cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Mesran
Contact Email
mesran.skom.mkom@gmail.com
Phone
-
Journal Mail Official
jurnal.bits@gmail.com
Editorial Address
-
Location
Kota medan,
Sumatera utara
INDONESIA
Building of Informatics, Technology and Science
Published by Forum Kerjasama Pendidikan TInggi
ISSN : 26848910     EISSN : 26853310     DOI : -
Core Subject : Science,
Computer Science & IT
Building of Informatics, Technology and Science (BITS) is an open access media in publishing scientific articles that contain the results of research in information technology and computers. Paper that enters this journal will be checked for plagiarism and peer-rewiew first to maintain its quality. This journal is managed by Forum Kerjasama Pendidikan Tinggi (FKPT) published 2 times a year in Juni and Desember. The existence of this journal is expected to develop research and make a real contribution in improving research resources in the field of information technology and computers.
Arjuna Subject : -
Articles 889 Documents
 37   38   39   40   41 
Optimal Number Data Trains in Hoax News Detection of Indonesian using SVM and Word2Vec Asramanggala, Muhammad Sulthon; Prasetyowati, Sri Suryani; Sibaroni, Yuliant
Building of Informatics, Technology and Science (BITS) Vol 5 No 1 (2023): June 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i1.3516

Abstract

Along with the development of the era of technological development also has an increase. Information dissemination occurs very quickly on social media, especially Twitter. On Twitter, only some news circulating is necessarily accurate information. Lots of information that is spread is hoax news that irresponsible individuals apply. In this research, the author will build a system to determine the optimal amount of data trained in the hoax news classification process. In this study, the authors will use the support vector machine and word2vec algorithms to classify hoax and non-hoax news on the system to be created. In this study, five experiments were carried out with the number of train data used as many as 5000, 10000, 15000, 20000, and 25000. 5000 data train results in an accuracy of 77.28%, 10000 data train produce an accuracy of 79.68%, data 15,000 trains produce an accuracy of 79.892%, 20,000 data trains produce an accuracy of 80,416%, and 25,000 data trains produce an accuracy of 81,184%, by using a combination of unigram with token full token selection. This research aims to build a hoax detection system that can determine the optimal amount of data training to use. Also, this research is used to see the performance of the Support Vector Machine algorithm with Word2Vec in detecting hoax news
Analisis Sentimen E-Wallet Menggunakan Support Vector Machine Berbasis Particle Swarm Optimization Vamilina, Vina; Novita, Rice
Building of Informatics, Technology and Science (BITS) Vol 5 No 1 (2023): June 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i1.3526

Abstract

E-Wallet applications in Indonesia have started to be in demand since the Covid-19 pandemic. The object being analyzed is an e-wallet application that is widely used in Indonesia and can be downloaded on the Google Playstore. The applications analyzed are Dana, Ovo, PayPal Link Aja and Doku. The advantages of these five applications are that Dana is user friendly or easy to use, while using Ovo is superior in terms of benefits, and Doku is superior in terms of security, Link Aja tends to be perceived by consumers in a neutral condition between security and user convenience because it is an e-wallet. It is still considered new in Indonesia, and PayPal has become a successful online payment system in C2C field. The focus of this research is to compare the comments of the users of the five applications. The method used in this study is the Support Vector Machine (SVM) algorithm. To produce high accuracy it is optimized using the Particle Swarm Optimization (PSO) algorithm. This was taken based on previous studies which stated that SVM-PSO has the highest percentage of accuracy compared to other algorithms. The data used is a thousand (1000) per application. So, the total amount of data is five thousand (5000) data. The results of the research show that the Ovo e-wallet is superior because it has the most positive comments, namely 579 and 421 negative comments, while the lowest position is occupied by Link Aja which only has 579 positive comments and 421 negatuve comments. In the process of sentiment analysis, the accuracy percentage of the SVM-PSO algorithm was also obtained, which was 91.10% in the Link Aja application. This means that SVM-PSO is very suitable to be combined to get the highest accuracy
Klasifikasi Sentimen Masyarakat di Twitter terhadap Ganjar Pranowo dengan Metode Naïve Bayes Classifier Ritonga, Sinta Wahyuni; ., Yusra; Fikry, Muhammad; Cynthia, Eka Pandu
Building of Informatics, Technology and Science (BITS) Vol 5 No 1 (2023): June 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i1.3535

Abstract

Indonesia is a country with a Democratic political system. The public is given freedom of speech, collaboration and public criticism. In the modern era, the use of social media is growing rapidly at the community level. One of the social media trends in Indonesia is Twitter which is used to convey aspirations to the government and as a means to convey daily activities, opinions, culture and get the latest information or news from Indonesia and abroad. Public opinion taken from Twitter can be positive, negative and neutral. The number of tweets on Twitter one of the trend topics in Indonesia is Ganjar Pranowo, can be used as a source of data in the assessment of sentiment classification which is processed to produce accuracy values. This study aims to classify public opinion on social media Twitter about Ganjar Pranowo using Naïve Bayes Classifier method. In the classification processing using a dataset of 4000 tweet data with two labeling classes, positive and negative to determine the efficiency of NBC performance combined with TF-IDF weighting, feature selection using supervised learning approach techniques. The results of the test on the classification of public sentiment research on Twitter about Ganjar Pranowo using NBC method using 10% of the test data from the dataset used to produce an accuracy value of 83.0%.
Komparasi Algoritma Neural Network dan K-Nearest Neighbor Dalam Mendeteksi Malware Android Ramadhan, Andi; Lindawati, Lindawati; Rose, Martinus Mujur
Building of Informatics, Technology and Science (BITS) Vol 5 No 1 (2023): June 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i1.3538

Abstract

The report from the State Cyber and Cryptography Agency (BSSN) recorded approximately 100 million cases of cyber attacks in Indonesia until April 2022, with ransomware and malware being the most commonly detected types of attacks. In this context, the increasingly sophisticated and hard-to-detect Android malware poses a serious threat, especially with successful penetrations into the Google Play Store. Therefore, early detection of Android malware is crucial. This research aims to compare the performance of two machine learning algorithms, Neural Network and K-Nearest Neighbors (KNN), in detecting malware on the Android platform. The dataset has been processed and divided into training and testing data. Both algorithms are trained using the training data, and their results are validated and evaluated. The research findings show that Neural Network achieves the best performance with an accuracy of 97%, precision of 97%, recall of 97%, and F1-score of 97%. Meanwhile, KNN performs slightly lower with an accuracy of 95%, precision of 96%, recall of 95%, and F1-score of 95%. In conclusion, Neural Network outperforms KNN in detecting Android malware based on accuracy and classification consistency. Further research suggestions involve the use of other algorithms, broader and more representative datasets, as well as the addition of features and parameter optimization. This research contributes to the development of accurate and effective solutions for detecting and identifying potentially harmful Android applications
Analisis Sentimen Masyarakat Terhadap Penghapusan Honorer Berdasarkan Opini Dari Twitter Menggunakan Naïve Bayes Classifier Andriyani, Dwi Ratna; Afdal, M; Monalisa, Siti
Building of Informatics, Technology and Science (BITS) Vol 5 No 1 (2023): June 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i1.3541

Abstract

The removal of honorees is currently a hot topic throughout Indonesia. Sharing how honorary personnel do so that the honorary removal policy is not implemented. Most honorary personnel have served for several years, but the government has issued a circular on the abolition of honorees. Various pros and cons of society regarding the abolition of honorees, such as honorary workers can lose their jobs, not get income, and unemployment is increasing. The purpose of the study is that the government can provide strategies that must be carried out in the event of the removal of honorees, such as appointing all honorees to become Civil Servants or Government Employees with Work Agreements. So the removal of the honoree became one of the trending topics on Twitter social media in 2022. From the results of the analysis conducted, public opinion that uses Twitter is very influential for honorary workers by grouping opinions into three categories, namely positive opinions, neutral opinions, and negative opinions. So the study with text mining used the Naïve Bayes Classifier algorithm with data from Twitter tweets from January 2022 to December 2022 with 2,705 data. The results of this study obtained accuracy with 10 K-fold Cross Validation on K-10, which was 73.01%. And it was found that sentiment polarity against the removal of honorees on positive class sentiment by 10% against agreeing to remove honorees with 285 data tweets, neutral class sentiment by 67% against agreeing and disagreeing with the removal of honorees with 1,801 data tweets, and negative class sentiment by 23% against disagreeing with the removal of honorees with 619 data tweets
Penerapan Deep Learning Menggunakan Gated Recurrent Unit Untuk Memprediksi Harga Minyak Mentah Dunia Saputra, Nugroho Wahyu; Insani, Fitri; Agustian, Surya; Sanjaya, Suwanto
Building of Informatics, Technology and Science (BITS) Vol 5 No 1 (2023): June 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i1.3552

Abstract

Crude oil is a much-needed energy for the whole world. Each country is inseparable from the use of crude oil for use in various sectors, such as transportation, so that the price of world crude oil is the most important variable for the world. Fluctuations in oil prices will cause various problems, such as inflation, changes in market prices, and others. Therefore, the prediction of world crude oil prices is very important as a consideration for decision making. This study implements deep learning using the Gated Recurrent unit model. The data used is the price of Brent crude oil with a total of 5834 data, starting from January 4, 2000 to December 19, 2022. The parameters used are the number of GRU units, batch size, and lookback. The best model produced in this study is the GRU model with hyperparameters consisting of 30 lookbacks, 50 GRU units, and 256 batch sizes with the lowest MAPE value among the other models, which is 2.25%. The MAPE value states that predictions using the GRU model are said to be very good at predicting world crude oil prices
Penerapan Gamma Correction Dalam Peningkatan Pendeteksian Objek Malam Pada Algoritma YOLOv5 Fransisca, Viviana; Santoso, Handri
Building of Informatics, Technology and Science (BITS) Vol 5 No 1 (2023): June 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i1.3553

Abstract

YOLOv5 (You Only Look Once) is a popular object detection method used in the field of computer vision. YOLOv5 is often used to detect objects in images and videos in real-time with high speed and accuracy. This method is easy to use because it is open-source, so it can be directly used to create a model that fits the object you want to detect. YOLOv5 can easily recognize objects detected during the day, but this method has difficulties when it is made to detect objects at night. With the improvisation of the YOLOv5 method which can accurately detect objects at night, other researchers who wish to conduct research related to object detection at night can use the exact technique to produce more accurate object detection. This study uses the Gamma Correction method by adding a Gamma of 2 so that the trained image dataset becomes bright and YOLOv5 can recognize objects at night more easily. As a result, an improvised technique using Gamma Correction can make YOLOv5 recognize objects and make detections at night more accurately, where the average accuracy obtained before improvisation is 0.846, while after improvisation the results obtained are 0.918. From these average results, it can be stated that the gamma correction method can improve the accuracy results in object detection on YOLOv5
Sistem Pendukung Keputusan Pemilihan Sales Supervisor Menerapkan Metode EDAS berdasarkan Pembobotan ROC Purnama, Iwan; Zulkifli, Zulkifli; Nasution, Muhammad Bobbi Kurniawan; Karim, Abdul; Trianovie, Sri
Building of Informatics, Technology and Science (BITS) Vol 5 No 1 (2023): June 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i1.3558

Abstract

Sales is a job that aims to sell a product in the form of goods, services and others and provide the best service to consumers or buyers. Sales will work optimally if managed properly. The person who works to manage sales work is a sales supervisor. Sales Supervisor is someone who is responsible for managing the work procedures of each sales person under his control. A supervisor is required to be able to control every task implementation of a salesperson. If the company hires someone who is not qualified to be a sales supervisor, it will cause losses. So to determine the sales supervisor, a system is needed that will help select good and quality sales supervisor candidates according to the criteria set by the company. The right system to assist companies in making elections is SPK. Decision support system (DSS) is a system that is deliberately created to assist certain parties in making decisions with quality and objective results. SPK requires a method. In this study the method used is the EDAS method. The EDAS method has a function, namely to produce a ranking value by implementing mathematical formulations correctly according to the rules. The mathematical formulation is systematically arranged by experts and produces a ranking value which will eventually be assembled into an accurate decision. From the results of this study, a value of 0.5348 was obtained by Mandala as an alternative to B7, which is the best sales supervisor candidate
Analisis Perbandingan Sistem Pakar dalam Mendiagnosa Penyakit Limfoma Hodgkin Menggunakan Algoritma Teorema Bayes dan Certainty Factor Mahendra, Muklis; Pane, Rahmadhani; Rohani, Rohani
Building of Informatics, Technology and Science (BITS) Vol 5 No 1 (2023): June 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i1.3560

Abstract

Disease is a major challenge in the medical world. Accurate and timely diagnosis is a crucial key in disease management, including in cases of cancer. One type of cancer that affects the lymphatic system in the body is Hodgkin's lymphoma, which is also considered a rare disease. Typically, this disease occurs in adolescents and adults. Hodgkin's lymphoma requires serious treatment, although there are also cases of successful recovery. The importance of accurate and timely diagnosis in diagnosing Hodgkin's lymphoma is a critical factor in planning effective treatment and providing a favorable prognosis for patients. This study aims to perform a comparative evaluation of the Bayesian Theorem and Certainty Factor methods in diagnosing Hodgkin's lymphoma by comparing both methods. Diagnosing this disease is challenging for an expert due to the similarity of symptoms with other lymphoma diseases, which adds complexity. Therefore, this research provides an alternative to facilitate diagnosis by utilizing a system that can determine the level of certainty of a disease based on available data, including symptoms, expert values, and user values. After conducting research by comparing the two algorithms, Bayesian Theorem and Certainty Factor, various processing stages were implemented according to the established algorithm. The Bayesian Theorem algorithm yielded a result of 77.7%, while the Certainty Factor algorithm produced a higher value of 94.1%. The comparison between the Bayesian Theorem and Certainty Factor methods shows that the Certainty Factor method is more accurate in diagnosing Hodgkin's lymphoma and can be used in further research
Pemodelan Prediksi Harga Ethereum (Atribut: Open, High dan Low) dengan Algoritma Extreme Learning Machine Kasliono, Kasliono; Candraningrum, Niken; Sari, Kartika
Building of Informatics, Technology and Science (BITS) Vol 5 No 1 (2023): June 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i1.3567

Abstract

The price of cryptocurrencies such as Ethereum often experiences high fluctuations and is difficult to predict. This study aims to predict Ethereum prices using the Extreme Learning Machine (ELM) algorithm which is a fast and efficient machine learning method. Ethereum price data is collected from CoinMarketCap by scraping the data using CoinmarketCap Scraper from the cryptocmd library using Python. An ELM model is built by changing the number of hidden nodes to determine the optimal prediction model of Ethereum prices based on the smallest average MAPE. Model performance was evaluated using the mean absolute percentage error (MAPE) on the test data set. The results show that the ELM model built can predict Ethereum prices with an accuracy of 96.96%. The MAPE obtained is 3.035334%, with 9 hidden nodes in the ELM network architecture model that was built. This shows that the model can explain about 96.96% of the variation in Ethereum price data. Therefore, the ELM model can be used as an aid in making investment decisions

Page 39 of 89 | Total Record : 889

 37   38   39   40   41 

Filter by Year

2019 2025


Reset
Filter By Issues
All Issue Vol 7 No 3 (2025): December 2025 Vol 7 No 2 (2025): September 2025 Vol 7 No 1 (2025): June (2025) Vol 6 No 4 (2025): March 2025 Vol 6 No 3 (2024): December 2024 Vol 6 No 2 (2024): September 2024 Vol 6 No 1 (2024): June 2024 Vol 5 No 4 (2024): March 2024 Vol 5 No 3 (2023): December 2023 Vol 5 No 2 (2023): September 2023 Vol 5 No 1 (2023): June 2023 Vol 4 No 4 (2023): March 2023 Vol 4 No 3 (2022): December 2022 Vol 4 No 2 (2022): September 2022 Vol 4 No 1 (2022): June 2022 Vol 3 No 4 (2022): March 2022 Vol 3 No 3 (2021): December 2021 Vol 3 No 2 (2021): September 2021 Vol 3 No 1 (2021): June 2021 Vol 2 No 2 (2020): December 2020 Vol 2 No 1 (2020): June 2020 Vol 1 No 2 (2019): December 2019 Vol 1 No 1 (2019): June 2019 Vol 1 No 1 (2019): Edisi Juni More Issue