Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI)

Accrual-Based Accounting Information System For Financial Compliance Monitoring

2026-07-14T07:17:10+00:00

Small and medium-sized enterprises (SMEs) often face challenges in implementing efficient and accurate financial reporting systems, primarily due to the limitations of manual accounting processes. These challenges lead to errors, delays, and compliance issues, which hinder timely decision-making and financial transparency. This research proposes the development and evaluation of an accrual-based Accounting Information System (AIS) designed to address these issues by automating financial reporting and compliance monitoring. The motivation behind this study is to improve the financial management practices of SMEs by providing a reliable system that ensures accurate financial reporting and real-time compliance monitoring. The main contribution of this research is the design of an AIS that integrates key financial functions, such as transaction processing, accrual calculations, and compliance checks, to streamline financial operations. Evaluation results from case studies indicate that the system significantly reduced reporting errors by 50%, enhanced compliance accuracy by 25%, and decreased report generation time by 40%. Despite these successes, challenges remain in system integration with legacy accounting software and handling complex financial transactions. Future work will focus on enhancing the scalability of the system, integrating advanced machine learning techniques for predictive financial analysis, and improving the integration process to allow for broader implementation in diverse business contexts. Additionally, the development of a mobile application to improve accessibility to financial reports and compliance alerts will be explored.

Development of an Accrual-Based Accounting Information System Using a Performance Measurement System

2026-07-14T07:17:10+00:00

The integration of accounting and performance measurement systems is a crucial advancement for small and medium-sized enterprises (SMEs), which often face challenges in managing financial processes efficiently. Traditional accounting systems, while reliable, lack real-time financial insights and performance metrics necessary for informed decision-making. This study addresses the problem by proposing an accrual-based Accounting Information System (AIS) integrated with a Performance Measurement System (PMS). The motivation behind this work is to enhance financial decision-making in SMEs by automating key accounting functions and providing real-time performance feedback. The proposed system automates revenue recognition, expense matching, and cost allocation, while simultaneously tracking key performance indicators (KPIs) such as profitability and return on assets. The system was evaluated in a case study involving several SMEs, where it demonstrated improved accuracy in financial reporting, reduced manual errors by 30%, and enhanced decision-making by providing real-time performance insights. Usability testing revealed high satisfaction from users, although additional training was recommended to fully leverage the system’s capabilities. The system's scalability for larger organizations remains an area for future exploration. Future work will focus on refining predictive analytics to further improve financial forecasting and expanding the system’s scalability to accommodate larger enterprises. The results highlight the potential of integrating accrual accounting with performance measurement to enhance financial management in SMEs, offering a practical solution for improved financial decision-making.

Design of Early Childhood Learning Media on Plant and Animal Life Using Digital Puppetry

2026-07-14T07:17:10+00:00

This animal puppetry learning video serves as an interesting alternative to convey educational material to children. Animal puppetry learning videos can stimulate children's imagination and creativity. The animal characters that exist in the puppetry world encourage children to think more broadly and see the world from a new perspective. In this instructional video, the author employed research methods such as observation and interviews, where the author directly visited Dharma Pertiwi Kindergarten to conduct an interview with the headmaster. The interview method involved asking several questions regarding the subject matter and the process of teaching and learning for children at Dharma Pertiwi Kindergarten. Additionally, observations were made by examining literature, materials, curriculum, and how teachers teach children about nature. The process of creating this instructional video involved utilizing puppetry and digital media, skillfully packaged using the Adobe Premiere Pro 2020 application, along with filming using a Lumix G7 mirrorless camera. Consequently, this instructional video was produced, and the results were further enhanced by a questionnaire, which evaluated the effectiveness of the instructional video on the children of Dharma Pertiwi Kindergarten, demonstrating positive outcomes for the instructional media.

Classifying Indonesian Batik Motifs by Region Using Swin Small Transformer Architecture

2026-07-14T07:17:10+00:00

Batik plays a crucial role in Indonesian cultural heritage, with regional motifs encoding local philosophies, identities, and socio-historical contexts while also sustaining creative industries and tourism. Automated classification of batik by region can support documentation, education, and authentication, yet remains challenging due to visually overlapping patterns, high intra-class variability, and subtle inter-regional differences. Building on recent advances in Vision Transformers, this study investigates the Swin Small Transformer architecture for classifying Indonesian batik motifs into five regional categories: Jawa Barat, Jawa Tengah, Jawa Timur, Madura, and Yogyakarta. The proposed framework employs the swin_small_patch4_window7_224} model initialized with ImageNet-pretrained weights and fine-tuned on a curated regional batik dataset. The hierarchical shifted-window attention mechanism of Swin is leveraged to capture both local repetitive elements and broader compositional structures that characterize regional styles. Experimental evaluation on a held-out test set consisting of 80 images demonstrates outstanding performance. The model achieves perfect classification results with overall accuracy, macro-averaged precision, recall, and F1-score all reaching 1.0000. No misclassifications are observed across any regional category, indicating that the proposed architecture effectively learns discriminative representations of regional batik motifs. These findings suggest that hierarchical Vision Transformers can robustly model the nuanced visual cues underpinning regional identity in batik patterns and provide a strong alternative to conventional convolutional neural network approaches. Beyond batik classification, the proposed framework may be extended to other cultural-heritage textile applications, supporting digital preservation, educational initiatives, and large-scale documentation of traditional artistic assets.

Enhancing Rice Disease Classification Using CLAHE and Transfer Learning on Leaf Image Data

2026-07-14T07:17:10+00:00

Rice foliar diseases pose a major threat to global food security by reducing yield and grain quality, motivating the need for scalable, objective, and automated diagnosis solutions. This study investigates the impact of Contrast Limited Adaptive Histogram Equalization (CLAHE) and transfer learning on the classification of three common rice leaf diseases—Bacterial Blight, Brown Spot, and Leaf Smut—from RGB leaf images. Using a dataset of 2,342 images split into training, validation, and test sets (80:10:10), we design a controlled experimental pipeline comprising four scenarios: with/without CLAHE, and with/without transfer learning. CLAHE is applied as a preprocessing step to enhance local contrast and lesion visibility under heterogeneous illumination and cluttered backgrounds, while transfer learning leverages ImageNet-pretrained convolutional neural networks fine-tuned for rice disease recognition. Models are trained and evaluated using accuracy, macro F1, and weighted F1 on a held-out test set. The combined CLAHE + transfer learning configuration achieves the best performance, with an overall accuracy of 0.94 and macro and weighted F1-scores of 0.94, substantially outperforming non-enhanced and non-transferred baselines. Qualitative analysis indicates improved separability between visually similar classes, particularly Brown Spot and Leaf Smut, under challenging imaging conditions. These findings underscore the effectiveness of integrating contrast enhancement with transfer learning for robust, field-oriented rice disease classification and highlight a practical pathway toward reliable image-based decision support in precision agriculture.