When labeled training data is scarce, a promising data augmentation approach is to generate visual features of unknown classes using their attributes. To learn the class conditional distribution of CNN features, these models rely on pairs of image features and class attributes. Hence, they can not make use of the abundance of unlabeled data samples. In this paper, we tackle any-shot learning problems i.e. zero-shot and few-shot, in a unified feature generating framework that operates in both inductive and transductive learning settings. We develop a conditional generative model that combines the strength of VAE and GANs and in addition, via an unconditional discriminator, learns the marginal feature distribution of unlabeled images. We empirically show that our model learns highly discriminative CNN features for five datasets, i.e. CUB, SUN, AWA and ImageNet, and establish a new state-of-the-art in any-shot learning, i.e. inductive and transductive (generalized) zeroand few-shot learning settings. We also demonstrate that our learned features are interpretable: we visualize them by inverting them back to the pixel space and we explain them by generating textual arguments of why they are associated with a certain label.

No abstract

Computed tomographic (CT) images are widely used in the diagnosis of stroke. In this paper, we present an automated method to detect and classify an abnormality into acute infarct, chronic infarct and hemorrhage at the slice level of non-contrast CT images. The proposed method consists of three main steps: image enhancement, detection of mid-line symmetry and classification of abnormal slices. A windowing operation is performed on the intensity distribution to enhance the region of interest. Domain knowledge about the anatomical structure of the skull and the brain is used to detect abnormalities in a rotation- and translation-invariant manner. A two-level classification scheme is used to detect abnormalities using features derived in the intensity and the wavelet domain. The proposed method has been evaluated on a dataset of 15 patients (347 image slices). The method gives 90% accuracy and 100% recall in detecting abnormality at patient level; and achieves an average precision of 91% and recall of 90% at the slice level.

No abstract

This research paper suggests and analyse a technique for congestion control in mobile ad hoc networks. The technique is based on a new hybrid approach that uses clustering and queuing techniques. In clustering, in general cluster head transfers the data, following a queuing method based on a RED (Random Early Detection), the mobile environment makes it Mobile RED (or MRED), It majorly depends upon mobility of nodes and mobile environments leads to unpredictable queue size. To simulate this technique, the Network Simulator 2 (or NS2) is used for various scenarios. The simulated results are compared with NRED (Neighbourhood Random Early Detection) queuing technique of congestion control. It has been observed that the results are improved using MRED comparatively.

A mobile adhoc network is an autonomous network that consists of nodes which communicate with each other with wireless channel. Due to its dynamic nature and mobility of nodes, mobile adhoc networks are more vulnerable to security attack than conventional wired and wireless networks. One of the principal routing protocols AODV used in MANETs. The security of AODV protocol is influence by malicious node attack. In this attack, a malicious node injects a faked route reply claiming to have the shortest and freshest route to the destination. However, when the data packets arrive, the malicious node discards them. To preventing malicious node attack, this paper presents PPN (Prime Product Number) scheme for detection and removal of malicious node.

No abstract

No abstract