Speaker: Sun Peng Identifying Drug (Cocaine) Intake Events from Acute Physiological Response in the Presence of Free-living Physical Activity.

Slides:



Advertisements
Similar presentations
Presents: CareTaker™. Presents: CareTaker™ CareTaker™
Advertisements

Drowsiness Detection System Using Heartbeat Rate in Android-based Handheld Devices Advisor : Dr. Kai-Wei Ke Presenter : D. Jayasakthi Department of Electrical.
ECG Signal Processing Ojasvi Verma
Signal processing techniques for fNIRS and application to Brain Computer Interfaces Gautier Durantin, ISAE/CERCO French community for functional NIRS.
Energy expenditure estimation with wearable accelerometers Mitja Luštrek, Božidara Cvetković and Simon Kozina Jožef Stefan Institute Department of Intelligent.
Sensitivity Analysis for Observational Comparative Effectiveness Research Prepared for: Agency for Healthcare Research and Quality (AHRQ)
Correlates of polydrug use among injection drug users: The role of socioeconomic stress and quality of life Marrero CA, Robles RR, Reyes JC, Matos TD,
Phyllis K Stein, Ph.D. Heart Rate Variability Laboratory
THreshold based Energy-efficient FAtigue MEasurment for Wireless Body Area Sensor Networks using Multiple Sinks By : Sana Akram.
LOINC Italia News Maria Teresa Chiaravalloti Technologist at National Research Council, Italy PhD Student at University of Calabria, Italy Giovanna Sannino.
GMSM Mission and Vision Jennie Watson-Lamprey October 29, 2007.
20 10 School of Electrical Engineering &Telecommunications UNSW UNSW Clinical Trial To compare the accuracy of the falls algorithms, a clinical.
Multi-agents based wireless sensor telemedicine network for E-Health monitoring of HIV Aids Patients. By: Muturi Moses Kuria, SCI, University of Nairobi,
A Framework for Discovering Anomalous Regimes in Multivariate Time-Series Data with Local Models Stephen Bay Stanford University, and Institute for the.
1 Computerized Recognition of Emotions from Physiological Signals Physiological Signals Dec Mr. Amit Peled Mr. Hilel Polak Instructor : Mr. Eyal.
Neurofeedback Training Michael Dahl CS 575. Introduction Goal: Learning to self-regulate one’s own brain It is technology’s answer to psychotherapy, cognitive.
Gait recognition under non- standard circumstances Kjetil Holien.
Heart Rate & Endurance Training Derek Boutang
Improving the quality of life with Medical Grade Platform, Personal Monitoring and Alarming System.
Smart Products and Connected Health The Personal Metrics Movement Fredric Raab Sr. Systems Engineer UCSD Center for Wireless and Population Health Systems.
Department of Signals and Systems Disease Management System for CHF Patients Bengt Arne Sjöqvist, Adj. Professor, Chalmers University of Technology Kaj.
The Body Sensor Network. Project Overview Develop an application that can identifying affective experience – physiological responses – Especially those.
Crowdsourcing Predictors of Behavioral Outcomes. Abstract Generating models from large data sets—and deter¬mining which subsets of data to mine—is becoming.
Update to Woodway. PSM Training Echo is a tool targeted at S&C coaches and trainers to provide; 1. Metrics to measure the effectiveness of their training.
Does reduction in cocaine use represent psychosocial benefit? Ivan D. Montoya, M.D., M.P.H. Deputy Director, NIDA-DPMC.
EKG Electrocardiogram.
Presentation for ENSC 440/305 Instructors: Patrick Leung, Steve Whitmore Department of Engineering Science Simon Fraser University.
Physiological sensors and EEG A short introduction to (neuro-)physiological measurements.
Soft Sensor for Faulty Measurements Detection and Reconstruction in Urban Traffic Department of Adaptive systems, Institute of Information Theory and Automation,
Stimulants History: 1930’s: Benzedrine is used in inhalers, used as a cure for many of illnesses. 1940: WWII used to treat battle fatigue (pep pills) 1950’s:
Using Neural Networks to Predict Claim Duration in the Presence of Right Censoring and Covariates David Speights Senior Research Statistician HNC Insurance.
Time Series Data Analysis - I Yaji Sripada. Dept. of Computing Science, University of Aberdeen2 In this lecture you learn What are Time Series? How to.
1 SmartSpaghetti: Use of Smart Devices to Solve Health Care Problems Mostafa Uddin,A. Gupta, T. Nadeem, K. Maly Sandip Godambe, Arno Zaritsky BIBM/BIH.
1 Methods for detection of hidden changes in the EEG H. Hinrikus*, M.Bachmann*, J.Kalda**, M.Säkki**, J.Lass*, R.Tomson* *Biomedical Engineering Center.
Heart Rate Monitor (HRM). Measurement of HR Plethysmograph or ECG techniques ECG superior as distinguishable R peak HR derived by – Sensors: Limb or.
D McCormack, CTBT Infvrasound, KNMI Netherlands 29 October 2002 Towards Characterization of Infrasound Signals David A McCormack CTBT Verification Office.
Automatic Ballistocardiogram (BCG) Beat Detection Using a Template Matching Approach Adviser: Ji-Jer Huang Presenter: Zhe-Lin Cai Date:2014/12/24 30th.
Department of Computer and Electrical Engineering A Study of Time-based Features and Regularity of Manipulation to Improve the Detection of Eating Activity.
DRUGS OF ABUSE Reynaldo J. Lesaca, M.D. Reynaldo J. Lesaca, M.D.
Drugs in the Body (1) Recurrence Relations A patient is given an initial dose of 50mg of a drug. Each hour the patient is given a 20mg tablet of the.
Abstinence Incentives for Methadone Maintained Stimulant Users: Outcomes for Those Testing Stimulant Positive vs Negative at Study Intake Maxine L. Stitzer.
Legal Applications for Drug and Alcohol Testing Kelly R. Broome ARCpoint Labs
Table 1. Prediction model for maximum daily dose of buprenorphine-naloxone in a 12-week treatment condition Baseline Predictors Maximum Daily Dose Standardized.
Advisor : Dr. Kai-Wei Ke Presenter : D. Jayasakthi Wireless and Broadband Networks Lab, Department of Electrical Engineering and Computer Science, National.
IEEE N SubmissionLiang Li VinnoSlide 1 Project: IEEE P Working Group for Wireless Personal Area Networks (WPANs) Submission.
Toward a Taxonomy of Autonomic Sleep Patterns with Electrodermal Activity Akane Sano and Rosalind W. Picard, Massachusetts Institute of Technology Media.
Student Name USN NO Guide Name H.O.D Name Name Of The College & Dept.
Exposure Assessment for Health Effect Studies: Insights from Air Pollution Epidemiology Lianne Sheppard University of Washington Special thanks to Sun-Young.
Introduction Objectives Methods ResultsConclusions Future Work Acknowledgements Skin microclimate has been linked to tissue health Relative humidity affects.
ABSTRACT The purpose of the present study was to investigate the test-retest reliability of force-time derived parameters of an explosive push up. Seven.
Ayan Banerjee and Sandeep K.S. Gupta
1 Heart rate variability: challenge for both experiment and modelling I. Khovanov, N. Khovanova, P. McClintock, A. Stefanovska Physics Department, Lancaster.
Learning Objectives After this section, you should be able to: The Practice of Statistics, 5 th Edition1 DESCRIBE the shape, center, and spread of the.
Printing: This poster is 48” wide by 36” high. It’s designed to be printed on a large-format printer. Customizing the Content: The placeholders in this.
A Day in the Life of Your Heart
A Cost Effective Centralized Single parameter Patient Monitoring System Abstract Lack of Medical monitoring equipment's in rural areas of underdeveloped.
Wearable health systems: from smart technologies to real applications Lymberis A, Gatzoulis L European Commission, Information Society and Media Directorate-
Eunjeh Hyun, Seungwoo Noh, Chiyul Yoon, Hee Chan Kim
Contributions to Modern Science GISELLE S. SIGUA III-DARWIN HEALTH GROUP.
Bob Bianchi Prescription Drug Research Center Category 1 Focus Group Meeting Washington DC November,
MPuff: Automated Detection of Cigarette Smoking Puffs from Respiration Measurements Amin Ahsan Ali, Syed Monowar Hossain, Karen Hovsepian, Md. Mahbubur.
IntroOH-1 CSE 5810 Remote Health Care Monitoring by Wearable Sensors and Mobile Devices Kanchan Jha Computer Science & Engineering Department The University.
screening, brief intervention, and referral to treatment
Heart Rate Variability (HRV) analysis
PATIENT MONITORING SYSTEMS
MART: Music Assisted Running Trainer
Posture Monitoring System for Context Awareness in Mobile Computing
Thesis Defense of Master’s Degree Chen Zhang Advisor: Dr. Yi Shang
34th Annual International Conference of the IEEE EMBS
Bench press exercise detection and repetition counting
Presentation transcript:

Speaker: Sun Peng Identifying Drug (Cocaine) Intake Events from Acute Physiological Response in the Presence of Free-living Physical Activity

Content  Introduction  Data Collection  Data Processing and Modeling  Conclusion  Comparison  Q & A

Introduction  Current Study Current Study  Motivation Motivation  Related Work Related Work  Key Challenge Key Challenge

Current Study  Mobile health is more popular in health study Wearable, inexpensive Collect data Many platforms  Problem: How to tell story from data collected from clients?

Motivation  Study on mobile health helps with several application areas: Identify physical activity Drug use Smoke and alcohol event Craving and Mental study

Related Work  Cocaine study 1.Effect of different doses of cocaine in different way 2.Nonlinear regression model to identify drug use which is not readily to use 3.“iHeal”: Drugs craving, not reported yet

Key Challenges  Cocaine study 1.Incorrect placement and poor attachment 2.Don’t wear sensor 3.Hard to find cocaine patient 4.Difficult to collect ground truth 5.Dosage and method of injection 6.Unconstrained environment

Data Collection  Lab and Field Lab and Field  Sensor Suite Sensor Suite  Data Collected Data Collected

Lab and Field  Johns Hopkins University Medical School (JHU Lab Study)  3 cocaine dependent volunteers  National Institute on Drug Abuse (NIDA Lab Study)  6 cocaine using volunteers  National Institute on Field Study  42 active poly-drug users at NIDA

Sensor Suite  AutoSense  Flexible band on chest  Respiration data : Hz  ECG: 64 Hz  Accelerometer: Hz  Ambient and skin temperature: 1 Hz  Galvanic skin response: Hz

Data Collected  JHU Lab Study:  554 hours of good data collected from 3 subject  NIDA Lab Study  280 hours of good ECG collected from 6 subject  NIDA Field Study  10,449 hours of good ECG collected from 42 subjects  Urine Reports  385 potential cocaine of the 922 days of data collection

Data Processing and Modeling  Pipeline Pipeline  RR Intervals Detection RR Intervals Detection  Activity Detection Activity Detection  Model Development Model Development  Windows Selection Windows Selection  ANS ANS

Pipeline

RR Intervals Detection  Heart rate variability (HRV) is the variation of beat to beat intervals, also known as R-R intervals  Detect R peak  Outlier removal

Activity Detection  Research on accelerometer  7 participants wore AutoSense  266 minutes moving  183 minutes stationary  Threshold of 0.35 to classify moving and stationary

Model Development  Candidate windows selection  MACD line (Moving average convergence divergence)  EMA (Exponential Moving Averages)  Autonomous Nervous System (ANS) Model

Windows Selection  MACD  EMA slow - EMA fast = MACD Line  Slow: [1, 180]; Fast: [2, 90]  Input: smoothed RR intervals

Windows Selection

Autonomous Nervous System

Conclusion  Parameter Estimation Parameter Estimation  Parameter Discussion Parameter Discussion  Result Discussion Result Discussion  Future Work Future Work

Pipeline

Parameter Estimation

Parameter Discussion  Different treatment has different recovery time  Calculate recovery time in each window

Result Discussion

Future work  Generalizable approaches  Detecting events  Smooth noisy data  More powerful model

Comparison  Key challenge is almost same  Effect on body with alcohol smaller  Alcohol study have more variables  Do not have so much related work  Windows selection is usable for alcohol

Thank you !

Any questions ?