cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Elsa Aditya
Contact Email
redaksijurnalupu@gmail.com
Phone
+6285175205250
Journal Mail Official
redaksijurnalupu@gmail.com
Editorial Address
JL. KL. Yos Sudarso Km. 6,5 No. 3A, Tanjung Mulia, Medan, Sumatera Utara, 20241
Location
Kota medan,
Sumatera utara
INDONESIA
CSRID
Published by Universitas Potensi Utama
ISSN : 20851367     EISSN : 2460870X     DOI : https://doi.org/10.22303/csrid
Core Subject : Science,
Computer Science & IT
CSRID (Computer Science Research and Its Development Journal) is a scientific journal published by LPPM Universitas Potensi Utama in collaboration with professional computer science associations, Indonesian Computer Electronics and Instrumentation Support Society (IndoCEISS) and CORIS (Cooperation Research Inter University).
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 161 Documents
 13   14   15   16   17 
Classification of Film Genres Based on Synopsis Using Support Vector Machine (SVM) Method with TF-IDF and N-Gram Rita Novita Sari; Dea Alya; Dodyk Fahlome
CSRID (Computer Science Research and Its Development Journal) Vol. 18 No. 2 (2026): Juni 2026
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.18.2.2026.381-394

Abstract

With the wide variety of film genres available, audiences often face difficulties in determining a movie’s genre solely based on its synopsis. Therefore, an automated system is needed to classify movie genres effectively. This study aims to classify movie genres based on film synopses using the Support Vector Machine (SVM) method combined with TF-IDF and N-Gram feature extraction techniques. The dataset used in this research was obtained from Kaggle and consisted of 10,000 movie records with multi-label characteristics, which were subsequently transformed into Single-label data. Four main genres were selected, namely Action, Comedy, Drama, and Horror, resulting in a final dataset of 6,000 records. The research process included data preparation, text preprocessing, TF-IDF feature extraction using unigram and bigram models, data splitting, and model evaluation. All data processing procedures were carried out in Google Colab using the Python programming language. The evaluation results indicate that the SVM model with a linear kernel achieved an accuracy of 83%. The Horror genre demonstrated the best performance, with a precision value of 91%, recall of 92%, and F1-score of 92%. These findings suggest that the combination of TF-IDF, N-Gram, and SVM provides satisfactory results for movie genre classification based on film synopses.
E-Canteen Universitas Al Washliyah Labuhanbatu Berbasis WEB Selamat Subagio; Samsir; Muhammad Rusdi
CSRID (Computer Science Research and Its Development Journal) Vol. 18 No. 2 (2026): Juni 2026
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.18.2.2026.395-408

Abstract

The rapid advancement of information technology has driven significant changes across various sectors, including facility management within higher education institutions. The Universitas Al Washliyah Labuhanbatu canteen—a crucial facility supporting daily campus activities—frequently faces operational challenges. These issues include long customer queues during break times, a lack of transparency in financial record-keeping, and difficulties for canteen owners in monitoring real-time stock levels. To address these problems, this study aimed to design and implement a web-based e-canteen management system. The system was designed to integrate the functional needs of students and lecturers (as buyers), canteen owners (as sellers), and campus administrators. The development process adopted the System Development Life Cycle (SDLC) methodology, encompassing user requirements analysis, database modeling (using ERD and DFD), and coding utilizing HTML, CSS, PHP, and MySQL technologies. Functionality testing demonstrated that the e-canteen application successfully reduces customer waiting times through an online ordering feature, provides clear digital cash flow records for management, and minimizes errors in product inventory tracking. The implementation of this platform is expected to accelerate digital transformation and help realize the "smart campus" concept at Universitas Al Washliyah Labuhanbatu.
Pengembangan Sistem Pendukung Keputusan Pemilihan Siswa Berprestasi Berbasis Multi-Kriteria Menggunakan Metode Simple Additive Weighting (SAW) pada Sekolah Menengah Kejuruan Samsir; Maisarah Ritonga; Muhammad Siddik
CSRID (Computer Science Research and Its Development Journal) Vol. 18 No. 2 (2026): Juni 2026
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.18.2.2026.205-217

Abstract

The selection process of outstanding students in Vocational High Schools (SMK) often suffers from subjectivity and inefficiency due to manual assessment procedures. This study aims to develop a web-based Decision Support System (DSS) using the Simple Additive Weighting (SAW) method to determine outstanding students more objectively. The system integrates three achievement categories—academic, professional, and sports achievements—represented by nine evaluation indicators with different weights according to their importance. The SAW method was applied through decision matrix construction, normalization, weighting, and preference value calculation. The results show that the best alternative obtained a preference value of 6.77 and was recommended as the outstanding student. Black Box testing indicated that all system functions operated successfully with a 100% success rate. Furthermore, the system reduced the selection process time from 40 minutes to 8 minutes, representing an 80% efficiency improvement compared with the manual process. These findings demonstrate that the implementation of the SAW method effectively improves objectivity, transparency, and efficiency in the outstanding student selection process in vocational high schools.
Sistem Pakar Deteksi Penyakit THT Menggunakan Metode SAW Samsir; Muhammad siddik; Azrai Sirait
CSRID (Computer Science Research and Its Development Journal) Vol. 18 No. 2 (2026): Juni 2026
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.18.2.2026.409-425

Abstract

Ear, Nose, and Throat (ENT) disorders are common health issues that require timely intervention from the early stages to prevent complications. However, a shortage of ENT specialists and the unequal distribution of healthcare services hinder optimal consultation and initial diagnosis, particularly in areas with limited access to healthcare. While various studies have developed disease diagnosis systems using inference methods—such as Forward Chaining and Certainty Factor—the application of the Simple Additive Weighting (SAW) method as a Multi-Criteria Decision Making (MCDM) approach to rank potential diseases based on symptom combinations remains relatively limited. This study aims to develop a web-based expert system for the initial diagnosis of ENT disorders by utilizing a knowledge base derived from ENT specialists and implementing the SAW method as a decision-making mechanism to identify the most likely disease (the alternative with the highest preference value). The knowledge base is represented through relationships between symptoms, diseases, symptom weights, and management guidelines. The diagnostic process involves constructing a decision matrix, normalizing values, weighting symptoms, and calculating preference values ​​using the SAW method. Developed using PHP and MySQL, the system provides initial diagnostic recommendations and management advice based on user-selected symptoms. This research contributes by applying the SAW method as a multi-criteria decision-making mechanism within an ENT diagnosis system, thereby making the process of identifying potential diseases more systematic, transparent, and adaptable to changes in the knowledge base
Pengembangan Sistem Informasi Laporan Praktik Kerja Lapangan Mahasiswa Berbasis Web Menggunakan Metode Waterfall di Universitas Alwashliyah Labuhanbatu Abdul Hakim Dalimunthe; Selamat Subagio; Samsir
CSRID (Computer Science Research and Its Development Journal) Vol. 18 No. 2 (2026): Juni 2026
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.18.2.2026.232-244

Abstract

The management of Field Work Practice (PKL) reports at the Faculty of Computer Science, Alwashliyah University (UNIVA) Labuhanbatu, is currently handled manually, leading to various issues such as delayed report submissions, document archiving difficulties, ineffective supervision monitoring, and slow grading processes by supervisors. This research aims to develop a web-based PKL report information system capable of centrally integrating administrative processes—ranging from student data management, placement, and report uploading to supervision monitoring and grading. The system was developed using the Waterfall method, comprising stages for requirements analysis, system design, implementation, testing, and maintenance. It was built using PHP, MySQL, and the Bootstrap framework. System testing employed the Black Box Testing method across 25 scenarios covering user authentication, management of student, lecturer, and industry partner (DU/DI) data, report uploads, the supervision process, and grading. Test results demonstrated that all scenarios executed successfully according to functional requirements, achieving a 100% success rate. Implementing this system improves the efficiency of PKL administration, accelerates information exchange among students, supervisors, and administrators, and results in report archiving that is more structured, well-documented, and accessible compared to the manual process.
Sistem Pendukung Keputusan Pemilihan Pengobatan Tradisional Kardivaskular Dengan Metode SAW Rahmad Aditiya; Samsir; Reagan Surbakti Saragih
CSRID (Computer Science Research and Its Development Journal) Vol. 18 No. 2 (2026): Juni 2026
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.18.2.2026.287-299

Abstract

Cardiovascular disease is one of the leading causes of death worldwide and requires appropriate treatment and therapy selection. In addition to conventional medical treatment, traditional herbal medicine is widely used as an alternative therapy. However, the large number of available herbal remedies often makes it difficult for people to determine the most appropriate option. This study aims to develop a web-based Decision Support System (DSS) to recommend traditional herbal treatments for cardiovascular diseases using the Simple Additive Weighting (SAW) method. The SAW method was implemented through the stages of alternative determination, criteria identification, criteria weighting, decision matrix construction, normalization, preference value calculation, and ranking. The system was developed using PHP and MySQL and evaluated through Black Box Testing. The results indicate that the system is capable of integrating disease data, symptom data, herbal treatment alternatives, and evaluation criteria to generate recommendations based on the highest preference values. Based on the SAW calculation, A1 (Garlic) achieved the highest preference value of 0.94, followed by A5 (0.91) and A7 (0.89), making it the most recommended traditional treatment according to the criteria of treatment effectiveness, cost, side effects, and herbal availability. The system testing results also showed that all major functions operated as expected. Therefore, the SAW method can be effectively applied as a simple, objective, and practical decision-making approach for recommending traditional treatments for cardiovascular diseases.
Pemodelan Risiko dan Upaya Mitigasi Serangan Route Hijacking Terhadap Sistem Informasi Akademik Kampus Dengan RPKI: Risk Modeling and Mitigation Efforts for Route Hijacking Attacks on a Campus Academic Information System Using RPKI Raja Hafiza Ramanda Putra; Linna Oktaviana Sari
CSRID (Computer Science Research and Its Development Journal) Vol 18 No 3 (2026): Oktober 2026
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.18.3.2026.439-456

Abstract

Route hijacking attacks on the Border Gateway Protocol (BGP) pose a serious threat to the reliability of campus Academic Information System services. One common form is route origin change, where an unauthorized Autonomous System (AS) announces IP prefixes belonging to another party. This study aims to model the risk and analyze its impact on service availability. The methodology uses a routing topology model involving internal, transit, external, and attacker routers in a controlled environment. The results show that prefixes announced by unauthorized ASes can be accepted and replace valid routes due to the lack of origin validation, causing traffic to be misdirected. This condition creates risks such as traffic redirection, credential theft, and reduced service reliability. As a mitigation effort, Resource Public Key Infrastructure (RPKI) is implemented through Route Origin Authorization (ROA) and Route Origin Validation (ROV), which effectively reject invalid routes and ensure traffic remains on legitimate paths.
Analisis Kinerja Protokol MQTT pada Sistem IoT Monitoring Tanaman Elisa Soleha; Linna Oktaviana Sari
CSRID (Computer Science Research and Its Development Journal) Vol 18 No 3 (2026): Oktober 2026
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.18.3.2026.474-490

Abstract

This study analyzes the effect of varying Quality of Service (QoS) levels 0, 1, and 2 in the MQTT protocol on network performance parameters in an IoT monitoring system for chili plants. The research uses an experimental method with a quantitative approach in a controlled local WiFi network environment. The IoT system is built using an ESP32 microcontroller equipped with a DHT22 sensor (temperature and air humidity), a capacitive soil moisture sensor, and a GY-2561 light intensity sensor, connected to a Mosquitto MQTT broker. Network performance parameters measured include delay, throughput, packet loss, bandwidth consumption, and jitter using Wireshark software. Each QoS scenario was run for 30 minutes with data transmission intervals of 5 seconds, generating a minimum of 360 packet samples per QoS level. Test results show that QoS 0 has the highest average delay (2,609.70 ms), QoS 1 with 2,488.51 ms, while QoS 2 produces the lowest delay (1,246.76 ms). Jitter values indicate QoS 2 is most stable (130.07 ms), QoS 0 (190.04 ms), and QoS 1 highest (276.50 ms). Packet loss across all QoS levels is below 1%, with QoS 2 being lowest. Bandwidth consumption increases with QoS level: QoS 0 (0.31 Kbps), QoS 1 (0.32 Kbps), and QoS 2 (0.51 Kbps). Throughput is consistent across all levels (0.23 Kbps). This study provides QoS configuration recommendations based on system requirements: QoS 0 for bandwidth efficiency, QoS 1 for reliability-efficiency balance, and QoS 2 for maximum reliability.
Classification of Low-Level Wind Shear on Imbalanced Radiosonde Data Using a Hybrid CNN-LSTM Architecture Sarnubih Hasan; Agung Budi Susanto; Arya Adhyaksa Waskita
CSRID (Computer Science Research and Its Development Journal) Vol 18 No 3 (2026): Oktober 2026
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.18.3.2026.426-438

Abstract

Low-Level Wind Shear (LLWS) during the takeoff and landing phases poses a severe and dynamic threat to aviation safety. However, it remains inherently challenging to detect directly from surface observations due to its highly non-linear, transient, and sequential nature in the lower atmosphere. This study proposes an advanced deep learning approach to classify LLWS events based on high-resolution vertical radiosonde profile data spanning the 2024–2025 period at Soekarno-Hatta International Airport, Indonesia. Addressing the critical challenge of a highly imbalanced dataset—where hazardous meteorological events are exceptionally rare compared to normal atmospheric conditions—the classification target was simplified into an event-level binary scheme. This scheme utilizes a hazard intensity threshold of ≥ 4 knots/100 ft, adhering strictly to the International Civil Aviation Organization (ICAO) moderate-to-severe hazard categories. The comprehensive research methodology involved fixed-grid interpolation into 21 uniform vertical observation points (spanning 0 to 2000 ft), rigorous wind vector transformation into zonal and meridional components, and circular encoding for wind direction to maintain absolute numerical stability during model training. A hybrid Convolutional Neural Network and Long Short-Term Memory (CNN-LSTM) architecture was developed to capture both local spatial gradients and long-term vertical dependencies, which was then systematically compared against a Transformer baseline equipped with a global self-attention mechanism. The empirical results and operational discussion demonstrate that the proposed CNN-LSTM model significantly outperformed the Transformer baseline, achieving an outstanding Area Under the Precision-Recall Curve (PR-AUC) of 0.9672 compared to the Transformer's 0.7533. Furthermore, the confusion matrix analysis conclusively proved the superior capability of the CNN-LSTM network in minimizing false negatives (missed detections) from 17 down to merely 7 critical events. In conclusion, the integration of local feature extraction through CNN and sequential dependency modeling via LSTM is highly effective for addressing imbalanced meteorological datasets, providing a highly robust and physically consistent computational foundation for automated aviation safety early warning systems.
Performance Analysis of CatBoost, XGBoost and Random Forest Models for Cloud Top Height Predicition Using Satelliite Data Ade Sekarningsih; Choirul Basir; Sudarno
CSRID (Computer Science Research and Its Development Journal) Vol 18 No 3 (2026): Oktober 2026
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.18.3.2026.457-473

Abstract

Cloud Top Height (CTH) is a critical parameter for convective weather monitoring and aviation meteorology, particularly over the Indonesian maritime continent, where deep convection occurs frequently. This study evaluates the predictive performance and behavior of three tree-based ensemble models XGBoost, CatBoost, and Random Forest—for estimating CTH from Himawari multispectral observations using the Sentinel-5P/TROPOMI CTH product as the reference. The input variables comprise Himawari brightness-temperature channels, cloud fraction, latitude, and longitude. Evaluation on an independent spatial validation set of 3,444,543 observations shows that XGBoost achieved the best aggregate performance, with a mean absolute error of 971.71 m, root mean square error of 1297.57 m, coefficient of determination of 0.646, and mean bias of -33.55 m. CatBoost and Random Forest produced RMSE values of 1340.95 m and 1371.11 m, respectively. Multi-method interpretability analysis using built-in importance, permutation importance, group permutation, SHAP, partial dependence, and individual conditional expectation indicates that spectral channels and cloud fraction are the principal information sources, whereas coordinates provide weaker but non-zero spatial context. The error audit reveals relatively stable predictions for mid-level clouds but strong underprediction for extremely high cloud tops. Inter-model disagreement is positively but weakly related to actual error, indicating that it is a useful diagnostic signal rather than a calibrated uncertainty estimate. These results demonstrate that model selection for operational meteorology should consider not only aggregate accuracy but also error regimes, spatial dependence, and physical consistency.

Page 16 of 17 | Total Record : 161

 13   14   15   16   17 

Filter by Year

2022 2026


Reset
Filter By Issues
All Issue Vol 18 No 3 (2026): Oktober 2026 Vol. 18 No. 2 (2026): Juni 2026 Vol. 18 No. 1 (2026): Februari 2026 Vol. 17 No. 3 (2025): Oktober 2025 Vol. 17 No. 2 (2025): Juni 2025 Vol. 17 No. 1 (2025): Februari 2025 Vol. 16 No. 3 (2024): October 2024 Vol. 16 No. 2 (2024): June 2024 Vol. 16 No. 1 (2024): February 2024 Vol. 15 No. 3 (2023): October 2023 Vol. 15 No. 2: June 2023 Vol. 15 No. 1: February 2023 Vol. 14 No. 3: October 2022 More Issue