cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Warto
Contact Email
warto@uinsaizu.ac.id
Phone
+6281327567868
Journal Mail Official
tids@uinsaizu.ac.id
Editorial Address
Fakultas Saintek UIN Saizu Jl. M.T. Haryono, Karangsentul, Padamara, Purbalingga, Jawa Tengah - 53372
Location
Kab. banyumas,
Jawa tengah
INDONESIA
Transaction on Informatics and Data Science
Published by Universitas Islam Negeri Profesor Kiai Haji Saifuddin Zuhri Purwokerto
ISSN : -     EISSN : 30641772     DOI : https://doi.org/10.24090/tids
Core Subject : Science, Engineering,
Computer Science & IT Decision Sciences, Operations Research & Management Engineering
Transactions on Informatics and Data Science (TIDS), with ISSN: 3064-1772 (online), is a scientific journal that publishes the latest research in the fields of informatics and data science, focusing on both theoretical advances and practical applications. Published by the Department of Informatics, Universitas Islam Negeri Prof. K.H. Saifuddin Zuhri Purwokerto, Purwokerto, this journal serves as a platform for researchers, academics, and practitioners to share new ideas and innovations in data science, artificial intelligence, natural language processing, cloud computing, and information technology applications across various domains. It promotes collaboration and deep knowledge exchange within the scientific community, bridging the gap between theory and practice in the rapidly evolving fields of informatics and data science. Aims Transaction on Informatics and Data Science aims to advance the frontiers of informatics and data science knowledge by publishing high-quality research that encompasses theoretical advancements and practical applications. The journal seeks to contribute significantly to the understanding and developing of innovative approaches, methodologies, and technologies in these domains. Scopes The scope of "Transaction on Informatics and Data Science" covers a wide range of topics related to informatics and data science, including but not limited to: - Data analysis and mining - Artificial intelligence and machine learning - Natural language processing and understanding - Cloud computing and big data technologies - Information retrieval and knowledge management - Data-driven decision-making and predictive modelling - Internet of Things (IoT) and data analytics - Cybersecurity and privacy in data science - Informatics and data science applications in various healthcare, finance, education, and other domains. The journal welcomes original research articles, reviews, case studies, and technical notes that contribute significantly to advancing knowledge and practice in informatics and data science. Submissions should demonstrate novelty, tightness, and relevance to the rapidly evolving landscape of information technology and data-driven decision-making processes.
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 17 Documents
 1   2 
Determining Promotions at UD. Jakarta Pixel using Web-Based FP-Growth Association Model Potale, Lisa Elisia; Ahmad, Muhammad Sabri; Khairan, Amal
Transactions on Informatics and Data Science Vol. 2 No. 1 (2025)
Publisher : Department of Informatics, Faculty of Da'wah, UIN Saizu Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24090/tids.v2i1.12208

Abstract

In the rapidly advancing digital era, the growth of e-commerce has significantly transformed the retail business paradigm. However, physical stores still play a crucial role in providing direct and personal experiences to customers. UD. Jakarta Pixel, a physical store specializing in photography and electronic products, faces increasingly intense competition from various e-commerce platforms. To remain competitive, sophisticated and effective promotional strategies are required. This research uses the FP-Growth association model as the method to determine effective website-based product promotions at UD. Jakarta Pixel. The research results indicate that the FP-Growth algorithm successfully analyzes customer purchasing patterns, identifies relationships between frequently purchased products, and enables the store to design more targeted promotions according to customer preferences. Implementing this system not only enhances operational efficiency in data analysis but also provides accurate information for strategic decision-making, optimizing product promotion strategies, and ultimately increasing sales. In conclusion, the application of the FP-Growth algorithm at UD. Jakarta Pixel is an innovative solution that strengthens the competitiveness and sustainability of physical stores amid the rapid growth of e-commerce, leveraging transaction data analysis for more effective and efficient promotion planning.
Haar Cascade Classifier and Adaboost Algorithm for Face Detection with the Viola-Jones Method Nidom, Mohammad Saichu
Transactions on Informatics and Data Science Vol. 2 No. 1 (2025)
Publisher : Department of Informatics, Faculty of Da'wah, UIN Saizu Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24090/tids.v2i1.12276

Abstract

Face detection is a significant challenge in image processing and computer vision, with broad security, identity recognition, and human-computer interaction applications. This study explores the effectiveness of the Haar Cascade Classifier method optimized with Adaboost to improve the accuracy and efficiency of face detection in various head covering conditions. In this experiment, two approaches were compared: using the Haar Cascade Classifier independently and in combination with Adaboost, with evaluation based on metrics such as accuracy, precision, sensitivity, and F1-Score. The results showed that the Adaboost combination significantly improved detection accuracy, with the "Hooded" class achieving an accuracy of 99.2% and the average detection time reduced from 14.9 seconds to 1.9 seconds. These findings show that the use of optimization techniques such as Adaboost not only improves detection performance but also overall system efficiency. The conclusion of this study emphasizes the importance of combining methods in developing a more robust and efficient face detection system. The implications of this research can be applied to create more effective security and facial recognition applications and pave the way for further study in optimizing object detection algorithms.
Corpus Development and NER Model for Identification of Legal Entities (Articles, Laws, and Sanctions) in Corruption Court Decisions in Indonesia Subowo, Edy; Bukhori, Imam; warto
Transactions on Informatics and Data Science Vol. 2 No. 1 (2025)
Publisher : Department of Informatics, Faculty of Da'wah, UIN Saizu Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24090/tids.v2i1.13592

Abstract

This study aims to develop an annotated corpus and a deep learning-based Named Entity Recognition (NER) model to identify legal entities in Indonesian corruption court rulings. The corpus was constructed from 450 Supreme Court documents related to the Anti-Corruption Laws (Laws No. 31/1999), collected via web scraping, with semi-automatic annotation (regex) and validation by legal experts. A total of 12,000 entities (Article, Laws, Sanctions) were tagged in IOB format, creating the first specialized dataset for Indonesian corruption laws. The NER model combines the IndoBERT (pre-trained language model) architecture with a CRF layer, fine-tuned to handle legal text complexities such as hierarchical article references (paragraphs, clauses) and amended laws citations (jo.). Evaluation using 10-fold cross-validation revealed that the model achieved an F1-score of 92.3%, outperforming standalone CRF (85.1%) and BiLSTM+CRF (88.7%), particularly in detecting ARTICLE entities (F1: 93.8%). Error analysis highlighted challenges in recognizing SANCTIONS entities (F1: 87.4%) due to sentence structure variability and conjunctions. The model’s implementation could accelerate judicial decision analysis, identify violation patterns, and support sanctions recommendation systems for laws enforcement. This research also provides legal entity annotation guidelines adaptable to other legal domains. Future work should expand to other laws (e.g., ITE Laws, Criminal Code) via transfer learning and integrate knowledge graphs to enhance entity relation detection.
The Role of Color in User Experience: A Systematic Literature Study of User Preferences for Dark and Light Mode Atsani, M. Rifqi; Mukaromah, Iif Alfiatul; Anugerah, M. Haikal Citra
Transactions on Informatics and Data Science Vol. 2 No. 1 (2025)
Publisher : Department of Informatics, Faculty of Da'wah, UIN Saizu Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24090/tids.v2i1.13903

Abstract

The increasing use of dark mode and light mode in user interfaces has prompted many studies to determine their effects on user experience. Findings in the literature show that research is still fragmented and does not provide a comprehensive understanding of the cognitive, emotional, and behavioral aspects of preferences for user interface themes. This study analyzed 25 selected scientific articles from 2020 to 2025. The identification topics were related to user preferences, performance, accessibility, and satisfaction with interface modes. The qualitative thematic analysis approach found 6 main themes, namely Readability and Accessibility, Cognitive and Emotional Responses, Usage Behavior and Preferences, Task Performance and Efficiency, Health and Environmental Impacts, and Interface Design and Satisfaction. The results showed that light mode was better in terms of readability and tasks that require high lighting, dark mode provides better visual comfort than light mode and reduces eye fatigue in low light conditions. User preferences were influenced by several things such as age, device type, environment, and emotional needs. This research emphasizes the development of an adaptive system that allows users to switch between dark and light modes according to their respective conditions is important. This research contributes to the field of Human Computer Interaction (HCI) by demonstrating an understanding of interface theme design as well as future research directions.
Positional Accuracy Measurement: Prototype Geographic Information System for Banyumas Regency Tourism Priyono, Putra Aditya; Qalban, Anas Azhimi; Salma, Azora Sania
Transactions on Informatics and Data Science Vol. 2 No. 2 (2025)
Publisher : Department of Informatics, Faculty of Da'wah, UIN Saizu Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24090/tids.v2i2.13874

Abstract

Banyumas Regency has high tourism potential, both in terms of nature, culinary, and culture. This study aims to assess the accuracy of geographic positioning (longitude and latitude) in a web-based Geographic Information System (GIS) to ensure the accurate and reliable presentation of tourist destination location data. Accurate spatial data is essential for planning, navigation, promotion, and improving visitor experiences through enhanced digital mapping and integrated tourism development strategies. The method used is prototyping, which allows the initial system development to be tested and refined based on the results of accuracy measurements. The system was developed using the Google Maps API and the PHP programming language and integrated with a GPS device to obtain real-time coordinates. Testing was conducted by comparing the field coordinates with digital map data to identify positional deviations. Analysis was carried out spatially using the Positional Accuracy Tolerance approach to improve the accuracy of the maps visualized in the Tourism Geographic Information System. The results of the study indicate the need for recalibration at several location points to improve the system's precision. This GIS is expected to provide valid location information for tourists in planning their tourism trips.
Predicting SPAD Values in Sri Lankan Paddy Rice Fields using UAV-based Vegetation Indices Fonseka, Ishani; Hewagamage, K.P.; Rathnayake, Upul; Bandara, R.M.U. S; Halloluwa, Thilina
Transactions on Informatics and Data Science Vol. 2 No. 2 (2025)
Publisher : Department of Informatics, Faculty of Da'wah, UIN Saizu Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24090/tids.v2i2.14980

Abstract

In Sri Lanka, the overuse of fertilizers by farmers leads to financial losses and environmental concerns. Due to the high cost and limited availability of SPAD equipment, UAV-based imagery presents a practical and cost-effective alternative for monitoring nitrogen levels in crops. This study evaluates the use of UAV-based multispectral imagery to assess the nitrogen status of rice crops and compares various vegetation indices with SPAD readings. Focusing on the BG300 rice variety. several vegetation indices were compared with SPAD readings using a Linear Regression (LR) model. Among them, NDVI showed the strongest correlation (R = 0.81106), confirming its reliability as an indicator of nitrogen status. This approach offers a cost-effective solution for Sri Lanka’s rice farming sector, aiding farmers in making more informed decisions to reduce fertilizer use and mitigate environmental impacts
Mitigating the Cost Amplification of Platform Defaults in Lean Cloud Data Deployments Through Configuration Hygiene Diaz, Manuel O.
Transactions on Informatics and Data Science Vol. 2 No. 2 (2025)
Publisher : Department of Informatics, Faculty of Da'wah, UIN Saizu Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24090/tids.v2i2.14737

Abstract

Cloud data platforms offer flexibility, but their default configurations are implicitly optimized for enterprise-scale environments, leading to hidden, disproportionate costs for small-scale deployments. This paper introduces the concept of a silent tax, where platform defaults, such as minimum billing durations and over-provisioned column types, disproportionately inflate costs for small business organisations with modest compute budgets, exemplified by a 10 IPU per month scenario. These defaults act as regressive cost drivers, penalizing users unable to amortize inefficiencies. We employ an analytical cost-modelling and Monte Carlo simulation approach, using Snowflake and Informatica Intelligent Data Management Cloud (IDMC) as reference platforms, and validate it through a paired, parametric Monte Carlo experiment using truncated normal and lognormal distributions. Our findings indicate that fixed-cost components embedded in these defaults can consume approximately 65% of a minimal budget. Key mechanisms include 60-second warehouse billing minimums, schema-driven memory over-allocation, and CI/CD pipeline reconfiguration costs. The study demonstrates that cost waste in minimal deployments is predominantly structural. An optimization pathway focusing on configuration hygiene—including explicit data types, aggressive warehouse tuning, and schema-as-code—can reclaim over 80% of this overhead, aligning with FinOps guidance for small estates. This research addresses a gap in cloud cost governance, empowering small teams to leverage cost intelligence for sustainability, and suggests transparent disclosure of default cost impacts by providers.

Page 2 of 2 | Total Record : 17

 1   2 

Filter by Year

2024 2025


Reset
Filter By Issues
All Issue Vol. 2 No. 2 (2025) Vol. 2 No. 1 (2025) Vol. 1 No. 2 (2024) Vol. 1 No. 1 (2024)