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 156 Documents
 12   13   14   15   16 
IoT-Based Seaweed Cultivation Monitoring System with Data Transmission Protection Using JSON Web Token (JWT) on ESP32 Iwan Fitrianto Rahmad; Yudho Andika; Vidi Agung Fragastia; Elsa Aditya
CSRID (Computer Science Research and Its Development Journal) Vol. 18 No. 1 (2026): Februari 2026
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.18.1.2026.18-31

Abstract

Security in the communication of IoT devices is a critical concern in seaweed cultivation monitoring systems, particularly when operating over open networks. This study presents the design and implementation of an IoT-based monitoring system for seaweed cultivation, incorporating data transmission protection on the ESP32 device through the use of JSON Web Token (JWT). The system monitors key parameters influencing seaweed growth—such as temperature, salinity, pH, and turbidity—and transmits this data to a server via HTTP/HTTPS protocols. JWT is employed for authentication and authorization, ensuring that only legitimate devices are permitted to send data to the server. The research methodology encompasses requirement analysis, system architecture design, hardware and software implementation, followed by functionality, security, and performance testing. Experimental results demonstrate that the proposed system successfully acquires sensor data and transmits it in real time to the server, while effectively rejecting unauthorized attempts lacking valid tokens. The application of JWT significantly enhances communication security with minimal impact on ESP32 performance. Overall, the proposed IoT-based Seaweed Cultivation Monitoring System with JWT protection provides an effective solution for safeguarding data integrity and authenticity in seaweed farming applications.
Sistem Pakar Identifikasi Hama Tanaman Perkebunan Menggunakan Metode Analytical Hierarchy Process (AHP) Yusup Anwar Siregar; Selamat Subagio; Wita Ferwati
CSRID (Computer Science Research and Its Development Journal) Vol. 18 No. 1 (2026): Februari 2026
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.18.1.2026.46-58

Abstract

Plantation crops such as oil palm, rubber, tea, and coffee are susceptible to pest attacks that can reduce crop productivity. The process of pest identification in the field often encounters obstacles due to limited experts and response time. This study aims to build an expert system based on the Analytical Hierarchy Process (AHP) method to help identify pests based on symptoms and severity of attacks. The AHP method is used to form a decision hierarchy, compile a pairwise comparison matrix, calculate priority weights, and conduct consistency tests. Alternative pests described include planthoppers, stem borers, leaf rollers, stink bugs, and rats, with categories of light and heavy attack levels. The calculation results show the highest composite value in the light category of 0.50717 and heavy of 0.25065. Validation of 15 test cases shows a system accuracy level of 93.33% compared to experts. Usability testing obtained a learnability value of 92.88%, efficiency of 92%, memorability of 94%, error of 94%, and satisfaction of 88.6%. These results indicate that the system is suitable for use as a tool for early identification of plantation pests.
Sistem Pakar Diagnosis Penyakit Typhus Menggunakan Metode Forward Chaining Berbasis Web Abdul Hakim Jambak; Samsir; Shabrina Rasyid Munthe
CSRID (Computer Science Research and Its Development Journal) Vol. 18 No. 1 (2026): Februari 2026
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.18.1.2026.148-161

Abstract

Typhoid fever is a digestive system infection caused by Salmonella Typhi and remains a significant health problem in Indonesia due to symptom similarities with other diseases, which often lead to delayed early diagnosis. This study aims to develop a web-based expert system to support early diagnosis of typhoid fever using the Forward Chaining method. The knowledge base was constructed through medical literature review and expert validation by an internal medicine specialist and represented using IF–THEN production rules. The system utilizes six main symptoms and seven disease conditions processed through a forward chaining inference mechanism to generate diagnostic conclusions automatically. System evaluation was conducted using 146 case datasets through Black Box Testing, White Box Testing, and Known Case Testing. The results show a diagnostic accuracy of 87.88%, while white box testing achieved 100% logical correctness. The findings indicate that the Forward Chaining method effectively performs symptom-based reasoning and can support structured early diagnosis of typhoid fever.
Sistem Pakar Diagnosis Kerusakan Rambut Berbasis Web Menggunakan Metode Certainty Factor Tisna Destiana; Samsir; Selamat Subagio
CSRID (Computer Science Research and Its Development Journal) Vol. 18 No. 1 (2026): Februari 2026
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.18.1.2026.83-97

Abstract

This study develops a web-based expert system for diagnosing hair damage using the Certainty Factor (CF) method to support early self-assessment and treatment recommendations. The knowledge base consists of five types of hair damage and five main symptoms with expert-validated belief weights. The CF method is applied to compute diagnostic confidence based on symptom combinations selected by users. System evaluation was conducted using test-case scenarios and numerical CF calculations. The results show that for three dominant symptoms, the system produces a CF value of 0.952, indicating a 95.2% confidence level. The novelty of this study lies in the expert-weighted knowledge modeling, transparent CF numerical analysis, and inference aggregation correction evaluation. The system can serve as an initial consultation tool before professional diagnosi.
Hybrid Decision Support System and Image Processing for Classifying Priority Applications in the Padang Government Agung Ramadhanu; Mardison; Halifia Hendri; Febri Hadi; Dodi Guswandi; Deri Marse Putra; Romi Hardianto; Syafrika Deni Rizki
CSRID (Computer Science Research and Its Development Journal) Vol. 18 No. 1 (2026): Februari 2026
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.18.1.2026.178-191

Abstract

The development of e-government has encouraged every Regional Apparatus Organization (OPD) within the Padang City Government to submit various digital applications to improve the quality of public services. However, the large number of applications often creates challenges in determining priorities, primarily due to limited resources and budgets. This research aims to design a Hybrid Decision Support System (DSS) that combines the WASPAS (Weighted Aggregated Sum Product Assessment) method and the development of the K-Means Clustering method to provide a more objective and measurable priority classification. The WASPAS method is used to provide a ranking of alternatives based on predetermined criteria, such as urgency of need, service impact, funding availability, and alignment with the regional strategic plan. Next, the K-Means algorithm is applied to group the calculation results into several priority classes, ranging from the most urgent to the least urgent. As an innovation, this research also utilizes image processing techniques to visualize the K-Means classification results, allowing for a more intuitive and easily understood presentation of priority grouping patterns for decision-makers. In this research, data were collected from 52 OPDs within the Padang City Government as a case study. The test results show that the hybrid DSS approach combining WASPAS and K-Means successfully produces priority scale classification with an accuracy level of 94.75%, which demonstrates consistency and accelerates the application evaluation process at OPDs. Integration with image processing for visualization of clustering results also successfully helps clarify data interpretation and facilitates analysis. Thus, this system is expected to support more effective, transparent decision-making in accordance with the principles of electronic-based governance in Padang City.
Automated Fruit Image Classification Based on HSV Features, Morphological Segmentation, and Extreme Learning Machine Agung Ramadhanu; Halifia Hendri; Wahyu Saptha Negoro; Mardison Mardison; Larissa Navia Rani; Sofika Enggari; Muhammad Reza Putra
CSRID (Computer Science Research and Its Development Journal) Vol. 18 No. 1 (2026): Februari 2026
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.18.1.2026.135-147

Abstract

Fruit image classification plays a crucial role in smart agriculture, particularly in automating sorting and quality control processes. This study proposes a fruit classification system by integrating HSV color space conversion, adaptive thresholding, morphological segmentation, and the Extreme Learning Machine (ELM) algorithm. The dataset consists of three fruit classes—apple, pineapple, and watermelon—with a total of 480 images, divided into 360 training samples and 120 testing samples. Image preprocessing involves resizing, HSV conversion, noise reduction through morphological operations, and feature extraction based on color and shape characteristics. The extracted features are used to train and test an ELM model. To improve classification performance and address potential overfitting in traditional ELM, this study introduces a new development called the Extended Extreme Learning Machine (EELM). The key innovation lies in modifying the calculation of the output weights βj, where a regularization term is introduced using ridge regression to stabilize learning and improve generalization. Experimental results show that the proposed system achieves 100% accuracy on the training data and an average accuracy of 83.3% on the testing data. The system also demonstrates robustness in handling varying lighting conditions and fruit shapes. These improvements enable EELM to better handle noisy or complex data by preventing over-reliance on randomly initialized hidden layer parameters. Consequently, EELM demonstrates improved reliability, making it more suitable for deployment in resourceconstrained real-world environments such as mobile or embedded systems.
Smart Plant Monitoring Sistem Suhu dan Kelembaban Tanah Pada Tanaman Cabai Berbasis IoT Menggunakan Protokol MQTT Dini Berlian; Linna Oktaviana Sari
CSRID (Computer Science Research and Its Development Journal) Vol. 18 No. 1 (2026): Februari 2026
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.18.1.2026.162-177

Abstract

Chili plants are very sensitive to environmental conditions, especially soil temperature and humidity, so they require continuous monitoring. Manual monitoring methods for chili plants are considered ineffective because they do not allow for continuous monitoring of changes in environmental conditions and do not always provide accurate and real-time information. In addition, the network infrastructure at the research site is still unstable due to limited Wi-Fi coverage and poor internet signal quality in relatively remote cultivation areas. Therefore, this study uses the Message Queue Telemetry Transport (MQTT) protocol, which is lightweight and efficient for data communication in limited network conditions. This study aims to design an IoT-based soil temperature and humidity monitoring system using the MQTT protocol. The method used is an experiment with a prototype approach. Sensor data is sent in real-time and displayed on an LCD and Node-RED dashboard that can be accessed via a laptop and smartphone. Testing was conducted for five days at three different times, namely morning, afternoon, and night. The results show that the system is capable of real-time monitoring and consistently displays soil temperature and humidity data according to the actual conditions of chili plants. Therefore, the IoT-based monitoring system using the MQTT protocol can be used to support real-time monitoring of chili plant conditions.
Implementasi dan Evaluasi Small Language Model untuk Chatbot CRM Menggunakan LoRA dan RAG Irawan Wingdes; Rendy Amy Saputra; Anne Putri Miranda
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-.18.2.2026.351-365

Abstract

The adoption of large language models (LLMs) in customer relationship management (CRM) has increased rapidly, but their use in micro, small, and medium enterprises (MSMEs) remains limited due to computational and cost constraints. This study explores the use of small language models (SLMs) as an efficient alternative for customer service chatbots, using parameter-efficient fine-tuning (PEFT) with Low-Rank Adaptation (LoRA) and comparing it with retrieval-augmented generation (RAG). This research follows the Design Science Research (DSR) approach with a case study on a local garment production business in Pontianak. The Qwen2-1.5B-Instruct model is adapted using LoRA and deployed on a 6GB GPU. Evaluation is conducted through quantitative and qualitative methods. Results show that the base model performs poorly without adaptation. The LoRA approach achieves the most stable performance, with intent accuracy up to 95%–100% and 0% hallucination rate, while RAG improves contextual understanding but lacks output consistency. The study concludes that domain-specific efficient fine-tuning is crucial to enabling SLM-based CRM solutions for SMEs.
Implementasi Metode Technology Accaptance Model (TAM) untuk Mengukur Aplikasi Sistem Informasi Universitas Putra Indonesia YPTK Muhammad Afdhal; Dhio Saputra
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-.18.2.2026.366-380

Abstract

The development of information technology in education has encouraged of implementation of integrated information systems to improve academic, administrative, and service processes; however, their effectiveness is strongly influenced by the level of user acceptance. This study aims to measure the acceptance of the Academic Information System at Universitas Putra Indonesia YPTK using the Technology Acceptance Model (TAM). The novelty of this study lies in the development of an extended TAM model by integrating Information Quality (INQ), System Quality (SYQ), and Service Quality (SVQ) as quality factors mediated by User Satisfaction (USF) in influencing Net Benefit (NBF). A quantitative descriptive approach was employed involving 108 respondents consisting of students, lecturers, and administrative staff. Data were collected using a Likert-scale questionnaire and analyzed using Structural Equation Modeling (SEM). The results indicate that System Quality (SYQ) is the strongest predictor of User Satisfaction (USF), which subsequently has a dominant effect on Net Benefit (NBF), thereby validating the model as an effective evaluation framework to support system quality improvement and digital transformation in higher education.
Aplikasi Kemiripan Dokumen Menggunakan Multi Algoritma Pada UNDIPA Makassar Nurdiansah; Arwansyah; Cucut Susanto; Willem Musu; Suryani; Saprial Metthew Godliving Perdamaian Ani
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-.18.2.2026.320-332

Abstract

Measuring similarity between text documents is a fundamental task in Natural Language Processing (NLP) with broad applications, such as plagiarism detection, document clustering, and recommendation systems. This study aims to analyze and compare the performance of various document similarity algorithms, ranging from traditional lexical approaches to modern semantic methods. The algorithms reviewed include Bag-of-Words (BoW), TF-IDF, and Jaccard Similarity, as well as semantic representation-based methods such as Word Embeddings, Doc2Vec, and Sentence-BERT. An interactive web application was developed using the Gradio library to visualize comparison results in real-time and allow users to upload their own documents. The results indicate that lexical methods are effective at detecting keyword-based similarity but fail to capture semantic similarity when synonyms are used. Conversely, semantic methods—particularly Sentence-BERT—significantly outperform others in identifying contextual and semantic similarity, yielding more accurate scores for documents that differ in vocabulary yet share similar meanings. The study concludes that selecting the appropriate algorithm requires considering document characteristics and analysis objectives, and that the developed interactive tool can serve as an educational and experimental platform for such evaluations

Page 15 of 16 | Total Record : 156

 12   13   14   15   16 

Filter by Year

2022 2026


Reset
Filter By Issues
All Issue 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