Yükleniyor…
Yükleniyor…
258
Archived Theses
0
DOIs Assigned
0
Researcher
0%
DOI Rate
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.
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.
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.
Underwater environment is potentially rich for scientific research and explorations, but it is challenging to capture the image of the underwater environment due to light absorption and scattering effects of water. In this research, white balance algorithm is employed to recover the lost color information and multiscale image fusion is applied to the features of gamma corrected and sharpened image for dehazing the underwater image and improve the contrast. This thesis proposes an approach that enhances color correction with Histogram Equalization (HE) and applies Contrast Limited Adaptive Histogram Equalization (CLAHE) to sharpened image to further improve the details of the underwater image. The UIEB and SQUID datasets are used which include underwater scenery with fish, coral reefs, divers, underwater structures and shipwrecks. The application of the multiscale image fusion with proposed algorithm achieves to balance the distorted colors of underwater image and enhances fine details and contrast to improve image quality. Keywords: underwater image enhancement, color compensation, multiscale image fusion.
In this thesis, a tracking system named “Diabetes Tracking System” that provides management and control mechanisms for diabetic patients in North Cyprus is proposed. This system allow to store and manage the diabetic patients' health data related to their diabetes lifelong. The system consists of two parts that are the patient portal used by the diabetic patients and doctors, and the management portal used by the system administrators. By using this system, blood glucose values, nutrition, exercises, medications, laboratory tests, vaccines, diagnosis, yearly examinations, complications, diabetes examinatios and other autoimmum diseases such as celiac or tyroid data of diabetic patients can be stored. All these data of a diabetic patient are used to track his/her course of diabetes by himself and the doctor. In the system, it is possible by super admins to filter diabetic patients in the country. Due the system has dynamic infrastructure for laboratory tests, it is easily adaptable to new developments regarding new laboratory test. The proposed system was designed based on responsive Web interface that makes it compatible with various devices such as desktop and smartphones. Therefore, it is expected to have high usage rates. In adition to this, as improvements have been observed in the clinical data of patients who use such diabetes monitoring systems, it is believed that this system will have positive effects n diabetes treathments of diabetic patients in North Cyprus. Keywords: Diabetes, Responsive Web, Mobile Application, e-Health, m-Health.
The detection of plant diseases is a vital factor in agricultural production worldwide, which if ignored, can lead to tremendous losses of plant products and revenue. Farmers and researchers from many centuries ago have learnt to identify some plant disease manually by inspection, but presently, technological development have advanced cultivation to an industrial scale, therefore detection of plant diseases has also become a great issue of concern as the farmers may be unable to identify the diseases, their point of origin or even the infected plants early enough. This can lead to a disease outbreak. Early detection of plant diseases can immensely reduce or avoid massive potential losses as it will provide the opportunity for active and cautionary measures. In view of the aforementioned issue, carrying out researches on different ways and methods to curb this problem is a vital necessity. This thesis study employs the application of computer vision and image processing techniques for plant disease identification. Principal Component Analysis (PCA), Local Binary Patterns (LBP) and Completed Local Binary Patterns (CLBP) feature extraction methods are used for the extraction of texture-based and appearance-based image features. Disease symptoms are analyzed and identified from four different plant leaves to evaluate the performance of the proposed method. We propose a method that incorporates Feature-Level Fusion of the gray level features and color based features using PCA and LBP methods to create a robust system. The proposed method has proven to be more robust compared to the individual systems using LBP and CLBP. Experiments are conducted on PlantVillage dataset due to its diversified collection of plant leaves. Furthermore, two classifiers are used for classification purposes namely k-Nearest Neighbor (k-NN) and Support Vector Machine (SVM). At the end of the empirical evaluations, a comparative study is presented. Keywords: plant disease identification, leaf images, color spaces, Feature-Level Fusion, feature extraction, texture-based features, appearance-based features.
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.
The most frequently used approaches for imbalance learning are balancing by resampling, cost-sensitive learning and thresholding. In the balancing technique, the minority class is oversampled. Most of the algorithms used for this purpose are variants of the well-known algorithm named SMOTE, which is based on creating synthetic samples on the lines connecting selected minority instances. In cost-sensitive learning, the penalty of misclassifying a minority sample is set to be higher than that of a majority instance. In the thresholding approach, the decision threshold is adjusted to detect the minority class at the cost of increased misclassification of the majority instances. In this thesis, the dependence of the optimal threshold on the performance metric is f irst studied. It is shown that the optimal thresholds for two widely used performance evaluation metrics, namely F score and G mean are different in most of the cases. In order to tackle the threshold estimation problem, building a threshold prediction model is defined as a meta-learning task. Novel features are suggested to quantify the imbalance characteristics of the datasets and the patterns among the prediction scores. The proposed threshold prediction model is built using these features extracted from external data. The model obtained is then employed to estimate the optimal thresholds for previously unseen datasets. Repositioning of samples instead of balancing is also addressed. The classifiers are enforced to learn the decision region of the minority class by mainly repositioning the majority class samples. By repositioning, the regions in which minority instances exist are not outnumbered by the majority class samples. Hence, the classifier labels these regions as the minority class. The minority samples are repositioned in small steps to avoid distorting the original distribution. The potential of the proposed repositioning scheme is also evaluated as a preprocessing algorithm for SMOTE. Keywords: imbalance learning, repositioning, thresholding, balancing, binary classification, SMOTE
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.
Hard optimization problems are solved successfully using nature inspired metaheuristics. However, in many cases of practical optimization problems, also called black-box problems, the evaluation of the objective function is main cause of high demand of computational resources. In the solution of these problems, objective function landscape is modeled mathematically, called a surrogate model which consist of replacing the objective function by an equivalent mathematical model, to reduce the computational evaluation time of the fitness function. The differential evolution (DE) algorithm is implemented with 4 strategies called rand/1, rand/2, best/2 and rand to best/1 to optimize the benchmark functions listed CEC2017 competition with dimensions D=10 and D=30. CEC2017 benchmark set is composed of 30 different functions with different degree of complexities. Locations of optimal solutions for these functions is supposed to be unknown and that’s why they are called black box functions. A surrogate model called the quadratic response surface model (QRSM) is used with Latin hyper square sampling strategy to replace objective function evaluations of benchmark functions. QRMS is used with DE for the solution of CEC2017 benchmark problems for the purpose of evaluating the performance of the surrogate assisted DE algorithm in terms of solution quality and runtime complexity. Experimental results obtained from the 4 different DE and DE+QRSM strategies illustrated that the rand/1 DE strategy was generally the best strategy in speed and accuracy for both dimensions D=10 and D=30. Also, the results generated by DE and DE+QRSM are compared with each other. As illustrated in tables of experimental evaluations, DE is found more accurate in majority of benchmark functions but it is slower generally. Also, a comparative study is done with other published algorithms such as L-SHADE, JSO, DISH, L-SHADE-LBR, JSO-LBR and DISH-LBR. Results obtained by these competitors are compared to only the best DE strategy, which is rand/1, employed within DE and DE+QRSM. The rand/1 strategy implemented within DE function was quit robust and performed better than other algorithms in many cases for D=10, but when implemented within DE+QRSM it becomes the worst one. For D=30 the rand/1 strategy loosed of its performance and was classified before the last position. Its rank is around of 80% when implemented within DE but it stays in last position with DE+QRSM algorithm.