cover
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
ISSN : 20851367     EISSN : 2460870X     DOI : https://doi.org/10.22303/csrid
Core Subject : Science,
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).
Articles 10 Documents
Search results for , issue "Vol. 17 No. 2 (2025): Juni 2025" : 10 Documents clear
Implementation of Social Media Analytics Using Buffer Tool to Measure Business Instagram Content Performance Yohana, Yohana; Kosasi, Sandy; Yuliani, I Dewa Ayu Eka
CSRID (Computer Science Research and Its Development Journal) Vol. 17 No. 2 (2025): Juni 2025
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.17.2.2025.191-203

Abstract

Instagram social media has been utilized by businesses as a platform for digital marketing activities. To assess the success of these marketing efforts, measuring content performance on Instagram is essential. This measurement involves analyzing data and insights regarding metrics such as reach, engagement, and impressions. These metrics are obtained through the process of Social Media Analytics (SMA) on the Instagram platform. However, many businesses experience a consistent decline in insights, resulting in decreased effectiveness of digital marketing. This study proposes a solution by implementing enhanced digital marketing on Instagram, followed by the measurement of Key Performance Indicators (KPIs). The measurement tool used is Buffer, which provides a comprehensive analysis dashboard concerning content performance, audience interaction patterns, and the impact of posting times on audience engagement in real-time. The KPI measurement during 3 months results indicate a significant increase, including a 66% rise in posts, a 69% increase in impressions, a 32% increase in reach, a 167% increase in likes, a 90% increase in comments, and a 105% increase in new followers for Casia store's Instagram channel. The accuracy of the data obtained from the Buffer analytic tool is verified through comparison with the impression metrics from Instagram Insight, which show identical figure, and Buffer has proven to be effective and accurate for measuring content performance and supports the implementation of SMA on the Instagram platform.
Segmentation and Classification of Vitamin C Content in Red Chili Pepper Images Using the Linear Discriminant Analysis (LDA) Method: Segmentation and Classification of Vitamin C Content in Red Chili Pepper Images Using the Linear Discriminant Analysis (LDA) Method Ramadhanu, Agung; Chan, Fajri Rinaldi; Yasmin, Nabilla; Negoro, Wahyu Saptha; Mardison, Mardison; Hendri, Halifia
CSRID (Computer Science Research and Its Development Journal) Vol. 17 No. 2 (2025): Juni 2025
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.17.2.2025.149-162

Abstract

The vitamin C content in red chili peppers plays a crucial role in meeting nutritional needs, particularly in free nutritious lunch programs. Red chili peppers are one of the essential sources of vitamin C in daily consumption. However, vitamin C content in chilies can degrade due to storage and drying processes. This study develops a segmentation and classification method for vitamin C content in red chili pepper images using Linear Discriminant Analysis (LDA) as a faster and more efficient alternative to conventional laboratory methods. The dataset consists of 100 red chili images categorized into fresh and dried chilies. The analysis process includes preprocessing, feature extraction of color and texture (RGB, HSV, GLCM), dimensionality reduction, and classification using LDA. Experimental results show that this method achieves 99% accuracy on training data and 97% on test data, demonstrating that digital image processing can serve as a non-destructive approach for food quality estimation. This approach has the potential to be applied in food quality monitoring within the food industry and public nutrition programs.
Expert System for Selecting College Majors Based on Interests and Talents Using the Certainty Factor (CF) Method Siregar, Aldi Sajali; Ritonga, Wahyu Azhar; Samsir, Samsir
CSRID (Computer Science Research and Its Development Journal) Vol. 17 No. 2 (2025): Juni 2025
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.17.2.2025.163-175

Abstract

Generally, new prospective students often experience confusion in choosing a major in Computer Science, Informatics Engineering Program at Universitas Al Washliyah Labuhanbatu that truly matches their academic abilities and interests. Often, the decision to choose a major is influenced by the environment, such as following close friends or advice from parents, without considering the students' true potential and talents. However, choosing an inappropriate major can negatively impact their academic future and career. Therefore, it is crucial for prospective students to recognize and understand their academic abilities as well as their special interests and talents. The expert system for major determination developed using the Certainty Factor method is expected to provide an effective solution by combining various indicators of interests, talents, and academic abilities of prospective students. This method utilizes established rules to calculate the certainty level (CF value) for each possible major based on the data and characteristics possessed by the student. By combining CF values from various facts, the system can provide recommendations for the major that best fits the student's greatest potential. This model does not rely solely on academic scores but also considers special interests such as social, creative, and artistic talents possessed by students, making the major selection decision more precise and directed. Thus, this Decision Support System can assist the Faculty of Computer Science, Informatics Engineering Program at Universitas Al Washliyah Labuhanbatu in selecting truly potential new students and providing appropriate recommendations, thereby minimizing the risk of wrong major choices and increasing the likelihood of academic and career success for prospective students.
Expert System for Stroke Diagnosis Using the Forward Chaining Method for Lecturers at UNIVA Labuhanbatu Samsir, Samsir; Syahputra, Andi; Subagio, S.
CSRID (Computer Science Research and Its Development Journal) Vol. 17 No. 2 (2025): Juni 2025
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.17.2.2025.176-190

Abstract

Stroke is a health problem that often occurs when the blood supply to the brain lacks oxygen and nutrients. As a result, in a matter of minutes, brain cells begin to die. This condition is classified as a serious disease and can be life-threatening, therefore requiring immediate medical attention. Stroke accounts for 10% of all deaths in the world and is the third leading cause of death after coronary heart disease (13%) and cancer (12%) in developed countries. The prevalence of stroke varies in different parts of the world. The prevalence of stroke in the United States is around 7 million (30%), while in China the prevalence of stroke ranges from 1.8% (rural) to 9.4% (urban). Worldwide, China is the country with the highest death rate from stroke (19.9% ​​of all deaths in China), along with Africa and North America. The incidence of stroke worldwide is 15 million each year, one third of whom die and one third of whom experience permanent disability. The purpose of this study is to help and facilitate lecturers at Labuhanbatu University to diagnose stroke in determining treatment and how to overcome it effectively and efficiently. Lecturers at Univa Labuhanbatu can diagnose in advance what disorders they are experiencing before going to the doctor, so they can save time and money. This system is present as a means to help diagnose patients using the Forward Chaining method. With an expert system, laypeople will be able to solve quite complicated problems that can actually only be solved with the help of experts. For experts, expert systems will also help their activities as very experienced assistants. Microsoft Visual Studio .NET is a complete collection of development tools for building ASP.NET Web applications, XML Web Services, desktop applications, and mobile applications. In Visual Studio, these are the .NET programming languages ​​such as Visual Basic, Visual C++, Visual C# (CSharp), and Visual J# (JSharp). All use the same integrated development environment or IDE so that it is possible to share tools and facilities
Expert System for Diagnosing Eye Disorders (Refractive Errors) Using the Certainty Factor (CF) Method at Tanjung Sarang Elang Community Health Center Subagio, Selamat; Harahap, Fauji; Samsir, Samsir
CSRID (Computer Science Research and Its Development Journal) Vol. 17 No. 2 (2025): Juni 2025
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.17.2.2025.204-216

Abstract

The medical and technology fields are rapidly advancing, leading many people to use computers to help diagnose, prevent, and treat human diseases. One major issue in the medical world is the imbalance between the number of patients and doctors. Additionally, most people lack medical training, so when experiencing symptoms of a disease, it is often difficult to immediately know the correct steps to take. Eye diseases vary in severity, ranging from mild to severe. One common eye disorder affecting many people is refractive error, which generally falls into two categories: hyperopia (farsightedness) and myopia (nearsightedness). Early detection of symptoms related to refractive errors requires accurate and prompt diagnosis. Therefore, with the rapid development of technology, it is essential to develop systems capable of early detection of eye diseases, especially refractive errors, by using technology that mimics human expert capabilities, such as expert systems. This expert system integrates expert knowledge within two main environments: the development environment and the consultation environment, helping the community diagnose diseases more easily and efficiently. For example, the use of the Certainty Factor method in expert systems enables the calculation of diagnostic certainty levels based on the combination of symptoms reported by patients and expert knowledge, achieving a confidence level of up to 96.7%. This demonstrates that expert system technology can be a valuable tool in addressing the imbalance between patients and doctors while improving access to faster and more accurate diagnoses. To build such systems, Microsoft Visual Studio .NET provides a complete set of tools for developing ASP.NET web applications, XML Web Services, desktop applications, and mobile applications. Within Visual Studio, .NET programming languages such as Visual Basic, Visual C++, Visual C# (CSharp), and Visual J# (JSharp) are used in a unified integrated development environment (IDE), enabling developers to efficiently share tools and resources to create reliable and user-friendly expert system applications. The system was developed and tested using symptom data from 40 patients collected at the Tanjung Sarang Elang Community Health Center. The testing showed a diagnostic accuracy of up to 96.7% in detecting symptoms of both hyperopia and myopia.
Analysis of User Satisfaction Level of Google Application Classroom Using the ECUS Method Putra, Edson Yahuda; Lahamendu, Irene Gloria; Ngangk, Stivia Yuliefri Lulij; Adam, Stenly Ibrahim; Tangka, George Morris William
CSRID (Computer Science Research and Its Development Journal) Vol. 17 No. 2 (2025): Juni 2025
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.17.2.2025.217-228

Abstract

Despite wide adoption during the COVID‑19 pandemic, Google Classroom’s long‑term acceptance in Indonesian higher education remains under‑examined. This study measures end‑user satisfaction using the five‑factor End‑User Computing Satisfaction (EUCS) framework. A cross‑sectional survey captured 247 valid responses from undergraduate students at Universitas Klabat who had used Google Classroom for at least one semester. Twenty Likert‑scaled items (4 per EUCS dimension) were adapted from Doll & Torkzadeh (1988) and checked for reliability (Cronbach’s α) and validity. Multiple‑linear regression assessed the partial effect of each EUCS factor on overall satisfaction, while descriptive statistics profiled satisfaction levels. Four dimensions—Content (β = 0.299, p < 0.001), Ease of Use (β = 0.268), Format (β = 0.182), and Timeliness (β = 0.222)—significantly predict satisfaction (Adj. R² = 0.682). Accuracy (β = 0.009, p = 0.841) is non‑significant, likely due to low internal consistency (α = 0.429). Overall, 69.6 % of respondents report being satisfied or very satisfied with Google Classroom. Content richness, intuitive interface, presentation quality, and timely feedback drive student satisfaction, whereas perceived accuracy warrants instrument refinement. Findings inform LMS developers and university decision‑makers on prioritised enhancement areas.
Evaluasi Performa Otomatisasi Skema Basis Data Dengan Model dan Migrasi Django Dalam Aplikasi Proyek Akhir Gat; Prasetya, Wahyu Sindu; Wibowo, Vellen
CSRID (Computer Science Research and Its Development Journal) Vol. 17 No. 2 (2025): Juni 2025
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.17.2.2025.270-284

Abstract

Effective management of database schemas is essential to ensure the scalability, performance, and integrity of academic applications. However, for systems with complex entities and large volumes of data, the use of framework-based schema automation remainsrelatively untested. Examiner, Guidance, Evaluation, Final Project, Lecturer, and Student are the six main entities that make up the final project management application, and the purpose of this study is to assess how well Django's models and migration tools can automate database schemas for this application. The case study methodology was used on two linked datasets with 1,000 and 10,000 entries, respectively. During the stages of installation, testing, and analysis, a descriptive-analytical approach was employed. Unit, functional, integration, and performance tests were conducted using MariaDB, Django 5.1.2, and a digital stopwatch. For the dataset with 1,000 entries, the read operation averaged 0.00010 seconds, the update operation 0.00439 seconds, and the delete operation 0.00124 seconds. The results demonstrate that the models remain consistent, migrations proceed smoothly, and all CRUD operations are completed with an effective average time. For the dataset containing 10,000 entries, the average operation times were 0.00045 seconds per operation, 0.00013 seconds for reads, 0.04535 seconds for updates, and 0.00345 seconds for deletions. In summary, Django can be effectively applied to large-scale academic applications, as it consistently and efficiently automates complex database schemas.
Diabetes Diagnosis Expert System Based on Family History Analytic Hierarchy Process (AHP) Method Saragih, Reagan Surbakti; Nufus, Inayah chayatun; Samsir, Samsir
CSRID (Computer Science Research and Its Development Journal) Vol. 17 No. 2 (2025): Juni 2025
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.17.2.2025.229-242

Abstract

An expert system is a branch of artificial intelligence (AI) designed to replicate the decision-making abilities of a human expert in a specific domain. It utilizes a rule-based approach by incorporating expert knowledge and experience into a computer system, allowing non-expert users to analyze and solve complex problems efficiently. One of the critical applications of expert systems is in the healthcare sector, especially in supporting early diagnosis of chronic diseases such as Diabetes Mellitus. Diabetes Mellitus is a metabolic disorder characterized by elevated blood glucose levels caused by insufficient insulin production or the body's inability to effectively use insulin. It is classified into two main types: Type 1 Diabetes Mellitus (Insulin Dependent) and Type 2 Diabetes Mellitus (Non-Insulin Dependent). Key factors contributing to the onset of diabetes include genetic predisposition, obesity, and unhealthy lifestyle habits. To assist the public in self-diagnosing the risk of diabetes, a web-based expert system was developed using the Analytic Hierarchy Process (AHP), a structured decision-making method that helps prioritize multiple criteria. In this system, symptoms such as frequent thirst, weight loss, and family history of diabetes are assessed and weighted using AHP to determine a person's risk level. The system is implemented using PHP programming language and MySQL database. Users interact with the system by answering a set of predefined questions, and based on their responses, the system calculates and displays the diagnosis result with corresponding risk categories.This expert system aims to raise public awareness and provide an accessible tool for early detection and prevention of diabetes, especially in regions with limited access to healthcare professionals.
Expert System for Early Detection of Depression Using Psychological Symptoms Certainty Factor Method Rambe, Nisa indriani; Samsir, Samsir; Subagio, S.
CSRID (Computer Science Research and Its Development Journal) Vol. 17 No. 2 (2025): Juni 2025
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.17.2.2025.243-255

Abstract

Depressive disorders in the elderly often go undetected due to early symptoms that resemble normal aging processes. The absence of an early detection system becomes a major obstacle to prompt treatment. This study aims to design an expert system for early detection of depression in the elderly using the Certainty Factor (CF) method. The dataset was collected from 60 patient complaint narratives and validated by three professional psychologists with over five years of experience in geriatric psychiatry. The system design process includes symptom extraction using Natural Language Processing (NLP), CF value calculation for each symptom, and classification of depression risk (low, moderate, high). The system architecture consists of a knowledge base, inference engine, and user interface. Validation was conducted through diagnostic accuracy testing and user evaluation using a Focus Group Discussion (FGD). The results showed a validity level of 73%, and 88.6% of respondents agreed that the system can assist in early diagnosis. The novelty of this study lies in the integration of NLP and Certainty Factor tailored to the narrative patterns of the elderly, combined with a user-friendly interface design. This system is expected to serve as a supportive tool for psychologists and families in the early detection of depression in elderly individuals.
Model Klasifikasi Machine Learning Berbasis Multiple Measurement Distance Arwansyah, Arwansyah; Susanto, Cucut; Nurdiansah, Nurdiansah
CSRID (Computer Science Research and Its Development Journal) Vol. 17 No. 2 (2025): Juni 2025
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.17.2.2025.256-269

Abstract

This study aims to explore and develop a K-Nearest Neighbors (KNN)-based classification model using various distance calculation methods, namely Euclidean, Manhattan, Minkowski, and Hamming Distance. To improve the model’s accuracy, the results from each distance method are combined using a weighted average technique. The datasets used are the Iris and Breast Cancer datasets obtained from the UCI Machine Learning Repository. Preprocessing is carried out using normalization with StandardScaler to ensure uniform feature scaling. The model is tested using cross-validation techniques and evaluated using accuracy metrics and a confusion matrix to assess classification performance. Based on the experimental results, the use of multiple distance methods combined with a weighted average approach yields improved accuracy compared to the conventional KNN method that relies on a single distance calculation. The findings of this study indicate that the combination of distance methods in KNN can enhance model performance in classification tasks. This study is expected to contribute to the development of a more adaptive KNN algorithm tailored to diverse data characteristics.

Page 1 of 1 | Total Record : 10