Kun Yi Li, Young Scholar Student, Quincy High School

Slides:



Advertisements
Similar presentations
Algorithms and applications
Advertisements

COMPUTER AIDED DIAGNOSIS: CLASSIFICATION Prof. Yasser Mostafa Kadah –
Associative Learning Memories -SOLAR_A
SOUTHEASTCON I KARMA ECE IEEE SoutheastCon Hardware Competition Must build an autonomous robot that can –Start at rest at the Starting Station.
IntroductionMethods Participants  7 adults with severe motor impairment.  9 adults with no motor impairment.  Each participant was asked to utilize.
Visualization of dynamic power and synchrony changes in high density EEG A. Alba 1, T. Harmony2, J.L. Marroquín 2, E. Arce 1 1 Facultad de Ciencias, UASLP.
Indian Statistical Institute Kolkata
Andre Gonzaga, YSP Student, Framingham High School Devan Tierney, YSP Student, Foxborough High School Omid Askari, PhD Student, Northeastern University.
Physiological Optical Image Processing Imani George, YSP Student, Thayer Academy Jenny Dinh, YSP Student, Lowell High School Yolanda Rodriguez-Vaqueiro,
AIIA Lab, Department of Informatics Aristotle University of Thessaloniki Z.Theodosiou, F.Raimondo, M.E.Garefalaki, G.Karayannopoulou, K.Lyroudia, I.Pitas,
CS 590M Fall 2001: Security Issues in Data Mining Lecture 3: Classification.
By Fernando Seoane, April 25 th, 2006 Demo for Non-Parametric Classification Euclidean Metric Classifier with Data Clustering.
Classification Dr Eamonn Keogh Computer Science & Engineering Department University of California - Riverside Riverside,CA Who.
1 Nearest Neighbor Learning Greg Grudic (Notes borrowed from Thomas G. Dietterich and Tom Mitchell) Intro AI.
KNN, LVQ, SOM. Instance Based Learning K-Nearest Neighbor Algorithm (LVQ) Learning Vector Quantization (SOM) Self Organizing Maps.
Redaction: redaction: PANAKOS ANDREAS. An Interactive Tool for Color Segmentation. An Interactive Tool for Color Segmentation. What is color segmentation?
Pattern Recognition. Introduction. Definitions.. Recognition process. Recognition process relates input signal to the stored concepts about the object.
Results Comparison with existing approaches on benchmark datasets Evaluation on a uveal melanoma datasetEvaluation on the two-spiral dataset Evaluation.
Kevin Cai, AMSA Charter School Matthew Greenlaw, Pioneer Charter School of Science Dr. Birol Ozturk, Northeastern University Professor Swastik Kar, Physics,
Methods in Medical Image Analysis Statistics of Pattern Recognition: Classification and Clustering Some content provided by Milos Hauskrecht, University.
A Simple Method to Extract Fuzzy Rules by Measure of Fuzziness Jieh-Ren Chang Nai-Jian Wang.
© Negnevitsky, Pearson Education, Will neural network work for my problem? Will neural network work for my problem? Character recognition neural.
Olivia Venezia, YSP participant, Revere High School
Professor: S. J. Wang Student : Y. S. Wang
COMMON EVALUATION FINAL PROJECT Vira Oleksyuk ECE 8110: Introduction to machine Learning and Pattern Recognition.
K Nearest Neighbors Saed Sayad 1www.ismartsoft.com.
IntroductionMethods Participants  7 adults with severe motor impairment performed EEG recording sessions in their own homes.  9 adults with no motor.
Medical Imaging Dr. Mohammad Dawood Department of Computer Science University of Münster Germany.
Directeur : Mr S. PERREY (PR). Improving Usability in Human Computer Interfaces: an investigation into cognitive fatigue and its influence on the performance.
1 Multiple Classifier Based on Fuzzy C-Means for a Flower Image Retrieval Keita Fukuda, Tetsuya Takiguchi, Yasuo Ariki Graduate School of Engineering,
AUTOMATIC TARGET RECOGNITION OF CIVILIAN TARGETS September 28 th, 2004 Bala Lakshminarayanan.
Random vs Deterministic Sequencing In RCP BCIs Katie Bradford, Littleton High School Jakob Farnham, Dedham High School Mohammad Moghadamfalahi, Graduate.
IE 585 Competitive Network – Learning Vector Quantization & Counterpropagation.
Classifying Event-Related Desynchronization in EEG, ECoG, and MEG Signals Kim Sang-Hyuk.
Motivation Increase bandwidth of BCI. Reduce training time Use non invasive technique.
Validation methods.
Detection, Classification and Tracking in Distributed Sensor Networks D. Li, K. Wong, Y. Hu and A. M. Sayeed Dept. of Electrical & Computer Engineering.
Machine Learning ICS 178 Instructor: Max Welling Supervised Learning.
BIOSTATISTICS Explorative data analysis. Box plot QQ plot Classification analysis Copyright ©2012, Joanna Szyda INTRODUCTION.
K nearest neighbors algorithm Parallelization on Cuda PROF. VELJKO MILUTINOVIĆ MAŠA KNEŽEVIĆ 3037/2015.
Eick: kNN kNN: A Non-parametric Classification and Prediction Technique Goals of this set of transparencies: 1.Introduce kNN---a popular non-parameric.
Next, this study employed SVM to classify the emotion label for each EEG segment. The basic idea is to project input data onto a higher dimensional feature.
In part from: Yizhou Sun 2008 An Introduction to WEKA Explorer.
Does one size really fit all? Evaluating classifiers in a Bag-of-Visual-Words classification Christian Hentschel, Harald Sack Hasso Plattner Institute.
Machine Learning Reading: Chapter Classification Learning Input: a set of attributes and values Output: discrete valued function Learning a continuous.
Gilad Lerman Math Department, UMN
Koichi Odajima & Yoichi Hayashi
Clustering CSC 600: Data Mining Class 21.
Bongjae Choi, Sungho Jo Presented by: Yanrong Wo
Deep Blue Brain Drone Introduction Brain Drone Components Purpose
[Ran Manor and Amir B.Geva] Yehu Sapir Outlines Review
Erich Smith Coleman Platt
Evaluating Techniques for Image Classification
Introduction to translational and clinical bioinformatics Connecting complex molecular information to clinically relevant decisions using molecular.
Statistical Techniques
When to engage in interaction – and how
Introduction Feature Extraction Discussions Conclusions Results
Figure 1.1 Rules for the contact lens data.
Nearest-Neighbor Classifiers
A Fast and Scalable Nearest Neighbor Based Classification
CS621: Artificial Intelligence Lecture 17: Feedforward network (lecture 16 was on Adaptive Hypermedia: Debraj, Kekin and Raunak) Pushpak Bhattacharyya.
Weka Free and Open Source ML Suite Ian Witten & Eibe Frank
Principal Component Analysis (PCA)
DataMining, Morgan Kaufmann, p Mining Lab. 김완섭 2004년 10월 27일
Lecture 7: Simple Classifier (KNN)
CSCI N317 Computation for Scientific Applications Unit Weka
Machine Learning for Visual Scene Classification with EEG Data
Signal amplification and digitization
Introduction.
Hairong Qi, Gonzalez Family Professor
Presentation transcript:

Minimum Mean Distance and k-Nearest Neighbor Classifiers for Signal Processing Kun Yi Li, Young Scholar Student, Quincy High School Eric Lehman, Young Scholar Student, Belmont High School Graduate research mentors: Matt Higger, Fernando Quiviria, PhD Candidate, Northeastern University Professor Deniz Erdogmus, Associate Professor, Northestern University College of Computer Engineering, Cognitive Systems Laboratory

Why use brain interfaces? Help a targeted group of individuals with severe speech and motor impairments who are unable to perform simple tasks or communicate with everyday individuals Image Source: http://i2.cdn.turner.com/cnn/dam/assets/121016060125-orig-ideas-brainwave-wheelchair-00013909-story-top.jpg

Brain Interface Stimulus User EEG Classifier Decision

SSVEP Brain Interface Video

SSVEP: Stands for “Steady State Visually Evoked Potential” SSVEP: Stands for “Steady State Visually Evoked Potential”. This type of brain signal is a response to looking at repeated intensities of light from 0 to 60 Hz. EEG: Stands for “electroencephalography”. EEG data is the measurement of the brain’s electrical activity voltages on the surface of the scalp over a certain period of time. Iris Dataset: A dataset that contains 3 different types for flowers, 50 samples each, and 4 different features (sepal length in cm, sepal width in cm, petal length in cm, petal width in cm).   Classifier: An algorithm that divides data into different group based on their similarities. Definitions

Minimum Mean Distance Classifier An algorithm that classifies multiple types of data. When given a test point, the program: calculates the distance from the new data point to the average of training data points. selects the training data point with the shortest distance identifies the new data point in the same group as the closest training point.

Minimum Mean Distance Classifier Classification of Iris Flower Dataset Using Minimum Mean Distance Classifier   Ground Truth Class Estimated Class I. setosa I.  versicolor I.  virginica 1 I. versicolor 0.92 0.14 I. virginica 0.08 0.86

Minimum Mean Distance Classifier Classification of EEG Data Using Minimum Mean Distance Classifier   Ground Truth Class Estimated Class 20 Hz 15 Hz 12 Hz 1

k-Nearest Neighbor Classifier An algorithm that classifies and divides multiple types of data. When given a new test data point, the KNN classifier: 1. Calculates the distance from the test data to all training data points 2. Selects the k number of training data points that are the closest to the test data point 3. Identifies the test data point as the same as the most common class among the k nearest training data points

k-Nearest Neighbor Classifier Classification of Iris Flower Dataset Using Minimum Mean Distance Classifier   Ground Truth Class Estimated Class I. setosa I.  versicolor I.  virginica 1 I. versicolor 0.94 0.04 I. virginica 0.06 0.96

K-Nearest Neighbor Classifier Classification of EEG Data Using K-Nearest Neighbor Classifier   Ground Truth Class Estimated Class 20 Hz 15 Hz 12 Hz 1

K Fold Cross Validation Separates the training set from the test set by segmenting the data into k number of sections The classifier will test on one section and train the remaining sections Prevents overfitting K Fold Cross Validation Image Source: http://classes.engr.oregonstate.edu/eecs/winter2011/cs434/notes/knn-4.pdf

Applications RSVP Typing system Uses P300 brain signal to determine which letter is the acquired target SSVEP brain interface Control robot motions through looking at a screen Applications Image Source: http://www3.ece.neu.edu/~purwar/research/photo_gallery.htm, http://www3.ece.neu.edu/~orhan/

Applications Can classify not just EEG data, but many other types of data! Iris Flower Dataset Image source: http://en.wikipedia.org/wiki/Iris_flower_data_set

Future Work Perform K-Fold Cross Validation Classify unprocessed EEG data using more advanced concepts to determine the most likely decision Classify EEG data obtained from other types of stimuli such as tactile sensors Help individuals with Locked-in Syndrome to communicate and with others through brain interfaces Future Work

Graduate Research Mentors: Matt Higger, Fernando Quivira, PhD Candidates, Northeastern University Professor Deniz Erdogmus, Department of Electrical and Computer Engineering, Cognitive Systems Lab, Northeastern University Orkan Sezer, Summer intern, Northeastern University Center for STEM Education Young Scholars Program & Team Claire Duggan - Director Kassi Stein, Jake Holstein, Chi Tse - YSP Coordinators Acknowledgements

Questions?