Amr Badr

Genome banks contain precious biological information that is mostly not discovered yet. Biologists in turn are keen to precisely explore these banks in order to discover effective patterns (such as motifs and retro-transposons) that have a real impact on the function and evolution of living creatures. Because the modern genome sequencing technologies produce genomes in high throughputs, many techniques have emerged to store genomes in the lowest possible space. Reference-based Compression algorithms (RbCs) efficiently compress the sequenced genomes by mainly storing their differences with respect to a reference genome. Therefore, RbCs give very high compression ratios compared to the traditional compression algorithms. However, in order to search a compressed genome for specific patterns, it has to be totally decompressed, wasting both time and storage. This paper introduces searching for either exact or incomplete patterns inside the referentially compressed genomes without their complete decompression. The introduced search methodolgy is based on instantly searching subsequent sequences that are partially decompressed from the compressed genome. Moreover, the same search process is allowed to simultaneously search for multiple patterns, thus saving more resources. The experimental results showed noticeable performance gains compared to traditionally searching the same compressed genomes after their complete referential decompression.

Membrane Computing (P Systems) is an emergent and promising branch of Natural Computing. Designing P Systems is a heavy difficult problem. Until now there is no tool exists that can help in designing of P systems. This book shows how to use clonal selection algorithm with adaptive mutation in the design of P systems. In Addition the book proposes a Membrane-Immune algorithm that is inspired from the structure of living cells and the vertebrate immune system. The algorithm is tested by solving the Multiple Zero/One Knapsack Problem. The Membrane-Immune algorithm surpassed two variants of genetic algorithms that solved the same problem. The Membrane-Immune algorithm is also applied to generate a fuzzy rule based system to be used in breast cancer diagnosis. Generating a fuzzy rule system composes an exponential search space, which leads to the area of NP-complete problems. The algorithm is compared with five techniques and surpassed them. Last chapter presents a proposal of P Systems implementation using Cloud Computing. The proposed Implementation is illustrated by solving SAT problem.

Particle Swarm Optimization used to solve a continuous problem and has been shown to perform well however, binary version still has some problems. In order to solve these problems a new technique called New Binary Particle Swarm Optimization using Immunity-Clonal Algorithm (NPSOCLA) is proposed This Algorithm proposes a new updating strategy to update the position vector in Binary Particle Swarm Optimization (BPSO), which further combined with Immunity-Clonal Algorithm to improve the optimization ability. To investigate the performance of the new algorithm, the multidimensional 0/1 knapsack problems are used as a test benchmarks. The experiment results demonstrate that the New Binary Particle Swarm Optimization with Immunity Clonal Algorithm, found the optimum solution for 53 of the 58 multidimensional 0/1knapsack problems.

Clustering is a primary method for DB mining. The clustering process becomes very challenge when the data is different densities, different sizes, different shapes, or has noise and outlier. Many existing algorithms are designed to find clusters. But, these algorithms lack to discover clusters of different shapes, densities and sizes. This paper presents a new algorithm called DBCLUM which is an extension of DBSCAN to discover clusters based on density. DBSCAN can discover clusters with arbitrary shapes. But, fail to discover different-density clusters or adjacent clusters. DBCLUM is developed to overcome these problems. DBCLUM discovers clusters individually then merges them if they are density similar and joined. By this concept, DBCLUM can discover different-densities clusters and adjacent clusters. Experiments revealed that DBCLUM is able to discover adjacent clusters and different-densities clusters and DBCLUM is faster than DBSCAN with speed up ranges from 11% to 52%.

Membrane Computing (MC) (or P System theory) is a recent area of Natural Computing, the field of computer science that deals with computational techniques is inspired by the structure and functioning of living cells. P systems are massively parallel and distributed model of computation. Membrane Computing investigates models of computation inspired by the structure and functions of biological cells. There are some simulations models that have been developed but do not usually allow parallelism. Turing Machine (TM) and membrane computing are computation models; one of the main differences between them is the behavior of each other, since TM is algorithmic behavior while on the other hand Transition P Systems are Interactive computing behavior. This research investigates a Turing machine model of a special class of P system under a condition which is the rules are applied in a predefined order (which is applying rules priority). From this point of view, the P Systems could assume the same behavior of Turing machine in its sequential behavior. A single membrane can be considered as a machine (membrane devices) in the membrane structure of transition P Systems; hence the whole system of membrane structure consists of several machines that interact with each other. The interaction can be in the form of data passing. The aim of this research is designing a TM to simulate the behavior of a Transition P System. Also the research will show how Turing Machine can be partitioned into sub machines as well as the design of membrane machines can be partitioned into sub machines or sub modules.

Cuckoo search is a nature-inspired metaheuristic algorithm, based on the brood parasitism of some cuckoo species, along with Lévy flights random walks. In this paper, a modified version is proposed, where the new solutions generated from the exploration and exploitation phases are combined, evaluated and ranked together, rather than separately in the original algorithm, in addition to imposing a bound by best solutions mechanism to help improve convergence rate and performance. The proposed algorithm was tested on a set of ten standard benchmark functions, and applied to a real-world problem of algorithmic trading systems optimization in the financial markets. Experimental analysis demonstrated improved performance in almost all benchmark functions and the problem under study.

A P system is a computability model which is biochemically inspired, it is a general distributed model, highly parallel, nondeterministic, based on the notion of a membrane structure. Till this moment, there is no exact idea about the real implementation of P systems. P systems are used in solving NP-complete problems in polynomial time, but with building the whole exponential search space. Cloud computing assume infinite memory and infinite processing power. This paper proposes an algorithm that uses the cloud resources in a fully parallel manner as a step towards P systems implementation, the nondeterminism property of P systems is certainly not maintained. The paper used the SAT problem as the case study.

Ontology matching is generally defined as the process of finding correspondences between entities of different ontologies. It can help the data integration between autonomous agents, web services composition, and P2P information sharing. This process is applied through the use of ontology matching tools which use one or more ontology matching techniques. This paper presents tools which have been published in this field, such as Prompt [7], Smatch [5] and Ontobuilder [16]. Moreover the paper illustrates the drawbacks of these tools. New two tools are proposed to handle these drawbacks. The new proposed and other tools are tested using GlycO [8]and EnzyO[10] in the biochemistry field, Osteoarthritis and Rheumatoid in the medical field.

Server Virtualization is a growing trend in almost all the critical IT infrastructures
all over the world. Apart from the cost savings involved with such approach, it is even useful
in increasing the infrastructure operational efficiency as it speeds up the operation

One of successful approaches for object localization and recognition is sliding window approach where different candidate windows are found and evaluated and the best window is selected to represent the object. To avoid exhaustive search over all windows locations, Efficient Sub-window Search (ESS) [1] algorithm were proposed to efficiently find the best window among all sub-windows using branch and bound technique. In case of multi-class multiple object detection problems, such methods are time consuming. To handle this issue, efficient multi-object detection approach is proposed based on image superpixelization We utilize image superpixels in 2 points. (a) Such preprocessing stage is done once for an image, hence multiple detections could be fast. (b) We observe that image superpixels could help in identifying the promising candidate sub-windows, hence evaluating all sub-windows could be avoided. An efficient brute force sub-window search algorithm is proposed based on these observations. Moreover, for improving its performance, the algorithm is integrated with ESS algorithm. The proposed algorithms are assessed on the PASCAL 2006 and PASCAL 2007 test-set and show that they are faster than the state-of-the art sub-window search algorithms, while achieving a comparable performance comparing with them.

A P system is a computability model which is biochemically inspired, it is a general distributed model, highly parallel, nondeterministic, based on the notion of a membrane structure. Till this moment, there is no exact idea about the real implementation of P systems. P systems are used in solving NP-complete problems in polynomial time, but with building the whole exponential search space. Cloud computing assume infinite memory and infinite processing power. This paper proposes an algorithm that uses the cloud resources in a fully parallel manner as a step towards P systems implementation, the nondeterminism property of P systems is certainly not maintained. The paper used the SAT problem as the case study.

This paper presents an application of supervised machine learning approaches to the classification of the colon cancer gene expression data. Established feature selection techniques based on principal component analysis (PCA), independent component analysis (ICA), genetic algorithm (GA) and support vector machine (SVM) are, for the first time, applied to this data set to support learning and classification. Different classifiers are implemented to investigate the impact of combining feature selection and classification methods. Learning classifiers implemented include K-Nearest Neighbors (KNN) and support vector machine. Results of comparative studies are provided, demonstrating that effective feature selection is essential to the development of classifiers intended for use in high dimension domains. This research also shows that feature selection helps increase computational efficiency while improving classification accuracy.

Cellular Genetic Algorithms) CGAs are a subclass of Genetic Algorithms (GAS) it enhanced the population diversity and exploration in which the tentative solutions thanks to the existence of small overlapped neighborhoods .It well suited for complex problems as one of structured algorithms .The study was conducted on the behavior of these algorithms has been Performed in terms of quality of solutions exist, at the time of implementation, And a number of function evaluations effort. We have chosen the benchmark Augerat et al. Set A, Augerat et al. Set B and Augerat et al. Set P to test (cellular genetic algorithm)
And compared with some other GAS. We have deceived that CGAs are capable of Always find optimal to the problem in a few times and reasonable.

Identification of major histocompatibility complex binding peptides is an important step in the selection of T-Cell epitope candidates suitable for usage in new vaccines.The binding groove of the MHC Class-II molecule is opened at both sides, which allows for high variability in length of the peptides that bind to this molecule and consequently complicates the prediction of the binding core motif. An accurate and efficient computational approach for the prediction of such peptides can greatly reduce the time and cost required for the design of new vaccines for infectious diseases and cancers. We have developed EpiGASVM, a new approach for the in silico prediction of MHC Class-II epitopes, by combining two artificial intelligence techniques namely: evolutionary algorithms and support vector machines. We have applied nine variations of EpiGASVM to a dataset of similarity-reduced benchmark data and we have calculated the prediction accuracy and the area under the receiver operating characteristic curve as measures of performance.The results indicate that EpiGASVM is a promising new technique that could provide researchers with a new tool for the in silico selection of candidate peptides that can be used in rational vaccine design.

The automatic diagnosis of breast cancer is an important medical problem. This paper hybridizes metaphors from cells membranes and intercommunication between compartments with clonal selection principle together with fuzzy logic to produce a fuzzy rule system in order to be used in diagnosis. The fuzzy-membrane-immune algorithm suggested were implemented and tested on the Wisconsin breast cancer diagnosis (WBCD) problem. The developed solution scheme is compared with five previous works based on neural networks and genetic algorithms. The algorithm surpasses all of them. There are two motivations for using fuzzy rules with the membrane-immune algorithm in the underline problem. The first is attaining high classification performance. The second is the possibility of attributing a confidence measure (degree of benignity or malignancy) to the output diagnosis, beside the simplicity of the diagnosis system, which means that the system is human interpretable.

Major Histocompatibility complex (MHC) molecules play an essential role in introducing and regulation immune system. The MHC molecules are divided into two classes, class I and class II which are differ in size of their binding pockets. Determining which peptides bind to a specific MHC molecule is fundamental to understanding the basis of immunity, and for the development of vaccines and immunotherapeutic for autoimmune diseases and cancer. Due to the variability of the locations of the class II binding cores, the process for predicting the affinity of these peptides is difficult.This paper investigates a new method for predicting peptides binding to MHC class II molecules and its affinity using genetic algorithms and metaheuristics. The algorithm is based on a fitness function that builds a scoring matrix for all suggested motifs in a specific iteration to test the motif ability to be one of the real motifs in the nature. The genetic algorithmpresented here shows increased prediction accuracy with higher number of true positives and negatives on almost of MHC class II alleles,about 80 percent of peptides were correctly classified when testing dataset from IEDB[26]. Generally, these results indicate that GA has a strong ability for MHC Class II binding prediction.

A Turing machine (TM) can be adapted to simulate the logic of any computer algorithm, and is particularly useful in explaining the functions of a CPU inside a computer. Membrane computing aims to develop models and paradigms that are biologically motivated. It identifies an unconventional computing model, namely a P system, which abstracts from the way living cells process chemical compounds in their compartmental structure. These systems are a class of distributed systems, maximally parallel computing devices of a biochemical type. In this research, the research tries investigating a new view to show Membrane computing is a multi TM that communicate with each other. The main idea is that each membrane is a TM itself and each TM can communicate with other TM through communication channels under the structure of membranes (tree membranes structure) where membrane (TM) can send and receive string (multiset) to or from other membrane (TM). This TM is a TM with three tapes.

In this paper a membrane-immune algorithm is proposed,which is inspired from the structure of living cells and the vertebrate immune system. The algorithm is used to solve one of the most famous combinatorial NP-complete problems, namely the Multiple Zero/One Knapsack Problem. Various heuristics, like genetic algorithms, have been devised to solve this class of combinatorial problems. The proposed algorithm is compared with two genetic based algorithms and overcame both of them. The algorithm is evaluated on nine benchmarks test problems and surpassed both of the genetic based algorithms in six problems, equaled with one of them in two problems and lost in one problem, which indicates that our algorithm surpasses in general genetic algorithms. We claim that the proposed algorithm is very useful in solving similar combinatorial NP-complete problems.

Ontology is generally defined as an explicit specification of conceptualization
which involves the exploration of concepts and its relationships in the domain of interest.
Ontology is used to share knowledge across semantic web services, agents and ..

A new variant of P Systems is considered, a rough p system which discussed before as an open problem. The proposed rough p system definition is based on boundary rules and on conditional communication, where communication is controlled by the contents of the strings not by the evolution rules for obtaining these strings.