cover
Contact Name
Mesran
Contact Email
mesran.skom.mkom@gmail.com
Phone
+6282370070808
Journal Mail Official
jurnal.bulletincsr@gmail.com
Editorial Address
Jalan sisingamangaraja No 338 Medan, Indonesia
Location
Kota medan,
Sumatera utara
INDONESIA
Bulletin of Computer Science Research
ISSN : -     EISSN : 27743659     DOI : -
Core Subject : Science,
Bulletin of Computer Science Research covers the whole spectrum of Computer Science, which includes, but is not limited to : • Artificial Immune Systems, Ant Colonies, and Swarm Intelligence • Bayesian Networks and Probabilistic Reasoning • Biologically Inspired Intelligence • Brain-Computer Interfacing • Business Intelligence • Chaos theory and intelligent control systems • Clustering and Data Analysis • Complex Systems and Applications • Computational Intelligence and Soft Computing • Distributed Intelligent Systems • Database Management and Information Retrieval • Evolutionary computation and DNA/cellular/molecular computing • Expert Systems • Fault detection, Fault analysis, and Diagnostics • Fusion of Neural Networks and Fuzzy Systems • 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 • Knowledge discovery and ontology engineering • Machine Learning, Reinforcement Learning • Networked Control Systems • Neural Networks and Applications • Natural Language Processing • Optimization and Decision Making • Pattern Classification, Recognition, speech recognition, and synthesis • Robotic Intelligence • Rough sets and granular computing • Robustness Analysis • Self-Organizing Systems • Social Intelligence • Soft computing in P2P, Grid, Cloud and Internet Computing Technologies • Support Vector Machines • Ubiquitous, grid and high-performance computing • Virtual Reality in Engineering Applications • Web and mobile Intelligence, and Big Data • Cryptography • Model and Simulation • Image Processing
Articles 291 Documents
Naïve Bayes Classifier dengan Particle Optimize Weight Forward pada Dataset Nuranisah; Yanti Yusman
Bulletin of Computer Science Research Vol. 3 No. 6 (2023): October 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v3i6.290

Abstract

Classification is the process of identifying and grouping objects into classes or categories based on their characteristics. In data mining, there are two processes, namely classification and clustering, which are used to group objects based on similarities. In the classification process, various methods such as K-NN, SVM, and Naïve Bayes are often used and developments are made in the method. The Naïve Bayes classifier is proven to have advantages, such as faster calculation and better accuracy. However, this method has limitations in the attribute selection process. To overcome this limitation, the Particle Optimize Weights Forward algorithm is used to improve accuracy by assigning weights to attributes in the Naïve Bayes method. This approach improves the efficiency and effectiveness of the Naïve Bayes classifier in data classification tasks.
Perancangan Sistem Informasi Presensi Online Karyawan Berbasis Website dengan Face Record dan Geo Location Nur Alif Irawan; Abdul Rahman Kadafi
Bulletin of Computer Science Research Vol. 3 No. 6 (2023): October 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v3i6.294

Abstract

This research discusses the development of an online employee attendance system in the context of the company. Attendance data includes employee attendance, arrival and return information, as well as absence status such as sickness or clearance. Traditionally, some organizations still use physical methods to collect attendance data, which is considered less efficient and effective. The research uses classical waterfall development method to facilitate the process of system development up to release. With face recognition and geo location methods, an online attendance system is proposed with IT infrastructure using private hosting and virtual machines with Red Hat Enterprise Linux 8.7 Operating System as a web server. With the implementation of this system, it is expected that benefits will be realized in the ease for employees to conduct attendance and management capabilities in managing employee attendance data in a structured manner.
Penentuan Program Indonesia Pintar (PIP) Pada Siswa Kurang Mampu dengan Metode Preference Selection Index (PSI) Berbasis Web Nelly Khairani Daulay; Asep Toyib Hidayat; Shelfia Shepty
Bulletin of Computer Science Research Vol. 4 No. 1 (2023): December 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v4i1.296

Abstract

The Indonesia Smart Program (PIP) is a scholarship assistance provided to individuals with the aim of continuing their education as tuition assistance. This program is the government's idea to reduce the high number of children who drop out of school due to lack of funds. This high dropout rate will also later lead to a high crime rate because children who drop out of school cannot work properly. To determine whether or not students are eligible to receive the Indonesia Pintar Program, a decision support system (SPK) is needed that can provide input for schools to assess properly, which students really deserve the scholarship. By using the Preference Selection Index (PSI) method, it is hoped that this method will be able to select the best alternative from a number of alternatives based on criteria from predetermined aspects.  In the Preference Selection Index (PSI) method which is used as a measure of assessment is the value of alternatives, matrix normalization, average performance value, preference variation value, preference value deviation, criteria weight, calculate the final value, and determine the ranking that will determine the optimal alternative, namely students who are entitled to a scholarship.  The purpose of this research is to determine which students are eligible and not eligible to receive assistance from the government in the form of PIP. The results of this study are in the form of rankings with the highest value of 0.7686 and ranked first or rank 1 and the lowest value of 0.7091 is ranked 5th.
Prediksi Tingkat Produksi Bawang Goreng menggunakan Metode K-Means dan Fuzzy Inference System Wisudawaty, Priska
Bulletin of Computer Science Research Vol. 4 No. 1 (2023): December 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v4i1.297

Abstract

Shallots are a strategic commodity because they are needed for household consumption as well as the food industry. Shallots are usually used as a cooking spice, or as a topping for food dishes called fried onions. Shallots are easily damaged, one way to prevent damage is to process shallots into fried onions. Sales of fried onions fluctuate every month due to consumer demand, therefore in this research a grouping of production levels and predictions of fried onion production was carried out. The methods used in this research are K-Means and Fuzzy Sugeno. From the results of research using the K-Means method, there are 3 clusters of fried onion production levels, namely high, medium and small production levels. High production levels were found in months 4, 5, 9, and 10; moderate production levels in months 1, 2, 3, 6, 7, 8 and 11; while a small production level was found in the 12th month. Based on system testing using the fuzzy Sugeno method, data was generated that could be processed and produce 9 rules to serve as a reference in predicting fried onion production for the following years. Apart from that, based on the results of the Mean Absolute Percent Error calculation, the capability of the model created is good and accurate because it has a value of 14.2%. Fried onion production levels in the 4th and 12th months have more accurate predictions compared to other months
Prediksi Harga Saham pada Portofolio Investor dengan Analisis Time Series Harga Saham menggunakan ANN Wibiksana, Hendra
Bulletin of Computer Science Research Vol. 4 No. 1 (2023): December 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v4i1.298

Abstract

The Indonesian Stock Exchange (BEI) is a place for stock market trading in Indonesia. In general, this is represented by the Composite Stock Price Index (IHSG) value. IHSG itself is the combined value of all shares listed on the Stock Exchange. It doesn't matter whether the shares traded that day are up, down, flat (no change in value), not traded, or even suspended (prohibited from making transactions within a certain period of time). The stock data source used is the closing price of BNI, BCA and Mandiri shares for 15 years from 2008-2022 from the Indonesian Stock Exchange (via the Yahoo Finance site). Each stock data is trained and tested, to see how accurate it is using this method. The stock prices predicted by ANN are combined into a portfolio, this portfolio will show an increase or decrease. At the end of the process, the rate of change in stock prices from predicted losses to predicted profitable stock prices is calculated. The daily data accuracy of BNI, BCA and Mandiri is 97.6927%, 97.9754% and 97.6275% respectively. Weekly data accuracy is slightly smaller than daily accuracy. The accuracy of weekly data for BNI, BCA and Mandiri is 95.7673%, 97.1222% and 96.5592% respectively. Monthly data accuracy is slightly smaller than weekly accuracy. The accuracy of BNI, BCA and Mandiri monthly data is 90.4161%, 94.781% and 93.0619% respectively. If an investor focuses all his funds on buying just one share, he will get 3 times the portfolio profit from before. If the profit on BNI shares is 46.12%, then in terms of portfolio, the investor gets a profit of 46.12% x 3 = 138.36%. Compare this with the profit levels of the 3 banks, which if added up, the value becomes as follows: 46.12+54.42+56.01 = 156.55%. So there is an additional profit from the portfolio of 156.55% - 138.36% = 18.19%.
Penerapan Uji Fungsionalitas dan Uji Pengguna Augmented Reality Word Warrior Sebagai Media Ajar Kosakata Bahasa Inggris Andam Lukcyhasnita; Ferry Fachrizal; Juneidy
Bulletin of Computer Science Research Vol. 4 No. 3 (2024): April 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v4i3.301

Abstract

This research developed and tested the "Word Warrior" game based on Augmented Reality (AR), applied as an Instagram filter, as a medium for teaching English vocabulary. The method used was Research and Development (R&D) with the 4D model (Define, Design, Development, Dissemination). The study focused on functionality and user testing. Functionality testing showed that all game features worked according to specifications after several improvements. User testing involved students from Politeknik Negeri Medan, indicating that the game is easy to use and well-received, with an overall product rating of 78.5. The lowest average score was found in the game mechanics aspect, with a value of 77.5, although this aspect was still rated as good. This will serve as a basis for future evaluations and improvements to enhance the comfort and ease of use for future players. In conclusion, the AR-based "Word Warrior" game effectively serves as a vocabulary teaching medium, meeting user needs and expectations, and providing important references for the further development of AR-based educational games in the future.
Penentuan Asosiation Rule Pada Penjualan Produk UMKM Tugu Mulyo Menggunakan Metode Apriori Wulandari, Cindi; Sunardi, Lukman; Syaifudin, Pebrian
Bulletin of Computer Science Research Vol. 4 No. 1 (2023): December 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v4i1.303

Abstract

Pondok Roti has many existing variants, ranging from chocolate bread, mocca bread, round bread, donut bread, coconut bread, strawberry bread and pineapple bread, green bean bread, birthday cake, burgers, hot dogs, pizza, so the bread that is produced must be right so that the bread can be sold out without any stale and moldy bread because it is not sold. The number of unsold breads will harm the business owner. Transactions that occur in a day are quite a lot in this bread business. Sales transactions are still recorded manually using excel, and existing data has not been managed properly to become new information that can help the management in bread production. The many types and flavors of bread make it easy for buyers to choose and buy the bread they want and like. Looking at existing transaction data, it can be seen that buyers prefer certain flavors. Knowledge Discovery in Databases (KDD) is used to explain how the process of extracting information hidden in the database. Knowledge Discovery in Databases (KDD) and data mining are related to each other. This research uses the apriori algorithm to get a rule base for purchasing products at Pondok Roti stores. The apriori algorithm will later be used to find the most frequent combination of an itemset. Research data will be simulated to get the best rule base using the Weka application. The results of the research are in the form of association rules on the sale of Tugu Mulyo MSME products.
Implementasi Sistem Penjadwalan Mata Kuliah Menggunakan Metode Algoritma Genetika Berbasis Web Toyib Hidayat, Asep; Hakim, Lukman; Rio; M.Afif Ravanza
Bulletin of Computer Science Research Vol. 4 No. 1 (2023): December 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v4i1.304

Abstract

The process of preparing the lecture schedule at Bina Insan University is still done semi-manually with the help of Microsoft Excel and takes days, even weeks, whereas making the schedule must be done optimally and quickly because the schedule will be used for lecture activities each semester, so that the scheduling process can be carried out effectively and efficiently, so we need an application that can simplify the scheduling process, namely a scheduling application and applying the right algorithm, one of the algorithms that can be used in scheduling applications is the Genetic Algorithm. Course scheduling is a process of allocating courses, lecturers, space and time by matching predetermined rules so that all these components can be fulfilled. Genetic Algorithms are search algorithms that are based on natural selection mechanisms and natural genetics. The results of the research are in the form of a schedule that is prepared automatically without any more clashes between times and classes to be used
Metode Spread Spectrum untuk Penyisipan Pesan pada Citra Digital Herri Setiawan; Bedy Briliant Wijaya; Dewi Sartika
Bulletin of Computer Science Research Vol. 4 No. 1 (2023): December 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v4i1.310

Abstract

Abstract The importance of the value of information in a message means that the message often does not reach the recipient, but instead falls into the hands of unwanted people. Various techniques are used to prevent access by unauthorized persons. One of the various techniques to protect this information is steganography, which is the hiding of a message inside another message to avoid suspicion that someone is trying to steal information. The initial stage of the insertion process is to perform a binary spread of the message characters with a scalar magnitude of 4 to produce a new segment followed by the generation of a random number (pseudonoise random number) using the steganography key and converted into binary form. Then proceed with modulation with XOR logic operation between the value of the binary segment and the line of random numbers that have been converted into binary to produce a new binary that will be inserted into the digital image object. The spread spectrum method produces quite good image quality after the insertion process, this can be proven by the PSNR test results which are more than 30 dB.
Penerapan Metode Fuzzy Tsukamoto dalam Penilaian Kinerja Karyawan di Perusahaan Air Minum Kabupaten OKU Joko Kuswanto; Benny Maulana; Ryan Vernando; Suhendra Berta
Bulletin of Computer Science Research Vol. 4 No. 1 (2023): December 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v4i1.312

Abstract

One effective way to encourage employee motivation is to provide recognition in the form of rewards that are in accordance with their performance. The assessment process to determine the best employees needs consideration and is certainly not easy because it must be in accordance with the criteria set by the company. Seeing these conditions, the need for the application of computerized systems that can be a solution to overcome complexity in decision making. One method in decision support systems is the fuzzy method. The method used in this study is Tsukamoto's fuzzy method. The employee appraisal process is carried out based on several criteria such as performance, discipline, and ability. From the calculation results, a Z value of 57.5 was obtained. The value is included in the category considered for reward. Based on the results of the assessment, it can be concluded that Tsukamoto's fuzzy method can be applied in employee performance appraisal.

Page 9 of 30 | Total Record : 291