cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Muhammad Wali
Contact Email
muhammadwali@amikindonesia.ac.id
Phone
+6285277777449
Journal Mail Official
ijsecs@lembagakita.org
Editorial Address
Jl. Teuku Nyak Arief No. 7b 23112, Kota Banda Aceh, Banda Aceh, Provinsi Aceh
Location
,
INDONESIA
International Journal Software Engineering and Computer Science (IJSECS)
Published by Lembaga Komunitas Informasi Teknologi Aceh
ISSN : 27764869     EISSN : 27763242     DOI : https://doi.org/10.35870/ijsecs
Core Subject : Science,
Computer Science & IT
IJSECS is committed to bridge the theory and practice of information technology and computer science. From innovative ideas to specific algorithms and full system implementations, IJSECS publishes original, peer-reviewed, and high quality articles in the areas of information technology and computer science. IJSECS is a well-indexed scholarly journal and is indispensable reading and references for people working at the cutting edge of information technology and computer science applications..
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 423 Documents
 39   40   41   42   43 
Analysis and Implementation of a Hybrid Case-Based Reasoning and K-Nearest Neighbor Approach for Chronic Kidney Disease Prediction Hananing Sumaningdiah Larasati; Shella Sukma Dewi Waramena; Wulan Pahira
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 1 (2026): APRIL 2026
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET) - Lembaga KITA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i1.6894

Abstract

Chronic Kidney Disease (CKD) is a progressive deterioration of kidney function that frequently goes undetected in its early stages, posing a growing clinical concern — particularly among productive-age individuals whose diagnosis is often delayed until irreversible damage has occurred. Early and accurate prediction remains a pressing challenge, especially given the rising CKD incidence in this demographic linked to hypertension, diabetes, and shifting lifestyle patterns. This study developed a hybrid method combining Case-Based Reasoning (CBR) with weighted similarity and K-Nearest Neighbor (KNN) to improve prediction accuracy while preserving model interpretability. The dataset was obtained from the UCI Machine Learning Repository and filtered for productive-age individuals aged 15–64 years, yielding 288 instances after preprocessing. Attribute weighting was performed using Information Gain to reflect the varying diagnostic relevance of each variable, and inter-case similarity was measured through a weighted similarity approach. Classification was then carried out using KNN across multiple K values. At K = 2, the proposed method achieved an accuracy of 98.26%, with precision, recall, and F1-score each recorded at 0.983 — results that suggest the hybrid CBR-KNN approach is well-suited for deployment as a clinical decision support system for early CKD detection.
Sentiment and Public Emotion Classification of Viral Content Using Transformer-Based Model Ferdi Antonio; Handry Eldo; Arrazy Elba Ridha; Iwan Adhicandra; Cut Susan Octiva
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 1 (2026): APRIL 2026
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET) - Lembaga KITA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i1.6969

Abstract

The proliferation of social media platforms has generated an unprecedented volume of viral content, each drawing varied public responses expressed through sentiment and emotion. Mapping those responses — not merely counting them — is what separates surface-level monitoring from a genuine understanding of public perception. This study classified sentiment (positive, negative, neutral) and emotion (anger, joy, sadness, and fear) toward viral content using a fine-tuned Transformer-based model. Data were collected from social media via web scraping, then subjected to standard text preprocessing: case folding, tokenization, stopword removal, and stemming. The cleaned dataset was subsequently annotated with sentiment and emotion labels. BERT (Bidirectional Encoder Representations from Transformers) served as the base architecture, fine-tuned for multi-label classification. Evaluation relied on an 80:20 train-test split, with performance measured through accuracy, precision, recall, and F1-score. Across all sentiment and emotion categories, the model returned consistently high scores and handled ambiguous, context-dependent text more reliably than conventional machine learning baselines. The Transformer-based approach proved well-suited for sentiment and emotion analysis on social media data, with clear potential for deployment in public opinion monitoring systems.
Design and Feasibility Evaluation of Redux Toolkit-Based State Management in a React Reservation Prototype (CoSpace) Hussein Nurrokhim; Alz Danny Wowor
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 1 (2026): APRIL 2026
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET) - Lembaga KITA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i1.7046

Abstract

This study examines the design and feasibility evaluation of a React-based coworking space reservation prototype named CoSpace, with Redux Toolkit applied as the state management architecture. The study was motivated by manual reservation processes that tend to produce delayed responses, recording errors, and schedule conflicts. A Research and Development (R&D) approach was employed, covering requirements analysis, system design, prototype implementation, functional testing, and user acceptance evaluation. Black Box Testing confirmed that all functional scenarios operated according to the intended design, including schedule conflict validation and role-based access restriction. User Acceptance Testing (UAT) involving 35 respondents produced an overall feasibility score of 95.4%, placing the prototype in the Very Feasible category. Within the scope of this prototype, Redux Toolkit supported centralized organization of application state and business logic — particularly through slice-based state separation and thunk-based reservation approval. The evaluation, however, was confined to a mock-data environment and did not compare Redux Toolkit against alternative state management approaches. Future work should integrate a real backend service and examine system behavior under multi-user operational conditions.
Driver Drowsiness Detection Using Multi-Metric Modeling Based on Facial Landmarks Ferry Angga Wijaya; T. Tamil Arsen; Ayu Endang Syah Putri; Mika Damayanti; Yennimar Yennimar
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 1 (2026): APRIL 2026
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET) - Lembaga KITA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i1.7106

Abstract

Drowsiness is a major factor contributing to traffic accidents, as it significantly reduces driver alertness, reaction time, and decision-making ability. This study aims to develop a real-time driver drowsiness detection system based on multi-metric modeling using facial landmarks. Three physiological indicators were employed: Eye Aspect Ratio (EAR) to measure eye openness, Mouth Aspect Ratio (MAR) to identify yawning activity, and Percentage of Eye Closure (PERCLOS) to assess prolonged eye closure patterns. These features were extracted using MediaPipe Face Landmarker, a lightweight and efficient facial landmark detection framework. A quantitative approach with a rule-based method was applied without requiring machine learning training, making the system computationally efficient and easily deployable. Sliding window smoothing was incorporated to reduce false detections and improve overall detection stability. The system was implemented as an Android mobile application and evaluated in real-time conditions using the device's front camera. Experimental results demonstrate that PERCLOS serves as the most stable and reliable drowsiness indicator, while the integration of all three metrics yields significantly more accurate detection compared to relying on a single indicator alone. This system offers a promising non-intrusive, accessible, and practical solution for real-time driver monitoring.
Dual-Band Microstrip Antenna Design for 2.4 GHz and 5.3 GHz WiFi Networks Muhammad Zainul Arifin; Syah Alam
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 1 (2026): APRIL 2026
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET) - Lembaga KITA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i1.7143

Abstract

This study reports the design and simulation of a dual-band rectangular patch microstrip antenna intended for Wi-Fi applications at 2.4 GHz and 5.3 GHz. Initial patch dimensions were derived analytically at 2.4 GHz, then refined through an iterative optimization process involving the progressive insertion of vertical slots on the radiating patch. Three iterations were performed, each modifying slot length and width to shift the second resonant frequency toward the 5.3 GHz target while preserving the first resonance at 2.4 GHz. The finalized design resonated at approximately 2.49 GHz and 5.3 GHz, with return loss values of −16.11 dB and −15.5 dB, respectively — both satisfying the −10 dB threshold commonly adopted as the minimum criterion for acceptable antenna matching. VSWR values of 2.945 at 2.493 GHz and 2.613 at 5.3 GHz were recorded; these remain above the ideal upper bound of 2, indicating that impedance matching between the antenna and the feed line has not been fully resolved. Measured bandwidths were 143 MHz at 2.498 GHz and 2.8 MHz at 5.3 GHz, with the notably narrow bandwidth at the higher frequency representing a practical limitation that warrants further attention. Gain at 2.498 GHz reached 6.01 dBi, while the value at 5.2 GHz dropped to −4.369 dBi, suggesting that the slot geometry, though effective for frequency tuning, introduced radiation efficiency losses at the upper band. Taken together, the results confirm that vertical slot insertion is a viable technique for generating dual-band resonance in a rectangular patch microstrip antenna; the approach, however, requires additional refinement — particularly in impedance matching and upper-band gain recovery — before the design can be considered fully deployment-ready.
Application of the Linear Congruential Generator Method in a Number-Guessing Game Efani Desi
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 1 (2026): APRIL 2026
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET) - Lembaga KITA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i1.7158

Abstract

Number guessing games occupy a deceptively simple position in the landscape of interactive software — easy to play, yet dependent on a mechanism that most players never think about: the quality of the number being generated. If that number is predictable, the game collapses. If it is genuinely unpredictable, the experience holds. This study applies the Linear Congruential Generator (LCG) method as the core algorithm for random number generation in a number-guessing game operating within the range of 1 to 100. LCG was selected not because it is the most statistically sophisticated option available, but because its computational simplicity and deterministic structure make it well-suited to lightweight game applications where speed and transparency of implementation matter more than cryptographic strength. Four parameters govern the algorithm's behavior — modulus, multiplier, increment, and seed — and each was configured deliberately to produce a distribution that remains acceptably uniform across repeated sessions. The seed value, generated dynamically at runtime, ensures that no two sessions begin from the same starting point, which is the primary mechanism for maintaining unpredictability from the player's perspective. Test results indicate that the application performs adequately: number distribution is reasonably balanced, the interface responds correctly to valid and invalid inputs, and the overall gameplay experience is fair. A more critical reading of the results, however, reveals that LCG carries inherent trade-offs — its period is finite, and under certain parameter configurations, detectable patterns can emerge in the generated sequence. For a single-player guessing game, these limitations are largely inconsequential. For applications requiring stronger statistical guarantees, they would not be. The application was built using Python with a graphical interface constructed through the tkinter library, making it accessible to users without any technical background. This study is intended as a practical reference for developers building number-based games and as a modest contribution to the applied literature on pseudo-random number generation in educational software.
Risk Management Evaluation Based on ISO/IEC 27005 Framework: A Case Study of ABC Company IT Workshop Room Muhammad Ferdi Kurniawan; Triana Dewi Salma
International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 2 (2025): AUGUST 2025
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET) - Lembaga KITA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v5i2.4549

Abstract

ABC Company operates as a technology firm based in France, maintaining its research and development operations in Jakarta. The company produces digital security technologies—biometrics, facial recognition systems, and digital identity solutions—alongside telecommunications and payment products including SIM cards, banking cards, and smart cards. Given how much the company relies on technology and secure information handling, it needs strong systems and infrastructure, especially when dealing with sensitive data. Yet no one has conducted a risk management assessment of the IT workshop room. Several problems have emerged with the physical security of this important area, such as people misusing access privileges and assets going missing. This research evaluates how the company manages information security risks by first identifying what's causing these problems through a fishbone diagram that looks at people, technology, and processes. We then assessed risks using the ISO/IEC 27005:2018 standard across 12 assets, examining threats, current controls, weak points, and what treatments are needed. Our analysis shows three assets (A5, A6, A7) carry high risk, three others (A4, A9, A12) have medium risk, and six assets (A1, A2, A3, A8, A10, A11) present low risk. Using these results, we developed specific recommendations for handling risks associated with each asset to improve information security throughout the company.
Forecasting Accuracy Analysis of Catering Raw Material Stock Using Simple Exponential Smoothing Based on Mean Absolute Percentage Error (MAPE) Dimas Eko Prasetyo; Endin Fahrudin
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 1 (2026): APRIL 2026
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET) - Lembaga KITA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i1.7039

Abstract

In the catering industry, inaccurate inventory management often leads to significant food waste or stockouts due to highly volatile raw material demand, and conventional intuition-based procurement methods are no longer sufficient to maintain operational efficiency. This research applies to the Simple Exponential Smoothing (SES) algorithm to forecast raw material requirements and evaluates its accuracy using the Mean Absolute Percentage Error (MAPE) metric. Twelve months of historical transaction data from a local catering business were analyzed, categorized into basic commodities, proteins, and vegetables, with the SES model calibrated by testing smoothing constants ( ) across the range of 0.1 to 0.9. The findings indicate that stable items such as rice achieve the highest accuracy at a low of 0.2, yielding a MAPE of 4.25% — classified as Very Good. Highly volatile items such as proteins and fresh vegetables require a high of 0.8–0.9 to remain responsive, producing MAPE values between 12.40% and 18.15%, classified as Good. These results confirm that SES offers a defensible, data-grounded decision-making structure that measurably reduces forecasting errors and improves procurement cost management in the catering sector.
Implementation of a Mental Health Care Website for Psychological Counseling and Education Based on Spring Boot and Tailwind CSS Yosua Christian Prasetio; Yeremia Alfa Susetyo
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 1 (2026): APRIL 2026
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET) - Lembaga KITA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i1.7132

Abstract

The increasing demand for mental health services among young people in Indonesia is not matched by adequate accessibility due to constraints related to time, cost, and social stigma. This study aims to implement a "Mental Health Care" website as an online counseling and psychological education platform by integrating the Spring Boot framework on the backend and Tailwind CSS on the frontend. The development method used is the Waterfall model, which includes the stages of problem identification, system analysis and design, implementation, and testing. The system is designed using a three-layer architecture consisting of a frontend layer based on Vanilla JavaScript and Tailwind CSS, a backend layer based on Spring Boot with Spring Security for authentication and authorization, and a database layer using MongoDB. The main features implemented include real-time online counseling using WebSocket (SockJS & StompJS), an artificial intelligence assistant powered by Gemini AI through Spring AI, MBTI psychological tests, access to psychological educational e-books, a per-session payment system, and authentication via Google OAuth2. Testing is conducted using the Black-box Testing method and interface responsiveness testing to validate system functionality and compatibility across various devices. The results of this study indicate that all 12 functional test scenarios passed with no failures detected, and interface responsiveness testing confirmed full compatibility across Desktop (1920×1080), Tablet (768×1024), and Mobile (375×667) devices. These findings demonstrate that the integration of Spring Boot and Tailwind CSS can produce a functional, secure, responsive, and accessible platform, making it a potential technological solution to improve the accessibility of mental health services and psychological literacy in the digital era.
Comparative Analysis of BGP, OSPF, and RIP Dynamic Routing Protocols in Metro Ethernet Network and Broadband Service Implementation Ekie Revsie Akbar; Try Mulyoto; Imelda Imelda
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 1 (2026): APRIL 2026
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET) - Lembaga KITA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i1.7141

Abstract

The reliability of Internet Service Provider (ISP) networks increasingly depends on the routing protocols employed to manage traffic across distributed infrastructure. This study investigates and compares the operational performance of three widely adopted dynamic routing protocols — Border Gateway Protocol (BGP), Open Shortest Path First (OSPF), and Routing Information Protocol (RIP) — deployed across the Metro Ethernet network of PT Kreatif Data Prima Nusantara, a regional ISP located in Kedaton, Bandar Lampung, Indonesia. The existing network architecture relies on a combined deployment of static routing and OSPF distributed across four Points of Presence (POP): QNN, Tamin, Labuhan Dalam, and INQI. This hybrid configuration has repeatedly produced prolonged convergence delays, operational complexity in fault isolation, and constrained scalability. A simulation-based experimental methodology was adopted, replicating the physical network topology using MikroTik RouterOS-based Cloud Core Routers (CCR). Key performance indicators evaluated include convergence time, CPU utilization, bandwidth overhead, and overall network availability. Experimental outcomes clearly show BGP's superior performance: an average convergence time of 18.36 seconds — substantially faster than RIP's 28.34 seconds and more resource-efficient across all measured dimensions, despite OSPF's faster raw reconvergence at 3.21 seconds; CPU utilization of only 11% compared to 19% for OSPF and 38% for RIP; and bandwidth overhead of 1.9 Kbps versus 9.2 Kbps for OSPF and 26.8 Kbps for RIP. BGP also recorded the highest network availability at 99.98%. The simulation topology encompasses four POPs — a relatively small-scale environment — and results should be read within that scope. These findings support the recommendation that PT Kreatif Data Prima Nusantara adopt a full BGP deployment as its primary routing strategy to improve long-term operational efficiency, network manageability, and service reliability.

Page 42 of 43 | Total Record : 423

 39   40   41   42   43 

Filter by Year

2021 2026


Reset
Filter By Issues
All Issue Vol. 6 No. 1 (2026): APRIL 2026 Vol. 5 No. 3 (2025): DECEMBER 2025 Vol. 5 No. 2 (2025): AUGUST 2025 Vol. 5 No. 1 (2025): APRIL 2025 Vol. 4 No. 3 (2024): DECEMBER 2024 Vol. 4 No. 2 (2024): AUGUST 2024 Vol. 4 No. 1 (2024): APRIL 2024 Vol. 3 No. 3 (2023): DECEMBER 2023 Vol. 3 No. 2 (2023): AUGUST 2023 Vol. 3 No. 1 (2023): APRIL 2023 Vol. 2 No. 2 (2022): OCTOBER 2022 Vol. 2 No. 1 (2022): MAY 2022 Vol. 1 No. 2 (2021): AUGUST 2021 Vol. 1 No. 1 (2021): APRIL 2021 More Issue