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
+6285261776876
Journal Mail Official
bit.journals@gmail.com
Editorial Address
Jalan sisingamangaraja No 338, Simpang Limun, Medan, Sumatera Utara, Indonesia
Location
Kota medan,
Sumatera utara
INDONESIA
Bulletin of Information Technology (BIT)
Published by Forum Kerjasama Pendidikan TInggi
ISSN : -     EISSN : 27220524     DOI : 10.47065/bit.v2i3.106
Core Subject : Science,
Computer Science & IT
Jurnal Bulletin of Information Technology (BIT) memuat tentang artikel hasil penelitian dan kajian konseptual bidang teknik informatika, ilmu komputer dan sistem informasi. Topik utama yang diterbitkan mencakup:berisi kajian ilmiah informatika tentang : Sistem Pendukung Keputusan Sistem Pakar Sistem Informasi, Kriptografi Pemodelan dan Simulasi Jaringan Komputer Komputasi Pengolahan Citra Dan lain-lain (topik lainnya yang berhubungan dengan teknologi informasi)
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 317 Documents
 28   29   30   31   32 
Klasifikasi Kematangan Buah Pinang (Areca catechu L.) Menggunakan Hybrid Deep Feature Fusion dan XGBoost Anggi; Nelly Khairani Daulay; Ahmad Sobri
Bulletin of Information Technology (BIT) Vol 7 No 2 (2026)
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bit.v7i2.2864

Abstract

Areca nut (Areca catechu L.) maturity is one of the factors affecting harvest quality. Visual maturity identification still has limitations because it can be influenced by observer subjectivity and environmental conditions. This study aims to classify areca nut maturity levels using a Hybrid Deep Feature Fusion approach by combining ResNet50 and EfficientNetB0 as feature extractors with XGBoost as the classification algorithm. The dataset used in this study was a primary dataset consisting of 1,200 areca nut images categorized into three maturity classes: unripe, semi-ripe, and ripe. The research stages included image preprocessing, feature extraction using CNN models, feature combination through feature concatenation, classification using XGBoost, and performance evaluation using accuracy, precision, recall, F1-score, confusion matrix, and 5-Fold Cross Validation. The experimental results showed that ResNet50 + XGBoost and Hybrid Deep Feature Fusion + XGBoost achieved accuracy, precision, recall, and F1-score values of 100%, while EfficientNetB0 + XGBoost achieved an accuracy of 99.16%. These results indicate that CNN-based features are able to represent the visual characteristics of areca nut images in the dataset used. The Hybrid Deep Feature Fusion approach provides an analysis of feature combination from two different CNN architectures, although increasing the feature dimensions does not always improve evaluation performance when a single feature extractor is already capable of representing dataset characteristics effectively. Future research can be conducted by increasing dataset variations to evaluate the generalization capability of the method under more diverse environmental conditions.
Perbandingan SVM dan IndoBERT untuk Analisis Sentimen Layanan Akademik Mahasiswa Muhammad Ibnu Sa'ad; Lailil Muflikhah; Fitra Abdurrachman Bachtiar
Bulletin of Information Technology (BIT) Vol 7 No 2 (2026)
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bit.v7i2.2913

Abstract

Digital transformation in higher education has generated an increasing volume of textual data, including student comments, academic service evaluations, and feedback on academic information systems. These data contain valuable information for supporting decision-making; however, their unstructured and contextual nature makes manual analysis inefficient. This study aims to compare the performance of a TF-IDF-based Support Vector Machine (SVM) model and a Transformer-based IndoBERT model for sentiment analysis of academic services from student feedback. The dataset consists of 1,700 text entries, combining template-based synthetic data and real-world data collected from social media, which were classified into positive, negative, and neutral sentiment categories. The research process involved exploratory data analysis, text preprocessing, feature extraction, model development, and evaluation using accuracy, precision, recall, and F1-score metrics. The experimental results showed that both models achieved very high performance on the dataset, with an accuracy of 100% on the test set. These findings indicate that both traditional machine learning and Transformer-based approaches are capable of identifying sentiment patterns within the dataset. Nevertheless, the results should be interpreted cautiously, as the relatively homogeneous nature of the dataset and the inclusion of synthetic data may affect the models’ generalizability. The main contribution of this study lies in the comparative evaluation of SVM and IndoBERT within the context of higher education academic services, as well as the development of a sentiment analysis framework that can support data-driven service quality monitoring. Future studies should employ larger, more diverse datasets derived entirely from real-world sources to further validate the findings.
Implementasi Metode SAW Dan MAUT Dalam Sistem Pendukung Keputusan Menentukan Verietas Nanas Terbaik Rahmad Aditiya; Angga Putra Juledi; Kusmanto; Andi Ernawari; Muhammad Bobbi Kurniawan Nasution
Bulletin of Information Technology (BIT) Vol 7 No 2 (2026)
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bit.v7i2.2993

Abstract

This research aims to assist farmers and agribusiness practitioners in determining the best pineapple variety in a more objective and systematic manner. Ultimately, this will positively impact the productivity and quality of pineapple yields, providing greater economic benefits to farmers and agribusiness practitioners. To address this issue, a Decision Support System (DSS) was employed using the SAW and MAUT methods. The SAW method is a simple and easily implemented MCDM method. It works by assigning weights to each criterion and then calculating the total score for each alternative based on these weights. On the other hand, the MAUT method is a more comprehensive approach to multi-criteria decision-making. This method is based on utility theory, which considers the decision-maker's preferences regarding various attributes or criteria. By using the SAW and MAUT methods, we can determine the best pineapple variety selection based on the available data. From the previously collected data, this study uses 5 criteria: Size (30%), Taste (25%), Skin Color (20%), Water Content (15%), and Texture (10%). The implementation of the SAW and MAUT methods revealed that the best pineapple variety is A5 (MD2) with a score of 0.9125 using the SAW method and a score of 2.2062 using the MAUT method. The last-ranked alternative, A10, shared the same ranking.
Analisis Certainty Factor Terhadap Anggaran Keuangan Daerah Dinas Ketahanan Pangan Pertanian dan Perikanan Berbasis Expert System Taslim Hadi Ariski; Ricky Ramadhan Harahap
Bulletin of Information Technology (BIT) Vol 4 No 2: Juni 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bit.v4i2.672

Abstract

Analysis of thel relgional financial budgelt at thel Meldan City agriculturel and fishelriels food selcurity selrvicel is quitel a difficult job and is carrield out relpelateldly elvelry yelar by financial managelmelnt to deltelrminel thel financial helalth condition of a selrviceld officel. Howelvelr, duel to thel limiteld knowleldgel of financial officelrs, this activity can only bel carrield out by celrtain peloplel who arel truly elxpelrts in that fielld. This application is delsigneld intelractivelly and elffelctivelly, whelrel this application can bel useld to calculatel financial pelrformancel at thel Meldan City agriculturel and fishelriels food selcurity selrvicel using thel celrtainty factor melthod according to thel ratio useld as thel basis for thel asselssmelnt. This application can only bel useld to calculatel thel valuel of thel celrtainty factor (celrtainty factor) and not to judgel thel pelrformancel of thel agelncy. This elxpelrt systelm is delsigneld so that financial elmployelels who do not know financial analysis can carry out financial analysis quickly elveln if thel quelstion elxpelrt is not prelselnt. Through elxpelrt knowleldgel that has beleln adopteld into thel systelm and thel infelrelncel elnginel, this systelm is capablel of making thel samel delcisions as thosel of elxpelrts. Thel relsults of this study will latelr bel ablel to obtain a financial systelm that has a valuel for elach stelp, thel CF celrtainty factor for thel MB valuel, and thel MD valuel has valuel for elach stelp 1 with a valuel of CF[h,el] = MB[h,el] -MD[h,el] = 0.92-0.6 =0.32, stelp 2 with valuel CF[h,el] = MB[h,el]-MD[h,el] = 0.97-0.37 =0.6, stelp 3 with valuel CF [h,el] = MB[h,el]-MD[h,el] = 0.92-0.52 =0.4, stelp 4 with valuel CF[h,el] = MB[h,el]-MD[h,el] = 0.94-0.44 =0.5, stelp 5 with a valuel of CF[h,el] = MB[h,el]-MD[h,el] = 0.92-0.54 =0.38 In addition, thel usel of thel celrtainty factor (CF) melthod makels it elasielr for uselrs to delfinel financial situation that is difficult to ascelrtain 100% truth.
Data Mining Menggunakan Algoritma Apriori Dalam Menentukan Tarif Pajak Penghasilan Di Oenity Hafiz Rodhiy; Zulham Sitorus
Bulletin of Information Technology (BIT) Vol 4 No 2: Juni 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bit.v4i2.673

Abstract

Thel Oelnity tax consulting officel is onel of thel companiels that havel a lot of data on goods, data-data, and transaction data elvelry day. In gelnelral, thel Oelnity tax consulting officel only usels this data for relporting purposels only. Tax transaction data collelcteld and storeld can providel uselful knowleldgel for company managelmelnt in carrying out elfforts rellateld to tax increlasels, for elxamplel in telrms of deltelrmining tax financel stratelgiels and supporting delcisions for thel company. Consumelrs who apply for thel procelss of deltelrmining incomel tax ratels usually havel relasons why thely choosel a tax data calculation systelm from a tax consultant rathelr than managing it thelmsellvels. Belcausel tax consultants can providel what thely want, such as convelnielncel, accuracy, speleld, and nelatnelss of incomel tax calculations. Many consumelrs complain about thel incomel tax ratel calculation systelm, whelrel thel layout, making it difficult for consumelrs to gelt thel final tax relsults thely neleld, will also spelnd quitel a long timel just to find thel total incomel tax ratel. Thel Apriori algorithm is onel of thel most frelquelntly useld typels of data analysis in thel world of data procelssing. This analysis procelss is to analyzel thel numbelr of businelssels and thel amount of consumelr incomel by finding associations beltweleln lists of taxels that must bel paid. Thel Apriori algorithm is useld to arrangel itelm layouts and group itelms. From thel relsults of systelm implelmelntation, it was concludeld that using thel Apriori Algorithm melthod can hellp thel procelss of finding incomel tax ratels for elach consumelr data.
Penerapan Algoritma K-Means Untuk Clustering Bakery Dan Cake Yang Laris Ahmad Fachriansyah; Efori Bu'ulolo
Bulletin of Information Technology (BIT) Vol 4 No 2: Juni 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bit.v4i2.675

Abstract

Bakery and Cake is a business engaged in the production of cakes, pastries and bread. Syahfira Bakery and Cake shop is a cake, sponge and bread shop which so far has not utilized data to determine store business strategy. The development of a business is based on good product sales marketing, this is inseparable from service between sellers and buyers as well as good relations between company owners and employees, this is the main key in a company. On this occasion the author will conduct research using the k-means algorithm for clustering bakeries and cakes which are in demand at CV. Syahfira Bakery and Cake by utilizing existing data that has been processed into excel data and cashier sales books. Based on the data previously obtained, there are six products that will be clustered on iteration or grouping calculations. With these data, the two best-selling products were obtained after calculating the application of the k-means algorithm, namely Cheese Wrap Bread and Chocolate Cheese Wrap Bread because they got a position in cluster 1
Sistem Jaringan Small Office Home Office (Soho) Menggunakan Mikrotik Ira Zulfa; Hendri Syahputra; M. Abdul Rahim; Fajrillah
Bulletin of Information Technology (BIT) Vol 4 No 2: Juni 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bit.v4i2.676

Abstract

A computer network system is defined as a collection of several independent computers connected to each other. This connection allows these computers to share information and programs with each other (Putuasduki, 2021). SOHO stands for Small Office, Home Office. SOHO is a hybrid apartment between residential and commercial space, where people can work and live in the same building. SOHO apartments are typically loft style, meaning they have high ceilings. High ceilings lend themselves well to building a mezzanine, an elevated area accessible by stairs that can be used as a bedroom or desk. (Armee et al., 2022). Mikrotik is a software-based operating system that turns a computer into a network router (Gamaliel and Arliyanto, 2022). This operating system is ideal for managing computer networks, such as building large or small computer network systems. (Putra et al., 2020). Gajah Putih University Faculty of Engineering always needs a very large network connection. In addition, many students use an internet connection. Difficulties in optimizing network use and equalizing bandwidth between students and faculties, internet network problems and difficulties in monitoring network users at the Gajah Putih Faculty of Engineering and students still asking for web searches off campus are the biggest problems. this lesson. For that we need a learning environment that can support the learning process in the field of computer networks. This study discusses learning media to build computer networks in small offices and home offices by using a proxy server, starting from the basic concept of computer networks so that the network can function properly. Network Development Life Cycle Model (NDLC). Flow Network Development Lifecycle Diagram Continuous process analysis is a step by step process that describes the journey of data or documents through ongoing processes in all research locations. The network topology that was operated at the Faculty of Engineering, University of Gajah Putih before using a proxy server is shown in Figure 2. Meanwhile, the network topology that was operated before using a proxy server in the laboratory of the Faculty of Engineering, University of Gajah Putih can be determined from the results of research and design of the home office network of the Faculty of Engineering, Gajah Putih University Using a proxy allows it to be concluded that with the help of the home office network of the Faculty of Technology, University of Gajah Putih using a proxy server technically students can easily access the internet for free and the signal in the university building can be easily closed. The security system used in this wireless network (base station) is implemented on the server. Therefore, if you want to use the Internet, the user must enter a username and password. This network uses a DHCP server so that the server distributes IP addresses as wide as possible resulting in long loading times when many users are active. Sharing Internet bandwidth with a proxy server enables efficient use of Internet bandwidth. By using a proxy server with Winbox, IT administrators can perform network configuration more easily.
Prediksi Ketebalan Powder Coating Menggunakan Algoritma SVM Dan Naïve Bayes Zaenur Rozikin; Ahmad Turmudi Zy; Antika Zahrotul Kamalia
Bulletin of Information Technology (BIT) Vol 4 No 2: Juni 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bit.v4i2.687

Abstract

Data Mining is a method that has been widely used to make scientific discoveries from a collection of datasets which so far have only been stored without further management. In the industrial world the use of data mining methods has helped with problems that are often found in the industrial field. Data mining helps in making predictions regarding thickness quality problems in a panel box product. Data mining is very useful for finding patterns in complex manufacturing data processing processes. Especially when we talk about consumers or service users of our product panels who want the panel to have good powder coating quality. This made the researchers conduct research to find the accuracy value which would later be used as a definite reference regarding the thickness of the powder coating. The results of this test the svm algorithm is better than naïve Bayes because the data in general can be categorized as a good result which has an accuracy of 97.60%, precision 99.56% and 96.03% recall. This res ult is an illustration for consumers to ensure that the panels to be purchased are of the best quality. By showing the data that has been processed, the consumer is sure that the purchase is really valid
Sistem Pendukung Keputusan Kelayakan Pemberian Kredit Nasabah Dengan Metode Electre Marlin Lasena; Sulistiawati Rahayu Ahmad
Bulletin of Information Technology (BIT) Vol 4 No 2: Juni 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bit.v4i2.690

Abstract

PT Hasjrat Abadi has collaborated with a financing institution to provide opportunities for vehicle ownership through credit facilities. The credit system offered by the financing institution can boost vehicle sales. However, before that, the lender must conduct a thorough consumer data analysis. This is crucial to ensure that potential customers can repay the approved vehicle loans, thereby avoiding the risk of loan defaults in the future. The process of consumer data analysis is time-consuming due to the abundance of documents involved. Additionally, field surveys are necessary to validate consumer data by applying the 5C Bank Principles (character, capital, capacity, collateral, and condition). Research Objective By implementing the Electre (Elimination and Choice Translation Reality) method in the decision support system, we can provide quick, accurate, and precise information to determine whether potential customers are eligible to purchase vehicles from PT Hasjrat Abadi through credit. This method utilizes the 5C Bank Principles (character, capital, capacity, collateral, and condition) to evaluate consumers. The method used is Research and Development (R&D), which aims to develop specific products and test their effectiveness. The research findings indicate that this system can enhance the services provided to customers at PT Hasjrat Abadi's branch in Gorontalo. Based on the data input by credit analysts, it was found that only 50 percent of the total potential customer data could be approved using the Electre method for credit applications. This facilitates faster, more accurate, and more reliable decision-making for customers.
Sistem Smart Door Lock Menggunakan Voice Recognition Berbasis Arduino Ray Fathur Rizky; Ahmad Turmudi Zy; Aswan S. Sunge
Bulletin of Information Technology (BIT) Vol 4 No 2: Juni 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bit.v4i2.696

Abstract

Penelitian ini mencakup implementasi algoritma HMM pada smart door lock dengan menggunakan pengenalan suara berbasis Arduino. Tujuan penelitian ini adalah untuk meningkatkan keamanan pintu agar terhindar dari upaya pembobolan dan kejahatan. Saat ini, penguncian pintu rumah masih dilakukan secara manual. Dalam penelitian ini, algoritma yang digunakan adalah Hidden Markov Model. Pembuatan alat ini dilakukan dengan menggunakan bahasa pemrograman C++. Hasil penelitian ini dapat diimplementasikan dalam bentuk alat/robotik, di mana sistem dapat membuka dan menutup pintu rumah sesuai dengan rancangan yang telah direncanakan, yaitu melalui perintah suara.

Page 30 of 32 | Total Record : 317

 28   29   30   31   32 

Filter by Year

2020 2026


Reset
Filter By Issues
All Issue Vol 7 No 2 (2026) Vol 7 No 1: Maret 2026 Vol 6 No 4 (2025): Desember 2025 Vol 6 No 3: September 2025 Vol 6 No 2: Juni 2025 Vol 6 No 1: Maret 2025 Vol 5 No 2 (2024): Juni 2024 Vol 5 No 4: Desember 2024 Vol 5 No 3: September 2024 Vol 5 No 1: Maret 2024 Vol 4 No 4: Desember 2023 Vol 4 No 3: September 2023 Vol 4 No 2: Juni 2023 Vol 4 No 1: Maret 2023 Vol 3 No 4: Desember 2022 Vol 3 No 3: September 2022 Vol 3 No 2: Juni 2022 Vol 3 No 1: Maret 2022 Vol 2 No 3: November 2021 Vol 2 No 2: Juli 2021 Vol 2 No 1: Maret 2021 Vol 1 No 3: November 2020 Vol 1 No 2: Juli 2020 Vol 1 No 1: Maret 2020 More Issue