Article Per Year (5 Year)
p-Index From 2020 - 2025
0.61
P-Index
This Author published in this journals
All Journal Journal of Information System JOURNAL OF APPLIED INFORMATICS AND COMPUTING Data Science: Journal of Computing and Applied Informatics
Soeleman, Moch. Arief
Unknown Affiliation
Computer Science & IT

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

Found 3 Documents
Search

 1 
Comparative Performance Analysis of Optimization Algorithms in Artificial Neural Networks for Stock Price Prediction Wijaya, Ekaprana; Soeleman, Moch. Arief; Andono, Pulung Nurtantio
Journal of Applied Informatics and Computing Vol. 9 No. 1 (2025): February 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i1.8820

Abstract

This study aims to enhance price prediction accuracy using Artificial Neural Networks (ANN) by comparing three optimization methods: Stochastic Gradient Descent (SGD), Adam, and RMSprop. The research employs a systematic approach involving the design, training, and validation of ANN models optimized by these techniques. Performance metrics such as Mean Squared Error (MSE), Mean Absolute Error (MAE), and R Square are utilized to evaluate the effectiveness of each method. The results indicate that the Adam optimization method outperforms the others, achieving the lowest MSE of 0.0000503 and the lowest MAE of 0.0046, resulting in an impressive R Square value of 0.9989. Adam's superior performance can be attributed to its adaptive learning rate mechanism, which effectively adjusts to the high volatility and noise characteristic of stock price data, enabling the model to converge faster and more accurately. In comparison, SGD produced a higher MSE of 0.0001208 and MAE of 0.0075, while RMSprop yielded an MSE of 0.0000726 and MAE of 0.0059. These findings highlight Adam's ability to significantly enhance the predictive capabilities of ANN, particularly in dynamic and complex datasets, making it a preferred choice for this application. The novelty of this research lies not only in its comparative analysis of various optimization methods within the ANN framework but also in the exploration of unique ANN features and their application to a specific stock price prediction case study, providing deeper insights into the practical implications of optimization strategies. This study lays the groundwork for future research by suggesting the exploration of additional optimization algorithms and more complex neural network architectures to further improve prediction accuracy.
Towards Automated Motor Impulsivity Monitoring in Real-world Scenarios: A Multiple Object Tracking Approach Dalimarta, Fahmy; Andono, Pulung Nurtantio; Soeleman, Moch. Arief; Hasibuan, Zainal Arifin
Data Science: Journal of Computing and Applied Informatics Vol. 9 No. 1 (2025): Data Science: Journal of Computing and Applied Informatics (JoCAI)
Publisher : Talenta Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32734/jocai.v9.i1-16686

Abstract

Assessment of motor impulsivity often faces several challenges. Conventional assessments that rely on controlled settings often fail to capture impulsive behaviors in real-world contexts. This study proposes an automated approach using Multiple Object Tracking (MOT) technology to assess motor impulsivity. The aim was to develop a system for detecting and quantifying motor impulsivity in naturalistic, multi-person environments. By employing cutting-edge MOT algorithms, the solution tracks multiple individuals concurrently, enabling movement and interaction analyses. This methodology integrates MOT with behavioral models to identify motor impulsivity patterns such as abrupt trajectory changes or impulsive gesturing. Trained on real-world annotated datasets, the system ensures adaptability across settings. Our approach successfully distinguished impulsive movements from typical behavioral patterns, with an accuracy of 95.43%. This approach could revolutionize assessments by providing objective and quantitative measurements and facilitating enhanced diagnostics and personalized interventions. Extensive evaluations are required to assess real-time capabilities, robustness in occluded environments, and accurate impulsive pattern identification. These findings could enable broader clinical, research, and behavioral monitoring applications, advancing our understanding of the implications of motor impulsivity.
Analisa Deteksi Citra Kerusakan pada Body Mobil dengan Menggunakan Metode Deteksi Tepi Canny Nasdal, Dannya Deczi; Soeleman, Moch. Arief; Fanani, A. Zainul
JOINS (Journal of Information System) Vol. 9 No. 1 (2024): Edisi Mei 2024
Publisher : Fakultas Ilmu Komputer, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33633/joins.v9i1.10550

Abstract

Kendala dalam penggunaan bahan perbaikan body mobil sering kali muncul akibat analisis kerusakan yang tidak tepat yang hanya berdasarkan pengamatan mata. Kendala ini juga menjadi hambatan bagi perusahaan asuransi kendaraan dalam menentukan klaim yang sepadan dengan tingkat kerusakan. Untuk itu, peneliti mengajukan metode baru dalam menganalisis kerusakan body mobil dengan menggunakan segmentasi citra deteksi tepi canny berbasis algoritma Canny. Metode ini mampu mengidentifikasi garis tepi pada gambar kerusakan body mobil dan mengkalkulasi persentase piksel tepi yang menunjukkan tingkat kerusakan. Selain itu, penelitian ini juga mengaplikasikan noise filtering dengan algoritma Machine Learning untuk meningkatkan kualitas gambar sebelum proses segmentasi. Implementasi metode ini dilakukan dengan menggunakan software MatLab versi 2015a.
Co-Authors Dalimarta, Fahmy Ferdian Ekaprana Wijaya Fanani, A. Zainul Nasdal, Dannya Deczi Pulung Nurtantio Andono Zainal Arifin Hasibuan