Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

A Semantics-based Approach to Machine Perception

1,095 views

Published on

Published in: Education, Technology
  • Be the first to comment

A Semantics-based Approach to Machine Perception

  1. 1. A SEMANTICS-BASED APPROACH TO MACHINE PERCEPTION Cory Andrew Henson August 27, 2013 1 Committee: Amit Sheth (advisor) Krishnaprasad Thirunarayan John Gallagher Payam Barnaghi Satya Sahoo Ph.D. Dissertation Defense Wright State University Dept. of Computer Science and Engineering
  2. 2. 2
  3. 3. 3 Thesis Machine perception can be formalized using semantic web technologies in order to derive abstractions from sensor data using background knowledge on the Web, and efficiently executed on resource-constrained devices.
  4. 4. 4 3 primary issues to be addressed Annotation of sensor data Semantic Sensor Web Semantic Perception Intelligence at the Edge Interpretation of sensor data Efficient execution on resource-constrained devices 1 2 3
  5. 5. 5 lives in has pet is ahas pet Person Animal Concrete Facts Resource Description Framework Semantic Web (according to Farside) General Knowledge Web Ontology Language “Now! – That should clear up a few things around here!” is a
  6. 6. Government Media Publications Life Sciences Geographic Semantic Web 6
  7. 7. 7http://www.opengeospatial.org/projects/groups/sensorwebdwg Semantic Sensor Web
  8. 8. 8 Sensor systems are too often stovepiped
  9. 9. 9 With freedom comes responsibility 1. discovery, access, and search 2. integration and interpretation We want to set this data free
  10. 10. 10 OGC Sensor Web Enablement (SWE)
  11. 11. 11 With freedom comes responsibility 1. discovery, access, and search 2. integration and interpretation We want to set this data free
  12. 12. 12 RDF OWL How are machines supposed to integrate and interpret sensor data? Semantic Sensor Networks (SSN)
  13. 13. 13 W3C Semantic Sensor Network Ontology Lefort, L., Henson, C., Taylor, K., Barnaghi, P., Compton, M., Corcho, O., Garcia-Castro, R., Graybeal, J., Herzog, A., Janowicz, K., Neuhaus, H., Nikolov, A., and Page, K.: Semantic Sensor Network XG Final Report, W3C Incubator Group Report (2011).
  14. 14. 14 W3C Semantic Sensor Network Ontology Lefort, L., Henson, C., Taylor, K., Barnaghi, P., Compton, M., Corcho, O., Garcia-Castro, R., Graybeal, J., Herzog, A., Janowicz, K., Neuhaus, H., Nikolov, A., and Page, K.: Semantic Sensor Network XG Final Report, W3C Incubator Group Report (2011).
  15. 15. 15 W3C Semantic Sensor Network Ontology Lefort, L., Henson, C., Taylor, K., Barnaghi, P., Compton, M., Corcho, O., Garcia-Castro, R., Graybeal, J., Herzog, A., Janowicz, K., Neuhaus, H., Nikolov, A., and Page, K.: Semantic Sensor Network XG Final Report, W3C Incubator Group Report (2011).
  16. 16. 16 Semantic Annotation of SWE Lefort, L., Henson, C., Taylor, K., Barnaghi, P., Compton, M., Corcho, O., Garcia-Castro, R., Graybeal, J., Herzog, A., Janowicz, K., Neuhaus, H., Nikolov, A., and Page, K.: Semantic Sensor Network XG Final Report, W3C Incubator Group Report (2011).
  17. 17. Semantic Sensor Observation Service (SemSOS) Cory Henson, Josh Pschorr,Amit Sheth, Krishnaprasad Thirunarayan, SemSOS: Semantic Sensor Observation Service, In Proceedings of the 2009 International Symposium on Collaborative Technologies and Systems (CTS 2009), Baltimore, MD, May 18-22, 2009. 17
  18. 18. Semantic Sensor Observation Service (SemSOS) Joshua Pschorr, Cory Henson, Harshal Patni, and Amit P. Sheth. Sensor Discovery on Linked Data. Kno.e.sis Center Technical Report 2010. 18
  19. 19. 19 3 primary issues to be addressed Annotation of sensor data Semantic Sensor Web Semantic Perception Intelligence at the Edge Interpretation of sensor data Efficient execution on resource-constrained devices1 2 3
  20. 20. 20 Semantic Perception • The role of perception is to transform raw sensory data into a meaningful and correct representation of the external world. • The systematic automation of this ability is the focus of machine perception. • For correct interpretation of this representation, we need a formal account of how this is done.
  21. 21. 21 What can we learn from cognitive models of perception? People are good at making sense of sensory input
  22. 22. 22 Perception is an active, cyclical process of exploration and interpretation. The perception cycle is driven by prior knowledge, in order to generate and test hypotheses. Some observations are more informative than others (in order to effectively test hypotheses*). Ulric Neisser Richard Gregory Kenneth Norwich 1970’s 1980’s 1990’s Cognitive Models of Perception * Applies to machine perception within Intellego, NOT human perception.
  23. 23. Observed Properties Perceived Features 23 Background knowledge Explanation Ontology of Perception Focus An Ontological Approach to Focusing Attention and Enhancing Machine Perception on the Web (Applied Ontology, 2011)
  24. 24. Example: Medical diagnosis as perception 24
  25. 25. Proactive, Preventative Healthcare 25
  26. 26. The Patient of the Future MIT Technology Review, 2012 26http://www.technologyreview.com/featuredstory/426968/the-patient-of-the-future/
  27. 27. Digital Doctor Let’s provide people with the tools needed to monitor and manage their own health http://worldofdtcmarketing.com/mobile-health-apps-a-new-opportunity-for-healthcare-marketers/mobile-healthcare-marketing-trends/ 27
  28. 28. Medical/healthcare expert systems have been around for a long time 28
  29. 29. 1. Ubiquitous Sensing 2. Always-on Computing 3. Knowledge on the Web 3 recent developments have changed the technological landscape … 29
  30. 30. 30 Making sense of sensor data with
  31. 31. DATA sensor observations KNOWLEDGE situation awareness useful for decision making Primary challenge is to bridge the gap between data and knowledge 31
  32. 32. SSN Ontology 2 Interpreted data (deductive) [in OWL] e.g., threshold 1 Annotated Data [in RDF] e.g., label 0 Raw Data [in TEXT] e.g., number Levels of Abstraction 3 Interpreted data (abductive) [in OWL] e.g., diagnosis Intellego ―150‖ Systolic blood pressure of 150 mmHg Elevated Blood Pressure Hyperthyroidism …… 32
  33. 33. Observed Properties Perceived Features 33 Background knowledge on the Web Low-level observed properties suggest explanatory hypotheses through abduction Explanation Focus Ontology of Perception An Ontological Approach to Focusing Attention and Enhancing Machine Perception on the Web (Applied Ontology, 2011)
  34. 34. 34 Semantics of Explanation Abduction – or, inference to the best EXPLANATION Task • Given background knowledge of the environment (SIGMA), and • given a set of sensor observation data (RHO), • find a consistent explanation of the situation (DELTA) Background knowledge Features (objects/events) in the world Sensor observation data
  35. 35. 35 Semantics of Explanation Background knowledge is represented as a causal network between features (objects or events) in the world and the sensor observations they give rise to.
  36. 36. 36 Semantics of Explanation Finding the sweet spot between abduction and OWL • Simulation of Parsimonious Covering Theory in OWL-DL (using the single-feature assumption*) * An explanation must be a single feature which accounts for all observed properties Semantic Perception: Converting Sensory Observations to Abstractions (IEEE Internet Computing, 2012) Theorem: Given a PCT problem P and its translation o(P) into OWL, Δ = {e} is a PCT explanation if and only if ExplanatoryFeature(e) is deduced by an OWL-DL reasoner — that is, if and only if o(P) ⊧ ExplanatoryFeature(e).
  37. 37. 37 Finding the Sweet Spot minimize explanations degrade gracefully w/ incomplete info decidable web reasoning Abductive Logic (e.g., PCT) high complexity Deductive Logic (e.g., OWL) (relatively) low complexity Explanation (in Intellego)
  38. 38. Explanatory Feature: A feature is explanatory w.r.t. a set of observed properties if it causes each property in the set. ExplanatoryFeature ≡ ∃isPropertyOf—.{p1} ⊓ … ⊓ ∃isPropertyOf—.{pn} elevated blood pressure clammy skin palpitations Hypertension Hyperthyroidism Pulmonary Edema Observed Property Explanatory Feature 38 Semantics of Explanation
  39. 39. Observed Properties Perceived Features 39 Background knowledge on the Web Hypotheses imply the informational value of future observations through deduction Explanation Focus Ontology of Perception An Ontological Approach to Focusing Attention and Enhancing Machine Perception on the Web (Applied Ontology, 2011)
  40. 40. Universe of observable properties 40 Semantics of Focus To predict which future observations have informational value, find those observable properties that can discriminate between the set of hypotheses. Expected Properties Not-applicable Properties Discriminating Properties
  41. 41. Expected Property: A property is expected w.r.t. a set of features if it is caused by each feature in the set. ExpectedProperty ≡ ∃isPropertyOf.{f1} ⊓ … ⊓ ∃isPropertyOf.{fn} elevated blood pressure clammy skin palpitations Hypertension Hyperthyroidism Pulmonary Edema Expected Property Explanatory Feature 41 Semantics of Focus
  42. 42. Not Applicable Property: A property is not-applicable w.r.t. a set of features if it is not caused by any feature in the set. NotApplicableProperty ≡ ¬∃isPropertyOf.{f1} ⊓ … ⊓ ¬∃isPropertyOf.{fn} elevated blood pressure clammy skin palpitations Hypertension Hyperthyroidism Pulmonary Edema Not Applicable Property Explanatory Feature 42 Semantics of Focus
  43. 43. Discriminating Property: A property is discriminating w.r.t. a set of features if it is neither expected nor not-applicable. DiscriminatingProperty ≡ ¬ExpectedProperty ⊓ ¬NotApplicableProperty elevated blood pressure clammy skin palpitations Hypertension Hyperthyroidism Pulmonary Edema Discriminating Property Explanatory Feature 43 Semantics of Focus
  44. 44. Off-the-shelf OWL-DL reasoners are too resource intensive in terms of both memory and time • Runs out of resources with background knowledge >> 20 nodes • Asymptotic complexity: O(n3) 44 O(n3) < x < O(n4) Semantic perception on resource-constrained devices
  45. 45. 45 3 primary issues to be addressed Annotation of sensor data Semantic Sensor Web Semantic Perception Intelligence at the Edge Interpretation of sensor data Efficient execution on resource-constrained devices1 2 3
  46. 46. Internet of Things 46http://www.idgconnect.com/blog-abstract/900/the-internet-things-breaking-down-barriers-connected-world
  47. 47. 47http://share.cisco.com/internet-of-things.html
  48. 48. 48 Basis Watch • Heart Rate Monitor • Accelerometer • Skin Temperature • Galvanic Skin Response
  49. 49. Homo Digitus 49 How do we make sense of this data … and do it efficiently and at scale?
  50. 50. Approach 1: Send all sensor observations to the cloud for processing 50 Approach 2: downscale semantic processing so that each device is capable of machine perception Intelligence at the Edge
  51. 51. Use bit vector encodings and their operations to encode background knowledge and execute perceptual inference 51 Efficient execution of semantic perception 01100011 10001110 11001110 01010110 01110101 OWL-DL An Efficient Bit Vector Approach to Semantics-based Machine Perception in Resource-Constrained Devices (ISWC, 2012)
  52. 52. lift lower Translate background knowledge, observations, and explanations between Semantic Web and bit vector representation 52 Lifting and lowering of knowledge
  53. 53. 53 Efficient execution of semantic perception Bit vector algorithms are provably equivalent to the OWL inference (i.e., semantics preserving) Intuition: discover and dismiss those features that cannot explain the set of observed properties. Intuition: discover and assemble those properties that discriminate between the explanatory features
  54. 54. bp 1 cs 0 pa 1 HN HM PE bp 1 1 1 cs 0 1 0 pa 1 1 0 HN HM PE 1 1 1 HN HM PE 1 1 1 1 1 0 AND => AND 1 1 1 Observed Property Prior Knowledge Previous Explanatory Feature Current Explanatory Feature => INTUITION: The strategy employed relies on the use of the bit vector AND operation to discover and dismiss those features that cannot explain the set of observed properties. 54 Explanation: efficient algorithm
  55. 55. bp 1 cs 0 pa 1 HN HM PE bp 0 1 1 cs 0 1 0 pa 1 1 0 HN HM PE 1 1 0 HN HM PE 0 1 0AND => 0 1 0 Observed Property Prior Knowledge Previous Explanatory Feature Current Explanatory Feature = INTUITION: The strategy employed relies on the use of the bit vector AND operation to discover and assemble those properties that discriminate between the explanatory features bp 0 cs 0 pa 0 Discriminatin g Property 1 1 0 … expected? 0 0 0 … not-applicable? ZERO Bit Vector 0 1 0 = => FALSE => FALSE 1 Is the property discriminating? 55 Focus: efficient algorithm
  56. 56. O(n3) < x < O(n4) O(n) 56 Evaluation on a mobile device Efficiency Improvement • Problem size increased from 10’s to 1000’s of nodes • Time reduced from minutes to milliseconds • Complexity growth reduced from polynomial to linear
  57. 57. 57 Technical contributions in a nutshell 1. Semantic Sensor Web: Developed technologies for the semantic annotation of sensor data on the Web - Semantic Sensor Web (IEEE Internet Computing, 2008) – 276 citations (as of Aug. 2013) - SemSOS: Semantic Sensor Observation Service (International Symposium on Collaborative Technologies and Systems, 2009) - Semantic Sensor Network XG Final Report (W3C Incubator Group Report, 2011) 2. Semantic Perception: Designed a declarative specification of perception, capable of utilizing an off-the-shelf OWL-DL reasoner - An Ontological Approach to Focusing Attention and Enhancing Machine Perception on the Web (Applied Ontology Journal, 2011) - Semantic Perception: Converting Sensory Observations to Abstractions (IEEE Internet Computing: Special Issue on Context- Aware Computing, 2012) – most downloaded paid paper in IEEE-IC 2012 3. Intelligence at the Edge: Implemented efficient algorithms for executing perceptual inference on resource-constrained devices - An Efficient Bit Vector Approach to Semantics-based Machine Perception in Resource-Constrained Devices (International Semantic Web Conference, 2012)
  58. 58. 58 W3C Reports 1. Semantic Sensor Network XG Final Report (W3C Incubator Group Report, 2011) Journal Publications 1. Physical-Cyber-Social Computing: An Early 21st Century Approach (IEEE Intelligent Systems, 2013) 2. Semantic Perception: Converting Sensory Observations to Abstractions (IEEE Internet Computing, 2012) 3. Semantics for the Internet of Things: Early Progress and Back to the Future (International Journal on Semantic Web and Information Systems, 2012) 4. The SSN ontology of the W3C semantic sensor network incubator group (Web Semantics: Science, Services and Agents on the World Wide Web, 2012) 5. An Ontological Approach to Focusing Attention and Enhancing Machine Perception on the Web (Applied Ontology, 2011) 6. Semantic Sensor Web (IEEE Internet Computing, 2008) Conference Publications 1. An Efficient Bit Vector Approach to Semantics-based Machine Perception in Resource-Constrained Devices (International Semantic Web Conference, 2012) 2. Computing Perception from Sensor Data (IEEE Sensors Conference, 2012) 3. SemSOS: Semantic Sensor Observation Service (International Symposium on Collaborative Technologies and Systems, 2009) 4. Situation Awareness via Abductive Reasoning for Semantic Sensor Data: A Preliminary Report (International Symposium on Collaborative Technologies and Systems, 2009). Workshop Publications 1. SECURE: Semantics Empowered Rescue Environment (International Workshop on Semantic Sensor Networks, 2011) 2. Representation of Parsimonious Covering Theory in OWL-DL (International Workshop on OWL: Experiences and Directions, 2011) 3. Provenance Aware Linked Sensor Data (Workshop on Trust and Privacy on the Social and Semantic Web, 2010) 4. Linked Sensor Data (International Symposium on Collaborative Technologies and Systems, 2010) 5. A Survey of the Semantic Specification of Sensors (International Workshop on Semantic Sensor Networks, 2009) 6. An Ontological Representation of Time Series Observations on the Semantic Sensor Web (International Workshop on the Semantic Sensor Web) 7. Video on the Semantic Sensor Web (W3C Video on the Web Workshop, 2007) Relevant Publications
  59. 59. 59 Application Proactive, preventative healthcare
  60. 60. Heart disease is a critical issue ~815,000 (2011) http://millionhearts.hhs.gov/abouthds/cost-consequences.html 60
  61. 61. Acute Decompensated Heart Failure (ADHF) • Affects nearly 6 million people (in U.S.) • 555,000 new cases are diagnosed each year 61U.S. Department of Health & Human Services. (2011). Hospital Compare. http://www.hospitalcompare.hhs.gov (Accessed on February 19, 2012).
  62. 62. • 4.8 million hospitalizations per year • 50% are readmitted within 6 months • 25% are readmitted within 30 days • 70% due to worsening conditions • Costing $17 billion per year ADHF hospital readmission rates are too high 62U.S. Department of Health & Human Services. (2011). Hospital Compare. http://www.hospitalcompare.hhs.gov (Accessed on February 19, 2012).
  63. 63. Congress has incentivized hospitals to lower readmission rates 63U.S. Department of Health & Human Services. (2011). Hospital Compare. http://www.hospitalcompare.hhs.gov (Accessed on February 19, 2012).
  64. 64. Current state-of-the-art 64
  65. 65. Score (0: Not at all, 1: A little, 2: A great deal, 3: Extremely) Heart Failure Somatic Awareness Scale (HFSAS) Current state-of-the-art 65
  66. 66. kHealth – knowledge-enabled healthcare Approach: • Use semantic perception inference • with data from cardio-related sensors • and curated medical background knowledge on the Web 1. to monitor and abstract health conditions 2. to ask the patient contextually relevant questions 66
  67. 67. Cardiology Background Knowledge • Symptoms: 284 • Disorders: 173 • Causal Relations: 1944 Unified Medical Language System Causal Network 67
  68. 68. kHealth Kit Weight Scale Heart Rate Monitor Blood Pressure Monitor 68 Sensors Android Device (w/ kHealth App) Total cost: < $500
  69. 69. 69 Explanation in kHealth • Abnormal heart rate • High blood pressure • Panic Disorder • Hypoglycemia • Hyperthyroidism • Heart Attack • Septic Shock Observed Property Explanatory Feature via Bluetooth
  70. 70. 70 Focus in kHealth Are you feeling lightheaded? Are you have trouble taking deep breaths? yes yes • Abnormal heart rate • High blood pressure • Lightheaded • Trouble breathing • Panic Disorder • Hypoglycemia • Hyperthyroidism • Heart Attack • Septic Shock Contextually dependent questioning based on prior observations (from 284 possible questions) Observed Property Explanatory Feature
  71. 71. 71 Evaluation of kHealth Evaluate the ability to discriminate between sets of potential disorders using: 1. HFSAS/WANDA’s restricted set of observable symptoms (12) 2. kHealth’s more comprehensive set of observable symptoms (284)
  72. 72. 72 Evaluation of kHealth Evaluation Metrics: 1. Efficiency: How many observations (or questions) required to minimize the set of explanations? 2. Specificity: How specific is the resulting minimum set of explanations (i.e., how many explanatory disorders in the set)? Explanatory Disorders (computed by Intellego) Actual Disorder (extracted from EMR) Possible Disorders (derived from cardiology KB)
  73. 73. 73 Evaluation of kHealth – Early Results HFSAS/WANDA Efficiency: ~7.45 (# questions asked) Specificity: ~11.95* (# minimum explanations) * Converged to 1 explanation 20% of the time • 496 EMRs • ~3.2 diagnosed disorders per EMR • 173 possible disorders The approach utilized by kHealth is more efficient and more specific than HFSAS/WANDA. kHealth Efficiency: ~7.28 (# questions asked) Specificity: 1 (# minimum explanations) Explanatory Disorders (computed by Intellego) Actual Disorder (extracted from EMR) Possible Disorders (derived from cardiology KB)
  74. 74. Pre-clinical usability trial Dr. William Abraham, M.D. Director of Cardiovascular Medicine 74
  75. 75. Sensing and Perception Health Care Academic Standards Org. Industry Government Research Collaborators by Research Topic and Organization Type 75
  76. 76. Special Thanks to AFRL and DAGSI 76 AFRL/DAGSI Research Topic SN08-8: Architectures for Secure Semantic Sensor Networks for Multi-Layered Sensing
  77. 77. 77
  78. 78. Semantic Sensor Web Team 78
  79. 79. A SEMANTICS-BASED APPROACH TO MACHINE PERCEPTION Cory Andrew Henson August 27, 2013 79 Thank you. For additional information visit: http://knoesis.org/researchers/cory

×