Aditya Khamparia | Searcharxiv

arXiv2020

Diagnosis of Breast Cancer Based on Modern Mammography using Hybrid Transfer Learning

Breast cancer is a common cancer for women. Early detection of breast cancer can considerably increase the survival rate of women. This paper mainly focuses on transfer learning process to detect breast cancer. Modified VGG (MVGG), residual network, mobile network is proposed and implemented in this paper. DDSM dataset is used in this paper. Experimental results show that our proposed hybrid transfers learning model (Fusion of MVGG16 and ImageNet) provides an accuracy of 88.3% where the number of epoch is 15. On the other hand, only modified VGG 16 architecture (MVGG 16) provides an accuracy 80.8% and MobileNet provides an accuracy of 77.2%. So, it is clearly stated that the proposed hybrid pre-trained network outperforms well compared to single architecture. This architecture can be considered as an effective tool for the radiologists in order to reduce the false negative and false positive rate. Therefore, the efficiency of mammography analysis will be improved.

eess.IV↗

arXiv2017

Blended e-Learning Training (BeLT): Enhancing Railway Station Controller Knowledge

With the growing economy, e-learning consequently gained increasing attention as it conveys knowledge globally with improved interactivity, assistance, and reduced costs. For the past few years, accidental challenges have become the severe problem with railway units due to irresponsibility, lack of knowledge and improper guidance of station controllers (learners). While focusing on e-learning technologies railway units failed to admit learner's need, cultural diversity and background skills by creating ethnically impartial e-learning environments, which resulted in inadequate training and degraded performance. The purpose of this study is to understand the vision of a global diverse group of station traffic controllers about e-learning courses developed by their individual railway units. The opinions of these officials have been verified by questionnaires on the basis of course organization, course accuracy, course effectiveness, course relevance, course productivity and course interactivity. The results obtained show that the developed e-learning course was highly helpful, interactive, creative, and user-friendly for learners. This lead to making e-learning conquered among independent learners.

cs.CY↗