The purpose of this article is to introduced the concept of weak contraction in cone metric space and also establish a coincidence and common fixed point result for weak contractions in cone metric spaces. Our result proper generalizes the results of Sintunavarat and Kumam [7]. We also give an example in support of our result. Keywords :- Cone metric spaces, weak contraction, weak contraction, coincidence point, common fixed point.
- Brinjal/ egg plant is an important crop in India. It is a warm seasoned crop. Crop undergoes significant damage due to poor soil and weather conditions. In turn farmers face a huge loss. However, an early detection of disease could be find out using image analysis on leaf images, that may result in greater yield. In this paper, a deep learning approach using the concept of transfer learning has been used to detect some of the diseases present in the brinjal crop. Three pretrained Convolution Neural Network (CNN) Architecture AlexNet, GoogleNet and ResNet have been applied on the image data set. 5 diseases have been classified using fully connected layer. ResNet showed the maximum accuracy.
Morphological operators are used in many applications like segmentation, edge detection and image analysis. These operations play a major role in medical image analysis. Therefore a novel approach has been proposed in this paper which improves the results of morphological operations, which in turn lead to improvement in the whole process of medical analysis. The proposed method makes use of effective pre-processing and improves the results of erosion and dilation. Noise from various sources gets introduced into Magnetic Resonance (MR) images. The MR images are firstly denoised and then morphological operations are applied, which results in better erosion and dilation process of MR images. The performance of proposed method is compared qualitatively as well as quantitatively on basis of metrics such as Peak Signal to Noise Ratio (PSNR), Mean Square Error (MSE) and Structure Similarity Index (SSIM) values.
Though semantic data models have become mainstream and gained popularity, they largely handle only textual data, and that only in English. Language-independent preservation of semantics and context related to a domain is required to attain equal status for all languages. Through this we can overcome national barriers which come from variations in languages. This will also facilitate cross-lingual access of information. This chapter discusses the motivation of multilingualism and multimodality and presents and exemplifies the ways through which they can be achieved in semantically enriched knowledge. Different use cases to access and manage this setup are also presented.
In this paper we propose a new approach to find the optimum learning rate that increases the recognition rate and reduces the training time of the back propagation neural network as well as single layer feed forward Neural Network. We give a comparative analysis of performance of back propagation neural network and single layer feed forward neural network. In our approach we use variable learning rate and demonstrate its superiority over constant learning rate. We use different inner epochs for different input patterns according to their difficulty of recognition. We also show the effect of optimum numbers of inner epochs, best variable learning rate and numbers of hidden neurons on training time and recognition accuracy. We run our algorithm for face recognition application using Principal Component Analysis and neural network and demonstrate the effect of number of hidden neurons and size of feature vector on training time and recognition accuracy for given numbers of input patterns. We use ORL database for all the experiments.
Barnsley (2006) introduced the notion of a fractal top, which is an addressing function for the set attractor of an Iterated Function System (IFS). A fractal top is analogous to a set attractor as it is the fixed point of a contractive transformation. However, the definition of IFS is extended so that it works on the colour component as well as the spatial part of a picture. They can be used to colour-render pictures produced by fractal top and stealing colours from a natural picture. Barnsley has used the one-step feed- back process to compute the fractal top. In this paper, the authors introduce a two-step feedback process to compute fractal top for contractive and non-contractive transformations.
