BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Electrical & Computer Engineering - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Department of Electrical & Computer Engineering
X-ORIGINAL-URL:https://ece.northeastern.edu
X-WR-CALDESC:Events for Department of Electrical & Computer Engineering
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20200308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20201101T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20210314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20211107T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20220313T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20221106T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20210421T090000
DTEND;TZID=America/New_York:20210421T100000
DTSTAMP:20260521T015642
CREATED:20210420T175730Z
LAST-MODIFIED:20210420T175730Z
UID:4851-1618995600-1618999200@ece.northeastern.edu
SUMMARY:ECE MS Thesis Defense: Rubens Lacouture
DESCRIPTION:MS Thesis Defense: GPUBLQMR: GPU-Accelerated Sparse Block Quasi-Minimum Residual Linear Solver \nRubens Lacouture \nLocation: Zoom Link \nAbstract: Solutions of linear systems of equations is the central point of many scientific and engineering research problems across a variety of domains. In many cases\, the solution of linear systems can even take most of the simulation time which presents a huge computational bottleneck issue. This can hinder the scalability of various scientific software hindering for larger problems. For large-scale simulations\, this can result in having to find the solutions of millions of unknowns\, making this an ideal problem to exploit parallelism to improve performance.\nPreconditioned Krylov subspace methods have proven effective and robust in various applications. The block Quasi-Minimum Residual (BLQMR) method as developed by Boyse et al. has been shown to be efficient for solving systems of equations with multiple righthand sides. This method is based on the conventional Quasi-Minimum Residual (QMR) method which is generalized using the block Lanczos algorithm to solve multiple solutions simultaneously. In particular\, it is shown that this method accelerates the convergence behavior based on the set number of righthand sides\, grouped to be solved simultaneously. Block iterative solver methods are often characterized by a high degree of parallelism.\nIn this thesis\, we show how BLQMR can be successfully implemented on a distributed memory computer taking advantage of Graphics Processing Units (GPU) accelerators. We leveraged the processing power of GPUs to show how the proposed GPU-accelerated BLQMR approach can out-perform state-of-the-art linear solvers and results in an ideal behavior for solving challenging linear algebra problems through data from various numerical experiments. The library code developed in this work is written using the CUDA framework. The performance of the parallel algorithm is optimized using several CUDA optimization strategies and the speedup of the parallel GPU implementation over the existing sequential CPU implementations is reported.
URL:https://ece.northeastern.edu/event/ece-ms-thesis-defense-rubens-lacouture/
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20210421T100000
DTEND;TZID=America/New_York:20210421T110000
DTSTAMP:20260521T015642
CREATED:20210420T180528Z
LAST-MODIFIED:20210420T180528Z
UID:4854-1618999200-1619002800@ece.northeastern.edu
SUMMARY:ECE MS Thesis Defense: Matin Raayai Ardakani
DESCRIPTION:MS Thesis Defense: A Framework for Denoising Two and Three-dimensional Monte CarloPhoton Transport Simulations Using Convolutional Neural Networks \nMatin Raayai Ardakani \nLocation: Zoom Link \nAbstract: The Monte Carlo (MC) method is considered to be the gold standard for modeling light propagation inside turbid media\, proving superior to other Radiative Transfer Equation (RTE) solvers relying on variational principles. However\, like most MC-based algorithm\, a large number of independently launched photons is needed for converging to the correct result and combating its inherent stochastic noise\, yielding longer computation times\, even when accelerated on GraphicProcessing Units (GPUs).\nTo remove this noise from the output without increasing the number of photons used for simulation\, modified versions of commonly used filters for image and volumetric data based on non-local self similarity has been used in the past. Current state-of-the-art denoising approaches rely on Convolutional Neural Networks (CNN) to remove spatially variant noise\, but the high dynamic range of MC simulations has hindered their adaptation to remove MC noise.\nIn this thesis\, we address this problem by presenting a supervised framework for using CNNs to denoise MC simulations. First\, a dataset is created with each entry comprising of a unique configuration simulated with different numbers of photons. The simulation configurations are generated using a simple generative model that introduces objects with both smooth and sharp edges into the volume. By selecting the group of fluence maps simulated with the maximum number of photons in the dataset as labels\, we train a range of CNN-based models to learn the underlying mapping between noisy and clean images. The CNN input is converted to log scale and normalized to reduce the high dynamic range\, and converted back after inference. The trained CNNs are then shown to have better performance compared to using an Adaptive Non-local Means filter\, in terms of mean square error (MSE)\, structural similarity index (SSIM)\, and peak signal-to-noise ratio (PSNR) in the image domain.\nFinally\, we purpose our own architecture that combines DnCNN and UNet\, a strategy that can learn both local and global residual noise maps\, achieving state-of-the-art performance compared to existing CNN methods. Future avenues of research and challenges for denoising 3D simulations are also discussed.
URL:https://ece.northeastern.edu/event/ece-ms-thesis-defense-matin-raayai-ardakani/
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20210421T100000
DTEND;TZID=America/New_York:20210421T170000
DTSTAMP:20260521T015642
CREATED:20210406T210701Z
LAST-MODIFIED:20210406T210701Z
UID:4831-1618999200-1619024400@ece.northeastern.edu
SUMMARY:MS Thesis Defense: Yuezhou Liu
DESCRIPTION:MS Thesis Defense: Optimizations of Caching Networks: Fairness and Application to Mobile Networks \nYuezhou Liu \nLocation: Zoom Link \nAbstract: In-network caching is playing a more and more important role in today’s network architectures\, because of the explosive growth of data traffic due to the proliferation of mobile devices and demands for high-volume media content\, as well as the development of low-latency applications\, such as VR/AR and cloud gaming. The replication of popular contents in the caches that located closer to end users than central servers\, can significantly reduce backbone traffic\, benefit request latency\, and balance the load of central servers. In this thesis\, we study two problems in the field of network caching. In the first part\, we consider fair caching policies in caching networks with arbitrary topology. We introduce a utility maximization framework to find a caching decision that reduces aggregate expected request routing cost in the network while taking fairness issues into consideration. The utility maximization problem is NP-hard\, and we propose two efficient approximation algorithms to solve it. In the second part\, we study how caching may affect user association in mobile networks. We jointly optimize the user association decision and caching at both base stations (BSs) and gateways (GWs). The resulting problem is also NP-hard. We propose a polynomial-time algorithm based on concave approximation and pipage rounding that produces a solution within a constant factor of 1-1/e from the optimal. Simulation results show that the proposed algorithm outperforms schemes that combine cache-independent user association methods with traditional caching strategies (e.g.\, LRU) in terms of minimizing the aggregate expected routing cost and backhaul traffic while achieving a high data sum rate in the access network.
URL:https://ece.northeastern.edu/event/ms-thesis-defense-yuezhou-liu/
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20210421T173000
DTEND;TZID=America/New_York:20210421T173000
DTSTAMP:20260521T015642
CREATED:20210421T193821Z
LAST-MODIFIED:20210421T193821Z
UID:4864-1619026200-1619026200@ece.northeastern.edu
SUMMARY:ECE PhD Dissertation Defense: Muhamed Yildiz
DESCRIPTION:PhD Dissertation Defense: Interpretable Machine Learning for Retinopathy of Prematurity \nMuhamed Yildiz \nLocation: Zoom Link \nAbstract: Retinopathy of Prematurity (ROP)\, a leading cause of childhood blindness\, is diagnosed by clinical ophthalmoscopic examinations or reading retinal images. Plus disease\, defined as abnormal tortuosity and dilation of the posterior retinal blood vessels\, is the most important feature to determine treatment-requiring ROP. State-of-the-art ROP detection systems employ convolutional neural networks (CNNs) %\cite{brown2018automated} and achieve up to $0.947$ and $0.982$ area under the ROC curve (AUC) in the discrimination of \textit{normal} and \textit{plus} levels of ROP. However\, due to their black-box nature\, clinicians are reluctant to trust diagnostic predictions of CNNs.\nFirst\, we aim to create an interpretable\, feature extraction-based pipeline\, namely\, I-ROP ASSIST\, that achieves CNN like performance when diagnosing plus disease from retinal images. Our method segments retinal vessels\, detects the vessel centerlines. Then\, our method extracts features relevant to ROP\, including tortuosity and dilation measures\, and uses these features for classification via logistic regression\, support vector machines and neural networks to assess a severity score for the input. For predicting \textit{normal} and \textit{plus} levels of ROP on a dataset containing 5512 posterior retinal images\, we achieve $0.88$ and $0.94$ AUC\, respectively. Our system combining automatic retinal vessel segmentation\, tracing\, feature extraction and classification is able to diagnose plus disease in ROP with CNN like performance.\nThen\, we introduce a novel method for extracting tortuosity features. Current feature extraction pipelines of retinal image analysis systems extract tortuosity features based on the derivatives of vessel centerlines or a segment of a vessel. Our method eliminates the need for finding vessel centerlines by introducing a method for calculating curvature at each pixel in the fundus image. When calculating curvature\, we use the geometric interpretation of eigenvectors of the Hessian of an interpolation function. By selecting an appropriate interpolation function\, our method can be applied in many domains\, including corner detection\, noise removal and image registration. We present the results of our method on artificial images that contains curved structures such as circle\, sine waves as well as real images from MNIST and our retinal fundus image dataset. Experimental results shows that our model accurately captures the high curvature parts of the blood vessels. \nFurthermore\, we aim to address the interpretability problem of CNN-based ROP detection system. Incorporating visual attention capabilities in CNNs enhances interpretability by highlighting regions in the images that CNNs utilize for prediction. Generic visual attention methods do not leverage structural domain information such as tortuosity and dilation of retinal blood vessels in ROP diagnosis. We propose the Structural Visual Guidance Attention Networks (SVGA-Net) method\, that leverages structural domain information to guide visual attention in CNNs. SVGA-Net achieves $0.979$ and $0.987$ AUC to predict \textit{normal} and \textit{plus} levels of ROP. Moreover\, SVGA-Net consistently results in higher AUC compared to visual attention CNNs without guidance\, baseline CNNs\, and CNNs with structured masks.
URL:https://ece.northeastern.edu/event/ece-phd-dissertation-defense-muhamed-yildiz/
END:VEVENT
END:VCALENDAR