Proceedings of the International Conference on Advanced Intelligent Systems and Informatics 2018

A forced convective pulsating flow of the air and magnetic field effect on the thermoelectric cooler performance is experimentally investigated. The experimental tests are conducted at a constant flow rate with Reynolds number of 5871. The applied electric power, magnetic field, pulsation rate and the output temperatures for both TEC sides are recorded and manipulated to evaluate the coefficient of the performance (COP) of the TEC. The obtained temperature differences are between 5.56 °C and 19.8 °C. TEC’s COPc ranges from 0.122 to 0.277. The optimum COP of 0.277 during these experimental tests occurred at 52.247 W input power, magnetic field of 1.25 T, and 41.28 Womersley number. Comparing with Fuzzy logic results it shows a good agreement (T; Tesla).

Infusion Stand is one of the medical supportive tools in the field of biomedical that assist in holding and carrying medications to patients via intravenous injections. Mobilization of Infusion Stand from a place to another place is necessary not only for the patients itself but also for the nurses. Therefore, this leads to not only uneasiness but also inconvenience for both parties. Therefore, to improve the existing situation and current Infusion Stand in the market, a proposal to design and implement a prototypic Robotic Infusion Stand is submitted. In this paper, 2-Degree of Freedom Proportional Integral Derivative (2-DOF PID) controller is proposed for Robotic Infusion Stand after comparison between 1-Degree of Freedom Proportional Integral Derivative (1-DOF PID) to find the most suitable controller. Analysis of reference tracking, disturbance rejection and controller effort are performed which demonstrate the ability of the proposed approach within the system parameters.

This paper aims to two main goals, first goal is to achieve the characterization of quality control of ultrasound scanners based on the potential image metrics. On the other hand, the most effective goal is how to classify ultrasound scanners based on image metrics to evaluate performance of ultrasound transducer. The authors utilize the metrics to give information about the spatial arrangement of the gray levels in the specific interest region. The execution of ultrasound images metric based on a set of 19 metrics (i.e. contrast, gradient and Laplacian). This set reflects quality control of ultrasound scanners. The wok of this paper based on the best 6 metrics from 19 metrics which extracted from linear discriminative analysis (LDA). The classification methods used for minimum numbers of metrics are fused using support vector machine (SVM) and the highest classification method is back propagation neural network (BPNN) classifiers to get the main target of paper. Finally, the results show that objective performance evaluation of ultrasound transducer accuracy was 100% by using back propagation neural network classifier.

This article presents performance evaluation and comparison between Voltage Oriented Control (VOC) methods for PWM-rectifiers, two levels and three levels, in order to demonstrate the great advantages of using a three-level Neutral Point Clamped (NPC). The control of the DC bus voltage is carried out using the PI controller. The effectiveness of this approach is illustrated by simulation results using MATLAB/Simulink.

Chaos theory deals with the behavior of dynamical systems that are highly sensitive to initial conditions. Chaotic systems are characterized by the property that small changes in the initial conditions result in widely diverging responses. In this paper, new control schemes of synchronization for different arbitrary incommensurate and commensurate fractional order chaotic systems are presented. Synchronization stability, based on stability of linear fractional-order systems and fractional Lyapunov stability, is proved theoretically. Numerical examples are given to show the effectiveness of the proposed method.

This paper represents the control of a two-wheel self-balancing robot based on the theory of controlling the inverted pendulum. This paper dividing the system modeling into two main parts. The first part is the dc motor and the second part are the whole mechanical design and its characteristics as a function in the motor speed and the torque depending on the system, creating two control closed loops inner and outer. The study uses conventional proportional–integral–derivative (PID) and two degree of freedom PID controllers to obtain a robust controller for the system. The inner loop controls the motor speed use the motor speed feedback signal from the encoder. The outer loop keeps the robot always in the accepted vertical angle boundary, using a six-degree of freedom gyroscope and accelerometer as a feedback signal. A state space model is obtained considering some assumptions and simplifications. The results are verified through simulations and experiments. Numerical simulation results indicate that the 2-DOF PID controller is superior to the traditional PID controller.

In this paper a novel strategy for the position control and trajectory tracking of robotic manipulators is proposed. This strategy consists of an independent two degree of freedom PID controller for a two links robotic arm. Due to the capability of two degree of freedom PID controllers to deal with disturbances, each link is controlled independently considering that the disturbance does not affect the system performance due to the robustness of the closed loop system. Then, a fuzzy type-2 centralized compensator is implemented to drive the orientation variables with the desired trajectory in order to improve the robustness and system performance. In this work, it is proved that the two degree of freedom fractional order PID controllers implemented with the fuzzy type-2 compensator improves the system performance in comparison with the results found in other studies, and one important issue is that the fuzzy type-2 system can be considered as a linear system emulating the capabilities of a linear compensator. To corroborate the theoretical results explained in this study, a numerical example is shown along with the respective discussion and conclusions.

This paper presents the contribution of a fuzzy controller to compensate the influence of stator resistance variation which can degrade the performance and stability of a direct torque control (DTC). Nevertheless, the original term DTC refers to a strategy that provides good performance, but it also has some negative aspects to the level of switching and inaccuracy in the engine model which recommends the use of a new technique the SVM which proposes an algorithm based on the modulation of the space vector in order to carry out a predictive regulation of the torque and flux of the induction motor and provides a fixed switching frequency, thus improving the dynamic response and the static behavior of the DTC.

Autonomous navigation is an important feature that allows the robot to move independently from a point to another without a teleoperator. In this paper, an investigation related to mobile robot navigation is presented. A group of supervised classification algorithms are tested and validated using the same dataset. Then focus will shift especially towards the k-Nearest Neighbors (KNN) algorithm. In order to improve the performance of KNN, an existing work related to genetic algorithms, local search, and Condensed Nearest Neighbors termed Memetic Controlled Local Search algorithm (MCLS) is applied to overcome the high running time of KNN. The results indicate that KNN is a competing algorithm especially after decreasing the running time significantly and combining that with existing algorithm features.

This paper presents a new hybrid chaos synchronization scheme, which assures the co-existence of the full-state hybrid function projective synchronization (FSHFPS) and the inverse full-state hybrid function projective synchronization (IFSHFPS) between wide classes of three-dimensional master systems and four-dimensional slave systems. In order to show the capability of co-existence approach, numerical example is reported, which illustrates the co-existence of FSHFPS and IFSHFPS between 3D chaotic system and 4D hyperchaotic system in different dimensions.

The scope of this proposed system is to implement multi-sensor robot architecture. The reduction of the human activities in hospital environment is the main target of utilizing the self-governing portable robots in numerous applications. The executed robot is a self-governing four wheels system that is designed to determine the sound level, light intensity, humidity and high temperature then transmitting data to a remote location and visualized in mobile application. Bluetooth connection is established between the Arduino on the robot and the smart phone. The smart phone acts as the manual controller which is responsible for directing the robot and receive data from Arduino. The Arduino navigates the robot based on the feedbacks from ultrasonic sensor to detect the barriers.

One of the main problems that face Motor Imagery-based system is addressing multi-class problem. Various approaches have been used to tackle this problem. Most of these approaches tend to divide multi-class problem into binary sub problems. This study aims to address the multi-class problem by comparing five multi-class approaches; One-vs-One (OVO), One-vs-Rest (OVR), Divide & Conquer (DC), Binary Hierarchy (BH), and Multi-class approaches. Renyi entropy was examined for feature extraction. Three linear classifiers were used to implement these five-approaches: Support Vector Machine (SVM), Multinomial Logistic Regression (MLR) and Linear Discriminant Analysis (LDA). These approaches were compared according to their performance and time consumption. The comparative results show that, Renyi entropy demonstrated its robustness not only as a feature extraction technique but also as a powerful dimension reduction technique, for multi-class problem. In addition, LDA proved to be the best classifier for almost all approaches with minimum execution time.

Cardiovascular diseases are one of the leading causes of death. Globally, they underlie the death of one third of the world’s population. The main cause of cardiovascular diseases is atherosclerosis which makes arteries less elastic (called ‘‘hardening of the arteries” or ‘‘arterial stiffness’’). The optical Micro Electro Mechanical System (MEMS) pressure sensor has shown its potential in the diagnosis of arterial stiffness that can be conducted by detecting the pulse pressure in the radial artery. In this paper, we attempt to improve the sensitivity of micro-diaphragm deflection in optical Micro-electromechanical System (MEMS) sensors as applied to pulse pressure detection, thus aiming to determine the safety of a person’s measured pulse of cardiovascular disease. The deflection sensitivity improvement was evidenced using Finite Element Analysis ANSYS software. Corrugation for periphery-clamped silicon nitride (Si₃N₄) micro-diaphragm based on the variation of the diaphragm thickness (t_d) and some corrugation factors such as the corrugation angle (β) and the corrugation depth (h_c) was implemented to reduce bending and tensile stresses which limit the micro-diaphragm deflection sensitivity. This was supported by calculating the von Mises stress. Analytic results show agreement with ANSYS software simulation with a static response of 1.27 μm maximum deflection under applied pressure of 300 mmHg in the case of the corrugated micro-diaphragm, compared to a 0.32 μm maximum deflection in the case of a flat micro-diaphragm, and for the same applied pressure, a maximum deflection sensitivity of 4.23 × 10−3 μm/mmHg for the corrugated micro-diaphragm compared to 1.07 × 10−3 μm/mmHg for the flat one, and the reduction of micro-diaphragm bending and initial tensile stresses exhibited by maximum equivalent stress (von Mises stress) of 159.99 MPa for the corrugated compared to 175.9 MPa for the flat one. Therefore, the implementation of corrugation presents the chance to control mechanical deflection sensitivity and compared to the film deposition process control it is often an easier way.

The motor vehicle industry has shown a mechatronics system with intelligent control systems. Mechatronics refers to a successful combination of mechanical and electronic systems. In mechatronics, traditional systems of mechanical engineering are combined together with components from computer science, mathematics and electrical engineering. This paper presents enhancing an active suspension for a quarter car model to improve its performance by applying a specific controller. Separating a vehicle’s body from road abnormalities is the major purpose of a suspension system, in order to provide the maximum ride comfort for passengers and keep hold of continuous road wheel contact to provide road holding. First controller applied is fuzzy logic controller (FLC), and the second one is a Linear Quadratic Regulator, the car’s behaviour such as car body displacement, suspension deflection, and wheel travel is considered to obtain maximum damping force in the actuator. A comparative study has been verified to get the best performance for comfort of passenger ride and road managing.

In this paper, learning with a teacher artificial neural network to predict the results of football matches is presented. This type of networks requires training via examples, and when the training is complete, the network can be tested to check the results of new examples. In this application, the training examples are the results of previous matches which the network will use to predict the results of new ones.

Machine Learning (ML) is the process of extracting knowledge from current information to enable machine to predict new information based on the learned knowledge. Many ML algorithms aim at improving the learning process. Support vector machine (SVM) is one of the best classifiers for hyper-spectral images. As many of the ML algorithms, SVM training require a high computational cost that considered a very large quadratic programming optimization problem. The proposed sequential minimal optimization solve the highly computational problems using a hybrid parallel model that employs both graphical processing unit to implement binary-classifier and message passing interface to solve multi-class on “one-against-one” method. Our hybrid implementation achieves a speed up of 40X over the sequential (LIBSVM), a speed up of 7.5X over the CUDA-OPENMP for training dataset of 44442 records and 102 features size for 9 classes and a speed up of 13.7X over LIBSVM in classification process for 60300 records.

Alzheimer’s Disease is a serious form of dementia. With no current cure, treatments focus on slowing the progression of the disease and controlling its symptoms. Early diagnosis by studying the biomarkers found in structural MRI is the key. This paper proposes a method which combines texture features extracted from gray level co-occurrence matrix and voxel-based morphometry neuroimaging analysis to classify Alzheimer’s disease patients. Different supervised classification techniques are studied, support vector machine, k-nearest neighbor, and decision tree, to obtain best identification accuracy. The paper explores as well the discriminative power for Alzheimer’s disease of certain anatomical regions of interest. The proposed technique is applied on gray matter tissues, and managed successfully to differentiate between Alzheimer’s disease patients and normal controls with accuracy 92%.

Genomic variation in DNA can cause many types of human cancer so the machine learning has important role in genomic medicine it can help to classify, predict and analysis of DNA sequence. Which is the most important biological characteristic? DNA copy number variations (CNVs) used to understand the difference between different human cancers and predict cancer causing from genetic sequence. But it’s not easy due to the high dimensionality of the CNV features. This paper presents approach to computationally classify a set of human cancer types. We use machine learning to train and test various models on set of human cancer using the CNV level values of 23,082 genes (features) for 2916 instances to construct the classifier. Then the genes are selected according to their importance by the filter feature selection method. We compare the performance of seven classifiers Support vector Machine, Random Forest, j48, Neural Network, Logistic Regression, Bagging and Dagging with other benchmark using 10-fold cross validation. The best performance achieved accuracy value 0.859 and ROC value 0.965 which are promising results. The classification models developed in this research could provide a reasonable prediction of the cancer patients’ stage based on their CNV level values. The proposed model confirmed that genes from chromosome 3 have in developing human cancers. It also predicted new genes not studied so far as important ones for the prediction of human cancers.

The paper describes a methodology for selecting relevant fuzzy implications in forward and backward reasoning. The proposed methodology is based on the functional representation of fuzzy implications and dependencies between fuzzy implications. This can be useful for the design of an inference engine based on the rule knowledge for a given rule-based system.

It has become common, especially among urban youth, for people to use more than one language in their everyday conversations - a phenomenon referred to by linguists as “code-switching”. With the rise in globalization and the widespread of code-switching among multilingual societies, a great demand has been placed on Natural Language Processing (NLP) applications to be able to handle such mixed data. In this paper, we present our efforts in language modeling for code-switch Arabic-English. In order to train a language model (LM), huge amounts of text data is required in the respective language. However, the main challenge faced in language modeling for code-switch languages, is the lack of available data. In this paper, we propose an approach to artificially generate code-switch Arabic-English n-grams and thus improve the language model. This was done by expanding the relatively-small available corpus and its corresponding n-grams using translation-based approaches. The final LM achieved relative improvements in both perplexity and OOV rates of 1.97% and 16.36% respectively.

Sentiment resources are essential components for developing applications for Sentiment Analysis (SA). Common publicly available datasets such as products, restaurants and movies reviews usually fulfil the researchers needs in order to conduct their experiments. However, for specific domains, the needed dataset sources could be difficult to find. This signifies the need to construct domain specific datasets and lexicons which are vital to evaluate SA tasks. In this paper, we present the work that has been done in order to produce a unique dataset that consists of government smart apps domain aspects and opinion words. Additionally, we explain the approach that was carried out to measure the sentiment scores to opinion words and build the desired lexicons. A general-purpose data annotation and preparation tool was developed for facilitating the development of SA lexical resources and dataset for government smart apps domain.

Recently, the use of word embeddings has become one of the most significant advancements in natural language processing (NLP). In this paper, we compared two word embedding models for aspect-based sentiment analysis (ABSA) of Arabic tweets. The ABSA problem was formulated as a two step process of aspect detection followed by sentiment polarity classification of the detected aspects. The compared embeddings models include fastText Arabic Wikipedia and AraVec-Web, both available as pre-trained models. Our corpus consisted of 5K airline service related tweets in Arabic, manually labeled for ABSA with imbalanced aspect categories. For classification, we used a support vector machine classifier for both, aspect detection, and sentiment polarity classification. Our results indicated that fastText Arabic Wikipedia word embeddings performed slightly better than AraVec-Web.

A segmentation tool for a hadith corpus is necessary to prepare the TEI hadith encoding process. In this context, we aim to develop a tool allowing the segmentation of hadith text from Sahih al-Bukhari corpus. To achieve this objective, we start by identifying different hadith structures. Then, we elaborate an automatic processing tool for hadith segmentation. This tool will be integrated in a prototype allowing the TEI encoding process. The experimentation and the evaluation of this tool are based on Sahih al-Bukhari corpus. The obtained results were encouraging despite some flaws related to exceptional cases of hadith structure.

The growth of electronically readable Arabic content available on the web has become a rich source from which to build new corpora or update the existing ones. The availability of such corpora will be beneficial for Arabic corpus linguistics, computational linguistics, and natural language processing. In this paper, we present ARARSS, a tool capable of automatically constructing and updating textual corpora benefiting from the Rich Site Summary (RSS) feeds. ARARSS is capable of collecting the texts in a properly categorized manner according to user needs, in addition to their metadata (for example, location, time, and topic) as provided by RSS sources. We used ARARSS to construct a modern standard Arabic corpus comprising 117,819 texts and more than 28 million words. ARARSS is an open source tool and freely available to download (http://corpus.kacst.edu.sa/more_info.jsp) along with the constructed corpus.

Face recognition systems are progressively becoming popular as means of determining the people’s identities. Moreover, face images are the only biometric trait that can be found in legacy databases and international terrorist watch-lists and can be taken without the need to the cooperation of subjects. In this paper, we present an effective face recognition system that consists of a set of steps: image preprocessing in which the person’s face is detected and the median filter is applied for noise removal, feature extraction using Gabor filters, feature reduction using principle component analysis, feature selection using the grey wolf optimization (GWO) algorithm, and classification using k-NN classifier. The proposed system has been evaluated using Yale face database. The experimental results have revealed that the proposed system can achieve recognition accuracy up to 97%. Also, the performance of the proposed system is compared to the performance of other face recognition system and the obtained results have revealed that the proposed system is better in terms of both recognition accuracy and run time.

Shredded document reconstruction problem has gained more attention in the last few years. The reconstruction process is commonly involved in forensics, investigation sciences, and reconstruction of destroyed archaeological papyrus and manuscripts. Exhaustive search is common for handling such problem for small dimensions but with higher dimension, the problem becomes worse. Recently, a bio-inspired grey wolf optimizer (GWO) is a great algorithm for solving continuous problem but the nature of Shredded document reconstruction is a discrete problem, so a discrete version of GWO has been proposed and applied to it, This paper also proposed a general simple fitness function that can handle both text and image-based documents.

Bird Swarm Algorithm (BSA) is a relatively new meta-heuristic optimization algorithm introduced to solve optimization problems. Birds have three types of conducts including searching for food (foraging), watchfulness (vigilance), and flying conduct. Foraging and vigilance behaviours are done by birds to improve their positions (exploitation) while flight behaviour is done to move from one location to another (exploration). This paper combines the chaotic-based methods with foraging and vigilance behaviours to improve the exploitation quality. The main privilege of chaotic-based methods is their capability for avoiding local minima. In order to assess the proposed chaotic BSA (CBSA) algorithm, a set of 7 unimodal benchmark functions are tested with ten different chaotic maps. The numerical results show that the performance of CBSA, with most of the chaotic maps, can clearly outperform the standard BSA.

This paper proposed spherical local search (SLS) for solving unconstrained optimization problems in three dimensions. The algorithm begins with a randomly chosen point in the search domain. Then, spherical trust region around this point is defined by the radius of SLS; where any point in this region is feasible. Finally, SLS can move from current search point to obtain a new best point by using three strategies of search: radius, azimuth, and inclination. These strategies are modified during the search process. SLS is tested on the set of the CEC’2005 special session on real parameter optimization. Results show the robustness and effectiveness of the proposed method.

This paper presents an swarm optimization approach based on flower pollination optimization algorithm for multilevel thresholding by the criteria of Otsu minimizes the weighted within-class variance to make the optimal thresholding more effective. An application of microscopic white blood cell imaging has been chosen and the proposed approach has been applied to see their ability and accuracy to segment and count the blood cells. An adaptive watershed segmentation algorithm was applied that depends on a mask created from the required microscopic image to detect the minima points for segmenting the overlapped cells. The cell counting process depends on labeling the connected regions of the segmented binary image and count the labeled cells. The proposed approach archives promised results with respect to quality measures of accuracy, peak to signal-to-noise ratio (PSNR) and the root mean square error (RMSE) on microscopic images. Experimental results are recorded for the proposed approach over ten selected different images with accuracy of 98.4% that present better accuracy over the manual traditional techniques.

Automated citation classification has received much attention in recent years from the research community. It has many benefits in the bibliometric field such as improving the methods of measuring publications’ quality and productivity of the researchers. Most of the existing approaches are based on supervised learning techniques with discrete manual features to capture linguistic cues. Though these approaches have reported good results, extracting such features are time-consuming and may fail to encode the semantic meaning of the citation sentences, which consequently limits the classification performance. In this paper, a hybrid neural model is proposed, which combines convolutional and recurrent neural networks to capture local n-gram features and long-term dependencies of the text. The proposed model extracts the features automatically and classifies the sentiments and purposes of scientific citations. We conduct experiments using two publicly available datasets and the results show that our model outperforms previously reported results in terms of precision, recall, and F-score for citation classification.

Sentiment analysis and emotion recognition are major indicators of society trends toward certain topics. Analyzing opinions and feelings helps improving the human-computer interaction in several fields ranging from opinion mining to psychological concerns. This paper proposes a deep learning model for emotion detection from short informal sentences. The model consists of three Convolutional Neural Networks (CNNs). Each CNN contains a convolutional layer and a max-pooling layer, followed by a fully-connected layer for classifying the sentences into positive or negative. The model employs the word vector representation as textual features, which works on random initialization for the word vectors, and are set to be trainable and updated through the model training phase. Eventually, task-specific vectors are generated as the model learns to distinguish the meaning of words in the dataset. The model has been tested on the Stanford Twitter Sentiment dataset for classifying sentiment into two classes positive and negative. The presented model achieved to record 80.6% accuracy as a prove that even with randomly initialized word vectors, it can work very well in text classification tasks when trained with CNNs.

In this paper, a system for aquarium family fish species identification is proposed. It identifies eight family fish species along with 191 sub-species. The proposed system is built using deep convolutional neural networks (CNN). It consists of four layers, two convolutional and two fully connected layers. A comparative result is presented against other CNN architectures such as AlexNet and VggNet according to four parameters (number of convolution and fully connected layers, the number of epochs in training phase to achieve 100% accuracy, validation accuracy, and testing accuracy). Through the paper, it is proven that the proposed system has competitive results against the other architectures. It achieved 85.59% testing accuracy while AlexNet achieves 85.41% over untrained benchmark dataset. Moreover, the proposed system has less trained images, less memory, less computational complexity in training, validation, and testing phases.

Due to the necessity of high availability for Cloud Systems, most organizations need cloud services which minimize system down-time. Virtual Machine (VM) Migration is a simple solution for what is called a Hot-Spot or highly utilized PM. Live Migrating VMs allows migration of VMs while they are running their applications with no shutdown or down-time. Therefore, it provides Hot-Spot relieve, helps in Business Continuity, and provides a high available system. In this paper, an adaptive migration scheme (AMS) is proposed in order to preserve the system’s load balance state. It considers migrating VMs in groups, where each group includes a number of VMs increases from two to a maximum concurrent limit. AMS provides a way to find a maximum concurrent limit for the number of migrated VMs to be used to enhance the migration process. AMS is applied on a real case study. Two metrics are used to evaluate the improvements in migrations; concurrent time reduction and transfer rate improvement. The experimental results show that AMS achieves a time reduction percentage reaches 44%. This percentage is increased proportionally with the increasing of used memory. In addition, the migrated memory transfer rate is improved by a ratio ranges from 27% to 86%.

With growing awareness and concerns in regards to cloud computing and information security with privacy protection, there is a need to increase a usage of security algorithms into data systems and processes. Homomorphic Encryption (HE) is the encryption scheme which accepts encrypted inputs and performs blind processing to achieve data confidentiality. HE is useful to transfer encrypted data in public area as it allows operations on the cipher text, which can provide the same results after calculations as working directly on raw data. In this paper, a Fully Homomorphic Encryption (FHE) system based on Advanced Encryption Standard (AES) is proposed. It can be applied to perform operations on encrypted data without decryption. The proposed scheme solves the problem of large cipher text usually associated with increased noise resulting from FHE usage.

Nowadays, large amounts of high resolution remote-sensing images are acquired daily. However, the satellite image classification is requested for many applications such as modern city planning, agriculture and environmental monitoring. Many researchers introduce and discuss this domain but still, the sufficient and optimum degree has not been reached yet. Hence, this article focuses on evaluating the available and public remote-sensing datasets and common different techniques used for satellite image classification. The existing remote-sensing classification methods are categorized into four main categories according to the features they use: manually feature-based methods, unsupervised feature learning methods, supervised feature learning methods, and object-based methods. In recent years, there has been an extensive popularity of supervised deep learning methods in various remote-sensing applications, such as geospatial object detection and land use scene classification. Thus, the experiments, in this article, carried out on one of the popular deep learning models, Convolution Neural Networks (CNNs), precisely AlexNet architecture on a standard sounded dataset, UC-Merceed Land Use. Finally, a comparison with other different techniques is introduced.

Online reviews have become one of the most important sources of customers’ opinions. These reviews influence potential purchasers to make or reverse decisions. Unfortunately, the existence of profit and publicity has emerged fake reviews to promote or demote some target products. Furthermore, reviews are generally imprecise and uncertain. So, it is a difficult task to uncover fake reviews from the genuine ones. In this paper, we propose a fake reviews detection method using the belief function theory. This method deals with the uncertainty in the given rating reviews and takes into account the similarity with other provided votes to detect misleading. We propose numerical examples to intuitively evaluate our method. Then, to prove its performance, we conducted on a real database. Experimentation shows that the proposed method is a valuable solution for the fake reviews detection problem.

In a cancelable iris recognition technique, all enrollment patterns are masked using a transformation function, and the invertibility for obtaining the original data should not be possible. This paper presents an approach for mixing multi-biometric features based on Double Random Phase Encryption (DRPE) to obtain a single protected IrisCode from different IrisCodes based on the Fractional Fourier Transform (FrFT). For the IrisCode generation, two encryption keys (RPM1 and RPM2) are utilized. The RPM2 is suggested to be the right iris feature vector of the same user. As a result, this feature level mixing of two different templates highly increases privacy and slightly enhances performance compared to its original counterpart. This proposed system achieves a high success rate in identification due to the fact that the iris authentication issue has been transformed to a key authentication process.

Due to the great improvement of technology, the representation of the data in three dimensions widely used in many applications like scientific visualization, manufacturing, computer vision, engineering design, virtual reality, architectural walk through, and video gaming. The 3D objects consist of a huge number of components like thousands of vertices and faces, and that make researchers to detect the more interest components to deal with this objects instead of to deal with the whole object that for many applications like a watermark, and mesh simplification. This paper presents a model to detect the interest points of the object using k mean clustering algorithm depend on the curvature areas. The proposed model is applied to a set of benchmark data of 3D mesh models. The evaluation of the proposed model is verified using three evaluation measures, namely False Positive, False Negative Errors, and Weighted Miss Error. The evaluation is also verified by comparing the proposed model with the most popular interest point detecting techniques.

Cloud computing is widely used by many users, so any one must be authenticated before accessing any service into the cloud. In this paper, a two-factor authentication scheme is proposed to authenticate users in cloud computing. The first factor uses the traditional user name and password, while the second factor uses one time password, which is valid for only one login session or transaction. During the registration phase, user must choose a user name and a password in addition to specify 4 cells from a 3 × 3 grid to use its containing characters when logging into the system. At the login phase, the user inputs his user name and password then, a grid with random numbers is displayed to him, and he must input the sequence of characters chosen during the registration phase. These characters represent the one time password which is changed every login. The results show that the proposed scheme can resist practical attacks, easy for users, does not have strong constrains, and does not require specific extra hardware.

Recently, intensive research efforts are conducted on the human ear as a promising biometric modality for identity recognition. However, one of the main challenges facing ear recognition systems is to find robust representation for the image information that is invariant to different imaging variations. Recent studies indicate that using the distribution of local intensity gradients or edge directions can better discriminate the shape and appearance of objects. Moreover, gradient-based features are robust to global and local intensity variations as well as noise and geometric transformation of images. This paper presents an ear biometric recognition approach based on the gradient-based features. To this end, four local feature extractors are investigated, namely: Histogram of Oriented Gradients (HOG), Weber Local Descriptor (WLD), Local Directional Patterns (LDP), and Local Optimal Oriented Patterns (LOOP). Extensive experiments are conducted for both identification and verification using the publicly available IIT Delhi-I, IIT Delhi-II, and AMI ear databases. The obtained results are encouraging, where the LOOP features excel in all cases achieving recognition rates of approximately 97%.

Recently, Internet of Things (IoT) is increasing pervasively, permits the unattended objects to be connected securely among themselves allowing highly classified processed data to be controlled. WSN has the most significant attention since transferring data is the most security challenge of the IoT environment. As well as, the previous messages which might be intercepted causing the established session key to be revealed. To mitigate such an attack, a lot of schemes were proposed, with an allegation of high efficient security features were achieved and powerful resilience against various attacks. After prudent studies have been made, we found that multiple proposed schemes do not support all the security requirements and are susceptible to some security attacks. In this paper, we propose a secure mutual authentication scheme with perfect forward-secrecy for WSN. Likewise, provides resilience against various types of known attacks in WSNs. Finally, the security of proposed scheme is proven.

This paper is addressing the personal identification problem by using mobile-based keystroke dynamics of touch mobile phone. The proposed approach consists of two main phases, namely feature selection and classification. The most important features are selected using Genetic Algorithm (GA). Moreover, Bagging classifier used the selected features to identify persons by matching the features of the unknown person with the labeled features. The outputs of all Bagging classifiers are fused to determine the final decision. In this experiment, a keystroke dynamics database for touch mobile phones is used. The database, which consists of four sets of features, is collected from 51 individuals and consists of 985 samples collected from males and females with different ages. The results of the proposed model conclude that the third subset of features achieved the best accuracy while the second subset achieved the worst accuracy. Moreover, the fusion of all classifiers of all ensembles will improve the accuracy and achieved results better than the individual classifiers and individual ensembles.

One of the important revolutionary tools widely used and globally implemented by educational institutes and universities is none other than the electronic learning (E-learning system). The aim of this system is to deliver education. As a result, the users of an E-learning system can have enormous benefits. The developed countries are successfully implementing the E-learning system besides realization of its massive benefits. On the contrary, the developing countries have failed, either fully or partially, to implement the E-learning system. A main reason is that those countries do not have an absolute utilization and considered below the satisfactory level. For instance, in United Arab Emirate, one of the developing countries, a growing number of universities are investing for many years in E-learning systems in order to enhance the quality of student education. However, their utilization among students has not fulfilled the satisfactory level. Imagine the evidence that the behavior of user is mainly required for the successful use of these web-based tools, investigating the unified theory of acceptance and use of technology (UTAUT) of E-learning system used in practical education is the basic aim of this research study. A survey on E-learning usage among 280 students was conducted and by using the given responses, the assumptions of the research resulting from this model have been practically validated. The partial least square method was employed to examine these responses. In predicting a student’s intention to use E-learning, the UTAUT model was strongly corroborated by the obtained results. In addition, the findings reveal that all important factors of behavioral intention to use E-learning system were reportedly found as the social influence, performance expectancy and facilitating conditions of learning. Remarkably, a significant impact on student intention towards E-learning system was not suggested by the effort expectancy. Consequently, The three key factors leading to successful E-Learning system are thought to be the good perception and encouraging university policy.

This paper employs the Technology Acceptance Model (TAM) to study the adoption of E-book amongst higher-education students in a well-known academic institute in the UAE, where E-book was being implemented. Computer self-efficacy, confirmation, innovativeness, satisfaction, and subjective norm are the five factors that this model embarks on to realize the influence on the university students as a result of the adoption of the E-book. This study was conducted among 350 university students through a survey which has used the quantitative evaluation to gain the optimum advantage from the subjective methods. The hypotheses were analyzed, and the model was assessed with the help of the statistical package for Structural Equation Modeling (SEM). The main findings that can be derived from the existing study are the factors that have positive impact on students’ perceived ease of use and perceived usefulness of E-book. They are computer self-efficacy, confirmation, innovativeness, and subjective norm. As a result, it is imperative for legislators and managers of E-book applications to concentrate on the factors that are critical for encouraging learning and enhancing students’ efficiency in developing and executing successful E-book applications.

This paper presents a predictive model of sperm quality based on personal lifestyle and environmental factors. Predicting the fertility based on measuring the quality of sperm is an urgent research problem since the fertility rates have been decreased mostly in men. Infertility is the biggest problem which faces the married persons. A lot of tests are expensive and time-consuming. Hence, these tests are not suitable for evaluating the quality of sperm; as a consequence, there is a need for implementing computational models that can predict the quality of sperm. The proposed model consists of two stages. In the first stage, Neutrosophic Rule-based Classification System (NRCS) and genetic NRCS (GNRCS) are proposed to classify an unknown seminal quality into normal or abnormal. NRCS and GNRCS forecast fertility based on nine input parameters which cover person lifestyle. The NRCS and GNRCS models were compared with three well-known classifiers such as decision trees, Support Vector Machines and Multilayer Perceptron with quality measures of GM, sensitivity, specificity, and accuracy. The proposed model (GNRCS) achieved promising results of 98.03% accuracy while basic NRCS achieved 95.55% accuracy. In the second stage, three different sampling algorithms are used to obtain balanced data.

In order to obtain the optical tradition of the satellite path, traditional orbital elements must be obtained. In recent years, models and simulation of spacecraft have been developed. The aim of this research paper is to demonstrate the detailed reliability and adequacy of simulations, which can be obtained using cable or neutral factors rather than the Cartesian’ coordinates accordingly to the state-consistent pattern of the spacecraft. The solid body pattern of the Multibody’s standard library is expanded by adding equations that determine the centre of the body’s transformation of cluster coordinates from Keplerian variables to Cartesian coordinates, and by assigning identified cases. The remaining parts of the model, including the gravitational field pattern, are left intact, ensuring a severe reuse of the system. The results shown in the paper show the super-precision and the calculation of the six elements in the case of reference to the gravitational field of the cluster point and the strong visualization of satellite tracking.

How to extract more knowledge from a complex information system is a hot issue in the big data era. Attribute reduction, as an effective method in rough set theory, is widely used for knowledge acquirement. In this paper, a novel positive region based parallel multi-reduction algorithm (POSMR) is proposed. Two strategies that for simplifying decision tables and computing the attribute importance are introduced based on MapReduce mechanism at first. And a non-core attribute replacement strategy based on positive region is employed to obtain multi-reduction. The experimental results conducted on UCI Datasets show the algorithm proposed in this paper can obtain multi-reduction correctly, and it is superior to the the binary discernibility matrix based parallel multi-reduction algorithm (BDMR) and traditional single-reduction algorithm.

In this paper, a proposed system for automatic counting and visual multi-tracking for human sperm in microscopic video frames is presented. It can be easily turned into a commercial computer-assisted sperm analysis (CASA) system. CASA systems help in detecting infertility in human sperm according to clinical parameters. The proposed system consists of nine phases and it counts sperm in every single frame of video in real time and calculates the average sperm count through the whole video with accuracy 94.3% if it is compared to the manual counting. Also, it tracks all identified sperm in video frames in real time. It works with different frame rates above 15 frame/s to track visually the movements of the sperm. The dataset consists of three high-quality 1080p videos with different frame rates and durations. Finally, the open challenging research points are addressed.

In this paper, a new approach for Arabian horse identification is represented base on bag of feature algorithm. This approach is based on three phases, the first is the extract bag of feature process which use speed up robust feature (SURF) to extract the features of muzzle print images then using K-mean cluster and histogram to extract features. The second phase is train support vector machine (SVM) classification which trains the features with its labels. Finally the SVM testing phase, the bag of feature is extracted from the input images and test SVM model to match the images with its labels. Arabian horse is correct identified if it matched to its label and if it matched to one of the other horse’s labels, the horse not identified. We represent results for the approach for different SVM kernels at different cluster number. The results demonstrate that SVM with polynomial kernel achieve height accuracy 95.4% compare to other kernels.

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 0.99. High accuracy of 98.75% was also achieved.

Sustainability development has become widely applied specially when considering construction projects as a result of the huge leap in the global urbanization rates. Researchers are continuously attempting to find accurate and reliable sustainability construction performance measures. However, the majority of these researches focus on studying the sustainability in a single construction project, although it might be worthwhile studying sustainability in multiple construction projects in order to maximize the overall sustainability. In this paper, the authors developed a simulation optimization model using simulated annealing for scheduling the different phases in their right sequence of multi-construction projects while maximizing the overall sustainability. The previous is done while assessing the sustainability development and simulating the effect of external factors such as technological advancement and change in people’s perception on sustainability measures. Results showed that considering scheduling in multi-construction projects increased the overall sustainability performance compared to unscheduled ones.

This study presents the development of artificial neural network (ANN) and support vector machine (SVM) classification models for predicting the safety conditions of water in distribution pipes. The study was based on 504 monthly records of water quality parameters; pH, turbidity, color and bacteria counts taken from nine different locations across the water distribution network in the city of Ålesund, Norway. The models predicted the safety conditions of the water samples in the pipes with 98% accuracy and 94% respectively during testing. The high accuracy achieved in the model results indicate that contamination events in distribution systems that result in unsafe values of the water quality parameters can be detected using these classification models. This can provide water utility managers with real time information about the safety conditions of treated water at different locations of distribution pipes before water reaches consumers.

Nowadays, in the diversifying economic environment, investors need various ways to help them in taking the right decisions and maximize their returns within certain acceptable risk. This research paper incorporates data mining clustering techniques to assist investors in constructing a balanced portfolio in Abu Dhabi Securities Exchange (ADX). The study examines and analyses ADX trade market history for the year of 2015. An extensive analysis has been done for various combinations of pre-processing-clustering algorithm techniques. An unexpected conclusion was revealed from this research. It is believed that small markets such as Abu Dhabi’s require different “clustering” treatment than the commonly applied ones for established markets such as New York Stock Exchange.

Communication between mobile clients and database servers in wireless environment suffers from; the user’s movement, disconnected modes, lots of data updates, low battery power, cache size limitation, and bandwidth limitation. Caching is used in wireless environment to overcome these challenges. The aim of this effort is to present enhanced invalidation policy that cooperates with a new cache replacement technique by using genetic programming to select the items that will be removed from the cache for improving data access in the wireless environment. Cooperation between servers and mobile clients to enhance data availability. Each mobile client Collects data like access probability, size, and next validation time and uses these parameters in a genetic programming method for selecting cached items to be removed when the cache is full. The experiments were carried using NS2 software to evaluate the efficiency of the suggested policy, and the results are compared with existing cache policies algorithms. The experiments have shown that the proposed policy outperfomed the LRU by 24% in byte hit ratio, and 11% in cache hit ratio. It is concluded that the presented policy achieves well than other policies.

Recommendation system has witnessed a significant improvement with the introduction of data mining. Data mining services require accurate input data for their results to be meaningful, but privacy concerns may influence users to provide spurious information. In order to preserve the privacy of the client in data mining process, the issue of information protection has become more urgently demanded. In this paper, an innovative system for movies recommendation is proposed. The new proposed system is fundamentally based on modified version of multi-parameters perturbation and query restriction as well as adopting non-linear programming strategy to select optimum privacy parameters. The results showed that the proposed framework is capable of providing the maximum security for the information available without decreasing the accuracy of recommendation.

This paper demonstrates Content Based Image Retrieval (CBIR) algorithms implementation on a huge image set. Such implementation will be used to match query images to previously stored geotagged image database for the purpose of vision based indoor navigation. Feature extraction and matching are demonstrated using the two famous key-point detection CBIR algorithms: Scale Invariant Feature Transformation (SIFT) and Speeded Up Robust Features (SURF). The key-points matching results using Brute Force and FLANN (Fast Library for Approximate Nearest Neighbors) on various levels for both SIFT and SURF algorithms are compared herein. The algorithms are implemented on Hadoop MapReduce framework integrated with Hadoop Image Processing Interface (HIPI) and Open Computer Vision Library (OpenCV). As a result, the experiments shown that using SIFT with KNN (4, 5, and 6) levels give the highest matching accuracy in comparison to the other methods.

Nuclear newcomer countries face a number of key challenges in infrastructure development, e.g. they have not Intelligent Transportation Systems. Therefore, one of challenges is the safety and security of nuclear materials during transporting, storing and disposing. Where, nuclear and radiological terrorism continues to be a worldwide concern as the nature of security threats evolves. This paper tries to solve that challenge by design and implement of an embedded system for nuclear materials cask. This system is suitable to developing countries, where it is cost effective and it uses the existing infrastructure‏.‏ By using GPS, GSM/GPRS and microcontroller, the embedded system will enables the responsible bodies to remotely and continuously; tracking, monitoring and inspection of nuclear materials casks; during transporting, storing and disposing. The ORIGEN code is used to calculate the thermal and radioactivity loads of the cask. The application of this system allows the rapid intervention of the concerned bodies, which will prevent many accidents, in particular those caused by terrorists, like stealing or dispersing of nuclear materials.

Multimedia resources are rapidly growing with a huge increase of visual contents. Thus, searching these images accurately and efficiently for all types of datasets becomes one of the most challenging tasks. Content-based image retrieval (CBIR) is the technique that retrieves images based on their visual contents. So that, selecting appropriate features that describe an image sufficiently is a clue for a successful retrieval system. To this end, in this paper, a comparative study to investigate the effect of using a single and a combined set of features in the context of a CBIR is presented. To achieve this goal, several features including, edge histogram (EHD), color layout (CLD) and fuzzy color texture histogram (FCTH) as well as different combinations of these features such as, all edges (local, global and semi-global edges), all edges with CLD and finally, all edges with FCTH have been exploited. To demonstrate the effectiveness of the proposed method, a set of experiments utilizing different images datasets have been carried out. The results in terms of precision, recall, F-measure and mean average precision show a higher retrieval accuracy while using a set of combined features compared to exploiting only single features for the same retrieval task.

The partial least squares-structural equation modelling (PLS-SEM) has become a key approach for validating the conceptual models across many disciplines in general, and the Information Systems (IS) in specific. This is guided through the assessment of the measurement and structural models. Several research articles were carried out to provide an extensive coverage of the usage and application of PLS-SEM. These articles were mainly concentrated on providing guidelines of how to use PLS-SEM in terms of reflective and formative measures, measurement and structural models, and the steps for analysing a particular conceptual model. Nevertheless, there are several steps and procedures that precede the evaluation of the measurement and structural models. The understanding of these steps and procedures is very important for many IS scholars, Ph.D. and Master students who are always struggling to find a comprehensive reference that could guide them through their research journey. Hence, the main contribution of this study is to a build a comprehensive methodological guideline of how the PLS-SEM approach can be employed in the context of IS adoption and acceptance, starting from the research design stage till the assessment of the measurement and structural models. This study may serve as a comprehensive reference for formulating the methodology in the IS adoption and acceptance related studies in the case of PLS-SEM employment.

Chromosome’s segmentation is an essential step in the automated chromosome classification system. It is important for chromosomes to be separated from noise or background before the identification and classification. Chromosomes image (Metaphase) is generated in the third phase of mitosis. During metaphase, the cell’s chromosomes arrange themselves in the middle of the cell through a cellular. The analysis of metaphase chromosomes is one of the essential tools of cancer studies and cytogenetics. The Chromosomes are thickened and highly twisted in metaphase which make them very appropriate for visual analysis to determine the kind of each chromosome within the 24 classes (Chromosome karyotyping). This paper represents a chromosome segmentation method of high-resolution digitized metaphase images. Segmentation is done using Difference of Gaussian (DoG) as a sharpening filter before the classic technique (Otsu’s thresholding followed by morphological operations). The proposed method is tested using 130 metaphase images (6011 chromosomes) provided by The Diagnostic Genomic Medicine Unit (DGMU) laboratory at King Abdulaziz University. The experimental results show that the proposed method can successfully segment the metaphase chromosome images with 99.8% segmentation accuracy.

Failure detection and recovery is one of the important operations of the health monitoring management system which plays a relevant role for keeping the reliability and availability of the failed sensor over an on-orbit system whole lifetime mission especially where the maintenance may be impossible. In this paper we have implemented Grey Wolf Optimization (GWO) for optimizing Support Vector Machines (SVM) in terms of recovering the detected failure of the failed sensor. The performance of the proposed model with GWO is compared against to four swarm algorithms; Ant Lion Optimizer (ALO), Dragonfly Algorithm (DA), Moth Flame Optimizer (MFO) and Whale Optimizer Algorithm (WOA), four different evaluation aspects are used in this comparison; failure recovering accuracy, stability, convergence and computational time. The experiment is implemented using cube satellite telemetry data, the experimental results demonstrate that the optimization of SVM using GWO (SVM-GWO) model can be regarded as a promising success for satellite failure detection and recovery.