Aly A. Fahmy

Bio: Aly A. Fahmy is an academic researcher from Cairo University. The author has contributed to research in topics: Support vector machine & Optimization problem. The author has an hindex of 19, co-authored 80 publications receiving 1740 citations. Previous affiliations of Aly A. Fahmy include Zagazig University.

Iris features segmentation for arabian horses identification

Abstract: This paper introduces a new approach for segmentation of the found significant features in the iris of Arabian horses. It was found that the most significant features are as follows; the retina cogina, the pupil shape and the pupil size. Accordingly; a new technique that depends on segmentation of the pupil region with the retina cogina in the iris is proposed. Circular hough transform, canny edge detection, and k-mean clustering are applied. For noise removal, connected component labeling and morphological analysis take place. The presented study surveys the application of the proposed technique on collected data set of iris images for different 145 Arabian horses, For testing the effectiveness and the success of such newly applied technique, Jaccard similarity coefficient was evaluated and it was found in the range 80% to 95%. Hence; such technique may represent a new contribution in the iris identification as it hasnfit been applied in any previous study.

Genetic Algorithms for Multi-Objective Community Detection in Complex Networks.

Abstract: Community detection in complex networks has attracted a lot of attention in recent years. Communities play special roles in the structure–function relationship. Therefore, detecting communities (or modules) can be a way to identify substructures that could correspond to important functions. Community detection can be viewed as an optimization problem in which an objective function that captures the intuition of a community as a group of nodes with better internal connectivity than external connectivity is chosen to be optimized. Many single-objective optimization techniques have been used to solve the detection problem. However, those approaches have drawbacks because they attempt to optimize only one objective function, this results in a solution with a particular community structure property. More recently, researchers have viewed the community detection problem as a multi-objective optimization problem, and many approaches have been proposed. Genetic Algorithms (GA) have been used as an effective optimization technique to solve both single- and multi-objective community detection problems. However, the most appropriate objective functions to be used with each other are still under debate since many similar objective functions have been proposed over the years. We show how those objectives correlate, investigate their performance when they are used in both the single- and multi-objective GA, and determine the community structure properties they tend to produce.

Stakeholders of Egypt Public Universities and Research Institutions: An Information Technology Governance Perspective

Abstract: Egypt public higher education and institutions (HEIs) have recognized the need to reassess their functions of teaching, research, and community services. Successful organizations are these providing value for their stakeholders. HEIs are indifference and their management need to identify their stakeholders’ needs and to reposition their institutions towards the fulfillment of these needs. On their quest to enhance their competencies, Information Technology (IT) plays an important role of these institutions. Consequently, governance of It (or ITG) becomes a necessity. From the view point of, this paper aims to identify Egypt public HEIs stakeholders and their needs as the first and necessary step towards the successful implementation of ITG in Egypt public HEIs.

A fuzzy expert system for transforming tabular information into linguistic rules

Abstract: An expert system has been built, using fuzzy logic to transform expertise, obtained from leading experts, from tabular linguistic values form to linguistic fuzzy rules. Those fuzzy rules are then been used to establish a knowledge base, that should be helpful to the decision maker in analyzing future situations. The paper presents a methodology for building those linguistic fuzzy rules for an analysis process of information of any field. The system has been implemented on SUN SPARC machine using SICStus PROLOG.

BNEM: a fast community detection algorithm using generative models

Abstract: Actors in social networks tend to form community groups based on common location, interests, occupation, etc. Communities play special roles in the structure–function relationship; therefore, detecting such communities can be a way to describe and analyze such networks. However, the size of those networks has grown tremendously with the increase of computational power and data storage. While various methods have been developed to extract community structures, their computational cost or the difficulty to parallelize existing algorithms make partitioning real networks into communities a challenging problem. In this paper, we introduce a generative process to model the interactions between social network’s actors. Through unsupervised learning using expectation maximization, we derive an efficient and fast community detection algorithm based on Bayesian network and expectation maximization (BNEM). We show that BNEM algorithm can infer communities within directed or undirected networks, and within weighted or un-weighted networks. We also show that the algorithm is easy to parallelize. We then explore and analyze the result of the BNEM method. Finally, we conduct a comparative analysis with other well-known methods in the fields of community detection.

Deep learning for electroencephalogram (EEG) classification tasks: a review.

Abstract: Objective Electroencephalography (EEG) analysis has been an important tool in neuroscience with applications in neuroscience, neural engineering (e.g. Brain-computer interfaces, BCI's), and even commercial applications. Many of the analytical tools used in EEG studies have used machine learning to uncover relevant information for neural classification and neuroimaging. Recently, the availability of large EEG data sets and advances in machine learning have both led to the deployment of deep learning architectures, especially in the analysis of EEG signals and in understanding the information it may contain for brain functionality. The robust automatic classification of these signals is an important step towards making the use of EEG more practical in many applications and less reliant on trained professionals. Towards this goal, a systematic review of the literature on deep learning applications to EEG classification was performed to address the following critical questions: (1) Which EEG classification tasks have been explored with deep learning? (2) What input formulations have been used for training the deep networks? (3) Are there specific deep learning network structures suitable for specific types of tasks? Approach A systematic literature review of EEG classification using deep learning was performed on Web of Science and PubMed databases, resulting in 90 identified studies. Those studies were analyzed based on type of task, EEG preprocessing methods, input type, and deep learning architecture. Main results For EEG classification tasks, convolutional neural networks, recurrent neural networks, deep belief networks outperform stacked auto-encoders and multi-layer perceptron neural networks in classification accuracy. The tasks that used deep learning fell into five general groups: emotion recognition, motor imagery, mental workload, seizure detection, event related potential detection, and sleep scoring. For each type of task, we describe the specific input formulation, major characteristics, and end classifier recommendations found through this review. Significance This review summarizes the current practices and performance outcomes in the use of deep learning for EEG classification. Practical suggestions on the selection of many hyperparameters are provided in the hope that they will promote or guide the deployment of deep learning to EEG datasets in future research.

SemEval-2016 Task 4: Sentiment Analysis in Twitter

Abstract: This paper discusses the fourth year of the ”Sentiment Analysis in Twitter Task”. SemEval-2016 Task 4 comprises five subtasks, three of which represent a significant departure from previous editions. The first two subtasks are reruns from prior years and ask to predict the overall sentiment, and the sentiment towards a topic in a tweet. The three new subtasks focus on two variants of the basic “sentiment classification in Twitter” task. The first variant adopts a five-point scale, which confers an ordinal character to the classification task. The second variant focuses on the correct estimation of the prevalence of each class of interest, a task which has been called quantification in the supervised learning literature. The task continues to be very popular, attracting a total of 43 teams.

Deep learning-based electroencephalography analysis: a systematic review.

Abstract: Context Electroencephalography (EEG) is a complex signal and can require several years of training, as well as advanced signal processing and feature extraction methodologies to be correctly interpreted. Recently, deep learning (DL) has shown great promise in helping make sense of EEG signals due to its capacity to learn good feature representations from raw data. Whether DL truly presents advantages as compared to more traditional EEG processing approaches, however, remains an open question. Objective In this work, we review 154 papers that apply DL to EEG, published between January 2010 and July 2018, and spanning different application domains such as epilepsy, sleep, brain-computer interfacing, and cognitive and affective monitoring. We extract trends and highlight interesting approaches from this large body of literature in order to inform future research and formulate recommendations. Methods Major databases spanning the fields of science and engineering were queried to identify relevant studies published in scientific journals, conferences, and electronic preprint repositories. Various data items were extracted for each study pertaining to (1) the data, (2) the preprocessing methodology, (3) the DL design choices, (4) the results, and (5) the reproducibility of the experiments. These items were then analyzed one by one to uncover trends. Results Our analysis reveals that the amount of EEG data used across studies varies from less than ten minutes to thousands of hours, while the number of samples seen during training by a network varies from a few dozens to several millions, depending on how epochs are extracted. Interestingly, we saw that more than half the studies used publicly available data and that there has also been a clear shift from intra-subject to inter-subject approaches over the last few years. About [Formula: see text] of the studies used convolutional neural networks (CNNs), while [Formula: see text] used recurrent neural networks (RNNs), most often with a total of 3-10 layers. Moreover, almost one-half of the studies trained their models on raw or preprocessed EEG time series. Finally, the median gain in accuracy of DL approaches over traditional baselines was [Formula: see text] across all relevant studies. More importantly, however, we noticed studies often suffer from poor reproducibility: a majority of papers would be hard or impossible to reproduce given the unavailability of their data and code. Significance To help the community progress and share work more effectively, we provide a list of recommendations for future studies and emphasize the need for more reproducible research. We also make our summary table of DL and EEG papers available and invite authors of published work to contribute to it directly. A planned follow-up to this work will be an online public benchmarking portal listing reproducible results.