Hamed Hamid Muhammed

Feature Vector Based Analysis of Hyperspectral Crop Reflectance Data for Discrimination and Quantification of Fungal Disease Severity in Wheat

The impact of plant pathological stress on crop reflectance can be measured both in broad-band vegetation indices and in narrow or local characteristics of the reflectance spectra. This work is con ...

Unsupervised fuzzy clustering and image segmentation using weighted neural networks

A new class of neuro fuzzy systems, based on so-called weighted neural networks (WNN), is introduced and used for unsupervised fuzzy clustering and image segmentation. Incremental and fixed (or grid-partitioned) weighted neural networks are presented and used for this purpose. The WNN algorithm (incremental or grid-partitioned) produces a net, of nodes connected by edges, which reflects and preserves the topology of the input data set. Additional weights, which are proportional to the local densities in the input space, are associated with the resulting nodes and edges to store useful information about the topological relations in the given input data set. A fuzziness factor, proportional to the connectedness of the net, is introduced in the system. A watershed-like procedure is used to cluster the resulting net. The number of resulting clusters is determined by this procedure. Experiments confirm the usefulness and efficiency of the proposed neuro fuzzy systems for image segmentation and, in general, for clustering multi- and high-dimensional data.

Using hyperspectral reflectance data for discrimination between healthy and diseased plants, and determination of damage-level in diseased plants

It has been found, through many research works, that hyperspectral reflectance data can be used for studying the pathological conditions of crops. The influence of the pathological status of a crop on its spectral characteristics can be visible or detectable in the visible and/or the near-infrared regions of the electromagnetic spectrum, depending on the spectral effects of the pathological conditions of the crop. Differences in the spectral characteristics between normal (i.e. healthy) crops and others suffering from physiological stress or disease, can be revealed and/or magnified by simply normalising the data properly. Such effects can be achieved by normalising the hyperspectral reflectance data into zero-mean and unit variance vectors (i.e. whitening the data). Spectral-wise and/or band-wise normalisation can be performed here. In the experimental part of this work we used a reference data set consisting of hyperspectral reflectance data vectors and the corresponding field measurements of leaf-damage level in the plants. Then, after normalising the new hyperspectral reflectance data; a nearest neighbour classifier is used to classify our new data against the reference data. The correlation coefficient and the sum of squared differences are used as distance measures (between two vectors) in the nearest neighbour classifier. High correlation is obtained between the classification results and the corresponding field leaf-damage measurements, confirming the usefulness and efficiency of this method for this type of analysis.

Using feature-vector based analysis, based on principal component analysis and independent component analysis, for analysing hyperspectral images

A pixel in a hyperspectral image can be considered as a mixture of the reflectance spectra of several substances. The mixture coefficients correspond to the (relative) amounts of these substances. The benefit of hyperspectral imagery is that many different substances can be characterised and recognised by their spectral signatures. Independent component analysis (ICA) can be used for the blind separation of mixed statistically independent signals. Principal component analysis (PCA) also gives interesting results. The next step is to interpret and use the ICA or PCA results efficiently. This can be achieved by using a new technique called feature-vector based analysis (FVBA), which produces a number of component-feature vector pairs. The obtained feature vectors and the corresponding components represent, in this case, the spectral signatures and the corresponding image weight coefficients (the relative concentration maps) of the different constituting substances.

Unsupervised Fuzzy Clustering Using Weighted Incremental Neural Networks

A new more efficient variant of a recently developed algorithm for unsupervised fuzzy clustering is introduced. A Weighted Incremental Neural Network (WINN) is introduced and used for this purpose. The new approach is called FC-WINN (Fuzzy Clustering using WINN). The WINN algorithm produces a net of nodes connected by edges, which reflects and preserves the topology of the input data set. Additional weights, which are proportional to the local densities in input space, are associated with the resulting nodes and edges to store useful information about the topological relations in the given input data set. A fuzziness factor, proportional to the connectedness of the net, is introduced in the system. A watershed-like procedure is used to cluster the resulting net. The number of the resulting clusters is determined by this procedure. Only two parameters must be chosen by the user for the FC-WINN algorithm to determine the resolution and the connectedness of the net. Other parameters that must be specified are those which are necessary for the used incremental neural network, which is a modified version of the Growing Neural Gas algorithm (GNG). The FC-WINN algorithm is computationally efficient when compared to other approaches for clustering large high-dimensional data sets.

Using Homo-Separation of Variables for Solving Systems of Nonlinear Fractional Partial Differential Equations

A new method proposed and coined by the authors as the homo-separation of variables method is utilized to solve systems of linear and nonlinear fractional partial differential equations (FPDEs). The new method is a combination of two well-established mathematical methods, namely, the homotopy perturbation method (HPM) and the separation of variables method. When compared to existing analytical and numerical methods, the method resulting from our approach shows that it is capable of simplifying the target problem at hand and reducing the computational load that is required to solve it, considerably. The efficiency and usefulness of this new general-purpose method is verified by several examples, where different systems of linear and nonlinear FPDEs are solved.

USING WEIGHTED FIXED NEURAL NETWORKS FOR UNSUPERVISED FUZZY CLUSTERING

A novel algorithm for unsupervised fuzzy clustering is introduced. The algorithm uses a so-called Weighted Fixed Neural Network (WFNN) to store important and useful information about the topological relations in a given data set. The algorithm produces a weighted connected net, of weighted nodes connected by weighted edges, which reflects and preserves the topology of the input data set. The weights of the nodes and the edges in the resulting net are proportional to the local densities of data samples in input space. The connectedness of the net can be changed, and the higher the connectedness of the net is chosen, the fuzzier the system becomes. The new algorithm is computationally efficient when compared to other existing methods for clustering multi-dimensional data, such as color images.

Noise type evaluation in positron emission tomography images

In Positron Emission Tomography (PET), the coincident emission of gamma photon pairs constitutes the useful signals that should be detected and processed to reconstruct the desired PET images of the studied objects. However, along with the useful signal, noise is also generated and added to the detected signals that are sorted with respect to their line-ofresponse and arranged as a sinogram for each two-dimensional slice. In this paper, the type and properties of noise in PET sinogram data will be evaluated. Furthermore, the effect of the used linear and non-linear image denoising and reconstruction procedures on the type of noise will be analyzed. For this purpose, the Gaussian filter, the Median filter, the Patch Confidence k-Nearest Neighbor filter (PCkNN) and the Block Matching 3D filter (BM3D) were used to denoise PET image data, as well as the maximum likelihood expectation maximization algorithm (MLEM) and the Filtered Back Projection algorithm (FBP) to reconstruct the PET images.

Automated Tracking of the Carotid Artery in Ultrasound Image Sequences Using a Self Organizing Neural Network

An automated method for the segmentation and tracking of moving vessel walls in 2D ultrasound image sequences is introduced. The method was tested on simulated and real ultrasound image sequences of the carotid artery. Tracking was achieved via a self organizing neural network known as Growing Neural Gas. This topology-preserving algorithm assigns a net of nodes connected by edges that distributes itself within the vessel walls and adapts to changes in topology with time. The movement of the nodes was analyzed to uncover the dynamics of the vessel wall. By this way, radial and longitudinal strain and strain rates have been estimated. Finally, wave intensity signals were computed from these measurements. The method proposed improves upon wave intensity wall analysis, WIWA, and opens up a possibility for easy and efficient analysis and diagnosis of vascular disease through noninvasive ultrasonic examination.

Optimization of radiation doses in panoramic X-ray examination using automated image processing

Radiological techniques based on X-rays are well established in medical diagnostics and there are known risks associated with the use of ionizing radiation like X-rays. That explains why the X-ray technology is constantly under development in the pursuit of new technologies that can contribute to reduce radiation dose to patients. Since the reduction of a radiation dose generally results in a poorer image quality, we have investigated whether the use of digital image processing can provide panoramic radiographs with enhanced image quality. An automated image processing algorithm was proposed and employed for this purpose. Panoramic X-ray examination is an important and common tool in dental radiology, used especially for children and teenagers. The technique is used to create an overview of a patients jaw.