3rd IEEE Big Data Governance and Metadata Management Workshop (BDGMM 2018)

 

big data header

Workshop Theme:
Big Data Bioscience Data Mashup and Analytics

Seattle, Washington, USA

December 10 - 11, 2018

In conjunction with
IEEE Big Data 2018

Sponsored by
IEEE Brain Initiative
IEEE Big Data Technical Community
IEEE Standards Association (IEEE-SA)

  Call for Hackathon Participation with Cash Awards!  
1st Place: $1500, 2nd Place: $1000, 3rd Place: $500

Registration: FREE for full-time IEEE Big Data Conference Registrants.
Click here to register for the IEEE Big Data Conference.
Complete the form to register for the BDGMM workshop and hackathon.

Pre-event Webinar on Hackathon Track #2:
Brain Data Bank on Video Gaming Enhances Cognitive Skills
November 8th, 3pm Eastern Time
Join us to ask questions about the upcoming brain hackathon in Seattle

 

Motivations

This workshop is aligned with the effort from the IEEE Big Data Technical Community (BDTC) on Standardization (see http://bigdata.ieee.org/). The BDTC standards research group is studying on where there is a need and opportunity for developing IEEE Standards for Big Data Metadata, its management, and governance. BDGMM 2018 follows the successful BDMM workshop held at IEEE BigData 2017 (http://cci.drexel.edu/bigdata/bigdata2017).

Big Data is a collection of data so large, so complex, so distributed, and growing so fast (or 5Vs- volume, variety, velocity, veracity, and value). It has been known for unlocking new sources of economic values, providing fresh insights into sciences, and assisting on policy making. However, Big Data is not practically consumable until it can be aggregated and integrated into a manner that a computer system can process. For instance, in the Internet of Things (IoT) environment, there is a great deal of variation in the hardware, software, coding methods, terminologies and nomenclatures used among the data generation systems. Given the variety of data locations, formats, structures and access policies, data aggregation has been extremely complex and difficult. More specifically, a health researcher was interested in finding answers to a series of questions, such as “How is the gene ‘myosin light chain 2’ associated with the chamber type hypertrophic cardiomyopathy? What is the similarity to a subset of the genes’ features? What are the potential connections among pairs of genes”? To answer these questions, one may retrieve information from databases he knows, such as the NCBI Gene database or PubMed database. In the Big Data era, it is highly likely that there are other repositories also storing the relevant data. Thus, we are wondering

  • Is there an approach to manage such big data, so that a single search engine available to obtain all relevant information drawn from a variety of data sources and to act as a whole?
  • How do we know if the data provided is related to the information contained in our study?
To achieve this objective, we need a mechanism to help us describe a digital source so well that allows it to be understood by both human and machine. Metadata is "data about data". It is descriptive information about a particular dataset, object or resource, including how it is formatted, and when and by whom it is collected. With those information, the finding of and the working with particular instances of Big Data would become easier. Besides, the Big Data must be managed effectively. This has partially manifested in data models a.k.a. “NoSQL”. The goal of this multidisciplinary workshop is to gather both researchers and practitioners to discuss methodological, technical and standard aspects for Big Data management. Papers describing original research on both theoretical and practical aspects of metadata for Big Data management are solicited.

 

Topics include, but are not limited to:

  • Metadata standard(s) development for Big Data management
  • Methodologies, architecture and tools for metadata annotation, discovery, and interpretation
  • Case study on metadata standard development and application
  • Metadata interoperability (crosswalk)
  • Metadata and Data Privacy
  • Metadata for Semantic Webs
  • Human Factors on Metadata
  • Innovations in Big Data management
  • Opportunities in standardizing Big Data management
  • Digital object architectures and infrastructures for Big Data management
  • Best practices and standard based persistent identifiers, data types registry structures and representations for Big Data management
  • Query languages and ontology in Big Data
  • NoSQL databases and Schema-less data modeling
  • Multimodal resource and workload management
  • Availability, reliability and Fault tolerance
  • Frameworks for parallel and distributed information retrieval
  • Domain standardization for Big Data management
  • Big Data governance for data integrity, quality, provenance, retention, asset management, and business intelligence
In addition to the accepted papers, the workshop intends to have an industry focus through a keynote speaker and hackathon challenges. The hackathon session will explore interoperable data infrastructure for Big Data Governance and Metadata Management that is scalable and can enable the Findability, Accessibility, Interoperability, and Reusability between heterogeneous datasets from various domains without worrying about data source and structure.

 

Paper submission instructions 

This workshop will only accept for review original papers that have not been previously published. Papers should be formatted based on the IEEE Transactions journals and conferences style; maximum allowed camera-ready paper length is ten (10) pages. Submissions must use the followiing formatting instructions:
8.5" x 11" x 2 (DOC, PDF, LaTex Formatting Macros)

Please use this submission site to submit your paper(s).

Accepted papers will be published in the IEEE BigData2018 proceedings (EI indexed). For further information please see IEEE BigData2018 @ http://cci.drexel.edu/bigdata/bigdata2018.

Review procedure 

All submitted papers will be reviewed by 3 international program committees.

 

Hackathon: 24 hours on Data Mashup (Varieties Problem) Big Data Analytics  

Governance and metadata management poses unique challenges with regard to the Big Data paradigm shift. It is critical to develop interoperable data infrastructure for Big Data Governance and Metadata Management that is scalable and can enable the Findability, Accessibility, Interoperability, and Reusability between heterogeneous datasets from various domains without worrying about data source and structure.

Hackathon Track#1: Personalized Medicine for Drug Targeting in Prostate Cancer Patients
Submitted and Subject Matter Expert by Dr. Elizabeth Chang
Research Fellow, Department of Radiation Oncology, University of Maryland Marlene and Stewart Greenebaum Comprehensive Cancer Center, USA

Problem Statement

Personalized medicine is the act of tailoring chemotherapy or drugs based on a patient’s specific set of DNA or genes. When a person is diagnosed with cancer, a variety of tests are performed (blood, DNA, urine, or tissue analysis), giving physicians a snapshot into that patient's unique set of DNA. This information allows for "smart" prescribing of medications that complement a patient's signature genetic background and achieve therapeutic response.

      

Problem: how do we find these biomarkers?

One approach: NCI’s Genomic Data Commons data portal is a huge data repository of over 32,000 patient cases, and includes clinical data, treatment data, or biopsy results, and over 22,000 genes, as well as a whole host of other information. This allows accessibility to other researchers who want to uncover new biomarkers, find correlations between genes and survival, or look into whatever topic they are interested in.

The President's Council of Advisors on Science and Technology (PCAST) believes that the convergence of scientific and clinical opportunity and public health need represented by personalized medicine warrants significant public and private sector action to facilitate the development and introduction into clinical practice of this promising class of new medical products… Based on these deliberations, PCAST determined that specific policy actions in the realm of genomics-based molecular diagnostics had the greatest potential to accelerate progress in personalized medicine. PCAST on Priorities for Personalized Medicine, September 2008

Tutorial and Hands-on (No biooscience background is needed but willing to work within a team is preferred)

Subject Matter Expert: Provide Genomic Data Commons data portal overview and hands-on excerise on given datasets

  • Dr. Elizabeth Chang, Research Fellow, Department of Radiation Oncology, University of Maryland Marlene and Stewart Greenebaum Comprehensive Cancer Center, USA

Challenges
Note: Not all data values may be present, and some patients may have multiple records
(Click here for step-by-step instructions using Xena Browser to check questions 2 and 3)

Develop data mashup scheme based on use cases to cross reference different clinical and genomic datasets and apply statistical analysis, visualization, and machine learning tools to statistically analyze and develop predictive models for survival data, uncover new molecular biomarkers, and find correlations between genes and cancer risk. Think outside the box and come up with innovative ideas that bring more value out of the data, or choose one or more of the following to:

  1. Find how many patient cases are “Primary Tumor” samples from Dataset 2 using Column A “sample_type”.
  2. Graph overall survival (OS) by Gleason score from Dataset 2 (using Kaplan Meier plot, see Computing Environment for reference)
  3. Graph overall survival by target gene TP53 when Gleason score is 6
  4. Graph overall survival by target gene TP53 when Gleason score is categorized into 3 groups (6-7, 8, and 9-10)
  5. Repeat #4 using your own Gleason score categories which produces the best P-value (example: P-value <0.05)
[Ultimate goal: Repeat #5, this time using all the genes in Dataset 1, and find the ones which produce a P-value <0.05]

Computing Environment 

Datasets 

Two public available datasets shall be used:
  1. Dataset 1: gene expression RNAseq – IlluminaHiSeq
    https://tcga.xenahubs.net/download/TCGA.PRAD.sampleMap/HiSeqV2.gz (570KB)

    The gene expression profile was measured experimentally using the Illumina HiSeq 2000 RNA Sequencing platform by the University of North Carolina TCGA genome characterization center. Level 3 data was downloaded from TCGA data coordination center. This dataset shows the gene-level transcription estimates, as in log2(x+1) transformed RSEM normalized count. Genes are mapped onto the human genome coordinates using UCSC Xena HUGO probeMap.

  2. Dataset 2: phenotype – Phenotypes
    https://tcga.xenahubs.net/download/TCGA.PRAD.sampleMap/PRAD_clinicalMatrix.gz (71MB)
    This dataset provides clinical data including overall survival (OS), treatment regimens, cancer staging (Gleason scores), diagnostic results, histology, pathologic staging, tumor characteristics, and much more.

Evaluation Criteria 

Technical Approach (40 pts)
- Data mashup (20)
- Big Data analytics (20)

Novelty (40 pts)
- Creativity (20)
- Efficiency (20)

Results (20 pts)
- Output content (10)
- Output format (10)

Hackathon Track#2: Brain Data Bank on Video Gaming Enhances Cognitive Skills
Sponsor by IEEE Brain Initiative

Submitted and Subject Matter Expert by Dr. David Ziegler
Director of Technology Program; Multimodal Biosensing – Neuroscape University of California San Francisco

[Reference: Nature. 2013 Sep 5; 501(7465): 97–101, doi: 10.1038/nature12486]

Problem Statement

Cognitive control is defined by a set of neural processes that allow us to interact with our complex environment in a goal-directed manner. Humans regularly challenge these control processes when attempting to simultaneously accomplish multiple goals (multitasking), generating interference as the result of fundamental information processing limitations. It is clear that multitasking behaviour has become ubiquitous in today’s technologically dense world3, and substantial evidence has accrued regarding multitasking difficulties and cognitive control deficits in our ageing population4.

Here we show that multitasking performance, as assessed with a custom-designed three-dimensional video game (NeuroRacer), exhibits a linear age-related decline from 20 to 79 years of age. By playing an adaptive version of NeuroRacer in multitasking training mode, older adults (60 to 85 years old) reduced multitasking costs compared to both an active control group and a no-contact control group, attaining levels beyond those achieved by untrained 20-year-old participants, with gains persisting for 6 months.

These findings highlight the robust plasticity of the prefrontal cognitive control system in the ageing brain, and provide the first evidence, to our knowledge, of how a custom-designed videogame can be used to assess cognitive abilities across the lifespan, evaluate underlying neural mechanisms, and serve as a powerful tool for cognitive enhancement.

      

Tutorial and Hands-on (No neuroscience background is needed but willing to work within a team is preferred)

Subject Matter Experts: Provide neuroscience overview and hands-on excerise on given datasets

  • Dr. David Ziegler (Tutorial), Director of Technology Program, Multimodal Biosensing, UCSF, USA
  • Dr. Seth Elkin-Frankston (Hands-on), Chief Scientist, Metrodora, USA

Challenges

Develop data mashup scheme based on use cases to cross reference different datasets and apply statistical analysis, visualization, and machine learning tools to statistically analyze and develop predictive models for what changed between “shoot only or single tasking” and “drive & shoot or multi-tasking” from the EEG (electroencephalography) signals.

For this hackathon track, please answer either the Beginner Challenges Questions or the Advanced Challenge Questions below:

Beginner Challenge Questions

  1. Understanding of the NeuroRacer dataset
    1. Briefly describe the experiment. What did participants do when they were being tested? Why would the same condition (trial) be repeated several times during an experimental session?
  2. Clarity and relevance of analysis - state clearly the rationale
    1. If the goal of the experiment was to improve people's behavioral performance would we expect also expect to see changes in patterns of brain activity? Why or why not?
  3. Methodology - clear explanation of process & controlling factors
    1. Can you visualize an Event Related Response (ERP)? What if you average ERPs by condition? Look for differences in brain signals between individuals, groups, and time point.
  4. Interpretation of brain signal data - creative and out-of-box thinking with limitations identified
    1. What are differences in brain signal data for different frequencies (e.g., alpha, beta, gamma, theta)?
    2. Are there differences between conditions? What about at different electrode sites?
Advanced Challenge Questions

Given the behavioral finding that NeuroRacer training led to persistent benefits SIX YEARS later, what neural signature shows a similar pattern of effect(s)?

  1. Would Deep Learning modeling help with better data analysis? and how?
  2. What neural signature at the Six Year Mark show an age-related difference between young and older adults (regardless of training group).
  3. How do measures of brain/network activity relate to NeuroRacer performance?
  4. Is there an alternative neural signature (other than ERSP or long-range theta coherence) that shows the same pattern of effects as the observed behaviour following training and at the 6 Year mark?
Computing Environment

  • Languages: MATLAB, Python, C++.
  • EEG Analysis & Visualization tools (all three are free and have excellent tutorials):
    • FieldTrip
      • MATLAB toolbox for M/EEG analysis
      • Largely command-line functionality
      • Particular emphasis on analyses in the time-frequency domain
    • EEGLAB
      • Interactive MATLAB toolbox for processing M/EEG data
      • GUI and command line options
      • Particular emphasis on ICA methods for decomposing data and extracting meaningful components
    • MNE
      • Open-source Python software for visualizing and analyzing M/EEG data
      • Particularly good for source-localization analysis
    • Cartool
Datasets

The competition datasets are hosted by the IEEE DataPort. To access IEEE DataPort, you need to have an IEEE account. You do not need to be an IEEE member to create an IEEE account, and you can use your own email address to create an account and password. Click here to sign up for an IEEE account.

Once you are in the competition module, scroll down and complete the “Apply for Access” form to request access to the datasets.

Hackathon Team, Computing Environment, and Implementation White Paper

All participants must be registered via the IEEE Big Data 2018 Registration and attend physically. You may register as a team (up to four per team) or an individual (we will place you on a team). Each participant brings his/her own laptop with all the necessary computing tools. No remote computing resources are allowed. All implementation must be based on the original work. Participating teams are encouraged to submit implementation approach as a white paper which will be published as part of the IEEE Big Data Governance and Metadata Management publication three months after the hackathon event.

Evaluation Criteria 

Entries will be judged in 6 categories:

  1. Understanding of the NeuroRacer dataset
  2. Clarity and relevance of analysis - state clearly the rationale
  3. Methodology - clear explanation of process & controlling factors
  4. Interpretation of brain signal data - creative and out-of-box thinking with limitations identified
  5. Significance of findings and recommendations - with reasonable, original and hopeful guidelines
  6. Delivery of findings and recommendations - organized, informative and responsive to challenging questions

Each Category will carry 5 points: 1 being the weakest, and 5 being the strongest.

Evaluation Team 

  • David Belanger, Chair of IEEE Big Data Technical Community, Stevens Institute of Technology
  • Mahmoud Daneshmand, Vice-Chair of BDGMM, Steven Institute of Technology
  • Kathy Grise, Senior Program Director, Future Directions, IEEE
  • Joan Woolery, Senior Project Manager, Industry Connections, IEEE Standards Association, IEEE
  • Cherry Tom, Emerging Technologies Initiatives Manager, IEEE Standards Association, IEEE
  • Elizabeth Chang, Research Fellow, Department of Radiation Oncology, University of Maryland Marlene and Stewart Greenebaum Comprehensive Cancer Center, USA
  • David Ziegler, Director of Technology Program; Multimodal Biosensing – Neuroscape University of California San Francisco, USA
  • Seth Elkin-Frankston, Chief Scientist, Metrodora, USA

Winners for each track
- 1st Place: $1500*
- 2nd Place: $1000*
- 3nd Place: $500*
  ( '*' - at the discretion from the Evaluation Team)
- IEEE Certificates for 1st, 2nd, 3rd winners
- All team members win a Polo-shirt

 

Important Dates

Oct 14, 2018: Paper submission deadline

Nov 10, 2018: Paper acceptance notification

Nov 15, 2018: Camera ready version due

Dec 3, 2018: Deadline for hackathon sign-up

Dec 10, 2018: Hackathon

Mar 11, 2019: Hackathon White Paper due

 

Program Schedules 

Day-1: Dec 10, 2018

TimeTopic
09:00 – 09:10Welcome, Wo Chang, Chair of IEEE BDGMM, NIST, USA
09:10 – 09:20Opening Remark, David Belanger, Chair of IEEE Big Data Technical Community, Stevens Institute of Technology
09:20 – 11:00
(in Parallel)
Hackathon Briefing on use case, datasets, challenges, Q/As
Hackathon Track#1: Personalized Medicine for Drug Targeting in Prostate Cancer Patients
Dr. Elizabeth Chang (Tutorial & Hands-on), Research Fellow, Department of Radiation Oncology, University of Maryland Marlene and Stewart Greenebaum Comprehensive Cancer Center, USA
Hackathon Track#2: Brain Data Bank on Video Gaming Enhances Cognitive Skills
Dr. David Ziegler (Tutorial), Director of Technology Program, Multimodal Biosensing, UCSF, USA
Dr. Seth Elkin-Frankston (Hands-on), Chief Scientist, Metrodora, USA
11:00 – till next day 09:00Solving hackathon challenges
Next day 09:00 – 12:00 Hackathon Presentation and Evaluation, See Evaluation Team & Criteria

Day-2: Dec 11, 2018

TimeTopic
09:00 - 12:00 Hackathon Evaluation, Evaluation Team
12:00 – 13:30Lunch (on your own)
13:30 – 13:40 Welcome, Wo Chang, Chair of IEEE BDGMM, NIST, USA
13:40 – 14:00 Opening Remark, David Belanger, Chair of IEEE Big Data Technical Community, Stevens Institute of Technology
14:00 – 14:40 Keynote Speaker: NCI Cancer Research Data Commons

Allen Dearry, Program Director, NCI Cancer Research Data Commons, Center for Biomedical Informatics and Information Technology, National Cancer Institute, National Institutes of Health, US

14:40 – 15:10Invited Speaker on Big Data Governance Management: Aggregating and Sharing De-Identified Clinical, Imaging, and Genomic Data from the VA to External Repositories for the APOLLO Network

Luis E. Selva, Research Health Scientist, Associate Center Director, VA Central Biorepository and Associate Director of Imaging Informatics, U.S. Department of Veterans Affairs (VA), US

15:10 – 15:40Coffee Break
15:40 – 16:10Invited Speaker on Big Data Metadata Management:

Speaker: TBD

16:10 – 16:40Invited Speaker: Modeling visual cortex through the lens of interpretable machine learning and biophysics

Reza Abbasi-Asl, Scientist, Allen Institute for Brain Science, Seattle, WA, USA

16:40 – 16:55Paper Presentation #1: Efficient Query Answering On Uncertain Big RDF Data

Mourad Ouziri and Salima Benbernou, University of Paris Descartes, France

16:55 - 17:10Paper Presentation #2: A Path to Big Data Readiness

Claire C. Austin, Environment and Climate Change Canada, Canada

17:10 – 17:25Hackathon Ceremony

David Belanger and Kathy Grise

17:25 – 17:30 Announcement for next BDGMM Event, Wo Chang

Keynote Speaker 

Dr. Allen Dearry, Program Director, NCI Cancer Research Data Commons, Center for Biomedical Informatics and Information Technology, National Cancer Institute, National Institutes of Health, US

Abstract: As -omics and other sciences increase the volume of data collection, the need for big data solutions in biomedical research intensifies. Biomedical informatics has reached a turning point where key innovations in data storage and distribution such as compression algorithms, indexing systems, and cloud platforms must be leveraged. In addition to the data curation and storage needs of modern biomedical research, other challenges include development of robust analytical tools as well as infrastructure and funding models to support these efforts. As data generation expands, local storage and computational solutions become less feasible. Thus, NCI has set out to build the NCI Cancer Research Data Commons (NCI CRDC), a cloud-based infrastructure in support of data sharing, tool development, and compute capacity to democratize big data analysis and to increase collaboration among researchers. NCI has sponsored recent initiatives that serve as the foundation for the Cancer Research Data Commons—the Genomics Data Commons (GDC), and three Cloud Resources. In addition, NCI has recently announced plans to expand NCI CRDC to include proteomics and imaging data and to develop semantic resources to ensure interoperability. Both current and planned NCI CRDC activities will be discussed.
Brief Bio: Dr. Allen Dearry serves as program director for the NCI Cancer Research Data Commons. Allen joined NCI in 2017 after 25 years at the National Institute of Environmental Health Sciences, where he most recently directed the Office of Scientific Information Management and served as a Senior Advisor for Data Science Technology and Sustainability with the NIH Associate Director for Data Science. Allen is a member of several trans-NIH and interagency committees that coordinate on bioinformatics, computational biology, and big data. For his work on various projects, Allen has been awarded three HHS Secretary’s Awards for Distinguished Service. Allen earned his doctorate in anatomy from the University of Pennsylvania, completed his postgraduate work at the University of California, Berkeley, and was an assistant professor of cell biology and ophthalmology at Duke University Medical Center, where he cloned the gene for the human D1 dopaminergic receptor. He has two U.S. patents for this and subsequent investigations.

Invited Speaker 

Dr. Luis E. Selva, Research Health Scientist, Associate Center Director, VA Central Biorepository and Associate Director of Imaging Informatics, U.S. Department of Veterans Affairs (VA), US
Abstract: Recent advances in Precision Medicine or Targeted Machine have been made through the creation of heterogeneous patient data (“Big Data”) by merging several types of data streams to derive knowledge for informing treatment options. The protection of patient information is paramount to all medical centers, Protected Health Information (PHI) and/or Personally Identifiable Information (PII) data is normally ensconce behind firewalls and are not easily accessible by most researchers. This regulatory hurdle limits the usefulness of these data sets to potential users. Typically, researcher lack the time and resources necessary to navigate through the governing system to acquire the needed approvals. The work described in this presentation is being done under the umbrella of the APOLLO (Applied Proteogenomics Organizational Learning and Outcomes) Network, a collaboration between the NCI, the DoD, and the VA for studying the proteogenomic pathways that impact disease. In support of this effort, the VA has been actively involved in the creation of regulatory and technical workflows that facilitate the release of de-identified patient data from database-centric sources (clinical, imaging and genomic). The data streams were integrated, de-identified, harmonized and then shared with partner institutions, e.g., the Genomic Data Commons (GDC) and the Cancer Imaging Archives (TCIA) of the National Cancer Institute (NCI). We believe that the experience of creating heterogenous patient data will prove useful to researchers and decision-makers who desire to make their own data available to the broader community. It is our hope that the information and knowledge gained through this effort will persuade patients themselves to share their own data and encourage healthcare institutions to change healthcare privacy policy and help establish protocols and workflows that facilitate the sharing of medical data.

Brief Bio: Dr. Selva obtained a PhD in Biomedical Physics from the David Geffen School of Medicine at UCLA. Currently Dr. Selva works for the Department of Veterans Affairs in support of two programs, the Million Veteran Program (MVP) and the Precision Oncology Program (POP). MVP is a research driven program whose goal is to investigate the effect of genes on health. POP is an operational program that merges several data streams to derive knowledge for informing treatment options. Prior to working with VA, Dr. Selva worked for NASA's Jet Propulsion Laboratory (JPL) in Pasadena California where he studied the effects of radiation on microelectronic devices.

Invited Speaker 

Dr. Reza Abbasi-Asl, Scientist, Allen Institute for Brain Science, Seattle, WA, USA
Abstract: In the past decade, research in machine learning has been exceedingly focused on the development of algorithms and models with remarkably high predictive capabilities. However, interpreting these models still remains a challenge, primarily because of a large number of parameters involved. In this first part of this talk, I will introduce our frameworks based on (1) stability and (2) compression to build more interpretable machine learning models. These two frameworks will be demonstrated in the context of a computational neuroscience study. First, we introduce DeepTune, a stability-driven visualization framework for models based on Convolutioanl Neural Networks (CNNs). DeepTune is used to characterize biological neurons in the difficult V4 area of primate visual cortex. This visualization uncovers the diversity of stable patterns explained by the V4 neurons. Then, we introduce CAR, a framework for structural compression of CNNs based on pruning filters. CAR increases the interpretability of CNNs while retaining the diversity of filters in convolutional layers. CAR-compressed CNNs give rise to new set of accurate models for V4 neurons but with much simpler structures. Our results suggest, to some extent, that these CNNs resemble the structure of the primate brain. I will also discuss some of our recent works at Allen Institute on biophysically and anatomically detailed models of neurons in mouse cortex. In the second part, I will outline how we employ some of the tools in machine learning to build EEG-based brain-computer interfaces (BCI). In particular, we design a headset that consists of three components: a wearable EEG device, a virtual reality (VR) headset and an interface. Using this headset, we study the performance of BCI system in the VR environment and compare it to 2D regular displays. Our results suggest that the design of future BCI systems can remarkably benefit from the VR setting.

Brief Bio: Dr. Reza Abbasi-Asl is a scientist at the Allen Institute for Brain Science. He completed his PhD and MSc in Electrical Engineering and Computer Sciences at UC Berkeley in 2018, where he worked with Bin Yu and Jack Gallant to develop interpretable machine learning tools with applications in computational neuroscience. During his PhD, he also worked as research associate intern at Simons Foundation's Flatiron Institute in New York and Neuralink Corp. in San Fransisco in the summers of 2015 and 2017, respectively. He received his MSc in Biomedical Engineering from Sharif University of Technology in 2013 and BSc in Electrical Engineering from Amirkabir University of Technology (Tehran Polytechnic) in 2010. Reza is the recipient of the 2018 Eli Jury Award from UC Berkeley, Department of Electrical Engineering and Computer Sciences, for "outstanding achievement in the area of systems, communications, control, or signal processing". He also received the May J. Koshland Fund in Memory of H.A. Jastro Award from UC Berkeley Graduate Division in 2016, the Excellence Award in Biomedical Engineering from Sharif University of Technology in 2013, the Excellence Award in Electrical Engineering from Tehran Polytechnic in 2010, and the best paper finalist award at the 7th Iranian Conference on Machine Vision and Image Processing.

 

Hackathon Organizers 

General Co-Chairs

Wo Chang
Digital Data Advisor
National Institute of Standards and Technology, USA
Chair, IEEE Big Data Governance and Metadata Management
Convenor, ISO/IEC JTC 1/SC 42/WG 2 Working Group on Big Data
Email: chang@nist.gov

David Belanger (PhD)
Chair of IEEE Big Data Technical Community
Stevens Institute of Technology
Email: dgb@ieee.org

Mahmoud Daneshmand (PhD)
Professor, Stevens Institute of Technology, USA
Co-Chair, IEEE Big Data Governance and Metadata Management
Co-founder, IEEE BDIs
Email: mahmoud.daneshmand@gmail.com

Program Co-Chairs

Kathy Grise
Senior Program Director, Future Directions, IEEE Technical Activities, USA
Email: k.l.grise@ieee.org

Yinglong Xia (PhD)
Huawei Research America, USA
Co-chair, IEEE BDI - Big Data Management Standardization
Email: yinglong.xia.2010@ieee.org

Publicity Chairs

Cherry Tom
Emerging Technologies Intelligence Manager
IEEE Standards Association
445 Hoes Lane, Piscataway, NJ 08854-4141
Email: c.tom@ieee.org

 

Technical Program Committee

Name Organization Country
Paventhan ArumugamERNETIndia
Claire AustinS&T Strategies,Environment & Climate Change Canada Canada
Ismael CaballeroUCLMSpain
Yue-Shan ChangNational Central UniversityTaiwan
Periklis ChatzimisiosDepartment of Informatics, Alexander TEI of ThessalonikiGreece
Hung-Ming ChenNational Taichung University of Science and TechnologyTaiwan
Miyuru DayarathnaWSO2 Inc.Sri Lanka
Jacob DillesAcuant Corp.US
Robert HsuChung Hua University Taiwan
Wei HuNanjing UniversityChina
Carson LeungUniversity of ManitobaCanada
Sian Lun LauSunway University Malaysia
Christian Camilo Urcuqui LóepzIcesi University Colombia
Neil MillerThe bioinformatics for Children's Mercy HospitalUSA
Jinghua MinChina Electronic Cyberspace Great Wall Co., Ltd.China
Carlos MonroyRice UniversityUS
Huansheng NingUSTBChina
Arindam PalTCS ResearchIndia
Lijun QianPrairie View A&M UniversityUSA
Weining Qianx East China Normal UniversityChina
Yufei RenIBMUSA
Robby RobsonEduworks CorporationUS
Angelo Simone ScottoEuropean Food Safety Authority Italy
Priyaa ThavasimaniNewcastle University UK
Alex ThomoUniversity of VictoriaCanada
Chongang WangInterDigital CommunicationsUSA
Jianwu WangUniversity of Maryland, Baltimore CountyUS
Shu-Lin WangNational Taichung University of Science and TechnologyTaiwan
Jens WeberUniversity of VictoriaCanada
Lingfei WuIBM ResearchUSA
Hao XuUniversity of North Carolina at Chapel HillUS
Godwin YeboahUniversity of WarwickUK
Tim ZimmerlinAutomation TechnologiesUS