX Design Prototype for Enhancing User Experience using User-Centered Method Egia Rosi Subhiyakto; Yani Parti Astuti
Scientific Journal of Informatics Vol 10, No 4 (2023): November 2023
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v10i4.47528

Abstract

Purpose: The teaching matrix often relies on conventional methods involving explanations on a board. It makes students easily bored and relatively focused for only a short period. Integrating multimedia features such as text, colors, and sound might enhance students' comfort and engagement in the learning matrix. In this study, we discuss how to design low-fidelity and high-fidelity prototypes to enhance the comfort of the learning matrix and give a solution to manage course and communication between teachers and students.Methods: We employed the User-Centered Design method, focusing on users as the central design consideration. The User-Centered Design process involves the analysis of user needs and context, followed by requirements identification, design solutions, and solution evaluation. Results: Based on the testing results, we scored 86.25%, categorizing it as "acceptable" with a grade of A and an adjective rating of "excellent." Meanwhile, the usability testing resulted in a score of 85.6%.Novelty: The main contribution to this research is proposing a new design for the UI/UX of the matrix learning application. The generated design can be recommended for implementing a matrix learning application.
Performance of the Decision Tree Algorithm in the Classification of Edible and Poisonous Mushrooms with Information Gain Optimization Arif Rifan Rudiyanto; Pujiono Pujiono; M. Arief Soeleman; Mustagfirin Mustagfirin
Scientific Journal of Informatics Vol 10, No 4 (2023): November 2023
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v10i4.47864

Abstract

Purpose: This study proposes a new mushroom classification model using a decision tree algorithm to classify edible and poisonous mushrooms by applying machine learning whose algorithm has better performance in terms of accuracy.  Methods: The information gain technique was applied at the data feature selection stage to increase the accuracy of the suggested decision tree model. This study used the same mushroom dataset as that employed in previous studies. Result: The proposed decision tree model in this study can classify edible and poisonous mushrooms with a good accuracy of 99.61%, outperforming a previous study whose final accuracy was 97.05%. Novelty: The novelty of this s is the use of information gain as a filter technique at the feature selection stage. This study aims to optimize the previous mushroom classification models with improved accuracy.
Comparative Study of Imbalanced Data Oversampling Techniques for Peer-to-Peer Landing Loan Prediction Muzayanah, Rini; Lestari, Apri Dwi; Jumanto, Jumanto; Prasetiyo, Budi; Pertiwi, Dwika Ananda Agustina; Muslim, Much Aziz
Scientific Journal of Informatics Vol 11, No 1 (2024): February 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i1.50274

Abstract

Purpose: Data imbalances that often occur in the classification of loan data on the Peer-to-Peer Lending platform cancause algorithm performance to be less than optimal, causing the resulting accuracy to decrease. To overcome thisproblem, appropriate resampling techniques are needed so that the classification algorithm can work optimally andprovide results with optimal accuracy. This research aims to find the right resampling technique to overcome theproblem of data imbalance in data lending on peer-to-peer landing platforms.Methods: This study uses the XGBoost classification algorithm to evaluate and compare the resampling techniquesused. The resampling techniques that will be compared in this research include SMOTE, ADACYN, Border Line, andRandom Oversampling.Results: The highest training accuracy was achieved by the combination of the XGBoost model with the Boerder Lineresampling technique with a training accuracy of 0.99988 and the combination of the XGBoost model with the SMOTEresampling technique. In accuracy testing, the combination with the highest accuracy score was achieved by acombination of the XGBoost model with the SMOTE resampling technique.Novelty: It is hoped that from this research we can find the most suitable resampling technique combined with theXGBoost sorting algorithm to overcome the problem of unbalanced data in uploading data on peer-to-peer lendingplatforms so that the sorting algorithm can work optimally and produce optimal accuracy.
Enhancing Transportation Route Optimization Through Genetic Algorithm-Based Vehicle Routing Problem Method Sidiq Syamsul Hidayat; Bagaskara Bagaskara; Amin Suharjono; Irfan Mujahidin
Scientific Journal of Informatics Vol 10, No 4 (2023): November 2023
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v10i4.47049

Abstract

Purpose: The purpose of this study is to identify effective and efficient waste collection route for cost savings. The focus is on Tembalang District, where waste management has been compromised due to inefficient transportation.Methods: The study employs genetic algorithm to ascertain the optimal routes for waste collection vehicles. This method seeks to design an improved transportation system, taking waste from transfer stations (TPS) to landfills.Results: The devised waste transport model from the study demonstrated an optimized route for Tembalang Sub-District, with a total distance of 17.90 km and took 49 minutes. This contrasts with the existing route defined by the Sanitation Department, which spans 18.20 km and requires 1 hour and 15 minutes.Novelty: Innovative application of the Vehicle Routing Problem method coupled with the Genetic Algorithm. This approach resulted in a significant reduction of time (by 35%) compared to traditional routing systems, and thus minimizing the number of waste collection vehicles required and enhancing overall waste management in Semarang.
Forensic Tools Comparison on File Carving using Digital Forensics Research Workshop Framework La Jupriadi Fakhri; Imam Riadi; Anton Yudhana
Scientific Journal of Informatics Vol 10, No 4 (2023): November 2023
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v10i4.46901

Abstract

Purpose: Cybercrime is the misuse of technology as a tool or medium in committing crimes such as hacking, stealing, deleting, hiding, and destroying information. Cybercriminals tend to delete, hide, and format all the data collected to eliminate traces of digital evidence. In digital forensics, file carving techniques can overcome data loss from storage media. This study aims to determine the results of the file carving process in uncovering digital evidence and evaluating the performance of digital forensic software, including Foremost and Scalpel, based on 3 assessment parameters.Methods: In this investigation, the Digital Forensics Research Workshop (DFRWS) research method is used with the following stages: Identification, Preservation, Collection, Examination, Analysis, and Presentation. Results: Comparison results of the data obtained from Foremost and Scalpel forensic tools are based on three primary parameters including the speed of the recovery process, the number of successfully recovered files, and the identical hash value. The Foremost tool managed to recover the carving files in 1 minute and 3 seconds, showing a success rate of 85% with a hash value similarity rate of 70.59%. On the other hand, Scalpel recovered the carving file in 2 minutes 17 seconds, achieving a success rate of 65% with a hash value similarity rate of 7.69%.Novelty: This data results from the performance of both forensic tool applications in collecting digital evidence from Flash disk storage media.
Classification of Early Stages of Lung Cancer based on First and Second Order Statistical Variations using Decision Tree Method Soeparmi Soeparmi; Umi Salamah; Arnita Ayu Ningrum; Mohtar Yunianto
Scientific Journal of Informatics Vol 10, No 4 (2023): November 2023
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v10i4.48026

Abstract

Purpose: This research aims to produce the best performance in identifying early-stage lung cancer class through CT-Scan image analysis using the decision tree classification method and to determine the results of the best classification performance from the variations carried out.Methods: Five steps in the CT-Scan image classification process for early-stage lung cancer class based on tumor density measurements. First, image data preparation where the image data used was 280 CT-Scan images with a pixel size of 607 x 607 and PNG format taken from the LIDC-IDRI database at https://www.cancerimagingarchive.net/ with a total of 1010 CT-Scan data scans. Second, the grayscaling stage converts the RGB image to a grayscale. Third, combining a high pass filter and Gaussian smoothing filter method is used to remove salt pepper noise and to smooth the image. Fourth, the feature extraction stage uses first and second-order statistics with 22 features used. The fifth is the classification stage using a decision tree, which is then validated using the k-fold method with k=10 so that all image data can be tested thoroughly.Result: The accuracy rate at the training stage was 90.51%, and at the testing stage was 89.99%. Stage I lung cancer detection program through CT-Scan imagery was successfully created with the highest PSNR value proven to optimize the accuracy level, precision, and recall in the testing phase results of 89.99%, 91.24%, and 89.64%.Novelty: Based on previous research searches, no one had used machine learning to classify early-stage lung cancer. Punithavathy et al. (2015) and Meliala (2021) stated that early detection of lung cancer can increase survival by 60%-70%. This research will produce a new method for determining early-stage lung cancer. 
Applying Structural Equational Model (SEM) to Analysis of Perceived Social Media Influence on Intention to Buy Online Store by Consumer Trust and Hedonic Brand Image Wisnalmawati, Wisnalmawati; Annegrat, Ahmed Mohamed; Rahadini, Marjam Desma; Sanosra, Abadi; Suryono, Agus
Scientific Journal of Informatics Vol 11, No 1 (2024): February 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i1.47859

Abstract

Purpose: This research aims to examine the influence of social media perceptions which directly influence repurchase intentions which are mediated by consumer trust and hedonic brand image in an online shop by applying the Structural Equational Model (SEM) with Partial Lease Square (Smart PLS) technique.Methods: This research examines the effect of social media perception intervention on repurchase intentions which is analyzed with a population taken from consumers in four marketplaces, including Lazora.Com, Lazada.com, and Blibli.com. bukalapak.com. The number of samples in this research was 80 respondents. The sampling technique uses accidental, namely distributing questionnaires to consumers who meet in WhatsApp groups. The data was tested with the variable social media perception, purchase intention, consumer trust, and hedonic brand image. Data were analyzed using the Structural Equational Model (SEM) with Partial Lease Square (Smart PLS) technique.Result: The research results show that the indicator variables proposed to test the influence of perceived social media on repurchase decisions. The Q2 predictive relevance value shows that the perceived social and consumer trust contributes 0.7647 towards the intention to buy. The rest which is 0.2353 is affected by the other variable. Therefore, social media perceptions do not influence repurchase intentions, but social media perceptions influence repurchase intentions which are mediated by consumer trust and Hedonic Brand Image in an online shop.Research limitation: We found that there are perceived social media influence repurchase intention to buy mediated by consumer trust and Hedonic Brand Image in an online store. This will contribute to other research, creating Consumer trust and a Hedonic Brand image is very important to increase repurchase intention to buy in an online store. Practical implications – The findings of this study may contribute to consumer behavior models, online stores, and Tripple duties.Novelty: The novelty of this research is that consumer trust and hedonic brand Image can increase the intention to buy in an online store.