Department of Computer and Information Science Works
Permanent URI for this collection
Browse
Recent Submissions
Item Point process modeling of drug overdoses with heterogeneous and missing data(Institute of Mathematical Statistics, 2021) Liu, Xueying; Carter, Jeremy; Ray, Brad; Mohler, George; Computer and Information Science, School of ScienceOpioid overdose rates have increased in the United States over the past decade and reflect a major public health crisis. Modeling and prediction of drug and opioid hotspots, where a high percentage of events fall in a small percentage of space–time, could help better focus limited social and health services. In this work we present a spatial-temporal point process model for drug overdose clustering. The data input into the model comes from two heterogeneous sources: (1) high volume emergency medical calls for service (EMS) records containing location and time but no information on the type of nonfatal overdose, and (2) fatal overdose toxicology reports from the coroner containing location and high-dimensional information from the toxicology screen on the drugs present at the time of death. We first use nonnegative matrix factorization to cluster toxicology reports into drug overdose categories, and we then develop an EM algorithm for integrating the two heterogeneous data sets, where the mark corresponding to overdose category is inferred for the EMS data and the high volume EMS data is used to more accurately predict drug overdose death hotspots. We apply the algorithm to drug overdose data from Indianapolis, showing that the point process defined on the integrated data out-performs point processes that use only coroner data (AUC improvement 0.81 to 0.85). We also investigate the extent to which overdoses are contagious, as a function of the type of overdose, while controlling for exogenous fluctuations in the background rate that might also contribute to clustering. We find that drug and opioid overdose deaths exhibit significant excitation with branching ratio ranging from 0.72 to 0.98.Item Deep-Learning-Based High-Intensity Focused Ultrasound Lesion Segmentation in Multi-Wavelength Photoacoustic Imaging(MDPI, 2023-09-08) Wu, Xun; Sanders, Jean L.; Dundar, M. Murat; Oralkan, Ömer; Computer and Information Science, School of SciencePhotoacoustic (PA) imaging can be used to monitor high-intensity focused ultrasound (HIFU) therapies because ablation changes the optical absorption spectrum of the tissue, and this change can be detected with PA imaging. Multi-wavelength photoacoustic (MWPA) imaging makes this change easier to detect by repeating PA imaging at multiple optical wavelengths and sampling the optical absorption spectrum more thoroughly. Real-time pixel-wise classification in MWPA imaging can assist clinicians in monitoring HIFU lesion formation and will be a crucial milestone towards full HIFU therapy automation based on artificial intelligence. In this paper, we present a deep-learning-based approach to segment HIFU lesions in MWPA images. Ex vivo bovine tissue is ablated with HIFU and imaged via MWPA imaging. The acquired MWPA images are then used to train and test a convolutional neural network (CNN) for lesion segmentation. Traditional machine learning algorithms are also trained and tested to compare with the CNN, and the results show that the performance of the CNN significantly exceeds traditional machine learning algorithms. Feature selection is conducted to reduce the number of wavelengths to facilitate real-time implementation while retaining good segmentation performance. This study demonstrates the feasibility and high performance of the deep-learning-based lesion segmentation method in MWPA imaging to monitor HIFU lesion formation and the potential to implement this method in real time.Item Augmented Reality-Assisted Deep Reinforcement Learning-Based Model towards Industrial Training and Maintenance for NanoDrop Spectrophotometer(MDPI, 2023-06-29) Alatawi, Hibah; Albalawi, Nouf; Shahata, Ghadah; Aljohani, Khulud; Alhakamy, A’aeshah; Tuceryan, Mihran; Computer and Information Science, School of ScienceThe use of augmented reality (AR) technology is growing in the maintenance industry because it can improve efficiency and reduce costs by providing real-time guidance and instruction to workers during repairs and maintenance tasks. AR can also assist with equipment training and visualization, allowing users to explore the equipment’s internal structure and size. The adoption of AR in maintenance is expected to increase as hardware options expand and development costs decrease. To implement AR for job aids in mobile applications, 3D spatial information and equipment details must be addressed, and calibrated using image-based or object-based tracking, which is essential for integrating 3D models with physical components. The present paper suggests a system using AR-assisted deep reinforcement learning (RL)-based model for NanoDrop Spectrophotometer training and maintenance purposes that can be used for rapid repair procedures in the Industry 4.0 (I4.0) setting. The system uses a camera to detect the target asset via feature matching, tracking techniques, and 3D modeling. Once the detection is completed, AR technologies generate clear and easily understandable instructions for the maintenance operator’s device. According to the research findings, the model’s target technique resulted in a mean reward of 1.000 and a standard deviation of 0.000. This means that all the rewards that were obtained in the given task or environment were exactly the same. The fact that the reward standard deviation is 0.000 shows that there is no variability in the outcomes.Item Registration and Localization of Unknown Moving Objects in Monocular SLAM(IEEE, 2022-03-23) Troutman, Blake; Tuceryan, Mihran; Computer and Information Science, School of ScienceAugmented reality (AR) applications require constant device localization, which is often fulfilled by visual simultaneous localization and mapping (SLAM). SLAM provides realtime camera localization by also dynamically building a 3D map of the environment, but the functionality of SLAM systems generally stops here. Useful applications of AR could make great use of additional information about the environment, such as the structure and location of moving objects in the scene (including objects that were not previously known to be separate from the static points of the map). We present an approach for solving the visual SLAM problem while also registering and localizing moving objects without prior knowledge of the objects’ structure, appearance, or existence. This is accomplished via analysis of reprojection errors and iterative use of the ePnP algorithm in a RANSAC scheme. The approach is demonstrated with the accompanying prototype system, LUMO-SLAM. The initial results achieved by this system indicate that the approach is both sound and potentially viable for some practical applications of AR and visual SLAM.Item Strategic signaling for utility control in audit games(Elsevier, 2022-07) Chen, Jianan; Hu, Qin; Jiang, Honglu; Computer and Information Science, School of ScienceAs an effective method to protect the daily access to sensitive data against malicious attacks, the audit mechanism has been widely deployed in various practical fields. In order to examine security vulnerabilities and prevent the leakage of sensitive data in a timely manner, the database logging system usually employs an online signaling scheme to issue an alert when suspicious access is detected. Defenders can audit alerts to reduce potential damage. This interaction process between a defender and an attacker can be modeled as an audit game. In previous studies, it was found that sending real-time signals in the audit game to warn visitors can improve the benefits of the defender. However, the previous approaches usually assume perfect information of the attacker, or simply concentrate on the utility of the defender. In this paper, we introduce a brand-new zero-determinant (ZD) strategy to study the sequential audit game with online signaling, which empowers the defender to unilaterally control the utility of visitors when accessing sensitive data. In addition, an optimization scheme based on the ZD strategy is designed to effectively maximize the utility difference between the defender and the attacker. Extensive simulation results show that our proposed scheme enhances the security management and control capabilities of the defender to better handle different access requests and safeguard the system security in a cost-efficient manner.Item SE3: Sequential Semantic Segmentation of Large Images with Minimized Memory(IEEE, 2022-08) Cheng, Guo; Zheng, Jiang Yu; Computer and Information Science, School of ScienceSemantic segmentation results in pixel-wise perception accompanied with GPU computation and expensive memory, which makes trained models hard to apply to small devices in testing. Assuming the availability of hardware in training CNN backbones, this work converts them to a linear architecture enabling the inference on edge devices. Keeping the same accuracy as patch-mode testing, we segment images using a scanning line with the minimum memory. Exploring periods of pyramid network shifting on image, we perform such sequential semantic segmentation (SE3) with a circular memory to avoid redundant computation and preserve the same receptive field as patches for spatial dependency. In the experiments on large drone images and panoramas, we examine this approach in terms of accuracy, parameter memory, and testing speed. Benchmark evaluations demonstrate that, with only one-line computation in linear time, our designed SE3 network consumes a small fraction of memory to maintain an equivalent accuracy as the image segmentation in patches. Considering semantic segmentation for high-resolution images, particularly for data streamed from sensors, this method is significant to the real-time applications of CNN based networks on light-weighted edge devices.Item Solving the Federated Edge Learning Participation Dilemma: A Truthful and Correlated Perspective(IEEE, 2022-07) Hu, Qin; Li, Feng; Zou, Xukai; Xiao, Yinhao; Computer and Information Science, School of ScienceAn emerging computational paradigm, named federated edge learning (FEL), enables intelligent computing at the network edge with the feature of preserving data privacy for edge devices. Given their constrained resources, it becomes a great challenge to achieve high execution performance for FEL. Most of the state-of-the-arts concentrate on enhancing FEL from the perspective of system operation procedures, taking few precautions during the composition step of the FEL system. Though a few recent studies recognize the importance of FEL formation and propose server-centric device selection schemes, the impact of data sizes is largely overlooked. In this paper, we take advantage of game theory to depict the decision dilemma among edge devices regarding whether to participate in FEL or not given their heterogeneous sizes of local datasets. For realizing both the individual and global optimization, the server is employed to solve the participation dilemma, which requires accurate information collection for devices’ local datasets. Hence, we utilize mechanism design to enable truthful information solicitation. With the help of correlated equilibrium , we derive a decision making strategy for devices from the global perspective, which can achieve the long-term stability and efficacy of FEL. For scalability consideration, we optimize the computational complexity of the basic solution to the polynomial level. Lastly, extensive experiments based on both real and synthetic data are conducted to evaluate our proposed mechanisms, with experimental results demonstrating the performance advantages.Item Social Welfare Maximization in Cross-Silo Federated Learning(IEEE, 2022-05-23) Chen, Jianan; Hu, Qin; Jiang, Honglu; Computer and Information Science, School of ScienceAs one of the typical settings of Federated Learning (FL), cross-silo FL allows organizations to jointly train an optimal Machine Learning (ML) model. In this case, some organizations may try to obtain the global model without contributing their local training, lowering the social welfare. In this paper, we model the interactions among organizations in cross-silo FL as a public goods game for the first time and theoretically prove that there exists a social dilemma where the maximum social welfare is not achieved in Nash equilibrium. To over-come this social dilemma, we employ the Multi-player Multi-action Zero-Determinant (MMZD) strategy to maximize the social welfare. With the help of the MMZD, an individual organization can unilaterally control the social welfare without extra cost. Experimental results validate that the MMZD strategy is effective in maximizing the social welfare.Item Sequential Semantic Segmentation of Road Profiles for Path and Speed Planning(IEEE, 2022-12) Cheng, Guo; Yu Zheng, Jiang; Computer and Information Science, School of ScienceDriving video is available from in-car camera for road detection and collision avoidance. However, consecutive video frames in a large volume have redundant scene coverage during vehicle motion, which hampers real-time perception in autonomous driving. This work utilizes compact road profiles (RP) and motion profiles (MP) to identify path regions and dynamic objects, which drastically reduces video data to a lower dimension and increases sensing rate. To avoid collision in a close range and navigate a vehicle in middle and far ranges, several RP/MPs are scanned continuously from different depths for vehicle path planning. We train deep network to implement semantic segmentation of RP in the spatial-temporal domain, in which we further propose a temporally shifting memory for online testing. It sequentially segments every incoming line without latency by referring to a temporal window. In streaming-mode, our method generates real-time output of road, roadsides, vehicles, pedestrians, etc. at discrete depths for path planning and speed control. We have experimented our method on naturalistic driving videos under various weather and illumination conditions. It reached the highest efficiency with the least amount of data.Item Robust Node Classification on Graphs: Jointly from Bayesian Label Transition and Topology-based Label Propagation(ACM, 2022-10-17) Zhuang, Jun; Al Hasan, Mohammad; Computer and Information Science, School of ScienceNode classification using Graph Neural Networks (GNNs) has been widely applied in various real-world scenarios. However, in recent years, compelling evidence emerges that the performance of GNN-based node classification may deteriorate substantially by topological perturbation, such as random connections or adversarial attacks. Various solutions, such as topological denoising methods and mechanism design methods, have been proposed to develop robust GNN-based node classifiers but none of these works can fully address the problems related to topological perturbations. Recently, the Bayesian label transition model is proposed to tackle this issue but its slow convergence may lead to inferior performance. In this work, we propose a new label inference model, namely LInDT, which integrates both Bayesian label transition and topology-based label propagation for improving the robustness of GNNs against topological perturbations. LInDT is superior to existing label transition methods as it improves the label prediction of uncertain nodes by utilizing neighborhood-based label propagation leading to better convergence of label inference. Besides, LIndT adopts asymmetric Dirichlet distribution as a prior, which also helps it to improve label inference. Extensive experiments on five graph datasets demonstrate the superiority of LInDT for GNN-based node classification under three scenarios of topological perturbations.