Article Per Year (5 Year)
p-Index From 2021 - 2026
0.817
P-Index
This Author published in this journals
All Journal DEVICE Jurnal Armada Informatika Jurnal Ilmu Komputer dan Sistem Informasi
Dedi Irawan
Universitas Muhammadiyah Sumatera Utara
Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Engineering Library & Information Science Mechanical Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
KLASIFIKASI FITUR WARNA LEVEL ROASTING BIJI KOPI MENGGUNAKAN ARTIFICIAL NEURAL NETWORK Tri Andre Anu; Rika Rosnelly; Dedi Irawan; Ubaidullah Hasibuan; Progresif Bulolo5
Device Vol 13 No 1 (2023): Mei
Publisher : Fakultas Teknik dan Ilmu Komputer (FASTIKOM) UNSIQ

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32699/device.v13i1.4094

Abstract

Abstract align="justify"Small and Medium Enterprises (SMEs) are using a manual method to notice the roasting level classification of coffee beans. However, the weaknesses in this technique are that the coffee roaster staff consumes time sorting the roasting level of the coffee beans. As a result, the coffee roaster focuses less because they take too long to sort the coffee beans—consequently, the mixed coffee beans in packages that should be elsewhere. Therefore a system is needed to help coffee roaster officers classify coffee beans using an artificial neural network. The data used are 60 coffee beans with three roasting levels: light roasted, medium roasted, and dark roasted. The classification process consists of a training stage and a testing stage. At the testing stage, using a sample of 30 coffee beans and based on the results of this study, the best results were obtained with a training value of 90%. In contrast, the testing accuracy was 66.67%.
The Implement’s Steganografi LSB dan Kriptografi AES-256 untuk Pengamanan Data Citra Digital Muhammad Haris; Dedi Irawan; Gunawan Gunawan; Mahardika Abdi Prawira Tanjung
Jurnal Ilmu Komputer dan Sistem Informasi Vol. 5 No. 2 (2025): Mei 2026
Publisher : LKP Unity Academy

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70340/jirsi.v5i2.420

Abstract

Digital data security has become a critical issue in the digital transformation era, particularly in the exchange of digital images that are vulnerable to interception and manipulation by unauthorized parties. This study aims to implement a layered data security method by combining Advanced Encryption Standard (AES) 256-bit cryptography and Least Significant Bit (LSB) steganography on PNG-format digital images. The approach used is encrypt-then-embed, where the secret message is first encrypted using AES-256 in CBC mode, then the ciphertext is embedded into the cover image pixels through LSB bit substitution. Testing was conducted on five test images with varying resolutions (256×256 to 1024×768 pixels) using Peak Signal-to-Noise Ratio (PSNR), Mean Squared Error (MSE), entropy, avalanche effect, and computation time metrics. The test results show an average PSNR of 70,58 dB and MSE of 0.11, indicating excellent visual quality of the stego images. Security analysis shows an average avalanche effect of 50.29%, approaching the ideal value of 50%, and stego image entropy approaching 7.0545 bits/pixel. The computation time for encryption and embedding processes ranges from 0,005847 to 0,006078 seconds. The combination of AES-256 and LSB has proven effective in providing layered security: AES-256 ensures data confidentiality, while LSB conceals the message existence within the image without significant visual degradation.
Content Marketing Strategy in Increasing Student MSME Brand Awareness Pius Deski Manalu; Dedi Irawan; Mutiara S. Simanjuntak; Dody Hidayat
Jurnal Armada Informatika Vol 10 No 1 (2026): Juni
Publisher : STMIK Methodist Binjai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36520/jai.v10i1.209

Abstract

This study is motivated by the low level of brand awareness among student-owned micro, small, and medium enterprises (MSMEs), which is mainly caused by the suboptimal implementation of digital marketing strategies, particularly content marketing. The main problem addressed in this research is how content marketing strategies can improve brand awareness among student MSMEs. This study aims to analyze the effect of content marketing on brand awareness and to identify effective content strategies that support such improvement. The research employs a quantitative approach using a survey method involving 100 student MSME actors in the Padang Bulan area. Data were collected through questionnaires using a Likert scale and analyzed using simple linear regression and t-test. The results indicate that content marketing has a positive and significant effect on brand awareness, with a regression coefficient of 0.68 and a significance value of 0.000 (less than 0.05). Additionally, about 78% of respondents actively use social media for marketing purposes, while only 65% ​​have structured content strategies. This finding suggests that improving content quality, creativity, and consistency can significantly enhance brand awareness. This study is expected to provide practical insights for student MSMEs in optimizing content-based digital marketing strategies.
Optimizing the Number of Trees in the Random Forest Algorithm to Improve Data Classification Accuracy Iqbal Giffari Ritonga; Pius Deski Manalu; Dedi Irawan; Syawaluddin Kadafi Parinduri
Jurnal Armada Informatika Vol 10 No 1 (2026): Juni
Publisher : STMIK Methodist Binjai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36520/jai.v10i1.306

Abstract

Classification is a technique in data mining used to build predictive models based on patterns or characteristics of data. One widely used classification algorithm is Random Forest, an ensemble learning method that combines several decision trees to produce more accurate and stable predictions. However, the performance of the Random Forest algorithm can be affected by the parameters used, one of which is the number of decision trees (n_estimators). This study aims to analyze the effect of variations in the number of trees on the performance of the Random Forest algorithm in classifying and determine the configuration of the number of trees that produces the best accuracy. The research method was carried out by applying the Random Forest algorithm using variations in the number of trees of 50, 100, 150, and 200. Model performance evaluation was carried out using accuracy, confusion matrix, and feature importance analysis. The test results showed that variations in the number of trees had an impact on model performance, although the increase in accuracy obtained was relatively small. The accuracy values ​​for n_estimators 50, 100, 150, and 200 were 89.44%, 89.44%, 89.53%, and 89.42%, respectively, with the best performance obtained when using n_estimators = 150. The confusion matrix results showed that this configuration provided a better classification balance between the Cancel and Not_Cancelled classes. In addition, feature importance analysis showed that lead time, average price, and special requests were the most influential features on the classification results across all variations in the number of trees. Based on the results of the study, the use of the optimal number of trees can improve the stability of the Random Forest model, but adding a larger number of trees does not always result in a significant increase in accuracy. The Random Forest source code and dataset are available on GitHub at https://github.com
Co-Authors Gunawan Gunawan Hidayat, Dody Iqbal Giffari Ritonga Muhammad Haris Mutiara S. Simanjuntak Pius Deski Manalu Pius Deski Manalu Progresif Bulolo5 Rika Rosnelly Syawaluddin Kadafi Parinduri Tri Andre Anu Ubaidullah Hasibuan