Computer Engineering
Bu konu başlığı altında 222 tez
Data Modeling with Type I and Type II Fuzzy Sets
The fuzzy classifier is an algorithm that assigns a class label to an object, based on the object description. It is also said that the classifier predicts the class label. The object description comes in the form of a vector containing values of the features (attributes) deemed to be relevant for the classification task. Typically, the classifier learns to predict class labels using a training algorithm and a training data set. When a training data set is not available, a classifier can be designed from prior knowledge and expertise. Once trained, the classifier is ready for operation on unseen objects.In this thesis, type-1fuzzy classifier, and the type-2 fuzzy classifier are used for the machine learning datasets classification. The Wisconsin breast cancer dataset, Iris Dataset, and Tic-Tac-Toe datasets are classified. Type-2 fuzzy classifiers are able to perform better than type-1 fuzzy classifiers which have additional design parameters. Therefore, type-2 fuzzy classifiers are more attractive than the type-1 classifiers. The essential benefits the type-2 fuzzy logic classifiers are their ability to handle more vagueness. Keywords: Classifier, Type-1fuzzy classifier, Type-2 fuzzy classifier, Machine learning dataset and Uncertainty.
Performance Evaluation of AODV and DSR Routing Protocols with PCM and GSM Voice Encoding Schemes
A mobile ad hoc network (MANET) is one of the narrowest and most specific of research topics in the field of telecommunications. The growth of this type of network, and the large number of applications with mobility requirements, has led to a wider study and research in the analysis and enhancement of the work in this area. In such networks, nodes are communicating with each other without the need of a centralized administration (This type of network does not contain any type of server or base station). In this topology, the communication between the nodes is done by pair to pair within the coverage area. The routing is managed and organized by a number of routing protocols. A limited coverage area, collision and power consumption for mobile nodes are the main problems occurring in such networks. In this thesis, two important MANET routing protocols were used, AODV and DSR to analyze their behavior with two different voice encoding schemes, Pulse Code Modulation (PCM) and Global System Mobile (GSM). The PCM and the GSM encoding voice schemes are evaluated with a different number of clients using a Random Way Point Mobility (RWPM) model. OPNET simulator version 17.1 was used to build the modeler and to simulate the ad hoc mobile network model. The benefit of this simulation program is the ability to build models for different network topologies and the large number of available choices for node performance statistics. In addition to that, results are more confident and accurate compared to other simulation programs found in the literature. From the analysis of the simulations, it was concluded that, in all cases, the AODV protocol performed better than the DSR protocol. This is because AODV doesn’t save the entire possible path from source to the destination node. It takes the newest and most refreshable one. On the other hand, DSR caches all possible paths to the destination. It is also shown that PCM performance is better and more quality than GSM in most of the performance metrics except end -to- end delay, for both AODV and DSR routing protocols. Keywords: OPNET simulator, Mobile Wireless Ad Hoc Network, AODV, DSR, PCM, GSM.
Fruit Classification using Global and Local Descriptors
Recognizing different kinds of food such as vegetables and fruits is a recurrent task in supermarkets where the cashier must be able to point out not only the species of a particular fruit but also its variety which will determine its price. The use of barcodes has mostly ended this problem for packaged products but given that consumers want to pick their produce, they cannot be packaged, and thus must be weighted. A common solution to this problem is issuing codes for each kind of fruit/vegetable; which have problems given that the memorization is hard, leading to errors in pricing. In view of this, attention for classification and matching of these foods were carried out using global and local descriptors. In this thesis, global descriptors such as Principal Component Analysis (PCA), Histograms of Oriented Gradients (HOG) and local descriptors such as Local Binary Patterns (LBP), Binarized Statistical Image Features (BSIF) are implemented in order to classify fruits. Experiments are conducted on two datasets from Fruits_360 database and TropicalFruits database. Experimental results obtained with global and local descriptors are presented as a comparative analysis on fruit classification on the aforementioned datasets. Among all descriptors, BSIF results are better than the other algorithms employed with 70.06% and 75.00% on the aforementioned datasets, respectively. On the other hand, LBP algorithm achieved 61.11% and 75.00% recognition rate while HOG results are 37.96% and 58.33% and PCA results are 42.90% and 45.83% on both datasets, respectively. The results show that local descriptors achieve better performance compared to the performance of the global descriptors for fruit classification. Keywords: Fruit classification, Global Descriptors, Local Descriptors, PCA, HOG, LBP, BSIF.
Performance Investigation of Simulation Models of Wireless Mobile Ad Hoc Networks
ABSTRACT: Wireless ad hoc networks have attracted great interest in last few years, due to envisioning of their great potential in military and commercial applications. Being a wireless network of mobile computing devices that doesn’t rely on any pre-established infrastructure, they eliminate the complexity of infrastructure setup. Accordingly become popular in several application areas, such as battlefields, emergency areas, wireless sensor networks and hybrid wireless networks and can be deployed anywhere at anytime. This thesis provides a Petri-net-based model of a wireless ad hoc network, where all fundamental aspects with the proposed, a general and more realistic, inter-node communication scheme are implemented. The model is implemented in terms of extended Petri nets and the simulation system Winsim is used in development and simulation. There are two types of modules in the model, namely node and switching module, that is, the model is organized in a multi-module system. Three fundamental performance metrics of an ad hoc network – packet delivery ratio, average number of hops and relative network traffic – were investigated under different transmission radius, model parameters and conditions of mobility model and inter-node communication scheme. The entire model, together with the proposed inter-node communication scheme can be used for study of routing protocols as well as other aspects of information transmission in wireless ad hoc networks. The further study of this thesis can be the development of an efficient routing protocol that results in reduced network load and energy usage at mobile nodes as well as increasing the security of the network. The thesis is organized as follows. Chapter 1 introduces the era of computer and wireless networks, with the problem and statement of the work goal of the thesis. Chapter 2 provides a survey of the existing methods and tools for modeling and simulation of wireless ad hoc networks. Chapter 3 is devoted to the specification of system assumptions and the chosen mobility model. Chapter 4 explains the proposed scheme of inter-node communication. In Chapter 5, the organization and components of the entire model is considered. Chapter 6 describes the simulation setup and results of simulation. Chapter 7 concludes the thesis. Keywords: Mobile wireless ad hoc networks, oriented links, simulation, extended Petri nets, mobility models.
Transmission Range Assignment with Balancing Connectivity in Clustered Wireless Networks
Currently, the main challenge for researchers in the field of wireless sensor networks is associated with reducing the energy consumption as much as possible to increase the lifetime of the nodes and improve the performance of the network. Furthermore, delivery of data to its destination is also an important key issue that represents throughput of the network. On the other hand, transmission range assignment in clustered wireless networks is the bottleneck of the balance between energy conservation and the connectivity to deliver a given size of data to the sink or gateway. Therefore, this research aims to optimize the energy consumption through reducing the transmission ranges of the backbone nodes in multihop network, while maintaining high probability to get end -to- end connectivity to the network’s data sink or gateway. Hence, this framework will decrease the energy used for the transmissions made by cluster head nodes, and improve the efficiency of the current clustering protocols that usually use huge transmission ranges for cluster heads (CHs) backbone in wireless sensor networks. We modified the approach given in [1] to achieve more than 30% power saving through reducing CH-transmissions of the backbone network nodes in a multihop wireless sensor network with ensuring at least 95% connectivity probability. Keywords: Wireless sensor networks; Adaptive transmission ranges; Clustering; Network topology.
An Online Automation System based on Windows Sidebar Gadget for Local Market in Turkish Republic of Northern Cyprus
In Turkish Republic of Northern Cyprus, there are some difficulties on effective communication between local companies and potential customers. Therefore, a complete online automation system is developed to have economical contribution for the local companies (which are one of the main economic resources) and to help customers for having new information about companies‟ products with less effort. Our system is working over Internet and can be establish a bridge between the companies and potential customers by using Windows Sidebar Gadget. Windows Sidebar Gadget is a very popular and default tool in Microsoft Windows Vista and Microsoft Windows 7 operating systems which are mostly using in Turkish Republic of Northern Cyprus. With our system, increasing local companies' sale performance, economical contribution, making company known, and attracting more customers can be provided.
A Connectivity Preservation Scheme for Randomly Deployed Wireless Sensor Networks
A wireless sensor network (WSN) consists of spatially distributed low-power sensors for the purpose of monitoring an area of interest such as battle field or environmental conditions such as weather, earthquakes, pressure, etc. These sensor nodes monitor the field, sense and process the monitored data, then deliver the processed data to the sink in a multi-hop fashion. To achieve communication between nodes, network connectivity should be maintained, which is not always the case especially when sensor nodes are randomly deployed. This will result in the appearance of unreachable nodes or isolated nodes. In most of these cases, network will be partitioned and disconnected. Therefore, connectivity is an essential key factor for determining network quality of service (QoS). This thesis focuses on achieving high connectivity for randomly deployed wireless sensors by referring to the concept of building a network virtual backbone approach. Although the concept of connected dominating set (CDS) is used as a method to achieve this purpose; however, this method has limitations in presence of isolated or unreachable nodes. Therefore, this thesis contributes to the CDS approach by adding few anchor nodes at calculated distance to gain high network connectivity. Using MATLAB, extensive simulations have been carried out and the results showed that connectivity has been gained by activating few anchor nodes or spare nodes to random WSNs. Our algorithm had approximately twice the Fiedler value enhancement of Random Addition algorithm. Keywords: Wireless Sensor Networks, Network Connectivity, Anchor Nodes, QoS
Investigation of delay tolerant network routing protocols with energy consumption analysis
Delay Tolerant Networks (DTNs) are the results of the evolutions in mobile networks in which an end-to-end path may not exist. The main principle of DTN to route messages is store, carry and forward technique, where intermediate hosts store data to be transmitted until it finds an appropriate relay host to forward the message in the route towards its target. DTNs have numerous applications in ad-hoc networking such as life monitoring and crisis management. Several routing and forwarding protocols have been proposed among the past few years. Majority of them uses asynchronous message passing scheme. The primary difference between various DTN routing protocols is the amount of knowledge that they have available to route the message. Flooding protocols such as Epidemic and Spray and Wait (SaW) routing protocols do not use any information. Predictive protocols such as PRoPHET and MaxProp uses past encounters of hosts to expect their future suitability to transmit messages to its destination. Store, carry and forward technique of DTN routing protocols causes a lot of copies of a message in the networks which consuming hosts’ resources like energy and buffer. The main challenge in DTN routing is how to increase delivery ratio of messages and consume less resources. This thesis focuses on the routing issue in DTNs using limited resources and investigate the performance of four well-known DTN protocols which is Epidemic, PRoPHET, MaxProp and SaW with the metrics node’s average remaining energy, number of dead nodes, delivery ratio, average latency and overhead ratio using the Opportunistic Network Environment (ONE) simulator. It has been observed that the performance of routing protocols has been affected by the changing of message generation interval, number of nodes, node’s speed, buffer size, time to live and the message size. The simulation investigation results that the SaW protocol outperforms other protocols in terms of energy consumption whereas MaxProp protocol has the highest delivery ratio. In contrast, Epidemic results the worst performance.
A Hardware Oriented Algorithm for 3D AOA Mobile Positioning
ABSTRACT: The determination of a mobile object’s location in a cellular network becomes very important with the new US Federal Communication Commission (FCC) standards regarding the wireless Enhanced 911 (E911) emergency calling systems. Most commonly used methods for location can be addressed as Time of Arrival (TOA), Time difference of Arrival (TDOA) and Angle of Arrival (AOA). The importance of finding the location of a mobile object in 3D becomes much more important especially after Federal Communication Commission’s announcement which asks about the vertical position estimation of a mobile object. There exist general approaches to simple algorithms for 2D positioning techniques in cellular networks and adhoc networks. Such an approach is missing for 3D positioning. The aim of this project is via using AOA signal measurement technique to form a simple algorithm for 3D positioning that could be implemented both as hardware and software. Four new 3D AOA algorithms; MEM-1, MEM-2, DMEM-1 and DMEM-2 are proposed in this study. At the end of simulation from the results it is clear that our proposed algorithms outperform the traditional algorithm in terms of computational cost and execution simplicity. Keywords : Positioning algorithm, Angle of Arrival, 3D positioning. …………………………………………………………………………………………………………………………
A Computational Analysis of the Impact of Transcript Diversity on Protein Domains Coded by Human, Mouse and Rat Transcription Factor Genes
In this study, three different mammalian genomes are investigated with respect to their transcript diversity. The main focus of the thesis is investigation of how this transcript diversity reflects on the protein structures. Within the three genomes, specifically Transcription Factor genes are analyzed. The methodologies employed include biological data retrieval from contemporary biomedical resources, storage of data in a relational database and further computational analyses. Our results revealed that both in human and in mouse more than half of the TF genes analyzed have unique transcripts which code for proteins with unique domains. That is they have at least 2 unique transcripts coding for differential protein domain structures. Importantly, the unique domain coded by one of the TF transcripts and not the other conveys DNA-binding ability. This is the case for 51% of TF human genes and 52% of TF mouse genes. Given the lesser number of transcripts sequenced per rat TF genes in general, this percentage stays at 37%, as expected. The overall conclusion from this thesis is that the majority of TF genes have transcript diversity and that this transcript diversity brings diversity in protein structures and thus in functions. Keywords: Transcription factor, genomes, transcripts, protein structure, domain function, DNA-binding, biological databases, data retrieval and storage.
Secure true random number generator in a distributed system via wireless LAN (Distributed-RNG protocol)
ABSTRACT: In computer network and cryptography era, the necessity of generating true random numbers (TRNG), in the security directions and cryptography algorithms which require random numbers as nonce, public keys, private keys, session keys, secret keys, seeds, salts and etc. is inevitable. Cryptography algorithms are widely used in various networks; among them, Wireless networks need more security in comparison to the other networks due to their intrinsic vulnerabilities against possible attacks. In the most of recently studies, it is proven that an acceptable random number will not be generated unless using a distributed method for random number generator. This thesis firstly analyses a protocol for generation of secure true random number (Scatter) which used distributed method via a wireless network. Secondly, after making some changes on the mentioned protocol in regard to protocol structure and entropy of randomness source, the enhanced Distributed-RNG protocol is introduced; it provides more security and flexibility. Then, the quality of randomness of obtained random numbers using National Institute of Standards and Technology (NIST) tests is evaluated. Finally, after analyzing the results of both studies, it can be conducted that 60 percent of obtained results in this thesis are better than the existing protocol (Scatter). Keywords: Cryptography, True Random Numbers Generator (TRNG), Network Security, Nonce, Key Generations. …………………………………………………………………………………………………………………………
Maze Router: Collected Techniques
ABSTRACT: In this thesis, Maze Router Problem (MRP) solved by using Connected Component Labeling, Depth First Search, Lee and A* Algorithms. The main goal of this research is to find a complete set of path which directs an agent to move from the Source node in the Maze towards a Target node in a Single-layer routing environment. In experiments different sized Maze Router Problem (MRP) instances are solved by using different Algorithms. From the results obtained we can conclude that Lee and A* Algorithms finds the shortest path for all the problem instances. It can also be concluded that A* Algorithm is the fastest Algorithm that finds the shortest path. Keywords: Maze, Maze Router, Maze Router Problem, Connected Component Labeling Algorithm, Depth First Search Algorithm, Lee Algorithm, A* Algorithm. …………………………………………………………………………………………………………………………
Performance Evaluation of Routing Protocols in Wireless Mobile Ad Hoc Networks (MANETS) using OPNET Simulator
ABSTRACT: Mobile ad hoc networks (MANETs) have already opened a new point of view in the field of wireless networks which includes hundreds and thousands of nodes. The wireless nodes are communicating without the need of any kind of neither infrastructure like the base stations or routers, nor centralized administration. Wireless nodes are free of moving anytime, anywhere. Therefore, mobile ad hoc networks need to have dynamic routing protocols. Mobile Ad hoc network routing protocols are divided into several different categories such as Proactive, Reactive and Hybrid Routing Protocols. Also there are a lot of performance metrics to compare the routing protocols. Each of them has its own attributes and well for specific area, such as: throughput, jitter, packet delivery ratio, average number of hops, route discovery time and end-to-end delay, which are some important ones. In this thesis three well known routing protocols; Optimized Link State Routing (OLSR), Ad-hoc On-demand Distance Vector (AODV) and Temporary Ordered Routing Algorithm (TORA) were evaluated using the OPNET simulator under the medium load traffic size in FTP protocol. The first one (OLSR) is a proactive protocol depending on routing tables which are maintained at each node. The second one (AODV) is a reactive protocol, that finds a route to a destination on-demand. And the third ones‘ TORA which works in both categories as reactive and proactive. The random waypoint mobility model is used as pattern of mobility. As performance metrics average throughput, average network load and average end-to-end delay are examined in different number of nodes, file sizes and node speeds. The result from the simulations of this study reveals that different protocols have different qualities; some of the protocols perform better than others in one metric when using them in a specific scenario and worse in other metrics. After analyzing performances of some well-known reactive and proactive routing protocols, in case of average throughput, average end-to-end delay and average network load, the superiority of proactive protocols, over reactive ones is observed in different network scenarios. From the simulation results it is observed that the average end-to-end delay increases slightly when the number of nodes increases in OLSR. Also average throughput shown in OLSR was the highest comparing to AODV and TORA. Among the reactive protocols, AODV performs better than TORA when file sizes, speed of nodes and number of nodes are changed. On the other hand, TORA gives a highest end-to-end delay and lowest throughput compared to AODV and OLSR. Keywords: Mobile wireless ad hoc networks, simulation, routing protocols, performance evaluation, OPNET simulator. …………………………………………………………………………………………………………………………
A Simulation Framework for Performance Analysis of Molecular Nano Communication Networks
Nanonetworks have attracted a lot of attention over the past decade due to advances in nanotechnology and their wide range of biomedical, industrial, environmental, and military applications. Nanodevices are made up of nanoscale components and are capable of performing only simple computation, sensing, and actuation tasks. A nanonetwork is formed when nanodevices are interconnected. In a nanonetwork, nanodevices can cooperate and share information to achieve more complex tasks. Nanomachines can employ diffusion-based molecular communication as a possible, biocompatible information transport method. Unlike traditional communication techniques in which electromagnetic waves are employed as information carriers, molecules are considered as carrier signals to convey the information. For instance, a transmitter nanomachine encodes the message symbols into the molecular signals and then sends them into a fluidic propagation channel. These information molecules propagate in the medium according to Fick’s laws of diffusion, and then are received by the receiver nanomachine at which the information is decoded. In this work, a simulation framework for molecular nano communication networks will be developed. In particular, transmission, propagation channel, and the reception processes of molecules will be analyzed. The simulator will then be used to analyze specific performance metrics in a diffusion-based molecular communication network. The simulator will also provide a three-dimensional visualization of the network. Keywords: Nanonetworks, Molecular Communication, Diffusion, Simulation
Evolutionary Design of Radial Basis Function Neural Network for Data Modelling
ABSTRACT: In this thesis, implementation of Radial Basis a Function Neural Network (RBFNN) using genetic algorithm is described. The developed algorithm is used to model a certain dataset by training a RBFNN using some part of it, and then testing the performance of this RBFNN using the rest of data. The objective function of the proposed algorithm is to minimize the error between the computed output by the model and the target output given in the dataset. The genetic algorithm used in this thesis is an evolutionary algorithm that uses natural evolutionary process for selection and reproduction. An individual is constructed from the RBFNN parameters, which are hidden units, centers, weights, widths and bias associated with hidden units and output of RBFNN. Therefore, the fitness values are also assigned to all chromosomes as a result of getting the difference between the target output and the computed output by the RBFNN, in which a Gaussian function was used as an activation function. In experimental results, different tests were conducted in order to see the performance and correctness of the developed model. Since the number of hidden units plays an important role as well as weights, the intervals of weight values were adjusted accordingly and the number of hidden units was changed for different tests. As a result of conducted experiments, it is observed that the developed algorithm is successful in obtaining good results by minimizing the error. Keywords: Evolutionary algorithms, Radial Basis Functions, Data Modeling. ……………………………………………………………………………………………………………………………………………………………………………………………………………………
An automation on interactive advertisement for companies on local street in TRNC
ABSTRACT: In this thesis, an online interactive Web application is developed to reduce the difficulties of communication between the customers and the companies on a local street, be a bridge between the customers and the companies and contribute in economic growth. The developed application has a friendly user interface for tablet PCs and mobile phones. In order to let the customers to navigate the companies freely, visual representation is used in the application. Our system is developed as a prototype and applicable for using in any local street of any city. Keywords: Web application, prototype, local street. …………………………………………………………………………………………………………………………
Semantic Web Service Filtering Strategy Based on Categories, Attributes and Mediation
[Abstract Not Available]
Palmprint Image Identification Using PCA, LBP and HOG Features
Biometrics considered as the science which is playing an important role of person recognition. User identification mainly based on the physiological characteristics of an individual. Palmprint is an example of physiological characteristics of an individual which can be easily captured by using some types of sensors and cameras. The palmprint has many nature compositions which contain rich features that mainly used for distinguishing such as, wrinkles, ridges, principal lines, singular and minutiae points, these make a palmprint as one of a unique biometric and reliable for human recognition. In this work different features extraction algorithms were used such as a texture based method (LBP, HOG), and appearance based method (PCA). Also K-Cross Validation algorithm was implemented. The accuracy rates of recognition results of implemented algorithms were acquired and compared. Keywords: Biometric, Palmprint, Accuracy rates and Recognition algorithms.
An investigation of the coefficient of variation using the dissipative stochastic mechanics based neuron model
ABSTRACT: In recent years, it has been argued and shown experimentally that ion channel noise in neurons can have profound effects on the neuron’s dynamical behavior. Most profoundly, ion channel noise was seen to be able to cause spontaneous firing and stochastic resonance. A physical approach for the description of neuronal dynamics under the influence of ion channel noise was proposed recently through the use of dissipative stochastic mechanics by Guler in a series of papers. He consequently introduced a computational neuron model incorporating channel noise. The most distinctive feature of the model is the presence of so-called the renormalization terms therein. This model exhibits experimentally compatible noise induced transitions among its dynamical states, and gives the rose-Hindmarash model of the neuron in the deterministic limit. In this thesis, statistics of coefficient of variation will be investigated using the dissipative stochastic mechanics based neuron model. Keywords: Ion Channel Noise, Stochastic Ion Channels, Neuronal Dynamic, Hindmarsh-Rose Model, Dissipative Stochastic Mechanism Model. …………………………………………………………………………………………………………………………………………………………………………………………………………
A CUDA based Parallel Implementation of Speaker Verification System
ABSTRACT: Speaker Verification (SV) is a type of speaker recognition that validates the identity of a claimed person by his/her voice. Training the models from large speech data requires a significant amount of memory and computational load. In this thesis we present a parallel implementation of speaker verification system based on Gaussian Mixture Modeling – Universal Background Modeling (GMM – UBM) designed for many-core architecture of NVIDIA’s Graphics Processing Units (GPU) using CUDA single instruction multiple threads (SIMT) model. CUDA implementation of these algorithms is designed in such a way that the speed of computation of the algorithm increases with number of GPU cores. In our experiments we have achieved 30 times speedup for k-means clustering and 65 times speedup for Expectation Maximization (EM) for an input of about 350K frames of 16 dimensions and 1024-2048 mixtures on GeForce GTX 570 (NVIDIA Fermi Series) with 480 cores when compared to a single threaded implementation on the traditional CPU. Keywords: Speaker Verification, Gaussian Mixture Models, Parallel Computing, Compute Unified Device Architecture, General-purpose computing on graphics processing units. ……………………………………………………………………………………………………………………………………………………………………………………………………………………
Texture Classification Using Texture-based Feature Extraction Algorithms
Texture is one of the significant characteristics used in identifying objects of interest or regions in an image. Texture is an important characteristic of surface property in visual scenes and is a power cue in visual perception. The real applications of texture classification are remote sensing, medical imaging, industrial inspection and pattern recognition. Texture images are highly affected by rotation and illumination. Extracting texture features that are rotation-invariant and insensitive to illumination with high classification accuracy is still a challenge. Texture analysis has been a popular area of study in computer vision for decades. In this thesis, six texture-based feature extractors that may perform variously to rotation and illumination are used namely Local Binary Patterns (LBP), Complete Local Binary Patterns (CLBP), Segmentation-based Fractal Texture Analysis (SFTA), Histogram of Oriented Gradients (HOG), Rotation Invariant Histogram of Oriented Gradients (RIHOG) and Haralick feature extractor. They are implemented and tested on three benchmark texture databases, such as The Columbia-Utrecht Database (CUReT), University of Oulu Texture database (OUTex) and Textured Surfaces Database. For feature matching, two classifiers are used namely Naive Bayes and Support Vector Machines (SVM). A comparative study is presented at the end of the experimental evaluations on texture classification.
Adaptive Differential Evolution Algorithm for Single and Multi-Objective Numerical Optimization
“DE/current-to-pbest” is a new and increasingly common mutation strategy that involves an additional external archive and adaptively updates the control. This thesis introduces a novel algorithm known as JADE. The “DE/current-to-pbest” is a simplification of the typical “DE/current-to-best,” while historical data is used by the additional archive operation to provide information on progress direction. Both convergence performance and the diversity of the population are enhanced by the two operations. The control parameters are automatically updated to the appropriate values through parameter adaptation, which avoids relying on outdated information regarding the relationship between the characteristics of the optimization problems and the parameter settings. This thesis work introduces a JADE Algorithm and examines its feasibility based on the results of CEC'17 expensive benchmark problems for single objective optimization problems and for Multi-objective optimization. The methods used in our studies are compared to different well-knows methods proposed in the related literature was conducted. The final ranking of all test problems indicate that JADE was always among the top best algorithms that were used for the same purpose.
Palmprint Recognition with Statistical, Wavelet and Local Feature Extraction Methods
ABSTRACT: Palmprint recognition has gained significant importance in biometric and multi- biometric identification systems and it has been widely used in most of the security projects. The reason behind this is that a palmprint is a unique sample for each individual person. It is a biometric signature of fix shape; a born baby holds the same shape up to death. Nowadays most of the studies focus on enhancing the recognition rate and determining the age and gender of palmprint images. In this thesis, three different feature extraction techniques have been applied on images of a well know palmprint database. The three methods can be characterized as a statistical method namely principle component analysis (PCA), a transformation method namely Haar wavelets and a texture method namely local binary pattern (LBP). The aim of applying different feature extraction methods is to compare their relative performance and determine the best method for palmprint recognition. Moreover, hybrid methods combining the algorithms mentioned above have been created in order to take the advantage of two or more feature extraction methods. Outputs individual method are fused using voting techniques. Keywords: Palmprint recognition, Principal Component Analysis, Local Binary Patterns, Haar Wavelets. …………………………………………………………………………………………………………………………
Genetic Optimization for Image Segmentation
ABSTRACT: The present study is concerned with optimization of image segmentation using Genetic Algorithms. The developed implementation utilizes the Split/Merge approach for image segmentation. The split portion involves K-means clustering algorithm and then a Genetic Algorithm (GA) with a proficient chromosome encoding model is applied in the merge procedure. The goals of this study are as follows: a) To study different image segmentation approaches in the literature, b) To review the objectives of optimization in image segmentation, c) To conduct and implement a genetic algorithm optimization for image segmentation. Experimental studies have shown that the above mentioned objectives are all achieved with the developed implementation. Keywords: Image segmentation, genetic algorithms, genetic optimization. ……………………………………………………………………………………………………………………………………………………………………………………………………………………