Publications

Attention-guided deep convolutional neural networks for skin cancer classification

Published in 2019 Ninth International Conference on Image Processing Theory, Tools and Applications (IPTA), IEEE Istanbul, Turkey, 2019

Skin cancer is a silently killing disease which commonly goes unnoticed in its primitive stage but proves to be deadly later on. Hence, it needs to be detected and classified in the early stages itself. The advent of machine learning as well as deep learning based classification techniques has made this task possible. Deep convolutional neural networks (D-CNNs) have the ability to extract universal and dataset-specific features for the image classification task. But the classification of skin cancer images remains a challenging task due to the absence of balanced class images, difference between images of the same class, similarity between inter-class images and the inefficiency in focusing on the semantically significant areas of the image. To improve the performance of these D-CNNs, we incorporate the attention mechanism that focuses on the regions of importance in an image. In that regard, we propose an attention-guided D-CNN for classification of skin cancer.

Recommended citation: Arshiya Aggarwal, Nisheet Das, Indu Sreedevi https://ieeexplore.ieee.org/document/8936100

A novel hybrid architecture for classification of power quality disturbances

Published in Paris, France, 2019

Power quality disturbances are introduced in the signals due to the increasing use of power electronic devices. To ensure reliability, security and adequate quality of power for consumption, the power quality disturbances need to be detected and classified accurately. This paper proposes an efficient algorithm for detecting and classifying the various power quality disturbances using a convolutional neural network (CNN) to extract various features from the input power signal which are then fed to the multi-class support vector classifier (MCSVC) to detect and classify the power quality disturbance events. It is observed from the simulation results and verified using an industrial dataset that the proposed model performs better than a normal convolutional neural network by approximately 10%. This work contributes to improving the quality of power delivered for industrial applications, making the operation of power systems economic, efficient and safe.

Recommended citation: Arshiya Aggarwal, Nisheet Das, Mansi Arora, Dr. M.M. Tripathi https://ieeexplore.ieee.org/document/8820557