Browsing by Author "Badr, Amr"

Now showing 1 - 4 of 4

Comparing Multi-class Approaches for Motor Imagery Using Renyi Entropy
(Springer International Publishing, 2019) Selim, Sahar; Tantawi, Manal; Shedeed, Howida; Badr, Amr
One of the main problems that face Motor Imagery-based system is addressing multi-class problem. Various approaches have been used to tackle this problem. Most of these approaches tend to divide multi-class problem into binary sub problems. This study aims to address the multi-class problem by comparing five multi-class approaches; One-vs-One (OVO), One-vs-Rest (OVR), Divide & Conquer (DC), Binary Hierarchy (BH), and Multi-class approaches. Renyi entropy was examined for feature extraction. Three linear classifiers were used to implement these five-approaches: Support Vector Machine (SVM), Multinomial Logistic Regression (MLR) and Linear Discriminant Analysis (LDA). These approaches were compared according to their performance and time consumption. The comparative results show that, Renyi entropy demonstrated its robustness not only as a feature extraction technique but also as a powerful dimension reduction technique, for multi-class problem. In addition, LDA proved to be the best classifier for almost all approaches with minimum execution time.
A CSP\AM-BA-SVM Approach for Motor Imagery BCI System
(IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC., 2018) Selim, Sahar; Mohsen Tantawi, Manal; A. Shedeed, Howida; Badr, Amr
Brain-computer interface (BCI) has become extremely popular in recent decades. It gained its significance from the intention of helping paralyzed people communicate with the external environment. One of the major challenges facing BCI systems is obtaining reliable classification accuracy of motor imagery (MI) mental tasks. In this paper, a novel CSP\AM-BA-SVM approach is proposed using bio-inspired algorithms for feature selection and classifier optimization to improve classification accuracy of the MI-BCI systems. The proposed approach applies optimum selection of time interval for each subject. The features are extracted from EEG signal using the common spatial pattern (CSP). Binary CSP is extended to multi-class problems by utilizing one-vs-one strategy. This paper introduces applying a hybrid attractor metagene (AM) algorithm along with the Bat optimization algorithm (BA) to select the most discriminant CSP features and optimize SVM parameters. The efficacy of the proposed approach was examined using three data sets. The proposed approach has achieved 78.55% accuracy and 0.71 mean kappa for BCI Competition IV data set 2a, 86.6% accuracy and 0.82 mean kappa for BCI Competition III data set Ma, and 85% for the binary class BCI Competition III data set IVa. For multi-class data sets, the proposed approach outperforms winners of BCIC IV, 2a and BCIC III, IIIa with kappa 0.14 and 0.17, respectively. For binary class BCIC III, IVa, it performed slightly better than existing studies in the literature by approximate to 0.5%. The proposed CSP\AM-BA-SVM transcends the traditional CSP\SVM approach and other existing studies.
A new hybrid approach for feature selection and predicting of protein interaction network in lung cancer
(ztaha, 2019) Abd El Haliem, Zeinab; Nassef, Mohammad; Badr, Amr
Different computational and evolutionary methods have been employed in the last decade for selecting important molecular features from biological data. Extracting information from microarray data is extremely important and complex task due to the high dimensionality of its datasets. Feature selection is a very important aspect of the analysis that helps in identifying the important genes that can be used in a further biological analysis. This paper proposes a new hybridization between the Flower Pollination and Differential Evolution algorithms for optimizing feature selection parameters and to find out the most important subset of features over gene expression profiles of lung cancer. The results showed that the hybrid approach has a better capability in searching for the best solutions compared to applying each algorithm independently. SLC5A1 gene was identified as a biomarker gene of lung cancer. By constructing the protein-protein interaction network for the extracted genes, a direct interaction has been detected between the SLC5A1 and EGFR genes, where the latter is known to have an important role in the mutation process of lung cells.
Reducing Execution Time for Real-Time Motor Imagery Based BCI Systems
(SPRINGER INTERNATIONAL PUBLISHING AG, 2017) Selim, Sahar; Tantawi, Manal; Shedeed, Howida; Badr, Amr
Brain Computer Interface (BCI) systems based on electroencephalography (EEG) has introduced a new communication method for people with severe motor disabilities. One of the main challenges of Motor Imagery (MI) is to develop a real-time BCI system. Using complex classification techniques to enhance the accuracy of the system may cause a remarkable delay of real-time systems. This paper aims to achieve high accuracy with low computational cost. Two public datasets (BCIC III IVa and BCIC IV IIa) were used in this study; to check the robustness of the proposed approach. Dimension reduction of input signal has been done by channel selection and extracting features using Root Mean Square (RMS). The extracted features have been examined with four different classifiers. Experimental results showed that using Least Squares classifier gives best results, compared to other classifiers, with minimum computational time.