Article Per Year (5 Year)
p-Index From 2021 - 2026
2.024
P-Index
This Author published in this journals
All Journal Tech-E Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) ComTech: Computer, Mathematics and Engineering Applications bit-Tech eCo-Buss Algor NEAR: Jurnal Pengabdian kepada Masyarakat
Yusuf Kurnia
Universitas Buddhi Dharma
Humanities Chemistry Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Engineering Environmental Science Health Professions Languange, Linguistic, Communication & Media Library & Information Science Mathematics Nursing Public Health Social Sciences Transportation Other

Published : 19 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 19 Documents
Search

 1   2 
Alleged Bad Credit at Saving Cooperatives Borrow Flamboyant Assistance PPSW Jakarta With Comparasion the Algorithms Naive Bayes and C4.5 Renaldi Renaldi; Yusuf Kurnia
bit-Tech Vol. 2 No. 3 (2020): Pandemik ICT
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v2i3.163

Abstract

Data mining is often used in the financial sector, one of which is cooperatives. According to Law No. 25 of 1992, what is meant by cooperatives are business entities whose members are individual or cooperative legal entities based on activities based on the principles of cooperatives as well as as a people's economic movement based on the principle of kinship. One of the things that needs to be considered is the provision of credit or borrowing in the Flamboyan cooperative, which in this study there are many bad crediting occurrences that occur in the Flamboyan cooperative. By using a lot of data mining techniques, data can be utilized optimally. From the above problems, it can be overcome by utilizing data mining techniques, namely Predicting Bad Credit at the Flamboyant Savings and Loan Cooperative Fostered by PPSW Jakarta Using Comparative Algorithms Naive Bayes and C4.5. The algorithm used in the system is the best result of the Naive Bayes and C4.5 comparison based on data from the Flamboyan cooperative. The results obtained from the comparative data processing between the Naïve Bayes algorithm and the C4.5 using a dataset of 2282 transaction data obtained the results of the accuracy of the Naïve Bayes algorithm of 69.19% and the C4.5 algorithm of 71.87%, based on the accuracy results state that the C4 algorithm .5 is superior to the Naïve Bayes algorithm. Then the results from the C4.5 decision tree are translated into the bad credit prediction system in the Flamboyan cooperative.
Designing Website-Based E-Learning Application on SMP Kusuma Bangsa Using Framework Codeigniter Cris Sunray; Yusuf Kurnia
bit-Tech Vol. 3 No. 1 (2020): Distance Learning
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v3i1.186

Abstract

The Covid-19 pandemic currently occurring around the world, including Indonesia has had an impact and changes in various areas of daily life. Especially, in the field of education which during the Covid-19 pandemic must make efforts to adapt. Minimizing direct interactions is an important first step to avoiding the spread of covid-19. This is also applied to teaching and learning activities between teachers and students therefore teaching and learning activities are carried out online. Without any doubt, this change creates problems and difficulties in the delivery of material, interactions between teachers and students, etc. However, SMP Kusuma Bangsa is a private school that still implements face-to-face learning system. To solve this problem, the author propose making an online learning system. In order to achieve this, the author intend to create an e-learning application. This e-learning application is based on website created using the Codeigniter framework. To find out the application requirements desired by the user, the author make user needs which will be used as a form of analysis in making e-learning application. After getting the results of user needs, the author complete the e-learning application with 3 user models, admin, teacher, and students, each of them has their own function. Likert scale is used to measure the level of user satisfaction of the e-learning application. Based on the results of the calculation, it can be seen that users as respondents who strongly agree with the statement that the e-learning application are in the good category, it shows the acquisition of 84.1%. Therefore, the e-learning application has helped minimize direct interaction, the application operates well, and the presence of an online exam feature, a conference system using the zoom application, etc make teaching and learning activities at SMP Kusuma Bangsa easier
Android-Based Musical Instrument Recognition Application For Vocational High School Level Yusuf Kurnia; Toga Parlindungan Silaen
bit-Tech Vol. 4 No. 2 (2021): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v4i2.288

Abstract

With the old way of learning and methods, Vocational High School students will be bored, especially in the field of Arts and Culture, which on average are considered difficult and not liked by most students. Therefore, it is necessary to make other learning media based on Android so that learning becomes more interesting and enjoyable. In addition, with this learning media, it is hoped that it can help children's creativity and thinking power, because it is equipped with several important components that can hone children's imaginative power such as pictures, videos in the material provided. Therefore, the authors design and create an application about interactive learning media that includes these components. This application will be aimed at the Vocational High School level with the title "Android-Based Musical Instrument Recognition Application for Vocational High School Level". Therefore, research was conducted at the Vocational High School level. Users want attractive images of each musical instrument such as guitar, bass, drums, keyboard, have video links, there are questions in the application, a menu in the form of icons, and attractive colors. After designing, manufacturing, and testing this application, several conclusions can be drawn. First, with this application, Vocational High School students can easily learn musical instruments in different ways. In addition, with this learning method, students become enthusiastic and learning becomes fun in studying cultural arts lessons in the field of musical instruments, especially musical instrument techniques and chords of musical instruments. Second, this application is able to hone the cognitive abilities of students because in this application there are practice questions, the questions are integrated with the material provided, so that students can easily practice their abilities through the practice questions available in this application. Third, and lastly, according to the author, this application is lacking in terms of animation in the application that was made late. Hopefully this application can be a learning material for students who want to take a Thesis with a title related to learning musical instruments. The author really expects criticism and suggestions because this design system still has many shortcomings
Smart Home Prototype with HC–05 Bluetooth and RFID Modules, Based on Microcontroller Indah Fenriana; Dicky Surya Dwi Putra; Bagus Dermawan; Yusuf Kurnia
bit-Tech Vol. 5 No. 2 (2022): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v5i2.564

Abstract

How is the performance of the Arduino Uno in processing smart home creation, as well as the implementation of the results of its classification into Android. This design uses various sensors, RFID for smart door locks and Bluetooth HC-05 for lights and fans. The benefit of making this prototype is to make it easier to turn on the lights and fans so you don't have to bother looking for light sockets or fans. Smart door lock using RFID is a technology used to identify opening doors. This design uses the Arduino Uno R3 device. This device can be remote with Android. The android application uses the MIT App Inventor software. This smart home design can make it easier for users to carry out activities at home where previously they could turn on and off the lights and fans in the living room, still manually by pressing the socket, now they can turn it on with a smart phone connected to the Bluetooth module via an application. Utilize Google's help on Android smartphones to control lights and fans using voice commands. In addition, the author also designed a smart door lock using RFID and matrix keypad, which previously opened and closed the door with a key, now only by attaching an RFID card or pressing a pin to open the door.
Enhancing Consumer-to-Consumer (C2C) E-Commerce through Blockchain: A Model-Driven Approach Aditiya Hermawan; Oscar Hasan Putra; Junaedi Junaedi; Yusuf Kurnia; Riki Riki
ComTech: Computer, Mathematics and Engineering Applications Vol. 15 No. 1 (2024): ComTech
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/comtech.v15i1.10638

Abstract

The rapid progress of Information and Communication Technology (ICT), especially the Internet, has changed lifestyles in profound ways, including sharing ideas, virtual interactions, digital entertainment, and online transactions. It has resulted in businesses globally turning to electronic commerce (e-commerce) to market products. E-commerce has revolutionized operations with features such as centralized storage and detailed product information in the marketing process. However, the inefficiency and lack of transparency in these centralized systems lead to high costs and limited user control, posing a significant challenge. Challenges include commission fees from E-Commerce providers, which hinder business growth. The research aimed to propose a more efficient and transparent model for Consumer-to-Consumer (C2C) e-commerce using blockchain technology. The C2C model enhanced user transactions and minimized third-party dependence, but centralization increased costs and limited seller access. Thus, a decentralized blockchain approach was proposed for greater transparency in e-commerce. The research innovatively applied blockchain to C2C e-commerce, enhancing market efficiency and transparency. The research method applied was a combination of Strengths, Weaknesses, Opportunities, and Threats (SWOT) analysis and practical application. The result shows that the approach succeeds in reducing high costs, transparency of data storage, and dependence on third parties. Blockchain reduces third-party involvement and promotes a fairer business environment because it uses a tamper-proof database for transparency, security, and efficiency in the ever-growing e-commerce ecosystem. Blockchain ensures automated transactions, real-time data tracking, and data security.
Perbandingan Naïve Bayes dan CNN yang Dioptimasi PSO pada Identifikasi Berita Hoax Politik Indonesia Yusuf Kurnia; Ellysha Dwiyanthi Kusuma; Lianny Wydiastuty Kusuma; Suwitno; Welman Apridius
bit-Tech Vol. 6 No. 3 (2024): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v6i3.1225

Abstract

Berita palsu dalam politik menjadi ancaman serius terhadap stabilitas demokrasi dan kepercayaan publik terhadap informasi. Fenomena ini tidak hanya meresahkan, tetapi juga memiliki dampak yang dapat mengganggu proses demokrasi serta kepercayaan masyarakat terhadap media dan pemerintah. Penelitian ini bertujuan untuk menyelidiki dan membandingkan kinerja dua algoritma yang berbeda, yaitu Naïve Bayes (NB) dan Convolutional Neural Network (CNN), yang telah dioptimalkan menggunakan Particle Swarm Optimization (PSO), dalam mendeteksi berita palsu di ranah politik Indonesia. Untuk mencapai tujuan ini, penelitian menggunakan dataset berita politik yang telah melalui proses text preprocessing, termasuk pembersihan data dan normalisasi teks. Hasil penelitian menunjukkan bahwa model Naïve Bayes secara konsisten mampu mengungguli kinerja CNN, baik dengan atau tanpa penerapan PSO. Akurasi model Naïve Bayes mencapai 90.71%, sementara CNN mencapai 80.86% tanpa PSO, 79.68% dengan PSO, dan Naïve Bayes dengan PSO mencapai 90.25%. Temuan ini menegaskan bahwa pendekatan menggunakan algoritma Naïve Bayes memiliki potensi lebih besar dalam mengidentifikasi berita palsu dalam konteks politik Indonesia. Kontribusi signifikan dari penelitian ini terletak pada pemahaman yang lebih mendalam mengenai metode deteksi berita palsu, serta memberikan wawasan yang penting bagi pengembangan strategi yang efektif dalam menanggulangi permasalahan berita palsu di era digital. Oleh karena itu, diharapkan bahwa penelitian ini akan memberikan nilai tambah dalam upaya mempertahankan keaslian informasi politik dan meningkatkan kualitas demokrasi di Indonesia.
Pengaruh Penggunaan Chatbot dan Asisten Virtual terhadap Peningkatkan Kepuasan Pelanggan serta Dampaknya terhadap Pengambilan Keputusan Pembelian Agus Soetiyono; Yusuf Kurnia; Rudy Kurnia
eCo-Buss Vol. 6 No. 3 (2024): eCo-Buss
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/eb.v6i3.1169

Abstract

Tujuan dari penelitian ini adalah untuk menguji pengaruh penggunaan Chatbot dan Virtual Asisten dalam manajemen pelanggan terhadap Kepuasan Pelanggan dan Keputusan Pembelian. Metode penelitian yang digunakan melibatkan pengumpulan data dari 200 responden, termasuk pelanggan dan pengelola bisnis, melalui kuesioner. Model struktural yang digunakan dalam penelitian ini adalah Partial Least Square (PLS), yang kemudian digunakan untuk mengetahui hubungan dengan menguji hubungan variabel yang digunakan dalam penelitian ini. Hasil penelitian menunjukkan bahwa penggunaan Chatbot dan Virtual Asisten secara signifikan berdampak pada Kepuasan Pelanggan dan Keputusan Pembelian. Implikasi penting dari penelitian ini adalah bahwa perusahaan dapat memanfaatkan teknologi Chatbot dan Virtual Asisten sebagai alat efektif untuk meningkatkan tingkat kepuasan pelanggan dan memengaruhi perilaku pembelian konsumen. Dengan memahami peran penting teknologi ini dalam manajemen pelanggan, perusahaan dapat mengembangkan strategi pemasaran yang lebih canggih dan pengelolaan pelanggan yang lebih adaptif untuk mendukung pertumbuhan bisnis jangka panjang yang berkelanjutan. Perlu juga dicatat bahwa penelitian ini menyoroti pentingnya adaptasi perusahaan terhadap inovasi teknologi untuk menjaga keunggulan kompetitif dalam era digital yang terus berkembang. Dengan demikian, penelitian ini memberikan kontribusi penting dalam memahami peran dan dampak teknologi terkini dalam konteks manajemen pelanggan dan pengambilan keputusan pembelian.
Peningkatan Kreativitas Digital melalui Pelatihan Pembuatan Poster dengan Menggunakan Canva pada SMK Penerus Bangsa Yusuf Kurnia; Rusman Efendi Sihombing; Wiyono Wiyono; Amesanggeng Pataropura
NEAR: Jurnal Pengabdian kepada Masyarakat Vol. 4 No. 2 (2025): NEAR
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/nr.v4i2.2234

Abstract

Pelatihan pembuatan poster digital menggunakan aplikasi Canva di SMK Penerus Bangsa bertujuan untuk meningkatkan keterampilan desain grafis siswa, khususnya dalam pembuatan poster yang efektif dan komunikatif. Seiring dengan pesatnya perkembangan teknologi digital, keterampilan desain grafis menjadi sangat penting, baik untuk mendukung kebutuhan akademik maupun sebagai persiapan untuk dunia kerja di industri kreatif. Pelatihan ini mengadopsi pendekatan berbasis praktik, di mana siswa belajar langsung menggunakan Canva untuk membuat poster dengan berbagai tema. Metode yang digunakan mencakup teori desain grafis dasar serta praktik langsung yang memungkinkan siswa untuk memahami dan menerapkan prinsip-prinsip desain seperti keseimbangan visual, tipografi, dan pemilihan warna. Hasil pelatihan menunjukkan peningkatan signifikan dalam keterampilan siswa, terutama dalam hal pemahaman desain grafis, rasa percaya diri, dan kemampuan menggunakan aplikasi Canva. Sebagian besar siswa melaporkan bahwa mereka merasa lebih siap untuk mengaplikasikan keterampilan ini dalam dunia kerja atau membuka peluang usaha kreatif. Pelatihan ini juga memberikan nilai tambah bagi siswa dalam mengembangkan kreativitas dan keterampilan desain visual yang relevan dengan kebutuhan pasar yang semakin bergantung pada komunikasi digital
Impact of Dataset Background on Deep Learning-Based Waste Classification Nazzua Azzahra; Aditiya Hermawan; Junaedi; Yusuf Kurnia; Edy
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 3 (2026): Juni 2026 (in progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i3.6965

Abstract

Accurate waste classification plays a vital role in supporting effective waste management and promoting environmental sustainability, especially amid the continuing increase in global waste generation. This study investigates how the presence and removal of image backgrounds influence the performance of deep learning models in automated waste classification. Two Convolutional Neural Network architectures, namely MobileNetV2 and DenseNet169, were evaluated using a dataset comprising 5,054 images across six waste categories: cardboard, glass, metal, paper, plastic, and trash. Each architecture was trained and tested on two dataset variants: original images with backgrounds and images with the backgrounds removed. Model performance was assessed using accuracy, precision, recall, F1-score, and ROC AUC. The results indicate that DenseNet169 consistently outperformed MobileNetV2 across all evaluation metrics. The highest accuracy, reaching 88.33%, was achieved by DenseNet169 when trained on images retaining their original backgrounds. This suggests that background information may provide meaningful contextual features that enhance classification performance. Conversely, removing backgrounds can limit the visual information available to the model and potentially reduce predictive effectiveness. These findings emphasize the importance of carefully considering background characteristics during dataset preparation and model training. Moreover, the study demonstrates that selecting an appropriate model architecture in relation to dataset properties is essential for optimizing classification outcomes. Overall, this research offers practical insights for improving dataset design and model selection in future automated waste classification systems, while contributing to the advancement of scalable and intelligent deep learning-based waste management solutions.
Co-Authors Aditiya Hermawan Agus Soetiyono Amesanggeng Pataropura Andrew Ryan Yosafat Bagus Dermawan Chrisantus Robert William Resi Cris Sunray Darwin Tantowi Dera Susilawati Desiyanna Lasut Dicky Surya Dwi Putra Edy Ellysha Dwiyanthi Kusuma Geraldi Aditya Hartana Wijaya Indah Fenriana Jeksen Li Sie Jerico Lois Junaedi Kuera Kusuma Lianny Wydiastuty Kusuma Nazzua Azzahra Oscar Hasan Putra Raditya Rimbawan Oprasto Refin . Renaldi - Renaldi Renaldi Riki Riki RIKI RIKI, RIKI Rudy Kurnia Rusman Efendi Sihombing Sandi Kristianto Suwitno Toga Parlindungan Silaen Welman Apridius Wiyono Wiyono