Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal Jurnal Elkasista
Lesmana, Dadang
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Materials Science & Nanotechnology

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Teknologi PENGAPLIKASIAN DEEP LEARNING DENGAN DESAIN ARSITEKTUR JST UNTUK TUGAS REGRESI DAN KLASIFIKASI: Elektronika lesmana, dadang
Jurnal Elkasista Vol 6 No 1 (2025): Jurnal Elkasista
Publisher : Pustaka Poltekad

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54317/elka.v6i1.564

Abstract

Abstract: Technological developments have driven the application of Deep Learning, particularly Artificial Neural Networks (ANN), in solving regression and classification tasks. ANNs consist of interconnected artificial neurons that are effective in classification, prediction, and pattern recognition. This study aims to build and analyze the impact of variations in Artificial Neural Network (ANN) architecture on prediction accuracy, using a quantitative experimental method with a controlled randomized design. The BostonHousing.csv dataset was used for regression, and the Iris.csv dataset for classification. Regression evaluation uses MSE, R², and MAE; while classification uses accuracy and confusion matrix. The best regression results were obtained from the 4-hidden-layer architecture (512, 256, 128, 64), with ReLU, sigmoid, tanh, and ReLU activation functions, a learning rate of 0.001, achieving an R² of 89.2% and an MAE of 1.94. For classification, the best architecture (128, 64, 32, 16) with a softmax output yielded an accuracy of 99.8% and a model accuracy of 100%. Keywords – deep learning, artificial neural network, regression, classification, ANN architecture
PENGAPLIKASIAN DEEP LEARNING DENGAN DESAIN ARSITEKTUR JST UNTUK TUGAS REGRESI DAN KLASIFIKASI: Elektronika lesmana, dadang
Elektronika Sistem Senjata Vol 6 No 1 (2025): Jurnal Elkasista
Publisher : Pustaka Poltekad

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54317/elka.v6i1.564

Abstract

Abstract: Technological developments have driven the application of Deep Learning, particularly Artificial Neural Networks (ANN), in solving regression and classification tasks. ANNs consist of interconnected artificial neurons that are effective in classification, prediction, and pattern recognition. This study aims to build and analyze the impact of variations in Artificial Neural Network (ANN) architecture on prediction accuracy, using a quantitative experimental method with a controlled randomized design. The BostonHousing.csv dataset was used for regression, and the Iris.csv dataset for classification. Regression evaluation uses MSE, R², and MAE; while classification uses accuracy and confusion matrix. The best regression results were obtained from the 4-hidden-layer architecture (512, 256, 128, 64), with ReLU, sigmoid, tanh, and ReLU activation functions, a learning rate of 0.001, achieving an R² of 89.2% and an MAE of 1.94. For classification, the best architecture (128, 64, 32, 16) with a softmax output yielded an accuracy of 99.8% and a model accuracy of 100%. Keywords – deep learning, artificial neural network, regression, classification, ANN architecture
DESIGN AND BUILD AN AUGMENTED REALITY-BASED 3D SANDBOX MAP DESIGN FOR MAP SIMULATION IN EXERCISE OPERATIONS TASKS EQUIPPED WITH ANIMATION AND LIVE STREAMING SERVICES (WEBRTC): RANCANG BANGUN DESAIN PETA SANDBOX 3D BERBASIS AUGMENTED REALITY UNTUK SIMULASI PETA DALAM LATIHAN TUGAS OPERASI nenet, antonius; Lesmana, Dadang; Syafaat, Mokhammad
Elektronika Sistem Senjata Vol 6 No 2 (2025): Jurnal Elkasista
Publisher : Pustaka Poltekad

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54317/elka.v6i2.736

Abstract

In the era of transformation, today's innovations are rapidly developing, one of which is technological advances in the military sector, such as Augmented Reality-based 3D Sandbox maps equipped with character animations and live streaming services (WebRTC) which function to improve the training performance of military soldiers, facilitate the provision of operational orders and facilitate monitoring by the top command. In society, it can also be useful for the educational process. Augmented Reality (AR) is a 3D visual object technology that can be connected to computers and mobiles. WebRTC is an HTML5 specification that allows users to improve communication in real-time directly from the browser to other devices. WebRTC easily makes it easier for us to carry out communication using video and voice directly within the website page without having to install any plugins. The research method used in this study is a real experimental research design. Experimental studies examining the effects between the treated group (experimental group) and the control group (not given the treatment) were then compared between the two. The expected results of the research on the design and construction of the design of 3D sandbox maps based on Augmented Reality (AR), namely maps in military exercises are equipped with character animations and live streaming services (WebRTC) to improve combat simulation tools from manual to digital in the form of more efficient visual viewmaps. There was a clear difference in technological progress from the experimental group (given treatment) compared to the control group (not given treatment). Technology needs to be updated more sophisticatedly in order to achieve optimal in the process of its use and operation so as to improve the professionalism of training and produce great soldiers. Keywords: Augmented Reality, WebRTC, Live Streaming
Co-Authors nenet, antonius Syafaat, Mokhammad