cover
Contact Name
Mesran
Contact Email
mesran.skom.mkom@gmail.com
Phone
+6282161108110
Journal Mail Official
jurnal.josyc@gmail.com
Editorial Address
Jalan Sisingamangaraja No. 338, Medan, Sumatera Utara
Location
Kota medan,
Sumatera utara
INDONESIA
Journal of Computer System and Informatics (JoSYC)
ISSN : 27147150     EISSN : 27148912     DOI : -
Journal of Computer System and Informatics (JoSYC) covers the whole spectrum of Artificial Inteligent, Computer System, Informatics Technique which includes, but is not limited to: Soft Computing, Distributed Intelligent Systems, Database Management and Information Retrieval, Evolutionary computation and DNA/cellular/molecular computing, Fault detection, Green and Renewable Energy Systems, Human Interface, Human-Computer Interaction, Human Information Processing Hybrid and Distributed Algorithms, High Performance Computing, Information storage, Security, integrity, privacy and trust, Image and Speech Signal Processing, Knowledge Based Systems, Knowledge Networks, Multimedia and Applications, Networked Control Systems, Natural Language Processing Pattern Classification, Speech recognition and synthesis, Robotic Intelligence, Robustness Analysis, Social Intelligence, Ubiquitous, Grid and high performance computing, Virtual Reality in Engineering Applications Web and mobile Intelligence, Big Data
Articles 443 Documents
The Classification of Batik Besurek Fabric Motifs in Indonesia Utilizing YOLOv8 for Enhanced Cultural Preservation Sutresno, Stephen Aprius
Journal of Computer System and Informatics (JoSYC) Vol 6 No 1 (2024): November 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v6i1.6123

Abstract

Batik Besurek is an Indonesian cultural heritage that presents a variety of motifs reflecting the richness of creativity and symbolic meanings. A significant challenge in this field is accurately and efficiently identifying and classifying batik Besurek motifs, known for their intricate designs and cultural significance. In efforts towards cultural preservation and development, a combination of modern technology and local wisdom is required. One technology that can be utilized is object detection technology using You Only Look Once (YOLO), specifically the latest version, YOLOv8, for the classification of batik Besurek motifs. The dataset collected consists of 1,656 images taken from the Roboflow public repository, containing various motifs such as Burung Kuau, Kaligrafi, Kembang Melati, Rafflesia, and Rembulan. The dataset is divided into 1,324 images (80%) for the training set, 166 images (10%) for the validation set, and 166 images (10%) for the test set. Model training is conducted with hyperparameter values: learning rate of 0.01, batch size of 16, and 100 epochs. The application of the YOLOv8 model as a training model for the batik Besurek motif dataset yields an accurate final model with an average precision value for each motif class of 96%, and an average recall value for each motif class of 93%. This study aims to assist communities in recognizing and distinguishing batik Besurek motifs, contributing to the preservation of Indonesia’s cultural heritage.
Analisis Sentimen Ulasan Pengguna Aplikasi Alibaba.Com pada Google Playstore Menggunakan Naïve Bayes Rahman, Rafi Fadhlur; Irwiensyah, Faldy
Journal of Computer System and Informatics (JoSYC) Vol 6 No 1 (2024): November 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v6i1.6132

Abstract

Alibaba.com, as one of the leading platforms, continues to strive to improve its services based on user feedback. One approach used is the collection of user reviews on the Google Play Store. To enhance service quality and user experience, sentiment analysis of these reviews becomes crucial. In this study, the Naive Bayes algorithm is applied to analyze the sentiment of the reviews with the aim of determining whether the sentiment is positive or negative. The data, consisting of reviews, was obtained through web scraping, resulting in 998 reviews that were processed through preprocessing stages. The dataset was then divided into training and testing data with a 60:40 ratio, where 599 reviews were manually labeled for training, and 399 reviews were used as test data. The Naive Bayes algorithm subsequently categorized the reviews as either positive or negative sentiment. An evaluation with a confusion matrix was then used to assess performance, this model showed an accuracy of 77.44%, precision of 83.39%, and recall of 85.16%. A total of 721 reviews were categorized as positive sentiment, while 277 reviews were categorized as negative sentiment. The main issues identified in the negative reviews included challenges related to language and payment. Additionally, there were complaints regarding online buying and selling fraud, which is a significant issue on this platform. Many users reported negative experiences related to transactions that did not match expectations, items that were not received, or products that did not match their descriptions. This highlights the importance of better verification and security systems to protect users from fraud. This study demonstrates that the Naive Bayes algorithm is quite efficient in analyzing user review sentiments on the Alibaba.com application.
Pemanfaatan Metode Analytical Hierarchy Process (AHP) dalam Sistem Pendukung Keputusan untuk Seleksi Programmer Rahmi, Lidya; Muchlis, Lita Sari; ., Iswandi; ., Adriyendi; Sari, Dewi Putri; Nadya, Rahma; Roofi, Ibnu
Journal of Computer System and Informatics (JoSYC) Vol 6 No 1 (2024): November 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v6i1.6146

Abstract

The recruitment process for programmers at the Tanah Datar District Communication and Information Office remains manual. Candidate evaluations are frequently performed without structured decision-making protocols, resulting in potential errors in identifying the most suitable applicants. This study seeks to develop a Decision Support System (DSS) employing the Analytical Hierarchy Process (AHP) methodology for the selection of programmers at the Tanah Datar District Communication and Information Office, by amalgamating hard-skill and soft-skill competencies. This study employs the Rapid Application Development (RAD) technique, comprising four phases: requirements planning, user design, building, and cutover. During the requirements planning phase, system needs are collected via interviews, documentation, and observation. This phase establishes the criteria, which encompass interviews (C1), application creation and design proficiency (C2), database and installation competencies (C3), and problem-solving skills (C4). During the user design phase, the system design is executed, followed by system development with PHP and MySQL in the building phase. In the cutover phase, system testing was performed utilizing the Computer System Usability Questionnaire (CSUQ) technique, yielding an average score of 86.74, which signifies that the system possesses commendable usability quality and is highly regarded by users. The research findings indicate that the AHP-based Decision Support System is successful in facilitating the selection process, expediting decision-making, and aiding agencies in identifying the most suitable applicants who fulfill the established criteria.
Analisis Sentimen Terhadap Film “Dirty Vote” Pada Media Sosial X dan Youtube dengan Algoritma Naive Bayes dan SVM Sasongko, Kukuh Hadi; Hilda, Atiqah Meutia
Journal of Computer System and Informatics (JoSYC) Vol 6 No 1 (2024): November 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v6i1.6150

Abstract

Indonesia's presidential and vice-presidential elections in 2024 sparked widespread discussion on social media, particularly regarding Gibran's candidacy as a vice presidential candidate. The documentary Dirty Vote deepened the discussion by exposing the practice of fraud and manipulation in the election, raising public concerns about the integrity of the election. This study aims to analyze public sentiment towards the Dirty Vote film on social media YouTube and Twitter (X) using Naïve Bayes and SVM algorithms. Data was collected through crawling techniques on YouTube and Twitter (X) from February 11, 2024 to August 30, 2024. The preprocessing stages include Cleansing, Transform Cases, Tokenizing, Stopwords Removal, and Stemming. The data obtained is then classified into positive and negative sentiment categories. Model evaluation is done using Confusion Matrix which includes accuracy, precision, and recall. The results showed variations in model performance on both social media. On YouTube, Naïve Bayes algorithm achieved 81.24% accuracy, with 63.44% precision and 100.00% recall, while SVM showed 86.94% accuracy, 91.62% precision, and 65.92% recall. On Twitter (X), Naïve Bayes produced the highest accuracy of 95.13%, precision 88.86%, and recall 100.00%, while SVM recorded the same accuracy of 95.13%, with the highest precision of 99.66% and recall 87.76%. These results show that SVM is superior in precision, while Naïve Bayes has a consistently high recall. The analysis showed dissatisfaction with election integrity on almost all YouTube and Twitter (X) platforms.
Pemanfaatan Algoritma Levenberg-Marquardt untuk Analisis Prediksi Persentase Penduduk yang Melakukan Pengobatan Sendiri Darma, Surya; Firzada, Fahmi
Journal of Computer System and Informatics (JoSYC) Vol 6 No 1 (2024): November 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v6i1.6153

Abstract

Self-medication is a practice in which individuals use drugs or administer treatments without a doctor's prescription or medical supervision. This phenomenon has become a significant health issue in Indonesia, particularly in the city of Pematangsiantar and Simalungun Regency, where many residents tend to self-medicate without receiving adequate medical consultation. Therefore, the aim of this study is to analyze the predicted percentage of health independence development among residents who self-medicate in Pematangsiantar and Simalungun Regency using the Levenberg-Marquardt algorithm. The research data consists of time-series data on the percentage of residents self-medicating in Pematangsiantar and Simalungun Regency from 2018 to 2023, obtained from the Central Statistics Agency of North Sumatra. The analysis was conducted using five architecture models: 4-5-1, 4-10-1, 4-15-1, 4-20-1, and 4-25-1. The results show that the Levenberg-Marquardt algorithm with the 4-15-1 architecture model provided the best performance, with the lowest Mean Squared Error (MSE) value of 0.0268691174 compared to the other architecture models. This study is expected to assist local governments by providing information on the development of the percentage of residents who self-medicate in Pematangsiantar and Simalungun Regency, enabling them to formulate the best policies for improving public health in the region in the future. This research also contributes to the development of artificial intelligence-based health prediction methods, particularly for analyzing the percentage of self-medicating residents in complex and dynamic regional contexts.
Implementasi Algoritma Gunning Fog Index Untuk Mengukur Tingkat Keterbacaan Tugas Akhir Mahasiswa Menggunakan Pemrograman Python Riza, Noviana; Supriady, Supriady; Setiadi, Hilman; Prianto, Cahyo
Journal of Computer System and Informatics (JoSYC) Vol 6 No 1 (2024): November 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v6i1.6176

Abstract

This research is motivated by the importance of abstracts in a scientific work as a key element that provides an overview of the content of the research. Abstracts are a key element in scientific work, and their readability is important so that the research message can be well understood by readers. However, students' abilities in writing abstracts vary greatly. Some students still have difficulty in compiling abstracts that comply with the rules, which affects the readability and understanding of their research by readers. In addition, there are also students who are already proficient in making abstracts. Therefore, this study aims to measure the level of readability of students' final project abstracts and identify the factors that influence it using the Gunning Fog Index. This study involves the analysis of 100 abstracts from various departments at the University of Logistics and International Business. A web-based application will be built using Python. The model created will be implemented in the form of an application to make it easier for users to find out the level of readability. The implementation results show that the average Gunning Fog Index of the 100 abstracts analyzed was 9.2564, which means that the abstracts can generally be understood by readers with an education level equivalent to grade 9 of junior high school. The majority of abstracts (68%) were categorized as easy to read, while 9% were in the moderate category and 23% were difficult. The analysis also showed variations in readability levels between departments, with Study Program D having the highest average Gunning Fog Index and Study Program A having the lowest. Overall, this implementation successfully demonstrated the readability levels of students’ abstracts and provided insight into variations in writing quality between departments.
Aplikasi Web Question Answering Menggunakan Langchain OpenAI Tentang Peraturan Perundang-undangan Bidang Pendidikan Saputra, Ikhsan Dwi; Harahap, Nazruddin Safaat; Agustian, Surya; Fikry, Muhammad; Oktavia, Lola
Journal of Computer System and Informatics (JoSYC) Vol 6 No 1 (2024): November 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v6i1.6182

Abstract

In the rapid development of information technology over the past few years, the ease of accessing information has been one of the significant achievements. Artificial intelligence (AI) has emerged as a potential tool in bringing innovative solutions in various sectors of human life. This research aims to develop a web application capable of answering questions related to educational legislation using the LangChain framework and BERT model. The primary issue addressed is the complexity and volume of legal documents that are challenging for lay users to access and understand. The methodology involves converting legal documents from PDF to text, segmenting the text using LangChain, and evaluating system performance with BERTScore and ROUGE Score. The results indicate that BERTScore is superior in measuring the alignment between the system’s answers and reference answers, with some questions achieving a score of 100%. However, there are limitations, such as the manual effort required for document conversion and the substantial computational resources needed for text processing. This research significantly contributes to facilitating access and comprehension of educational legal documents and opens opportunities for further development with more advanced conversion techniques and AI models.
Implementasi Algoritma K-Nearest Neighbor dalam Klasifikasi Penyakit Kanker Paru Paru Hadiansyah, Zikri; Rozikin, Zaenur; Fatchan, Muhamad
Journal of Computer System and Informatics (JoSYC) Vol 6 No 1 (2024): November 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v6i1.6195

Abstract

Lung cancer is one type of cancer with the highest death rate in the world. Smoking is the main risk factor that causes 20% of cancer deaths and 70% of lung cancer deaths in the world. However, people who do not smoke can also suffer from lung cancer, especially if they are frequently exposed to air pollution, live in an environment contaminated with dangerous substances, or have a family member who suffers from lung cancer. Early detection in the classification of lung cancer is an important factor in increasing the patient's chances of survival. Therefore, this study aims to classify lung cancer using the K-Nearest Neighbor algorithm. The K-Nearest Neighbor algorithm was chosen because in various studies it has a better level of accuracy compared to other supervised learning algorithms. To overcome data imbalance, the Random oversampling technique is used. Based on tests carried out using the Confusion Matrix, the results of measuring the performance values ​​of Accuracy, Precision, Recall and f1-score using the K-Nearest Neighbor algorithm with Random oversampling technique, it can be concluded that the K-Nearest Neighbor algorithm received an Accuracy value of 0.99, Precision 0.99, Recall 0.99 and f1-score 0.99.
Prediksi Nilai Tukar Mata Uang Menggunakan Algoritma Long Short-Term Memory dan Random Forest Hidayat, Imam; Akbar, Lalu A. Syamsul Irfan; Rachman, Ahmad SjamSjiar
Journal of Computer System and Informatics (JoSYC) Vol 6 No 1 (2024): November 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v6i1.6200

Abstract

Currency exchange rate is an exchange between two different currencies, which is a comparison of the value or price between the two currencies and this comparison is often called the exchange rate. Currency exchange rate movements are very complex and influenced by many factors, including economic, political, and social factors. In an effort to understand and predict these movements, many studies have been conducted using various methods of analysis and prediction. however, there is still no consensus on the best method to predict exchange rate movements. This study aims to compare the performance between the Long Short Term-Memory and Random Forest algorithms in predicting the exchange rate of the Rupiah (IDR) against the Singapore Dollar (SGD). By utilizing the historical data of currency exchange rate movements, the main data and the data of import and export values from the two countries as additional variables, After going through a series of stages ranging from data collection, preprocessing, to modeling, the evaluation results show that the Long Short Term-Memory algorithm has a better performance with a Root Mean Square Error (RMSE) of 152.28, Mean Absolute Percentage Error (MAPE) 1.25%, and 98.74% accuracy, while Random Forest has an RMSE of 284.3, a MAPE of 2.07%, and an accuracy of 97.93%. These results show that Long Short Term-Memory is superior in capturing complex exchange rate change patterns, making it a more effective choice in predicting currency exchange rates than Random Forest.
Implementasi K-Means Clustering dalam Mengklasifikasi Pengaruh Les Terhadap Prestasi Siswa dengan Metode Elbow Habibie, Alief Fathul; R, Rakhmat Kurniawan
Journal of Computer System and Informatics (JoSYC) Vol 6 No 1 (2024): November 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v6i1.6201

Abstract

Student achievement and ability are very important perspectives to consider. In this regard, Madrasah Ibtidaiyah Swasta (MIS) Al-Falah Medan is an educational institution that has a good reputation in both religious and other sciences. This study aims to analyze the influence of tutoring on student achievement at Madrasah Ibtidaiyah Swasta (MIS) Al-Falah Medan using the K-Means Clustering method and the Elbow technique to determine the optimal number of clusters. The data used in this research involves 514 students from classes 1A to 6B, with the analyzed variables including semester exam scores, participation in additional tutoring, and extracurricular activities. The analysis results show that students who participate in additional tutoring have higher average scores compared to those who do not. The average score of students in the semester exams is 87.71, while the average score for students participating in tutoring and extracurricular activities is 87.12. The clustering process results in four groups of students, with the highest performing group in cluster 2, while the lowest performing groups are in clusters 3 and 4. This research provides important information for the school in understanding the impact of tutoring on students' academic performance and can be used to improve learning strategies at MIS Al-Falah Medan.