Computer Sciences Commons^™

Roadside Lidar Data Processing For Intelligent Transportation System, Md Parvez Mollah

Computer Science ETDs

Roadside LiDAR (Light Detection and Ranging) sensors are recently being explored for Intelligent Transportation System aiming at safer and faster traffic management and vehicular operations. However, massive data volume, occlusion, and limited viewing angles are significant obstacles to the widespread use of roadside LiDARs. In this dissertation, we address three major challenges to enable applications of Intelligent Transportation System through roadside LiDAR data: (i) real-time transmission of the massive point-cloud data from the roadside LiDAR devices to the cloud using 5G network, (ii) mitigating sensor occlusion problem to increase coverage and detect events occurred in occluded regions of a sensor, …

Ai Assisted Workflows For Computational Electromagnetics And Antenna Design, Oameed Noakoasteen

Electrical and Computer Engineering ETDs

These days large volumes of data can be recorded and manipulated with relative ease. If valuable information can be extracted from them, these vast amounts of data can be a rich resource not just for the digital economy but also for scientific discovery and development of technology. When it comes to deriving valuable information from data, Machine Learning (ML) emerges as the key solution. To unlock the potential benefits of ML to science and technology, extensive research is needed to explore what algorithms are suitable and how they can be applied.

To shine light on various ways that ML can …

Domain Specific Feature Representation Learning For Diverse Temporal Data, Farhan Asif Chowdhury

Computer Science ETDs

Humans can leverage domain context to recognize novel patterns and categories based on limited known examples. In contrast, computational learning methods are not adept at exploiting context and require sufficient labeled examples to achieve similar accuracy. Many temporal data domain, for example, seismic signals and oil mining sensor data, requires domain expert annotation, which is both costly and time-consuming. The dependency on training data limits the applicability of machine learning algorithms for domains with limited labeled data. This dissertation aims to address this gap by developing temporal mining algorithms that exploit domain context to learn discriminative feature representation from limited …