检索结果-内蒙古大学图书馆

Membership Inference Attacks Against Temporally Correlated Data in Deep Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Gomrokchi, Maziar Amin, Susan Aboutalebi, Hossein Wong, Alexander Precup, Doina Department of Computer Science McGill University Mila Canada Cheriton School of Computer Science University of Waterloo VIP Lab Canada Department of Systems Design Engineering University of Waterloo VIP Lab DarwinAI Canada Department of Computer Science McGill University Mila DeepMind Canada

While significant research advances have been made in the field of deep reinforcement learning, there have been no concrete adversarial attack strategies in literature tailored for studying the vulnerability of deep reinforcement learning algorithms to membership inference attacks. In such attacking systems, the adversary targets the set of collected input data on which the deep reinforcement learning algorithm has been trained. To address this gap, we propose an adversarial attack framework designed for testing the vulnerability of a state-of-the-art deep reinforcement learning algorithm to a membership inference attack. In particular, we design a series of experiments to investigate the impact of temporal correlation, which naturally exists in reinforcement learning training data, on the probability of information leakage. Moreover, we compare the performance of collective and individual membership attacks against the deep reinforcement learning algorithm. Experimental results show that the proposed adversarial attack framework is surprisingly effective at inferring data with an accuracy exceeding 84% in individual and 97% in collective modes in three different continuous control Mujoco tasks, which raises serious privacy concerns in this regard. Finally, we show that the learning state of the reinforcement learning algorithm influences the level of privacy breaches significantly. Copyright © 2021, The Authors. All rights reserved.

关键词： Reinforcement learning

Fractal dimension and retinal pathology: A meta-analysis

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yu, Sam Lakshminarayanan, Vasudevan Department of Physics and Astronomy University of Waterloo ONN2L 3G1 Canada Theoretical and Experimental Epistemology Lab School of Optometry and Vision Science Department of Electrical and Computer Engineering University of Waterloo ONN2L 3G1 Canada Department of Systems Design Engineering University of Waterloo ONN2L 3G1 Canada

Due to the fractal nature of retinal blood vessels, the retinal fractal dimension is a natural parameter for researchers to explore and has garnered interest as a potential diagnostic tool. This review aims to summarize the current scientific evidence regarding the relationship between fractal dimension and retinal pathology and thus assess the clinical value of retinal fractal dimension. Following the PRISMA guidelines, a literature search for research articles was conducted in several internet databases (Embase, PubMed, Web of Science, Scopus). This led to a result of 28 studies included in the final review, which were analyzed via meta-analysis to determine whether the fractal dimension changes significantly in retinal disease versus normal individuals. © 2021, CC BY.

关键词： Ophthalmology

Distributed nonlinear model predictive control and metric learning for heterogeneous vehicle platooning with cut-in/cut-out maneuvers

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Basiri, Mohammad Hossein Ghojogh, Benyamin Azad, Nasser L. Fischmeister, Sebastian Karray, Fakhri Crowley, Mark The Department of Systems Design Engineering University of Waterloo ON Canada The Department of Electrical and Computer Engineering University of Waterloo ON Canada The Smart Hybrid and Electric Vehicles Systems Lab The Real-Time Embedded Software Lab The Machine Learning Lab The Centre for Pattern Analysis and Machine Intelligence

Vehicle platooning has been shown to be quite fruitful in the transportation industry to enhance fuel economy, road throughput, and driving comfort. Model Predictive Control (MPC) is widely used in literature for platoon control to achieve certain objectives, such as safely reducing the distance among consecutive vehicles while following the leader vehicle. In this paper, we propose a Distributed Nonlinear MPC (DNMPC), based upon an existing approach, to control a heterogeneous dynamic platoon with unidirectional topologies, handling possible cut-in/cut-out maneuvers. The introduced method addresses a collision-free driving experience while tracking the desired speed profile and maintaining a safe desired gap among the vehicles. The time of convergence in the dynamic platooning is derived based on the time of cut-in and/or cut-out maneuvers. In addition, we analyze the improvement level of driving comfort, fuel economy, and absolute and relative convergence of the method by using distributed metric learning and distributed optimization with Alternating Direction Method of Multipliers (ADMM). Simulation results on a dynamic platoon with cut-in and cut-out maneuvers and with different unidirectional topologies show the effectiveness of the introduced method. Copyright © 2020, The Authors. All rights reserved.

关键词： Topology

MRI images, brain lesions and deep learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Castillo, Darwin Lakshminarayanan, Vasudevan Rodríguez-Álvarez, Maria J. Departamento de Química y Ciencias Exactas Sección Fisicoquímica y Matemáticas Universidad Técnica Particular de Loja Loja11-01-608 Ecuador Theoretical and Experimental Epistemology Lab School of Optometry and Vision Science University of Waterloo Ontario Canada Departments of Physics Electrical and Computer Engineering and Systems Design Engineering University of Waterloo Ontario Canada Valencia Spain

Medical brain image analysis is a necessary step in the Computers Assisted /Aided Diagnosis (CAD) systems. Advancements in both hardware and software in the past few years have led to improved segmentation and classification of various diseases. In the present work, we review the published literature on systems and algorithms that allow for classification, identification, and detection of White Matter Hyperintensities (WMHs) of brain MRI images specifically in cases of ischemic stroke and demyelinating diseases. For the selection criteria, we used the bibliometric networks. Out of a total of 140 documents we selected 38 articles that deal with the main objectives of this study. Based on the analysis and discussion of the revised documents, there is constant growth in the research and proposal of new models of deep learning to achieve the highest accuracy and reliability of the segmentation of ischemic and demyelinating lesions. Models with indicators (Dice Score, DSC: 0.99) were found, however with little practical application due to the uses of small datasets and lack of reproducibility. Therefore, the main conclusion is to establish multidisciplinary research groups to overcome the gap between CAD developments and their complete utilization in the clinical environment. © 2021, CC BY.

关键词： Magnetic resonance imaging

Information Technology systems at the sharp end of medication therapy management

学校读者我要写书评

暂无评论

Proceedings of the Human Factors and Ergonomics Society Annual Meeting 2019年第1期63卷 698 - 702页

作者： Reicelis Casares Li Rodrigo Arcuri Marques Pereira Alessandro Jatobá Mario Cesar Rodríguez Vidal Paulo Victor Rodrigues de Carvalho Kelly Grindrod Catherine Burns Advanced Interface Design Lab Systems Design Engineering University of Waterloo Ontario Canada Advanced Interface Design Lab Systems Design Engineering University of Waterloo Ontario CanadaComplex Systems Ergonomics Research Unit (GENTE) Federal University of Rio de Janeiro Brazil Oswaldo Cruz Foundation (FIOCRUZ) Rio de Janeiro Brazil Complex Systems Ergonomics Research Unit (GENTE) Federal University of Rio de Janeiro Brazil Nuclear Engineering Institute (IEN) Rio de Janeiro Brazil School of Pharmacy University of Waterloo Ontario Canada

This study explored how to inform the design of information systems for medication therapy management, in the context of the southwestern Ontario health system. The data collection comprised document analysis, interviews, and process mapping, and the analysis of previous interview records. The Functional Resonance Analysis Method (FRAM) was used for data analysis to identify the effects of functional variability in system outcomes, and to propose ways to redesign future systems. The results from the FRAM showed that shortcomings in the information systems require users to adapt in many ways. While these adjustments are essential to delivering care in everyday practice, they may lose their effectiveness in the face of specific situations, creating brittleness and risk of adverse outcomes as users are led to make challenging decisions.

关键词：

Robust Simultaneous and Proportional Myoelectric Control Scheme for Individuals with Transradial Amputations

学校读者我要写书评

暂无评论

Robust Simultaneous and Proportional Myoelectric Control Sch...

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： A. Pradhan U. Kuruganti W. Hill N. Jiang V. Chester eBionics Lab Systems Design Engineering University of Waterloo Waterloo Canada Andrew and Marjorie McCain Human Performance Laboratory Faculty of Kinesiology University of New Brunswick Fredericton Canada Institute of Biomedical Engineering University of New Brunswick Fredericton Canada

ISBN: (数字)9781728119908

ISBN: (纸本)9781728119915

Commercial myoelectric prostheses need to be accurate and clinically viable to be successful. This study proposed a simultaneous and proportional control scheme with frequency division technique (SPEC-FDT) to address limitations in current myoelectric prosthesis control, specifically to address non-stationaries such as contraction level variations and unintended activations. Twenty able-bodied participants (14 males and 6 females, age 23.4 ± 3.0) and four individuals with transradial amputations performed wrist movements (flexion/extension, rotations and combined movements) in two degrees-of freedom virtual tasks. The SPEC-FDT had a completion rate (CR)>90% for both control and clinical participants which was significantly higher than the conventional technique (CR=68%). Our results showed that SPEC-FDT is highly accurate for both able-bodied and clinical participants and provides a robust myoelectric control scheme allowing for increased prosthetic hand functions.

关键词： Task analysis Prosthetics Robustness Training Electromyography Testing Wrist

Test-retest evaluation of a notched-noise test using consumer-grade mobile audio equipment

学校读者我要写书评

暂无评论

International Audiology 2024年第2期63卷

作者： Petteri Hyvärinen Michal Fereczkowski Ewen N. MacDonald a Acoustics Lab Department of Signal Processing and Acoustics Aalto University Espoo Finlandb Hearing Systems Section Department of Health Technology Technical University of Denmark Lyngby Denmark b Hearing Systems Section Department of Health Technology Technical University of Denmark Lyngby Denmarkc Institute of Clinical Research Faculty of Health Sciences University of Southern Denmark Odense Denmarkd Research Unit for ORL – Head & Neck Surgery and Audiology Odense University Hospital & University of Southern Denmark Odense Denmark b Hearing Systems Section Department of Health Technology Technical University of Denmark Lyngby Denmarke Department of Systems Design Engineering University of Waterloo Waterloo Canada

ObjectiveThe aim of this study was to investigate whether consumer-grade mobile audio equipment can be reliably used as a platform for the notched-noise test, including when the test is conducted outside the *** studies were conducted: Study 1 was a notched-noise masking experiment with three different setups: in a psychoacoustic test booth with a standard laboratory PC; in a psychoacoustic test booth with a mobile device; and in a quiet office room with a mobile device. Study 2 employed the same task as Study 1, but compared circumaural headphones to insert *** sampleNine and ten young, normal-hearing participants completed studies 1 and 2, *** test-retest accuracy of the notched-noise test on the mobile implementation did not differ from that for the laboratory setup. A possible effect of the earphone design was identified in Study 1, which was corroborated by Study 2, where test-retest variability was smallest when comparing results from experiments conducted using identical acoustic *** and test-retest repeatability comparable to standard laboratory settings for the notched-noise test can be obtained with mobile equipment outside the laboratory.

关键词： Notched-noise test telemedicine test-retest reliability

Densenet for breast tumor classification in mammographic images

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Gaona, Yuliana Jiménez Rodriguez-Alvarez, María José Morató, Hector Espinó Malla, Darwin Castillo Lakshminarayanan, Vasudevan Departamento de Química y Ciencias Exactas Universidad Técnica Particular de Loja San Cayetano Alto s/n LojaCP1101608 Ecuador Instituto de Instrumentación para la Imagen Molecular I3M Universitat Politécnica de Valencia ValenciaE-46022 Spain Theoretical and Experimental Epistemology Lab School of Optometry and Vision Science Department of Systems Design Engineering Physics and Electrical and Computer Engineering University of Waterloo WaterlooONN2L3G1 Canada

Breast cancer is the most common invasive cancer in women, and the second main cause of death. Breast cancer screening is an efficient method to detect indeterminate breast lesions early. The common approaches of screening for women are tomosynthesis and mammography images. However, the traditional manual diagnosis requires an intense workload by pathologists, who are prone to diagnostic errors. Thus, the aim of this study is to build a deep convolutional neural network method for automatic detection, segmentation, and classification of breast lesions in mammography images. Based on deep learning the Mask-CNN (RoIAlign) method was developed to features selection and extraction;and the classification was carried out by DenseNet architecture. Finally, the precision and accuracy of the model is evaluated by cross validation matrix and AUC curve. To summarize, the findings of this study may provide a helpful to improve the diagnosis and efficiency in the automatic tumor localization through the medical image classification. © 2021, CC BY.

关键词： Convolutional neural networks

Breast mass regions classification from mammograms using convolutional neural networks and transfer learning.

学校读者我要写书评

暂无评论

Optica Acta: International Journal of Optics 2023年第10期70卷

作者： Yuliana Jiménez-Gaona María José Rodríguez-Álvarez Diana Carrión-Figueroa Darwin Castillo-Malla Vasudevan Lakshminarayanan a Departamento de Química y Ciencias Exactas Universidad Técnica Particular de Loja Loja Ecuadorb Instituto de Instrumentación para la Imagen Molecular i3M Universitat Politècnica de València (UPV)- Consejo Superior de Investigaciones Científicas (CSIC) Valencia Spaind Theoretical and Experimental Epistemology Lab School of Optometry and Vision Science University of Waterloo Waterloo Canada b Instituto de Instrumentación para la Imagen Molecular i3M Universitat Politècnica de València (UPV)- Consejo Superior de Investigaciones Científicas (CSIC) Valencia Spain c Hospital Carlos Andrade Marín IESS Quito Ecuador d Theoretical and Experimental Epistemology Lab School of Optometry and Vision Science University of Waterloo Waterloo Canadae Department of Systems Design Engineering Physics and Electrical and Computer Engineering University of Waterloo Waterloo Canada

This study introduces a novel approach aimed at enhancing the quality of digital mammography images through pre-processing techniques, to improve breast cancer detection accuracy. The primary objective is to enhance image resolution, thus leading to more precise breast tissue segmentation and subsequent classification utilizing convolutional neural networks (CNNs). Three recognized public mammography databases: CBIS-DDSM, Mini-MIAS, and Inbreast were used as pre-processing data. Our statistical findings revealed that the EDSR method (PSNR = 39.05 dB/ SSIM = 0.90) consistently outperformed the visual quality of images when compared to SR-RDN (PSNR = 32.68 dB/SSIM = 0.82). Similarly, UNet demonstrated superior performance over SegNet, boasting an average Intersection over Union (IoU) of 0.862, an average Dice coefficient of 0.991, and an accuracy rate of 0.947 in Region of Interest (RoI) segmentation results. In conclusion, the ResNet model contributed to enhanced accuracy compared to conventional machine learning algorithms. However, it did not surpass state-of-the-art deep CNN-based classifiers, achieving an accuracy rate of 75%.Abbreviations:AUC: Area under curve; CAD: Computer aided system; CC: Cranio caudal; CNN: Convolutional neural network; DNN: Deep neural network; DDSM: Digital Database for Screening Mammography; DM: Digital mammography; DL: Deep learning; EDSR: Enhanced Deep Residual Network; E2E: End to End; ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks; ESPCN: Efficient sub-pixel convolutional neural network; GAN: Generative adversarial network; HR: High resolution; IoU: Intersection over Union; LR: Low resolution; MDSR: Multi-scale deep super-resolution; MLO: Mediolateral Oblique; PSNR: Peak signal to Noise Ratio; RoI: Region of interest; RDN: Residua Dense Network; RDB: Residual Dense Block; RNN: Recurrent Neural Network; ReLU: Rectified Linear Unit; SR-GAN: Super-Resolution Using a Generative Adversarial Network; SSIM: Structural Sim

关键词： Breast cancer classification convolutional neural network mammography images segmentation super resolution