A. James Clark School of Engineering
Permanent URI for this communityhttp://hdl.handle.net/1903/1654
The collections in this community comprise faculty research works, as well as graduate theses and dissertations.
Browse
4 results
Search Results
Item NATURAL LANGUAGE PROCESSING, SOCIAL MEDIA, AND EPIDEMIC MODEL-ING FOR WILDFIRE RESPONSE AND RE-SILIENCE ENHANCEMENT(2024) Ma, Zihui; Baecher, Gregory B; Civil Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Effective disaster response is critical for communities to remain resilient and advance the development of smart cities. Responders and decision-makers benefit from reliable, timely measures of the issues impacting their communities during a disaster, and social media offers a potentially rich data source. Social media can reflect public concerns and behaviors during a disaster, offering valuable insights for decision-makers to understand evolving situations and optimize resource allocation. A comprehensive literature review of natural language processing (NLP) of social media data in disaster management, covering 324 articles published between 2011 and 2022, revealed a gap in applying NLP techniques to wildfire scenarios. Meanwhile, the increasing frequency of wildfires highlights the need for advanced management tools. To address this, we integrated the BERTopic and SIR models to capture public responses on Twitter during the 2020 western U.S. wildfire season, analyzing both the magnitude and velocity of topic diffusion. The results displayed a clear relationship between topic trends and wildfire propagation patterns. The parameters estimated from the SIR model for selected cities revealed that residents expressed various levels of concern or demand during wildfires. The study also demonstrated a practical framework for utilizing social media data to aid wildfire evacuations. Through social network analysis, we clarified the roles of key information disseminators and provided guidelines for extracting high-priority information. Although biases in social media and model limitations exist, the study offers qualitative and quantitative approaches to investigate wildfire response and sup-port community resilience enhancement.Item Dynamic EM Ray Tracing for Complex Outdoor and Indoor Environments with Multiple Receivers(2024) Wang, Ruichen; Manocha, Dinesh; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Ray tracing models for visual, aural, and EM simulations have advanced, gaining traction in dynamic applications such as 5G, autonomous vehicles, and traffic systems. Dynamic ray tracing, modeling EM wave paths and their interactions with moving objects, leads to many challenges in complex urban areas due to environmental variability, data scarcity, and computational needs. In response to these challenges, we've developed new methods that use a dynamic coherence-based approach for ray tracing simulations across EM bands. Our approach is designed to enhance efficiency by improving the recomputation of bounding volume hierarchy (BVH) and by caching propagation paths. With our formulation, we've observed a reduction in computation time by about 30%, all while maintaining a level of accuracy comparable to that of other simulators. Building on our dynamic approach, we've made further refinements to our algorithm to better model channel coherence, spatial consistency, and the Doppler effect. Our EM ray tracing algorithm can incrementally improve the accuracy of predictions relating to the movement and positioning of dynamic objects in the simulation. We've also integrated the Uniform Geometrical Theory of Diffraction (UTD) with our ray tracing algorithm. Our enhancement is designed to allow for more accurate simulations of diffraction around smooth surfaces, especially in complex indoor settings, where accurate prediction is important. Taking another step forward, we've combined machine learning (ML) techniques with our dynamic ray tracing framework. Leveraging a modified conditional Generative Adversarial Network (cGAN) that incorporates encoded geometry and transmitter location, we demonstrate better efficiency and accuracy of simulations in various indoor environments with 5X speedup. Our method aims to not only improve the prediction of received power in complex layouts and reduce simulation times but also to lay a groundwork for future developments in EM simulation technologies, potentially including real-time applications in 6G networks. We evaluate the performance of our methods in various environments to highlight the advantages. In dynamic urban scenes, we demonstrate our algorithm’s scalability to vast areas and multiple receivers with maintained accuracy and efficiency compared to prior methods; for complex geometries and indoor environments, we compare the accuracy with analytical solutions as well as existing EM ray tracing systems.Item DISTRIBUTED FLOW OPTIMIZATION IN DENSE WIRELESS NETWORKS(2011) Zahedpour Anaraki, Sina; Kalantari, Mehdi; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Due to large number of variables, optimizing information flow in a dense wire- less network using discrete methods can be computationally prohibitive. Instead of treating the nodes as discrete entities, these networks can be modeled as continuum of nodes providing a medium for information transport. In this scenario multi-hop information routes transform into an information flow vector field that is defined over the geographical domain of the network. At each point of the network, the orientation of the vector field shows the direction of the flow of information, and its magnitude shows the density of information flow. Modeling the dense network in continuous domain enables us to study the large scale behavior of the network under existing routing policies; furthermore, it justifies incorporation of multivariate calculus techniques in order to find new routing policies that optimize a suitable cost function, which only depend on large scale properties of the network. Thus, finding an optimum routing method translates into finding an optimal information flow vector field that minimizes the cost function. In order to transform the optimal information flow vector field into a routing policy, connections between discrete space (small scale) and continuous space (large scale) variables should be made and the question that how the nodes should interact with each other in the microscopic scale in order that their large scale behavior become optimal should be answered. In the past works, a centralized method of calculating the optimal information flow over the entire geographical area that encompasses the network has been suggested; however, using a centralized method to optimize information flow in a dynamic network is undesirable. Furthermore, the value of information flow vector field is needed only at the locations of randomly scattered nodes in the network, thus calculation of the information flow vector field for the entire network region (as suggested in previous models) is an unnecessary overhead. This poses a gap between the continuous space and discrete space models of information flow in dense wireless networks. This gap is how to calculate and apply the optimum information flow derived in continuous domain to a network with finite number of nodes. As a first step to fill this gap, a specific quadratic cost function is considered. In previous works, it is proved that the the vector field that minimizes this cost function is irrotational, thus it is written as the gradient of a potential function. This potential function satisfies a Poisson Partial Differential Equation (PDE) which in conjunction with Neumann boundary condition has a unique solution up to a constant. In this thesis the PDE resulted by optimization in continuous domain is discretized at locations of the nodes. By assuming a random node distribution with uniform density, the symmetries present enable us to solve the PDE in a distributed fashion. This solution is based on Jacobi iterations and requires only neighboring nodes to share their local information with each other. The gradient of the resulting potential defines the routes that the traffic should be forwarded. Furthermore, based on a graph theory model, we generalize our distributed solution to a more general cost function, namely, the p-norm cost function. This model also enables us to enhance the convergence rate of the Jacobi iterations.Item IP Geolocation in Metropolitan Areas(2011) Singh, Satinder Pal; Shayman, Mark; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)In this thesis, we propose a robust methodology to geolocate a target IP Address in a metropolitan area. We model the problem as a Pattern Recognition problem and present algorithms that can extract patterns and match them for inferring the geographic location of target's IP Address. The first algorithm is a relatively non-invasive method called Pattern Based Geolocation (PBG) which models the distribution of Round Trip Times (RTTs) to a target and matches them to that of the nearby landmarks to deduce the target's location. PBG builds Probability Mass Functions (PMFs) to model the distribution of RTTs. For comparing PMFs, we propose a novel `Shifted Symmetrized Divergence' distance metric which is a modified form of Kullback-Leibler divergence. It is symmetric as well as invariant to shifts. PBG algorithm works in almost stealth mode and leaves almost undetectable signature in network traffic. The second algorithm, Perturbation Augmented PBG (PAPBG), gives a higher resolution in the location estimate using additional perturbation traffic. The goal of this algorithm is to induce a stronger signature of background traffic in the vicinity of the target, and then detect it in the RTT sequences collected. At the cost of being intrusive, this algorithm improves the resolution of PBG by approximately 20-40%. We evaluate the performance of PBG and PAPBG on real data collected from 20 machines distributed over 700 square miles large Washington-Baltimore metropolitan area. We compare the performance of the proposed algorithms with existing measurement based geolocation techniques. Our experiments show that PBG shows marked improvements over current techniques and can geolocate a target IP address to within 2-4 miles of its actual location. And by sending an additional traffic in the network PAPBG improves the resolution to within 1-3 miles.