cover
Contact Name
Jumanto
Contact Email
jumanto@mail.unnes.ac.id
Phone
+628164243462
Journal Mail Official
sji@mail.unnes.ac.id
Editorial Address
Ruang 114 Gedung D2 Lamtai 1, Jurusan Ilmu Komputer Universitas Negeri Semarang, Indonesia
Location
Kota semarang,
Jawa tengah
INDONESIA
Scientific Journal of Informatics
ISSN : 24077658     EISSN : 24600040     DOI : https://doi.org/10.15294/sji.vxxix.xxxx
Scientific Journal of Informatics (p-ISSN 2407-7658 | e-ISSN 2460-0040) published by the Department of Computer Science, Universitas Negeri Semarang, 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. The SJI publishes 4 issues in a calendar year (February, May, August, November).
Articles 122 Documents
Development of School Exam Administration Based on LCDP with Scrum Method: An Innovation in Administrative Efficiency in Education Anggraeni, Lia; Dliyaul Haq, Muh; Harliati Putri Pertiwi
Scientific Journal of Informatics Vol. 11 No. 2: May 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i2.27

Abstract

Purpose: This study aims to explore the potential benefits of integrating innovative technology and agile methodologies, precisely the Scrum method and the AppSheet platform, to enhance the efficiency and effectiveness of school exam administration. The research seeks to address the constraints of manual exam administration and investigate the role of technology in providing practical and efficient solutions. Methods: The study was conducted at Sekolah Indonesia Kota Kinabalu, Sabah, Malaysia, utilizing the Scrum method with the AppSheet platform. The development of the school exam administration application with AppSheet, the low-code development platform (LCDP), using the Scrum method was carried out with a structured and adaptive approach. User stories and use case diagrams were employed to translate user insights into tangible visualizations, ensuring alignment with the intricate needs of the examination committee. Result: Implementing the Scrum methodology in the development process has proven effective in creating a tailored and efficient application for school exam administration. The application's design and functionality have been carefully crafted to meet the specific requirements of exam administration, including form-filling, data entry, PDF report generation, and user feedback collection. The user survey conducted as part of the development process has provided valuable insights into user experiences, guiding areas for improvement and ensuring a user-centric approach to application development. Novelty: This study contributes to the field by demonstrating the successful integration of agile methodologies and user-centric design principles in developing a comprehensive solution for school exam administration. The research highlights the potential of innovative technology to revolutionize exam administration for improved educational outcomes, emphasizing the significance of the Scrum methodology and the AppSheet platform in providing a structured yet adaptive approach to application development in the education sector.
Classification Model of Public Sentiments About Electric Cars Using Machine Learning Romadoni, Nurul; Siregar, Amril Mutoi; Kusumaningrum, Dwi Sulistya; Rohana, Tatang
Scientific Journal of Informatics Vol. 11 No. 2: May 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i2.1309

Abstract

Purpose: This research compared the accuracy level of six algorithms based on the ROC method and the Confusion Matrix evaluation on data regarding public sentiments towards electric cars. Methods: Data collection was conducted for data sourced from TikTok. Next, the data underwent text preprocessing (data cleaning and case folding) and text processing (stemming, tokenizing, stopword removal, word frequency, word relation, TF-IDF, scoring, and labeling). Modeling was then conducted using supervised (labeled) algorithms consisting of the Support Vector Machine (SVM), Decision Tree, Naive Bayes, Random Forest, K-Neighbor, and Logistic Regression. Finally, an evaluation was conducted (confusion matrix and ROC). Result: The results revealed that the Decision Tree algorithm with the Confusion Matrix and ROC evaluation obtained the highest result of 87%. The algorithm with the lowest result is KNN, which has an accuracy of 56%. The classification result for the neutral sentiment has a percentage of 57.1%, followed by negative sentiment at 26.8% and positive sentiment at 16.1%. The KNN algorithm is suitable for large and low-dimensional data, SVM is suitable for data with many features and clear separation between classes, and Naive Bayes is efficient for large datasets with many low-quality features. Additionally, the Random Forest algorithm could overcome overfitting and unbalanced data. Logistic regression is also suitable for linear data without assuming a certain distribution. The Decision Tree algorithm is good for complex data as it provides a visual explanation of predictions. In this study, the Decision Tree algorithm obtained high results because it has the best characteristics and is a linear technique. Novelty: This study found that based on the ROC method and the Confusion Matrix evaluation conducted, the Decision Tree algorithm is more accurate than the other algorithms studied.
Identifying Relevant Messages from Citizens in a Social Media Platform for Natural Disasters in Indonesia Using Histogram Gradient Boosting and Self-Training Classifier Yunita, Ariana; Ramadhan, Zhafran; Angelia Regina Dwi Kartika; Irawan, Ade
Scientific Journal of Informatics Vol. 11 No. 2: May 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i2.2287

Abstract

Purpose: This research aims to develop a classification model using histogram-based gradient boosting to identify relevant contextual tweets about disasters. This model can then be used for subsequent data cleaning stages. Methods: This study uses a semi-supervised approach to develop a classification model using histogram-based gradient boosting. The model is trained to identify and remove irrelevant tweets that are related to disasters and gathered from Twitter. Optimization techniques, such as the AdaBoost classifier, calibrated classifier, and self-training classifier, are used to enhance the model's performance. The goal is to accurately recognize and categorize relevant tweets for additional data analysis and decision-making. Result: The classification model that has been developed has achieved a high F1-score of 93.07%, which indicates its effectiveness in filtering disaster-related tweets that are relevant. This highlights the potential of the model to enable more precise aid distribution and faster decision-making in disaster response efforts. The successful implementation of the model also demonstrates its usefulness in utilizing social media data to enhance disaster management practices. Novelty: This research contributes to the analysis of social media through machine learning algorithms. By utilizing social media, specifically Twitter, as a valuable resource for disaster response efforts, this study tackles challenges related to data collection and analysis in disaster management. The classification of relevant tweets into different types of natural disasters offers opportunities to enhance stakeholder decision-making processes in disaster scenarios.
Hiragana Character Classification Using Convolutional Neural Networks Methods based on Adam, SGD, and RMSProps Optimizer Mulyono, Ibnu Utomo Wahyu; Kusumawati, Yupie; Susanto, Ajib; Sari, Christy Atika; Islam, Hussain Md Mehedul; Doheir, Mohamed
Scientific Journal of Informatics Vol. 11 No. 2: May 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i2.2313

Abstract

Purpose: Hiragana image classification poses a significant challenge within the realms of image processing and machine learning. Despite advances, achieving high accuracy in Hiragana character recognition remains elusive. In response, this research attempts to enhance recognition precision through the utilization of a Convolutional Neural Network (CNN). Specifically, the study explores the efficacy of three distinct optimizers like Adam, Stochastic Gradient Descent with Momentum (SGDM), and RMSProp in improving Hiragana character recognition accuracy. Methods: This research adopts a systematic approach to evaluate the performance of a Convolutional Neural Network (CNN) in the context of Hiragana character recognition. A meticulously prepared dataset is utilized for in-depth testing, ensuring robustness and reliability in the analysis. The study focuses on assessing the effectiveness of three prominent optimization methods: Stochastic Gradient Descent (SGD), RMSProp, and Adam. Result: The results of the model performance evaluation show that the highest accuracy was obtained from the RMSP optimizer with an F1-Score reaching 99.70%, while the highest overall accuracy was 99.87% with the Adam optimizer. The analysis is carried out by considering important metrics such as precision, recall, and F1-Score for each optimizer. Novelty: The performance results of the developed model are compared with previous studies, confirming the effectiveness of the proposed approach. Overall, this research makes an important contribution to Hiragana character recognition, by emphasizing the importance of choosing the right optimizer in improving the performance of image classification models.
Securing Digital Wallet Loyalty: Unveiling the Impact of Privacy and Security Utomo, Rio Guntur; Yasirandi, Rahmat
Scientific Journal of Informatics Vol. 11 No. 2: May 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i2.2423

Abstract

Purpose: The study investigates the fast-evolving fintech landscape, specifically the impact of digital wallets on the financial industry. It focuses on the competitive digital wallet market in Indonesia, examining how service quality influences user satisfaction and loyalty in a saturated market. By integrating a Security variable into the E-Servqual method, this research aims to offer a new perspective on assessing the effects of digital wallet services on user satisfaction and loyalty. Methods: This study employs the Modified E-Servqual model with an added Security variable to explore how service quality variables like Site Organization, Efficiency, Personal Needs, Privacy, Reliability, Responsiveness, Security, and User’s Friendliness impact customer satisfaction and loyalty in digital transactions. Surveying 287 digital wallet users, mostly GoPay, OVO, ShopeePay and DANA, the research provides a detailed analysis of these variables' effects on E-Customer Satisfaction and E-Customer Loyalty. Result: The findings show that digital wallet users value certain service quality aspects differently in terms of their impact on satisfaction and loyalty. While variables like Reliability, User’s Friendliness, Personal Needs, Privacy, Security, and Efficiency significantly influence user satisfaction, Site Organization and Responsiveness do not. This highlights the importance of security and efficiency in enhancing user satisfaction and loyalty in digital wallets. Novelty: The study's novel contribution is integrating a Security variable into the E-Servqual method, enhancing the assessment of digital wallets' inherent security risks. This integration provides a detailed analysis of how security impacts user satisfaction and loyalty, alongside other service quality factors. This systematic evaluation offers new insights for improving service quality, benefiting companies in the competitive digital wallet market, and informing future research on customer loyalty and provider success.
Comparative Analysis of YOLOv5 and YOLOv8 Cigarette Detection in Social Media Content Cinantya Paramita; Catur Supriyanto; Amalia; Khalivio Rahmyanto Putra
Scientific Journal of Informatics Vol. 11 No. 2: May 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i2.2808

Abstract

Purpose: Addresses the pressing public health concern of tobacco product portrayal on social media, which significantly influences the younger demographic by glamorizing smoking culture. The purpose is to compare the capabilities of YOLOv5 and YOLOv8 models in detecting and censoring cigarette-related imagery on social media platforms, aiming to reduce exposure among children and teenagers. Methods: Employing a dataset of 2,188 images collected from Twitter, this research undertook a comprehensive methodology involving data preprocessing, YOLOv5 and YOLOv8 model training, and rigorous evaluation. The study utilized mean Average Precision (mAP) and F1-Score metrics to evaluate the performance of YOLOv5 and YOLOv8 models, focusing on their precision, recall, and efficacy in detecting cigarette and cigarette pack objects. Result: The analysis highlighted YOLOv8's superiority, with a marginally higher mAP value of 0.933 compared to YOLOv5's 0.919, alongside enhanced precision and recall rates. This result underscores YOLOv8's advanced object detection capabilities, owing to its architectural innovations and anchor-free detection system. Additionally, the study confirmed the absence of significant overfitting or underfitting issues, indicating robust learning processes of the models. Novelty: Innovates in digital public health by using YOLOv5 and YOLOv8 models to automatically censor tobacco-related content on social media, effectively reducing youth exposure to such imagery. YOLOv8, in particular, exhibits marginally superior detection capabilities. The evaluation results surpass those of previous research on cigarette and cigarette burning detection, underscoring the study's significant contribution to future research and public health initiatives.
Performance Analysis of Support Vector Classification and Random Forest in Phishing Email Classification Umam, Chaerul; Handoko, Lekso Budi; Isinkaye, Folasade Olubusola
Scientific Journal of Informatics Vol. 11 No. 2: May 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i2.3301

Abstract

Purpose: This study aims to conduct a performance analysis of phishing email classification system using machine learning algorithms, specifically Random Forest and Support Vector Classification (SVC). Methods/Study design/approach: The study employed a systematic approach to develop a phishing email classification system utilizing machine learning algorithms. Implementation of the system was conducted within the Jupyter Notebook IDE using the Python programming language. The dataset, sourced from kaggle.com, comprised 18,650 email samples categorized into secure and phishing emails. Prior to model training, the dataset was divided into training and testing sets using three distinct split percentages: 60:40, 70:30, and 80:20. Subsequently, parameters for both the Random Forest and Support Vector Classification models were carefully selected to optimize performance. The TF-IDF Vectorizer method was employed to convert text data into vector form, facilitating structured data processing. Result/Findings: The study's findings reveal notable performance accuracies for both the Random Forest model and Support Vector Classification across varying data split percentages. Specifically, the Support Vector Classification consistently outperforms the Random Forest model, achieving higher accuracy rates. At a 70:30 split percentage, the Support Vector Classification attains the highest accuracy of 97.52%, followed closely by 97.37% at a 60:40 split percentage. Novelty/Originality/Value: Comparisons with previous studies underscored the superiority of the Support Vector Classification model. Therefore, this research contributes novel insights into the effectiveness of this machine learning algorithms in phishing email classification, emphasizing its potential in enhancing cybersecurity measures.
Multi-Layer Convolutional Neural Networks for Batik Image Classification Sinaga, Daurat; Jatmoko, Cahaya; Suprayogi, Suprayogi; Hedriyanto, Novi
Scientific Journal of Informatics Vol. 11 No. 2: May 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i2.3309

Abstract

Purpose: The purpose of this study is to enhance the classification of batik motifs through the implementation of a novel approach utilizing Multi-Layer Convolutional Neural Networks (CNN). Batik, a traditional Indonesian textile art form, boasts intricate motifs reflecting rich cultural heritage. However, the diverse designs often pose challenges in accurate classification. Leveraging advancements in deep learning, this research proposes a methodological framework employing Multi-Layer CNN to improve classification accuracy. Methods: The methodology integrates Multi-Layer CNN architecture with an image dataset comprising various batik motifs, meticulously collected and preprocessed for uniformity. The CNN architecture incorporates convolutional layers of different sizes (3x3, 5x5, and 7x7) to extract unique features from batik images. Training options, including the Adam optimizer and validation frequency, are optimized based on parameters to enhance model efficiency and effectiveness. Result: Results from the experimentation demonstrate significant improvements in classification accuracy, with an overall accuracy rate of 90.88%. Notably, precision and recall scores for individual batik motifs, such as Motif Cual Bangka and Motif Rumah Adat Belitung, reached remarkable levels, showcasing the efficacy of the proposed approach. Novelty: This study contributes novelty through the integration of Multi-Layer CNN in batik classification, offering a robust and efficient method for identifying intricate batik motifs. Additionally, the research presents a pioneering application of deep learning techniques in preserving and promoting traditional cultural heritage, thereby bridging the gap between tradition and modern technology.
Comparative Analysis of K-Medoids and Purity K-Medoids Methods for Identifying Accident-Prone Areas in North Aceh Regency Hasdyna, Novia; Dinata, Rozzi Kesuma
Scientific Journal of Informatics Vol. 11 No. 2: May 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i2.3433

Abstract

Purpose: This study aimed to conduct a comprehensive comparative analysis between K-Medoids and Purity K-Medoids clustering methods for identifying accident-prone areas in North Aceh Regency. The analysis was carried out to provide valuable insights for policymakers and stakeholders to implement targeted interventions as well as improve road safety measures in the region. Methods: This study compared the performance of K-Medoids and Purity K-Medoids, on accident-prone area data in North Aceh Regency. The algorithm performance was measured using the Davies-Bouldin Index (DBI) method, where a low value signifies superior performance. Additionally, the number of iterations produced by K-Medoids and Purity K-Medoid methods were compared, with lower iterations indicating better performance. Result: The results showed that Purity K-Medoids had superior performance with an average of 2 iterations and DBI value of 0.7847 across 10 testing runs, while K-Medoids obtained 13.4 iterations and 1.5128, respectively. Novelty: The study offers valuable insights into the effectiveness and efficiency of clustering methods for identifying accident-prone areas, as guides for policymakers and stakeholders in implementing targeted interventions to improve road safety measures. Additionally, the results provide a methodological framework for evaluating clustering algorithms in similar geographical contexts, enhancing the understanding of their applicability and performance in real-world scenarios.
Exploring Data Analytics in Attendance Systems: Unveiling Machine Learning Techniques, Patterns, Practices, and Emerging Trends Santoso, Joseph Teguh; Manongga, Danny; Setyawan, Iwan; Purnomo, Hindriyanto Dwi; Hendry
Scientific Journal of Informatics Vol. 11 No. 2: May 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i2.3438

Abstract

Purpose: The research aims to identify patterns and trends in attendance management through the application of reward and punishment systems as innovative solutions for improving employee attendance and well-being. Methods: This research utilizes a descriptive analysis approach with the application of Machine Learning (ML) techniques to enhance the accuracy of attendance pattern prediction and ML models for the classification of emerging trends and patterns. Research data were obtained through the company's attendance system and divided into two segments (80% for training and 20% for testing) while maintaining a balanced class proportion, then processed using SPSS and Python software with the Scikit-learn library. Result: The results of the study show that employee attendance is increased from 86.52% to 90.44% when the reward and punishment method is applied to the employee attendance system. Proper reward allocation can increase employee motivation to adhere to work schedules and consistently attend, while punishment tends to lead to lower attendance rates. Novelty: This research emphasizes the optimization of attendance management through data analytics approaches and the implementation of advanced technology in attendance systems with the application of ML techniques to analyze attendance data comprehensively and detect significant patterns.

Page 1 of 13 | Total Record : 122