BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Electrical & Computer Engineering - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
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:20210416T093000
DTEND;TZID=America/New_York:20210416T103000
DTSTAMP:20260515T143413
CREATED:20210412T185721Z
LAST-MODIFIED:20210412T185721Z
UID:4838-1618565400-1618569000@ece.northeastern.edu
SUMMARY:ECE MS Thesis Defense: Shanchuan Liang
DESCRIPTION:MS Thesis Defense: Design and Characterization of Flexible Neural Interface Connector for Large-scale Neuronal Recording \nShanchuan Liang \nLocation: Zoom Link \nAbstract: With the increasing demand of the electrically active implantable devices for studying neuroscience\, microelectrode arrays (MEAs) have been widely developed to measure extracellular neuronal activity. Multiple channels MEAs with electrodes embedded are designed to allow coupling time-resolved data simultaneously. In this process\, a well-designed PCB is also essential which use as a bridge to connect MEAs and back-end data acquisition system. This work developed an up to 256-channel flexible neural interface connector for neural signal recording. This thesis aims to introduce the detailed design and implementation procedures of the neural interface connector which consists of MEA\, PCB and amplifier. Considering the contact physics of the connector\, a contact model was established by using COMSOL to address the contact zone and figure out the displacement and pressure on the layer MEAs embedded. The simulation results were used for characterization and optimizing. Robustness tests reveal that the connector is stable up to 500 cycles with high yield. The following in vivo recordings by installed the device on mouse brain validate its excellent performance of recordings of spontaneous single-unit activity of neurons in which spikes in neurons were captured after signal processing.
URL:https://ece.northeastern.edu/event/ece-ms-thesis-defense-shanchuan-liang/
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20210416T130000
DTEND;TZID=America/New_York:20210416T140000
DTSTAMP:20260515T143413
CREATED:20210414T005310Z
LAST-MODIFIED:20210414T005310Z
UID:4841-1618578000-1618581600@ece.northeastern.edu
SUMMARY:ECE PhD Dissertation Defense: Kai Li
DESCRIPTION:PhD Dissertation Defense: Robust Visual Learning with Limited Labels \nKai Li \nLocation: Zoom Link \nAbstract: The recent flourish of deep learning in various tasks is largely credited to the rich and accessible labeled data. Nonetheless\, massive supervision remains a luxury for many real-world applications: It is costly and time-consuming to collect and annotate a large amount of training data. Sometimes it is even infeasible to get large training datasets because for certain tasks only a few or even no examples are available\, or annotating requires expert knowledge.\nIn this dissertation research\, I investigate techniques systematically addressing the problem of learning with limited labels from the following three aspects. The first aspect is learning to generalize from limited label supervision. I develop few-shot learning algorithms that perform data augmentation in the feature space and that generate task-specific networks based on the limited supervision provided. The second aspect is learning to reuse label supervision from a relevant but different task. I propose domain adaptation algorithms that adapt label supervision from a richly-labeled source domain to a scarcely-labeled target domain with consistency learning\, data augmentation and adversarial learning. The last aspect is learning representations without label supervision. I develop algorithms that learn semantic-rich representations that allow to reliably establish relations among high-dimensional data. This is achieved by explicitly modeling the intrinsic relationship among data points during the representation learning process. \n 
URL:https://ece.northeastern.edu/event/ece-phd-dissertation-defense-kai-li/
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20210416T153000
DTEND;TZID=America/New_York:20210416T163000
DTSTAMP:20260515T143413
CREATED:20210412T185358Z
LAST-MODIFIED:20210412T185358Z
UID:4837-1618587000-1618590600@ece.northeastern.edu
SUMMARY:ECE MS Thesis Defense: Mehrshad Zandigohar
DESCRIPTION:MS Thesis Defense: Real-Time Grasp Type Estimation for a Robotic Prosthetic Hand \nMehrshad Zandigohar \nLocation: Zoom Link \nAbstract: For lower arm amputees\, prosthetic hands promise to restore most of physical interaction capabilities. This requires to accurately predict hand gestures capable of grabbing varying objects and execute them timely as intended by the user. Current approaches often rely on physiological signal inputs such as Electromyography (EMG) signal from residual limb muscles to infer the intended motion. However\, limited signal quality\, user diversity and high variability adversely affect the system robustness.\nInstead of solely relying on EMG signals\, our work enables augmenting EMG intent inference with physical state probability through machine learning and computer vision method.\nTo this end\, we: (i) study state-of-the-art deep neural network architectures to select a performant sources of knowledge transfer for the prosthetic hand; (ii) use a dataset containing object images and probability distribution of grasp types as a new form of labeling where instead of using absolute values of zero and one as the conventional classification labels\, our labels are a set of probabilities whose sum is 1. The proposed method generates probabilistic predictions which could be fused with EMG prediction of probabilities over grasps by using the visual information from the palm camera of a prosthetic hand.\nMoreover\, As robotic prosthetic hands are targeted for amputees with the goal of assisting them for their daily life activities\, it is crucial to have a portable and reliable system. Although embedded devices employed in such systems\, provide portability and comfort for the end user\, their limited computational resources comparing to a desktop or server computer impose longer latencies when executing such applications\, making them unreliable and generally impractical to use. Therefore\, it is critical to optimize the aforementioned applications especially DNNs to meet the specified deadline\, resulting in a real-time system. Therefore\, for real-time execution of grasp estimation we propose: (iii) the concept of layer removal as a means of constructing TRimmed Networks (TRNs) that are based on removing problem-specific features of a pretrained network used in transfer learning\, and (iv) NetCut\, a methodology based on an empirical or an analytical latency estimator\, which only proposes and retrains TRNs that can meet the application’s deadline\, hence reducing the exploration time significantly. We demonstrate that TRNs can expand the Pareto frontier that trades off latency and accuracy to provide networks that can meet arbitrary deadlines with potential accuracy improvement over off-the-shelf networks. Our experimental results show that such utilization of TRNs\, while transferring to a simpler dataset\, in combination with NetCut\, can lead to the proposal of networks that can achieve relative accuracy improvement of up to 10.43\% among existing off-the-shelf neural architectures while meeting a specific deadline\, and 27x speedup in exploration time.\nThe proposed methods in this work enable robust and realistic prediction of the grasp type as well as real-time execution of the detection pipeline\, resulting in the improved overall satisfaction of the targeted population.
URL:https://ece.northeastern.edu/event/ece-ms-thesis-defense-mehrshad-zandigohar/
END:VEVENT
END:VCALENDAR