Journal of Computer Science and Technology (JCS-TECH)

IMPLEMENTASI GRAF MENGGUNAKAN QGIS UNTUK EFISIENSI PROMOSI DENGAN METODE SHORTEST PATH BERBASIS DESKTOP

2025-04-12T12:13:50+07:00

Graph theory serves as the foundation for creating representations of a network's connectivity. With graph theory, routing algorithms such as the shortest path method can be developed, which can help optimize finding the best route. Thus, solving problems related to the most optimal distance, time, and cost can be easily and effectively addressed. This research uses the shortest path method with the help of QGIS Desktop. The goal is to find the best route in terms of distance (shortest) and time (fastest) so that the pemasaran division can easily determine the promotional targets at schools that are prioritized for visits. The results of this study indicate that the primary promotion targets to be visited are SMA Raksana and Yayasan Pendidikan Harapan 1 Medan, which are approximately 3.1-3.2 km away. If compared to the schools that are not a priority to visit (not potential), namely SMA/SMK Advent, because its distance is ± 6.9 km, making it the farthest from other schools that are the focus of this research.

METODE FORWARD CHAINING UNTUK DIAGNOSA PENYAKIT DAN HAMA PADA TANAMAN KOPI

2025-04-25T11:06:21+07:00

Various problems can be encountered in agriculture, for example problems about diseases and pests in coffee plants. There are few experts or experts in the field of agriculture, so it is necessary to build a system that is able to adopt human processes and ways of thinking in the form of an expert system. The purpose of this study is to build an expert system to diagnose diseases and pests in coffee plants. The method used in this study is the forward chaining method. The system testing was carried out using the black box testing method which was tested on experts and coffee farmers. Based on the test results, the results of the assessment were obtained that the expert system for diagnosing diseases in coffee plants that was built was proven to work well as expected with 100% validation. Based on the results of the research that has been carried out, it can be concluded that the application that has been built is another alternative for users, both the general public or people who are having problems with diseases in coffee, which can be used as a guide as a step to seek control of the diseases experienced

SMART CLASS PROTOTYPE USING INTERNET OF THINGS TECHNOLOGY AT PACITAN STATE COMMUNITY ACADEMY

2025-04-25T11:04:32+07:00

This study aims to overcome the causes of wasteful electricity usage in the study room and the swelling of electricity bills that must be paid due to user negligence in turning off existing electronic devices and the length of time to start lectures because they have to turn on electronic devices one by one, then the conventional control system in the study room can be updated to be semi-automatic. The system that can be created is a smart class, where a smart class is a system for accessing electricity using a smartphone or by attaching the RFID card of a lecturer who enters the class or security staff to the RFID reader. After the system reads the appropriate ID number, the electrical system in the study room can be accessed. The system will automatically disconnect after 2 minutes the RFID card is removed from the RFID reader or by accessing the blynk application on the smartphone. This study uses an experimental research method that begins with design analysis, design, implementation to testing. The results of the system test show that the smart class system is successful in all processes, both turning on and off electronic devices using RFID and the blynk application or monitoring electronic devices via smartphones effectively.

ANALISIS SENTIMEN PENGGUNA TIKTOK TENTANG PROGRES PEMBANGUNAN IKN DENGAN METODE RANDOM FOREST

2025-05-02T13:54:45+07:00

Abstract

Sentiment classification is a text analysis technique used to identify and categorize user opinions about an application or service. This study aims to classify public sentiment about the progress of the development of the IKN (Indonesian Capital) with the Random Forest algorithm based on comments from users of the Tiktok platform. The dataset was taken from Kaggle with 1472 comments in Indonesian. The dataset used consists of user comments categorized into positive and negative sentiments. The evaluation was carried out based on the accuracy, precision, recall, and F1-score metrics to determine the results of the user sentiment classification. Testing the Random Forest method on Google Colab showed an accuracy value of 77%, precision 78%, recall 77% and F1-score 77%. From these values, the Random Forest method is considered quite good in classifying Tiktok user sentiment in responding to the progress of the IKN relocation.

KLASIFIKASI JUDUL SKRIPSI MAHASISWA BERDASARKAN KONSENTRASI PROGRAM STUDI MENGGUNAKAN ALGORITMA NAIVE BAYES

2025-04-25T11:01:32+07:00

This study discusses the development of an automatic classification model for student thesis titles based on study program concentrations using the Naive Bayes algorithm. The background of this research is the increasing number of thesis titles produced each year, which complicates the classification and management process if done manually. The Naive Bayes algorithm was chosen for its simplicity, efficiency, and suitability for text classification tasks. The dataset comprises thesis titles from students of the D4 Software Engineering Program with six areas of concentration: Software Engineer, Mobile Developer, Full Stack Developer, UI/UX Designer, Software Quality Assurance Engineer, and Technopreneur. The data underwent several preprocessing stages including tokenization, stopword removal, and stemming. The model was trained and tested using a train-test split approach and evaluated using accuracy, precision, recall, and f1-score metrics. The results indicate that the Naive Bayes algorithm can classify thesis titles into their appropriate concentrations with an accuracy of 65%. This research contributes to improving the efficiency of academic administration management and serves as a foundation for developing AI-based classification systems in higher education

A THEORETICAL EXTENSION OF TECHNOLOGY ORGANIZATION ENVIRONMENT (TOE) IN E-GOVERNMENT: A SYSTEMATIC LITERATURE REVIEW AND THEORY EVALUATION

2025-04-29T11:52:32+07:00

Currently, the universal influence of information technology has been considered as an important tool in enhancing the performance of local governments in a country. There is a consensus that information technology has a significant impact on good government. This effect will be realized when information technology is widely distributed and used in integrated e-government. Therefore, it is important to understand the determining factors when considering the adoption of information technology. In this article, we review The Technology Organization Environment (TOE) Framework theory for the adoption model in e-government, which is widely used in the information systems literature. The TOE framework identifies three contextual aspects: technology context, organization context, and environment context. We conduct an analysis of the TOE framework and studies that combine the TOE framework with other theories. This research examines the TOE framework and also provides recommendations for future research opportunities

FORECASTING INTERNET BANDWIDTH USAGE WITH TIME SERIES ARIMA APPROACH USING PARAMETER OPTIMIZATION

2025-04-25T11:00:47+07:00

Efficient internet bandwidth management is a critical challenge in network administration, especially in institutions with high data usage. Significant fluctuations in internet traffic can cause bottlenecks and a decline in service performance. Therefore, the ability to accurately estimate bandwidth requirements becomes crucial. This research implements the Autoregressive Integrated Moving Average (ARIMA) time series forecasting method to predict bandwidth usage on a local network over a one-month period. The data uses a dummy dataset of 100 rows aimed at analyzing the performance of the ARIMA model and is analyzed using Python with statistical libraries such as Pandas, Statsmodels, and Matplotlib. The ARIMA model was selected based on the results of the stationarity test and ACF/PACF analysis. Performance evaluation was conducted using RMSE. The research results show that the ARIMA(4,2,7) model provides high prediction accuracy with an RMSE value of 3.276. This estimation can assist network administrators in proactively planning capacity, avoiding service disruptions due to overload, and supporting data-driven decision-making in network management.

OPTIMIZATION OF K VALUE IN THE K-NEAREST NEIGHBOR ALGORITHM FOR FETAL HEALTH CLASSIFICATION

2025-04-29T11:56:44+07:00

Fetal health classification is an essential step in supporting early diagnosis of fetal conditions and preventing pregnancy complications that can threaten the lives of both mother and fetus. The K-Nearest Neighbor (K-NN) algorithm is one of the commonly used methods for this classification due to its ability to recognize patterns from training data. However, the performance of K-NN is greatly influenced by the choice of the K value, which is the number of nearest neighbors considered in determining the class of new data. This study aims to optimize the K value in the K-NN algorithm to achieve the highest accuracy in fetal health classification. The data used consists of cardiotocography (CTG) examination results classified into three categories is Normal, Suspect, and Pathological. K values from 1 to 20 were tested to determine the optimal K value based on classification accuracy. The results indicate that the optimal K range is between 1 and 3, with the highest accuracy achieved at K = 1 and K = 2, both at 99.91%. In contrast, K values greater than 3 show a significant decrease in accuracy. Based on these findings, K = 3 is chosen as the optimal value to balance high accuracy with the model’s generalization capability. In conclusion, optimizing the K value in the K-NN algorithm can improve the accuracy of fetal health classification, potentially supporting more accurate and timely medical decision-making. These findings can be applied in developing a more reliable fetal health prediction system, thereby contributing to reducing the risk of maternal and fetal health complications