Analysis of classification accuracy for pre-filtered multichannel remote sensing data

Noise is one of the main factors degrading the quality of original multichannel remote sensing data and its presence influences classification efficiency, object detection, etc. Thus, pre-filtering is often used to remove noise and improve the solving of final tasks of multichannel remote sensing. Recent studies indicate that a classical model of additive noise is not adequate enough for images formed by modern multichannel sensors operating in visible and infrared bands. However, this fact is often ignored by researchers designing noise removal methods and algorithms. Because of this, we focus on the classification of multichannel remote sensing images in the case of signal-dependent noise present in component images. Three approaches to filtering of multichannel images for the considered noise model are analysed, all based on discrete cosine transform in blocks. The study is carried out not only in terms of conventional efficiency metrics used in filtering (MSE) but also in terms of multichannel data classification accuracy (probability of correct classification, confusion matrix). The proposed classification system combines the pre-processing stage where a DCT-based filter processes the blocks of the multichannel remote sensing image and the classification stage. Two modern classifiers are employed, radial basis function neural network and support vector machines. Simulations are carried out for three-channel image of Landsat TM sensor. Different cases of learning are considered: using noise-free samples of the test multichannel image, the noisy multichannel image and the pre-filtered one. It is shown that the use of the pre-filtered image for training produces better classification in comparison to the case of learning for the noisy image. It is demonstrated that the best results for both groups of quantitative criteria are provided if a proposed 3D discrete cosine transform filter equipped by variance stabilizing transform is applied. The classification results obtained for data pre-filtered in different ways are in agreement for both considered classifiers. Comparison of classifier performance is carried out as well. The radial basis neural network classifier is less sensitive to noise in original images, but after pre-filtering the performance of both classifiers is approximately the same.

The bactericidal effect of dendritic copper microparticles, contained in an alginate matrix, on Escherichia coli

Although the bactericidal effect of copper has been known for centuries, there is a current resurgence of interest in the use of this element as an antimicrobial agent. During this study the use of dendritic copper microparticles embedded in an alginate matrix as a rapid method for the deactivation of Escherichia coli ATCC 11775 was investigated. The copper/alginate produced a decrease in the minimum inhibitory concentration from free copper powder dispersed in the media from 0.25 to 0.065 mg/ml. Beads loaded with 4% Cu deactivated 99.97% of bacteria after 90 minutes, compared to a 44.2% reduction in viability in the equivalent free copper powder treatment. There was no observed loss in the efficacy of this method with increasing bacterial loading up to 10(6) cells/ml, however only 88.2% of E. coli were deactivated after 90 minutes at a loading of 10(8) cells/ml. The efficacy of this method was highly dependent on the oxygen content of the media, with a 4.01% increase in viable bacteria observed under anoxic conditions compared to a >99% reduction in bacterial viability in oxygen tensions above 50% of saturation. Scanning electron micrographs (SEM) of the beads indicated that the dendritic copper particles sit as discrete clusters within a layered alginate matrix, and that the external surface of the beads has a scale-like appearance with dendritic copper particles extruding. E. coli cells visualised using SEM indicated a loss of cellular integrity upon Cu bead treatment with obvious visible blebbing. This study indicates the use of microscale dendritic particles of Cu embedded in an alginate matrix to effectively deactivate E. coli cells and opens the possibility of their application within effective water treatment processes, especially in high particulate waste streams where conventional methods, such as UV treatment or chlorination, are ineffective or inappropriate.