1 / 78

Technical Solutions Underlying Wireless Health Systems

Technical Solutions Underlying Wireless Health Systems. John A. Stankovic BP America Professor Department of Computer Science University of Virginia. http://www.cs.virginia.edu/wsn/medical/ http://wirelesshealth.virginia.edu/. What’s Wrong With Wires.

hanh
Télécharger la présentation

Technical Solutions Underlying Wireless Health Systems

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Technical Solutions Underlying Wireless Health Systems John A. Stankovic BP America Professor Department of Computer Science University of Virginia http://www.cs.virginia.edu/wsn/medical/ http://wirelesshealth.virginia.edu/

  2. What’s Wrong With Wires And we don’t want a patient tethered to a bed or fixed medical device

  3. Realisms and Main Points • Realisms • Humans and their behaviors are not simple • Example: Sleep • Environments are not simple • Example: Acoustics

  4. Realities – Sounds Encountered Physiological: Sneezing, nose blowing, sniffling, clearing throat, hiccup, eating, burp, humming, laughter, drinking, snoring Objects: phone vibrating or ringing, typing, mouse wheel, unwrapping food, papers rustling, clothes rustling, television, piano, moving furniture, doors opening and closing, objects dropping or moving, footsteps, pouring liquid, coffee percolation, dishwasher, cleaning sounds Ambient: truck backing up, siren, birds chirping, passing airplane, traffic, motorized tools (lawnmower, etc)

  5. Main Point • Many current solutions work ONLY when humans and environments are (assumed to be) very constrained

  6. Outline • Motivation • Architecture • ADLs and Semantic Anomaly Detection • Control Heart Rate • Vision: Aggression in Dementia Patients (not today) • Acoustics: Reverberation (not today)

  7. Motivation - The Problems • Aging Populations • High Cost of Medical Care • Lack of Facilities • Quality of Life Issues • Solution: Home Health Care CCRC Assisted Living

  8. Vision - Smart Living Space • Humans-in-Loop • Heterogeneous • Evolution • Open • Privacy Reality: NOT SIMPLE

  9. Research Q: Architecture • Alarmnet • Web based (Empath) Inference DB Med Records Web Server

  10. Our Solution: Empath • Realisms • Off-the-shelf • Non-expert user • Easy installation and maintenance • Remote monitoring • Extensible (HW) • Evolve (Behavior) • Patients are very different than grad students • Main Points • Web-like architecture is quite flexible • Single hop

  11. Architecture Web Server Base Station Sensors Collectors MQTT Broker Inference Modules CDMA Modem 4G Cloud Controller MongoDB Home Controller Monitoring Modules Monitoring Modules System Repository

  12. Applications – Versions of Architecture • Depression and General Anomalies • Dementia and Incontinence • Exercise and Epilepsy

  13. Depression Detection andGeneral Anomalies • Multi-modal • Passive • Combines Objective and Subjective Measures

  14. Empath: Depression Monitoring Patient Display Caregivers Display Depression Inference Eating Sleep Quality Movement Mood Weight Gain/Loss DB Cloud Motion and Contact Sleep Data PHQ-9 Acoustic Weight

  15. Caregivers Display

  16. Dementia and Incontinence • Bedwetting and sleep agitation relationship • Interventions on sleep • Sleep labs impractical • Goal: 50 patients

  17. Dementia and Incontinence(subsystem of Empath) • Passive Sleep system uva built • UVA Tempo device uva built • Wetness sensors – Dry Buddy off-shelf • Acoustic sensors – Screaming off-shelf

  18. Example Correlations

  19. Epilepsy Study(subsystem of Empath) • Linkage: between exercise, stress, sleep and epilepsy seizures • Measure: HR, BP (CareTaker), sleep quality, frequency of seizures • Intervention: qigong (Chinese healing art)

  20. Many Seizures at Night

  21. Status • Depression – 2 homes • Dementia – 11 real patients (on-going) • Epilepsy – 2 real patients

  22. Research Q: (Robust) Activities of Daily Living • Monitor eating, sleeping, exercising, … • What’s normal • Detect anomalies • Intervene: send alarms, inform someone, prevent, …

  23. Realisms • Activity Recognition (AR) of ADLs • Higher accuracy required • Overlapped activities • Across room activities • Many realities (missing data) …. • Anomaly detection • Accurate AR and what’s normal support good anomaly detection

  24. Main Point • Normal behavior is very complex • Per day • On Wednesdays • Two times per week • Every other month • In summer when condition X exists • Grouping of activities • Context dependent • …

  25. Big Picture Behavioral Anomaly Detection Learn Regular Behavior Sleep Eat Toilet Shower Exercise Entertainment Activity Recognition Pre-Processing Motion Sensors Contact Sensors Bed Sensors Body Sensors

  26. AALO (Active Learning based Activity recognition in the presence of Overlapped activities) Behavioral Anomaly Detection Learn Regular Behavior Sleep Eat Toilet Shower Exercise Entertainment Activity Recognition Overlapped Activities AALO Pre-Processing Motion Sensors Contact Sensors Bed Sensors Body Sensors

  27. Holmes: A comprehensive anomaly detection system Reduce False Positives & Negatives Behavioral Anomaly Detection Semantic Rules Holmes Context-based Multiple Models Temporal & Causal Correlations Learn Regular Behavior Sleep Eat Toilet Shower Exercise Entertainment Activity Recognition Pre-Processing Motion Sensors Contact Sensors Bed Sensors Body Sensors

  28. Robust Activity Recognition Accurate detection and summary of daily activities are essential Proper training and periodic retraining are necessary Necessary to ensure user comfort PervasiveHealth 2012 31

  29. Overlapped Activities Interrupted by room changes Concurrent in the same room Across rooms (not done yet) PervasiveHealth 2012

  30. Room Level Segmentation • First consider spatial regularity • In real life: • Within one episode, multiple activities may take place • We use Itemset identification • An activity may not complete within one episode (<roomID, entranceTime, duration, usedSensors>) (<timestamp, sensor-firing> pairs) Segmentation into Occupancy Episodes PervasiveHealth 2012 33

  31. Room Level Segmentation • Successive Occupancy Episode Merging (SOEM) • to identify overlapped activities interleaved across multiple rooms • We construct a new occupancy episode by merging two occupancy episodes in the same room that are separated by less than a time interval threshold PervasiveHealth 2012 34

  32. Example Evaluation Public Dataset List of Sensors • Single resident home • Activity annotation by the resident using Bluetooth headset • 26 days of data • 4 rooms (Bedroom, Kitchen, Toilet, Shower) • ‘Out of house’ considered as another room PervasiveHealth 2012 35

  33. Effectiveness of SOEM • Accuracy of ‘Sleep’ & ‘Prepare Dinner’ detection improved • SOEM does not reduce the accuracy for any activity PervasiveHealth 2012 36

  34. Comparison with Supervised Algorithms PervasiveHealth 2012 37

  35. Semantic Anomaly Detection • Sensor Level Anomalies • Activity Level Anomalies • Point • Context • Collective • Semantics

  36. Sensor Level Anomalies • May be due to different types of sensor failures • Fail-stop failure (may be detected by Ping) • Stuck-at failure • Transient • Obstructed field-of-view • Sensor movement

  37. Sensor Level Anomalies • How to detect: • Use temporal and spatial correlation among different sensors • Use multiple classifiers • Many systems assume no sensor failures! K. Kapitanova, E. Hoque, D. Alessandrelli, J. Stankovic, S, Son and K. Whitehouse, Being SMART About Failures: Assessing Repairs in Activity Detection, Ubicomp, Sept. 2012.

  38. Activity Level Anomalies • Point Anomalies • For each activity, one or more models based on training data • Different set of features for different activities • Sleep: sleep onset time, duration, number of interruptions, movement level • Showering: Start time, duration, water usage • Use statistical anomaly detection • Too many false alarms if used alone!

  39. Context Anomalies • For each activity, one or more models based on training data • Daily, specific day / days of week, specific time periods in a day

  40. Collective Anomalies • Monitor instances of same activity for N days collectively • Example: exercise twice per week • Monitor whether other activities happen before/after/during that activity in each time period • Example: have coffee before breakfast • Monitor instances of all activities for N days collectively • Example: every week shop, exercise, see doctor, …

  41. Semantics • Watching a pet for a few days • Entertaining visitors • Power outage • Recovering from major medical operation • Sensors died • Extreme weather: cold/heat wave • Social security check did not arrive: cannot purchase food or medication • Major medication change • Life changing events: sibling etc died, new grandchild etc.

  42. Holmes Framework Training Data Testing Data Learn Regular Behavior Calculate Anomaly Score and Initial Filter Regular Behavior Models Semantics: Expert Knowledge & User Feedback Semantic Anomaly Filters Explainable Scenarios True Anomalies

  43. MusicalHeart • Music non-invasive recommendation system to control heart rate • Bio-feedback (human-in-the-loop) • Context aware • Sitting, lying, walking, jogging, exercising • Home, traveling • Personalized • Learns Contexts: jogging, relaxing, traveling, etc.

  44. Wellness - Musical Heart Realisms Main Points Human in the Loop PI Control matches well • Movement (rustling) of ear buds • Music reaction is personal • Max HR per person • Context dependent • Impact changes over time

  45. Calm Your Heart

  46. Exercise Your Heart

  47. 3 Parts to Musical Heart Sensor Equipped Earphones Smartphone App Cloud

More Related