D
Deepika Kumar
Researcher at Bharati Vidyapeeth's College of Engineering
Publications - 24
Citations - 427
Deepika Kumar is an academic researcher from Bharati Vidyapeeth's College of Engineering. The author has contributed to research in topics: Computer science & Convolutional neural network. The author has an hindex of 5, co-authored 16 publications receiving 103 citations. Previous affiliations of Deepika Kumar include GD Goenka University.
Papers
More filters
Journal ArticleDOI
AiCNNs (Artificially-integrated Convolutional Neural Networks) for Brain Tumor Prediction
Ansh Mittal,Deepika Kumar +1 more
TL;DR: A model named Artificially-integrated Convolutional Neural Networks (AiCNNs) is proposed that accurately classifies brain MRI scans to 3 classes of brain tumor and negative diagnosis results.
Journal ArticleDOI
A median based quadrilateral local quantized ternary pattern technique for the classification of dermatoscopic images of skin cancer
TL;DR: In this article , a texture based feature extraction algorithm is presented for the classification of dermatoscopic images, where a median based Local Ternary Pattern is extracted followed by the computation of local quantized ternary patterns.
Journal ArticleDOI
Classification of Invasive Ductal Carcinoma from histopathology breast cancer images using Stacked Generalized Ensemble
Deepika Kumar,Usha Batra +1 more
Journal ArticleDOI
Epidemiology of Breast Cancer in Indian Women: Population and Hospital Based study
Deepika Kumar,Usha Batra +1 more
TL;DR: Additional awareness & screening programs early diagnosis and treatment facilities can only significantly improve the breast cancer’s clinical picture in India.
Proceedings ArticleDOI
Novel approach for incremental learning using ensemble of SVMs with particle swarm optimization
TL;DR: This work proposes a novel approach, which firstly uses SVMs in an ensemble manner for learning from the batches of data, it then discards the correctly classified data and trains a new SVM on the misclassified data points, the weighted sums of the correctly trained SVMs, and the machines trained on themisclassified points are then used to obtain the final classification values.