Showing papers by "Aly A. Fahmy published in 2018"

Hybrid Grasshopper Optimization Algorithm and Support Vector Machines for Automatic Seizure Detection in EEG Signals

Abstract: In this paper, a hybrid classification model using Grasshopper Optimization Algorithm (GOA) and support vector machines (SVMs) for automatic seizure detection in EEG is proposed called GOA-SVM approach Various parameters were extracted and employed as the features to train the SVM with radial basis function (RBF) kernel function (SVM-RBF) classifiers GOA was used for selecting the effective feature subset and the optimal settings of SVMs parameters in order to obtain a successful EEG classification The experimental results confirmed that the proposed GOA-SVM approach, able to detect epileptic and could thus further enhance the diagnosis of epilepsy with accuracy 100% for normal subject data versus epileptic data Furthermore, the proposed approach has been compared with Particle Swarm Optimization (PSO) with support vector machines (PSO-SVMs) and SVM using RBF kernel function The computational results reveal that GOA-SVM approach achieved better classification accuracy outperforms both PSO-SVM and typical SVMs

Automatic Short Answer Scoring based on Paragraph Embeddings

Abstract: Automatic scoring systems for students’ short answers can eliminate from instructors the burden of grading large number of test questions and facilitate performing even more assessments during lectures especially when number of students is large. This paper presents a supervised learning approach for short answer automatic scoring based on paragraph embeddings. We review significant deep learning based models for generating paragraph embeddings and present a detailed empirical study of how the choice of paragraph embedding model influences accuracy in the task of automatic scoring.

Using Functional Dependencies in Conversion of Relational Databases to Graph Databases

Abstract: Graph database management systems are widely used in scenarios where the data are intensively connected. Handling such connected data in a relational database is not an efficient task. Converting relational databases to graph ones is one of the solutions that can empower users with handling such data using the graph model features. In this paper, we propose a new algorithm to ease such conversion and overcome the limitations of the existing algorithms. The state of the art algorithms cannot handle multiple relationships types such as unary relationships and associative entities with non-foreign key attributes. Our proposed algorithm, FD2G, leverages the existence of functional dependencies information inside the input relational database to automatically perform the conversion to property graph databases. In addition, we updated the state of the art algorithm, named R2G, to handle its limitations and be able to fairly compare both algorithms performance. We evaluated FD2G against the updated R2G algorithm where it efficiently and effectively outperformed the existing one.

Detection of Mass Panic using Internet of Things and Machine Learning

Abstract: The increase of emergency situations that cause mass panic in mass gatherings, such as terrorist attacks, random shooting, stampede, and fires, sheds light on the fact that advancements in technology should contribute in timely detecting and reporting serious crowd abnormal behaviour. The new paradigm of the ‘Internet of Things’ (IoT) can contribute to that. In this study, a method for real-time detection of abnormal crowd behaviour in mass gatherings is proposed. This system is based on advanced wireless connections, wearable sensors and machine learning technologies. It is a new crowdsourcing approach that considers humans themselves as the surveillance devices that exist everywhere. A sufficient number of the event’s attendees are supposed to wear an electronic wristband which contains a heart rate sensor, motion sensors and an assisted-GPS, and has a wireless connection. It detects the abnormal behaviour by detecting heart rate increase and abnormal motion. Due to the unavailability of public bio-dataset on mass panic, dataset of this study was collected from 89 subjects wearing the above-mentioned wristband and generating 1054 data samples. Two types of data collected were: firstly, the data of normal daily activities and secondly, the data of abnormal activities resembling the behaviour of escape panic. Moreover, another abnormal dataset was synthetically generated to simulate panic with limited motion. In our proposed approach, two-phases of data analysis are done. Phase-I is a deep machine learning model that was used to analyze the sensors’ collected readings of the wristband and detect if the person has indeed panicked in order to send alerting signals. While phase-II data analysis takes place in the monitoring server that receives the alerting signals to conclude if it is a mass panic incident or a false positive case. Our experiments demonstrate that the proposed system can offer a reliable, accurate, and fast solution for panic detection. This experiment uses the Hajj pilgrimage as a case study.

Sheep identity recognition, age and weight estimation datasets

Abstract: Increased interest of scientists, producers and consumers in sheep identification has been stimulated by the dramatic increase in population and the urge to increase productivity. The world population is expected to exceed 9.6 million in 2050. For this reason, awareness is raised towards the necessity of effective livestock production. Sheep is considered as one of the main of food resources. Most of the research now is directed towards developing real time applications that facilitate sheep identification for breed management and gathering related information like weight and age. Weight and age are key matrices in assessing the effectiveness of production. For this reason, visual analysis proved recently its significant success over other approaches. Visual analysis techniques need enough images for testing and study completion. For this reason, collecting sheep images database is a vital step to fulfill such objective. We provide here datasets for testing and comparing such algorithms which are under development. Our collected dataset consists of 416 color images for different features of sheep in different postures. Images were collected fifty two sheep at a range of year from three months to six years. For each sheep, two images were captured for both sides of the body, two images for both sides of the face, one image from the top view, one image for the hip and one image for the teeth. The collected images cover different illumination, quality levels and angle of rotation. The allocated data set can be used to test sheep identification, weigh estimation, and age detection algorithms. Such algorithms are crucial for disease management, animal assessment and ownership.

A hybrid automated detection of epileptic seizures in EEG based on wavelet and machine learning techniques

Abstract: Epilepsy is a neurological condition such that it affects the brain and the nervous system. It is characterized by recurrent seizures, which are physical reactions to sudden, usually brief, excessive electrical discharges in a group of brain cells. Hence, seizure identification has great importance in clinical therapy of epileptic patients. Electroencephalogram (EEG) is one of the main biomarker that can measure voltage fluctuations of the brain and EEG data analysis helps to investigate the patient with epilepsy syndrome as epilepsy leaves their signature in EEG signals. In this paper, the Discrete Wavelet Transform (DWT) is applied to EEG signals to pre-processing, decompose it till the 4th level of decomposition tree.Various features like Entropy, Min, Max, Mean, Median, Standard deviation, Variance, Skewness, Energy and Relative Wave Energy (RWE) were computed in terms of detailed coefficients and the approximation coefficients of the last decomposition level.Then, the extracted features are evaluated by three modern machine-learning classifiers such as Radial Basis Function based Support Vector Machine (SVMRBF), k-Nearest Neighbor (KNN) and Naive Bayes (NB). The experimental results demonstrate that the highest classification accuracy (100\%) for normal subject data versus epileptic data is obtained by SVMRBF. the corresponding accuracy between normal subject data and epileptic data using KNN and NB is obtained as 99.50\% and 99\% for the eyes open and eyes closed conditions, respectively. The similar accuracies, while comparing the interictal and ictal data, are obtained as 99\%, 97.50\% and 98.50\% using the SVMRBF, KNN and NB classifiers, respectively. These accuracies are quite higher than earlier results published.

Automatic Sheep Weight Estimation Based on K-Means Clustering and Multiple Linear Regression

Abstract: Using a balance to estimate sheep’s weight is inefficient and time consuming Sheep’s weight also fluctuates with many factors such as pregnancy, lactation, and gut fill However, linear measurements are not highly affected by such type of factors Therefore, in this paper, sheep weight was determined by calculating linear measurements from sheep images using visual analysis techniques The system starts, followed by applying the K-means clustering for sheep segmentation Then, biggest blob detection along with morphological analysis take place After that breadth and width of sheep are extracted Weight is then estimated from the linear dimensions using a regression function learned from the data-set In the experiments, sheep weight estimation was tested on data set of 104 side images for 52 sheep For performance evaluation, R-squared was measured and it reached 099 High accuracy of 9875% was also achieved

Conditional Text Paraphrasing: A Survey and Taxonomy

Abstract: This work introduces a survey for the Text Para-phrasing task. The survey covers the different types of tasks around text paraphrasing and mentions the techniques and models that are regularly used when approaching towards it, alongside the datasets that are used while training and evaluating the models. Text paraphrasing has an effective impact when it is used in other applications, so, the paper mentions some text paraphrasing applications. Also, this work proposes a new taxonomy that it is called Conditional Text Paraphrasing. To the best of our knowledge, this is the first work that shows varieties and sub-problems of the original text paraphrasing task. The target of this taxonomy is to expand the definition of the text paraphrasing by adding some conditional constraints as features that either control the paraphrase generation or discrimination. This expanded definition opens in mind a new domain for research in Natural Language Processing (NLP) and Machine Learning. Finally, some useful applications for the conditional text paraphrasing are represented.