GPU-Enabled Visual Analytics Framework for Big Transportation Datasets

Abstract

Transportation agencies rely on a variety of data sources for condition monitoring of their assets and making critical decisions such as infrastructure investments and project prioritization. Recent exponential increase in the volumes of these datasets has been causing significant information overload problems for data analysts; data curation process has increasingly become time consuming as legacy CPU-based systems are reaching their limits for processing and visualizing relevant trends in these massive datasets. There is a need for new tools that can consume these new datasets and provide analytics at rates resonant with the speed of human thought. The current paper proposes a new framework that allows for both multidimensional visualization and analytics to be carried seamlessly on large transportation datasets. The framework stores data in a massively parallel database and leverages the immense computational power available in graphical processing units (GPUs) to carry out data analytics and rendering on the fly via a Structured Query Language which interacts with the underlying GPU database. A front-end is designed for near-instant rendering of queried results on simple charts and maps to enable decision makers to drill down insights quickly. The framework is used to develop applications for analyzing big transportation datasets with over 100 million rows. Performance benchmarking experiments conducted showed that the methodology developed is able to provide real-time visual updates for big data in less than 100 ms. The performance of the developed framework was also compared with CPU-based visual analytics platforms such as Tableau and D3.

COVID-19 prediction through X-ray images using various layers in convolutional neural network

“…In this way, authors used CNN features to improve SVM classifier. For the experimental population COVID-19, they used 25 fold k-fold cross-validations (Adu-Gyamfi, 2019). This strategy will be beneficial to a physician because it will allow for the early detection of HIV1 patients.…”

The Role of Data Visualization and Analytics of Highway Accidents

“…Many transport agencies adopt Tableau as visual analytic platforms. For example, the National Highway Traffic Safety Administration uses Tableau as an analytical visualization tool to provide insights into highway accidents across the USA [8]. Tableau was used to design a dashboard on accident data described earlier in this paper.…”

“…Visualization allows users to understand data through the meaningful presentation of charts and maps, whereas analytics conduct aggregations, computations, and data reductions. Data visualization and analytics provide decision makers with well-informed, data-driven, and actionable insights that can be used to develop strategies and programs for improving road traffic safety [8,9].…”

Interactive, multi-purpose traffic prediction platform using connected vehicles dataset

“…The data is then provided to the front end for visual exploration after being filtered, aggregated, and lightweight. Although this method is useful for managing the challenges of massive data, it restricts the effectiveness of visual analytics because tiny details are lost in the aggregate and filtering processes [118]. The main purpose of this chapter is to develop an interactive visual analytics application that allows the big CV dataset (historical and predicted) to be visualized, interacted with, and analyzed in the browser (front end).…”

“…The data is then provided to the front end for visual exploration after being filtered, aggregated, and lightweight. Although this method is useful for managing the challenges of massive data, it restricts the effectiveness of visual analytics because tiny details are lost in the aggregate and filtering processes [24].…”