Research Interests:
advances in techniques, services, and applications dedicated to a global approach of eHealth. Development of wireless homecare, of special types of communications with patient data, of videoconferencing and telepresence, and the progress... more
advances in techniques, services, and applications dedicated to a global approach of eHealth. Development of wireless homecare, of special types of communications with patient data, of videoconferencing and telepresence, and the progress in image processing and date protection increased the eHealth applications and services, and extended Internet-based patient coverage areas. Social and economic aspects as well as the integration of classical systems with the telemedicine systems are still challenging issues. eTELEMED 2015 provided a forum where researchers were able to present recent research results and new research problems and directions related to them. The topics covered aspects from classical medicine and eHealth integration, systems and communication, devices, and applications. We take this opportunity to thank all the members of the eTELEMED 2015 Technical Program Committee as well as the numerous reviewers. The creation of such a broad and high-quality conference program w...
Research Interests:
Research Interests:
Research Interests:
Cloud Computing is an emerging trend in the outsourced information technology (OIT) and provides a lot of functions as services. However, it suffers from many challenges such as resource provisioning, integrity, federation, and security.... more
Cloud Computing is an emerging trend in the outsourced information technology (OIT) and provides a lot of functions as services. However, it suffers from many challenges such as resource provisioning, integrity, federation, and security. This paper focuses on the major problem, resource provisioning, that explored by many companies and researchers as a critical problem. Such researches are attempted to find method that minimizes provisioning time and reduces the number of resources in the cloud environment. Consequently, this paper proposes a dynamic resources provisioning algorithm by using Artificial Bees Colony (ABC) and Ant Colony Optimization (ACO) and focus on time optimization in multi-tier clouds. Accordingly, the obtained results show that the ACO faster than other meta-heuristic algorithm such as ABC, Particle Swarm Optimization (PSO), Simulated Annealing (SA) and hybrid Particle Swarm Optimization-Simulated Annealing (PSO-SA).
Research Interests:
ABSTRACT
Research Interests:
DESCRIPTION
Research Interests:
This paper describes an application of a reusable mobile agent system in network management. A mobile agent reusable system is constructed to realize a new method in forming mobile agent systems. By using this method, an agent can change... more
This paper describes an application of a reusable mobile agent system in network management. A mobile agent reusable system is constructed to realize a new method in forming mobile agent systems. By using this method, an agent can change its route dynamically without making any change to its specific behavior. By classifying mobile agents into two categories, the task agent can be reusable in different networks. In this way, a mobile agent system can easily carry out network management tasks.
Research Interests:
Solving duster identification problem on large amount of data ig known to be time consuming. Àlmoit au the state of art clustering techniques focuses on sequential algorithms which suffer from me problem of long runtime. So, parallel... more
Solving duster identification problem on large amount of data ig known to be time consuming. Àlmoit au the state of art clustering techniques focuses on sequential algorithms which suffer from me problem of long runtime. So, parallel algorithms are needed. One of the attempts is a parallel minimum spanning tree (MST)-based clustering technique, called CLUMP, which identifies dense clusters in
Research Interests:
Research Interests:
ABSTRACT The problem of optimally locating the numbers around a dartboard is a Combinatorial Optimization problem. In this paper, we’re solving this problem using Ant System and Max-Min Ant System (MMAS) algorithm. The algorithm... more
ABSTRACT The problem of optimally locating the numbers around a dartboard is a Combinatorial Optimization problem. In this paper, we’re solving this problem using Ant System and Max-Min Ant System (MMAS) algorithm. The algorithm reinforces local search in neighborhood of the best solution found in each iteration while implementing methods to slow convergence and facilitate exploration. Both algorithms has been proved to be very effective in finding optimum solution to hard combinatorial optimization problems.
Research Interests:
In contrast to English search engines, Arabic search engines did not have their fair share in modern studies despite the continuous growth of Arabic Internet users and data. Towards bridging the gap, this paper presents a novel indexing... more
In contrast to English search engines, Arabic search engines did not have their fair share in modern studies despite the continuous growth of Arabic Internet users and data. Towards bridging the gap, this paper presents a novel indexing algorithm customized for Arabic documents. Our algorithm exploits the characteristics of the Arabic language to enhance indexing and lookup. Additionally, the algorithm utilizes the highly parallel architecture of the graphics processing unit to speed-up the indexing. Finally, we discuss some of the synchronization challenges we faced and the techniques we used to overcome them. The preliminary tests of our GPU-accelerated Arabic indexer show promising speed-up factors.
Research Interests:
Parallel Computing 18 (1992) 103107 103 NorthHolland Short communication A synchronous algofitban for shortest paths on a tree machine EISayed M. EIHorbaty Maths. Dept., Faculty of Science. Ain Shams University, Egypt Alaa ElDin H.... more
Parallel Computing 18 (1992) 103107 103 NorthHolland Short communication A synchronous algofitban for shortest paths on a tree machine EISayed M. EIHorbaty Maths. Dept., Faculty of Science. Ain Shams University, Egypt Alaa ElDin H. Mohamed Maths. Dept., Faculty of ...
Research Interests:
Research Interests:
ABSTRACT
Research Interests:
This paper is concerned with the consequences of calculating the two-variable invariant polynomials associated with representation of braid groups (Jones polynomials). Recurrence relations for simplifying the required calculations have... more
This paper is concerned with the consequences of calculating the two-variable invariant polynomials associated with representation of braid groups (Jones polynomials). Recurrence relations for simplifying the required calculations have been driven and an algorithm depending on them has been designed. We implemented the algorithm using Mathematica as a computing environment and computational results are given.
Research Interests:
The Social Media (SM) is affecting clients' preferences by modeling their thoughts, attitudes, opinions, views and public mood. Observing the SM activities is a decent approach to measure clients' loyalty, keeping a track on their... more
The Social Media (SM) is affecting clients' preferences by modeling their thoughts, attitudes, opinions, views and public mood. Observing the SM activities is a decent approach to measure clients' loyalty, keeping a track on their opinion towards products preferences or social event. Opinion Mining (OM) is the most rising research field of text mining using Machine Learning (ML) algorithms and Natural Language Processing (NLP). Several algorithms such as Support Vector Machines (SVM), Naïve Bayes (NB) and Maximum Entropy (ME), were utilized to extract information that differentiates the user's opinion whether it's positive, negative or neutral. User's opinions and reviews are very beneficial information for individuals, businesses, and governments. In this paper, we compare the intelligent algorithms, which are utilized for OM in SM data over the last five years. The results show that using SVM with Part Of Speech (POS) or POS, Unigram and Bigram with J48 accomplish Sentiment Classification (SC) accuracy 92%.
Research Interests:
Smart healthcare systems play a vital role in people's everyday lives and hence, healthcare systems are expected to continue to improve and advance. AI and IoT techniques are employed in the prescription of medicine and in setting the... more
Smart healthcare systems play a vital role in people's everyday lives and hence, healthcare systems are expected to continue to improve and advance. AI and IoT techniques are employed in the prescription of medicine and in setting the different actions and procedures that need to be followed by patients by the health service providers. These technologies, along with ML algorithms, form a reliable and concrete platform because of their high processing performance. Meanwhile, it is important to maintain accurate input data for these new technologies to ensure that they will give us the desired output at the right time. In the healthcare industry, the most popular means to ensure the correctness of input data is to collect them through surveys and questionnaires that are completed by field specialists. In this paper, we report on the results of a questionnaire that was used in Egypt to collect the needed input data for our intended emergency healthcare system. Our aim is to offer t...
Research Interests:
Research Interests:
The internet of things (IoT) had a variety of uses, namely smart homes, smart cities, wearables, smart grid, self-driven cars, IoT retail-shops, farming, industrial internet, smart supply chain management, and the health care. The IoT’s... more
The internet of things (IoT) had a variety of uses, namely smart homes, smart cities, wearables, smart grid, self-driven cars, IoT retail-shops, farming, industrial internet, smart supply chain management, and the health care. The IoT’s boom is altering the existing healthcare state with thrilling technological, economical, and social implications. The dilemma of an increasing number of patients with heart diseases and a limited number of caregivers is that each caregiver must care for multiple patients, causing stress for caregivers and suffering for patients. Therefore, we designed a comparative study (network designs/programs, appliances, and industry trends) in IoT-established healthcare results. The development of IoT-based health care technology especially cardiac patients was also considered. Additionally, the underlying mechanism of the fluctuation effects of IoT modern advances on cardiac patients were elucidated throughout the key articles in the last 3 years. Our results proved that the secluded health checking system using IoT, especially for Cardiac patients, improved the health care process. This process is a nonstop scrutinizing and control equipment to monitor the patient's conditions. It also affected by the number and type of sensors used, and it could save the patient's information on a server, meanwhile, the authorized personnel may access the data using any IoT platform. Most importantly, doctors can continuously monitor the patient from afar and predict the diseases based on the values obtained.
Research Interests:
Cloud computing technology is a modern emerging trend in the distributed computing technology that is rapidly gaining popularity in network communication field. Despite the advantages that the cloud platforms bolstered, it suffers from... more
Cloud computing technology is a modern emerging trend in the distributed computing technology that is rapidly gaining popularity in network communication field. Despite the advantages that the cloud platforms bolstered, it suffers from many security issues such as secure communication, consumer authentication, and intrusion caused by attacks. These security issues relevant to customer data filtering and lost the connection at any time. In order to address these issues, this chapter, introduces an innovative cloud computing cryptographic environment, that entails both Quantum Cryptography-as-service and Quantum Advanced Encryption Standard. CCCE poses more secure data transmission channels by provisioning secret key among cloud's instances and consumers. In addition, the QCaaS solves the key generation and key distribution problems that emerged through the online negotiation between the communication parties. It is important to note that the CCCE solves the distance limitation co...
Research Interests:
Cloud computing environment is a new approach to the intelligent control of network communication and knowledge-based systems. It drastically guarantees scalability, on-demand, and pay-as-you-go services through virtualization... more
Cloud computing environment is a new approach to the intelligent control of network communication and knowledge-based systems. It drastically guarantees scalability, on-demand, and pay-as-you-go services through virtualization environments. In a cloud environment, resources are provided as services to clients over the internet in the public cloud and over the intranet in the private cloud upon request. Resources’ coordination in the cloud enables clients to reach their resources anywhere and anytime. Guaranteeing the security in cloud environment plays an important role, as clients often store important files on remote trust cloud data center. However, clients are wondering about the integrity and the availability of their data in the cloud environment. So, many security issues, which pertinent to client data garbling and communication intrusion caused by attackers, are attitudinized in the host, network and data levels. In order to address these issues, this chapter introduces a new intelligent quantum cloud environment (IQCE), that entails both Intelligent Quantum Cryptography-as-a-Service (IQCaaS) and Quantum Advanced Encryption Standard (QAES). This intelligent environment poses more secured data transmission by provisioning secret key among cloud’s instances and machines. It is implemented using System Center Manager (SCM) 2012-R2, which in turn, installed and configured based on bare-metal Hyper-V hypervisor. In addition, IQCaaS solves the key generation, the key distribution and the key management problems that emerged through the online negotiation between the communication parties in the cloud environment.
Research Interests:
Cloud computing is an internet-based computing, where shared resources, software, and information are provided with consumers on-demand. They guarantee a way to share distributed resources and services that belong to different... more
Cloud computing is an internet-based computing, where shared resources, software, and information are provided with consumers on-demand. They guarantee a way to share distributed resources and services that belong to different organizations. In order to build secure cloud environment, data security and cryptography must be assured to share data through distributed environment. So, this paper provides more flexibility and secured communication environment by deploying a new cryptographic service. This service entails both Quantum Key Distribution (QKD) and enhanced version of Advanced Encryption Standard (AES). Moreover, this service solves the key distribution and key management problems in cloud environment which emerged through the two implemented modes, on-line and off-line modes.
Research Interests:
ABSTRACT Recently, Quantum cryptography researchers utilize the quantum keys, in order to provide a more trusted environment for both key distribution and management processes. The quantum keys are generated based on quantum mechanics... more
ABSTRACT Recently, Quantum cryptography researchers utilize the quantum keys, in order to provide a more trusted environment for both key distribution and management processes. The quantum keys are generated based on quantum mechanics phenomena. However, all events for the quantum key generation rely on exchanging photons between parties over limited distances. So, in this paper, random tests algorithms, such as NIST and DIEHARD, are implemented to test and evaluate the randomness rates for quantum keys generation. After then, the initialized vector, which is the seed of the symmetric encryption algorithms, is established based on specific analysis to be a key for the algorithms. The paper utilizes the (BB84) quantum key distribution (QKD) protocol based on two different innovated modes, the raw and privacy modes.
Research Interests:
The concept of “cloud computing” is not new, it is undisputable that they have proven a major commercial success over recent times. Cloud computing is the delivery of computing services by shared resources, software and information over... more
The concept of “cloud computing” is not new, it is undisputable that they have proven a major commercial success over recent times. Cloud computing is the delivery of computing services by shared resources, software and information over the internet (public) or intranet (private). The improvement of cloud technology is reinforced by the improvement of the security concerns, accordingly various encryption algorithms have been developed. This paper provides a comparative study that represents the differences between modern encryption algorithms in cloud computing. The study encompasses the key size, the performance and the size of the output encrypted file based two different categorizes of algorithms (symmetric and asymmetric).
Research Interests:
Analyzing gait data is a branch of biomechanics that offers a degree of privacy, low-cost, and effortless objective identification for individuals. Consequently, gait recognition can be used as a replacement for passwords, or as an extra... more
Analyzing gait data is a branch of biomechanics that offers a degree of privacy, low-cost, and effortless objective identification for individuals. Consequently, gait recognition can be used as a replacement for passwords, or as an extra security measure with existing passwords. This paper focuses on surveying footstep recognition, comparing deep learning and shallow learning, and providing an overview of the current state of footstep recognition. It might be useful to both professionals and beginners in this field of research.
Research Interests:
Cloud computing is the new paradigm of representing computing capabilities as a service. With its facility of resource sharing and being cost-effective, it exists in every domain of life, enhancing their functionality and adding new... more
Cloud computing is the new paradigm of representing computing capabilities as a service. With its facility of resource sharing and being cost-effective, it exists in every domain of life, enhancing their functionality and adding new opportunities to it. Accordingly, the focus on solving its dilemmas like load balancing becomes more challenging and the research in swarm-based algorithms to find optimal results has been expanding. This paper discusses the use of two swarm algorithms including Ant-Lion optimizer (ALO) and Grey wolf optimizer (GWO) in task scheduling of the Cloud Computing environment. Additionally, compare the results with commonly known swarm algorithms: Particle Swarm Optimization (PSO) and Firefly Algorithm (FFA). The results show the ALO and GWO are a strong adversary to Particle Swarm Optimization (PSO), and better than Firefly (FFA) and they have potential in load balancing.
Research Interests:
Cloud computing services are growing very fast especially with the high demand of mobile and online applications (Apps) and services. This exponential growth emphasis on the need of minimizing the makespan scheduling and utilizing the... more
Cloud computing services are growing very fast especially with the high demand of mobile and online applications (Apps) and services. This exponential growth emphasis on the need of minimizing the makespan scheduling and utilizing the resources efficiently based on dynamic environment. Accordingly, many load balancing algorithms have been developed to overcome these issues using intelligent optimization methodologies, such as Genetic Algorithms (GA), Ant Colony optimization (ACO), Artificial Bee Colony (ABC) and Particle Swarm Optimization (PSO). This paper surveys the above intelligent optimization techniques and focuses on the Ant Lion Optimizer (ALO) intelligent technique, also it proposes an implementation of ALO based cloud computing environment as efficient algorithm that expected to supplies better outcomes in load balancing.
Research Interests:
Research Interests:
Cloud Communication Environment is an internet-based computing, where shared resources, software, and information are provided with computers and devices on-demand. They guarantee a way to share distributed resources and services that... more
Cloud Communication Environment is an internet-based computing, where shared resources, software, and information are provided with computers and devices on-demand. They guarantee a way to share distributed resources and services that belong to different organizations. In order to develop cloud computing applications, security and trust to share data through distributed resources must be assured. This paper offers a study of the different mechanisms used in open cloud environments such as keys generation and management, and encryption/decryption algorithms. In addition, the paper proposes a new cryptographic environment, annotated as “CCCE” that deploys the combination between quantum key distribution mechanisms (QKD) and advanced encryption standard (AES), and demonstrates how quantum mechanics can be applied to improve computation.
Research Interests:
Research Interests:
Container handling problems at container terminals<br> are NP-hard problems. This paper presents an approach using<br> discrete-event simulation modeling to optimize solution for storage<br> space allocation problem,... more
Container handling problems at container terminals<br> are NP-hard problems. This paper presents an approach using<br> discrete-event simulation modeling to optimize solution for storage<br> space allocation problem, taking into account all various interrelated<br> container terminal handling activities. The proposed approach is<br> applied on a real case study data of container terminal at Alexandria<br> port. The computational results show the effectiveness of the<br> proposed model for optimization of storage space allocation in<br> container terminal where 54% reduction in containers handling time<br> in port is achieved.
Research Interests:
Cloud computing technology is very useful in present day to day life, it uses the internet and the central remote servers to provide and maintain data as well as applications. Such applications in turn can be used by the end users via the... more
Cloud computing technology is very useful in present day to day life, it uses the internet and the central remote servers to provide and maintain data as well as applications. Such applications in turn can be used by the end users via the cloud communications without any installation. Moreover, the end users' data files can be accessed and manipulated from any other computer using the internet services. Despite the flexibility of data and application accessing and usage that cloud computing environments provide, there are many questions still coming up on how to gain a trusted environment that protect data and applications in clouds from hackers and intruders. This paper surveys the "keys generation and management" mechanism and encryption/decryption algorithms used in cloud computing environments, we proposed new security architecture for cloud computing environment that considers the various security gaps as much as possible. A new cryptographic environment that impl...
Research Interests:
Making realistic facial animation is one of the most challenging research topics in facial animation field because producing realistic photo and sentimental virtual characters require a combination of face modeling, animating, and... more
Making realistic facial animation is one of the most challenging research topics in facial animation field because producing realistic photo and sentimental virtual characters require a combination of face modeling, animating, and rendering. Techniques that commonly used for facial animation are in need of naturalism. The most popular expression coding systems are FACS (Facial Action Coding System) and MPEG-4 (Moving Pictures Experts Group-4) Facial animation models. FACS is a landmark technique that enables remarkable improvements in making realistic facial animations. Where MPEG-4 Facial Animation provides a standard way of encoding facial actions by defining various parameters for a talking face. In this paper, we made a review on how to achieve realistic facial animation, focusing on the applications and limitations of the FACS comparing to MPEG-4 facial animation. The review inferred that FACS helps animators to represent and build realistic facial expressions by configuring al...
Research Interests:
Energy Efficiency has become a crucial concern in modern data centers. Dynamic VM consolidation is one of the effective approaches endorsed to achieve energy efficiency in cloud data centers hosting thousands of servers. Live migration is... more
Energy Efficiency has become a crucial concern in modern data centers. Dynamic VM consolidation is one of the effective approaches endorsed to achieve energy efficiency in cloud data centers hosting thousands of servers. Live migration is a core feature enabling VM consolidation. However, live migration is a costly operation imposing energy and performance overhead. An efficient dynamic virtual machine consolidate should consider the cost due to live migration. In this paper, we design and implement a dynamic VM consolidation algorithm based on simulated annealing that accounts for the migration cost imposed by a consolidation plan. We conduct simulation-based experiments on CloudSim using real cloud workload traces from PlanetLab to evaluate the performance of the proposed algorithm. Results show that the using the proposed algorithm, the simulated data center consumes almost the same amount of energy of that using a FF based consolidation. However, the proposed algorithm accounts ...
The technological developments of machine learning in educational technology lead to the development of intelligent e-learning systems. Hence, the accumulated educational materials feed huge databases. Classifying those databases and... more
The technological developments of machine learning in educational technology lead to the development of intelligent e-learning systems. Hence, the accumulated educational materials feed huge databases. Classifying those databases and finding out suitable methods to retrieve information from them created the needs for new approaches. Data mining provides a robust methodology to extract and produce a valuable analysis in this objective. Data mining techniques can analyze relevant information results and produce different perspectives to understand more about the students’ activities. In this paper, we present a technical analysis for seven studies in the context of the application of data mining approach in e-learning. The results of our analysis supports the usage of data mining techniques for building a new generation of intelligent e-learning systems for different tasks and domains. Current research areas and promising benefits from applying data mining techniques in educational sy...
Cloud computing in healthcare services is gaining a wide interest across the world due to its affordable cost and enormous data storage capabilities. Smart healthcare is also another growing area of interest to researchers and governments... more
Cloud computing in healthcare services is gaining a wide interest across the world due to its affordable cost and enormous data storage capabilities. Smart healthcare is also another growing area of interest to researchers and governments due to the increasing development of new smart cities. However, there is no current standard practice to format the cloud computing infrastructure. In order to assist the smart healthcare system architect in designing a comprehensive solution for the basic services that are required by the healthcare users. Architects need to take into consideration a balanced approach towards their specific functional and non-functional needs such as openness, scalability, concurrency, interoperability and security factors. The integration of smart healthcare services based on cloud computing architecture is considered a new field of interest and research. The main objective of this paper is to provide a brief analysis of the cloud computing architectures in healt...
Research Interests:
Microarray gene expression data has a high dimensionality, e.g. small number of samples with large number of genes. Using machine learning techniques for knowledge discovery in such data become a rich area for researchers. This large... more
Microarray gene expression data has a high dimensionality, e.g. small number of samples with large number of genes. Using machine learning techniques for knowledge discovery in such data become a rich area for researchers. This large number of genes, not all has the useful information that can be used to perform a certain diagnostic test, so feature selections become very important in both research and application communities of data mining. This paper proves the importance of finding the most informative genes in the database by using statistical gene selection technique to achieve a reduction in time, cost and increase the efficiency of the classifier. We applied T-Test statistical feature selection technique and K-Nearest neighbor (KNN) classifier on two public microarray data sets, SRBCT and Leukemia datasets. The feature selection is done on the whole available datasets and the data reduction results are then divided into training and testing and supplemented to the KNN classif...
Malignant melanoma is one of the most dangerous types of skin cancers, which may grow on any part of the body. Medical Informatics utilized computer technology such as Computer Aided Diagnosis (CAD) to diagnose the disease. Many... more
Malignant melanoma is one of the most dangerous types of skin cancers, which may grow on any part of the body. Medical Informatics utilized computer technology such as Computer Aided Diagnosis (CAD) to diagnose the disease. Many researchers developed CAD systems for melanoma diagnosis. Early diagnosis of melanoma is a main strategy to reduce melanoma-related deaths. This paper presents intelligence techniques namely, Naïve Bayes and Decision Tree to diagnose malignant melanoma. Dermoscopy images are taken from Dermatology Information System (DermIS) and DermQuest, image enhancement is achieved by various pre-processing techniques. The extracted features are based on hybrid Discrete Wavelet Transform (DWT) and Principle Component Analysis (PCA), and texture features. These features become the input to the various classification techniques like Naïve Bayes and Decision Tree to classify the lesions as malignant or benign. The results show that rate of accuracy of using hybrid DWT and PCA with Decision Tree is 92.86%, while Naive Bayes gives a higher rate of accuracy of about 98.8%. The results indicate that the Naive Bayes is better than decision tree, because it has shown excellent diagnostic accuracy; also the results show that the hybrid DWT and PCA features are more effective in improving the accuracy than the texture features for melanoma diagnosis. The comparative results indicated that the proposed techniques have excellent accuracy than the other techniques in this field of melanoma diagnosis.
Research Interests:
Nowadays, computers are extremely beneficial to music composers. Computer music generation tools are developed for aiding composers in producing satisfying musical pieces. The automation of music composition tasks is a challenging... more
Nowadays, computers are extremely beneficial to music composers. Computer music generation tools are developed for aiding composers in producing satisfying musical pieces. The automation of music composition tasks is a challenging research point, specially to the field of Artificial Intelligence. Converting melodies that are played on a major scale to minor (or vice versa) is interesting to both composers and music listeners. Newly converted melodies of famous songs, either from major to minor or the opposite, are becoming blockbusters on the social media. In this paper we propose an intelligent method for automating the conversion between major and minor melodies using Artificial Intelligence techniques. We run our experiments on melodies in the MIDI format which is a standard music format enabling the communication between computers and various musical devices. We also propose a smart method for musical scale detection for the input melodies. Scale detection is a critical step for...
Research Interests:
Recently, a lot of researches have been made in the area of automatic detection and diagnosing the brain tumor type based on different medical imaging techniques. This paper presents a new intelligent methodology applying k-means... more
Recently, a lot of researches have been made in the area of automatic detection and diagnosing the brain tumor type based on different medical imaging techniques. This paper presents a new intelligent methodology applying k-means segmentation technique and a hybrid support vector machine (SVM) classifier based on Linear-SVM and Multi-SVM using two feature extraction techniques, namely : Gray level co-occurrence matrix (GLCM) and discrete wavelet transform (DWT) followed by Principle component analysis (PCA) to detect brain tumors in brain magnetic resonance images (MRIs) and differentiate between three types of malignant brain tumors: glioblastoma, sarcoma and metastatic bronchogenic carcinoma. The results of the two feature extraction techniques were compared according to their accuracy, sensitivity and specificity showing good results and high robustness. Keywords—machine learning, support vector machine, k-means, discrete wavelet transform, Principle component analysis, Gray leve...
Ever expanding utilization of the internet and online activities such as booking, blogging, e-commerce and conferencing, leads us to analyze very large quantities of structured data and unstructured data through Sentiment Analysis (SA).... more
Ever expanding utilization of the internet and online activities such as booking, blogging, e-commerce and conferencing, leads us to analyze very large quantities of structured data and unstructured data through Sentiment Analysis (SA). SA refers to the application of Natural Language Processing (NLP), computational linguistics, and data mining to classify whether the review is positive or negative. SA of this customer-generated data is extremely valuable to get a clearer perspective of public opinion and mood. In this paper, we evaluate the most popular Machine Learning (ML) algorithms such as Artificial Neural Networks (ANN), Support Vector Machines (SVM), and Nave Bayes (NB), which are utilized for SA on different user reviews datasets such as movie reviews, product reviews, and smart electronics devices over the last five years. The results show that using the ANN classifier along with the unigram as a feature extractor accomplishes a high accuracy 90.3%.
Segmentation is a core process for automatic detection and identification of brain tumors as it plays a vital role in extracting the information of the image as measuring and visualizing the brain's anatomical structures and analyzing... more
Segmentation is a core process for automatic detection and identification of brain tumors as it plays a vital role in extracting the information of the image as measuring and visualizing the brain's anatomical structures and analyzing the brain changes. From this point the need for accurate and automatic segmentation techniques has risen as manual segmentation is not a realistic solution and yet time consuming. This paper examines the various automated segmentation techniques used by researchers on brain magnetic resonance images (MRI), giving the most important features for the most common techniques used in the area of brain tumors. Moreover, a comparative study to address the differences, limitations, advantages and challenges of each technique mentioned when being used on brain MRI to find out their efficiency in this area and to put guidelines that should be considered when using these techniques.
Malignant melanoma is reported to be the deadliest of skin cancers. Therefore, early diagnosis is crucial for reducing of melanoma-related deaths. Medical Informatics uses the computer technology such as Computer Aided Diagnosis (CAD) for... more
Malignant melanoma is reported to be the deadliest of skin cancers. Therefore, early diagnosis is crucial for reducing of melanoma-related deaths. Medical Informatics uses the computer technology such as Computer Aided Diagnosis (CAD) for melanoma diagnostic. This paper presents computational intelligence approaches namely, Artificial Neural Network (ANN) and Adaptive-Network-based Fuzzy Inference System (ANFIS). The dermoscopy images are taken from Dermatology Information System (DermIS) and DermQuest, image enhancement is achieved by various pre-processing approaches. The extracted features are based on Discrete Wavelet Transform (DWT), and Principle Component Analysis (PCA) is used to take the eigenvalue as features. These features become the input to the various classification approaches such as: ANN and ANFIS to classify the lesions as malignant or benign. The results show the rate of accuracy for ANFIS is 95.18%, while ANN gives higher rate of accuracy about 98.8%. Moreover; the results obtained are compared with other approaches. The comparative results indicated that the proposed feature extraction and classification approaches are more accurate than other approaches in this field of melanoma diagnosis.
Research Interests:
Research Interests:
Sentiment classification (SC) is a reference to the task of sentiment analysis (SA), which is a subfield of natural language processing (NLP) and is used to decide whether textual content implies a positive or negative review. This... more
Sentiment classification (SC) is a reference to the task of sentiment analysis (SA), which is a subfield of natural language processing (NLP) and is used to decide whether textual content implies a positive or negative review. This research focuses on the various machine learning (ML) algorithms which are utilized in the analyzation of sentiments and in the mining of reviews in different datasets. Overall, an SC task consists of two phases. The first phase deals with feature extraction (FE). Three different FE algorithms are applied in this research. The second phase covers the classification of the reviews by using various ML algorithms. These are Naïve Bayes (NB), Stochastic Gradient Descent (SGD), Support Vector Machines (SVM), Passive Aggressive (PA), Maximum Entropy (ME), Adaptive Boosting (AdaBoost), Multinomial NB (MNB), Bernoulli NB (BNB), Ridge Regression (RR) and Logistic Regression (LR). The performance of PA with a unigram is the best among other algorithms for all used ...