Search for: All records

An alarming proportion of the US population is overweight: 2/3 of US adults are overweight, and 1/3 of those overweight are obese. Obesity increases the risk of illnesses such as diabetes and cardiovascular diseases. This epidemic can be attributed to the combination of cheap, high-calorie food and lack of physical activity. In this paper, we propose a Big Data Analytics framework, called BiDAF, that aims to explore social contextual influences on healthy eating. For this purpose, we classified food tweets and social media images into as either healthy or unhealthy as well as food sentiments into either positive or negative, and further mapped them to an obesity prevalence map. The classification outcomes would be useful to reveal the social food trends and sentiments of the Centers for Disease and Control Prevention (CDC) USA obesity regions. The BiDAF framework has been implemented on Apache Spark and TensorFlow platforms. We have evaluated the BiDAF framework in terms of the accuracy on the food tweet classification and sentiment analysis. The experimental results indicated that the BiDAF framework is effective in classification and sentiment analysis of food tweet messages and also showed its potential in exploring social contextual influences that may contribute to healthy eating. 

We have developed a fast, scalable, and purely geometric structure search combining techniques from information retrieval and big data with a novel approach to encoding sequences of torsion angles. Along the way, we introduce a new torsion angle plot without breaks in continuity while still maintaining traditional torsion angle ranges, to assist in identifying separable regions of torsion angles. Subsequently, we introduce a new heuristic we call run position encoding, for handling the lack of specificity of items within character sequences containing runs of repeats. Comparing our results to the output of the CATH structural scan, response times are measured in seconds as opposed to minutes and average RMSDs and TM-scores are better. Our approach is a step towards a comprehensive indexing of protein structures scalable to millions of entries. Code and data are available at https://github.com/rayoub/rupee.