Subclinical mastitis (SCM) represents a major proportion of the burden of mastitis. Determining somatic cell count (SCC) and electrical conductivity (EC) of milk are useful approaches to detect SCM. In order to correlate grades of SCM with the load of five major mastitis pathogens, 246 milk samples from a handful of organized and unorganized sectors were screened. SCC (>5 × 10(5)/mL) and EC (>6.5 mS/cm) identified 110 (45 %) and 153 (62 %) samples, respectively, to be from SCM cases. Randomly selected SCM-negative samples as well as 186 samples positive by either SCC or EC were then evaluated for isolation of five major mastitis-associated bacteria. Of the 323 isolates obtained, 95 each were S. aureus and coagulase-negative staphylococci (CoNS), 48 were E. coli and 85 were streptococci. There was no association between the distribution of organisms and (a) the different groups of SCC, or (b) organised farms and unorganised sectors. By contrast, there was a significant difference in the distribution of CoNS, and not other species, between organized farms and unorganized sectors. In summary, bacteria were isolated irrespective of the density of somatic cells or the type of farm setting, and the frequency of isolation of CoNS was higher with organized farms. These results suggest the requirement for fine tuning SCC and EC limits and the higher probability for CoNS to be associated with SCM in organized diary sectors, and have implications for the identification, management and control of mastitis in India.
Sign language recognition (SLR) is considered a multidisciplinary research area engulfing image processing, pattern recognition and artificial intelligence. The major hurdle for a SLR is the occlusions of one hand on another. This results in poor segmentations and hence the feature vector generated result in erroneous classifications of signs resulting in deprived recognition rate. To overcome this difficulty we propose in this paper a 4 camera model for recognizing gestures of Indian sign language. Segmentation for hand extraction, shape feature extraction with elliptical Fourier descriptors and pattern classification using artificial neural networks with backpropagation training algorithm. The classification rate is computed and which provides experimental evidence that 4 camera model outperforms single camera model.
Machine learning is penetrating most of the classification and recognition tasks performed by a computer. This paper proposes the classification of flower images using a powerful artificial intelligence tool, convolutional neural networks (CNN). A flower image database with 9500 images is considered for the experimentation. The entire database is sub categorized into 4. The CNN training is initiated in five batches and the testing is carried out on all the for datasets. Different CNN architectures were designed and tested with our flower image data to obtain better accuracy in recognition. Various pooling schemes were implemented to improve the classification rates. We achieved 97.78% recognition rate compared to other classifier models reported on the same dataset.
A study was conducted to observe the prevalence of Culicoides a biting midge, important pest and prime vector for various viruses, protozoa and filarid worms. In the vicinity of 11 different farms of cattle, buffalo, sheep and goats in Bangalore rural and urban districts the flies were collected by using UV traps (Onderstepoort Veterinary Institute. ARC. LNR) connected with suction fan for the period of 1 year (2012)(2013). Around 83,629 Culicoides were collected of which 77,906 (93.16 %) were female and 5,723 (6.84 %) were males and 40,120 (47.97 %) of C. imicola, 39,366 (47.07 %) C. oxystoma, 2,504 (2.99 %) C. actoni, 1,145 (1.37 %) C. peregrinus, 145 (0.17 %) C. huffi, 120 (0.16 %) C. innoxius, 90 (0.11 %) C. palpifer, 67 (0.08 %) C. anopheles, 37 (0.04 %) C. circumscriptus and 25 (0.03 %) were C. arakawae. It was observed that C. imicola and C. oxystoma were the most predominant species prevalent in Bangalore rural and urban districts of Karnataka.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.