We have collated hERG inhibition data of 165 compounds from literature and employed two regression procedures, namely, Local Lazy Regression (LLR) and k-Nearest Neighbor (kNN)-QSAR regression methods in combination with Genetic Algorithms (GAs) to select significant and independent molecular descriptors and to build robust predictive models. This methodology helped us to derive four, optimal 2D-and 3D-QSPR models, M1 -M4, based on five descriptors. Extensive validation tests using leave-one-out method and 61 compounds that are not used in the model generation strongly suggest that: (i) models M1 and M2, based on LLR, are very stable and robust; (ii) the model, M2 based on 3-D descriptors, performs better than the one based on 2-D descriptors, M1; and (iii) LLR method outperforms kNN regression approach. These results strongly suggest that the combination of GA and LLR method is a promising methodology, to build multiple stable models that are useful in consensus prediction. Further, from the analysis of the physical meaning of the descriptors, used in the best 2-D and 3-D descriptor models, M1 and M2, the significant physico-chemical forces that determine the hERG inhibition profile of small organic compounds are uncovered. Finally, as the models reported herein, are based on computed properties, they appear a valuable tool in virtual screening, where selection and prioritization of candidates is required.
Agriculture productivity mainly depends on Indian economy. Hence, Disease prediction plays a important role in agriculture field. In image analyzing the symptoms is an essential part for feature extraction and classification. However, some of the challenges are still lacking to predict the disease. To meet those challenges, the proposed algorithm focuses on a specific problem to predict the disease from early symptoms. Bacterial Leaf Blight and Brown Spot are a major bacterial and fungal disease respectively in rice (Oryza sativa) crops, it causes yield loss and reduce the grains quality. This research work focused on automatic detection method for image segmentation on rice leaves under wide range of environmental condition for further analysis. Various hybrid techniques for image segmentation and classification algorithms were analyzed and an automatic detection method has been proposed for identifying the specified diseases in rice leaves under different environmental condition.
Automatic detection of plant diseases is one the important challenging problems in agriculture field. So the basic analyzing method for automatic identification is filtering technique of preprocessing method. Hence, this Image filtering plays a important role to remove noise from image. Consequently this preprocessing method is the initial stage to make better image quality. The purpose of this paper is comparing four types of filtering techniques to differentiate the image quality in Gaussian filter, median filter, mean filter and weiner respectively filter using common data set. The image quality of overall results shows that the comparison of various filtering technique performed to enhancement quality using hybrid technique. So this paper gives best starting for researchers to automatic detection of rice plant disease detection.
Coin is very important role in human's day life. For daily routine like shop, super market, banks etc the coins to be used. The coin is important part of economies and currency and it is used to pay for goods and also for our needs. Here the Indian coin has many number of count five rupee, ten rupee, two rupee, from this any one of the coin we are going to extract the texture feature for our Indian coin, first step is to preprocess the image is that method to enhance the image and remove the noise from enhanced image. For extracting clear information the image has to be preprocessed through some of the filtering techniques such as image size has to be resized, changing the contrast of the image, changing RGB to grayscale conversion for further operation such as segmentation and classification. At last the values to be compared by using PSNR, SNR, MSE of Filter noise removal with respective coin images.
Accurate and reliable diagnosis of carotid artery stenosis depends on the quality of IVUS images. Especially in ultrasound images where coherent sources are involved, speckle noise causes blurring and loss of information. Thus, methods to eliminate speckle noise plays an essential part in the field of medical imaging. This paper compares various speckle noise suppression algorithms for carotid artery ultrasound images. Speckle noise reduction algorithms that are implemented includes Homomorphic Wavelet Level 1 and Level 2, Perona-Malik (PM) filter, Modified PM1, Modified PM2, Adaptive PM, Butterworth Filter, Doubly Degenerative Diffusion (DDD), Speckle Reducing Anisotropic Diffusion (SRAD) and Total Variance (TV) filter. A quantitative evaluation is carried out by estimating Signal to Noise Ratio (SNR), Peak Signal to Noise Ratio (PSNR), Structural Similarity Index (SSIM), Beta Metric and Natural Image Quality Evaluator (NIQE). The performance metrics shows that Homomorphic Wavelet Level1, Modified PM 2, Adaptive PM and SRAD are robust in eliminating speckle noise from carotid artery ultrasound images, thereby increasing its diagnostic accuracy. Though DDD and TV approach have good SNR and PSNR values, their low Beta metric and high NIQE values have made them ineffective.
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.