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 38 Documents
Search results for , issue "Vol 5 No 4 (2024): August 2024" : 38 Documents clear
Analisis Sentimen Program Makan Gratis Pada Media Sosial X Menggunakan Metode NLP Anggriyani, Wisda; Fakhriza, Muhammad
Journal of Computer System and Informatics (JoSYC) Vol 5 No 4 (2024): August 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i4.5826

Abstract

This study aims to analyze public sentiment toward the free meal program initiated on Social Media X. Utilizing Natural Language Processing (NLP) methods klasification navie bayes, this research processes text data collected from various user comments and posts on the platform. The collected data is then classified into positive, negative, and neutral sentiment categories. The analysis process involves text preprocessing techniques, including tokenization, stemming, and stop words removal, to enhance the accuracy of the sentiment model. The analysis results show that most users responded positively to the program, particularly regarding the social benefits it offers. However, some negative sentiments were also detected, primarily related to the program's implementation and the quality of the provided meals. These findings offer valuable insights for program organizers to comprehensively understand public perception and make improvements in the future. This study also highlights the importance of using NLP in social media data analysis as a tool to identify and understand public opinion on a large scale.
Analisis Algoritma C45 dan Regresi Linear untuk Memprediksi Hasil Panen Kelapa Sawit Nurahman, Nurahman; Ernawati, Nindi
Journal of Computer System and Informatics (JoSYC) Vol 5 No 4 (2024): August 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i4.5828

Abstract

Indonesia, as one of the main producers of palm oil in the world, has an agricultural sector that is very influential on the national economy, especially through palm oil exports. Prediction of oil palm yields is crucial to improve efficiency in planning and resource management. This study was conducted to compare the performance of two prediction methods, namely the C45 Algorithm and Linear Regression, in predicting oil palm yields. The formulation of the problems raised in this study includes: (1) How does the performance of the C45 Algorithm and Linear Regression compare in predicting oil palm yields? (2) How accurate are the predictions generated by the two algorithms based on historical data on crop yields? (3) What are the factors that influence the choice between C45 Algorithm and Linear Regression for oil palm yield prediction? The data used in this study is historical data from PT. Surya Inti Sawit Kahuripan, which includes 106 data blocks. The variables analyzed included land area, number of trees, number of trees per hectare, planting year, soil type, fertilizer use plan, and yield in tons. Data analysis was carried out using the C45 Algorithm, which forms a decision tree based on historical data, and the Linear Regression method, which analyzes the linear relationship between independent variables and dependent variables. Prediction accuracy is measured using Root Mean Squared Error (RMSE). The results show that the C45 Algorithm has a lower RMSE value than Linear Regression, indicating that the C45 Algorithm provides more accurate predictions.
Implementasi Error Checking dalam Integritas Pengiriman Data Pada Komunikasi Ground Control Station dan UAV Menggunakan Algoritma CRC Assidik, Reksa Qodri; Muludi, Kurnia; Triloka, Joko
Journal of Computer System and Informatics (JoSYC) Vol 5 No 4 (2024): August 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i4.5829

Abstract

Komunikasi wireless adalah komunikasi secara wireless atau tanpa kabel contoh komunikasi wireless adalah transfer informasi apapun secara jarak jauh tanpa menggunakan kabel. Pengiriman data secara nirkabel mempunyai tingkat kehilangan data yang sangat besar. Kehilangan data dalam jaringan sensor nirkabel umum dan mempunyai pola khusus karena banyak factor terjadi kerusakan yang tidak terduga yang sangat mengurangi akurasi rekontruksi. Maka dari itu perlu adanya pengamanan data agar data yang dikirim secara nirkabel akan tetap aman pada saat proses mengirim dan menerima Kontes Robot Terbang Indonesia (KRTI) merupakan kompetisi pesawat tanpa awak yang sangat bergengsi di Indonesia yang di selenggarakan oleh Kementerian Riset, Teknologi, dan Pendidikan Tinggi Republik Indonesia melalui Pusat Prestasi Nasional yang di gunakan untuk seluruh perguruan tinggi di Indonesia. dalam kompetisi ini peserta di wajibkan membuat pesawat tanpa awak dengan sistem kendali sebagai pesawat kendali dan membuat Ground Control Station (GCS) yang dimana kendaraan tersebut harus dapat terbang dan menjalankan misi sesuai dengan peraturan yang tertera dalam kompetisi pedoman teknis.Dalam penelitian ini di khususkan pada pengamanan data pada saat pengiriman ke Ground Control Station. pembuatan Ground Control Station menggunakan Node.js dalam merancang desain front end dan back end serta nilai yang akan di kirim peneliti menggunakan alat desain sederhana menggunakan Arduino Mega sebagai pengontrol transmisi data, sensor yang digunakan menggunakan Mpu 6050 Inertial Measurement Unit ( IMU) dan Global Positioning System (GPS) Neo 8m, dan telemetri yang digunakan adalah NRF24l01. Berdasarkan hasil pengujian dengan mengirimkan 11 data sensor menggunakan checksum di dapatkan bahwa jumlah data sensor yang masuk ke Ground Control Station masih aman dan dapat meminimalisir kerusakan paket data serta menggunakan Cyclic Redudancy Check (CRC) sebagai checksumnya. keutuhan data yang di terima tetap terjaga dengan cukup baik karena algoritma Cyclic Redudancy Check (CRC) mampu membuang data yang tidak lengkap/rusak. Dari hasil penelitian sementara dengan menggunakan algoritma CRC sebagai error checking dapat mampu mendeteksi paket-paket yang rusak saat dikirim ke receiver dapat terlihat jelas dari segi jarak,saat pengujian jarak tanpa menggunakan CRC dengan varian jarak 10 sampai 50 meter terjadi kerusakan paket data dan semakin jauh komunikasi yang dilakukan paket yang rusak semakin banyak. Dari jarak yang paling jauh yaitu 50 meter,dari 5 percobaan pengiriman dan di setiap percobaan selalu ada paket data yang mengalami kerusakan paket data, namun dengan menggunakan algoritma CRC dalam error checking di jarak varian jarak 10 sampai 50 meter dalam 5 kali percobaan pengiriman dan diambil 10 paket yang dikirim masih belum ada paket yang rusak alias 0% kerusakan paket data.
Penerapan Algoritma K-Medoids Data Mining untuk Clustering Wilayah Penderita Demam Berdarah Berdasarkan Data Set Wahyuni, Diny
Journal of Computer System and Informatics (JoSYC) Vol 5 No 4 (2024): August 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i4.5831

Abstract

Disease is a disorder that occurs in the body, either in form or function, so that the body cannot work properly or normally. Dengue fever (DF) is an infection caused by the dengue virus that can cause accurate fever. Dengue fever is still a serious problem for public health. The Health Service in each region has the task of helping the community in dealing with dengue fever cases. Data sets are collections of data arranged in a structured format, such as tables or files, and contain information from various sources. In this study, data mining analysis was carried out using the Clustering technique using the K-Medoids method. The use of the K-Medoids Algorithm is said to be better at grouping datasets than k-means because K-Medoids is one of the effective clustering methods for dealing with small datasets. Data mining can be interpreted as the process of selection, exploration, and modeling of large amounts of data to find patterns or tendencies that are usually not realized. Clustering is a process of grouping records, observations, or grouping classes that have similar objects. The results obtained from the study show that the application of the K-Medoids algorithm can be done to form 2 clusters. In the first cluster there are 4 cluster results and in the second cluster there are 6 cluster results.
Penentuan Desa Terbaik dengan Menerapkan Kombinasi Metode ROC dan SMART Margolang, R. Siddik; Fakhriza, Muhammad
Journal of Computer System and Informatics (JoSYC) Vol 5 No 4 (2024): August 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i4.5834

Abstract

The problem that is used as a reference in this research is the assessment process which still uses the old method, namely by opening pages of documents, so this method takes a lot of time and energy in the assessment process and allows tolerance of values ​​that are similar, making it very difficult to determine the best village. The process of selecting the best village is a very important stage in building a competent and innovative village. The system built using the ROC and SMART methods aims to help data collectors reduce time in data collection and be effective in determining the best villages according to the criteria used. The criteria used are Village Cleanliness (K1), Education (K2), Economy (K3), Security and Order (K4), Role of the PKK (K5), Village Governance (K6) with 7 alternative data samples. Data for this research was collected through interviews and observations at the Rahuning District Office and processed using the ROC and SMART methods for weighting and evaluating decisions. The results of calculations using the ROC and SMART methods found that among the best villages, Gunung Melayu Village was a worthy candidate to become the best village candidate by obtaining a total score of 0.738889.
Penerapan Algoritma Logika Fuzzy Mamdani Untuk Optimalisasi Stok Dari Berbagai Jenis Spareparts Handphone Muntaja, Nadia; Sriani, Sriani
Journal of Computer System and Informatics (JoSYC) Vol 5 No 4 (2024): August 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i4.5836

Abstract

Effective inventory management is crucial for businesses in the mobile phone spare parts industry, where accurate stock levels directly impact operational efficiency and customer satisfaction. Traditional stock management methods are often inadequate in dealing with the uncertainty and complexity of demand forecasting. In the mobile phone repair and distribution industry, demand for spare parts varies significantly depending on factors such as new model launches, device failure rates, and fluctuating market trends. Conventional stock management systems often fail to handle this variability, leading to issues like stock-outs, which harm customer satisfaction, or overstocking, which increases storage costs and the risk of obsolescence. This research addresses these challenges by applying the Fuzzy Mamdani method to optimize spare parts inventory. The study focuses on transforming crisp stock data into fuzzy inputs to improve prediction accuracy. Data from UD.WSP for the year 2023 is fuzzified by incorporating variables such as initial stock, sales volume, and additional stock, with the output variable being the final stock level. The spare parts analyzed include LCDs, batteries, chargers, screen protectors, speakers, RAM, flex cables, rear cameras, front cameras, and SIM trays. The application of the Fuzzy Mamdani method resulted in a Mean Absolute Percentage Error (MAPE) of 11%, indicating a high level of prediction accuracy. These findings demonstrate that the Fuzzy Mamdani method is a viable solution for optimizing spare parts inventory management, offering an advanced approach to managing inventory amidst uncertainty.
A Hybrid Ensemble Approach for Enhanced Fraud Detection: Leveraging Stacking Classifiers to Improve Accuracy in Financial Transaction Airlangga, Gregorius
Journal of Computer System and Informatics (JoSYC) Vol 5 No 4 (2024): August 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i4.5840

Abstract

Fraud detection in financial transactions presents a significant challenge due to the evolving tactics of fraudsters and the inherent imbalance in datasets, where fraudulent activities are rare compared to legitimate transactions. This study proposes a Hybrid Model utilizing a stacking ensemble technique that combines multiple machines learning algorithms, including Random Forest, Gradient Boosting, SVM, LightGBM, and XGBoost, to enhance the accuracy of fraud detection systems. The Hybrid Model is evaluated against traditional machine learning models using a comprehensive cross-validation approach, with results indicating a near-perfect accuracy of 99.99%, outperforming all individual models. The study also examines the trade-offs associated with the Hybrid Model, including increased computational demands and reduced interpretability, highlighting the need for careful consideration when deploying such models in real-world scenarios. Despite these challenges, the Hybrid Model's ability to significantly reduce both false positives and false negatives makes it a powerful tool for financial institutions aiming to mitigate the risks associated with fraudulent activities. In conclusion, the findings demonstrate the effectiveness of hybrid ensemble methods in fraud detection, providing a robust solution that balances the complexities of real-world applications with the need for high accuracy. The research underscores the potential of advanced machine learning techniques in enhancing the security and reliability of financial transactions, offering valuable insights for the development of future fraud detection systems.
Anemia Classification Using Hybrid Machine Learning Models: A Comparative Study of Ensemble Techniques on CBC Data Airlangga, Gregorius
Journal of Computer System and Informatics (JoSYC) Vol 5 No 4 (2024): August 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i4.5848

Abstract

Anemia is a prevalent and potentially serious medical condition characterized by a deficiency in the number or quality of red blood cells. Accurate classification of anemia types is crucial for ensuring appropriate treatment, as different types of anemia require distinct therapeutic approaches. However, the classification of anemia presents specific challenges due to the complexity of the condition, the variability in CBC data, and the need to differentiate between multiple anemia types that may present with overlapping symptoms. In this study, we explore the application of hybrid machine learning models to classify anemia types using Complete Blood Count (CBC) data. We evaluated the performance of various models, including DecisionTree, RandomForest, XGBoost, LightGBM, CatBoost, and ensemble methods such as Stacking and Voting. The ensemble models, particularly Stacking and Voting, demonstrated superior performance with balanced accuracy reaching 0.9976 and F1 scores of 0.9964, significantly outperforming individual classifiers. These results underscore the efficacy of ensemble techniques in handling the complex and imbalanced datasets commonly encountered in medical diagnostics. Despite their high accuracy, we identified challenges related to model interpretability, computational demands, and data quality. The complexity and resource requirements of these models may limit their practical application in resource-constrained environments. This study provides a comprehensive analysis of the trade-offs between model complexity, accuracy, and interpretability, offering valuable insights for the deployment of machine learning models in clinical settings. Our findings highlight the potential of hybrid models to improve anemia diagnosis, suggesting their integration into healthcare systems could enhance diagnostic accuracy and patient outcomes. Future work will focus on expanding the dataset, refining model interpretability, and addressing ethical considerations in the use of AI in healthcare.

Page 4 of 4 | Total Record : 38