Showing papers by "Mohamed Elhoseny published in 2017"

Genetic algorithm based model for optimizing bank lending decisions

Abstract: The bank lending decisions in credit crunch environments are big challenge.This NP-hard optimization problem is solved using a proposed GA based model.The proposed model is tested using two scenarios with simulated and real data.The real data is collected from Southern Louisiana Credit Union.The proposed model increased the bank profit and improved the system performance. To avoid the complexity and time consumption of traditional statistical and mathematical programming, intelligent techniques have gained great attention in different financial research areas, especially in banking decisions optimization. However, choosing optimum bank lending decisions that maximize the bank profit in a credit crunch environment is still a big challenge. For that, this paper proposes an intelligent model based on the Genetic Algorithm (GA) to organize bank lending decisions in a highly competitive environment with a credit crunch constraint (GAMCC). GAMCC provides a framework to optimize bank objectives when constructing the loan portfolio, by maximizing the bank profit and minimizing the probability of bank default in a search for a dynamic lending decision. Compared to the state-of-the art methods, GAMCC is considered a better intelligent tool that enables banks to reduce the loan screening time by a range of 12%50%. Moreover, it greatly increases the bank profit by a range of 3.9%8.1%.

A Genetic Algorithm-Based, Dynamic Clustering Method Towards Improved WSN Longevity

Abstract: The dynamic nature of wireless sensor networks (WSNs) and numerous possible cluster configurations make searching for an optimal network structure on-the-fly an open challenge. To address this problem, we propose a genetic algorithm-based, self-organizing network clustering (GASONeC) method that provides a framework to dynamically optimize wireless sensor node clusters. In GASONeC, the residual energy, the expected energy expenditure, the distance to the base station, and the number of nodes in the vicinity are employed in search for an optimal, dynamic network structure. Balancing these factors is the key of organizing nodes into appropriate clusters and designating a surrogate node as cluster head. Compared to the state-of-the-art methods, GASONeC greatly extends the network life and the improvement up to 43.44 %. The node density greatly affects the network longevity. Due to the increased distance between nodes, the network life is usually shortened. In addition, when the base station is placed far from the sensor field, it is preferred that more clusters are formed to conserve energy. The overall average time of GASONeC is 0.58 s with a standard deviation of 0.05.

K -Coverage Model Based on Genetic Algorithm to Extend WSN Lifetime

Abstract: Currently, wireless sensor networks (WSNs) are extensively used in target monitoring applications. Classical target coverage methods often assume that the environment is perfectly known, and each target is covered by only one sensor. Such algorithms, however, are inflexible, especially if a sensor died, i.e., ran out of energy, and hence, a target may need to be covered by more than one sensor, which is known as the $K$ -coverage problem. The $K$ -coverage problem is a time and energy consuming process, and the organization between sensors is required all the time. To address this problem, this article proposes a $K$ -coverage model based on genetic algorithm to extend a WSN lifetime. In the search for the optimum active cover, different factors such as targets positions, the expected consumed energy, and coverage range of each sensor are taken into account. A set of experiments were conducted using different $K$ -coverage cases. Compared to some state-of-the-art methods, the proposed model improved the WSN's performance regarding to the amount of the consumed energy, the network lifetime, and the required time to switch between different covers.

Optimizing robot path in dynamic environments using Genetic Algorithm and Bezier Curve

Abstract: Robots have recently gained a great attention due to their potential to work in dynamic and complex environments with obstacles, which make searching for an optimum path on-the-fly an open challenge. To address this problem, this paper proposes a Genetic Algorithm (GA) based path planning method to work in a dynamic environment called GADPP. The proposed method uses Bezier Curve to refine the final path according to the control points identified by our GADPP. To update the path during its movement, the robot receives a signal from a Base Station (BS) based on the alerts that are periodically triggered by sensors. Compared to the state-of-the-art methods, GADPP improves the performance of robot based applications in terms of the path length, the smoothness of the path, and the required time to get the optimum path. The improvement ratio regarding the path length is between 6% and 48%. While the path smoothness is improved in the range of 8% and 52%. In addition, GADPP reduces the required time to get the optimum path by 6% up to 47%.

Dynamic Multi-hop Clustering in a Wireless Sensor Network: Performance Improvement

Abstract: A cluster-based model is preferable in wireless sensor network due to its ability to reduce energy consumption. However, managing the nodes inside the cluster in a dynamic environment is an open challenge. Selecting the cluster heads (CHs) is a cumbersome process that greatly affects the network performance. Although there are several studies that propose CH selection methods, most of them are not appropriate for a dynamic clustering environment. To avoid this problem, several methods were proposed based on intelligent algorithms such as fuzzy logic, genetic algorithm (GA), and neural networks. However, these algorithms work better within a single-hop clustering model framework, and the network lifetime constitutes a big issue in case of multi-hop clustering environments. This paper introduces a new CH selection method based on GA for both single-hop and the multi-hop cluster models. The proposed method is designed to meet the requirements of dynamic environments by electing the CH based on six main features, namely, (1) the remaining energy, (2) the consumed energy, (3) the number of nearby neighbors, (4) the energy aware distance, (5) the node vulnerability, and (6) the degree of mobility. We shall see how the corresponding results show that the proposed algorithm greatly extends the network lifetime.

Prediction of biochar yield using adaptive neuro-fuzzy inference system with particle swarm optimization

Abstract: This paper proposed an intelligent approach to predict the biochar yield. The biochar is an important renewable energy that produced from biomass thermochemical processes with yields that depend on different operating conditions. There are some approaches that are used to predict the production of biochar such as least square support vector machine. However, this approach suffers from some drawbacks such as get stuck in local point and high time complexity. In order to avoid these drawbacks, the adaptive neuro-fuzzy inference system approach is used and this approach is trained with a particle swarm optimization algorithm to improve the prediction performance of the biochar. Heating rate, pyrolysis temperature, Moisture content, holding time and sample mass were used as the input parameters and the outputs are biochar mass and biochar yield. The results show that the proposed approach is better than other approaches based on three measures the root mean square error, the coefficient of determination and average absolute percent relative error (0.2673, 0.9842 and 3.4529 respectively).

Social-spider optimization algorithm for improving ANFIS to predict biochar yield

Abstract: The production of renewable and sustainable energy has more attention because the traditional energy sources such as fossil fuel are decreasing dramatically. The prediction of biochar yield from manure pyrolysis is considered as one type of renewable energy that used to produce energy. However, the experimental methods that used to produce energy from biochar yield are time-consuming and expensive, therefore, computational methods are applied to solve this problem. There are many methods applied to predict the biochar like least square-support vector machine (LS-SVM) and neural network. However, these methods can get stuck in local point and time complexity. To avoid these drawbacks, this paper works to improve the Adaptive Neuro-Fuzzy Inference System (ANFIS) using Social-Spider Optimization algorithm to predict biochar yield. The results of the proposed method are compared to classic ANFIS, artificial bee colony, particle swarm optimization, and LS-SVM. The results of ANFIS-SSO approach outperformed the standard ANFIS and they are better than other approaches.

Equilibrium and uniform charge distribution of a classical two-dimensional system of point charges with hard-wall confinement

Abstract: We study the minimum energy equilibrium configurations of a classical two-dimensional system of point charges confined by a triangular, square and disk region with a hard-wall boundary. It is assumed that the point charges interact via a repulsive Coulomb interaction potential. Monte Carlo simulations with the annealing algorithm suggest that the equilibrium configurations of a given system are strongly influenced by the external (isotropic/anisotropic) geometry of the hard-wall boundary. The numerically obtained energies extrapolated in the bulk limit converge to the expected continuum equilibrium values (when known). It is found that the equilibrium charge distribution is non-uniform in the continuum limit for all the hard-wall confining regions considered in this work. Since the continuum equilibrium charge distribution is not known for the case of an equilateral triangle or a square domain we choose to compare the numerically obtained bulk energy results to corresponding values for a uniformly charged system. We calculated exactly the electrostatic energy of various uniformly charged planar objects and used the results to assess the discrepancy between such results and the numerically obtained equilibrium bulk energy values for the cases of equilateral triangle and square hard-wall boundaries. These estimates help us understand how an anisotropic boundary with the shape of an equilateral triangle or square influences the energy of an equilibrium charge distribution. The results indicate that the energy discrepancy between equilibrium and uniform charge distributions in the continuum limit is not very large. It is found that the order of magnitude of the relative deviation of the energy for all three different planar domains considered here is approximately the same.

Shareability of correlations in multiqubit states: Optimization of nonlocal monogamy inequalities

Abstract: It is a well-known fact that both quantum entanglement and nonlocality (implied by the violation of Bell inequalities) constitute quantum correlations that cannot be arbitrarily shared among subsystems. They are both monogamous, albeit in a different fashion. In the present contribution we focus on nonlocality monogamy relations such as the Toner-Verstraete, the Seevinck, and a derived monogamy inequality for three parties and compare them with multipartite nonlocality measures for the whole set of pure states distributed according to the Haar measure. In this numerical endeavor, we also see that, although monogamy relations for nonlocality cannot exist for more than three parties, in practice the exploration of the whole set of states for different numbers of qubits will return effective bounds on the maximum value of all bipartite Bell violations among subsystems. Hence, we shed light on the effective nonlocality monogamy bounds in the multiqubit case.

Quantified Self Using IoT Wearable Devices

Abstract: Nowadays, designing and developing wearable devices that could detect many types of diseases has become inevitable for E-health field. The decision-making of those wearable devices is done by various levels of analysis of enormous databases of human health records. Systems that demand a huge number of input data to decide to require real-time data collected from devices, processes, and analyzing the data. Many researchers utilize the Internet of Things (IoT) in medical wearable devices to detect different diseases by using different sensors together for one goal. The IoT promises to revolutionize the lifestyle using a wealth of new services, based on interactions between large numbers of devices data. The proposed work is human monitor system to track the human body troubles. Smart wearable devices can provide users with overall health data, and alerts from sensors to notify them on their mobile phones accordingly. The proposed system developed a technique using Internet of Things technique to decrease the load on IOT network and decrease the overall cost of the users. The simulation results proved that the proposed system could provide identical communication for IOT devices even if many nodes are used.

Intelligent Algorithms for Optimal Selection of Virtual Machine in Cloud Environment, Towards Enhance Healthcare Services

Abstract: Cloud computing plays a very important role in healthcare services (HCS). Cloud computing for HCS can restore patients’ records, diseases diagnosis and other medical domains in less time and less of cost. In cloud computing, optimally chosen of virtual machines (VMs) is very significant to interest in healthcare services (IHS) (patients, doctors, etc.) in HCS to implementation time and speed of response to medical requests. This paper proposes a new intelligent architecture for HCS. also, this paper proposes three intelligent algorithms are a genetic algorithm (GA), particle swarm optimization (PSO) and parallel particle swarm optimization (PPSO) to find optimal chosen of VMs in a cloud environment. For that, this paper uses MATLAB tool to find optimal intelligent algorithm and CloudSim to find optimal chosen of VMs in a cloud environment. The results proved that PPSO algorithm is better than GA and PSO algorithms.

Cascade Multimodal Biometric System Using Fingerprint and Iris Patterns

Abstract: Unimodal biometric systems based on single biometric trait do not often afford performance requirements for the security applications. Multimodal biometric system uses two or more biometric traits consolidated in one single system to identify users of the system. Among many biometrics traits, fingerprint and iris can accurately identify system’s users due to their unique textures which extracted during the recognition process. In this paper we proposed a multimodal biometric identification system that sequentially combines fingerprint and iris traits in the identification process. The proposed system design improves the user convenience by reducing the identification time and maintaining very high accuracy. The proposed system tested on CASIA-Iris V1 database and FVC 2000 and 2002 fingerprint database. The experimental results show that proposed multimodal system is better than unimodal system using fingerprint or iris.

Intelligent information system to ensure quality in higher education institutions, towards an automated e-university

Abstract: Despite great efforts to assure quality in higher education institutions, the ambiguity of its related concepts and requirements constitute a big challenge when trying to implement it as an intelligent information system. The present work introduces a framework for an intelligent information system that manages the quality assurance in higher education's institutions. The aim of designing such a system is to provide an automation tool that avoids unnecessary and redundant tasks associated to quality in higher education institutions. In addition, the proposed system helps all higher education stockholders to handle and monitor their tasks. Moreover, it aims to help the quality assurance units in a higher education institution to apply their quality's standards and to make sure that they are being maintained and enhanced. This information system contains a core module and 18 sub-modules, which are described in detail. Finally, the characteristics and components of each of these sub-modules are also discussed.

Autonomic Self-healing Approach to Eliminate Hardware Faults in Wireless Sensor Networks

Abstract: Recently, Wireless Sensor Networks (WSNs) are gained great attentions due to its ability to serve effectively in different applications. However, sensor nodes have energy and computational challenges. Moreover, WSNs may be prone to software failure, unreliable wireless connections, malicious attacks, and hardware faults; that make the network performance degrade significantly during its lifespan. One of these well-known challenges that affect the network performance is the fault tolerance. Therefore, this paper reviews this problem and provides a self-healing methodology to avoid these faults. Moreover, the structure and challenges of wireless sensor networks and the main concepts of self-healing for fault management in WSN are discussed. The results of the proposed method are illustrated to evaluate the network performance and measure its ability to avoid the network failure.

Secure Image Processing and Transmission Schema in Cluster-Based Wireless Sensor Network

Abstract: 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). Secure Image Processing and Transmission Schema in Cluster-Based Wireless Sensor Network

Equilibrium charge distribution on a finite straight one-dimensional wire

Abstract: The electrostatic properties of uniformly charged regular bodies are prominently discussed on college-level electromagnetism courses. However, one of the most basic problems of electrostatics that deals with how a continuous charge distribution reaches equilibrium is rarely mentioned at this level. In this work we revisit the problem of equilibrium charge distribution on a straight one-dimensional (1D) wire with finite length. The majority of existing treatments in the literature deal with the 1D wire as a limiting case of a higher-dimensional structure that can be treated analytically for a Coulomb interaction potential between point charges. Surprisingly, different models (for instance, an ellipsoid or a cylinder model) may lead to different results, thus there is even some ambiguity on whether the problem is well-posed. In this work we adopt a different approach where we do not start with any higher-dimensional body that reduces to a 1D wire in the appropriate limit. Instead, our starting point is the obvious one, a finite straight 1D wire that contains charge. However, the new tweak in the model is the assumption that point charges interact with each other via a non-Coulomb power-law interaction potential. This potential is well-behaved, allows exact analytical results and approaches the standard Coulomb interaction potential as a limit. The results originating from this approach suggest that the equilibrium charge distribution for a finite straight 1D wire is a uniform charge density when the power-law interaction potential approaches the Coulomb interaction potential as a suitable limit. We contrast such a finding to results obtained using a different regularised logarithmic interaction potential which allows exact treatment in 1D. The present self-contained material may be of interest to instructors teaching electromagnetism as well as students who will discover that simple-looking problems may sometimes pose important scientific challenges.

Ubiquitous smart learning system for smart cities

Abstract: This paper proposes a customized Ubiquitous smart Teaching and smart-Learning system that use Internet of Things (IoT), huge information, supercomputing, and profound figuring out how to give improved advancement, administration, and conveyance of instructing and learning in smart society settings. A proof of an idea is that framework has been created in light of the structure. A detailed, gritty outline, execution, and assessment of the smart learning framework, including its five parts, are given utilizing 11 utilized datasets.

A Proposed Architecture for Key Management Schema in Centralized Quantum Network

Abstract: Most existing realizations of quantum key distribution (QKD) are point-to-point systems with one source transferring to only one destination. Growth of these single-receiver systems has now achieved a reasonably sophisticated point. However, many communication systems operate in a point-to-multi-point (Multicast) configuration rather than in point-to-point mode, so it is crucial to demonstrate compatibility with this type of network in order to maximize the application range for QKD. Therefore, this chapter proposed architecture for implementing a multicast quantum key distribution Schema. The proposed architecture is designed as a Multicast Centralized Key Management Scheme Using Quantum Key Distribution and Classical Symmetric Encryption. In this architecture, a secured key generation and distribution solution has been proposed for a single host sending to two or more (N) receivers using centralized Quantum Multicast Key Distribution Centre and classical symmetric encryption. A Proposed Architecture for Key Management Schema in Centralized Quantum Network

Intelligent systems based on loud computing for healthcare services: a survey

Abstract: Cloud computing plays an important role in healthcare services (HCS) due to its the ability to retrieve patients' data, diagnosis of diseases and other medical fields in less time and less cost. This paper presents a survey of intelligent systems based on cloud environment for HCS. It reviews the uses of intelligent techniques such as genetic algorithm (GA), particle swarm optimisation (PSO) and parallel particle swarm optimisation (PPSO) on cloud computing environment to enhance task scheduling, reduce execution time of requests from stakeholders (patients, doctors, nurses, e.g.) and maximise of resources utilisation on clouds. This paper presents evaluation criteria of selected researches based on accuracy, usability, agility and applied method. Selected researches in this field were reviewed, analysed, summarised and compared according to the used intelligent techniques in cloud computing, healthcare systems and the concluded results. This paper also proposes architecture for intelligent healthcare systems based on cloud computing environment.

Quantum Secret Sharing in Noisy Environment

Abstract: As an unavoidable factor of real-world implementation of quantum cryptograph, quantum noise severally affects the security and reliability of the quantum system. In this paper, we study how QSS, an important branch of quantum cryptograph, is affected by noise or decoherence. QSS protocols for sharing classical information and quantum states are studied in four types of noise that usually encountered in real-world, i.e., the bit-flip, phase-flip (phase-damping), depolarizing and amplitude-damping noise, respectively. Two methods are introduced to evaluate the effect of noise. For the QSS protocol sharing classical information, the efficiency for generating secret key is used. Our results show that the efficiencies are quiet different from each other in four types of noise. While for the protocol sharing quantum states, the output states and the state-independent average fidelity are studied, respectively. It indicates that the players will get two different output states in the amplitude-damping noise, but get one output state in the other three types of noise. Besides, the state-independent average fidelity behaves differently from each other. Our study will be helpful for analyzing and improving quantum secure communications protocols in real-world.

Evaluating Learners’ Progress in Smart Learning Environment

Abstract: The advancement of innovations empowers learners to take in more viable, proficiently, adaptable and serenely. Smart learning, an idea that portrays learning in advanced age, has increased expanded consideration. This paper examines the meaning of Smart learning and shows an applied structure. The smart teaching method structure incorporates class-based separated direction [13], gather based communitarian learning, individual-based customized learning and mass-based generative learning. This paper proposes the Higher Particle Optimization (HPO) clustering as an instrument to trigger learning engagement activities. Utilizing (HPO), learners are clustered utilizing likeness measures construed from watched skill, meta-fitness, and certainty values, notwithstanding viability measures of instructional devices. A reenactment thinks about demonstrates that the (HPO)-based clustering is more ideal than Parallel M-implies grouping.

Arabic handwritten characters recognition system, towards improving its accuracy

Abstract: Although the extensive work towards building Optical Character Recognition systems(OCR) for Arabic handwritten characters, the unlimited variation and different writing styles of each character make building such these systems a big research challenge. In Arabic alphabetic system, each character has different forms (three or four) depending on its position in a word. In this paper, a handwritten character recognition system was proposed. The proposed system is implemented using a set of well-known optimizers, Bat Algorithm (BAT), Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and Grey Wolf Optimization (GWO) algorithm. The proposed system was tested by well-known classifiers to test the efficiency; linear discriminant analysis, support vector machines and random forest. Among all of them, GWO greatly improves the classification accuracy and time efficiency. Compared to the state-of-the-art methods, the optimized feature sets were efficient than the whole feature set in terms of accuracy as well as time consumption.

Self-organizing single-hop wireless sensor network using a genetic algorithm: Longer lifetimes and maximal throughputs

Abstract: In wireless sensor networks (WNSs), the network structure, which specifies how sensor nodes work, is greatly affects the network lifetime. To build the optimum network structure in cluster-based WSN may differs from round to round depending on a set of sensor nodes factors, i.e, remaining energy, vulnerability index, and the distance from BS. Getting the intended optimum structure is non trivial process, which includes determining the appropriate number of clusters, electing a cluster head (CH) for each cluster, and assigning each sensor node to a clusters. Recently, several studies propose CH selection protocols with predefined number of clusters. The present work introduces a new Genetic Algorithm (GA) based protocol that aims to get the optimum network structure for single-hop cluster model in WSN. This structure may differ after each round. The results show that the proposed GA-based method leads to more network lifetime and throughput. Also, it is more efficient in the context of a dynamic environment.

A New Model for Detecting Similarity in Arabic Documents

Abstract: With the hug of the information on WWW and digital libraries, Plagiarism became one of the most important issues for universities, schools and researcher’s fields. While there are many systems for detecting plagiarism in Arabic language documents, the complexity of writing Arabic documents make such scheme a big challenge. On the other hand, although search engines such as Google can be utilized, there would be boring efforts to copy some sentences and paste them into the search engine to find similar resources. For that reason, developing Arabic plagiarism detection tool accelerate the process since plagiarism can be detected and highlighted automatically, and one only needs to submit the document to the system. This paper presents an effective web-enabled system for Arabic plagiarism detection called APDS, which can be integrated with e-learning systems to judge students’ assignments, papers and dissertations. The experimental results are provided to evaluate APDS regarding the precision and recall ratios. The result shows that the average percentage of the precision is 82% and the average percentage of the recall is 92.5%.

Genetic Algorithm Based Model For Optimizing Bank Lending Decisions

Abstract: To avoid the complexity and time consumption of traditional statistical and mathematical programming, intelligent techniques have gained great attention in different financial research areas, especially in banking decisions’ optimization. However, choosing optimum bank lending decisions that maximize the bank profit in a credit crunch environment is still a big challenge. For that, this paper proposes an intelligent model based on the Genetic Algorithm (GA) to organize bank lending decisions in a highly competitive environment with a credit crunch constraint (GAMCC). GAMCC provides a framework to optimize bank objectives when constructing the loan portfolio, by maximizing the bank profit and minimizing the probability of bank default in a search for a dynamic lending decision. Compared to the state-of-the art methods, GAMCC is considered a better intelligent tool that enables banks to reduce the loan screening time by a range of 12% to 50%. Moreover, it greatly increases the bank profit by a range of 3.9% to 8.1%.

FPSS: Fingerprint-based semantic similarity detection in big data environment

Abstract: Although the problem of plagiarism is an ancient problem that exists before the start of internet revolution, the accessibility of free and easy accessed electronic paper on the Internet complicated and increased the problem. However, there are many systems for detecting plagiarism in natural language documents. Contrary to Latin documents, the same Arabic letter can be written into three various ways based on its position in the word. The complex nature of writing Arabic documents makes such system is a big challenge. Accordingly, this paper presents a Fingerprint-Based Semantic Similarity detection system, called (FPSS) to detect plagiarism in Arabic documents. It generates a digital fingerprint (df) for each sentence and compares all the df values. Moreover, it analyzes corresponding detection schemes to detect Semantic Similarity effectively. FPSS improves the effectiveness regarding the matched similarity ratio, the precision ratio, the recall ratio, the F-measure ratio, the plagdet ratio, and the granularity ratio.