cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Nelly Khairani Daulay
Contact Email
nellykhairanilestari@gmail.com
Phone
+6282370070808
Journal Mail Official
mesran.skom.mkom@gmail.com
Editorial Address
Jalan sisingamangaraja No 338 Medan, Indonesia
Location
Kota medan,
Sumatera utara
INDONESIA
Bulletin of Artificial Intelligence
Published by CV. Graha Mitra Edukasi
ISSN : -     EISSN : 29623944     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering
The field of study of the Bulletin of Artificial Intelligence journal, in the field of Artificial Intelligence, includes: 1) Decision Support Systems, 2) Data Mining, 3) Expert Systems, 4) Big Data, 5) Text Mining, and 6) Natural Language Processing. But does not rule out the possibility of publishing manuscripts in the field of Computer Science.
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 5 Documents
 1 
Search results for , issue "Vol 1 No 2 (2022): October 2022" : 5 Documents clear
Implementasi Algoritma Support Vector Machine untuk Analisis Sentimen LGBT di Indonesia Mustakim Mustakim; Muhammad Ridwan; Nanda Try Luchia
Bulletin of Artificial Intelligence Vol 1 No 2 (2022): October 2022
Publisher : Graha Mitra Edukasi

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

LGBT cases began to appear openly in Indonesia in 2016. This case has received a lot of discussion in that year until now because of the number of people who commented agreeing and disagreeing with actions, activities, and the existence of the LGBT gender in Indonesia. The sentiments from the community's comments refer to various aspects of life so as to produce community opinions that are positive, negative and neutral. Seeing this, it is necessary to perform a classification and analysis of tweet sentiments to see the tendency of each community's opinion. Analysis and classification is done with text mining data processing techniques using the Support Vector Machine (SVM) algorithm. The classification process is done in 3 stages with the division of data 90%:10%, 80%:20% and 70%:30% using 3 kernels namely linear, polynominal and Radial Basic Function (RBF). The classification results obtained from the three kernels show that the tendency of society's view of LGBT cases is negative and neutral which is shown with the highest accuracy on the linear and RBF kernels. The SVM experiment produced an accuracy of 74% on the linear kernel with 90%:10% and 74% data experiments and on the RBF kernel with C=100 gamma=0,01. The grouping of this tweet sentiment data resulted in an analysis of the tendency not to support or disagree with the LGBT gender because it is not in accordance with the established basis in the country of Indonesia which prioritizes religious aspects over other aspects
Implementasi Algoritma Adaptive Huffman Coding Pada Aplikasi Kamus Kedokteran Berbasis Android Rio Parmana
Bulletin of Artificial Intelligence Vol 1 No 2 (2022): October 2022
Publisher : Graha Mitra Edukasi

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Technological advances that continue to develop in the era of globalization demand progress from all fields that can provide convenience in presenting information and sending information, with the increasing number of current internet users the information presented is increasing, one of which is information in the form of text such as warning messages, appeals or text that describes an event in the form of text information is used more often than in other forms. The size of the file or text file can be overcome by using a compression or compression process. Compression is a process to reduce the size of a file so as to save storage space and the process of exchanging data. The Huffman algorithm compression technique is able to provide memory usage savings of up to 30%. The Huffman coding algorithm has a complexity of 0(n log n) for a set of n characters
Implementasi Algoritma Redundant Pattern Encoding Untuk Menyisipkan Pesan Teks Ke Dalam Gambar dan Algoritma Fibonacci Codes Untuk Kompresi Frayogi Aditiya
Bulletin of Artificial Intelligence Vol 1 No 2 (2022): October 2022
Publisher : Graha Mitra Edukasi

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Information is a collection of data in the form of unified text that is public or confidential. Confidential data is data that contains something or that is not for publication. One way to secure the data is to use Steganography techniques. This provides tremendous benefits for maintaining data confidentiality. In steganography there are several methods, one of which is Redundant Pattern Encoding. However, from this process, the object that will be used as a container to accommodate the data will experience a change in the size of the data. This can raise the suspicion of many parties who want to access the data. This study describes how the procedure is carried out to compress objects that are used as containers to insert messages. The process uses the Fibonacci Codes method which is a simple and very simple data compression method. The results of this research will produce a stronger level of data security.
Analisis Perbandingan Algoritma Longest Common Subsequence Dengan Simple Hill Climbing Pada Permainan TTS Yardani Yardani
Bulletin of Artificial Intelligence Vol 1 No 2 (2022): October 2022
Publisher : Graha Mitra Edukasi

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Crossword is a game to sharpen the brain. Crossword puzzles can be used in the field of education to test students' abilities, so that the questions used are adapted to their needs. But it will be difficult if a large number of questions are used, because to make a crossword puzzle from a set of questions, the possible combinations of existing words form a crossword puzzle. Research in optimizing the filling of empty spaces in the crossword matrix board certainly requires an algorithm using a comparison of the Longest Common Subsequence (LCS) algorithm and the Simple Hill Climbing algorithm. By comparing the performance of the Longest Common Subsequence (LCS) algorithm and the Simple Hill Climbing algorithm, it will be known how the work and performance in terms of speed and accuracy of the two algorithms work. The questions displayed in the crossword application are obtained from the database access randomly by the program. The crossword puzzle that is formed is a collection of answers to the questions used, the answers to the questions are arranged in such a way that they intersect with one another. On this matrix board, the answers to the questions will be placed to form a crossword puzzle. Each letter of the answer will occupy one cell on the matrix board. The number of questions is the number of questions that will be used in the crossword game. Apart from receiving input from the user, the application also provides output to the user in the form of a crossword puzzle and the correct answer from the TTS
Peramalan Nilai Penjualan Gas Elpiji 3 Kg di Sumatera Utara dengan bantuan Analisis Metode Jaringan Saraf Tiruan Maulidya Rahma Siregar; Adinda Putri Azhari; Dedy Hartama; Agus Perdana Windarto
Bulletin of Artificial Intelligence Vol 1 No 2 (2022): October 2022
Publisher : Graha Mitra Edukasi

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This research is related to forecasting the sales value of 3 Kg LPG in North Sumatra. The level of sales is influenced by customer satisfaction, service and customer needs. The purpose of this study is to determine the level of sales of 3 Kg LPG in North Sumatra and can overcome problems and overcome the amount of LPG demand in North Sumatra. So this research is needed using an artificial neural network method with a backpropagation algorithm to find the best sales results. The data used is divided into 2 parts, namely training and test data. The best network is taken from the Mean Square error (MSE) value and the smallest test. The experiments carried out in this study used a data rotation pattern, with 6 training and testing models. The experimental results of the 3-10-1 model are tests with the highest accuracy value, which is 100% and the MSE test is 0.00100005

Page 1 of 1 | Total Record : 5

 1 

Filter by Year

2022 2022


Reset
Filter By Issues
All Issue Vol 3 No 1 (2024): April 2024 Vol 2 No 2 (2023): October 2023 Vol 2 No 1 (2023): April 2023 Vol 1 No 2 (2022): October 2022 Vol 1 No 1 (2022): April 2022