Abstract: Wireless sensor network is highly data centric. Data communication in wireless sensor network must be efficient one and must consume minimum power. Every sensor node consists of multiple sensors embedded in the same node. Thus every sensor node is a source of data. These raw data streams cannot be straightway communicated further to the neighboring node. These sensor data streams are first classified. A group of sensor nodes forms a cluster. Each node transfer data to a cluster head and then cluster head aggregates the data and sends to base station. Hence clustering and classification techniques are important and can give new dimension to the WSN paradigm. Basically, classification system is either supervised or unsupervised, depending on whether they assign new inputs to one of a infinite number of discrete supervised classes or unsupervised categories respectively. ART1 and Fuzzy ART are unsupervised neural network models which are used for classification of sensor data. ART1 model

• Publication Date: 12-Mar-2012
• DOI: 10.15224/978-981-07-1403-1-890
• Views: 0
• Downloads: 0

Abstract: Image denoising algorithms may be the oldest in image processing. A first pre-processing step in analyzing such datasets is denoising, that is, estimating the unknown signal of interest from the available noisy data. There are several different approaches to denoise images. To remove noise several techniques and image denoising filters are used. This paper shows a comparative study and analysis of image denoising techniques relying on fuzzy filters. First is the fuzzy impulse noise detection and reduction method (FIDRM) and second is noise adaptive fuzzy switching median filter for salt and pepper noise reduction (NAFSM). The comparative analysis shows that the NAFSM filter is better then the FIDRM filter in terms of execution time, peak signal to noise ratio (PSNR) and mean square error (MSE).

• Publication Date: 03-Jun-2011
• DOI: 10.15224/978-981-07-1847-3-1027
• Views: 0
• Downloads: 0