Quantcast


CURATOR
A pinboard by
Ali lalbakhsh

PhD Student, Macquarie University

PINBOARD SUMMARY

Design a compact and planar satellite antenna to replace the current parabolic antennas.

My PhD has been designed to have a real impact, as it is dealing with a real issue in the electromagnetics field. There is a crucial need for inexpensive and efficient passive devices that can provide desired EM properties in conjunction with high-gain antennas like Resonant Cavity antennas (RCAs). A full accommodation of this necessity would be a breakthrough in the field and will introduce applications which can be considered as 21st century technologies. Low-cost and reliable Meta-surfaces used with planar RCAs would make the bulky parabolic antennas redundant and satellite communication would be far more accessible, regardless of terrestrial position. Replacing reflector-shaped dishes with planar relatively small antennas composed of Meta-surfaces and RCAs will make a reliable satellite TV reception available even for moving vehicles, opening up a huge market. Such a mechanism can provide the internet through satellites, which is an emerging multibillion-dollar market which can remove inaccessibility to the internet in the remote or less-developed areas, specially in Africa, which is consistent with two of the United Nation's key issues (Development of Africa and Human rights). It should be noted that an specialized electromagnetic optimization algorithm based on particle swarm intelligence has been implemented for designing passive Meta-surfaces.

6 ITEMS PINNED

Multivariate Approach for Alzheimer's Disease Detection Using Stationary Wavelet Entropy and Predator-Prey Particle Swarm Optimization.

Abstract: The number of patients with Alzheimer's disease is increasing rapidly every year. Scholars often use computer vision and machine learning methods to develop an automatic diagnosis system.In this study, we developed a novel machine learning system that can make diagnoses automatically from brain magnetic resonance images.First, the brain imaging was processed, including skull stripping and spatial normalization. Second, one axial slice was selected from the volumetric image, and stationary wavelet entropy (SWE) was done to extract the texture features. Third, a single-hidden-layer neural network was used as the classifier. Finally, a predator-prey particle swarm optimization was proposed to train the weights and biases of the classifier.Our method used 4-level decomposition and yielded 13 SWE features. The classification yielded an overall accuracy of 92.73±1.03%, a sensitivity of 92.69±1.29%, and a specificity of 92.78±1.51%. The area under the curve is 0.95±0.02. Additionally, this method only cost 0.88 s to identify a subject in online stage, after its volumetric image is preprocessed.In terms of classification performance, our method performs better than 10 state-of-the-art approaches and the performance of human observers. Therefore, this proposed method is effective in the detection of Alzheimer's disease.

Pub.: 22 Jul '17, Pinned: 26 Aug '17