Remli, Muhammad Akmal
Unknown Affiliation

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

Found 4 Documents
Search

Improving imbalanced class intrusion detection in IoT with ensemble learning and ADASYN-MLP approach Soni, Soni; Remli, Muhammad Akmal; Mohd Daud, Kauthar; Al Amien, Januar
Indonesian Journal of Electrical Engineering and Computer Science Vol 36, No 2: November 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v36.i2.pp1209-1217

Abstract

The exponential growth of the internet of things (IoT) has revolutionized daily activities, but it also brings forth significant vulnerabilities. intrusion detection systems (IDS) are pivotal in efficiently detecting and identifying suspicious activities within IoT networks, safeguarding them from potential threats. It proposes a ensemble approach aimed at enhancing model performance in such scenarios. Recognizing the unique challenges posed by imbalanced class distribution, the research employs three sampling techniques LightGBM adaptive synthetic sampling (ADASYN) with multilayer perceptron (MLP), XGBoost ADASYN with MLP, and LightGBM ADASyn with XGBoost to address class imbalance effectively. Evaluation confusion matrix performance metrics underscores the efficacy of ensemble models, particularly LightGBM ADASYN with MLP, XGBoost ADASYN with MLP, and LightGBM ADASYN with XGBoost, in mitigating imbalanced class issues. The LightGBM ADASYN with MLP model stands out with 99.997% accuracy, showcasing exceptional precision and recall, demonstrating its proficiency in intrusion detection within minimal false positives negatives. Despite computational demands, integrating XGBoost within ensemble frameworks yields robust intrusion detection results, highlighting a balanced trade-off between accuracy, precision, and recall. This research offers valuable insights into the strengths with different ensemble models, significantly contributing to the advancement of accurate and reliable IDS in realm of IoT.
Performance evaluation of multiclass classification models for ToN-IoT network device datasets Soni, Soni; Remli, Muhammad Akmal; Daud, Kauthar Mohd; Al Amien, Januar
Indonesian Journal of Electrical Engineering and Computer Science Vol 35, No 1: July 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v35.i1.pp485-493

Abstract

Internet of things (IoT) technology has empowered tangible objects to establish internet connections, facilitating data exchange with computational capabilities. With significant potential across sectors like healthcare, environmental monitoring, and industrial control, IoT represents a promising technological advancement. This study explores datasets from ToN-IoT’s IoT devices, focusing on multi-class classification, including normal and attack classes, with an additional aim of identifying potential attack sub-classes. Datasets comprise various IoT devices, such as refrigerators, garage doors, global positioning systems (GPS) sensors, motion lights, modbus devices, thermostats, and weather sensors. Comparative analysis is conducted between two prominent multiclass classification models, extreme gradient boosting (XGBoost) and light gradient boosting machine (LightGBM), utilizing accuracy and computational time metrics as evaluation criteria. Research findings highlight that the LightGBM model achieves superior accuracy at 78%, surpassing XGBoost 74.31%. However, XGBoost demonstrates an advantage with a shorter computational time of 1.23 seconds, compared to LightGBM 6.79 seconds. This study not only provides insights into multiclass classification model selection but also underscores the crucial consideration of the trade-off between accuracy and computational efficiency in decision-making. Research contributes to advancing our understanding of IoT security through effective classification methodologies. The findings offer valuable information for researchers and practitioners, emphasizing the nuanced decisions needed when selecting models based on specific priorities like accuracy and computational efficiency.
Advanced tourist arrival forecasting: a synergistic approach using LSTM, Hilbert-Huang transform, and random forest Mukhtar, Harun; Remli, Muhammad Akmal; Mohamad, Mohd Saberi; Wan Salihin Wong, Khairul Nizar Syazwan; Ridhollah, Farhan; Deprizon, Deprizon; Soni, Soni; Lisman, Muhammad; Amran, Hasanatul Fu'adah; Sunanto, Sunanto; Ismanto, Edi
Indonesian Journal of Electrical Engineering and Computer Science Vol 38, No 1: April 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v38.i1.pp517-526

Abstract

An advanced synergistic approach for forecasting tourist arrivals is presented, integrating long short-term memory (LSTM), Hilbert-Huang transform (HHT), and random forest (RF). LSTM is leveraged for its capability to capture long-term dependencies in sequential data. Additional data from Google Trends (GT) is processed with HHT for feature extraction, followed by feature selection using the RF algorithm. The combined HHT-RF-LSTM model delivers highly accurate forecasts. Evaluation employs regression analysis with metrics such as root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and mean square error (MSE), highlighting the effectiveness of this innovative approach in predicting tourist arrivals. This methodology provides a robust framework for handling limited datasets and improving forecast reliability. By incorporating diverse data sources and advanced preprocessing techniques, the model enhances prediction performance, demonstrating the strong performance of RF in feature selection.
Deep learning-based cryptanalysis in recovering the secret key and plaintext on lightweight cryptography Fatma, Yulia; Remli, Muhammad Akmal; Mohamad, Mohd Saberi; Al Amien, Januar
Indonesian Journal of Electrical Engineering and Computer Science Vol 38, No 2: May 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v38.i2.pp1115-1123

Abstract

The development of machine learning (ML) technologies provide a new development direction for cryptanalysis. Several ML research in the field of cryptanalysis was carried out to identify the cryptographic algorithm used, find out the secret key, and even recover the secret message The first objective of this study is to see how much influence optimization and activation function have on the multi-layer perceptron (MLP) model in performing cryptanalysis. The second research objective, which is to compare the performance of cryptanalysis in recovering keys and the plaintext. Several experiments have been carried out, the observed parameters found that the use of the rectified linear unit (ReLU) activation function and the ADAM optimizer improves the performance of deep learning (DL)-based cryptanalysis as evidenced by a significantly smaller error rate. DL-based cryptanalysis works more effectively in recovering keys than recovering plaintext. DL-based cryptanalysis managed to recover the keys with an average loss of 0.007, an average of 49 epochs, and an average time of 0.178 minutes.