cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
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
Published by Universitas Negeri Semarang
ISSN : 24077658     EISSN : 24600040     DOI : https://doi.org/10.15294/sji.vxxix.xxxx
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering
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).
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 161 Documents
 1   2   3   4   5 
OffensiveRezzer: A Novel Black-Box Fuzzing Tool for Web API Putera, Danar Gumilang; Harwahyu, Ruki
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.v11i2.4631

Abstract

Purpose: The purpose of this study is to introduce OffensiveRezzer, a novel tool designed for black-box fuzzing on Web APIs, and to evaluate its effectiveness in detecting errors, particularly focusing on errors related to input validation implementation. Methods: We introduced OffensiveRezzer and conducted a comparative analysis against existing fuzzing tools such as EvoMaster, Schemathesis, RestTestGen, Restler, and Tcases to assess its performance. Fuzzing experiments were carried out on a custom Web API application with different input validation levels, namely no input validation, partial input validation, and full input validation. Result: OffensiveRezzer demonstrated superior performance compared to other fuzzing tools in identifying errors in Web APIs. It outperformed competitors by detecting the highest number of unique errors. The total number of errors found by OffensiveRezzer in the application without validation, the application with partial validation, and the application with full validation was 416, followed by Restler (240), RestTestGen (145), EvoMaster (138), Tcases (78), and Schemathesis (42). Novelty: The study has presented OffensiveRezzer as a novel tool specifically designed for black-box fuzzing on Web APIs, with a primary focus on testing input validation implementation. This tool fills a gap in existing fuzzing tools and offers improved capabilities for detecting errors in Web APIs.
Siamese Neural Networks with Chi-square Distance for Trademark Image Similarity Detection Suyahman; Sunardi; Murinto; Arfiani Nur Khusna
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.v11i2.4654

Abstract

Purpose: The objective of this study is to address the limitations of existing trademark image similarity analysis methods by integrating a Chi-square distance metric within a Siamese neural network framework. Traditional approaches using Euclidean distance often fail to accurately capture the complex visual features of trademarks, leading to suboptimal performance in distinguishing similar trademarks. This research aims to improve the precision and robustness of trademark comparison by leveraging the Chi-square distance, which is more sensitive to image variations. Methods: The approach involves modifying a Siamese neural network traditionally employing Euclidean distance with the use the Chi-square distance metric instead. This alteration allows the network to better capture and analyze critical visual features such as color and texture. The modified network is trained and tested on a comprehensive dataset of trademark images, enabling the network to learn and distinguish between similar and dissimilar trademarks based on subtle visual cues. Result: The findings from this study show a significant increase in accuracy, with the modified network achieving an accuracy rate of 98%. This marks a notable improvement over baseline models that utilize Euclidean distance, demonstrating the effectiveness of the Chi-square distance metric in enhancing the model's ability to discriminate between trademarks. Novelty: The novelty of this research lies in its application of the Chi-square distance in a deep learning framework specifically for trademark image similarity detection, presenting a novel approach that yields higher precision in image-based comparisons.
Performance of Ensemble Learning in Diabetic Retinopathy Disease Classification Nurizki, Anisa; Fitrianto, Anwar; Mohamad Soleh, Agus
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.v11i2.4725

Abstract

Purpose: This study explores diabetic retinopathy (DR), a complication of diabetes leading to blindness, emphasizing early diagnostic interventions. Leveraging Macular OCT scan data, it aims to optimize prevention strategies through tree-based ensemble learning. Methods: Data from RSKM Eye Center Padang (October-December 2022) were categorized into four scenarios based on physician certificates: Negative & non-diagnostic DR versus Positive DR, Negative versus Positive DR, Non-Diagnosis versus Positive DR, and Negative DR versus non-Diagnosis versus Positive DR. The suitability of each scenario for ensemble learning was assessed. Class imbalance was addressed with SMOTE, while potential underfitting in random forest models was investigated. Models (RF, ET, XGBoost, DRF) were compared based on accuracy, precision, recall, and speed. Results: Tree-based ensemble learning effectively classifies DR, with RF performing exceptionally well (80% recall, 78.15% precision). ET demonstrates superior speed. Scenario III, encompassing positive and undiagnosed DR, emerges as optimal, with the highest recall and precision values. These findings underscore the practical utility of tree-based ensemble learning in DR classification, notably in Scenario III. Novelty: This research distinguishes itself with its unique approach to validating tree-based ensemble learning for DR classification. This validation was accomplished using Macular OCT data and physician certificates, with ETDRS scores demonstrating promising classification capabilities.
Modified Convolutional Neural Network for Sentiment Classification: A Case Study on The Indonesian Electoral Commission Riyadi, Slamet; Mahardika, Naufal Gita; Damarjati, Cahya; Ramli, Suzaimah
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.v11i2.4929

Abstract

Purpose: This study aims to analyze public sentiment towards the Indonesian Electoral Commission (KPU) performance and evaluate a modified Convolutional Neural Network (CNN) model effectiveness in sentiment analysis. Methods: This research employs several methods to achieve its objectives. First, data collection was conducted using web crawling techniques to gather public opinions on the performance of the Indonesian Electoral Commission for the 2024 elections, with a specific focus on platform X. A total of 5,782 data points were collected and underwent preprocessing before sentiment analysis was performed. This study uses the CNN method due to its exceptional ability to recognize patterns and features in text data through its convolutional layers. CNN is highly effective in sentiment analysis tasks because of its ability to capture local context and spatial features from text data, which is crucial for understanding the nuances of sentiment in comments. The modified CNN model was then trained and evaluated using a labeled dataset, where each comment was classified into positive, negative, or neutral sentiment categories. Modifying the CNN model involved adjusting its architecture and parameters, as well as adding layers such as batch normalization and dropout to optimize its performance. The effectiveness of the modified CNN model was assessed based on metrics such as classification accuracy, precision, recall, and F1 score. Through this methodological approach, the research aims to gain insights into public sentiment towards the KPU performance in the 2024 elections and to evaluate the effectiveness of the modified CNN model in sentiment analysis. Result: The research revealed several significant findings. Firstly, most comments expressed concerns regarding performance aspects of KPU’s, including transparency, fairness, and integrity. Neutral sentiment dominated the discourse, with approximately 23.66% of comments conveying dissatisfaction or skepticism towards KPU's handling of the elections. Additionally, sentiments expressed on social media platform X mirrored those found across other platforms, indicating a consistent perception of KPU performance among users. Furthermore, the evaluation of the modified CNN model demonstrated a substantial improvement in accuracy, achieving an impressive 93% accuracy rate compared to the pre-modification model's accuracy of 77%. These results suggest that the modifications made to the CNN model effectively enhanced its performance in sentiment analysis tasks related to KPU performance during the 2024 elections. These findings contribute to a deeper understanding of public sentiment toward KPU performance and underscore the importance of leveraging advanced technology, such as modified CNN models, for sentiment analysis. Novelty: This study contributes novelty in several ways. Firstly, it provides insights into public sentiment towards the performance of the KPU during the 2024 General Elections, which is crucial for understanding the perception of democracy in Indonesia. Second, the study employs a mixed-methods approach, combining web crawling techniques for data collection and a modified CNN model for sentiment analysis, which offers a comprehensive and advanced methodology for analyzing sentiments on social media platforms. Thirdly, the evaluation of the modified CNN model demonstrates a significant improvement in accuracy, indicating the approach's efficacy in analyzing sentiments related to KPU performance. This study offers valuable contributions to academic research and practical applications in sentiment analysis, particularly in democratic processes and institutional performance evaluation.
Analysis of Student Graduation Prediction Using Machine Learning Techniques on an Imbalanced Dataset: An Approach to Address Class Imbalance Hermanto, Dedy; Desy Iba Ricoida; Desi Pibriana; Rusbandi; Muhammad Rizky Pribadi
Scientific Journal of Informatics Vol. 11 No. 3: August 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i3.5528

Abstract

Purpose: Machine learning is a key area of artificial intelligence, applicable in various fields, including the prediction of timely graduation. One method within machine learning is supervised learning. However, the results are influenced by the distribution of data, particularly in the case of imbalanced classes, where the minority class is significantly smaller than the majority class, affecting classification performance. Timely graduation from a university is crucial for its sustainability and accreditation. This research aims to identify a suitable method to address the issue of predicting timely graduation by managing class imbalance using SMOTE (Synthetic Minority Oversampling Technique). Methods: This study uses a five-year dataset with 26 attributes and 1328 records, including status labels. The preprocessing stages involve applying five classification algorithms: Decision Tree (DT), Naive Bayes (NB), Logistic Regression (LR), K-Nearest Neighbors (KNN), and Random Forest (RF). Each algorithm is used both with and without SMOTE to handle the class imbalance. The dataset indicates that 60.84% of the cases represent timely graduations. To mitigate the imbalance, over/under-sampling methods are employed to balance the data. The evaluation metric used is the confusion matrix, which assesses the classification performance. Result: Without SMOTE, the accuracies were 89.12% for DT, 79.65% for NB, 89.47% for LR, 87.72% for KNN, and 90.88% for RF. With SMOTE, the accuracies were 88.89% for DT, 81.48% for NB, 91.05% for LR, 92.59% for KNN, and 89.81% for RF. The algorithms NB, LR, and KNN showed improvement with SMOTE, with KNN yielding the best results. Novelty: Based on the comparison results, a comparison of five algorithms with and without SMOTE can reasonably classify several of the algorithms being compared.
Nowcasting Hotel Room Occupancy Rate using Google Trends Index and Online Traveler Reviews Given Lag Effect with Machine Learning (Case Research: East Kalimantan Province) Rahmawati, Adelina; Nurmawati, Erna; Sugiyarto, Teguh
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.v11i2.5553

Abstract

Purpose: The presence of a two-month lag in Hotel Room Occupancy Rate (TPK) data necessitates an alternative method to accommodate adjustments in the economic circumstances of the tourism industry. In this context, TPK is connected to the influx of tourists, making the data a valuable resource for assessing the tourism potential of a particular area. The information can be used to make informed decisions when considering investments in the local tourism industry. Therefore, this research aimed to formulate predictions for future trends using now-forecasting. The variables of Google Trends Index (IGT) and online traveler reviews considered were obtained from big data. Methods: This research used machine learning methods with Random Forest, LSTM, and CNN-BiLSTM-Attention models in determining the best model. Meanwhile, the datasets were acquired from diverse secondary data sources. Hotel Occupancy Rooms Rate was derived from BPS-Statistics Indonesia, while additional data were collected through web scraping from online travel agency websites such as Tripadvisor.com, IGT with keywords “IKN”, “hotel”, and “banjir”. For the sentiment variable from online reviews, lag effects of one, two, and three months were analyzed to determine the correlation with TPK. The highest correlation was selected for inclusion in the prediction model across all machine learning methods. Result: The results showed that the use of IGT and online traveler reviews increased the precision of forecasting models. The best model of hotel TPK nowcasting was Random Forest Regression with the lowest MAPE value and accuracy of 5.37% and 94.63%, respectively. Novelty: The proposed method showed great potential in improving the prediction of hotel TPK by leveraging new technology and extensive data sources. The correlation with TPK decreases with an increasing time lag of sentiment. Therefore, the sentiment of reviews in the current month has the highest correlation with TPK, compared to the previous one, two, or three months.
Prediction-based Stock Portfolio Optimization Using Bidirectional Long Short-Term Memory (BiLSTM) and LSTM Putra, Raditya Amanta; Nurmawati, Erna
Scientific Journal of Informatics Vol. 11 No. 3: August 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i3.5941

Abstract

Purpose: Investment is the allocation of funds with the aim of obtaining profits in the future. An example of the investment instruments with high returns and high risks are stocks. The risks associated with the investment can be reduced by forming a portfolio of quality stocks optimized through mean-variance (MV). This is necessary because successful selection of high-quality stocks depends on the future performance which can be determined through accurate price prediction. Methods: Stock price can be predicted through the adoption of different forms of deep learning methods. Therefore, BiLSTM and LSTM models were applied in this research using the stocks listed on the LQ45 index as case study. Result: The utilization of LSTM and BiLSTM models for stock price prediction produced favorable outcomes. It was observed that BiLSTM outperformed LSTM by achieving an average MAPE value of 2.1765, MAE of 104.05, and RMSE of 139.04. The model was subsequently applied to predict a set of stocks with the most promising returns which were later incorporated into the portfolio and further optimized using the Mean-Variance (MV). The results from the optimization and evaluation of the portfolio showed that the BiLSTM+MV strategy proposed had the highest Sharpe Ratio value at k=4 compared to the other models. The stocks found in the optimal portfolio were BRPT with a weight of 19.7%, ACES had 16.9%, MAPI 11.8%, and BMRI at 51.6%. Novelty: This research conducted a novel comparison of LSTM and BiLSTM models for the prediction of stock prices of companies listed in the LQ45 index which were further used to construct a portfolio. Past research showed that the development of portfolios based on predictions was not popular.
Sign Language Detection System Using YOLOv5 Algorithm to Promote Communication Equality People with Disabilities Ningsih, Maylinna Rahayu; Nurriski, Yopi Julia; Sanjani, Fathimah Az Zahra; Hakim, M. Faris Al; Unjung, Jumanto; Muslim, Much Aziz
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.v11i2.6007

Abstract

Purpose: Communication is an important asset in human interaction, but not everyone has equal access to this key asset. Some of us have limitations such as hearing or speech impairments, which require a different communicative approach, namely sign language. These limitations often present accessibility gaps in various sectors, including education and employment, in line with Sustainable Development Goals (SDGs) numbers 4, 8, and 10. This research responds to these challenges by proposing a BISINDO sign language detection system using YOLOv5-NAS-S. The research aims to develop a sign language detection model that is accurate and fast, meets the communicative needs of people with disabilities, and supports the SDGs in reducing the accessibility gap. Methods: The research adopted a transfer learning approach with YOLOv5-NAS-S using BISINDO sign language data against a background of data diversity. Data pre-processing involved Super-Gradients and Roboflow augmentation, while model training was conducted with the Trainer of SuperGradients. Result: The results show that the model achieves a mAP of 97,2% and Recall of 99.6% which indicates a solid ability in separating sign language image classes. This model not only identifies sign language classes but can also predict complex conditions consistently. Novelty: The YOLOv5-NAS-S algorithm shows significant advantages compared to previous studies. The success of this performance is expected to make a positive contribution to efforts to create a more inclusive society, in accordance with the Sustainable Development Goals (SDGs). Further development related to predictive and real-time integration, as well as investigation of possible practical applications in various industries, are some suggestions for further research.
Optimizing Customer Segmentation in Online Retail Transactions through the Implementation of the K-Means Clustering Algorithm Awaliyah, Desi Adrianti; Budi Prasetiyo; Muzayanah, Rini; Lestari, Apri Dwi
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.v11i2.6137

Abstract

Purpose: The main objective of this research is optimal use of customer segmentation using the Recency, Frequency and Monetary (RFM) approach so that companies can better understand and comprehend the needs of each customer. By carrying out this segmentation, companies can communicate better and provide services tailored to each customer. Methods: The K-means algorithm is used as the main method for customer segmentation in this research. This research uses a dataset of online retail customers. Apart from that, this research also uses the elbow method to help determine the best number of clusters to be created by the model. Result: Based on the elbow method, the most optimal is to use 3 clusters for this case. Thus, in K-means modeling, forming 3 clusters is the best choice. Clusters produce groups of customers who have specific characteristics in each cluster. The analysis shows that quantity and unit price have a significant influence on online retail customer behavior. Novelty: This research strengthens the trend of using the K-means algorithm for customer segmentation in online retail datasets, which has proven popular in journals from 2018 to 2022. This research creates 3 new variables that will be used by the model to understand the characteristics of customer transaction behavior. This study also emphasizes the importance of exploratory data analysis in understanding data before clustering and the use of the elbow method to determine the most appropriate number of clusters, providing a significant contribution in analyzing customer segmentation.
Recognition of Organic Waste Objects Based on Vision Systems Using Attention Convolutional Neural Networks Models Aradea; Rianto; Mubarok, Husni
Scientific Journal of Informatics Vol. 11 No. 3: August 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i3.6494

Abstract

Purpose: High population growth and increasing consumption patterns have resulted in significant organic waste production. The public often does not understand the correct way to deal with the problem of organic waste, including public awareness regarding the need for its management. Therefore, a system is needed to recognize waste objects based on various types. Currently, much research in this field has been studying object recognition, for example, the implementation of the Convolutional Neural Networks (CNN) model. However, there are still various challenges that must be addressed, including objects with diverse visual characteristics such as form, size, color, and physical condition. This research focuses on developing a system that enhances object recognition of waste, specifically organic waste, using an Attention Convolutional Neural Network (ACNN). By integrating attention mechanisms into the CNN model, this study addresses the challenges of recognizing waste objects with diverse visual characteristics. The proposed system seeks to improve the accuracy and efficiency of organic waste identification, which is crucial for advancing waste management practices and reducing environmental impact. Methods: This research combines a CNN architecture with an attention mechanism to create a better object detection environment called Attention-CNN (ACNN). The ACNN architecture employed consists of one layer input, three convoluted layers, three max-pooling layers, one attention layer, one flattened layer, four dropout layers, and two dense layers arranged in a certain way. Result: The research result shows that the model CNN with attention mechanism (ACNN) was slightly better at 86.93% than the standard model of CNN, which accounted for 86.70% in accuracy. Novelty: In general, the current use of CNN architecture to address waste object recognition problems typically employs standard architectures, resulting in lower accuracy for complex waste objects. In contrast, our research integrates attention mechanisms into the CNN architecture (ACNN), enhancing the model's ability to focus on relevant features of waste objects. This leads to improved recognition accuracy and robustness against visual variability. This distinction is important as it overcomes the limitations of standard CNN models in handling visually diverse and complex waste objects, thereby highlighting the novelty and contribution of our research.

Page 3 of 17 | Total Record : 161

 1   2   3   4   5 

Filter by Year

2024 2026


Reset
Filter By Issues
All Issue Vol. 13 No. 1: February 2026 Vol. 12 No. 4: November 2025 Vol. 12 No. 3: August 2025 Vol. 12 No. 2: May 2025 Vol. 12 No. 1: February 2025 Vol. 11 No. 4: November 2024 Vol. 11 No. 3: August 2024 Vol. 11 No. 2: May 2024