In this manuscript, we model and visualize the region-wise trends of the evolution to COVID-19 infections employing a SIR epidemiological model. The SIR dynamics are expressed using stochastic differential equations. We first optimize the parameters of the model using RMSE as loss function on the available data using L-BFGS-B gradient descent optimisation to minimise this loss function. This helps to gain better approximation of the model's parameter for specific country or region. The derived parameters are aggregated to project future trends for the Indian subcontinent for next 180 days, which is currently at an early stage within the infection cycle. The projections are meant to function a suggestion for strategies for the socio-political counter measures to mitigate COVID-19. This study considers the current data for India from various open sources. The SIR models prediction is found following the actual trends till date. The inflection point analysis is important to find out which countries have reached their inflection point of the number of infection. We found that if current restrictions like lockdown in India continues with same control, then India will observe itś peak in active patients count on 22 May 2020, it will take 28 August 2020 for 90% of the peak active infections to end. Inspired from the study of DDI Lab at Singapore university of technology and design (SUTD), this study additionally tries to model and quantify the variations in the count of active patients in the country which might occur due to effect of waiver in restrictions. It should be noted that these results were predicted using COVID-19 data of India

No abstract

Conventional machine learning (ML) needs centralized training data to be present on a given machine or datacenter. The healthcare, finance, and other institutions where data sharing is prohibited require an approach for training ML models in secured architecture. Recently, techniques such as federated learning (FL), MIT Media Lab's Split Neural networks, blockchain, aim to address privacy and regulation of data. However, there are difference between the design principles of FL and the requirements of Institutions like healthcare, finance, etc., which needs blockchain-orchestrated FL having the following features: clients with their local data can define access policies to their data and define how updated weights are to be encrypted between the workers and the aggregator using blockchain technology and also prepares audit trail logs undertaken within network and it keeps actual list of participants hidden. This is expected to remove barriers in a range of sectors including healthcare, finance, security, logistics, governance, operations, and manufacturing.