http://dspace1.isd.glam.ac.uk:80/dspace/handle/10265/346 2013-05-22T05:36:13Z http://dspace1.isd.glam.ac.uk:80/dspace/handle/10265/515 Title: Round-robin sequential forward selection algorithm for prostate cancer classification and diagnosis using multispectral imagery Authors: Roula, Mohammed. A Abstract: This paper proposes an automatic classification system for the use in prostate cancer diagnosis. The system aims to detect and classify prostatic tissue textures captured from microscopic samples taken from needle biopsies. Biopsies are usually analyzed by a trained pathologist with different grades of malignancy typically corresponding to different structural patterns as well as apparent textures. In the context of prostate cancer diagnosis, four major groups have to be accurately recognized: stroma, benign prostatic hyperplasia, prostatic intraepithelial neoplasia, and prostatic carcinoma. Recently, multispectral imagery has been proposed as a new image acquisition modality which unlike conventional RGB-based light microscopy allows the acquisition of a large number of spectral bands within the visible spectrum, resulting in a large feature vector size. Many features in the initial feature set are irrelevant to the classification task and are correlated with each other, resulting in an increase in the computational complexity and a reduction in the recognition rate. In this paper, a Round-Robin (RR) sequential forward selection RR-SFS is used to address these problems. RR is a technique for handling multi-class problems with binary classifiers by training one classifier for each pair of classes. The experimental results demonstrate this finding when compared with classical method based on the multiclass SFS and other ensemble methods such as bagging/boosting with decision tree (C4.5) classifier where it is shown that RR-SFS method achieves the best results with a classification accuracy of 99.9%. 2012-05-01T23:00:00Z http://dspace1.isd.glam.ac.uk:80/dspace/handle/10265/514 Title: Approaches for improving image quality in magnetic induction tomography Authors: Roula, Mohammed. A Abstract: Magnetic induction tomography (MIT) is a contactless and non-invasive method for imaging the passive electrical properties of objects. Measuring the weak signal produced by eddy currents within biological soft tissues can be challenging in the presence of noise and the large signals resulting from the direct excitation–detection coil coupling. To detect haemorrhagic stroke in the brain, for instance, high measurement accuracy is required to enable images with enough contrast to differentiate between normal and haemorrhaged brain tissues. The reconstructed images are often very sensitive to inevitable measurement noise from the environment, system instabilities and patient-related artefacts such as movement and sweating. We propose methods for mitigating signal noise and improving image reconstruction. We evaluated and compared the use of a range wavelet transforms for signal denoising. Adaptive regularization methods including L-curve, generalized cross validation (GCV) and noise estimation were also compared. We evaluated all these described methods with measurements of in vitro tissues resembling a peripheral haemorrhagic cerebral stroke created by placing a bio-membrane package filled with 10 ml blood in a swine brain of 100 ml. We show that wavelet packet denoising combined with adaptive regularization can improve the quality of reconstructed images. 2012-05-01T23:00:00Z http://dspace1.isd.glam.ac.uk:80/dspace/handle/10265/505 Title: Radiated emissions and experimental precautions of equipment with cables in GTEM cells Authors: Al-Daher, Zaid Muhi-Eldeen Abstract: Any electric or electronic equipment sold within the European Union has to comply with the EC Directive on Electromagnetic Compatibility (EMC). To achieve compliance, the equipment must be tested for radiated/conducted emissions and immunity. A wide range of national and international testing methods and standards are in force such as the IEC 61000-40-20. However, standards in general lack of describing testing methods for equipment with cables. Since most devices and systems contain leads and cables; the current standards cannot be directly employed. In an effort to approach this crucial matter, we present the outcomes of measurements conducted on an EUT (metal box) with different cable bundle configurations, in conjunction with both, the correlation algorithm given in the standards and the repeatability concerns between different GTEM cells 2012-04-30T23:00:00Z http://dspace1.isd.glam.ac.uk:80/dspace/handle/10265/502 Title: Measurements and modelling of cellular interference in local point-to-multipoint distribution systems Authors: Al-Daher, Zaid Muhi-Eldeen Abstract: Frequency and polarisation reuse for optimum spectral efficiency in local multipoint distribution system (LMDS) networks generate co- and adjacent-channel inter-and intra-cell interference because of the line-of-sight constraints among transmitting and receiving antennas. Such operational constraints limit the system capacity and affect link performance. Measurements at 40 GHz from a number of possible interference scenarios for two different LMDS reuse cellular plans of dual-frequency and dual-polarisation discriminations are presented. An electromagnetic-stochastic propagation model is employed. The model successfully predicts the interference parameters and takes into account the effects of multiple paths and depolarisation caused by reflection and scatter from building surfaces at millimetre-wave frequencies. The probability density function of the signal-to-interference ratio and the statistical channel parameters, such as the average signal strength and the Rician K-factor, are extracted from the measured data and compared with model predictions. 2012-04-30T23:00:00Z