Computer Science

Permanent URI for this collection

This collection includes scholarly output from both faculty and students in Computer Science.


Recent Submissions

Now showing 1 - 5 of 19
  • Item
    Integrating Communication and Sensor Arrays to Model and Navigate Autonomous Unmanned Aerial Systems
    (Electronics (Switzerland), 2022-10) Perera, Sirani M.; Myers, Rodman J.; Sullivan, Killian; Byassee, Kyle; Song, Houbing; Madanayake, Arjuna
    The emerging concept of drone swarms creates new opportunities with major societal implications. However, future drone swarm applications and services pose new communications and sensing challenges, particularly for collaborative tasks. To address these challenges, in this paper, we integrate sensor arrays and communication to propose a mathematical model to route a collection of autonomous unmanned aerial systems (AUAS), a so-called drone swarm or AUAS swarm, without having a base station of communication but communicating with each other using multiple spatio-temporal data. The theories of structured matrices, concepts in multi-beam beamforming, and sensor arrays are utilized to propose a swarm routing algorithm. We address the routing algorithm’s computational and arithmetic complexities, precision, and reliability. We measure bit-error-rate (BER) based on the number of elements in sensor arrays and beamformed output of the members of the swarm to authenticate and secure the routing for the decentralized AUAS networking. The proposed model has the potential to enable future drone swarm applications and services. Finally, we discuss future work on obtaining a machine-learning-based low-cost drone swarm routing algorithm. © 2022 by the authors.
  • Item
    Estimating vehicle fuel economy from overhead camera imagery and application for traffic control
    (OSTI.GOV U.S. Department of Energy Office of Scientific and Technical Information, 2020-01-01) Karnowski, Thomas; Tokola, Ryan; Oesch, T Sean; Eicholtz, Matthew R.; Price, Jeff; Gee, Tim
    In this work, we explore the ability to estimate vehicle fuel consumption using imagery from overhead fisheye lens cameras deployed as traffic sensors. We utilize this information to simulate vision-based control of a traffic intersection, with a goal of improving fuel economy with minimal impact to mobility. We introduce the ORNL Overhead Vehicle Dataset (OOVD), consisting of a data set of paired, labeled vehicle images from a ground-based camera and an overhead fisheye lens traffic camera. The data set includes segmentation masks based on Gaussian mixture models for vehicle detection. We show the dataset utility through three applications: the estimate of fuel consumption based on segmentation bounding boxes, vehicle discrimination for those vehicles with largest bounding boxes, and a fine-grained classification on a limited number of vehicle makes and models using a pre-trained set of convolutional neural network models. We compare these results with estimates based on a large open-source data set based on web-scraped imagery. Finally, we show the utility of the approach using reinforcement learning in a traffic simulator using the open source Simulation of Urban Mobility (SUMO) package. Our results show the feasibility of the approach for controlling traffic lights for better fuel efficiency based solely on visual vehicle estimates from commercial, fisheye lens cameras.
  • Item
    Fast, Simple Calcium Imaging Segmentation with Fully Convolutional Networks
    (arXiv, 2017-06) Klibisz, Aleksander; Rose, Derek; Eicholtz, Matthew; Blundon, Jay; Zakharenko, Stanislav
    Calcium imaging is a technique for observing neuron activity as a series of images showing indicator fluorescence over time. Manually segmenting neurons is time-consuming, leading to research on automated calcium imaging segmentation (ACIS). We evaluated several deep learning models for ACIS on the Neurofinder competition datasets and report our best model: U-Net2DS, a fully convolutional network that operates on 2D mean summary images. U-Net2DS requires minimal domain-specific pre/post-processing and parameter adjustment, and predictions are made on full $512\times512$ images at $\approx$9K images per minute. It ranks third in the Neurofinder competition ($F_1=0.569$) and is the best model to exclusively use deep learning. We also demonstrate useful segmentations on data from outside the competition. The model's simplicity, speed, and quality results make it a practical choice for ACIS and a strong baseline for more complex models in the future. Comment: Accepted to 3rd Workshop on Deep Learning in Medical Image Analysis (
  • Item
    A Monte Carlo tree search player for birds of a feather solitaire
    (PKP Publishing Services Network, 2019) Roberson, Christian; Sperduto, Katarina
    Artificial intelligence in games serves as an excellent platform for facilitating collaborative research with undergraduates. This paper explores several aspects of a research challenge proposed for a newly-developed variant of a solitaire game. We present multiple classes of game states that can be identified as solvable or unsolvable. We present a heuristic for quickly finding goal states in a game state search tree. Finally, we introduce a Monte Carlo Tree Search-based player for the solitaire variant that can win almost any solvable starting deal efficiently.
  • Item
    A 2.5d Yolo-Based Fusion Algorithm for 3d Localization of Cells
    (Institute of Electrical and Electronics Engineers (IEEE), 2019-11-06) Ziabari, Amirkoushyar; Rose, Derek C.; Eicholtz, Matthew R.; Solecki, David J.; Shirinifard, Abbas
    Advances in microscopy techniques such as lattice-light-sheet, confocal, two-photon, and electron microscopy have enabled the visualization of 3D image volumes of tightly packed cells, extracellular structures in tissues, organelles, and subcellular components inside cells. These images sampled by 2D projections are often not accurately interpreted even by human experts. As a use case we focus on 3D image volumes of tightly packed nuclei in brain tissue. Due to out-of-plane excitation and low resolution in the z-axis, non-overlapping cells appear as overlapping 3D volumes and make detecting individual cells challenging. On the other hand, running 3D detection algorithms is computationally expensive and infeasible for large datasets. In addition, most existing 3D algorithms are designed to extract 3D objects by identifying the depth in the 2D images. In this work, we propose a YOLO-based 2.5D fusion algorithm for 3D localization of individual cells in densely packed volumes of nuclei. The proposed method fuses 2D detection of nuclei in sagittal, coronal, and axial planes and predicts six coordinates of the 3D bounding cubes around the detected 3D cells. Promising results were obtained on multiple examples of synthetic dense volumes of nuclei imitating confocal microscopy experimental datasets.