Time-series forecasting and analysis of COVID-19 outbreak in highly populated countries- A data-driven approach

A novel corona virus, COVID-19 is spreading across different countries in an alarming proportion and it has become a major threat to the existence of human community. With more than eight lakh death count within a very short span of seven months, this deadly virus has affected more than 24 million people across 213 countries and territories around the world. Time-series analysis, modeling and forecasting is an important research area that explores the hidden insights from larger set of time-bound data for arriving better decisions. In this work, data analysis on COVID-19 dataset is performed by comparing the top six populated countries in the world. The data used for the evaluation is taken for a time period from 22nd January 2020 to 23rd August 2020.A novel time-series forecasting approach based on Auto-regressive integrated moving average (ARIMA) model is also proposed. The results will help the researchers from medical and scientific community to gauge the trend of the disease spread and improvise containment strategies accordingly.

Applying adaptive learning by integrating semantic and machine learning in proposing student assessment model

<p>Adaptive learning is one of the most widely used data driven approach to teaching and it received an increasing attention over the last decade. It aims to meet the student’s characteristics by tailoring learning courses materials and assessment methods. In order to determine the student’s characteristics, we need to detect their learning styles according to visual, auditory or kinaesthetic (VAK) learning style. In this research, an integrated model that utilizes both semantic and machine learning clustering methods is developed in order to cluster students to detect their learning styles and recommend suitable assessment method(s) accordingly. In order to measure the effectiveness of the proposed model, a set of experiments were conducted on real dataset (Open University Learning Analytics Dataset). Experiments showed that the proposed model is able to cluster students according to their different learning activities with an accuracy that exceeds 95% and predict their relative assessment method(s) with an average accuracy equals to 93%.</p>

RWRoute: An Open-source Timing-driven Router for Commercial FPGAs

One of the key obstacles to pervasive deployment of FPGA accelerators in data centers is their cumbersome programming model. Open source tooling is suggested as a way to develop alternative EDA tools to remedy this issue. Open source FPGA CAD tools have traditionally targeted academic hypothetical architectures, making them impractical for commercial devices. Recently, there have been efforts to develop open source back-end tools targeting commercial devices. These tools claim to follow an alternate data-driven approach that allows them to be more adaptable to the domain requirements such as faster compile time. In this paper, we present RWRoute, the first open source timing-driven router for UltraScale+ devices. RWRoute is built on the RapidWright framework and includes the essential and pragmatic features found in commercial FPGA routers that are often missing from open source tools. Another valuable contribution of this work is an open-source lightweight timing model with high fidelity timing approximations. By leveraging a combination of architectural knowledge, repeating patterns, and extensive analysis of Vivado timing reports, we obtain a slightly pessimistic, lumped delay model within 2% average accuracy of Vivado for UltraScale+ devices. Compared to Vivado, RWRoute results in a 4.9× compile time improvement at the expense of 10% Quality of Results (QoR) loss for 665 synthetic and six real designs. A main benefit of our router is enabling fast partial routing at the back-end of a domain-specific flow. Our initial results indicate that more than 9× compile time improvement is achievable for partial routing. The results of this paper show how such a router can be beneficial for a low touch flow to reduce dependency on commercial tools.

Correlation-Based Discovery of Disease Patterns for Syndromic Surveillance

Early outbreak detection is a key aspect in the containment of infectious diseases, as it enables the identification and isolation of infected individuals before the disease can spread to a larger population. Instead of detecting unexpected increases of infections by monitoring confirmed cases, syndromic surveillance aims at the detection of cases with early symptoms, which allows a more timely disclosure of outbreaks. However, the definition of these disease patterns is often challenging, as early symptoms are usually shared among many diseases and a particular disease can have several clinical pictures in the early phase of an infection. As a first step toward the goal to support epidemiologists in the process of defining reliable disease patterns, we present a novel, data-driven approach to discover such patterns in historic data. The key idea is to take into account the correlation between indicators in a health-related data source and the reported number of infections in the respective geographic region. In an preliminary experimental study, we use data from several emergency departments to discover disease patterns for three infectious diseases. Our results show the potential of the proposed approach to find patterns that correlate with the reported infections and to identify indicators that are related to the respective diseases. It also motivates the need for additional measures to overcome practical limitations, such as the requirement to deal with noisy and unbalanced data, and demonstrates the importance of incorporating feedback of domain experts into the learning procedure.