Remote sensing images are commonly used to monitor the earth surface evolution. This surveillance can be conducted by detecting changes between acquired at different times and possibly kinds of sensors. A representative case is when an optical image a given area available new in emergency situation (resulting from natural disaster for instance) radar satellite. In such case, with heterogeneous properties have compared change detection. paper proposes approach similarity measurement The...

This paper introduces a Bayesian non parametric (BNP) model associated with Markov random field (MRF) for detecting changes between remote sensing images acquired by homogeneous or heterogeneous sensors. The proposed is built an analysis window which takes advantage of the spatial information via MRF. does not require any priori knowledge about number objects contained in thanks to BNP framework. change detection strategy can be divided into two steps. First, segmentation performed using...

The classification of epileptic seizure events in EEG signals is an important problem biomedical engineering. In this paper we propose a Bayesian method for multivariate signals. based on multilevel 2D wavelet decomposition that captures the distribution energy across different brain rhythms and regions, coupled with generalised Gaussian statistical representation scheme. proposed approach demonstrated challenging paediatric dataset containing both normal function signals, where it...

A statistical model for detecting changes in remote sensing images has recently been proposed (Prendes et al., 2014a,b). This is sufficiently general to be used homogeneous acquired by the same kind of sensors (e.g., two optical from Pléiades satellites, possibly with different acquisition conditions), and heterogeneous an image a satellite synthetic aperture radar (SAR) TerraSAR-X satellite). assumes that each pixel distributed according mixture distributions depending on noise properties...

In recent years, remote sensing of the Earth surface using images acquired from aircraft or satellites has gained a lot attention. The acquisition technology been evolving fast and, as consequence, many different kinds sensors (e.g., optical, radar, multispectral, and hyperspectral) are now available to capture features observed scene. One main objectives is monitor changes on surface. Change detection thoroughly studied in case by same (mainly optical radar sensors). However, due diversity...

Pattern classification in electroencephalography (EEG) signals is an important problem biomedical engineering since it enables the detection of brain activity, particularly early epileptic seizures. In this paper, we propose a k-nearest neighbors for EEG based on t-location-scale statistical representation to detect spike-and-waves. The proposed approach demonstrated real dataset containing both spike-and-wave events and normal function signals, where our performance evaluated terms...

This paper introduces a new statistical model for homogeneous images acquired by the same kind of sensor (e.g., two optical images) and heterogeneous different sensors synthetic aperture radar (SAR) images). The proposed assumes that each image pixel is distributed according to mixture multi-dimensional distributions depending on noise properties transformation between actual scene intensities. parameters this can be estimated classical expectation-maximization algorithm. are finally used...

Spike-and-wave discharge (SWD) pattern classification in electroencephalography (EEG) signals is a key problem signal processing. It particularly important to develop SWD automatic detection method long-term EEG recordings since the task of marking patters manually time consuming, difficult and error-prone. This paper presents new with low computational complexity that can be easily trained if standard medical protocols are respected. The procedure as follows: First, each divided into...

Teaching a speech processing course in an undergraduate engineering program is challenge, especially country where research not priority. We address the concerns of providing suitable training to students, designing syllabus under many constraints, keeping students motivated and finding appropriate way grading. Constant innovation has proven be key this course's success, encouraging our choose among others. The increase enrollment over years both achievement challenge. This initiative...