cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kab. indragiri hilir,
Riau
INDONESIA
Sistemasi: Jurnal Sistem Informasi
Published by Universitas Islam Indragiri
ISSN : 23028149     EISSN : 25409719     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Electrical & Electronics Engineering
Sistemasi adalah nama terbitan jurnal ilmiah dalam bidang ilmu sains komputer program studi Sistem Informasi Universitas Islam Indragiri, Tembilahan Riau. Jurnal Sistemasi Terbit 3x setahun yaitu bulan Januari, Mei dan September,Focus dan Scope Umum dari Sistemasi yaitu Bidang Sistem Informasi, Teknologi Informasi,Computer Science,Rekayasa Perangkat Lunak,Teknik Informatika
Arjuna Subject : -
Articles 1,176 Documents
 114   115   116   117   118 
Vegetable Sales Transaction Segmentation using K-Means Clustering for Sales Strategy Optimization Dimas Wahyu Eko Prasetyo; Charitas Fibriani (SCOPUS ID=57192643331)
SISTEMASI Vol 15, No 8 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Universitas Islam Indragiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i8.6674

Abstract

Managing fresh vegetable inventory requires accurate decision-making because of its limited shelf life and variations in unit prices and sales volumes. This study aims to segment vegetable sales transactions at D2 Vegetables, a vegetable supplier, using K-Means Clustering based on unit price and sales volume; evaluate cluster quality; and develop operational recommendations based on the characteristics of each segment. The dataset consists of 1,016 vegetable sales transactions recorded from June 25, 2024, to June 23, 2025. The analytical procedures included data preprocessing, standardization, determination of the optimal number of clusters using the Elbow Method, evaluation using the Silhouette Coefficient and Davies-Bouldin Index, K-Means clustering, and comparison with Agglomerative Hierarchical Clustering. Internal evaluation indicated that K = 2 achieved the highest Silhouette Coefficient (0.6114) and the lowest Davies-Bouldin Index (0.5156). However, K = 3 was selected by considering the Elbow pattern, cluster structure quality, and interpretability of the resulting three transaction segments. At K = 3, K-Means achieved a Silhouette Coefficient of 0.5719 and a Davies-Bouldin Index of 0.6029, outperforming Agglomerative Clustering, which achieved scores of 0.5031 and 0.6595, respectively. The resulting segmentation comprised 682 Standard transactions (67.13%), 235 Bulk transactions (23.13%), and 99 Premium transactions (9.74%). The Bulk segment had the highest total sales volume, the Standard segment had the largest number of transactions and the greatest diversity of vegetable types, while the Premium segment had the highest average unit price and relatively low sales volume. The segmentation results can serve as a decision-support basis for procurement planning, inventory management, storage allocation, and segment-specific promotional strategies, enabling operational decisions to be aligned with the characteristics of each transaction segment.
Comparative Performance Analysis of EfficientNet-B0, ConvNeXt-Tiny, and MobileNetV2 for Oil Palm Fruit Ripeness Classification Samsudin Samsudin; Abdullah Abdullah; Abdul Muni; Misnawati Misnawati
SISTEMASI Vol 15, No 8 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Universitas Islam Indragiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i8.6755

Abstract

The classification of Fresh Fruit Bunch (FFB) ripeness levels in oil palm is a crucial aspect of agricultural automation for maintaining production quality. This study evaluates the performance of three deep learning architectures through a comparative analysis of EfficientNet-B0, ConvNeXt-Tiny, and MobileNetV2 for distinguishing different fruit ripeness classes. The experimental results show that MobileNetV2 achieved the highest accuracy of 97%, followed by ConvNeXt-Tiny at 94%, whereas EfficientNet-B0 achieved only 32%, primarily due to systematic prediction bias on the complex dataset. The confusion matrix analysis indicates that although MobileNetV2 and ConvNeXt-Tiny performed effectively, visual ambiguity during transitional ripeness stages remains a challenge for purely computer vision-based approaches. These findings highlight the importance of selecting an appropriate backbone architecture and the potential need for hybrid approaches to improve system reliability. As a direction for future research, the application of Neuro-Symbolic AI is proposed to combine deep learning-based feature extraction with knowledge-based reasoning to resolve ambiguous predictions, together with model optimization to achieve greater computational efficiency on edge devices. This study provides a strategic contribution to the development of transparent and accurate automated sorting systems for the oil palm plantation sector.
Analysis of Wireless Network Performance at UGM Academic Hospital based On QoS Parameter Rahmat Gunawan Ediyasanto; Danur Wijayanto
SISTEMASI Vol 15, No 8 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Universitas Islam Indragiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i8.6812

Abstract

RSA UGM integrates healthcare, education, and research services, making it highly dependent on reliable wireless network infrastructure. However, the performance of the RSA UGM wireless network often deteriorates when user demand approaches the maximum capacity of access points, particularly in public areas such as auditoriums and patient waiting rooms. This condition may result in channel interference, reduced throughput, and increased response times. This study analyzes wireless network performance based on Quality of Service (QoS) parameters while integrating a digital forensics approach to distinguish legitimate user traffic surges (flash crowds) from Distributed Denial-of-Service (DDoS) attacks. The study employs an Action Research methodology consisting of diagnosis, planning, action implementation, and evaluation. QoS measurements were conducted using iPerf3 and Wireshark/tcpdump over three days across three time sessions, accompanied by a SYN Flood attack simulation in a laboratory environment replicating the hospital network topology. QoS parameters were analyzed based on the TIPHON standard, including throughput, packet loss, delay, and jitter, while the integrity of digital evidence was verified using SHA-256 hashing and a chain-of-custody procedure. The results show that under normal conditions (11 samples), throughput ranged from 9,877.75 to 23,452.12 Kbps, with a TIPHON Index of 4.00, indicating very good performance. Under flash crowd conditions, throughput increased sharply to 104,602.77 Kbps, while the other QoS parameters remained stable, resulting in a TIPHON Index of 4.00. In contrast, during the DDoS attack condition (7 samples), packet loss increased substantially to 42.64%, accompanied by significant increases in delay and jitter, causing the TIPHON Index to decline to 3.25–3.75. These findings indicate that throughput alone is insufficient to distinguish between flash crowds and DDoS attacks, whereas packet loss represents the most significant distinguishing parameter. All 19 digital evidence items (C-01–C-19) matched during SHA-256 hash verification, demonstrating that data integrity was preserved throughout the investigation. The study concludes that integrating TIPHON-based QoS analysis with digital forensics can support early detection and accurate investigation of network security incidents, particularly in hospital environments where high network reliability is essential.
Hybrid Particle Swarm and Chicken Swarm Optimization for Plant Disease Diagnosis using Leaf Images Rana Muayad Hasan
SISTEMASI Vol 15, No 8 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Universitas Islam Indragiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i8.6400

Abstract

Background: Plants play a vital role in sustaining life on Earth, particularly in maintaining ecological balance. They also contribute significantly to the economies of many countries and provide other valuable benefits. These plants are susceptible to many different diseases. Traditionally, trained specialists diagnose plant diseases based on their experience. However, this approach leads to problems, as diagnoses can vary from person to person. Objective: This work aims to present a novel approach to reduce errors and eliminate guesswork using a hybrid method. Methodology: We have developed a novel hybrid method combining Particle Swarm Optimization (PSO) and Chicken Swarm Optimization (CSO) algorithms to diagnose plant diseases in a group of ten species based on images of their leaves. Therefore, images of leaves from ten different plant species were collected and processed to improve contrast and remove noise. Using a statistical method incorporating hybrid classification, features were extracted. The method was applied to leaf images of ten different plant species, such as guava, jamun, mango, grape, apple, tomato, argon, and cherry, using a MATLAB simulation program. Results: The results for the hybrid method (PSO-CSO) achieved a diagnostic accuracy of 98.9%. Conclusions: The results indicate that the proposed model is an effective tool for the automated diagnosis of plant diseases. Future efforts may include expanding the database to include new crops and integrating the model into mobile applications for immediate field use.
Network Emergent Coverage Patterns from Stochastic Dynamic Models Ahmed Salih Hasan
SISTEMASI Vol 15, No 8 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Universitas Islam Indragiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i8.6831

Abstract

This work investigates the influence of the movement patterns (mobility) of network nodes on the overall performance of the network in terms of the area that can be covered by nodes' communications. This is important because, in urban areas, there are still areas that cannot be covered due to a lack of communication range of network nodes (sensors). Usually covering all areas may lead to a heavy cost due to the number of static sensors that might be implanted in particular areas. Therefore, this research comes to overcome this issue by testing a variety of mobility models and seeing which of them lead to a better performance. This work is based on simulations performed on a wide range of settings and variables such as mobility models, number of nodes within the network, network distribution of nodes, communication range of nodes, and other settings. The evaluation is based on the amount of area that is covered under particular settings. The findings show that the Exponential and Levy Flight models reflect the highest exploration efficiency (MNVL = 96.39 and 95.59 respectively). The Rayleigh Flight model show the largest average coverage area with alomost 36.3%. However, it shows high variability of CV=5.04%. The Levy with Exponential Cutoff model reflects high stability rate with CV=0.16% and moderate coverage of 31.7%.
Usability Analysis of the SIPBSI Website using the System Usability Scale as a Basis for Interface Improvement Priorities Kieky Adrian Sarwono; Charitas Fibriani (SCOPUS ID=57192643331)
SISTEMASI Vol 15, No 8 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Universitas Islam Indragiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i8.6814

Abstract

The Information System of the Indonesian Badminton Association (SIPBSI) is a web-based system designed to manage athlete, club, and ranking data in an integrated manner. The successful implementation of such a system is determined not only by its functionality but also by its level of usability, which influences user satisfaction and acceptance. However, the usability of SIPBSI from the users’ perspective has not yet been clearly established. This study aims to evaluate the usability level of the SIPBSI website using the System Usability Scale (SUS) and to develop prioritized recommendations for interface improvement. A quantitative approach was employed, with data collected through a SUS questionnaire administered to 30 respondents who were active club coaches in Salatiga City. The research procedures included calculating the SUS score, analyzing the mean scores of individual items, and mapping the results onto usability aspects, including learnability, consistency, complexity, need for assistance, and interface clarity. The results show that the SIPBSI website achieved an average SUS score of 62. Based on SUS interpretation, this score corresponds to Grade D, with an adjective rating of “Poor” and an acceptability rating of “Marginal.” Further analysis revealed that the main usability issues were related to need for assistance (2.20), learnability (2.22), consistency (2.30), complexity (2.33), and interface clarity (2.46). These findings indicate that the usability of the system still needs improvement, as usability issues may hinder the effectiveness of data management and access in supporting PBSI operations at both regional and national levels. The redesign recommendations focus on simplifying navigation and user flows, improving interface consistency, and providing clear instructions or user assistance features. This study is expected to serve as an evaluation reference and provide practical recommendations for developers to improve the quality and usability of the SIPBSI website.
Comparison of Sequential and Logarithmic Data Access Methods based on Archiving Scenarios Validity Evan Averill Andika; Bambang Agus Herlambang; Nur Latifah Dwi Mutiara Sari
SISTEMASI Vol 15, No 8 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Universitas Islam Indragiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i8.6768

Abstract

The growing volume of customer documents in financing companies presents challenges in archive retrieval when the search method is not well suited to increasing data volumes. This study aims to compare Linear Search and Binary Search methods within a web-based customer document archiving information system at PT Multindo Auto Finance. An experimental comparative analysis was conducted by empirically evaluating both algorithms under identical conditions and using the same dataset. The dataset consisted of 4,996 customer documents and was evaluated under two testing scenarios: searching for data that exists in the system and searching for data that does not exist. The primary performance metric was execution time, measured in milliseconds (ms). The results show that Binary Search outperformed Linear Search in both scenarios, achieving an execution time of 0.01 ms, while Linear Search required 0.09 ms when the target data was found and 0.23 ms when the target data was not found. However, Binary Search requires the data to be sorted, which may limit its suitability for systems containing frequently updated or dynamically changing data. The study concludes that Binary Search is recommended for large-volume systems with relatively static datasets, whereas Linear Search is more suitable for systems with dynamic datasets that are continuously updated.
LGI: Label-Graph Inference Multi-Benchmark Emotion Detection Transformer Framework for Intelligent Chatbots Karam Muayad Abdullah
SISTEMASI Vol 15, No 8 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Universitas Islam Indragiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i8.6669

Abstract

The fundamental ability of intelligent chatbots is to detecting emotions evident in intelligent recommendation systems, learning agent systems and mental health systems. Emotions are a key element in facilitating interaction and communication between humans. Researchers face challenges in studying the transmission of emotions through text. Despite significant advances in language transformation models, emotion recognition remains a major challenge due to the high semantic overlap between emotion categories and unbalanced distributions in datasets. This paper suggests an improved framework for enhanced transformer model based on a Label-Graph Interface (LGI) for ratings to robustly detect emotions across texts using various criteria specific to social media and conversations between humans and human-machine. It combines a pretrained transformer encoder with lightweight label relation inference layer that uses a row normalized graph prior and sample adaptive gate to propagate evidence among related emotion labels. In single label case, cross entropy loss is used to optimize the model, but in multi label detection a binary cross entropy is used with logits, class aware positive weighting and threshold selection based on validation sets. Six datasets were used in order to assess the framework: DAIR Emotion, achieved an macro-F1 to 89.10%. TweetEval Emotion is the second dataset reached an macro-F1 is 81.56%. DailyDialog, the macro-F1 arrived to 58.62%. GoEmotions, got micro-F1 about 60.03%. Empathetic Context dataset reached to 85.80% Top-3 accuracy and macro-F1 is 85.69% on the 32-class task. Lastly EmoWOZ is the most important dataset because it contains real conversation between human-machine has an accuracy about 92.86%, macro-F1 to 59.95% and AUC to 94.97%. The results demonstrate that the significant value and usefulness of relational inference at the classification level for emotion-based chatbot systems.
Enhancing DES Encryption Efficiency through a Metrics-Centric Pipeline and AI-Driven Analytical Framework Alaa Othman Mahmood
SISTEMASI Vol 15, No 8 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Universitas Islam Indragiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i8.6796

Abstract

This paper introduces an improved Data Encryption Standard (DES) framework that incorporates a metrics-driven data processing pipeline, AI-powered analytical decision support and a quantum-inspired entropy-based key generation process to enhance both encryption efficiency and key security. It validates data, preprocesses it, encodes it, optimizes it, encrypts it, monitors it in real-time, analyzes entropy and also analyzes the execution time, encryption speed, throughput, CPU utilization, memory consumption and key randomness. Experimental results indicate that the encryption throughput was achieved on average at 5.11 MB/s, with a maximum value of 12.15 MB/s, while the time required for encryption and decryption were on average 42.67 ms and 44.21 ms, respectively. The proposed quantum-inspired key generator has an average key entropy of 0.82 (compared with 0.68 for standard random keys) and a higher uniformity of 0.88 (compared with 0.72 for standard random keys), which corresponds to an approximately 20.6% improvement. Furthermore, the quantum-inspired approach achieved a maximum entropy of 0.95 compared with 0.89 for random generation, and its strongest keys had a collision rate of no more than 0.01%. The overall average security improvement for the AI analysis was 13.30% and the overall completion rate for the full processing pipeline was 98.50%. The findings highlight practical solutions for optimizing the performance, randomness, and security evaluation of DES-based encryption by incorporating AI-driven analysis, entropy-driven key generation, and regular monitoring.
Performance Evaluation of Plane Detection in Markerless Augmented Reality under Variations in Surface Characteristics and Light Intensity Muhammad Zaidaan Fadhlullah; Mulia Sulistiyono
SISTEMASI Vol 15, No 8 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Universitas Islam Indragiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i8.6834

Abstract

Plane detection is a key component of markerless augmented reality (AR) systems, as it determines the system’s ability to recognize surfaces for virtual object placement. However, plane detection performance is influenced by surface characteristics and lighting intensity, which can affect the quality and stability of feature points during the tracking process. This study aims to evaluate the performance of plane detection in a Unity-based markerless AR system using AR Foundation under varying surface characteristics and lighting intensities. The experiments were conducted using three surface types: highly textured, low-textured, and reflective surfaces, under three lighting conditions: bright, dim, and dark. Each scenario was tested five times using four evaluation parameters: tracking time, detection success rate, drift distance, and coverage area. The results show that highly textured surfaces provided the best overall performance across all evaluation parameters, with the fastest tracking time ranging from 2.82 to 6.66 seconds, a detection success rate of 100%, the lowest drift distance ranging from 0.04 to 1.55 cm, and a wider coverage area of 81.04% compared with the other conditions. In contrast, low-textured surfaces presented the most challenging condition, particularly under dark lighting, which resulted in detection failure across all trials. Meanwhile, reflective surfaces were still able to detect planes in most trials but exhibited reduced performance due to the instability of feature points caused by light reflections. Overall, the findings demonstrate that plane detection performance varies across different combinations of surface characteristics and lighting intensities.

Page 117 of 118 | Total Record : 1176

 114   115   116   117   118 

Filter by Year

2013 2026


Reset
Filter By Issues
All Issue Vol 15, No 8 (2026): Sistemasi: Jurnal Sistem Informasi Vol 15, No 7 (2026): Sistemasi: Jurnal Sistem Informasi Vol 15, No 6 (2026): Sistemasi: Jurnal Sistem Informasi Vol 15, No 5 (2026): Sistemasi: Jurnal Sistem Informasi Vol 15, No 4 (2026): Sistemasi: Jurnal Sistem Informasi Vol 15, No 3 (2026): Sistemasi: Jurnal Sistem Informasi Vol 15, No 2 (2026): Sistemasi: Jurnal Sistem Informasi Vol 15, No 1 (2026): Sistemasi: Jurnal Sistem Informasi Vol 14, No 6 (2025): Sistemasi: Jurnal Sistem Informasi Vol 14, No 5 (2025): Sistemasi: Jurnal Sistem Informasi Vol 14, No 4 (2025): Sistemasi: Jurnal Sistem Informasi Vol 14, No 3 (2025): Sistemasi: Jurnal Sistem Informasi Vol 14, No 2 (2025): Sistemasi: Jurnal Sistem Informasi Vol 14, No 1 (2025): Sistemasi: Jurnal Sistem Informasi Vol 13, No 6 (2024): Sistemasi: Jurnal Sistem Informasi Vol 13, No 5 (2024): Sistemasi: Jurnal Sistem Informasi Vol 13, No 4 (2024): Sistemasi: Jurnal Sistem Informasi Vol 13, No 3 (2024): Sistemasi: Jurnal Sistem Informasi Vol 13, No 2 (2024): Sistemasi: Jurnal Sistem Informasi Vol 13, No 1 (2024): Sistemasi: Jurnal Sistem Informasi Vol 12, No 3 (2023): Sistemasi: Jurnal Sistem Informasi Vol 12, No 2 (2023): Sistemasi: Jurnal Sistem Informasi Vol 12, No 1 (2023): Sistemasi: Jurnal Sistem Informasi Vol 11, No 3 (2022): Sistemasi: Jurnal Sistem Informasi Vol 11, No 2 (2022): Sistemasi: Jurnal Sistem Informasi Vol 11, No 1 (2022): Sistemasi: Jurnal Sistem Informasi Vol 10, No 3 (2021): Sistemasi: Jurnal Sistem Informasi Vol 10, No 2 (2021): Sistemasi: Jurnal Sistem Informasi Vol 10, No 1 (2021): Sistemasi: Jurnal Sistem Informasi Vol 9, No 3 (2020): Sistemasi: Jurnal Sistem Informasi Vol 9, No 2 (2020): Sistemasi: Jurnal Sistem Informasi Vol 9, No 1 (2020): Sistemasi: Jurnal Sistem Informasi Vol 8, No 3 (2019): Sistemasi: Jurnal Sistem Informasi Vol 8, No 2 (2019): Sistemasi: Jurnal Sistem Informasi Vol 8, No 1 (2019): Sistemasi Vol 8, No 1 (2019): Sistemasi: Jurnal Sistem Informasi Vol 7, No 3 (2018): Sistemasi: Jurnal Sistem Informasi Vol 7, No 2 (2018): Sistemasi: Jurnal Sistem Informasi Vol 7, No 2 (2018): SISTEMASI Vol 7, No 1 (2018): Sistemasi: Jurnal Sistem Informasi Vol 6, No 3 (2017): Sistemasi: Jurnal Sistem Informasi Vol 6, No 2 (2017): Sistemasi: Jurnal Sistem Informasi Vol 6, No 1 (2017): Sistemasi: Jurnal Sistem Informasi Vol 5, No 3 (2016): Sistemasi: Jurnal Sistem Informasi Vol 5, No 2 (2016): sistemasi Vol 5, No 2 (2016): Sistemasi: Jurnal Sistem Informasi Vol 5, No 1 (2016): Sistemasi: Jurnal Sistem Informasi Vol 4, No 3 (2015): Sistemasi: Jurnal Sistem Informasi Vol 4, No 2 (2015): Sistemasi: Jurnal Sistem Informasi Vol 4, No 1 (2015): Sistemasi: Jurnal Sistem Informasi Vol 3, No 4 (2014): SISTEMASI: Jurnal Sistem Informasi Vol 3, No 3 (2014): Sistemasi: Jurnal Sistem Informasi Vol 3, No 2 (2014): Sistemasi: Jurnal Sistem Informasi Vol 3, No 1 (2014): Sistemasi: Jurnal Sistem Informasi Vol 2, No 4 (2013): Sistemasi: Jurnal Sistem Informasi Vol 2, No 3 (2013): Sistemasi: Jurnal Sistem Informasi Vol 2, No 2 (2013): Sistemasi:Jurnal Sistem Informasi Vol 2, No 1 (2013): Sistemasi: Jurnal Sistem Informasi More Issue