No abstract

During a dermoscopy examination, accurate and automatic skin lesion detection and segmentation can assist medical experts in resecting problematic areas and decrease the risk of deaths due to skin cancer. In order to develop fully automated deep learning model for skin lesion segmentation, the authors design a model Attention Res-UNet by incorporating residual connections, squeeze and excite units, atrous spatial pyramid pooling, and attention gates in basic UNet architecture. This model uses focal tversky loss function to achieve better trade off among recall and precision when training on smaller size lesions while improving the overall outcome of the proposed model. The results of experiments have demonstrated that this design, when evaluated on publicly available ISIC 2018 skin lesion segmentation dataset, outperforms the existing standard methods with a Dice score of 89.14% and IoU of 81.16%; and achieves better trade off among precision and recall. The authors have also performed statistical test of this model with other standard methods and evaluated that this model is statistically significant.

No abstract

Cognitive Radio Network Technology makes the efficient utilization of scarce spectrum resources by allowing the unlicensed users to opportunistically use the licensed spectrum. Cognitive Radio Network due to its flexible and open nature is vulnerable to a number of security attacks. This paper is mainly concerned with one of the physical layer attack called Primary User Emulation Attack and its detection. This paper solves the problem of PUE attack by localization technique based on TDOA measurements with reduced error in location estimation using a Novel Bat Algorithm (NBA). A number of cooperative secondary users are used for detecting the PUEA by comparing its estimated position with the known position of incumbent. The main goal of NBA is to minimize two fitness functions namely non-linear least square and the maximum likelihood in order to optimize the estimation error. After evaluation, simulation results clearly demonstrates that NBA results in reduced estimation error as compared to Taylor Series Estimation and Particle Swarm Optimization.

No abstract