Computer Science
Permanent URI for this collection
This collection includes scholarly output from both faculty and students in Computer Science.
Browse
Recent Submissions
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, ArjunaThe 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, TimIn 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, StanislavCalcium 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 (http://cs.adelaide.edu.au/~dlmia3/)Item A Monte Carlo tree search player for birds of a feather solitaire(PKP Publishing Services Network, 2019) Roberson, Christian; Sperduto, KatarinaArtificial 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, AbbasAdvances 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.Item A Two-Tier Convolutional Neural Network for Combined Detection and Segmentation in Biological Imagery(Institute of Electrical and Electronics Engineers (IEEE), 2019-11-14) Ziabari, Amirkoushyar; Shirinifard, Abbas; Eicholtz, Matthew R.; Solecki, David J.; Rose, Derek C.Deep learning techniques have been useful for modern microscopy imaging techniques to further study and analyze biological structures and organs. Convolutional neural networks (CNN) have improved 2D object detection, localization, and segmentation. For imagery containing biological structures with depth, it is especially desirable to perform these tasks in 3D. Traditionally, performing these tasks simultaneously in 3D has proven to be computationally expensive. Currently available methodologies thus largely work to segment 3D objects from 2D images (without context from captured 3D volumes). In this work, we present a novel approach to perform fast and accurate localization, detection, and segmentation of volumes containing cells. Specifically, in our method, we modify and tune two state-of-the-art CNNs, namely 2D YOLOv2 and 3D U-Net, and combine them with a new fusion and image processing algorithms. Annotated volumes in this space are limited, and we have created synthetic data that mimics actual structures for training and testing our proposed approach. Promising results on this test data demonstrate the value of the technique and offers a methodology for 3D cell analysis in real microscopy imagery.Item MOCSIDE: An open-source and scalable online IDE and auto-grader for computer science education(Association for Computing Machinery, 2022-03) Cazalas, Jonathan; Barlow, Max; Cazalas, Ibraheem; Robinson, ChaseProgramming is learned through practice, with said practice in introductory programming courses often translating to a prohibitively large number of assignments, increasing the grading workload for faculty and/or teaching assistants. In short, this is unsustainable. Several publishers and a few notable companies have provided meritable auto-grading solutions, although most are plagued with problems including minimal problem sets, limited customization options, high cost, and at times even a disconnect with the pedagogical needs of academia. This poster presents our newly-developed web application, MOCSIDE, an open-source and scalable online IDE and auto-grader for computer science education. Results indicate a positive user experience from students and instructors alike, with cost savings, ease of use, and code collaboration highlighted as key features.Item A framework for preserving location privacy for continuous queries(Springer, 2019-09) Al-Dhubhani, Raed Saeed; Cazalas, Jonathan; Mehmood, Rashid; Katib, Iyad; Saeed, FaisalThe growth of the location-based services (LBSs) market in recent years was motivated by the widespread use of mobile devices equipped with positioning capability and Internet accessibility. To preserve the location privacy of LBS users, many mechanisms have been proposed to provide a partial disclosure by decreasing or blurring or the accuracy of the shared location. While these Location Privacy Preserving Mechanisms (LPPMs) have demonstrated effective performance with snapshot queries, this work shows that preserving location privacy for continuous queries should be addressed differently. In this paper, MOPROPLS framework is proposed with the aim to preserve location privacy in the specific case of continuous queries. As part of the proposed framework, a novel set of six requirements that any LPPM should meet in order to provide location privacy for continuous queries is proposed. In addition, a novel location privacy leakage metric and a novel two-phased probabilistic candidate selection algorithm are proposed. Comparing the performance of MOPROPLS framework with the geo-indistinguishability LPPM in terms of privacy (adversary estimation error) shows that the average of MOPROPLS framework improvement is 34%.Item An adaptive geo-indistinguishability mechanism for continuous LBS queries(Springer US, 2018-11-01) Al-Dhubhani, Raed Saeed; Cazalas, JonathanThe popularity of mobile devices with positioning capability and Internet accessibility in recent years has led to a revolution in the Location-based services (LBSs) market. Unfortunately, without preserving the user’s location privacy, LBS providers can collect and log the accurate location data of the service users and provide them to third parties. Many mechanisms have been proposed to preserve the LBS user’s location privacy. These mechanisms provide a partial disclosure of the user’s location. While said mechanisms have had demonstrable effectiveness with snapshot queries, the shortcoming of supporting continuous queries is their main drawback. Geo-indistinguishability represents a formal notion of obfuscation-based location privacy which protects the user’s accurate location while allowing an adequate amount of information to be released to get the service with an accepted utility level. Despite its effectiveness and simplicity, geo-indistinguishability does not address the potential correlation of the subsequent locations reported within the continuous queries. In this paper, we investigate the effect of exploiting the correlation of the user’s obfuscated locations on the location privacy level. We propose an adaptive location preserving privacy mechanism that adjusts the amount of noise required to obfuscate the user’s location based on the correlation level with its previous obfuscated locations. The experiments show that adapting the noise based on the correlation level leads to a better performance by applying more noise to increase the location privacy level when required or by reducing the noise to improve the utility level.Item A survey: The current trends of privacy techniques for protecting the location privacy of users in LBS(Little Lion Scientific, 2018-08-15) Albelaihy, Abdullah; Cazalas, Jonathan; Thayananthan, VijeyWith GPS-enabled devices and data connectivity now ubiquitous, Location Based Services (LBSs) have seemingly penetrated all aspects of our lives. While profoundly valuable, these services expose the user to a litany of privacy and security issues. LBS users must reveal their location, and at times other sensitive personal information, in order to effectively use the service and receive accurate results. This paper presents a survey of the current trends of privacy techniques employed in protecting the location privacy of users in LBSs. The paper further highlights the efficacy, or otherwise, of each technique discussed in this paper, with each technique having been evaluated based on accuracy, quality, efficiency, flexibility, location privacy, and query privacy. The outcome of this study is a taxonomy of current privacy and security techniques, which will assist researchers and developers as they look to further protect the sensitive information of their customer base.Item Privacy-preserving queries for LBS: Independent secured hash function(Little Lion Scientific, 2018-06-15) Albelaihy, Abdullah; Cazalas, Jonathan; Thayananthan, VijeyWhile location-based services have become ubiquitous, seemingly permeating our personal and professional lives, their inherent nature poses security risks to users, who are forced to reveal their highly-sensitive location data in order to make effective use of the service. Towards this end, a litany of techniques have been proposed to provide efficient answers for privacy-preserving queries in LBS. Spatial bloom filters were initially proposed as an efficient data structure used to manage special and geographic information in an space-efficient manner. Unfortunately, bloom filters suffer from two deficiencies: they leak at most one bit of information per query, and the hash functions require careful design and security analysis in order to be orthogonal and independent. In fact, developing quality hash function is paramount. We propose a method to automatically generate good, independent hash functions, with the goal of reducing information leakage. This means that even if one of the hash function is broken, for any reason, nothing can be learned about any other hash function. The results show that our proposed Hash functions are less dependent and leaked than the compared approach, while still seeing a notable improvement in performance.Item BL0T: A novel phase privacy-preserving framework for location-based services(MDPI, 2018) Albelaihy, Abdullah; Cazalas, Jonathan; Thayananthan, VijeyThe inherent challenge within the domain of location-based services is finding a delicate balance between user privacy and the efficiency of answering queries. Inevitably, security issues can and will arise as the server must be informed about the query location in order to provide accurate responses. Despite the many security advancements in wireless communication, servers may become jeopardized or become infected with malicious software. That said, it is possible to ensure queries do not generate fake responses that appear real; in fact, if a fake response is used, mechanisms can be employed for the user to identify the query's authenticity. Towards this end, the paper propose BLoom Filter Oblivious Transfer (BLOT), a novel phase privacy preserving framework for LBS that combines a Bloom filter hash function and the oblivious transfer protocol. These methods are shown to be useful in securing a user's private information. An analysis of the results revealed that BLOT performed markedly better and enhanced entropy when compared to referenced approaches.Item A survey of the current trends of privacy techniques employed in protecting the Location privacy of users in LBSs(IEEE, 2017) Albelaihy, Abdullah; Cazalas, JonathanIn the age of the smartphone, Location Based Services (LBSs) have been immensely popular and changed the everyday routines of every individual user. However, an issue concerning the privacy and security of the user has been raised in the course of tracking the user as relevant and sensitive information about the user's location are revealed. This paper presents a survey of the current trends of privacy techniques employed in protecting the location privacy of users in LBSs. The paper further highlights the efficiency and deficiency of each technique discussed in this paper. The study, however, recommends that future researchers should endeavor to conduct a security analysis, simulation set-up and evaluate the proposed algorithm use of a modified Hilbert Curve to ensure the privacy efficiency of the proposed scheme.Item Privacy preserving queries for LBS: Hash function secured (HFS)(IEEE, 2017) Albelaihy, Abdullah; Cazalas, JonathanLocation-based services can be seen everywhere today in our smartphones and devices that use GPS, and this service has become invaluable to customers. LBSs, however, do have their flaws. Users are forced to reveal location data if they want to use the service, which can be a risk for their own privacy and security. Therefore, several techniques have been proposed in literature in order to provide an optimal solution for privacy preserving queries in LBS. This paper will firstly explore the use of bloom filters in existing research and their inherent limitation. While using Bloom Filers can be straightforward, finding good hash functions can be challenging. We propose a method to automatically generate good, independent hash functions, with the goal of reducing information leakage while also creating an automated performance measure.Item Correlation analysis for geo-indistinguishability based continuous LBS queries(IEEE, 2017) Al-Dhubhani, Raed Saeed; Cazalas, JonathanThe popularity of mobile devices with positioning capability and Internet accessibility in recent years has caused a revolution in the Location Based Services (LBS) market. Unfortunately, without preserving the user's location privacy, LBS providers can collect and log the accurate locations of the service users. Many mechanisms have been developed to preserve the LBS user's location privacy. While said mechanisms have had demonstrable effectiveness with snapshot queries, the shortcoming of supporting continuous queries is their main drawback. Geo-indistinguishability represents an obfuscation-based location privacy notion, which preserves the user's accurate location while allowing an adequate amount of information to be released. Despite its effectiveness and simplicity, geo-indistinguishability notion does not address the potential correlation of the subsequent locations reported within the continuous queries. In this paper, we report our progress on developing an adaptive geo-indistinguishability mechanism for continuous LBS queries. We show the effect of exploiting the correlation of the user's obfuscated locations on the location privacy level. The initial results show the need for an adaptive mechanism that adjusts the amount of noise required to obfuscate the user's location based on the correlation level with its previous obfuscated locations.Item Leveraging computation sharing and parallel processing in location-dependent query processing(Springer US, 2012-07) Cazalas, Jonathan; Guha, RatanA variety of research exists for the processing of continuous queries in large, mobile environments. Each method tries, in its own way, to address the computational bottleneck of constantly processing so many queries. In this paper, we introduce an efficient and scalable system for monitoring continuous queries by leveraging the parallel processing capability of the Graphics Processing Unit. We examine a naive CPU-based solution for continuous range-monitoring queries, and we then extend this system using the GPU. Additionally, with mobile communication devices becoming commodity, location-based services will become ubiquitous. To cope with the very high intensity of location-based queries, we propose a view oriented approach of the location database, thereby reducing computation costs by exploiting computation sharing amongst queries requiring the same view. Our studies show that by exploiting the parallel processing power of the GPU, we are able to significantly scale the number of mobile objects, while maintaining an acceptable level of performance.Item Performance modeling of spatio-temporal algorithms over GEDS framework(IGI Global, 2012) Cazalas, Jonathan; Guha, RatanThe efficient processing of spatio-temporal data streams is an area of intense research. However, all methods rely on an unsuitable processor (Govindaraju, 2004), namely a CPU, to evaluate concurrent, continuous spatio-temporal queries over these data streams. This paper presents a performance model of the execution of spatio-temporal queries over the authors' GEDS framework (Cazalas & Guha, 2010). GEDS is a scalable, Graphics Processing Unit (GPU)-based framework, employing computation sharing and parallel processing paradigms to deliver scalability in the evaluation of continuous, spatio-temporal queries over spatio temporal data streams. Experimental evaluation shows the scalability and efficacy of GEDS in spatio-temporal data streaming environments and demonstrates that, despite the costs associated with memory transfers, the parallel processing power provided by GEDS clearly counters and outweighs any associated costs. To move beyond the analysis of specific algorithms over the GEDS framework, the authors developed an abstract performance model, detailing the relationship of the CPU and the GPU. From this model, they are able to extrapolate a list of attributes common to successful GPU-based applications, thereby providing insight into which algorithms and applications are best suited for the GPU and also providing an estimated theoretical speedup for said GPU-based applications.Item GEDS: GPU execution of continuous queries on spatio-temporal data streams(IEEE, 2010) Cazalas, Jonathan; Guha, RatanMuch research exists for the efficient processing of spatio-temporal data streams. However, all methods ultimately rely on an ill-equipped processor, namely a CPU, to evaluate concurrent, continuous spatio-temporal queries over these data streams. This paper presents GEDS, a scalable, Graphics Processing Unit (GPU)-based framework for the evaluation of continuous spatio-temporal queries over spatio-temporal data streams. GEDS employs the computation sharing and parallel processing paradigms to deliver scalability in the evaluation of continuous spatio-temporal queries. The GEDS framework utilizes the parallel processing capability of the GPU, a stream processor by trade, to handle the computation required in this application. Experimental evaluation shows promising performance and shows the scalability and efficacy of GEDS in spatio-temporal data streaming environments.Item Leveraging computation sharing and parallel processing in location-based services(IEEE, 2009) Cazalas, Jonathan; Hua, KienA variety of research exists for the processing of continuous queries in large, mobile environments. Each method tries, in its own way, to address the computational bottleneck of constantly processing so many queries. In this paper, we introduce an efficient and scalable system for monitoring continuous queries by leveraging the parallel processing capability of the graphics processing unit. We examine a naive CPU-based solution for continuous range-monitoring queries, and we then extend this system using the GPU. Additionally, with mobile communication devices becoming commodity, location-based services will become ubiquitous. To cope with the very high intensity of location-based queries, we propose a view oriented approach of the location database, thereby reducing computation costs by exploiting computation sharing amongst queries requiring the same view. Our studies show that by exploiting the parallel processing power of the GPU, we are able to significantly scale the number of mobile objects, while maintaining an acceptable level of performance.