Journal of Computer Science and Technology (JCS-TECH)

LITERATURE REVIEW: COMPARISON OF K-MEANS AND FUZZY C-MEANS ALGORITHMS IN CLUSTERING ANALYSIS

2025-07-20T19:36:15+07:00

The increasing volume and complexity of data across sectors such as healthcare, business, education, and security necessitates analytical methods capable of handling uncertainty and structural variability. One widely used approach is clustering, which groups data based on similarity. Two commonly applied algorithms are K-Means and Fuzzy C-Means (FCM), each with distinct characteristics: K-Means applies hard clustering, while FCM adopts soft clustering using degrees of membership. This study presents a literature review of 12 national scientific journals that implemented both algorithms in contexts such as employee performance evaluation, patient classification, spatial disease analysis, and customer segmentation. The findings show that algorithm selection depends heavily on data characteristics and analytical objectives. K-Means excels in computational efficiency and interpretability, while FCM offers greater flexibility for modeling complex data. Several studies also suggest that combining both algorithms can enhance clustering accuracy and robustness. Thus, this review is expected to serve as both an academic and practical reference in selecting appropriate clustering methods.

Keywords: Clustering, K-Means, Fuzzy C-Means, Literature Review, Data Analysis.

SISTEM DETEKSI DINI KEBAKARAN BERBASIS IOT UNTUK LINGKUNGAN PENDIDIKAN: STUDI KASUS SMK DIPONEGORO BANYUPUTIH

2025-10-22T19:08:41+07:00

Fires can occur unexpectedly, even if you are careful when using equipment that produces fire. However, there are still several sources of fires such as electrical short circuits, gas stoves, burning trash, cigarette butts and candles during a power outage. The purpose of this research is to create a tool that can detect fire and temperature in a room and can overcome (minimize) the threat of fire disasters based on a microcontroller and C language. This research uses a Fire Sensor to detect fire, a DHT 11 Sensor to detect room temperature, NODEMCU as a microcontroller input and output controller, the BLYNK application as a system monitoring tool, a green LED if the room temperature is normal, a yellow LED if the room temperature rises above the normal limit, and a red LED if the room temperature rises drastically. The system will assign the fire extinguishing system using APAR if there is a significant increase in temperature or if the system detects a fire. The output from the Flame Sensor that detects fire will be processed into a microcontroller that has been programmed using C language so that it will produce two states: low when no fire is detected, and high when a fire is detected. Likewise for the output of DHT11. This tool will provide a warning to the BLYNK application if it detects a fire and then gives a command to spray the APAR.

VEHICLE LICENSE PLATE RECOGNITION USING YOLOV8 AND PADDLEOCR

2025-07-28T17:49:40+07:00

This study focuses on developing a computer vision-based vehicle license plate recognition system designed to enhance operational efficiency and support the implementation of real-time intelligent transportation systems. Specifically, the research evaluates the system's performance in detecting and recognizing license plate characters using a two-stage approach: (1) an object detection stage employing the YOLOv8 model to identify plate locations, and (2) a character recognition stage utilizing PaddleOCR for text extraction. Experimental results demonstrate exceptional detection accuracy, with 96.3% precision and 98.7% recall, indicating the system's robustness under varying environmental conditions such as lighting changes and camera angles. However, character recognition accuracy remains relatively low (39.62%), potentially due to input image quality limitations or license plate complexity. These findings highlight the critical need for optimized image pre-processing techniques (including noise reduction, contrast enhancement, and perspective correction) to improve text readability prior to OCR. Future research will explore various image processing methods and alternative model architectures to enhance recognition accuracy and real-time performance stability, enabling effective integration into intelligent transportation applications such as traffic monitoring, automated parking systems, and AI-based law enforcement.

ANALYSIS OF OPTIMIZATION OF TASK DISTRIBUTION AND WORKING TIME EFFICIENCY WITH THE HUNGARIAN METHOD APPROACH AT GLORY LAUNDRY

2025-04-12T12:13:15+07:00

In response to the rapid development of business and increasingly intense competition, small businesses such as laundry services are required to manage time and task allocation efficiently to improve productivity. One of the laundry businesses facing this issue is the business owned by Mrs. Oktovina, located at Jl. A. M. Sangajai Gonof, Klawuyuk Subdistrict, Sorong City. The main problem encountered is the imbalance between the number of employees and the workload, resulting in ineffective task assignment and time management. To address this problem, the Hungarian Method was applied, which is known to be effective in solving optimal assignment problems. With the help of POM-QM software, the calculation process was carried out accurately to determine the most efficient work allocation for each employee. The calculation results showed that the optimal working time for Mrs. Oktovina is 15 minutes, Ima 30 minutes, and Sarman 5 minutes, bringing the total completion time to 50 minutes. The application of this method has proven to enhance work efficiency, accelerate task completion, and optimize employee productivity in providing better service to customers

FAKTOR-FAKTOR MEMENGARUHI NIAT MAHASISWA MEMPELAJARI SISTEM INFORMASI MANAJEMEN KEUANGAN BERBASIS THEORY OF PLANNED BEHAVIOR

2025-04-25T11:02:21+07:00

This research aimed to test whether the learning model obtained by Financial Management Information System (MIS) intention can strengthen attitude variables, subjective norms and self-efficacy control of Unwidha undergraduate students' interest. The research design was carried out using quantitative methods that explained the causal relationship between one variable and the other variables to be tested. The hypothesis test was formulated in a model using the Structural Equation Model multivariate test. The population in this research are all FEP Unwidha undergraduate students who have a strong interest in Financial MISp. The sampling technique was carried out by purposive sampling of 120 student respondents. The results of the analysis found that financial MIS influences three variables and the overall model in the SEM fit test. The research results can serve as a basis for making quality financial MIS learning problem-based models by adding aspects of real financial MIS practice for Unwidha undergraduate students

ANALISIS KINERJA NOISE FILTERING UNTUK MENGHILANGKAN DERAU PADA CITRA SEDIAAN DARAH TIPIS MALARIA

2025-07-30T07:53:26+07:00

In automated malaria diagnosis systems, the images resulting from the acquisition process may
contain noise, which can obscure the visual appearance of the Plasmodium. Therefore, noise filtering
techniques are needed to remove noise from the images. This study evaluates the performance of noise
filtering techniques under various noise conditions to determine the most effective method for removing
noise in blood smear images.The research consists of several stages: acquisition of thin blood smear
images, noise addition, noise filtering, and performance comparison of the noise filtering methods. The
image acquisition was carried out using the publicly available MP-IDB malaria dataset. Noise addition was
performed using salt and pepper, Gaussian, and mixed noise. The tested noise filtering techniques include
median filtering, Gaussian filtering, and average filtering. The performance of the noise filtering methods
was assessed using Mean Squared Error (MSE) and Peak Signal-to-Noise Ratio (PSNR)
measurements.The experimental results show that for blood smear images with salt and pepper noise, the
median filtering method provided the best results with an MSE of 6.51 and a PSNR of 43.13. Visually, the
noise-removed image using median filtering closely resembled the original image. For images with
Gaussian noise, the average filtering method achieved the best performance with an MSE of 31.81 and a
PSNR of 33.19. For images with mixed noise, the median filtering method again provided the best
performance with an MSE of 46.95 and a PSNR of 31.46.

INTEGRATION OF IOT AND GIS FOR OPTIMIZING DISASTER RELIEF DISTRIBUTION RESPONSE IN REMOTE AREAS

2025-10-22T10:23:08+07:00

Natural disasters often pose significant challenges in aid distribution, especially in remote areas with limited infrastructure and difficult access. Slow and inefficient responses can exacerbate the impact of disasters and lead to greater losses. This research proposes an integrated Internet of Things (IoT) and Geographic Information System (GIS) to optimize disaster aid distribution response in remote areas. The system is designed to provide real-time monitoring of logistics assets, efficient route planning, dynamic data management, and performance reporting. By leveraging IoT sensors for real-time field data collection and GIS spatial analysis capabilities for visualization and optimization, this system aims to enhance situational awareness, accelerate response times, and ensure aid reaches those in need more effectively and safely. Key features of the system include secure user authentication, an interactive real-time map dashboard, intelligent logistics route planning, dynamic data management, centralized IoT sensor monitoring, and performance reporting and analysis. This integration is expected to overcome various logistical constraints faced in disaster relief operations in challenging environments.

SISTEM INFORMASI LAYANAN SERVIS PADA BENGKEL MOBIL BERKAH JAYA BERBASIS WEB

2025-05-19T09:01:12+07:00

The advancement of information technology has driven digital transformation across various sectors, including automotive workshop services. Bengkel Berkah Jaya still operates using manual business processes, leading to inefficiencies, recording errors, and limited customer service. This study aims to develop a web-based automotive service information system to automate service processes, simplify information access, and improve operational efficiency and customer satisfaction. The system development was carried out using the Waterfall method through several stages: needs analysis, system design using UML, implementation with Laravel and MySQL, testing, deployment, and maintenance. The research results show that all functions in the service information system have operated properly. Evaluation through questionnaires indicates an average user satisfaction level of 84% regarding system features and ease of use. Most respondents stated that the application is easy to use and helpful in supporting service processes. However, the visual design aspect still needs improvement. Overall, the system provides an effective solution for enhancing service quality and workshop operations. The application is expected to help Bengkel Berkah Jaya expand its reach and become more responsive to customer needs.