Article Per Year (5 Year)
p-Index From 2021 - 2026
9.028
P-Index
This Author published in this journals
All Journal Jurnal Media Infotama Bulletin of Electrical Engineering and Informatics Jurnal Pseudocode Jurnal Informatika Upgris Sistemasi: Jurnal Sistem Informasi Journal of Economic, Bussines and Accounting (COSTING) INTECOMS: Journal of Information Technology and Computer Science JSAI (Journal Scientific and Applied Informatics) Journal of Technopreneurship and Information System (JTIS) Just TI (Jurnal Sains Terapan Teknologi Informasi) Jurnal Abdimas Serawai Jurnal Sistem Informasi Dan E-Bisnis Jurnal Ilmu Komputer Dan Informatika JPMTT (Jurnal Pengabdian Masyarakat Teknologi Terbarukan) JCOSIS (Journal Computer Science and Information Systems) Jurnal Komputer, Informasi dan Teknologi
Putra, Erwin Dwika
Program Studi Teknik Informatika, Fakultas Teknik, Universitas Muhammadiyah Bengkulu
Religion Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Nursing Public Health Social Sciences

Published : 71 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 71 Documents
Search

 4   5   6   7   8 
Perancangan Enterprise Architecture Sistem Deteksi Fraud Transaksi Keuangan Menggunakan TOGAF ADM dan Deep Learning Long Short-Term Memory (LSTM) Marissa Utami; Putra, Erwin Dwika
Jurnal Sistem Informasi dan E-Bisnis Vol 8 No 1 (2026): Januari
Publisher : LPPMPP Yayasan Sejahtera Bersama Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54650/jusibi.v8i1.637

Abstract

Peningkatan volume dan kompleksitas transaksi keuangan digital mendorong meningkatnya risiko fraud yang bersifat dinamis dan adaptif. Penelitian ini bertujuan merancang Enterprise Architecture (EA) sistem deteksi fraud transaksi keuangan berbasis TOGAF ADM yang terintegrasi dengan model Deep Learning Long Short-Term Memory (LSTM). Dataset publik fraud detection dari Kaggle digunakan untuk memastikan reprodusibilitas penelitian. Model LSTM dievaluasi menggunakan metrik accuracy, precision, recall, dan F1-score. Hasil pengujian menunjukkan performa yang sangat baik dengan accuracy 99,25%, precision 96,40%, recall 92,80%, dan F1-score 94,55%. Integrasi LSTM dalam EA memastikan keselarasan antara kebutuhan bisnis, arsitektur data, aplikasi, dan teknologi. Penelitian ini tidak hanya menghasilkan model deteksi fraud yang akurat, tetapi juga blueprint EA yang terstruktur, scalable, dan siap diimplementasikan pada organisasi keuangan modern.
SOSIALISASI PENGGUNAAN APLIKASI EVALBEE PADA GURU SD NEGERI 50 KOTA BENGKULU Ilham Fahriansyah; Erwin Dwika Putra; Ruliyani; Rizky Rahmat Saputra; M. Alfarisi; Azildjian Arma Yuda
JPMTT (Jurnal Pengabdian Masyarakat Teknologi Terbarukan) Vol. 6 No. 1 (2026): April
Publisher : Lembaga Penelitian Pengabdian Masyarakat Penerbitan dan Percetakan Indonesian Scholar Khiar Wafi (LPPMPP IKHAFI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54650/jpmtt.v6i1.644

Abstract

Berkembangnya teknologi digital yang membuka peluang untuk meningkatkan efisiensi proses evaluasi pembelajaran di sekolah dasar. Namun, sebagian guru masih menghadapi keterbatasan dalam memanfaatkan aplikasi penilaian berbasis digital yang dapat mempercepat proses koreksi dan analisis hasil belajar siswa. Kegiatan sosialisasi ini bertujuan untuk meningkatkan pemahaman dan keterampilan guru menggunakan media penilaian berbasis teknologi, yaitu aplikasi EvalBee. Kegiatan dilaksanakan di SDN 50 Kota Bengkulu pada tanggal 30 Januari 2026 dengan melibatkan 18 orang guru sebagai peserta. Kegiatan ini menggunakan pendekatan Participatory Action Research (PAR) yang melibatkan partisipasi aktif guru melalui tahapan perencanaan, pelaksanaan tindakan, observasi, dan refleksi. Bentuk kegiatan berupa sosialisasi dan pelatihan penggunaan aplikasi EvalBee yang meliputi proses instalasi aplikasi melalui Play Store, pembuatan akun, pengenalan fitur aplikasi, serta simulasi proses penilaian menggunakan pemindaian lembar jawaban siswa. Hasil kegiatan menunjukkan bahwa guru mampu memahami prosedur penggunaan aplikasi EvalBee, mulai dari pembuatan soal hingga proses pemindaian lembar jawaban siswa untuk memperoleh nilai secara otomatis. Selain itu, guru juga menunjukkan peningkatan pemahaman terhadap pemanfaatan teknologi dalam proses evaluasi pembelajaran. Kegiatan ini memberikan kontribusi positif dalam meningkatkan efisiensi dan efektivitas proses penilaian hasil belajar siswa serta mendorong pemanfaatan teknologi digital dalam kegiatan pembelajaran di lingkungan sekolah dasar
Apriori Algorithm Implementation on Market Basket Analysis (MBA) of Mobile Phone Accessories Erwin Dwika Putra; Muhammad Husni Rifqo; Depmi Hardianto
Jurnal Komputer, Informasi dan Teknologi Vol. 2 No. 2 (2022): Desember
Publisher : Penerbit Jurnal Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53697/jkomitek.v2i2.879

Abstract

Theuse of data mining techniques presently help business owners to facilitate the promotion of their product marketing. One of the most techniques is well-known as association analysis. This association analysis aims to find the relationship between the goods purchased by customers. This kind of association analysis is commonly known as market basket analysis. Market basket analysis uses customer data that has been stored in the database to find new information in it. The apriori algorithm, is applied an algorithm for conducting market basket analysis, which aims to find the most frequently purchased items. This apriori algorithm produces an association rule that is useful for business actors. By analyzing the association a priori algorithm can be seen that customers’ data can be used as input for business owners to determine sales strategies for their business.
Analysis of The Theme Clustering Algorithm Using K-Means Method Erwin Dwika Putra; Muhammad Husni Rifqo; Dwita Deslianti; Krismiyani Krismiyani
Jurnal Komputer, Informasi dan Teknologi Vol. 2 No. 2 (2022): Desember
Publisher : Penerbit Jurnal Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53697/jkomitek.v2i2.884

Abstract

The title of this research is the analysis of the thesis theme clustering algorithm using the k-means method. The main problem is how we can find out which theme is most in demand by thesis students at the Faculty of Engineering, University of Muhammadiyah Bengkulu. This clustering uses the K-means method. The K-Means method was chosen because this method is one of the non-hierarchical data clustering methods that seeks to partition data into two or more clusters with the same characteristics included in the same cluster. The purpose of this research is to help prospective students who will write their thesis in knowing which themes are more interested in them.
Implementation of Blowfish Algorithm for Encryption and Decription on Android-Based QR Code Zulhamdi Putra; Dedy Abdullah; Erwin Dwika Putra; Yulia Darmi
Jurnal Komputer, Informasi dan Teknologi Vol. 2 No. 2 (2022): Desember
Publisher : Penerbit Jurnal Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53697/jkomitek.v2i2.897

Abstract

The development of technology is currently growing very rapidly which allows us to access various kinds of data and information, but there are lots of people who abuse this ability, for example phishing activities that often target data and information owned by individuals and companies. Loss of data and information is very detrimental to individuals and companies, where the data and information can be used as a tool for extortion, used as a fraud tool and even the information can be traded. The main reason for the importance of maintaining the security of information is to protect information from online crimes. One of the techniques designed to protect important and confidential information is a cryptographic technique using the Blowfish algorithm and also a QR Code which functions as second line security. where data and information that has been converted into a QR Code cannot be changed. The purpose of this study is to apply the Blowfish Algorithm for Encryption and Decryption of the QR Code into an android-based application system. The results of this study are: The blowfish algorithm can be implemented into an android-based application. Plaintext which is converted into ciphertext using the blowfish algorithm can be used as a QR Code using a QR Code generator. A QR code is up to 7089 numeric digits and 4296 alphanumeric characters. The amount of information will affect the QR Code module, so the symbols in the QR Code will become more complicated. This application has received an assessment from respondents from users with an average value (6.5) with the category of choice "agree".
Analysis of Mental Ray Rendering Techniques in 3D Animation Film Analisis Teknik Rendering Mental Ray Pada Film Animasi 3D Bony Triwahyuda; Erwin Dwika Putra; Agung Kharisma Hidayah; Harry Witriyono
Jurnal Komputer, Informasi dan Teknologi Vol. 3 No. 2 (2023): Desember
Publisher : Penerbit Jurnal Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53697/jkomitek.v3i2.1473

Abstract

Rendering is the final stage of the modeling or animation process. It is during this rendering that the polygons that make up a model will be computed on the computer to form an image. Along with the times, there are many rendering provider applications for 3D animation, one of which is Mental Ray. The formulation of the research problem is How long does it take to render a 3D animated film using mental ray and analyze the size of the rendered using mental ray? The development model in this study uses the Multimedia Development Life Cycle (MDLC) development which is the Luther version of the development method. Data collection by taking two finished or ready-to-rendering 3D films. The results show that the average length of time needed to render of The Little Human animation is 8.3 minutes, while the animated film Go Alex is 8.8 minutes. While the average size of the 12 rendered scenes of The Little Human animation is 17.3 mb and the animated film Go Alex is 17.8 Mb. Computer specifications will affect the performance of the rendering engine itself. This test only uses one type of computer, so to really test the performance of the rendering engine, a similar test is needed using several different types of computers and sepsis. When using the Autodesk Maya 2019 application, it is recommended to use incrementalSave to find out every step of the changes made, because it is to remember the steps to be taken if you forget and anticipate unexpected things such as blackouts.
Perbandingan Metode Naive Bayes dan Bayesian Regularization Neural Network Untuk Klasifikasi Jenis Penyakit Diabetes Mellitus Filda Rahayu; Erwin Dwika Putra; Yuza Reswan; Agung Kharisma Hidayah
Jurnal Komputer, Informasi dan Teknologi Vol. 5 No. 2 (2025): Desember
Publisher : Penerbit Jurnal Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53697/jkomitek.v5i2.2985

Abstract

Diabetes Mellitus is associated with long-term damage, dysfunction, and failure of various organs, especially the eyes, kidneys, nerves, heart, and blood vessels. Naive Bayes is a classification method that can predict the probability of a class, thus generating decisions based on learning data. The Naive Bayes method is used to classify Diabetes Mellitus. To predict a disease using a data mining approach, symptoms accompanied by clinical data are required. Therefore, the problem is formulated how the Naive Bayes method compares with Bayesian regularization neural networks for classifying types of Diabetes Mellitus. With the RapidMiner tool, it becomes educational information in providing information on Diabetes Mellitus based on Type 1 Diabetes, Type 2 Diabetes, and Gestational Diabetes
METODE IDENTIFIKASI PENGENALAN WAJAH MENGGUNAKAN METODE HAAR FEATURE Marissa Utami; Erwin Dwika Putra
JSAI (Journal Scientific and Applied Informatics) Vol 6 No 3 (2023): November
Publisher : Fakultas Teknik Universitas Muhammadiyah Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36085/jsai.v6i3.4997

Abstract

The face recognition process aims to identify some of the basic requirements of the system and learn the techniques required for the development of a realtime face recognition system. Facial recognition is one of the pattern recognition approaches for the purpose of identifying a person's face with a biometric approach. In this case Haar Feature is one of the methods to identify face recognition, Haar feature is used to recognize objects based on the simple value of a feature, not the pixel value contained in the object image. In testing this system, it is known that the success rate in the Confusion Matrix calculation on the image is between the actual and predicted values with a Precission value of 93%, meaning that the level of accuracy between the information requested by the user and the answer given by the system is the same. Recall results from the Precission value tend to be inverse to the results of the Recall value. If the Precission result is small then the Recall result is large, because the success rate of the Recall system in finding back a given information is 98%. Precission and Recall results are not the result of Accuracy. The difference is the level of closeness between the predicted results and the actual results of Precission and Recall. Where the actual results are the results found / relevant (True Positive) and the absence of true results / not found (True Negative) and these results are calculated based on the results found. The prediction results that users want, then the result of Accuarcy is 93% which is obtained based on the addition of actual results divided by the prediction results.
ANALISIS SENTIMEN ULASAN PENGGUNA APLIKASI BY.U PADA GOOGLE PLAY STORE MENGGUNAKAN ALGORITMA CNN Altra Yudha Mawlana; Erwin Dwika Putra
INTECOMS: Journal of Information Technology and Computer Science Vol. 9 No. 3 (2026): INTECOMS: Journal of Information Technology and Computer Science
Publisher : Institut Penelitian Matematika, Komputer, Keperawatan, Pendidikan dan Ekonomi (IPM2KPE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31539/vfwsfx96

Abstract

Peningkatan penggunaan aplikasi layanan digital by.U diikuti oleh bertambahnya jumlah ulasan pengguna pada Google Play Store yang mencerminkan tingkat kepuasan dan ketidakpuasan pengguna. Banyaknya data teks yang tidak terstruktur menyebabkan analisis secara manual menjadi kurang efektif, sehingga diperlukan pendekatan otomatis melalui analisis sentimen. Penelitian ini bertujuan untuk mengklasifikasikan sentimen ulasan pengguna ke dalam kategori positif, netral, dan negatif menggunakan metode Convolutional Neural Network (CNN). Sebanyak 3.000 ulasan berhasil dikumpulkan, dan 2.984 ulasan diproses melalui tahapan preprocessing sebelum dilakukan pelabelan sentimen berdasarkan rating pengguna. Dataset kemudian dibagi dengan rasio 80% data latih dan 20% data uji. Penelitian ini melakukan beberapa skenario pengujian untuk menganalisis pengaruh preprocessing dan konfigurasi model terhadap kinerja klasifikasi. Hasil penelitian menunjukkan bahwa model CNN dengan penerapan stopword removal menghasilkan akurasi terbaik sebesar 76%. Sementara itu, hasil evaluasi keseluruhan model menunjukkan akurasi sebesar 73% dengan nilai precision sebesar 75%, recall sebesar 73%, dan F1-score sebesar 73%, yang mengindikasikan performa klasifikasi yang cukup baik. Namun, model masih memiliki keterbatasan dalam mengidentifikasi sentimen netral secara optimal. Kata kunci: Convolutional Neural Network (CNN), ulasan pengguna, klasifikasi teks, Google Play Store
Analisis Robustness Model Deep Learning pada Klasifikasi Sampah Non-Organik terhadap Variasi Pencahayaan dan Noise Citra Erwin Dwika Putra; Marissa Utami
JSAI (Journal Scientific and Applied Informatics) Vol 9 No 2 (2026): Juni
Publisher : Fakultas Teknik Universitas Muhammadiyah Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36085/jsai.v9i2.10791

Abstract

The increasing amount of non-organic waste presents challenges in effective waste management and sorting processes. Deep learning technology has been widely used for image-based waste classification; however, most previous studies mainly focused on improving model accuracy under ideal conditions without considering model robustness against visual disturbances in real-world environments. This study aims to analyze the robustness of deep learning models for non-organic waste classification under illumination variations and image noise using the public TACO (Trash Annotations in Context) dataset. Three deep learning models were employed, namely EfficientNet-B0, ResNet50, and MobileNetV2. The experiments were conducted by applying multiple brightness levels and Gaussian noise disturbances. The results showed that EfficientNet-B0 achieved the best performance with an accuracy of 87.84%, precision of 87.17%, recall of 85.35%, and F1-score of 85.39%. Furthermore, EfficientNet-B0 obtained the highest robustness score of 0.823 compared to ResNet50 and MobileNetV2. The findings indicate that illumination variations and image noise significantly affect model performance, especially under severe visual disturbances.
Co-Authors Abdiansah, Abdiansah Abdullah, Dedy Abdullah, Dedy Ade Rangga Saputera Agastra Galih Setiawan Ahmad Sayyeid Al Jadd Alber Uci Saputra Altra Yudha Mawlana Andi Nugroho Angtyas Candra Pratama Anita Septiani Putri Apridiansyah, Yovi Ayumi, Vina Azildjian Arma Yuda Azildjian Arma Yuda Bony Triwahyuda Charles Roenal Krisubiyantoro Dede Erwan Dedy Abdullah Dedy Abdullah Dedy Agung Prabowo Depmi Hardianto Deslianti, Dwita Deslianti, Dwita Diana Diana Ermatita - Erzi Hidayat Fikri Agnesa Putra Filda Rahayu Firdianti Sukemi Hadiguna Setiawan Handrie Noprison Hardianto, Depmi Harry Witriyono Harry Witriyono Herianto Herianto hidayah, agung kharisma Ilham Fahriansyah Ilham Fahriansyah Ilham Fahriansyah, Ruliyani Jastrawan, Noris Jefri Zulkarnain Khairullah khairullah Krismiyani Krismiyani Krismiyani, Krismiyani M Khairunnas M. Alfarisi M. Alfarisi M. Husni Rifqo Mariana Purba Mariana Purba Marissa Utami Marrisa Utami Mellysa Pratama Moh. Rere Valentino Zantohar Monsya Juansen Muhammad Hikmal Febrian Muhammad Husni Rifqo Muhammad Husni Rifqo Muntahanah Naufal Afif Hawari Noprisson, Handrie Noris Jastrawan Nuri David Maria Veronika Pahrizal, Pahrizal Pitersa Susanto Purba, Mariana Putra, Zulhamdi Rahmat Arif Ma’ruf Rega Satya Putra Rifqo, Muhammad Husni Rio Eka Prayuda Rizky Rahmat Saputra Rizky Rahmat Saputra Ruliyani Sahrudin Sahrudin Sandhy Fernandez Sarwati Rahayu Sonita, Anisya Stefanus Santosa Sulis Sandiwarno ujang juhardi Umniy Salamah Vendi Handoyo Handoyo Veronika, Nuri David Maria Wachyu Hari Haji Wahyu Adianto Wijaya, Ardi Yetman Erwadi Yulia Darmi Yuza Reswan Zalia Apriyanti Zulhamdi Putra