Aboul Ella Hassanien (Abo)

Support Vector Machine (SVM) is one of the widely used algorithms for classification and regression problems. In SVM, penalty parameter C and kernel parameters can have a significant impact on the complexity and performance of SVM. In this paper, an Optimal Foraging Algorithm (OFA) is proposed to optimize the main parameters of SVM and reduce the classification error. Six public benchmark datasets were employed for evaluating the proposed (OFA-SVM). Also, five well-known and recently optimization algorithms are used for evaluation. These algorithms are Artificial Bee Colony (ABC), Genetic Algorithm (GA), Chicken Swarm Optimization (CSO), Particle Swarm Optimization (PSO) and Bat Algorithm (BA). The experimental results show that the proposed OFA-SVM obtained superior results. Also, the results demonstrate the capability of the proposed OFA-SVM to find optimal values of SVM parameters.

Cluster analysis is a popular technique whose aim is to segregate a set of data points into groups, called clusters. Simulated Annealing (SA) is a popular meta-heuristic inspired by the annealing process used in metallurgy, useful in solving complex optimization problems. In this paper, the use of the Quantum Computing (QC) and SA is explored to design Quantum Inspired Simulated Annealing technique, which can be applied to compute optimum number of clusters for image clustering. Experimental results over a number of images endorse the effectiveness of the proposed technique pertaining to fitness value, convergence time, accuracy, robustness, and standard error. The paper also reports the computation results of a statistical superiority test, known as t-test. An experimental judgement to the classical technique has also be presented, which eventually demonstrates that the proposed technique outperforms the other.

The rapid increase in social networks data and users present an urgent need for predicting the performance of posted data over these networks. It helps in many industrial aspects such as election, public opinion detection and advertising or branding over social networks. This paper presents a new posts’ prediction system for Facebook’s branding pages concerning the user’s attention and interaction. CSO is utilized to optimize the ANFIS parameters for accurate prediction. CSO-ANFIS is compared with several methods including ANFIS, particle swarm optimization, genetic algorithm and krill herd optimization.

This paper presents a chaotic crow search algorithm (CCSA) for solving fractional optimization problems (FOPs). To refine the global convergence speed and enhance the exploration/exploitation tendencies, the proposed CCSA integrates chaos theory (CT) into the CSA. CT is introduced to tune the parameters of the standard CSA, yielding four variants, with the best chaotic variant being investigated. The performance of the proposed CCSA is validated on twenty well-known fractional benchmark problems. Moreover, it is validated on a fractional economic environmental power dispatch problem by attempting to minimize the ratio of total emissions to total fuel cost. Finally, the proposed CCSA is compared with the standard CSA, particle swarm optimization (PSO), firefly algorithm (FFA), dragonfly algorithm (DA) and grey wolf algorithm (GWA). Additionally, the efficiency of the proposed CCSA is justified using the non parametric Wilcoxon signed-rank test. The experimental results prove that the proposed CCSA outperforms other algorithms in terms of quality and reliability.

In today’s medical world, the patient’s data with symptoms and diseases are expanding rapidly, so that analysis of all factors with updated knowledge about symptoms and corresponding new treatment is merely not possible by medical experts. Hence, the essential for an intelligent system to reflect the different issues and recognize an appropriate model between the different parameters is evident. In recent decades, rough set theory (RST) has been broadly applied in various fields such as medicine, business, education, engineering and multimedia. In this study, a hybrid intelligent system that combines rough set (RST) and bijective soft set theory (BISO) to build a robust classifier model is proposed. The aim of the hybrid system is to exploit the advantages of the constituent components while eliminating their limitations. The resulting approach is thus able to handle data inconsistency in datasets through rough sets, while obtaining high classification accuracy based on prediction using bijective soft sets. Toward estimating the performance of the hybrid rough-bijective soft set (RBISO)-based classification approach, six benchmark medical datasets (Wisconsin breast cancer, liver disorder, hepatitis, Pima Indian diabetes, echocardiogram data and thyroid gland) from the UCI repository of machine learning databases are utilized. Experimental results, based on evaluation in terms of sensitivity, specificity and accuracy, are compared with other well-known classification methods, and the proposed algorithm provides an effective method for medical data classification.

This paper presents a hybrid algorithm based on using moth-flame optimization (MFO) algorithm with simulated annealing (SA), namely (SA-MFO). The proposed SA-MFO algorithm takes the advantages of both algorithms. It takes the ability to escape from local optima mechanism of SA and fast searching and learning mechanism for guiding the generation of candidate solutions of MFO. The proposed SA-MFO algorithm is applied on 23 unconstrained benchmark functions and four well-known constrained engineering problems. The experimental results show the superiority of the proposed algorithm. Moreover, the performance of SA-MFO is compared with well-known and recent meta-heuristic algorithms. The results show competitive results of SA-MFO concerning MFO and other meta-heuristic algorithms.

This work proposes a watermarking approach by utilizing the use of Bio-Inspired techniques such as swarm intelligent in optimizing watermarking algorithms for 3D models. In this proposed work we present an approach of 3D mesh model watermarking by introducing a new robust 3D mesh watermarking authentication methods by ensuring a minimal surface distortion at the same time ensuring a high robustness of extracted watermark. In order to achieve these requirements this work proposes the use of Particle Swarm Optimization (PSO) as Bio-Inspired optimization techniques. The experiments were executed using different sets of 3D models. In all experimental results we consider two important factors: imperceptibility and robustness. The experimental results show that the proposed approach yields a watermarked object with good visual definition; at the same time, the embedded watermark was robust against a wide variety of common attacks.

There are still many obstacles for achieving high recognition accuracy for Arabic handwritten optical character recognition system, each character has a different shape, as well as the similarities between characters. In this chapter, several feature selection-based bio-inspired optimization algorithms including Bat Algorithm, Grey Wolf Optimization, Whale optimization Algorithm, Particle Swarm Optimization and Genetic Algorithm have been presented and an application of Arabic handwritten characters recognition has been chosen to see their ability and accuracy to recognize Arabic characters. The experiments have been performed using a benchmark dataset, CENPARMI by k-Nearest neighbors, Linear Discriminant Analysis, and random forests. The achieved results show superior results for the selected features when comparing the classification accuracy for the selected features by the optimization algorithms with the whole feature set in terms of the classification accuracy and the processing time. The experiments have been performed using a benchmark dataset, CENPARMI by k-Nearest neighbors, Linear Discriminant Analysis, and random forests. The achieved results show superior results for the selected features when comparing the classification accuracy for the selected features by the optimization algorithms with the whole feature set in terms of the classification accuracy and the processing time.

Artificial neural network (ANN) models are involved in many applications because of its great computational capabilities. Training of multi-layer perceptron (MLP) is the most challenging problem during the network preparation. Many techniques have been introduced to alleviate this problem. Back-propagation algorithm is a powerful technique to train multilayer feedforward ANN. However, it suffers from the local minima drawback. Recently, meta-heuristic methods have introduced to train MLP like Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Cuckoo Search (CS), Ant Colony Optimizer (ACO), Social Spider Optimization (SSO), Evolutionary Strategy (ES) and Grey Wolf Optimization (GWO). This chapter applied Multi-Verse Optimizer (MVO) for MLP training. Seven datasets are used to show MVO capabilities as a promising trainer for multilayer perceptron. Comparisons with PSO, GA, SSO, ES, ACO and GWO proved that MVO outperforms all these algorithms.

Enzymes are important in our life and it plays a vital role in the most biological processes in the living organisms and such as metabolic pathways. The classification of enzyme functionality from a sequence, structure data or the extracted features remains a challenging task. Traditional experiments consume more time, efforts, and cost. On the other hand, an automated classification of the enzymes saves efforts, money and time. The aim of this chapter is to cover and reviews the different approaches, which developed and conducted to classify and predict the functions of the enzyme proteins in addition to the new trends and challenges that could be considered now and in the future. The chapter addresses the main three approaches which are used in the classification the function of enzymatic proteins and illustrated the mechanism, pros, cons, and examples for each one.

Alzheimer's disease (AD) is considered one of the most common dementia's forms affecting senior's age staring from 65 and over. The standard method for identifying AD are usually based on behavioral, neuropsychological and cognitive tests and sometimes followed by a brain scan. Advanced medical imagining modalities such as MRI and pattern recognition techniques are became good tools for predicting AD. In this chapter, an automatic AD diagnosis system from MRI images based on using machine learning tools is proposed. A bench mark dataset is used to evaluate the performance of the proposed system. The adopted dataset consists of 20 patients for each diagnosis case including cognitive impairment, Alzheimer's disease and normal. Several evaluation measurements are used to evaluate the robustness of the proposed diagnosis system. The experimental results reveal the good performance of the proposed system.

WSN as a new category of computer-based computing platforms and network structures is showing new applications in different areas such as environmental monitoring, health care and military applications. Although there are a lot of secure image processing schemas designed for image transmission over a network, the limited resources and the dynamic environment make it invisible to be used with Wireless Sensor Networks (WSNs). In addition, the current secure data transmission schemas in WSN are concentrated on the text data and are not applicable for image transmission's applications. Furthermore, secure image transmission is a big challenging issue in WSNs especially for the application that uses image as its main data such as military applications. The reason why is because the limited resources of the sensor nodes which are usually deployed in unattended environments. This chapter introduces a secure image processing and transmission schema in WSN using Elliptic Curve Cryptography (ECC) and Homomorphic Encryption (HE).

The most recent rise of telemetry is around the use of Radio-telemetry technology for tracking the traces of moving objects. Initially, the radio telemetry was first used in the 1960s for studying the behavior and ecology of wild animals. Nowadays, there's a wide spectrum application of can benefits from radio telemetry technology with tracking methods, such as path discovery, location prediction, movement behavior analysis, and so on. Accordingly, rapid advance of telemetry tracking system boosts the generation of large-scale trajectory data of tracking traces of moving objects. In this study, we survey various applications of trajectory data mining and review an extensive collection of existing trajectory data mining techniques to be used as a guideline for designing future trajectory data mining solutions.

Investigating information credibility is an important problem in online social networks such as Twitter. Since misleading information can get easily propagated in Twitter, ranking tweets according to their credibility can help to detect rumors and identify misinformation. In this paper, we propose a Petri net model to visualise tweet credibility in Twitter. We consider the uniform resource locator (URL) as an effective feature in evaluating tweet credibility since it is used to identify the source of tweets, especially for newsworthy tweets. We perform an experimental evaluation on about 1000 tweets, and show that the proposed model is effective for assigning tweets to two classes: credible and incredible tweets, which each class being further divided into two sub-classes (“credible” and “seem credible” and “doubtful” and “incredible” tweets, respectively) based on appropriate features.

Preserving the content of historic handwritten manuscripts is important for a variety of reasons. On the other hand, digital libraries are rapidly expanding and thus facilitate to store this information directly in digital form. For digitising text documents, a crucial step is to binarise the captured images to separate the text from the background. In this paper, we propose an effective approach for binarisation of handwritten Arabic manuscripts which employs a whale optimisation algorithm, incorporating a fuzzy c-means objective function, to obtain optimal thresholds. Experimental results confirm the effectiveness of the proposed approach compared to earlier methods.

For many decades, artificial neural network (ANN) proves successful results in thousands of problems in many disciplines. Back-propagation (BP) is one of the candidate algorithms to train ANN. Due to the way of BP to find the solution for the underlying problem, there is an important drawback of it, namely the stuck in local minima rather than the global one. Recent studies introduce meta-heuristic techniques to train ANN. The current work proposes a framework in which grey wolf optimizer (GWO) provides the initial solution to a BP ANN. Five datasets are used to benchmark GWO BP performance with other competitors. The first competitor is an optimized BP ANN based on genetic algorithm. The second is a BP ANN powered by particle swarm optimizer. The third is the BP algorithm itself and lastly a feedforward ANN enhanced by GWO. The carried experiments show that GWOBP outperforms the compared algorithms.

This paper presents a hybrid approach to an Automated Essay Grading System (AEGS) that provides automated grading and evaluation of student essays. The proposed system has two complementary components: Writing Features Analysis tools, which rely on natural language processing (NLP) techniques and neural network grading engine, which rely on a set of pre-graded essays to judge the student answer and assign a grade. By this way, students essays could be evaluated with a feedback that would improve their writing skills. The proposed system is evaluated using datasets from computer and information sciences college students' essays in Mansoura University. These datasets was written as part of mid-term exams in introduction to information systems course and Systems analysis and design course. The obtained results shows an agreement with teachers' grades in between 70% and nearly 90% with teachers' grades. This indicates that the proposed might be useful as a tool for automatic assessment of students' essays, thus leading to a considerable reduction in essay grading costs.

Optimal search is a major challenge for wrapper-based attribute reduction. Rough sets have been used with much success, but current hill-climbing rough set approaches to attribute reduction are insufficient for finding optimal solutions. In this paper, we propose an innovative use of an intelligent optimisation method, namely the flower search algorithm (FSA), with rough sets for attribute reduction. FSA is a relatively recent computational intelligence algorithm, which is inspired by the pollination process of flowers. For many applications, the attribute space, besides being very large, is also rough with many different local minima which makes it difficult to converge towards an optimal solution. FSA can adaptively search the attribute space for optimal attribute combinations that maximise a given fitness function, with the fitness function used in our work being rough set-based classification. Experimental results on various benchmark datasets from the UCI repository confirm our technique to perform well in comparison with competing methods.

Analytical prediction of oxidative stress biomarkers in ecosystem provides an expressive result for many stressors. These oxidative stress biomarkers including superoxide dismutase, glutathione peroxidase and catalase activity in fish liver tissue were analyzed within feeding different levels of selenium nanoparticles. Se-nanoparticles represent a salient defense mechanism in oxidative stress within certain limits; however, stress can be engendered from toxic levels of these nanoparticles. For instance, prediction of the level of pollution and/or stressors was elucidated to be improved with different levels of selenium nanoparticles using the bio-inspired Sine-Cosine algorithm (SCA). In this paper, we improved the prediction accuracy of liver enzymes of fish fed by nano-selenite by developing a neural network model based on SCA, that can train and update the weights and the biases of the network until reaching the optimum value. The performance of the proposed model is better and achieved more efficient than other models.