Program for 2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP)

  Tuesday, November 12 Wednesday, November 13 Thursday, November 14
8:00 ‑ 8:15 Opening Remarks and Plenary I        
8:15 ‑ 9:30   Plenary II   Plenary IV
9:30 ‑ 10:00 Coffee Break Signal Processing for Human Machine Learning Systems: Poster Session
Graph Signal Processing & Machine Learning for Rare Event Detection in Healthcare: Poster Session
GS: Signal Processing Theory and Methods: Poster Session
Coffee Break & Poster Session GS: Image and Video Processing: Poster Session
GS: Classification and Learning: Poster Session
Machine Learning for Wireless Communications, Networking, and Security II: Poster Session
Coffee Break
10:00 ‑ 12:00 Graph Signal Processing I
Machine Learning, Optimization and Security for Future Energy Delivery Systems I
Machine Learning for Rare Event Detection in Healthcare I
Signal Processing for Human Machine Learning Systems I
Mathworks Workshop
Signal Processing and Machine Learning for Social Good I
Machine Learning, Optimization and Security for Future Energy Delivery Systems IV
Machine Learning for Wireless Communications, Networking, and Security I
GS: Compressed sensing, sparsity aware processing
Signal/Information Processing and AI for Finance and Business I
Machine Learning for Wireless Communications, Networking, and Security IV
GS: Cognitive communications and radar
12:00 ‑ 13:00 Lunch & Poster Session
Young Professionals Networking Event
Lunch Lunch
13:00 ‑ 13:30 Plenary III
13:30 ‑ 14:00 Deep Learning for Healthcare Engineering I
Graph Signal Processing II
Machine Learning, Optimization and Security for Future Energy Delivery Systems II
Machine Learning for Rare Event Detection in Healthcare II
Artificial Intelligence for Future Wireless Communication I
Signal/Information Processing and AI for Finance and Business III: Poster Session
Signal and Information Processing for Person-centered and Citizen-centered Smart Living I
Signal/Information Processing and AI for Finance and Business II
Advanced Bio-Signal Processing and Machine Learning for Assistive and Neuro-Rehabilitation Systems II
GS: MIMO Systems
14:00 ‑ 14:20  
14:20 ‑ 15:30 Tensor Methods in Signal Processing and Machine Learning I
Signal Processing and Machine Learning for Social Good II
GS: Classification and Learning I
Advanced Bio-Signal Processing and Machine Learning for Assistive and Neuro-Rehabilitation Systems I
GS: Image and Video Processing II
15:30 ‑ 16:00 Coffee Break & Poster Session Coffee Break
16:00 ‑ 16:30 Deep Learning for Healthcare Engineering II
GS: Array Signal Processing
Machine Learning, Optimization and Security for Future Energy Delivery Systems III
Signal Processing for Human Machine Learning Systems II
Artificial Intelligence for Future Wireless Communication II
Coffee Break & Poster Session Signal and Information Processing for Person-centered and Citizen-centered Smart Living II
Signal/Information Processing and AI for Finance and Business IV
Advanced Bio-Signal Processing and Machine Learning for Assistive and Neuro-Rehabilitation Systems III
GS: Machine Learning Networks
GS: Signal Processing for Communications
16:30 ‑ 18:00 Tensor Methods in Signal Processing and Machine Learning II
GS: Hardware and Real-Time Implementations
GS: Speech and Acoustic Signal Processing
Machine Learning for Wireless Communications, Networking, and Security III
GS: Image and Video Processing I
18:00 ‑ 18:30        
18:30 ‑ 19:00          
19:00 ‑ 19:30 Welcome Reception        
19:30 ‑ 22:00   Conference Dinner    

Tuesday, November 12

Tuesday, November 12 8:00 - 9:30

Opening Remarks and Plenary I

Haizhou Li
Room: Plenary Room

Tuesday, November 12 9:30 - 10:00

Coffee Break

Tuesday, November 12 9:30 - 18:00

GS: Signal Processing Theory and Methods: Poster Session

Chair: Sundeep Prabhakar Chepuri (Indian Institute of Science, India)
Cramer-Rao Bound for Joint Angle and Delay Estimators by Partial Relaxation
Ahmad Bazzi (CEVA, France); Dirk Slock (EURECOM, France)
Interactive Multi-model Tracking of a Highly Maneuvering Target using MSPDAF with Least Squares Virtual Fusion
Qin Tang (University of Electronic Science and Technology of China, P.R. China); Fangqi Zhu (University of Texas at Arlington, USA); Jing Liang (University of Electronic Science and Technology of China, P.R. China)
Cramér-Rao Bound for Wideband DOA Estimation with Uncorrelated Sources
Yibao Liang, Qing Shen and Wei Cui (Beijing Institute of Technology, P.R. China); Wei Liu (University of Sheffield, United Kingdom (Great Britain))
Localization in Autonomous Vehicles Using a Generalized Inner Product
Samuel Todd Flanagan, Drupad K Khublani and Jean-Francois Chamberland (Texas A&M University, USA); Siddharth Agarwal and Ankit Vora (Ford Motor Company, USA)
Velocity Estimation Algorithms for Suspensions
Diana Hernandez-Alcantara (Universidad de Monterrey, Mexico); Luis Amezquita-Brooks (Universidad Autonoma de Nuevo Leon, Mexico); Nancy Morales-Villarreal and Omar Juarez-Tamez (Universidad de Monterrey, Mexico)
Multi-Objective Gain Optimizer for an Active Disturbance Rejection Controller
Brayden M DeBoon, Brayden Kent and Maciej Lacki (Ontario Tech University, Canada); Scott B. Nokleby (University of Ontario Institute of Technology, Canada); Carlos Rossa (Ontario Tech University, Canada)
Low Complexity Frequency Monitoring Filter for Fast Exon Prediction Sequence Analysis
Daniel Massicotte and Marwan Jaber (Universite du Quebec a Trois-Rivieres, Canada); Marie-Ange Massicotte (Universite Laval, Canada); Philippe Massicotte (Universite du Quebec a Trois-Rivieres, Canada)
α Belief Propagation as Fully Factorized Approximation
Dong Liu (KTH, Sweden); Nima N. Moghadam (Huawei Technologies Sweden AB, Sweden); Lars Kildehoj Rasmussen (KTH Royal Institute of Technology, Sweden); Jingliang Huang (Huawei, Sweden); Saikat Chatterjee (KTH - Royal Institute of Technology & Communication Theory Lab, Sweden)

Signal Processing for Human Machine Learning Systems: Poster Session

Chair: Bhavya Kailkhura (Lawrence Livermore National Lab, USA)
An Accurate Evaluation of MSD Log-likelihood and its Application in Human Action Recognition
Nuha Zamzami and Nizar Bouguila (Concordia University, Canada)
Mechanical Acoustic Signal Assisted Translational Model for Industrial Human-Machine Interaction
Zhiduo Ji, Cailian Chen, Jianping He and Xinping Guan (Shanghai Jiao Tong University, P.R. China)
A Novel Slip-Kalman Filter to Track the Progression of Reading Through Eye-Gaze Measurements
Stephen Bottos and Balakumar Balasingam (University of Windsor, Canada)
Identity Retaining and Redundancy Reducing GAN for Person Re-identification
Jiangbo Pei and Yinsong Xu (Beijing University of Posts and Telecommunications, P.R. China)
A Comparison of Boosted Deep Neural Networks for Voice Activity Detection
Harshit Krishnakumar (Indiana University Bloomington, USA); Donald S Williamson (Indiana University, USA)
Privacy Preserving Deep Learning with Distributed Encoders
Yitian Zhang and Hojjat Salehinejad (University of Toronto, Canada); Joseph Barfett (St. Michael's Hospital, Canada); Errol Colak and Shahrokh Valaee (University of Toronto, Canada)
Visually Assisted Time-Domain Speech Enhancement
Elham Ideli (Simon Fraser University & SingSoftNext, Canada); Bruce Sharpe (Singular Software Inc., Canada); Ivan V. Bajic and Rodney Vaughan (Simon Fraser University, Canada)
Generative Counterfactual Introspection for Explainable Deep Learning
Shusen Liu (Lawrence Livermore National Laboratory, USA); Bhavya Kailkhura (Lawrence Livermore National Lab, USA); Donald Loveland and Yong Han (Lawrence Livermore National Laboratory, USA)
On Amelioration Of Human Cognitive Biases In Binary Decision Making
Baocheng Geng and Pramod Varshney (Syracuse University, USA); Muralidhar Rangaswamy (AFRL, USA)
A Privacy Solution for Voice Enabled Devices Connected to the Internet
Mohammad Niknazar, Aditya Vempaty and Paul Haley (Xio Research Inc., USA)

Graph Signal Processing & Machine Learning for Rare Event Detection in Healthcare: Poster Session

Chairs: Sundeep Prabhakar Chepuri (Indian Institute of Science, India), Yasmina Souley Dosso (Carleton University, Canada)
Kernel Node Embeddings
Abdulkadir Celikkanat (CentraleSupelec, Paris-Saclay University, France); Fragkiskos Malliaros (CentraleSupelec, University of Paris-Saclay, France)
Graph Filtering with Quantization over Random Time-varying Graphs
Leila Ben Saad (University of Agder, Norway); Elvin Isufi (Delft University of Technology, The Netherlands); Baltasar Beferull-Lozano (University of Agder, Norway)
The Cosine Number Transform: A Graph Signal Processing Approach
Guilherme Ribeiro (Universidade Federal de Pernambuco, Brazil); Juliano B. Lima (Federal University of Pernambuco, Brazil)
Bayesian Design of Sampling Set for Bandlimited Graph Signals
Xuan Xie, Junhao Yu and Hui Feng (Fudan University, P.R. China); Bo Hu (Fudan University, Shanghai, P.R. China)
Anomalous Sensor Detection Based on Nonlinear Graph Filter
Zhuo Li and Zhenlong Xiao (Xiamen University, P.R. China); Chao Lan (University of Wyoming, USA)
GSP Analysis of Brain Imaging Data from Athletes with History of Multiple Concussions
Saurabh Sihag (Rensselaer Polytechnic Institute & Computational Biology Center, T. J. Watson IBM Research Center, USA); Sebastien Naze (T. J. Watson IBM Research Center, USA); Foad Taghdiri and Maria Carmela Tartaglia (Tanz Centre for Research in Neurodegenerative Diseases, University of Toronto, Canada); James Kozloski (IBM Research, USA)
On Critical Sampling of Time-Vertex Graph Signals
Junhao Yu, Xuan Xie and Hui Feng (Fudan University, P.R. China); Bo Hu (Fudan University, Shanghai, P.R. China)
Towards a Graph Signal Processing Framework for Modeling Power System Dynamics
Xinyue Hu and Zhi-Li Zhang (University of Minnesota, USA)
AMA: An Open-source Amplitude Modulation Analysis Toolkit for Signal Processing Applications
Where am I Looking: Localizing Gaze in Reconstructed 3D Space
Devarth Parikh (Rochester Institute of Technology, USA); Yawen Lu (Rochester Institute of Tech, USA); Yuan Xin and Di Wu (Tencent Deep Sea Lab, P.R. China); Jeff Pelz and Guoyu Lu (Rochester Institute of Technology, USA)

Tuesday, November 12 10:00 - 12:00

Graph Signal Processing I

Room 202
Chair: Gonzalo Mateos (Rochester University, USA)
Sampling Signals on Meet/Join Lattices
Chris Wendler and Markus Püschel (ETH Zurich, Switzerland)
Modeling and Recovery of Graph Signals and Difference-Based Signals
Ariel Kroizer (Ben Gurion University of the Negev, Israel); Yonina C. Eldar (Weizmann Institute of Science, Israel); Tirza Routtenberg (Ben Gurion University of the Negev, Israel)
Mapping brain structural connectivities to functional networks via graph encoder-decoder with interpretable latent embeddings
Yang Li, Rasoul Shafipour and Gonzalo Mateos (University of Rochester, USA); Zhengwu Zhang (Duke University & SAMSI, USA)
On Folded Graph Signals
Feng Ji, Pratibha Pratibha and Wee Peng Tay (Nanyang Technological University, Singapore)
Sampling and Reconstruction of Diffusive Fields on Graphs
Siddartha Reddy (Indian Institute Of Sciences, India); Sundeep Prabhakar Chepuri (Indian Institute of Science, India)

Machine Learning, Optimization and Security for Future Energy Delivery Systems I

Room 203
Chair: Mahnoosh Alizadeh (University of California, Santa Barbara, USA)

Keynote Speaker: Alejandro Dominguez-Garcia, UIUC

Invited Talks

Mads Almassalkhi

Title Enabling Real-time, Network-admissible Disaggregation of Market Services with Convex Inner Approximations

Abstract The talk presents a novel method to obtain a convex inner approximation that aims to improve the feasibility of optimal power flow (OPF) models in distribution networks. For a resistive distribution network, both real and reactive power effect the node voltages and this makes it necessary to consider both when formulating the OPF problem and the available dispatchable resources. Inaccuracy in linearized OPF models may lead to under and over voltages when dispatching flexible demand, at scale and in response to whole-sale, fast market or variable grid conditions. In order to guarantee feasibility, we obtain an inner convex set, in which the dispatchable resources can operate, based on their real and reactive power capabilities. This convex set is the effective dynamic DER hosting capacity and by disaggregating market signals within this set, we can a-priori guarantee a network admissible dispatch at any timescale. This DER hosting capacity enables us to employ feedback-based methods to perform real-time, network admissible disaggregation of market/grid signal across available DERs in the network. We will also adapt this method to develop a multi-period version of the dynamic DER hosting capacity and present simulation-based analysis on realistic test feeders.

Bio Mads Almassalkhi (IEEE M'06; SM'19) is Assistant Professor in the Department of Electrical and Biomedical Engineering at the University of Vermont and co-founder of startup company Packetized Energy. His research interests lie at the intersection of power systems, mathematical optimization, and control systems and focuses on developing scalable algorithms that improve responsiveness and resilience of power systems. He was awarded the Outstanding Junior Faculty award by his college in 2016. Prior to joining the University of Vermont, he was lead systems engineer at Root3 Technologies, which developed software for set-point optimization of multi-energy systems. Before that, he received his PhD from the University of Michigan in Electrical Engineering (EE): Systems in 2013 and a dual major in Electrical Engineering and Applied Mathematics at the University of Cincinnati in Ohio in 2008. When he is not working on energy problems or teaching, he is spending his time with his amazing wife and their three small children.

Severin Nowak, Liwei Wang, and Christine Chen

Title Measurement-based Optimal DER Dispatch via Distributed ADMM Optimization

Abstract The proliferation of distributed energy resources (DERs) across power distribution networks requires new monitoring and control schemes to ensure power availability and quality and avoid costly infrastructure investments. Concurrently, recent advances in sensor technologies, such as smart metres and micro phasor measurement units (micro-PMUs), offer ample measurement data of key attributes in the distribution system. These are crucial for developing operational tools to, e.g., detect abnormal events, estimate the network topology, and trigger protective relays. In this work, we develop a measurement- based method to optimally dispatch DER active- and reactive-power injections aimed at improving overall system performance. Specifically, we seek to minimize DER injection costs as well as deviations of bus voltages and bus injections away from their respective setpoints. Central to the proposed framework is the synthesis of a linear pseudo-power-flow model from only micro-PMU measurements of voltages and power injections at a subset of nodes in a distribution network. We then incorporate the estimated linear model into a modified optimal power-flow problem that is solved via distributed alternating direction method of multipliers (ADMM). Individual DER controllers concurrently optimize their respective active- and reactive-power setpoints to satisfy local constraints of available DER capacities and voltage levels, while also jointly achieving global operational objectives. In this talk, we will demonstrate the following benefits of the proposed method: (i) it adapts to network reconfigurations by not relying on an up-to- date offline model, (ii) it achieves similar global performance as nonlinear model-based optimization formulations, and (iii) it significantly reduces computational burden via parallel computing.

Bio Christine Chen is an Assistant Professor with the Department of Electrical and Computer Engineering, The University of British Columbia, Vancouver, BC, Canada, where she is affiliated with the Electric Power and Energy Systems Group. She received the M.S. and Ph.D. degrees in Electrical Engineering from the University of Illinois at Urbana-Champaign in 2011 and 2014, respectively. Prior to graduate school, she earned the B.A.Sc. degree in Engineering Science (Electrical option) from the University of Toronto in 2009. Her research interests include power system analysis, monitoring, and control. Christine is a recipient of the 2017-2018 Best Paper Award from the IEEE Transactions on Energy Conversion. She presently serves Associate Editors for the International Journal of Electrical Power & Energy Systems and the IEEE Transactions on Energy Conversion.

Risk-Sensitive Energy Procurement with Uncertain Wind
Avinash N Madavan (University of Illinois at Urbana-Champaign, USA); Subhonmesh Bose (University of Illinois at Urbana Champaign, USA)

Machine Learning for Rare Event Detection in Healthcare I

Room 204
Chairs: Mohamed Abdelazez (Carleton University, Canada), Yasmina Souley Dosso (Carleton University, Canada)

Distinguished Lecturer: Dr. Thomas Heldt

Finding the Needle in the Haystack: Approaches to Identifying Septic Patients in the Emergency Department

Sepsis is by no means a rare condition, contributing by some estimates to 1 to 2 of every three in-hospital deaths. While much effort has been focused on identifying the onset of sepsis in intensive care patients, the vast majority of patients with sepsis come through the Emergency Department, which consequently is the first point of patient contact and the first point to identify patients with sepsis and to initiate appropriate therapy.

In this talk, I will outline the challenges associated with identifying septic patients in a busy, tertiary care Emergency Department and our work to address this challenge at triage and throughout the patient's stay in the Emergency Department. I will also outline model-based approaches to determine which patients might benefit from transitioning from fluid resuscitation to vasopressor therapy to support prevent transition to septic shock.

Biography Thomas Heldt studied physics at Johannes Gutenberg University, Germany, at Yale University, and at MIT. He received the PhD degree in Medical Physics from MIT's Division of Health Sciences and Technology and undertook postdoctoral training at MIT's Laboratory for Electromagnetic and Electronic Systems. Prior to joining the MIT faculty in 2013, Thomas was a Principal Research Scientist with MIT's Research Laboratory of Electronics. He currently holds the W.M. Keck Career Development Chair in Biomedical Engineering. He is a member of MIT's Institute for Medical Engineering and Science and on the faculty of the Department of Electrical Engineering and Computer Science.

Thomas's research interests focus on signal processing, mathematical modeling and model identification in support of real-time clinical decision making, monitoring of disease progression, and titration of therapy, primarily in neurocritical and neonatal critical care. In particular, Thomas is interested in developing a mechanistic understanding of physiologic systems, and in formulating appropriately chosen computational physiologic models for improved patient care. His research is conducted in close collaboration with clinicians from Boston-area hospitals, where he is integrally involved in designing and deploying high-quality data-acquisition systems and collecting clinical data.

A comparative study of motor imagery based BCI classifiers on EEG and iEEG Data
Continuous Parkinsonian Tremor Estimation Using Motion Data
Murtadha D. Hssayeni (Florida Atlantic University, USA); Joohi Jimenez-Shahed (Baylor College of Medicine, USA); Michelle A. Burack (University of Rochester Medical Center, USA); Behnaz Ghoraani (Florida Atlantic University, USA)
ITD Modeling Based on Anthropometrics and KEMAR Coefficients Using Deep Neural Networks
Saif Alotaibi (University of Colorado Colorado Springs, USA); Mark Wickert (University of Colorado at Colorado Springs, USA)

Signal Processing for Human Machine Learning Systems I

Room 211
Chairs: Pramod Varshney (Syracuse University, USA), Aditya Vempaty (Xio Research Inc., USA)

Distinguished Lecture:

Towards Man-Machine Symbiosis

A. H. Tewfik Department of Electrical and Computer Engineering, University of Texas Austin Numerous articles in the general press warn against a dark future in which evermore powerful machines will displace humans. Yet, empirical evidence establishes that properly designed human - machine systems outperform man and machine and have the potential of increasing human creativity and cognitive abilities. In this talk, I will provide an overview of cognitive biases in human decision-making, give examples of man-machine symbiosis and review our recent work in the area. In particular, I will focus on machine-assisted human decision making and the use of brain machine interfaces to improve speech recognition, recognize the audio source a person is listening to and whether the person is listening to her mother tongue. Time permitting, I will describe some of the work that we have been performing on reducing the amount of data needed to train support vector machines and deep neural networks.

Ahmed H Tewfik received his B.Sc. degree from Cairo University, Cairo Egypt, in 1982 and his M.Sc., E.E. and Sc.D. degrees from MIT, in 1984, 1985 and 1987 respectively. He is the Cockrell Family Regents Chair in Engineering and the Chairman of the Department of Electrical and Computer Engineering at the University of Texas Austin. He was the E. F. Johnson professor of Electronic Communications with the department of Electrical Engineering at the University of Minnesota until September 2010. Dr. Tewfik worked at Alphatech, Inc. and served as a consultant to several companies. From August 1997 to August 2001, he was the President and CEO of Cognicity, Inc., an entertainment marketing software tools publisher that he co-founded, on partial leave of absence from the University of Minnesota. His current research interests are in cognitive augmentation through man-machine symbiosis and mobile computing, low energy broadband communications, applied machine learning and brain computing interfaces. Prof. Tewfik is a Fellow of the IEEE. He was a Distinguished Lecturer of the IEEE Signal Processing Society in 1997 - 1999. He received the IEEE third Millennium award in 2000 and the IEEE Signal Processing Society Technical Achievement Award in 2017. He was elected to the positions of President-elect of the IEEE Signal Processing Society in 2017 and VP Technical Directions of that Society in 2009. He served as VP from 2010-2012 and on the board of governors of that Society from 2006 to 2008. He has given several plenary and keynote lectures at IEEE conferences.

On Amelioration Of Human Cognitive Biases In Binary Decision Making
Baocheng Geng and Pramod Varshney (Syracuse University, USA); Muralidhar Rangaswamy (AFRL, USA)
An Accurate Evaluation of MSD Log-likelihood and its Application in Human Action Recognition
Nuha Zamzami and Nizar Bouguila (Concordia University, Canada)
Mechanical Acoustic Signal Assisted Translational Model for Industrial Human-Machine Interaction
Zhiduo Ji, Cailian Chen, Jianping He and Xinping Guan (Shanghai Jiao Tong University, P.R. China)
A Novel Slip-Kalman Filter to Track the Progression of Reading Through Eye-Gaze Measurements
Stephen Bottos and Balakumar Balasingam (University of Windsor, Canada)
A Privacy Solution for Voice Enabled Devices Connected to the Internet
Mohammad Niknazar, Aditya Vempaty and Paul Haley (Xio Research Inc., USA)

Tuesday, November 12 12:00 - 13:30

Lunch & Poster Session

Young Professionals Networking Event

Room 102

Join early-career engineers and scientists as well as senior graduate students for an opportunity to network with peers and hear from Peyman Moeini, B. Eng., MASc, PMP, P.Eng. as he shares his career story and experience.

Tuesday, November 12 13:30 - 15:30

Deep Learning for Healthcare Engineering I

Room 201
Chair: Martin McKeown (University of British Columbia, Canada)

Keynote: Le Lu

An Attention Based Deep Neural Network for Automatic Lexical Stress Detection
LSTM Siamese Network for Parkinson's Disease Detection from Speech
Saurabhchand Bhati, Laureano Moro Velazquez and Jesus Villalba (Johns Hopkins University, USA); Najim Dehak (Hopkins University, unknown)
A Deep Convolutional-Recurrent Neural Network Architecture for Parkinson's Disease EEG
Soojin Lee (UBC, Canada); Ramy Hussein (Unversity of British Columbia, Canada); Martin McKeown (University of British Columbia, Canada)
Epileptic Seizure Prediction: A Multi-Scale Convolutional Neural Network Approach
Ramy Hussein (Unversity of British Columbia, Canada); Rabab Ward (University of British Columbia, Canada)

Graph Signal Processing II

Room 202
Chair: Gonzalo Mateos (Rochester University, USA)

Keynote Speaker: Wee Peng Tay - Generalized Graph Signal Processing

Machine Learning, Optimization and Security for Future Energy Delivery Systems II

Room 203
Chair: Christine Chen (University of British Columbia, Canada)

Invited Talks:

Berkay Turan, Ramtin Pedarsani, Mahnoosh Alizadeh

Title Online management of electric and autonomous mobility on demand vehicles

Abstract This talk considers the joint routing, battery charging, and pricing problem faced by a profit-maximizing transportation service provider that operates a fleet of autonomous electric vehicles. We will formulate the decision problem faced by the operator under both static and dynamic settings. Under the static setting, we first characterize the set of trip demands for rides, called the capacity region, for which there exists a routing and charging policy under which the underlying queueing network is stable. Furthermore, by setting prices, the transportation service provider aims to reshape the potential demand (which is not necessarily in the capacity region) so that the induced demand is in the capacity region while maximizing profits. The static policy allows us to portray the marginal prices for trips as functions of costs associated with providing them, such as operational and charging costs. Although the static policy provides important insights on optimal pricing and fleet management, its practical use in a real dynamic setting is limited. To accommodate for the time-varying nature of trip demands, renewable energy availability, and electricity prices and also to manage queues for rides, a dynamic policy is required. As such, we first characterize the dynamic setting as a Markov decision process and then apply a deep reinforcement learning algorithm in order to jointly optimize pricing, routing and charging decisions. The two case studies we have conducted in Manhattan and San Francisco demonstrate the performance of our dynamic policy in terms of stability and profit maximization.

Bio Mahnoosh Alizadeh is an assistant professor of Electrical and Computer Engineering at the University of California Santa Barbara. Dr. Alizadeh received the B.Sc. degree in Electrical Engineering from Sharif University of Technology in 2009 and the M.Sc. and Ph.D. degrees from the University of California Davis in 2013 and 2014 respectively, both in Electrical and Computer Engineering. From 2014 to 2016, she was a postdoctoral scholar at Stanford University. Her research is focused on the design of network control and optimization algorithms for societal-scale cyber-physical systems, with a particular focus on renewable energy integration in the power grid and electric transportation systems. She is a recipient of the NSF CAREER award.

Josh Taylor

Title Power system harmonics: identification and mitigation

Abstract Power system harmonics are mostly managed locally by the filters in converters. This is expensive and does not ensure that the aggregate level of harmonic distortion will be small. In this talk, we present Harmonic-Constrained Optimal Power Flow (HCOPF) for managing harmonics at the network level. HCOPF consists of conventional OPF and constraints on the total harmonic distortion in the network. We model the harmonics with the frequency coupling matrix (FCM), which maps fundamental frequency currents and voltages to the resulting harmonics. The FCM of a converter may not be known in practice. We give an algorithm to estimate FCMs from PMU and metering data. We also give a network reduction theorem based on Kron reduction that enables us to model unobservable portions of the network with virtual FCMs.

Bio Josh Taylor is an associate professor in the Department of Electrical and Computer Engineering at the University of Toronto. He received the B.S. from Carnegie Mellon University in 2006 and the Ph.D. from the Massachusetts Institute of Technology in 2011, all in Mechanical Engineering. From 2011 to 2012, he was a postdoctoral researcher at the University of California, Berkeley. His research focuses on control and optimization of power systems.

Melike Erol-Kantarci

Title Machine Learning for Resource Allocation and Scheduling in Device-to-Device (D2D) Microgrid Communications

Abstract

To make smart grid solutions economically feasible, there is interest in implementing mobile wireless communication technology, i.e. Fourth Generation Long Term Evolution (4G LTE) and in the coming years Fifth Generation New Radio (5G NR) to establish a network of communication links over a distribution system with minimal investment in physical infrastructure. Nevertheless, the latency of existing mobile networks is not guaranteed to be satisfactory for latency-critical smart grid services such as synchrophasor applications, and addressing this problem is an ongoing area of research. Device-to-Device (D2D) communication is a promising means to improve communication performance at a neighborhood area network scale by allowing direct data exchange between users. This talk will focus on machine learning techniques as applied to microgrid communications. In particular a multi-agent Q-learning-based resource allocation algorithm will be introduced that allows device-to-device (D2D) communication agents to generate the orthogonal transmission schedules outside the network coverage. This algorithm reduces packet drop rates (PDR) in distributed D2D communication networks to meet the quality-of-service requirements of the microgrid communications. The talk will present results over three archetypal smart grid applications, namely demand response, solar, and generation forecasting, and synchrophaspor communications.

Bio

Dr. Erol-Kantarci is an Associate Professor at the School of Electrical Engineering and Computer Science at uOttawa and the founding director of Networked Systems and Communications Research (NETCORE) laboratory. She is an influential researcher with more than 100 peer-reviewed publications, citations over 4000 and h-index of 32. Her pioneering works have received several awards and recognitions. She has received the 2017 IEEE Communication Society Best Tutorial Paper Award which is regarded as one of the society's most prestigious awards. She is the co-editor of two books: "Smart Grid: Networking, Data Management, and Business Models" and "Transportation and Power Grid in Smart Cities: Communication Networks and Services" published by CRC Press and Wiley, respectively. She has delivered seven tutorials and more than 30 invited talks around the globe. She is a director for IEEE MMTC Frontiers journal, an editor of the IEEE Communications Letters and IEEE Access. She has acted as the general chair or technical program chair for many international conferences and workshops. She is currently the chair of Green Smart Grid Communications special interest group of IEEE Technical Committee on Green Communications and Computing. She is also a senior member of the IEEE. Her main research interests are 5G and beyond wireless networks, smart grid, electric vehicles and Internet of Things.

Exploration of tensor decomposition applied to commercial building baseline estimation
David Hong (University of Pennsylvania, USA); Shunbo Lei, Johanna Mathieu and Laura Balzano (University of Michigan, USA)
A Data-driven Convex-optimization Method for Estimating Load Changes
Abdullah Al-Digs and Bo Chen (University of British Columbia, Canada); Sairaj Dhople (University of Minnesota, USA); Christine Chen (University of British Columbia, Canada)
Partial Discharge Classification in Power Electronics Applications using Machine Learning
Ebrahim Balouji (Chalmers University of Tech Company, Sweden); Thomas Hammarstroem (Chalmers University Of Technology, Sweden); Tomas McKelvey (Chalmers University of Technology, Sweden)

Machine Learning for Rare Event Detection in Healthcare II

Room 204
Chairs: Madison Cohen-McFarlane (Carleton University, Canada), Yasmina Souley Dosso (Carleton University, Canada)
Classifying Melanoma and Seborrheic Keratosis Automatically with Polarization Speckle Imaging
Wang Yuheng, Jiayue Cai, Daniel C. Louie, Harvey Lui, Tim Lee and Z. Jane Wang (University of British Columbia, Canada)
Combining TD-IDF with symptom features to differentiate between lymphoma and tuberculosis case reports
Moanda Pholo, Abdelbaset Abdelrahim Khalaf, Chunling Tu and Yskandar Hamam (Tshwane University of Technology, South Africa)
Serious Games and ML for Detecting MCI
Robert D McLeod, Marcia Friesen and Mahmood Aljumaili (University of Manitoba, Canada)
GMM-UBM based Person Verification using footfall signatures for Smart Home Applications
Sahil Anchal, Bodhibrata Mukhopadhyay and Manohar Parvatini (Indian Institute of Technology Delhi, India); Subrat Kar (Indian Institute of Technology, Delhi, India)
Identification of Essential Proteins Based on Centrality Methods Using Improved Collective Influence Algorithm
Houwang Zhang (China University of Geosciences (Wuhan), P.R. China); He Zhang (Beijing University of Posts and Telecommunications, P.R. China); Chong Wu (City University of Hong Kong, P.R. China)

Artificial Intelligence for Future Wireless Communication I

Room 211
Chair: Jienan Chen (University of Electronic Science and Technology of China, P.R. China)

Keynote: Warren Gross, McGill University

ML-Based Block Sparse Recovery for distributed MIMO Radars in Clutter Environments
Azra Abtahi (Sharif University of Technology & INSF, Iran); Mohammad Mahdi Kamjoo (Sharif University of Technology, Iran); Farokh Marvasti (Sharif University of Technology (SUT), Iran); Saeed Gazor (Queen's University, Canada)
Energy Efficiency of Full-Duplex Two-Way Channels
Wei Guo (UESTC, P.R. China); Chuan Huang (University of Electronic Science and Technology of China, P.R. China)
Blind Recognition of Channel Codes via Deep Learning
Boxiao Shen, Hongyi Wu and Chuan Huang (University of Electronic Science and Technology of China, P.R. China)
Constructing Index Codes with Coded Demands and Side Information through Matrix Completion
Lakshmi Narasimhan Theagarajan (Indian Institute of Technology, Palakkad, India)

Tuesday, November 12 15:30 - 16:00

Coffee Break & Poster Session

Tuesday, November 12 16:00 - 18:00

Deep Learning for Healthcare Engineering II

Room 201
Chair: Martin McKeown (University of British Columbia, Canada)
Infant Brain Development Prediction using Multi-Task Hypergraph Neural Network
Yan Wang (1520 6th Ave, P.R. China); Yue Gao and Qionghai Dai (Tsinghua University, P.R. China)
Deep learning methods for Image Segmentation Containing Translucent Overlapped Objects
Tayebeh Lotfi Mahyari and Richard Dansereau (Carleton University, Canada)
A Two-Tier Convolutional Neural Network for Combined Detection and Segmentation in Biological Imagery
Amir Koushyar Ziabari (Oak Ridge National Lab, USA); Abbas Shirinifard (St. Jude Children's Research Hospital, USA); Matthew Eicholtz (Florida Southern College, USA); David Solecki (St. Jude Children's Research Hospital, USA); Derek Rose (Oak Ridge National Lab, USA)
Pain Detection from Facial Videos Using Two-Stage Deep Learning
Zhanli Chen (University of Illinois at Chicago, USA); Menchetti Guglielmo (University of Illinois Chicago, USA & Politecnico di Milano, Italy); Rashid Ansari (University of Illinois at Chicago, USA); Diana Wilkie (University of Florida, USA); Enis Cetin (Bilkent University, Ankara, Turkey); Yasemin Yardimci (Middle East Technical University, Turkey)
Deep Learning Based Mass Detection in Mammograms
Zhenjie Cao, Zhicheng Yang, Yanbo Zhang and Ruei-Sung Lin (PingAn Tech, US Research Lab, USA); Shibin WU and Lingyun Huang (Ping An Technology, P.R. China); Mei Han (PingAn Tech, US Research Lab, USA); Jie Ma (Shenzhen People's Hospital, P.R. China)
COMPUTER ASSISTED READING OF CHEST RADIOGRAPHS
Z. Jane Wang (University of British Columbia, Canada)

GS: Array Signal Processing

Room 202
Chair: Dirk Slock (EURECOM, France)
Joint Angle and Delay Estimation (JADE) by Partial Relaxation
Ahmad Bazzi (CEVA, France); Dirk Slock (EURECOM, France)
Majorization-Minimization Algorithms for Analog Beamforming with Large-Scale Antenna Arrays
Aakash Arora (SnT, University of Luxembourg, Luxembourg); Christos G. Tsinos (University of Luxembourg, Luxembourg); Bhavani Shankar Mysore R (Interdisciplinary Centre for Security, Reliability and Trust & University of Luxembourg, Luxembourg); Symeon Chatzinotas (University of Luxembourg, Luxembourg); Björn Ottersten (University of Luxembourg, Luxembourg)
Coverage Analysis for Cellular-Connected UAVs with 3D Antenna Patterns
Xueyuan Wang and M. Cenk Gursoy (Syracuse University, USA)
Statistical Analysis of Antenna Array Systems with Perturbations in Phase, Gain and Element Positions
Mohammad Hossein Moghaddam, Sina Rezaei Aghdam and Thomas Eriksson (Chalmers University of Technology, Sweden)
Beam Alignment-Based mmWave Spectrum Sensing in Cognitive Vehicular Networks
He Zhang and Caili Guo (Beijing University of Posts and Telecommunications, P.R. China)
Robust Direction of Arrival Estimation in the Presence of Array Faults using Snapshot Diversity
Gary C.F. Lee (Massachusetts Institute of Technology, USA); Ankit Singh Rawat (Google Research, USA); Gregory Wornell (MIT, USA)

Machine Learning, Optimization and Security for Future Energy Delivery Systems III

Room 203
Chair: Joshua Taylor (University of Toronto, Canada)

Keynote Speaker: Vincent Wong Demand Response Programs for Workload Scheduling in Data Centers Abstract: The issue of energy efficiency poses a crucial challenge to today's data centers owing to the growing requirements for data storage and analysis services. Data centers often support a range of delay-tolerant workloads with adjustable execution time under a service level agreement. This potential for workload management has motivated utility companies to deploy demand response programs to encourage data centers toward shifting workload execution away from peak load periods. However, deployment of a demand response program for data centers is challenging as there is always uncertainty in the arrival rate of workload, the local renewable generation (e.g., photovoltaic (PV) panels, wind turbines), and electricity price (e.g., in a real-time pricing scheme). The uncertainties require a dynamic provisioning of servers to optimally schedule the workload. In this talk, we will discuss how data centers can benefit from participating in demand response programs. We will focus on data centers demand response in deregulated electricity markets, where a data center can enter a contract with one of several competing utility companies. The joint decision of utility company choices and workload scheduling will be captured as a many-to-one matching game with externalities and a distributed algorithm will be developed to determine a stable outcome of such a game. Finally, we will discuss how online convex optimization techniques can be applied to obtain a local optimal workload scheduling for data centers in a demand response program without any knowledge of the stochastic process that uncertain parameters follow.

Biography: Vincent Wong is a Professor in the Department of Electrical and Computer Engineering at the University of British Columbia, Vancouver, Canada. His research areas include protocol design, optimization, and resource management of communication networks, with applications to the Internet, wireless networks, smart grid, fog computing, and Internet of Things. Currently, he is an executive editorial committee member of the IEEE Transactions on Wireless Communications, an Area Editor of the IEEE Transactions on Communications, and an Associate Editor of the IEEE Transactions on Mobile Computing. Dr. Wong is a Fellow of the IEEE and an IEEE Communications Society Distinguished Lecturer (2019 - 2020).

Invited Talks:

Towards a Co-Simulation-Data Analytics Platform for IT/OT Converged Smart Grid Cybersecurity Analysis Marthe Kassouf, Scott Sanner, Amir Abiri, Yew Meng Khaw, Deepa Kundur

Pirathayini Srikantha Title: Hidden Convexities in Decentralized Microgrid Coordination

Abstract The evolving landscape of the electricity sector along with increasing environmental concerns necessitate modern power grids to be more efficient, sustainable and adaptive. Microgrids are typically composed of distributed energy sources which have great potential for enabling energy independence, sustainability and flexibility. However, practical difficulties that deter the widespread deployment of microgrids include the unpredictability of local generation sources (e.g. renewables) and the lack of inertia that is naturally present in systems containing bulk synchronous plants. In this paper, a near real-time microgrid coordination algorithm is proposed that allows actuating components to adapt to changing system conditions. Electrical dependencies and limits in microgrid systems are accounted for by constructing voltage/current balance relations in the dq0 frame and applying strategic decompositions to invoke the Schur's complement and S-procedure that allow for zero duality gap. The convergence, feasibility and scalability features of the proposed decentralized algorithm are highlighted via theoretical and comparative practical simulation studies.

Bio Dr. Pirathayini Srikantha received her B.A.Sc. degree in Systems Design Engineering from the University of Waterloo in 2009 and her M.A.Sc. degree in Electrical and Computer Engineering from the same institute in 2013. She obtained her Ph.D. degree from The Edward S. Rogers Sr. Department of Electrical and Computer Engineering at the University of Toronto in 2017. She is a certified Professional Engineer (P.Eng.) in Ontario. Her main research interests are in the areas of game theory, large-scale optimization and distributed control for enabling adaptive, sustainable and resilient power grid operations. Her work has been published in premier smart grid journal and conference venues. Her research efforts have received recognitions that include the best paper award (IEEE Smart Grid Communications) and runner-up best poster award (ACM Women in Computing). She has been an organizer for the ``Artificial Intelligence in Energy Systems" workshop at the IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids in 2018 and 2019. She is currently an Assistant Professor at Western University and will be joining the Electrical Engineering and Computer Science department at York University in the Fall of 2019 as an Assistant Professor.

Integrated Power and D2D Communications Simulator for Future Power Systems

Signal Processing for Human Machine Learning Systems II

Room 204
Chairs: Bhavya Kailkhura (Lawrence Livermore National Lab, USA), Pramod Varshney (Syracuse University, USA)

Keynote: Dennis Wei of IBM Research Title: One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques

Generative Counterfactual Introspection for Explainable Deep Learning
Shusen Liu (Lawrence Livermore National Laboratory, USA); Bhavya Kailkhura (Lawrence Livermore National Lab, USA); Donald Loveland and Yong Han (Lawrence Livermore National Laboratory, USA)
A Comparison of Boosted Deep Neural Networks for Voice Activity Detection
Harshit Krishnakumar (Indiana University Bloomington, USA); Donald S Williamson (Indiana University, USA)
Privacy Preserving Deep Learning with Distributed Encoders
Yitian Zhang and Hojjat Salehinejad (University of Toronto, Canada); Joseph Barfett (St. Michael's Hospital, Canada); Errol Colak and Shahrokh Valaee (University of Toronto, Canada)
Visually Assisted Time-Domain Speech Enhancement
Elham Ideli (Simon Fraser University & SingSoftNext, Canada); Bruce Sharpe (Singular Software Inc., Canada); Ivan V. Bajic and Rodney Vaughan (Simon Fraser University, Canada)
Identity Retaining and Redundancy Reducing GAN for Person Re-identification
Jiangbo Pei and Yinsong Xu (Beijing University of Posts and Telecommunications, P.R. China)

Artificial Intelligence for Future Wireless Communication II

Room 211
Chair: Jienan Chen (University of Electronic Science and Technology of China, P.R. China)
Deep Neural Hybrid Beamforming for Multi-User mmWave Massive MIMO System
Jiyun Tao, Jing Xing and Jienan Chen (University of Electronic Science and Technology of China, P.R. China); Chuan Zhang (National Mobile Communications Research Laboratory, Southeast University, P.R. China); Shengli Fu (University of North Texas, USA)
Reinforcement Learning-Driven QoS-Aware Intelligent Routing for Software-Defined Networks
Md Billal Hossain (The University of Akron, USA); Jin Wei (Purdue University, USA)
Occupancy Estimation Using WiFi Motion Detection Via Supervised Machine Learning Algorithms
Muhammad Azam (Smart Building Lab, BrainBox AI, Montreal, Quebec, Canada); Marion Blayo and Jean-Simon Venne (Smart Buildings Lab, BrainBox AI, Montreal, Quebec, Canada); Michel Allegue (Aerial, Canada)
Impact analysis of Reciprocity Mismatch in Relaying Systems
Rongjiang Nie (University of Science and Technology of China, P.R. China); Chen Li (University of Science And Technology of China, P.R. China)
Q-Learning Based Aerial Base Station Placement for Fairness Enhancement in Mobile Networks
Rozhina Ghanavi (University of Toronto, Canada); Maryam Sabbaghian (University of Tehran, Iran); Halim Yanikomeroglu (Carleton University, Canada)
A BP Neural Network Based Punctured Scheduling Scheme Within Mini-slots for Joint URLLC and eMBB Traffic
Qingqing Shang, Fangfang Liu, Chunyan Feng, Ruiyi Zhang and Shulun Zhao (Beijing University of Posts and Telecommunications, P.R. China)

Tuesday, November 12 19:00 - 22:00

Welcome Reception

Shaw Centre
Room: Trillium Ballroom

Wednesday, November 13

Wednesday, November 13 8:15 - 9:30

Plenary II

Wei Yu
Room: Plenary Room

Wednesday, November 13 9:30 - 18:00

Machine Learning for Wireless Communications, Networking, and Security II: Poster Session

Chairs: Silvija Kokalj-Filipović (Perspecta Labs, Inc, USA), George Stantchev (Naval Research Laboratory, USA)
Deep Learning-Based Detection of Fake Task Injection in Mobile Crowdsensing
Ankkita Sood (University of Ottawa, Canada); Murat Simsek (University of Ottawa & Istanbul Technical University, Canada); Yueqian Zhang and Burak Kantarci (University of Ottawa, Canada)
Power Delay Profile in Coordinated Distributed Networks: User-Centric v/s Disjoint Clustering
Hussein A. Ammar and Raviraj Adve (University of Toronto, Canada)
Deep Ensemble Learning: A Communications Receiver Over Wireless Fading Channels
Amer Al Baidhani and Howard Fan (University of Cincinnati, USA)
Multi-Discriminator Distributed Generative Model for Multi-Layer RF Metasurface Discovery
John Hodge (Virginia Tech, USA); Kumar Vijay Mishra (The University of Iowa, USA); Amir I Zaghloul (US Army Research Laboratory & Virginia Tech, USA)
Neural Network-based Equalizer by Utilizing Coding Gain in Advance
Chieh-Fang Teng, Han-Mo Ou and An-Yeu Wu (National Taiwan University, Taiwan)

Wednesday, November 13 9:30 - 10:00

Coffee Break & Poster Session

Wednesday, November 13 9:30 - 18:00

GS: Image and Video Processing: Poster Session

Chair: Yasin Yilmaz (University of South Florida, USA)
Scene Text Aware Image Retargeting
Diptiben Patel (Indian Institute of Technology Gandhinagar, India); Shanmuganathan Raman (Indian Institute of Technology, Gandhinagar, India)
TwinsAdvNet:Adversarial Learning for Semantic Segmentation
Yan Zhou, Dongli Wang and Bo Wang (Xiangtan University, P.R. China)
GOP Level Quality Dependency Based Frame Level Rate Control Algorithm
Meng Zhang, Wei Zhou, Zhemin Duan, Guanwen Zhang and Henglu Wei (Northwestern Polytechnical University, P.R. China)
A Novel Blurring based Method for Video Compression
Himanshu Kumar (IIT Jodhpur, India); Sumana Gupta (IIT, Kanpur - INDIA, India); Venkatesh K Subramanian (IIT Kanpur, India)
Image Alpha Matting via Residual Convolutional Grid Network
Huizhen Zhang, Yang Zhou, Lei Chen and Jiying Zhao (University of Ottawa, Canada)
Low-Complexity Adaptive Switched Prediction-based Lossless Compression of Time-lapse Hyperspectral Image Data
Tushar Shankar Shinde (Indian Institute of Technology Jodhpur, India); Anil Tiwari (IIT Jodhpur, India); Weiyao Lin (Shanghai Jiao Tong University, P.R. China)
Wide Separate 3D Convolution for Video Super Resolution
Xiafei Yu and Jiying Zhao (University of Ottawa, Canada)
A QoE-Based Alarm Model for Terminal Video Quality
Xiang Peng and Yiping Duan (Tsinghua University, P.R. China); Bingrui Geng (University of Tsinghua, P.R. China); Xiwen Liu, Xiaoming Tao and Ning Ge (Tsinghua University, P.R. China)
Data Driven QoE-QoS Association Modeling of Conversational Video
HongCheng Gu, Yu-ning Dong and TingTing Cao (Nanjing University of Posts and Telecommunications, P.R. China)
Efficient motion estimation and predictive coding methods for compression of spatio-temporal sequences
Tushar Shankar Shinde (Indian Institute of Technology Jodhpur, India)

GS: Classification and Learning: Poster Session

Chair: Pramod Varshney (Syracuse University, USA)
Component Splitting-based Approach for Multivariate Beta Mixture Models Learning
Narges Manouchehri, Hieu Nguyen and Nizar Bouguila (Concordia University, Canada)
Collaborative Machine Learning at the Wireless Edge with Blind Transmitters
Mohammad Mohammadi Amiri (Princeton University, USA); Tolga M. Duman (Bilkent University, Turkey); Deniz Gündüz (Imperial College London, United Kingdom (Great Britain))
An Unsupervised Sequence-to-Sequence Autoencoder based Human Action Scoring Model
Hiteshi Jain (Indian Institute of Technology Jodhpur, India); Gaurav Harit (IIT Rajasthan, India)
Learning Based Regularization for Spatial Multiplexing Cameras
Oğuzhan Fatih Kar (ASELSAN Research Center, Turkey); Alper Gungor (Aselsan Research Center & Bilkent University, Turkey); H. Emre Güven (ASELSAN Inc., Turkey)
Stochastic Principal Component Analysis Via Mean Absolute Projection Maximization
Mayur Dhanaraj and Panos P. Markopoulos (Rochester Institute of Technology, USA)
Dynamic Texture Recognition using a Hybrid Generative-Discriminative Approach with Hidden Markov Models and Support Vector Machines
Samr Samir Ali and Nizar Bouguila (Concordia University, Canada)
Copy and Move Forgery Detection Using SIFT and Local Color Dissimilarity Maps
Gaël Mahfoudi (University of Technology of Troyes, France); Frédéric Morain-Nicolier (Université de Reims Champagne Ardenne, France); Florent Retraint (UTT & University of Technology of Troyes, France); Marc Pic (SURYS, France)

Wednesday, November 13 10:00 - 12:00

Mathworks Workshop

Room 201

Title: Developing AI-based Smart Signal Processing Systems using MATLAB

The use of AI techniques on signals is growing in popularity across a variety of applications. In this practical session, we will explore how MATLAB can help accelerate the development and deployment of predictive models as applicable to timeseries data using transfer learning workflows. We will explore some specific tools to speed up AI workflow - From signal labeling to deployment on Embedded Systems such as NVIDIA Jetson. We will also look at newer techniques at the intersection of signal processing and deep learning that can be particularly useful when available data is low.

Presenter Bio: Kirthi K. Devleker is WW Medical Devices and Healthcare Industry Marketing Manager at MathWorks. Previously, he served as a product manager at MathWorks focusing on Machine Learning and Deep Learning applications for sensor data. Kirthi is responsible for overall medical devices and healthcare strategy and execution. Kirthi has been with MathWorks for 9 years; and has a master's in electrical engineering from San Jose State University, CA USA. Prior to joining MathWorks, Kirthi worked as a software evangelist developing sensor characterization tools in MATLAB.

Presenter Bio: Akhilesh Mishra is an Application Engineer for the Medical devices and Healthcare industry at MathWorks. He specializes in the signal/data processing, artificial intelligence and GPU computing workflows. He has been with MathWorks since 2016. Akhilesh holds a M.S. degree from University of Kansas where he was the signal processing lead in a group working on radar and sonar systems for sounding the ice sheets of Greenland and Antarctica to study global sea-level rise.

Signal Processing and Machine Learning for Social Good I

Room 202
Chairs: Theodora Chaspari (Texas A&M University, USA), Daphney-Stavroula Zois (University at Albany, SUNY, USA)

Keynote Speaker: Stefanie Blain-Moraes, McGill University

Signal processing for the detection of consciousness in unresponsive patients

Robust Bayesian and Maximum a Posteriori Beamforming for Hearing Assistive Devices
Poul Hoang (Aalborg University & Oticon A/S, Denmark); Zheng-Hua Tan (Aalborg University, Denmark); Jan de Haan (Oticon, Denmark); Thomas Lunner (Eriksholm Research Centre, Oticon A/S, Denmark); Jesper Jensen (Oticon A/S, Denmark)
Generation of References by Minimum Norm Projection Operators for Frequency Dependent Subtraction in Fetal Biological Signals
Neslihan Bisgin and James Wilson (University of Arkansas at Little Rock, USA); Hari Eswaran (University of Arkansas for Medical Sciences, USA)
Radar as a Security Measure - Real Time Neural Model based Human Detection and Behaviour Classification
Prakhar Kaushik (Johns Hopkins University, USA)

Machine Learning, Optimization and Security for Future Energy Delivery Systems IV

Room 203
Chair: Mads Almassalkhi (University of Vermont, USA)

Keynote Speaker: Johanna Mathieu, University of Michigan Learning about loads to improve power system operation and control

Dynamic Power Network State Estimation with Asynchronous Measurements
Guido Cavraro (National Renewable Energy Laboratory, USA); Emiliano Dall'Anese (University of Colorado Boulder, USA); Andrey Bernstein (National Renewable Energy Laboratory, USA)
Detection of False Data Injection Attack using Graph Signal Processing for the Power Grid
Raksha Ramakrishna and Anna Scaglione (Arizona State University, USA)
Power System Dynamic State Estimation Using Smooth Variable Structure Filter

Machine Learning for Wireless Communications, Networking, and Security I

Room 204
Chairs: Silvija Kokalj-Filipović (Perspecta Labs, Inc, USA), George Stantchev (Naval Research Laboratory, USA)

Keynote Speaker: Prof. Deniz Gunduz

Feature Learning for Enhanced Security in the Internet of Things
Enrico Mattei (Expedition Technology, Inc., USA)
Spectrum Activity Estimation by Partition-blind Block Partitioned Tensor Decomposition
Christopher Mueller-Smith (Rutgers University & SRI International, USA); Predrag Spasojević (Rutgers University, USA)
Age of Information Analysis for Dynamic Spectrum Sharing
Yao Zhao (ShanghaiTech University, P.R. China); Bo Zhou and Walid Saad (Virginia Tech, USA); Xiliang Luo (ShanghaiTech University, P.R. China)

Wednesday, November 13 12:00 - 13:00

Lunch

Wednesday, November 13 13:00 - 14:00

Plenary III

Robert W. Heath Jr.
Room: Plenary Room

Wednesday, November 13 14:20 - 16:00

Tensor Methods in Signal Processing and Machine Learning I

Room 201

Keynote Speaker: TBD

Tensor completion via global low-tubal-rankness and nonlocal self-similarity
Tian Lu, Xi-Le Zhao, Yu-Bang Zheng, Meng Ding and Xiao-Tong Li (University of Electronic Science and Technology of China, P.R. China)
Low-complexity Proximal Gauss-Newton Algorithm for Nonnegative Matrix Factorization
Kejun Huang (University of Florida, USA); Xiao Fu (Oregon State University, USA)
Robust Multi-Relational Learning with Absolute Projection Rescal
Dimitris G. Chachlakis (Rochester Institute of Technology, USA); Yorgos Tsitsikas (University of California, USA); Evangelos Papalexakis (University of California Riverside, USA); Panos P. Markopoulos (Rochester Institute of Technology, USA)

Signal Processing and Machine Learning for Social Good II

Room 202
Chairs: Yasin Yilmaz (University of South Florida, USA), Daphney-Stavroula Zois (University at Albany, SUNY, USA)
Estimating Public Speaking Anxiety from Speech Signals Using Unsupervised Transfer Learning
Butterfly Classification with Machine Learning Methodologies for an Android Application
Lili Zhu and Petros Spachos (University of Guelph, Canada)
Evaluation of Bias in Sensitive Personal Information Used to Train Financial Models
Scenario Planning for Sea Level Rise via Reinforcement Learning
Salman Shuvo, Yasin Yilmaz, Alan Bush and Mark Hafen (University of South Florida, USA)
VayuAnukulani: Adaptive Memory Networks for Air Pollution Forecasting
Divyam Madaan (KAIST, Korea); Radhika Dua (IIT Hyderabad, India); Prerana Mukherjee (IIIT Sri City); Brejesh Lall (Indian Institute of Technology Delhi, India)

GS: Classification and Learning I

Room 203
Chair: Wee Peng Tay (Nanyang Technological University, Singapore)
Orthogonal Projection in Linear Bandits
Qiyu Kang and Wee Peng Tay (Nanyang Technological University, Singapore)
Improved Subspace K-Means Performance via a Randomized Matrix Decomposition
Trevor C Vannoy, Jacob Senecal and Veronika Strnadová-Neeley (Montana State University, USA)
Bayesian Learning for Classification using a Uniform Dirichlet Prior
Paul Rademacher (Naval Research Laboratory, USA); Milos Doroslovacki (The George Washington University, USA)
New Filtering Approaches to Improve the Classification Capability of Resting-state fMRI Transfer Functions
Michael Smith (University of Calgary, Schulich School of Engineering, Canada); Ehsan Shahrabi Farahani-, Samiul Choudhury, Fiona Costello and Bradley Goodyear (University of Calgary, Canada)
New Results on Testing Against Independence with Rate-Limited Constraints
Sebastian Espinosa (Universidad de Chile, Chile); Jorge F Silva (University of Chile, Chile); Pablo Piantanida (CentraleSupélec-CNRS-Université Paris-Sud, France)

Advanced Bio-Signal Processing and Machine Learning for Assistive and Neuro-Rehabilitation Systems I

Room 204
  1. Keynote Speaker, 40 minutes;
  2. Q&A: 20 minutes
  3. Convergence Initiative Presentations: 60 Minutes

GS: Image and Video Processing II

Room 211
Chair: Jean-Francois Chamberland (Texas A&M University, USA)
Finite Inverted Dirichlet Mixture Optimal Pixel Predictor
Omar Graja and Nizar Bouguila (Concordia University, Canada)
Learning product codebooks using vector-quantized autoencoders for image retrieval
Hanwei Wu and Markus Flierl (KTH Royal Institute of Technology, Sweden)
An Improved Image Codec Based on the Steerable Discrete Cosine Transform
Geraldo Arruda Filho and Juliano B. Lima (Federal University of Pernambuco, Brazil)
FHDR: HDR Image Reconstruction from a Single LDR Image using Feedback Network
Zeeshan Khan, Mukul Khanna and Shanmuganathan Raman (Indian Institute of Technology, Gandhinagar, India)
Bring Light to the Night: Classifying Thermal Image via Convolutional Neural Network based on Visible Domain Transformation
Guoyu Lu (Rochester Institute of Technology, USA)

Wednesday, November 13 16:00 - 16:30

Coffee Break & Poster Session

Wednesday, November 13 16:30 - 18:30

Tensor Methods in Signal Processing and Machine Learning II

Room 201

Keynote Speaker: TBD

Matrix- and Tensor-Based RFI Detectors for Multi-Antenna Wireless Communications
Tilahun M. Getu (École de Technologie Supérieure (ETS), Canada); Wessam Ajib (Université du Québec à Montréal, Canada); Rene Jr. Landry (University of Quebec & Ecole de Technologie Supérieure, Canada); Georges Kaddoum (ETS Engineering School, University of Québec, Canada)
A Tensor-Based Spectrum Sensing Technique for MIMO Cognitive Radio Networks
Tilahun M. Getu (École de Technologie Supérieure (ETS), Canada); Wessam Ajib (Université du Québec à Montréal, Canada); Rene Jr. Landry (University of Quebec & Ecole de Technologie Supérieure, Canada); Georges Kaddoum (ETS Engineering School, University of Québec, Canada)
Tensor-based Blind fMRI Source Separation Without Gaussian Noise Assumption --- A Beta-Divergence Approach
Christos Chatzichristos and Michiel Vandecappelle (KU Leuven, Belgium); Eleftherios Kofidis (University of Piraeus & Computer Technology Institute (CTI), Greece); Sergios Theodoridis (University of Athens, Greece); Lieven De Lathauwer (KU Leuven Kulak, Belgium); Sabine Van Huffel (Katholieke Universiteit Leuven, Belgium)
Stochastic Tucker-Decomposed Recurrent Neural Networks for Forecasting
Zachariah J. L. Carmichael and Dhireesha Kudithipudi (Rochester Institute of Technology, USA)

GS: Hardware and Real-Time Implementations

Room 202
Chair: Sayed Ahmad Salehi (University of Kentucky, USA)
A Multitaper Model for Quiet Voltage in Relative Ionospheric Opacity Meters
François Marshall, David Thomson and Glen Takahara (Queen's University, Canada); Robyn Fiori (Geomagnetic Laboratory, NRCan, Canada)
Low-correlation Low-cost Stochastic Number Generators for Stochastic Computing
Sayed Ahmad Salehi (University of Kentucky, USA)
Real-time Compressive Video Reconstruction for Spatial Multiplexing Cameras
Oğuzhan Fatih Kar (ASELSAN Research Center, Turkey); Alper Gungor (Aselsan Research Center & Bilkent University, Turkey); H. Emre Güven (ASELSAN Inc., Turkey)
3-D MIMO-SAR Imaging Using Multi-Chip Cascaded Millimeter-Wave Sensors
Muhammet Yanik (The University of Texas at Dallas, USA); Dan Wang (Texas Instruments, Inc., USA); Murat Torlak (The University of Texas at Dallas, USA)
Computer-Generated Holography Using a Digital Signal Processor
Youchao Wang, Daoming Dong and Andrew C Kadis (University of Cambridge, United Kingdom (Great Britain)); Peter J. Christopher (Cambridge University, United Kingdom (Great Britain)); Timothy David Wilkinson (University of Cambridge, United Kingdom (Great Britain))
A Block-Floating-Point Arithmetic Based FPGA Accelerator for Convolutional Neural Networks
Heshan Zhang (Northwestern Polytechnical University, P.R. China); Zhenyu Liu (Tsinghua University, P.R. China); Guanwen Zhang and Jiwu Dai (Northwestern Polytechnical University, P.R. China); Xiaocong Lian (Tsinghua University, P.R. China); Wei Zhou (Northwestern Polytechnical University, P.R. China); Xiangyang Ji (Tsinghua University, P.R. China)

GS: Speech and Acoustic Signal Processing

Room 203
Chair: Balakumar Balasingam (University of Windsor, Canada)
Adaptation of an EMG-Based Speech Recognizer via Meta-Learning
Krsto Proroković and Michael Wand (IDSIA, Switzerland); Tanja Schultz (University of Bremen, Germany); Juergen Schmidhuber (IDSIA, Switzerland)
Virtual Phone Discovery for Speech Synthesis Without Text
Shekhar Nayak and Chintigari Shiva Kumar (IIT Hyderabad, India); Ramesh Gundluru (IIIT RK Valley, RGUKT-AP, India); Saurabhchand Bhati (Johns Hopkins University, USA); Sri Rama Murty Kodukula (Indian Institute of Technology Hyderabad, India)
Adaptive Feedback Active Noise Control (AFB-ANC) System Equipped with Online Adaptation and Convergence Monitoring of the Cancellation-Path Estimation (CPE) Filter
Muhammad Tahir Akhtar (Nazarbayev University, Kazakhstan)
Speaker Embedding Extraction with Virtual Phonetic Information
Sreekanth Sankala and Shaik Mohammad Rafi (RGUKT RK Valley, India); Sri Rama Murty Kodukula (Indian Institute of Technology Hyderabad, India); Saurabhchand Bhati (Johns Hopkins University, USA)
Bottom-Up Unsupervised Word Discovery via Acoustic Units
Saurabhchand Bhati, Chunxi Liu, Jesus Villalba, Jan Trmal and Sanjeev Khudanpur (Johns Hopkins University, USA); Najim Dehak (Hopkins University, unknown)
Multi-scale Generative Adversarial Networks for Speech Enhancement
Yihang Li (Beijing University of Posts and Telecommunications, P.R. China); Ting Jiang (Beijing University of Posts & Telecommunications, P.R. China); Shan Qin (Beijing University of Posts and Telecommunications, P.R. China)

Machine Learning for Wireless Communications, Networking, and Security III

Room 204
Chairs: Silvija Kokalj-Filipović (Perspecta Labs, Inc, USA), George Stantchev (Naval Research Laboratory, USA)

Keynote Speaker: Prof. Danijela Cabric

Communication without Interception: Defense against Modulation Detection
Muhammad Zaid Hameed (Imperial College London, United Kingdom (Great Britain)); András György (DeepMind, United Kingdom (Great Britain)); Deniz Gündüz (Imperial College London, United Kingdom (Great Britain))
Adversarial Examples in RF Deep Learning: Detection and Physical Robustness
Silvija Kokalj-Filipović (Perspecta Labs, Inc, USA); Robert D Miller and Garrett M Vanhoy (Perspecta Labs, USA)
Smart Spying via Deep Learning: Inferring Your Activities from Encrypted Wireless Traffic
Tao Hou (University of South Florida, USA); Tao Wang (New Mexico State University, USA); Zhuo Lu and Yao Liu (University of South Florida, USA)

GS: Image and Video Processing I

Room 211
Chair: Markus Flierl (KTH Royal Institute of Technology, Sweden)
Fixed-Point Accuracy Analysis of 2D FFT for the Creation of Computer Generated Holograms
Daoming Dong and Youchao Wang (University of Cambridge, United Kingdom (Great Britain)); Peter J. Christopher (Cambridge University, United Kingdom (Great Britain)); Andrew C Kadis and Timothy David Wilkinson (University of Cambridge, United Kingdom (Great Britain))
Super-Resolution for Imagery Enhancement Using Variational Quantum Eigensolver
Ystallonne C. S. Alves (Boxcat Inc., Canada & Federal University of Rio Grande do Norte, Brazil)
An embedding framework for video reconstruction using Gaussian mixture models
Vahid Khorasani Ghassab and Nizar Bouguila (Concordia University, Canada)
Hybrid IMU-Aided Approach for Optimized Visual Odometry
Ahmed G. Mahmoud (Carleton University, Canada); Mohamed Atia (Carleton University & Queen's University, Canada)
Single Image 3D Vehicle Pose Estimation for Augmented Reality
Yawen Lu (Rochester Institute of Tech, USA); Sophia Kourian and Carl Salvaggio (Rochester Institute of Technology, USA); Chenliang Xu (University of Rochester, USA); Guoyu Lu (Rochester Institute of Technology, USA)
Compressive Super-Pixel LiDAR for High-Framerate 3D Depth Imaging
Andreas Aßmann (Heriot-Watt University & STMicroelectronics R&D Ltd., United Kingdom (Great Britain)); Joao Mota (Heriot-Watt University, United Kingdom (Great Britain)); Brian Stewart (STMicroelectronics R&D Ltd., United Kingdom (Great Britain)); Andrew M Wallace (Heriot-Watt University, United Kingdom (Great Britain))

Wednesday, November 13 19:30 - 22:00

Conference Dinner

Room: Gatineau 206 & 208

Thursday, November 14

Thursday, November 14 8:15 - 9:30

Plenary IV

Min Wu
Room: Plenary Room

Thursday, November 14 9:30 - 10:00

Coffee Break

Thursday, November 14 10:00 - 12:00

GS: Compressed sensing, sparsity aware processing

Room 201
Chair: Chinmay Hegde (Iowa State University, USA)
On theoretical optimization of the sensing matrix for sparse-dictionary signal recovery
Jianchen Zhu and Shengjie Zhao (Tongji University, P.R. China); Xu Ma (Beijing Institute of Technology, P.R. China); Gonzalo Arce (University of Delaware, USA)
A Fast Iterative Method for Removing Sparse Noise from Sparse Signals
Seyedeh Sahar Sadrizadeh and Nematollah Zarmehi (Sharif University of Technology, Iran); Farokh Marvasti (Sharif University of Technology (SUT), Iran); Saeed Gazor (Queen's University, Canada)
A Compressibility Result for AMS Processes
Jorge F Silva (University of Chile, Chile)
Covariance Matrix Decomposition Using Cascade of Linear Tree Transformations
Navid Tafaghodi Khajavi (University of Hawaii at Manoa, USA); Anthony Kuh (Univ of Hawaii, Manoa, USA)
Signal Reconstruction from Modulo Observations
Viraj Shah and Chinmay Hegde (Iowa State University, USA)
A robust algorithm for multichannel EEG compressed sensing with mixed noise
Wei Tao, Chang Li and Juan Cheng (Hefei University of Technology, P.R. China)

Signal/Information Processing and AI for Finance and Business I

Room 202

Keynote: TBD

Evaluating goal-advice appropriateness for personal financial advice
Sue Ann Chen (IBM Research, Australia); Adam Makarucha (IBM Australia); Nebula Alam and Wanita Sherchan (IBM Research, Australia); Simon Harris (IBM Research); George Yiapanis (Deloitte, Australia); Christopher J. Butler (IBM Research, Australia)
A Divide-and-Conquer Framework for Attention-based Combination of Multiple Investment Strategies
Xiao Yang and Weiqing Liu (Microsoft Research, P.R. China); Lewen Wang (Peking University, P.R. China); Cheng Qu (University of Science and Technology of China, P.R. China); Jiang Bian (Microsoft Research, P.R. China)
A Study of Cross Sectional Stock Returns Using High-Dimensional SUR model and Many Firm Level Characteristics
Qingliang Fan and Yong Han (Xiamen University, P.R. China); Xiao-Ping (Steven) Zhang (Ryerson University, Canada)
Large-Scale Regularized Portfolio Selection via Convex Optimization
Ziping Zhao (The Hong Kong University of Science and Technology, Hong Kong); Daniel P Palomar (Hong Kong University of Science and Technology, Hong Kong)

Machine Learning for Wireless Communications, Networking, and Security IV

Room 203
Chairs: Silvija Kokalj-Filipović (Perspecta Labs, Inc, USA), George Stantchev (Naval Research Laboratory, USA)
Dynamic Network Slicing for Fog Radio Access Networks
Almuthanna Nassar and Yasin Yilmaz (University of South Florida, USA)
A Novel Quantization Method for Deep Learning-Based Massive MIMO CSI Feedback
Tong Chen (Southeast University, P.R. China); Jiajia Guo (Southeast University, P. R. China); Shi Jin (Southeast University, P.R. China); Chao-Kai Wen (National Sun Yat-sen University, Taiwan); Geoffrey Li (Georgia Tech, USA)
High-Dimensional Stochastic Gradient Quantization for Communication-Efficient Edge Learning
Yuqing Du (The University of Hong Kong, Hong Kong); Sheng Yang (CentraleSupélec, France); Kaibin Huang (The University of Hong Kong, Hong Kong)
Policy Based Synthesis: Data Generation and Augmentation Methods for RF Machine Learning
Silvija Kokalj-Filipović (Perspecta Labs, Inc, USA); Robert D Miller and Garrett M Vanhoy (Perspecta Labs, USA); Joshua Morman (Rutgers University, USA)
MAC ID Spoofing-Resistant Radio Fingerprinting
Machine Learning-Based Roadside Vehicular Traffic Localization via Opportunistic Wireless Sensing
Kyle McClintick (Worcester Polytechnic Institute, USA); Mark Page and Thanuka Wickramarathne (University of Massachusetts Lowell, USA); Alexander M. Wyglinski (Worcester Polytechnic Institute, USA)

GS: Cognitive communications and radar

Room 211
Exploiting Structural Information in Camera Aided Radar Parameter Estimation
Khurram Usman and Sai Annaluru (The University of Texas at Austin, USA); Amine Mezghani (Electrical and Computer Engineering & University of Manitoba, Canada); Robert Heath (The University of Texas at Austin, USA)
Extended Logarithmic Frequency Domain Rulers for Joint Radar-Communications
Alexander Byrley and Adly T. Fam (University at Buffalo, USA)
Estimating Correlation Coefficients for Quantum Radar and Noise Radar: A Simulation Study
David Luong (Defence Research and Development Canada & Carleton University, Canada); Sreeraman Rajan (Carleton University, Canada); Bhashyam Balaji (DRDC-Ottawa, Canada)
Integrated Camera and Radar Tracking using Multi-Model Cubature Kalman Filter
Venkata Pathuri Bhuvana (Silicon Austria Labs GmbH, Austria); Mario Huemer (Johannes Kepler University Linz, Austria)
Extended Target Frequency Response Estimation Using Infinite HMM in Cognitive Radars
ADMM for gridless DOD and DOA estimation in bistatic MIMO radar based on decoupled atomic norm minimization with one snapshot
Wen-gen Tang, Hong Jiang and Qi Zhang (Jilin University, P.R. China)

Thursday, November 14 12:00 - 13:30

Lunch

Thursday, November 14 13:30 - 15:30

Signal/Information Processing and AI for Finance and Business III: Poster Session

Conservative or Aggressive? Confidence-Aware Dynamic Portfolio Construction
Lewen Wang (Peking University, P.R. China); Weiqing Liu, Jiang Bian and Xiao Yang (Microsoft Research, P.R. China)
Incentivizing Crowdsourced Workers via Truth Detection
Chao Huang (The Chinese University of Hong Kong, Hong Kong); Haoran Yu (Northwestern University, USA); Jianwei Huang (The Chinese University of Hong Kong, Hong Kong); Randall A Berry (Northwestern University, USA)
Generative-Discriminative Crop Type Identification using Satellite Images
Nan Qiao, Bo Gong, Ruei-Sung Lin and Yi Zhao (PingAn Tech, US Research Lab); Mei Han (PingAn Tech, US Research Lab, USA); Zhongxiang Wu (PingAn Tech, US Research Lab)
Double-Selection Based High-dimensional Factor Model with Application in Asset Pricing
Qingliang Fan and Fan Hu (Xiamen University, P.R. China); Xiao-Ping (Steven) Zhang (Ryerson University, Canada)

Signal and Information Processing for Person-centered and Citizen-centered Smart Living I

Room 201

Keynote: Prabhakaran Balakrishnan, Professor, University of Texas at Dallas Title: Personalized Care and Intervention: Challenges and Opportunities

Framework for promoting social interaction and physical activity in elderly people using gamification and fuzzy logic strategy
Juana Isabel Méndez and Pedro Ponce (Tecnologico de Monterrey, Mexico); Alan Meier (University of California, Davis); Therese Peffer (University of California, Berkeley, USA); Omar Mata and Arturo Molina (Tecnologico de Monterrey, Mexico)
MisophoniAPP: Person-Centric Gamified Therapy for Smarter Treatment of Misophonia
Providing navigation assistance through ForceHand: a wearable force-feedback glove
Swagata Das and Yuichi Kurita (Hiroshima University, Japan)
Using Multimodal Data for Automated Fidelity Evaluation in Pivotal Response Treatment Videos

Signal/Information Processing and AI for Finance and Business II

Room 202

Keynote: TBD

Advanced Bio-Signal Processing and Machine Learning for Assistive and Neuro-Rehabilitation Systems II

Room 203
Semi-autonomous Robot-assisted Cooperative Therapy Exercises for a Therapist's Interaction with a Patient
Carlos Martínez and Jason Fong (University of Alberta, Canada); Seyed Farokh Atashzar (Imperial College London, United Kingdom (Great Britain)); Mahdi Tavakoli (University of Alberta, Canada)
Linear Discriminant Analysis with Bayesian Risk Parameters for Myoelectric Control
Evan D Campbell (University of New Brunswick & Institute of Biomedical Engineering, Canada); Angkoon Phinyomark and Erik Scheme (University of New Brunswick, Canada)
Training of Deep Bidirectional RNNs for Hand Motion Filtering via Multimodal Data Fusion
Soroosh Shahtalebi (Concordia University, Canada); S. Farokh Atashzar (New York University, USA); Rajni Patel (Canadian Surgical Technologies & Advanced Robotics, Canada); Arash Mohammadi (Concordia University, Canada)
sEMG-Based Hand Gesture Recognition via Dilated Convolutional Neural Networks
Elahe Rahimian and Soheil Zabihi (Concordia University, Canada); S. Farokh Atashzar (New York University, USA); Amir Asif and Arash Mohammadi (Concordia University, Canada)
Speech Recognition Driven Assistive Framework for Remote Patient Monitoring
Marc Jayson Baucas and Petros Spachos (University of Guelph, Canada)
A Multivariate Approach for Denoising of T2 Relaxation Decay Curves in Myelin Water Fraction Imaging
Tobias R Baumeister (The University of British Columbia, Canada); Z. Jane Wang and Martin McKeown (University of British Columbia, Canada)

GS: MIMO Systems

Room 211
Chair: M. Cenk Gursoy (Syracuse University, USA)
PCA-Aided Precoding for Correlated MIMO Broadcast Channels
Mouncef Benmimoune (Universite du Quebec a Trois-Rivieres, Canada); Sofiane Hachemi (Université de Québec à Trois Rivières, Canada); Daniel Massicotte (Universite du Quebec a Trois-Rivieres, Canada); Messaoud Ahmed Ouameur (Université du Québec à Trois-Rivières, Canada)
A Worst-Case Performance Optimization Based Design Approach to Robust Symbol-Level Precoding for Downlink MU-MIMO
Alireza Haqiqatnejad (University of Luxembourg & Interdisciplinary Centre for Security, Reliability and Trust (SnT), Luxembourg); Shahram ShahbazPanahi (University of Ontario Institute of Technology, Canada); Björn Ottersten (University of Luxembourg, Luxembourg)
Single RF Chain Hybrid Analog/Digital Beamforming for mmWave Massive-MIMO
Alireza Morsali, Sara Norouzi and Benoit Champagne (McGill University, Canada)
Distributed Sparse Activity Detection in Cell-Free Massive MIMO Systems
Mangqing Guo and M. Cenk Gursoy (Syracuse University, USA)
Multi-Mode Generalized Space-Time Index Modulation: A High-Rate Index Modulation Scheme for MIMO-ISI Channels
Lakshmi Narasimhan Theagarajan (Indian Institute of Technology, Palakkad, India)
Energy- and Spectral-Efficiency Tradeoff in Beam Domain Massive MIMO Downlink with Statistical CSIT
Jiayuan Xiong and Li You (Southeast University, P.R. China); Alessio Zappone (University of Cassino and Southern Lazio, Italy); Wenjin Wang and Xiqi Gao (Southeast University, P.R. China)

Thursday, November 14 15:30 - 16:00

Coffee Break

Thursday, November 14 16:00 - 18:00

Signal and Information Processing for Person-centered and Citizen-centered Smart Living II

Room 201
Chair: Troy L McDaniel (Arizona State University, USA)

Keynote: "Automatic Food Intake Recognition for Smarter Eating", Shervin Shirmohammadi and Alaa Eddin Alchalabi, University of Ottawa, Canada

Bridging Connected Vehicles with Artificial Intelligence for Smart First Responder Services
Nima Taherifard (University of Ottawa, Canada); Murat Simsek (University of Ottawa & Istanbul Technical University, Canada); Burak Kantarci (University of Ottawa, Canada)
Robust Minimum Variance Distortionless Response Beamformer based on Target Activity Detection in Binaural Hearing Aid Applications
Hala As'ad and Martin Bouchard (University of Ottawa, Canada); Homayoun Kamkar Parsi (Sivantos Group, Germany)
The Blind Date: Improving the Accessibility of Mobile Dating Platforms for Individuals with Visual Impairments
Meredith K Moore (Arizona State University & Center for Cognitive Ubiquitous Computing, USA); Corey Heath, Troy L McDaniel and Sethuraman Panchanathan (Arizona State University, USA)

Signal/Information Processing and AI for Finance and Business IV

Room 202

Academia/Industry Mixer Panel: Challenges in Artificial Intelligence, Big data and Signal Processing in Finance and Business

Advanced Bio-Signal Processing and Machine Learning for Assistive and Neuro-Rehabilitation Systems III

Room 203
The Onset of Parietal Alpha- and Beta- Band Oscillations Caused by an Initial Video Delay
Yifeng Liu, Xiaoming Tao and Yiping Duan (Tsinghua University, P.R. China)
Adaptive Subject-specific Bayesian Spectral Filtering for Single Trial EEG Classification
Identifying High-resolution Spatiotemporal Components Contributing to the Fast Spiking Response Dynamics of Visual Neurons
Yasin Zamani and Neda Nategh (University of Utah, USA)
Recovery of Event Related Potential Signals using Compressive Sensing and Kronecker Technique
Seyed Alireza Khoshnevis (University of South Florida, USA); Seyed Ghorshi (The University of Texas at Tyler, USA)
Study on Novel Designs with Reduced Fatigue for Steady State Motion Visual Evoked Potentials
Extracting Audio-Visual Features for Emotion Recognition through Active Feature Selection
Fasih Haider, Senja Pollak, Pierre Albert and Saturnino Luz (University of Edinburgh, United Kingdom (Great Britain))

GS: Machine Learning Networks

Room 204
Chair: Alireza Morsali (McGill University, Canada)
Efficient Multi-Domain Dictionary Learning with GANs
Cho-Ying Wu (University of Southern California, USA); Ulrich Neumann (USC, USA)
A Domain Knowledge -Enabled Hybrid Semi-Supervision Learning Method
Yifu Wu and Jin Wei (Purdue University, USA); Rigoberto Roche' (NASA Glenn Research Center, USA)
On Convex Stochastic Variance Reduced Gradient for Adversarial Machine Learning
Saikiran Bulusu, Qunwei Li and Pramod Varshney (Syracuse University, USA)
Ising Dropout with Node Grouping for Training and Compression of Deep Neural Networks
Hojjat Salehinejad, Zijian Wang and Shahrokh Valaee (University of Toronto, Canada)
Video Manipulation Detection via Recurrent Residual Feature Learning Networks
Matthew J Howard and Alexander Williamson (University of California, Santa Cruz, USA); Narges Norouzi (University of California at Sant Cruz, USA)
A Geometric Convolutional Neural Network for 3D Object Detection
Yawen Lu (Rochester Institute of Tech, USA); Qianyu Guo (Rochester Institute of Technology, USA & Shanxi University, P.R. China); Guoyu Lu (Rochester Institute of Technology, USA)

GS: Signal Processing for Communications

Room 211
Chair: Timothy N. Davidson (McMaster University, Canada)
A Power Control Game with Uncertainty On the Type of the Jammer
Andrey Garnaev (WINLAB, Rutgers University, USA); Athina Petropulu (Rutgers, The State University of New Jersey, USA); Wade Trappe (WINLAB, Rutgers University, USA); H. Vincent Poor (Princeton University, USA)
Application of FBMC to DVB-T2: a Comparison vs Classical OFDM Transmissions
Honfoga Anne-Carole (University of Mons, Belgium); Tu T. Nguyen (AIPT, Aston University, United Kingdom (Great Britain)); Michel Dossou (University of Abomey-calavi, Benin); Véronique Moeyaert (Université de Mons (UMONS) & Faculté Polytechnique, Belgium)
Optimized Polarization Filtering Based Self-Interference Cancellation Scheme for Full-Duplex Communication
Fengqi Bai, Fangfang Liu and Chunyan Feng (Beijing University of Posts and Telecommunications, P.R. China)
Ergodic Capacity Analysis for Full-Duplex Integrated Access and Backhaul System
Xiaoqian Zhang, Fangfang Liu and Hailun Xia (Beijing University of Posts and Telecommunications, P.R. China)
Ambient OFDM Pilot-Aided Delay-Shift Keying and Its Efficient Detection for Ultra Low-Power Communications
Ryuhei Takahashi and Koji Ishibashi (The University of Electro-Communications, Japan)
Joint Subchannel and Power Allocation for Cognitive NOMA Systems with Imperfect CSI
Yongjun Xu (Chongqing University of Posts and Telecommunications, P.R. China); Yang Yang (Chongqing University of Posts and Telecommunications & School of Communication and Information Engineering, P.R. China); Guoquan Li and Zhengqiang Wang (Chongqing University of Posts and Telecommunications, P.R. China)