Claim Missing Document
Check
Articles

Found 3 Documents
Search

The effect of feature selection with optimization on taxi fare prediction A. Naim, Amany; Hekal Omar, Asmaa; A. Ibrahim, Asmaa; Mohamed, Asmaa; M. Mostafa, Naglaa
Bulletin of Electrical Engineering and Informatics Vol 14, No 3: June 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v14i3.8658

Abstract

Feature selection plays a key influence in machine learning (ML); the main objective of feature selection is to eliminate irrelevant and redundant variables in different classification problems to improve the performance of the learning algorithms. Classification accuracy is improved by reducing the number of selected features. Many real-world problems, such as taxi fare can be predicted by ML. This paper proposes feature selection using genetic algorithm (GA) optimization to predict taxi fare. Experiments are performed on real datasets of taxi fare, and this paper uses eight classifiers to evaluate the selected features. The performance of the classifiers is assessed using various performance metrics. The results are compared with feature selection without optimization. The proposed method records high classification accuracy when evaluated by three types of classifiers (random forest, AdaBoost, and Gradient Boost). The results indicate that the prediction accuracy of the proposed method is 99.7% on taxi fare dataset.
An improved round robin time sharing algorithm for optimizing data mapping in cloud computing environments Abdelkader, Afaf; Mohamed, Asmaa; Ghazy, Nermeen
Bulletin of Electrical Engineering and Informatics Vol 14, No 5: October 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v14i5.8087

Abstract

Cloud computing in recent years has been widely applied in a wide number of applications and fields. However, allocating tasks to virtual machines (VMs) remains a part that needs enhancement. Task scheduling algorithms in heterogeneous computing system are required to satisfy high-performance data mapping requirements. The efficient allocation between resources and tasks decreases waiting time (WT), turnaround time (TT) and maximizes resource utilization. Various task scheduling algorithms, including round robin (RR) and some improved RR algorithm are used for cloud environment. A novel time-sharing algorithm (NRRTSA) is introduced, demonstrating enhancements in WT and TT. Simulation findings indicate that the NRRTSA algorithm effectively schedules multiple requests (cloudlets) among several VMs, the proposed NRRTSA outperforms RR and other algorithms in terms of the average of both TT and WT. The average turnaround time (ATT) is enhanced with a ratio of 10.8% to 45%, the average waiting time (AWT) is enhanced with a ratio of 10.9% to 45%.
Hybrid CNBLA architecture for accurate earthquake magnitude forecasting Shams, Somia A.; Mohamed, Asmaa; Desuky, Abeer S.; A. Elsharawy, Gaber; El-Sayed, Rania Salah
International Journal of Electrical and Computer Engineering (IJECE) Vol 15, No 6: December 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v15i6.pp5879-5893

Abstract

Earthquake prediction in seismology is challenging due to sudden events and lack of warnings, requiring rapid detection and accurate parameter estimation for real-time applications. This study proposed a novel automatic earthquake detection model to enhance the processing and analysis of seismic data. The hybrid model comprises convolutional layers, normalization techniques, bidirectional long short-term memory (Bi-LSTM) networks, and attention mechanisms, collectively referred to as the hybrid convolutional–normalization–BiLSTM–attention (CNBLA) model. The attention mechanism allows the model to focus on critical segments of seismic sequences, while layer normalization stabilizes training by normalizing activations, thus reducing the effects of input scale variations. This dual approach mitigates the impact of input scale variations and enhances the model’s ability to effectively decode complex temporal patterns. The hybrid CNBLA model optimizes the extraction and processing of temporal features from raw waveforms recorded at single stations, thereby improving the accuracy and efficiency of seismic magnitude estimation. The proposed model is evaluated using two datasets: the STEAD and USGS achieving a mean square error (MSE) values 0.054 and 0.0843 and a mean absolute error (MAE) 0.15 and 0.2526 respectively. The hybrid CNBLA model outperforms two baseline models and five state-of-the-art approaches in earthquake magnitude estimation, improving seismic monitoring and early warning systems.