Download - Machine Reasoning about Anomalous Sensor Data

Transcript
Page 1: Machine Reasoning about Anomalous Sensor Data

Machine Reasoning about Anomalous Sensor Data

Matt Calder, Francesco Peri, Bob Morris

Center for Coastal Environmental Sensoring Networks CESNUniversity of Massachusetts Boston

Page 2: Machine Reasoning about Anomalous Sensor Data

Goal

Provide scientists with software to explore domain hypotheses about their data

Page 3: Machine Reasoning about Anomalous Sensor Data

Outline1. Outline2. Motivation3. Knowledge Representation4. Our Knowledge System5. Software Architecture6. What’s missing (future work)

Page 4: Machine Reasoning about Anomalous Sensor Data

UMB CESN

• Interdisciplinary Research effort• Oceanography

• Biology

• Computer Science

• Policy / Law

• Cyber-infrastructure – Smart Sensor Networks

Page 5: Machine Reasoning about Anomalous Sensor Data

Outline1. Outline2. Motivation3. Knowledge Representation4. Our Knowledge System5. Software Architecture6. What’s missing (future work)

Page 6: Machine Reasoning about Anomalous Sensor Data

Algal Bloom ?

Page 7: Machine Reasoning about Anomalous Sensor Data

Benthic Resuspension ?

Page 8: Machine Reasoning about Anomalous Sensor Data

Aha!

Page 9: Machine Reasoning about Anomalous Sensor Data

Outline1. Outline2. Motivation3. Knowledge Representation4. Our Knowledge System5. Software Architecture6. What’s missing (future work)

Page 10: Machine Reasoning about Anomalous Sensor Data

Knowledge Representation• An ontology is a model of the relationships between concepts (ideas) of a particular domain. • OWL Web Ontology Language from the W3C

• Classes, Properties, Instances

Page 11: Machine Reasoning about Anomalous Sensor Data

Semantic Reasoners• Validation

• Checks that the constraints made in the ontology are not violated

• For example, a temperature sensor should not have taken any measurements other than temperature measurements.

• Inference and Rules• An inference is a conclusion drawn from the the truth

value of previously known facts

• antecedent -> consequence

• A ∧ B ∧ C -> D

Page 12: Machine Reasoning about Anomalous Sensor Data

Rule Example in Jena RL

[winter rule: (?x measurementOf Temperature)

(?x type Average),(?x value ?v),lessThan(?v, 0) →

(Season isWinter true) ]

In English:If x is a temperature and is an

average and has value v and v is less than 0 then it is winter.

Page 13: Machine Reasoning about Anomalous Sensor Data

Outline1. Outline2. Motivation3. Knowledge Representation4. Our Knowledge System5. Software Architecture6. What’s missing (future work)

Page 14: Machine Reasoning about Anomalous Sensor Data

Knowledge System

Page 15: Machine Reasoning about Anomalous Sensor Data

PhysicalPropertyPhysicalProperty

Measurement

Sensor

hasTakencanMeasure

real number dateTime

value timestamp

CESN Sensor Ontology: Core Components

Page 16: Machine Reasoning about Anomalous Sensor Data

Domain Knowledge Ontology: Ocean Events

OceanEvent

AlgalBloom BenthicResuspension

subClass subClass

dateTime

occurredAtTime

occurredAtLocationInfluencedBy

cesn:Locationcesn:PhysicalProperty

Page 17: Machine Reasoning about Anomalous Sensor Data

By the way…

Was it an Algal Bloom? ….No. It was winter!

Was it bethic diatom resuspension? Maybe – That is consistent with data and knowledge

Page 18: Machine Reasoning about Anomalous Sensor Data

Outline

1. Outline2. Motivation3. Knowledge Representation4. Our Knowledge System5. Software Architecture6. What’s missing (future work)

Page 19: Machine Reasoning about Anomalous Sensor Data

Sensor Data Reasoning System

Page 20: Machine Reasoning about Anomalous Sensor Data

Outline

1. Outline2. Motivation3. Knowledge Representation4. Our Knowledge System5. Software Architecture6. What’s missing (future work)

Page 21: Machine Reasoning about Anomalous Sensor Data

To Be Done• Distributed Sensor Reasoning Systems• Integrate with a stronger observations

ontology such as OBOE Ontology from SEEK

• User Interfaces for Rules • Investigate scalability and performance of

large sensor data sets.• Integrate with our existing SOS server• Collaborate with others

Page 22: Machine Reasoning about Anomalous Sensor Data

Summary

• Software System to test domain knowledge hypothesis about Sensor Data•

Page 23: Machine Reasoning about Anomalous Sensor Data

Thanks. Any Questions?

Page 24: Machine Reasoning about Anomalous Sensor Data

Key Components

Ontology

Rules

Software – Jena framework