Arpita Das

= Data Scientist familiar with gathering, cleaning and organizing data for use by technical and non-technical personnel. Advanced understanding of statistical, algebraic and other analytical techniques. Highly organized, motivated and diligent with significant background in leveraging data-driven models to solve complex business problems and drive strategic decision-making. Detail-oriented team player with strong organizational skills. Ability to handle multiple projects simultaneously with a high degree of accuracy.

• M.TECH
• MAJOR PROJECT
• An Ensemble of Deep Learning Models for detecting Invasive Ductal Carcinoma from Histopathological
• Image
• For classifying histopathological images into IDC and IDC - categories, four different deep CNNs
• DenseNet, ResNet, Xception, and VGG19 are trained on histological images and to get advantages to every deep CNNs and optimize the model performance, both stacking and weighted average ensemble methods have been used
• The ensembled loss function is also used for getting the advantages of each loss function
• In this project, the proposed loss function is a combination of MAE, Hinge, and Binary
• Cross-Entropy loss functions, leading to a more robust, generalized, and improved probability estimator respectively
• B.TECH
• MAJOR PROJECT
• A web application on E-Governance
• Use J2EE to implement an application for the collection of services like
• Employment, Agriculture, Electricity, and Land Information.