Constructing Multiple Views The architecture of the window was altered to accommodate switching between waveform, spectrogram, energy, and all combinations.

Slides:



Advertisements
Similar presentations
Take the Survey! Big data needs? How could membership benefit you? Automatic Interpretation of EEGs Statistics Acknowledgements DARPA/MTO (D13AP00065)
Advertisements

Corpus Development EEG signal files and reports had to be manually paired, de-identified and annotated: Corpus Development EEG signal files and reports.
Guide to Oracle10G1 Introduction To Forms Builder Chapter 5.
GridScape Ding Choon Hoong Grid Computing and Distributed Systems (GRIDS) Lab. The University of Melbourne Melbourne, Australia WW Grid.
Graphical User Interface (GUI) Nelson Padua-Perez Chau-Wen Tseng Department of Computer Science University of Maryland, College Park.
Access Tutorial 3 Maintaining and Querying a Database
Abstract EEGs, which record electrical activity on the scalp using an array of electrodes, are routinely used in clinical settings to.
Automatic Labeling of EEGs Using Deep Learning M. Golmohammadi, A. Harati, S. Lopez I. Obeid and J. Picone Neural Engineering Data Consortium College of.
Data Processing Machine Learning Algorithm The data is processed by machine algorithms based on hidden Markov models and deep learning. They are then utilized.
C51BR Applications of Spreadsheets 1 Chapter 16 Getting Started Making Charts.
Abstract The emergence of big data and deep learning is enabling the ability to automatically learn how to interpret EEGs from a big data archive. The.
Acknowledgements This research was also supported by the Brazil Scientific Mobility Program (BSMP) and the Institute of International Education (IIE).
Views The architecture was specifically changed to accommodate multiple views. The used of the QStackedWidget makes it easy to switch between the different.
THE TUH EEG CORPUS: The Largest Open Source Clinical EEG Corpus Iyad Obeid and Joseph Picone Neural Engineering Data Consortium Temple University Philadelphia,
THE TUH EEG CORPUS: A Big Data Resource for Automated EEG Interpretation A. Harati, S. López, I. Obeid and J. Picone Neural Engineering Data Consortium.
Data Acquisition An EEG measurement represents a difference between the voltages at two electrodes. The signal is usually displayed using a montage which.
Creating Graphical User Interfaces (GUI’s) with MATLAB By Jeffrey A. Webb OSU Gateway Coalition Member.
TUH EEG Corpus Data Analysis 38,437 files from the Corpus were analyzed. 3,738 of these EEGs do not contain the proper channel assignments specified in.
Big Mechanism for Processing EEG Clinical Information on Big Data Aim 1: Automatically Recognize and Time-Align Events in EEG Signals Aim 2: Automatically.
Adobe AuditionProject 4 guide © 2012 Adobe Systems IncorporatedOverview of Adobe Audition workspace1 Adobe Audition is an audio application designed for.
Automatic Discovery and Processing of EEG Cohorts from Clinical Records Mission: Enable comparative research by automatically uncovering clinical knowledge.
Automated Interpretation of EEGs: Integrating Temporal and Spectral Modeling Christian Ward, Dr. Iyad Obeid and Dr. Joseph Picone Neural Engineering Data.
Abstract Automatic detection of sleep state is important to enhance the quick diagnostic of sleep conditions. The analysis of EEGs is a difficult time-consuming.
Demonstration A Python-based user interface: Waveform and spectrogram views are supported. User-configurable montages and filtering. Scrolling by time.
Market: Customer Survey: 57 clinicians from academic medical centers and community hospitals, and 44 industry professionals. Primary Customer Need: 70%
Data Analysis Generation of the corpus statistics was accomplished through the analysis of information contained in the EDF headers. Figure 4 shows some.
Views The architecture was specifically changed to accommodate multiple views. The used of the QStackedWidget makes it easy to switch between the different.
Abstract Automatic detection of sleep state is an important queue in accurate detection of sleep conditions. The analysis of EEGs is a difficult time-consuming.
Improved EEG Event Classification Using Differential Energy A.Harati, M. Golmohammadi, S. Lopez, I. Obeid and J. Picone Neural Engineering Data Consortium.
 2002 Prentice Hall. All rights reserved. 1 Introduction to the Visual Studio.NET IDE Outline Introduction Visual Studio.NET Integrated Development Environment.
The Virtual Observatory and Ecological Informatics System (VOEIS): Using RESTful architecture and an extensible data model to provide a unique data management.
1 INTRODUCTION TO COMPUTER GRAPHICS. Computer Graphics The computer is an information processing machine. It is a tool for storing, manipulating and correlating.
The Neural Engineering Data Consortium Mission: To focus the research community on a progression of research questions and to generate massive data sets.
Constructing Multiple Views The architecture of the window was altered to accommodate switching between waveform, spectrogram, energy, and all combinations.
Results from Mean and Variance Calculations The overall mean of the data for all features was for the REF class and for the LE class. The.
Descriptive Statistics The means for all but the C 3 features exhibit a significant difference between both classes. On the other hand, the variances for.
Kai Li, Allen D. Malony, Sameer Shende, Robert Bell
Scalable EEG interpretation using Deep Learning and Schema Descriptors
BioSignal Analytics Inc.
Chapter 9: Graphical User Interfaces
User Profiles and Workspaces
Working in the Forms Developer Environment
AESA – Module 8: Using Dashboards and Data Monitors
Graphical User Interface in MATLAB
Chapter 2 – Introduction to the Visual Studio .NET IDE
CLASSIFICATION OF SLEEP EVENTS IN EEG’S USING HIDDEN MARKOV MODELS
G. Suarez, J. Soares, S. Lopez, I. Obeid and J. Picone
Enhanced Visualizations for Improved Real-Time EEG Monitoring
THE TUH EEG SEIZURE CORPUS
Introduction to the Visual C# 2005 Express Edition IDE
Enhanced Visualizations for Improved Real-Time EEG Monitoring
N. Capp, E. Krome, I. Obeid and J. Picone
Chapter 2 – Introduction to the Visual Studio .NET IDE
Document Visualization at UMBC
Optimizing Channel Selection for Seizure Detection
EEG Recognition Using The Kaldi Speech Recognition Toolkit
Big Data Resources for EEGs: Enabling Deep Learning Research
GRAPHICAL USER INTERFACE
AN ANALYSIS OF TWO COMMON REFERENCE POINTS FOR EEGS
E. von Weltin, T. Ahsan, V. Shah, D. Jamshed, M. Golmohammadi, I
LonMaker® Turbo Editions New Features
Improved EEG Event Classification Using Differential Energy
Environmental Monitoring: Coupling Function Calculator
Automatic Interpretation of EEGs for Clinical Decision Support
feature extraction methods for EEG EVENT DETECTION
Software Engineering System Modeling Chapter 5 (Part 1) Dr.Doaa Sami
EEG Event Classification Using Deep Learning
Deep Residual Learning for Automatic Seizure Detection
Seizure Detection Algorithm in Neonates Using Limited Channel aEEG
UML Design for an Automated Registration System
Presentation transcript:

Constructing Multiple Views The architecture of the window was altered to accommodate switching between waveform, spectrogram, energy, and all combinations of the available views. Currently, the structure of these combined views includes a scrolling area in which there are multiple channels with labels, and each channel is split into some combination of the three views. To switch between the views, a Python tool called a regular expression is used. A regular expression refers to a set of strings that match it, so it can be used to build a set of objects upon which functions can be performed. For example, if we want to manipulate all spectrogram widgets, we would build a regular expression which would contain all objects relevant to plotting spectrograms (assuming all of the plots are named accordingly). Significance of Alternate Plots A spectrogram is a graphical plot of the spectrum of frequencies in a signal. In a typical spectrogram, the x-axis represents time, and the y-axis represents frequency. In addition to these dimensions, color is used to indicate the intensity of each frequency over time. An energy plot is simply a plot of the energy of a signal over time. Spectrogram and energy plots offer unique graphical representations of a signal that provide different insight than a typical waveform plot. For example, these alternate views make it easier to identify transient events such as a seizure. Spectrograms especially are becoming used more often by neurologists because they are an efficient way to display a fair amount of EEG data and identify significant events. Constructing Multiple Views The architecture of the window was altered to accommodate switching between waveform, spectrogram, energy, and all combinations of the available views. Currently, the structure of these combined views includes a scrolling area in which there are multiple channels with labels, and each channel is split into some combination of the three views. To switch between the views, a Python tool called a regular expression is used. A regular expression refers to a set of strings that match it, so it can be used to build a set of objects upon which functions can be performed. For example, if we want to manipulate all spectrogram widgets, we would build a regular expression which would contain all objects relevant to plotting spectrograms (assuming all of the plots are named accordingly). Significance of Alternate Plots A spectrogram is a graphical plot of the spectrum of frequencies in a signal. In a typical spectrogram, the x-axis represents time, and the y-axis represents frequency. In addition to these dimensions, color is used to indicate the intensity of each frequency over time. An energy plot is simply a plot of the energy of a signal over time. Spectrogram and energy plots offer unique graphical representations of a signal that provide different insight than a typical waveform plot. For example, these alternate views make it easier to identify transient events such as a seizure. Spectrograms especially are becoming used more often by neurologists because they are an efficient way to display a fair amount of EEG data and identify significant events. Abstract An electroencephalogram, or EEG, is used to monitor the electrical activity in the brain through electrodes placed on the scalp. AutoEEG™ is a system which generates time- aligned markers, called annotations, which indicate significant events within these EEG signals. This demonstration system is a graphical display which incorporates AutoEEG™ to analyze an EEG recording. The system also displays these recordings graphically as waveforms and overlays colored annotations to show where events occur. The graphical display is based in PyQt, which is a python extension of the cross-platform Qt application framework. The goal of this project was to expand the available views for analyzing the signals in a manner such that other views could be easily added in the future. In addition to a waveform display, the planned modes included spectrogram and energy views. The ability to view a spectrogram within this software is especially useful in a clinical context because it is a powerful way to visualize signals. Spectrograms are becoming more accepted in continuous EEG (cEEG) monitoring because they allow neurologists to easily view hours’ worth of data to pinpoint areas of concern. Abstract An electroencephalogram, or EEG, is used to monitor the electrical activity in the brain through electrodes placed on the scalp. AutoEEG™ is a system which generates time- aligned markers, called annotations, which indicate significant events within these EEG signals. This demonstration system is a graphical display which incorporates AutoEEG™ to analyze an EEG recording. The system also displays these recordings graphically as waveforms and overlays colored annotations to show where events occur. The graphical display is based in PyQt, which is a python extension of the cross-platform Qt application framework. The goal of this project was to expand the available views for analyzing the signals in a manner such that other views could be easily added in the future. In addition to a waveform display, the planned modes included spectrogram and energy views. The ability to view a spectrogram within this software is especially useful in a clinical context because it is a powerful way to visualize signals. Spectrograms are becoming more accepted in continuous EEG (cEEG) monitoring because they allow neurologists to easily view hours’ worth of data to pinpoint areas of concern. Enhanced Visualizations for Improved Real-Time EEG Monitoring M. Thiess, E. Krome, M. Golmohammadi, Dr. I. Obeid and Dr. J. Picone The Neural Engineering Data Consortium, Temple University Introduction There are many open-source tools, such as EDFBrowser, which can be used to view EEG recordings stored in EDF files: The demonstration system for AutoEEG™ is a graphical display implemented using the popular Qt framework which allows users to interactively view and manipulate EEG signals. Thanks to markers generated by AutoEEG™, users can quickly and easily search through events in the EEG recordings such as seizures, PLEDS, and GPEDS. Commercial tools such as Persyst® offer spectrogram analysis for EEGs. Introduction There are many open-source tools, such as EDFBrowser, which can be used to view EEG recordings stored in EDF files: The demonstration system for AutoEEG™ is a graphical display implemented using the popular Qt framework which allows users to interactively view and manipulate EEG signals. Thanks to markers generated by AutoEEG™, users can quickly and easily search through events in the EEG recordings such as seizures, PLEDS, and GPEDS. Commercial tools such as Persyst® offer spectrogram analysis for EEGs. College of Engineering Temple University Sample Views Waveform only Waveform/Spectrogram combined Combining the different views allows one to compare between different signal visualizations for more analysis options. Sample Views Waveform only Waveform/Spectrogram combined Combining the different views allows one to compare between different signal visualizations for more analysis options. Summary The demonstration system for AutoEEG™ has been modified to support multiple views. Users can use the menu to select which views they want to see, and the window will change to show all of the selected views. The code has been updated in such a manner that new views can be added in a modular manner using functions that address groups of objects. Alternate methods for visualizing signals will allow clinicians and other users more diverse inspection tools. Spectrogram analysis offers a different perspective which is gaining traction as an effective manner of classifying EEG data. Acknowledgements This research was funded by the Temple University Honors Program through the Merit Scholar Stipend Program Summary The demonstration system for AutoEEG™ has been modified to support multiple views. Users can use the menu to select which views they want to see, and the window will change to show all of the selected views. The code has been updated in such a manner that new views can be added in a modular manner using functions that address groups of objects. Alternate methods for visualizing signals will allow clinicians and other users more diverse inspection tools. Spectrogram analysis offers a different perspective which is gaining traction as an effective manner of classifying EEG data. Acknowledgements This research was funded by the Temple University Honors Program through the Merit Scholar Stipend Program Clinical EEG Data An EEG is a multi-channel time varying signal describing voltages in different regions on the scalp, measured using electrodes. EEG recordings are interpreted using a montage, which defines the channels as differences between these electrodes. Overview of Demonstration Software AutoEEG™ is a tool which uses machine learning in the form of hidden Markov models and deep learning to deliver accurate event detection with good performance. AutoEEG™ is trained on the TUH-EEG corpus, which is the largest publicly-available EEG corpus, containing over 25,000 clinical EEG recordings The demonstration system encapsulates AutoEEG™ by providing a graphical representation of the data and its associated events. The application is mostly written in Python, and it relies heavily on the PyQt cross-platform toolkit. Qt Designer, which is a graphical layout designer included with the Qt framework, was used to create and edit this simple, robust graphical interface. In the current stable release of this software, the graphical tool displays waveforms read from an EDF file containing a recording of an EEG session. The tool also overlays colored annotations based on event markers generated by AutoEEG™, which include EYEBL, SPSW, GPED, PLED, ARTF, and BCKG. Users can use the buttons in the corner to quickly search through the annotations. In addition, the tool provides the ability to hide or show certain types of event markers, change the sensitivity scale, and alter the frame of time displayed in the window. Clinical EEG Data An EEG is a multi-channel time varying signal describing voltages in different regions on the scalp, measured using electrodes. EEG recordings are interpreted using a montage, which defines the channels as differences between these electrodes. Overview of Demonstration Software AutoEEG™ is a tool which uses machine learning in the form of hidden Markov models and deep learning to deliver accurate event detection with good performance. AutoEEG™ is trained on the TUH-EEG corpus, which is the largest publicly-available EEG corpus, containing over 25,000 clinical EEG recordings The demonstration system encapsulates AutoEEG™ by providing a graphical representation of the data and its associated events. The application is mostly written in Python, and it relies heavily on the PyQt cross-platform toolkit. Qt Designer, which is a graphical layout designer included with the Qt framework, was used to create and edit this simple, robust graphical interface. In the current stable release of this software, the graphical tool displays waveforms read from an EDF file containing a recording of an EEG session. The tool also overlays colored annotations based on event markers generated by AutoEEG™, which include EYEBL, SPSW, GPED, PLED, ARTF, and BCKG. Users can use the buttons in the corner to quickly search through the annotations. In addition, the tool provides the ability to hide or show certain types of event markers, change the sensitivity scale, and alter the frame of time displayed in the window. Main Window Scrolling Area Channel Frame/Container Waveform Plot Spectrogram Plot Energy Plot