International Journal of Advances in Data and Information System
Not a member yet
161 research outputs found
Sort by
Factors Influencing Public Intention to Use the Kepahiang Local Tax Mobile Application: An Adapted UTAUT Perspective
Full text linkThis study aims to identify factors that influence the public’s behavioral intention to use the Kepahiang Local Tax Mobile Application. Developed by the Regional Government of Kepahiang Regency through the Revenue Division of the Regional Financial Agency, the application facilitates local tax payments, particularly for PBB-P2 (Rural and Urban Land and Building Tax). The research adopts an extended Unified Theory of Acceptance and Use of Technology (UTAUT) framework, incorporating additional variables such as Computer Self-Efficacy and Cost of Service, along with original UTAUT constructs: Performance Expectancy, Effort Expectancy, Social Influence, and Facilitating Conditions. It also examines moderating variables including Gender, Age, and Experience. Data were gathered through a questionnaire distributed to 152 respondents and analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). Results reveal that Performance Expectancy and Social Influence significantly and positively affect Behavioral Intention to use the application, whereas Cost of Service shows a negative influence. Furthermore, Gender is found to moderate the relationship between Social Influence and Behavioral Intention. These findings offer insights into the key factors influencing the adoption of government mobile applications, serving as a useful reference for policymakers aiming to increase user acceptance and enhance the effectiveness of digital public services
Implementation of Transfer Function ARIMA Model for Stock Price Prediction
Full text linkDynamic economic growth requires stable financing sources, one of which is through the capital market. In stock investment activities, risk and return are two fundamental aspects that are interrelated and must be carefully considered. The volatility of ASII stock prices, influenced by various factors including exchange rates, can create uncertainty in investment decision-making. This study aims to predict the stock price of PT Astra International Tbk (ASII) using a transfer function model approach that integrates the influence of the Indonesian rupiah to US dollar exchange rate as an external variable. The transfer function model is an extension of the ARIMA model that can measure the dynamic relationship between input and output variables. Based on the estimation results, the best model obtained has a transfer function order of (b,s,r) = (1,0,0) with a noise series of (p_n,q_n) = (1,0). The prediction results show that ASII stock price movements tend to be stable with a gradual decline over the next 20 days. Model evaluation demonstrates low error rates, with MAE of 84.19, RMSE of 110.37, and MAPE of 1.65%. These results indicate that the transfer function model is effective in modeling and predicting short-term stock prices with reasonably good accuracy
A Value-Driven Approach to Software Project Prioritization: Integrating AHP and Value-Focused Thinking in a Messaging Service Firm
Full text linkAs requests for development projects grow, a real-life messaging service firm faces increasing challenges in objectively prioritizing initiatives due to limited developer capacity and a high number of concurrent projects. These issues have resulted in inefficient resource allocation, delayed timelines, and declining customer satisfaction, exacerbated by unclear and unstructured project selection methods. This study proposes an integrated decision-making framework that combines the Analytical Hierarchy Process (AHP), stakeholder analysis, and Value-Focused Thinking (VFT) to address the firm’s prioritization challenges. AHP structures the decision criteria and evaluates project alternatives based on their relative importance, stakeholder analysis identifies key decision-makers and their influence, and VFT ensures alignment with organizational values and strategic goals. To uncover underlying issues and stakeholder expectations, the study employs Problem Tree Analysis, structured interviews, and questionnaires. Four typical sub-project alternatives—Custom Projects, New Features, Bug Fixing, and Optimization—are assessed against four criteria: Cost, Quality, Functionality, and Client Satisfaction. The study concludes with an implementation roadmap and actionable recommendations to improve the firm’s project selection and prioritization process
Implementation of ARIMA for Prediction of Paddy Rice Production in Cisolok Sub-District, Sukabumi District
Full text linkIndonesia as an agricultural country, agriculture, especially paddy production, plays an important role in food security. However, Cisolok District, Sukabumi Regency faces challenges in terms of effective rice production management. This study aims to improve the accuracy of rice production prediction in Cisolok District by implementing Arima. The methodology used is Knowledge Discovery in Databases (KDD), which includes data selection, data pre-processing, model selection, model training, and model evaluation. The data used include weather attributes and paddy production, which are collected from various related sources. The results of the study indicate that the model built with Arima provides accurate estimates and can help farmers and decision makers in planning and managing paddy production more efficiently. These findings are expected to increase paddy productivity in Cisolok District, Sukabumi Regency
Grid-Based Ship Density Analysis and Anomaly Detection for Ship Movements Monitoring at Tanjung Priok Port
Full text linkIndonesia, as a maritime country, depends on ports to support inter-island transport and a smooth regional economy. So, the awareness of knowing the marine status with various platforms is needed. This research distinguishes itself from several previous studies on ship movement detection by concentrating specifically on anomalies in ship movement within areas of high traffic density. This research proposes to find out the ship density area using the grid technique and identify the anomalies that have occurred, as information on ship movements at Tanjung Priok Port. Anomaly detection is done by looking for it through visualization, where AIS data is converted into a form of visualization using the Python language. The results obtained two pieces of information, namely that the areas with the highest density are around the harbor, docks, and ship lanes. Then, two types of anomalies were detected, namely large ships with dangerous cargo speeding in dense areas and ships that behave differently compared to other ships with the same status
Deep Learning and Remote Sensing for Agricultural Land Use Monitoring: A Spatio-Multitemporal Analysis of Rice Field Conversion using Optical Satellite Images
Full text linkRice is a staple food for over half of the global population, making its production crucial for food security, especially in Indonesia, the world\u27s third-largest rice consumer. Population growth and urban expansion have led to agricultural land conversion, necessitating efficient monitoring methods. Traditional approaches, such as area sample frameworks and tile surveys, are costly and time-consuming, prompting the need for remote sensing and deep learning solutions. This study utilizes medium-resolution Sentinel-1, Sentinel-2, and Landsat-8 optical satellite imagery from 2013 and 2021 to analyze land cover changes in West Bandung and Purwakarta Regencies, key agricultural regions in Indonesia. A deep learning model is developed to classify land cover, validated through ground-truth evaluation, and applied to assess spatio-multitemporal land use conversion, paddy field estimation, and conversion rates. Results show that deep learning models effectively classify land cover with high accuracy, revealing significant agricultural land loss due to urban expansion. This research contributes to artificial intelligence (AI)-driven land monitoring, particularly in tropical regions, and supports policymakers in sustainable food agriculture land management. The findings highlight the potential of integrating remote sensing and deep learning for cost-effective agricultural monitoring, ensuring food security and sustainable land use. Future research should explore higher-resolution imagery and advanced AI techniques to enhance predictive accuracy and decision-making
Indonesian Sign Language (BISINDO) Classification Using Xception Transfer Learning Architecture
Full text linkHuman communication generally relied on speech. However, this was not applicable to the deaf people, who depended on sign language for daily interactions. Unfortunately, not everyone had the ability to understand sign language. In higher education environments, the lack of individuals proficient in sign language often created inequality in the learning process for deaf students. This limitation could be addressed by fostering a more inclusive environment, one of which was through the implementation of a sign language translation system. Therefore, this study aimed to develop a machine learning model capable of detecting and translating Indonesian Sign Language (BISINDO) alphabet gestures. The model was built using the Xception transfer learning method from Convolutional Neural Networks (CNN). The dataset consisted of 26 BISINDO alphabet gestures with a total of 650 images. The model was evaluated using K-Fold cross-validation and achieved an F1-score of 94% during testing
AI Agents for Organizational Knowledge Retrieval and Sharing: A Systematic Literature Review
Full text linkAs complexity and volume of data continue to increase, studies have found that traditional knowledge management systems are unable to keep up. Distributed teams, which are increasingly adopted by organizations as ways of working, have significantly transformed how employees manage their knowledge within these organizations. Artificial intelligence (AI), especially AI agents, is increasingly being used by organizations as a solution to enhance knowledge retrieval and sharing. However, it remains fragmented, with little awareness of its effective capabilities, limitations, and implications for organizational knowledge processes. The objective of this study was to systematically evaluate and synthesize recent research on AI agents for organizational knowledge retrieval and sharing. A PRISMA-based Systematic Literature Review (SLR) was carried out on studies published between 2021 and 2025. A total of 28 studies were analyzed to classify AI agent capabilities, supporting technologies, and key challenges across diverse domains and regions. The results revealed five key capabilities of AI agents, such as user-centered interaction, semantic knowledge extraction & retrieval, intelligent reasoning & decision support, automation & workflow management, and explainability & traceability. These capabilities were supported by technologies such as large language models, machine learning, natural language processing, knowledge graphs, ontologies, and other prominent technologies. Adoption challenges primarily included data quality & semantic alignment, system interoperability, trust & adoption issues, and ethical & governance concerns. This review concludes that AI agents hold strong potential to improve organizational knowledge processes, but it requires strategic integration, strong data governance, and human-centered design principles
Development and Implementation of the Primakara Virtual Assistant Based on Generative Artificial Intelligence
Full text linkThe growing need for efficient, accessible, and context-aware academic support systems has led to the exploration of Generative AI (GenAI) technologies in educational settings. However, existing virtual assistants often lack contextual relevance, adaptability, and user-friendly interaction, limiting their effectiveness in higher education environments. This study proposes a GenAI-based Virtual Assistant (VA) tailored for university-related applications, combining voice recognition, natural language understanding, and text-to-speech technologies to create an interactive and intelligent support system. The proposed work was evaluated through four key testing stages: black-box functionality testing, response similarity analysis, inference time measurement, and user acceptance testing. Black-box testing validated the system’s ability to process speech input, generate accurate audio responses, and provide responsive UI/UX feedback. A TF-IDF cosine similarity analysis across 11 academic departments yielded an average similarity score of 81.86%, demonstrating semantic alignment with institutional content. The system also maintained an average response time of 3.88 seconds. User feedback from 25 participants revealed high satisfaction levels, with scores exceeding 4.0 across all indicators and large T-statistic value. These results confirm the system’s potential as an effective, real-time academic assistant
Classification of Crystallization Images of Pharmaceutical Raw Materials Using Convolutional Neural Network Algorithm
Full text linkThe rapid advancement of artificial intelligence (AI) has opened new opportunities for automation in the pharmaceutical industry, particularly in the classification of raw drug materials. Manual classification methods are time-consuming and prone to human error, highlighting the need for reliable automated solutions. This study applied a deep learning approach for classifying crystallization images of pharmaceutical raw materials using a Convolutional Neural Network (CNN). A dataset of 300 crystallization images of Nicotinamide and Ferulic Acid was obtained through hot-stage microscopy, preprocessed with normalization, resizing, and augmentation, and divided into training, validation, and testing subsets. The CNN model was trained for 10 epochs and evaluated using a confusion matrix and standard performance metrics (accuracy, precision, recall, and F1-score). The model achieved perfect recall for Ferulic Acid and 90% recall with 100% precision for Nicotinamide, resulting in an overall accuracy of 95%. While these results are promising, the relatively small dataset may limit generalization, and further validation with larger or external datasets is required. The findings indicate that CNN-based methods hold strong potential for automating crystallization classification, improving pharmaceutical quality control, and reducing reliance on manual assessment, in line with recent advances in medical and pharmaceutical image analysis