Wearable Technology: the wave of the future Omid Dehzangi Computer - PowerPoint PPT Presentation

Wearable Technology: the wave of the future Omid Dehzangi Computer and Information Science University of Michigan - Dearborn Wearable Sensing and Signal Processing Lab

Outline  Introduction to wearable technology  Vision and mission  Application and high level model design  Wearable platform design and development  My research contributions  Brain-computer interface  Activity of daily living (ADL) monitoring  My current research plans 2

Technology Trends Wearable Computers Personal Computers Analog computer Today’s Computers  Transistors  Smaller  Smarter  Digital Processing  Slimmer  Hands free  Brought to homes  Faster  Natural Interface  Hand held 3

Wearable Technology  ABI Research has projected that by 2016, wearable wireless device sales will reach more than 100 million devices annually.  The market for wearable sports, fitness, and healthcare monitoring devices cover 80% of it.  The market for wearable technologies in healthcare "is projected to exceed $2.9 billion in 2016 (at least half of all wearable technology) Photo courtesy of http://www.phonearena.com/ 4

Wearable Computers Flex, Pressure and Piezo-electric Sensors Galvanic Skin Inertial Response Sensors Dry-contact Sensors EEG Feedback GUI-based feedback Deep Brain Stimulation Phantom Haptics Photo Courtesy of Photo Courtesy of mindmodulation.com SenseGraphics Vibrotactile Modules 5

Wearable Computers Sensors Processing Unit Signal Processing Data Analytics Communication Big data analysis Information Fusion Data mining Machine learning Prediction/Detection Predictive modeling Statistical analysis Feedback 6

Outline  Introduction to wearable technology  Vision and mission  Application and high level model design  Wearable platform design and development 7

Research Vision Applications  Demonstrate the linkage between discovery and societal benefit Model design  Validate real pains and necessities and identify Wearable platform effective high level solutions  Design and develop in multiple technical levels Algorithms and analytics  Resolve upcoming challenges in practice System integration  Generate transitioning technologies Technologies 9

Wireless Health Ubiquitous monitoring and intervention for the applications of health-care and wellness Courtesy of Misha Pavel, Program Director, National Science Foundation 9

Outline  Introduction to wearable technology  Vision and mission  Application and high level model design  Wearable platform design and development  My current research contributions  Brain-computer interface  Activity monitoring and motion detection 10

Application Case Study WEARABLE BRAIN COMPUTER INTERFACE Applications 11

Brain Computer Interface • Brain Computer Interface – Provide a non-muscular avenue for the user to communicate with others and to control external devices – Infer user’s intentions using brain activities • Applications – Assist locked-in individuals to interact with cyber and physical system – Gaming – Diagnosis and treatment for neurological disorder 12

Wearable EEG Systems • Smaller form factor (size of a credit card vs. bulky amps) • Quicker setup time (seconds vs. 30 mins) • Faster software training (5 mins vs. 30 mins) • Quicker EEG signal detection (seconds vs. minutes) • No need for EEG tech 13

Wearable EEG-Based BCI  Custom-designed mobile EEG-based BCI  Dry-contact electrodes  Low-noise front-end (ADS1299)  Low power processing (MSP430)  Low component count  Bluetooth low energy (TI BLE) communication module 14

Wearable BCI Units 15

Canonical Correlation Analysis(CCA) Video Picture taken from ref.1 17 16

ACTIVITY OF DAILY LIVING MONITORING Application Case Study USING GAIT AND SWAY BIOFEEDBACK TO REDUCE FALLS IN THE ELDERLY • Dehzangi, Omid, Biggan, John, Birjandtalab Golkhatmi, Javad, Ray, Christopher, Jafari, Roozbeh , “An Inertial Sensor -Based Method for Early Detection and Prevention of Excessive Sway in Older Adults via Gait Analysis and Vibrotactile Biofeedback ”, Gait & Posture journal. • Dehzangi, Omid, Zhao, Zheng, Biggan, John, Ray, Christofer, Jafari, Roozbeh , “The Impact of Vibrotactile Biofeedback on the Excessive Walking Sway and the Postural Applications Control in Elderly”, Wireless Health 2013, November 1 -3, Baltimore, Maryland, 2013. 17

Postural control and gait analysis 18

Sway Biofeedback for Fall Prevention  Fall is a considerable health concern in the elderly  Wearable kinematic biofeedback system to detect pre-cursors of falls based on the sway of the upper body and other gait parameters, and activate biofeedback 19

Hardware Architecture I 2 C Motion Sensor: Microprocessor Gyro & Accelerometer BLE Laptop UART BLE transceiver 20

Software Architecture Accelerometer Accelerometer Angle Threshold Gyroscope Self-adaptive X,Y,Z X,Y,Z X,Y,Z X,Y,Z Setting Calibrated Accelerometer X,Y,Z Sensor Calibration Calibrated Drift Gyroscope Detection X,Y,Z Euler Angles DCM (roll, pitch) Feedback loop PI controller 21

The developed system (a) (b) (a) Our designed wearable low-power motion sensor board, (b) Our biofeedback system, consisting of two motion sensor boards for the chest and the ankle along with the vibratory feedback modules. 22

Experiments  Subjects: 24 older adults (age: M = 75.5, SD = 4.32 years; 10 females) Procedure: 23

Results and Analysis Mean difference in the sway range. The results of the statistical test on the sway range The test Control Experimental P-value Difference in 0.59±1.77 -0.60±0.63 0.04 the sway range 24

Gait phase analysis Mid stance Initial sway Mid sway Terminal sway The selected phases of a gait cycle. Identification of the gait phases on the ACC X readings 25

Gait phase analysis 4 4 1.5 x 10 2 x 10 1.5 1 1 0.5 ACC X reading ACC X reading 0.5 0 0 -0.5 -0.5 -1 -1 -1.5 -1.5 -2 -2 0 0 5 5 10 10 15 15 20 20 25 25 30 Sample Sample DTW extracted strides based on ACC X readings DTW extracted strides based on ACC X readings (Experimental) (Control) 26

Gait phase analysis Mid stance Initial sway Mid sway Terminal sway Mean difference in the variance of the gait phases between pre- and post- training. The results of the Chi-square test on the gait phases The gait phases Control Experimental P-value Initial sway 0.17±0.62 0.40±0.15 0.09 Mid sway -1.54±1.72 -0.03±0.48 0.08 Terminal sway -1.29±1.04 0.038±1.01 0.05 27 Mid stance -0.18±0.89 -0.07±1.14 0.27

Outline  Introduction to wearable technology  Vision and mission  Application and high level model design  Wearable platform design and development  My current research contributions  Brain-computer interface  Activity of daily living (ADL) monitoring  My Current Research Plans 28

Application Case Study WEARABLE DRIVER MONITORING Applications 29

Goal • To form relationships between biological state of the driver with his/her driving behavior 37

Multi-Modal Driver Monitoring and Modeling via Heterogeneous Wearable Body Sensor Network Motivation: Body sensor networks are capable of generating a reliable human state model System photograph: a) b) c) Integration of heterogeneous wearable monitoring technology, on-board sensing units, and wireless 31 networking capabilities : a) The full body sensor network, b) the portable EEG system, c) the OBD-II device

Multi-Modal Driver Monitoring and Modeling via Heterogeneous Wearable Body Sensor Network The Proposed Platform: Hypotheses: Hypothesis 1 : Specific driver mental and 1. Minimally intrusive : Driver behavior is not affected by physical states can generate abnormal driving the devices that are used to acquire the necessary biomedical markers behaviors and a high level of driving impairment. 2. Comprehensive : the system will extract the data Hypothesis 2 : Driver biological states will have collected from a large number of heterogeneous an impact on his/her biometric measures while sensors and correlate the various readings for earlier detection driving. Biometric markers that correspond to changes in performance of the impaired driver 3. Ubiquitous and remotely available : The collected measurements will be transmitted to a remote location subjects will aid in explaining the underlying for longitudinal analysis and discover association in a impact on driving outcome. long term Hypothesis 3 : There are signature patterns in 4. Real--time responsive : The information will be the biometric readings from the normal behavior accessible in an online fashion to enable real--time processing and decision- making of the driver that can be non-invasively extracted and employed for control, identification & 5. User- friendly : Suitable user interface and visualization tools will be in place for a human user to authentication, and interaction with other smart be able to interpret the acquired information infrastructures. 39