Post on 01-Jan-2016
Engineering Computing and Informatics
Engineering Informatics Group (EIG)
Students: Charles Heenan (Law School), Jie Wang (CEE), David Liu (EE/CS), Jerome Lynch (CEE/EE),
Shawn Kerrigan (CEE/CS), Gloria Lau (CEE/CS), Jim Cheng (CEE/CS), Bill Labiosa (CEE),
Yang Wang (CEE), Arvind Sundarajan (EE), Urmi Holtz (Math/SCCM), Haoyi Wang (CEE/CS),
Xiaoshan Pan (Arch/CS)
Research Engineer: Jun Peng Consulting Faculty: Charles Han (Autodesk, Inc.)
2
Distributed Engineering
Services
System Sensing,
Monitoring and Control
Scientific Computing
Information Management and Retrieval
Current Research Topics
3
Current Research
I. Scientific Computing
Current Focus: Parallel, Distributed and Internet Computing
• Software Paradigms: SPMD, Task- and Component-based Computing, , ….
• Numerical Methods: Sparse Solvers, Generalized, Quadratic and Perturbed Eigenvalue Problems, ….
• Computational Engineering: Finite Element Computing, Linear and Nonlinear Problems, Structural Dynamics and Earthquake Engineering, Device Simulation
(Students: Urmi Holz, Jun Peng, Yang Wang)(Collaborators: Gene Golub, Ahmed Elgamal, Frank McKenna, Greg Fenves)
4
Linear Solver, Eigensolver
(Finite Element Analysis Core Program)
5
Current Research
II. Distributed Engineering Services(Mobile, Web and Ubiquitous Computing)
Current Focus: Internet and Wireless Enabled Collaboration
• Middleware Infrastructure: Software Mediators, Communication Technologies, ….
• Service Integration: Access Language, Product and Process Modeling, ….
• Project and Workflow Management: Facility Design, Construction and Operations, ….
(Students: David Liu, Jim Cheng, Pooja Trivedi)(Collaborator: Gio Wiederhold)
6
Distributed Engineering Application Services
Distributed Engineering Service and Integration Communication Devices
Mediators (content and access), DBMS, Information Exchange and Software Integration
(PSL, IFC, XML, SOAP, .NET)
7
Current Research
III. System Sensing, Monitoring and Control
Current Focus: Wireless Structural Monitoring System
• Technologies: MEMS, Wireless Systems, Microprocessors, ….
• Data Processing and Communication: Embedded Computing, Synchronized and Asynchronized Communication, ….
• Engineering Applications: Structural Damage Monitoring, Damage Assessment and Prognosis, Structural Control….
(Students: Jerome Lynch, Arvind Sundarajan)
(Collaborators: Anne Kiremidjian, Tom Kenny, Ed. Carryer, Chuck Farrar, Hoon Sohn, and others)
8
Wireless Sensing Device
• Off the shelf components used
• Size is about 4”x4”x1.5”
• Component Cost is about $400
9
Dynamic Vehicle Test
0 1 2 3 4 5 6 7 8 9 10
-0.1
0
0.1
Time (sec)
Acc
eler
atio
n (g
)
Response of Alamosa Canyon Bridge to Van Excitation (Los Alamos Lab System)
Piezotronics PCB336A @ 320 Hz
0 1 2 3 4 5 6 7 8 9 10
-0.1
0
0.1
Time (sec)
Acc
eler
atio
n (g
)
Response of Alamosa Canyon Bridge to Van Excitation (WiMMS System)
Crossbow CXL01LF1 @ 244.14 Hz
0 5 10 15 20 25 3010
-3
10-2
10-1
100
101
Mag
nitu
de
FRF of Alamosa Canyon Bridge to Modal Hammer
Frequency (Hz)
LANL PCB336 WiMMS CXL01LF1
10
Current Research
IV. Engineering Information Management(Collaborators: Gio Wiederhold, Barton Thompson, Jim Leckie, Charles Han)
Current Focus: E-Government, Regulatory Information Management and
ComplianceDisabled Access (ADAAG, Title 24)Environmental (40 CFR)• Information Management: Document Management,
Information Retrieval and Access, ….• Public Access and Engineering Application Supports:
Facility Planning, Design, Operations, Conformance Assistance ….
(Students: Shawn Kerrigan, Gloria Lau, Charles Heenan, Bill Labiosa, Haoyi Wang, Xiaoshan Pan)
11
Online Code Compliance
Checking
Virtual Simulation
12
13
REGNET: An Infrastructure for Regulatory Information Management and Compliance Assistance
Kincho H. LawProf., Civil and Env. Engr.
Jim Leckie
Prof., Civil and Env. Engr.
Barton Thompson
Prof., School of Law
Gio WiederholdProf., Computer Science
Shawn KerriganBill Labiosa
Gloria LauHaoyi Wang
Jie WangCivil and Env. Engr.
Pooja Trivedi Li Zhang
Liang Zhou(former students)Computer Science
Charles HeenanResearcher, Law Student
Stanford University, Stanford, CA 94305
14
The Public and Scientific Problem
• Regulations are established to protect the public• Regulations constrain businesses’ actions• Many organizations participate to set and use regulations• Interpretation of regulations is costly and inconsistent
• Regulations are voluminous, often incomplete, sometimes conflicting
• Regulations are written in natural language• The objects and interests being regulated are often encoded• Many sources of supportive documents – interpretative
documents, guidelines, etc..
15
MotivationThe complexity, diversity, and volume of
federal and state regulations:• Require considerable expertise to understand• Increase the risk of companies failing to comply
with environmental regulations• Hinder public understanding of the government
How would IT help• to make “applicable” regulations easily
accessible? • to assist parties involved in regulation
compliance?
16
REGNET Research Goals
• Research questions
– What is an appropriate model for a information management system for compliance assistance?
– How to build such a system
– How to deal with the conflicting objectives?
• Research goal
– Developing information management frameworks that can facilitate public access to regulations, improve the efficiency of regulation compliance and facilitate the compliance process.
17
• Repositories: Infrastructure for online repository of regulations and translating texts into processable form and facilitate access
• Access Tools: Access of the regulation text and related information
• Ontology Development: Formalize terms and meanings to help development of logical rules about relationships in the regulations and among the different regulations
• Integrated Access: Retrieval of regulations based on the content or relationships between the regulations
• Analysis Tools: To validate and improve the quality of the ontology and to check the content of regulations within a domain or across different domains of federal, state and local regulations.
• Compliance Checking Assistance: To develop the means to interface the regulations with usage.
Research Tasks
18
Establishing Concepts and Classification Structure
Original Documents(pdf,html)
TextCategorization
(Semio)
Concepts andClassificationin Documents
Documents with
Concept Tags
Document
Program
Concepts of InterestsAnd Rules
19
Home page (http://eil.stanford.edu/regnet/)
20
Establishing Classification Structures
21
Classification Structures(EPA List of Extremely Hazardous Substances)
22
Classification Structures (cont’d)
23
Classification Structures (cont’d)
24
Displaying Context using Semio
25
• Developed a hierarchical structure to organize documents
• Regulations structured using XML• Methodology developed to classify documents for
different purposes with a singled repository• Included a variety of documents – guidelines,
background information, etc… • Developed a logic-based compliance assistance
methodology and prototype• Integrating compliance assistance with document
repository
Current Features of REGNET
26
27
28
Document Repository and Access
XMLRegulation
HTMLRegulation
AddConcepts
RegulationDocuments
Semio
XML Regulation With Concept
Tags
Parser
Concept List
29
Regulatory Compliance Assistance
Shawn Kerrigan
Engineering Informatics Group
Stanford University
30
Background• Current state of compliance checking:
• Paper-based process• Locating and interpreting the relevant regulations is
complex, even with the help of supplementary information
• Small companies have difficulty conducting compliance checks due to lack of resources and knowledge
• Vision for future:• Up-to-date regulations and compliance-checking
assistance procedures available online• Improved regulation and compliance-requirement
transparency through clear presentation and linking
31
Research Questions
• How can we make the information and rules more accessible?
• How can we represent the information and rules in environmental regulations in a computer interpretable format?
• How can we structure this information to assist with regulation compliance checking?
32
General Approach
• Information Integration• Formalization of meaning and relationships• Regulation-centric• Tie the information to the appropriate
portion of the regulation
33
Regulation Assistance System (RAS)
• Provides a unifying web interface for the regulation documents and meta-data
• Demonstrates the usefulness of XML structured regulation documents with meta-data
• Works with a logic-based compliance-checking assistance system to demonstrate web-based regulation services
34
Regulation Parsing
• Need to transform plain text/PDF regulations into XML
• Can structure the XML to represent the hierarchical structure of the regulation
35
HTML to XML Regulation Parsing
XMLStructuredDocument
36
Regulation Parsing§ 279.12 Prohibitions.
(a) Surface impoundment prohibition. Used oil shall not be managed in surface impoundments or waste piles unless the units are subject to regulation under parts
264 or 265 of this chapter.
<regElement id = “40.cfr.279.12” title = “Prohibitions”> < regElement id = “40.cfr.279.12.a” title = “Surface Impoundment prohibition”> <regText>
Used oil shall not be managed in surface impoundments or waste piles unless the units are subject to regulation under parts 264 or 265 of this chapter.
</regText> </regElement></regElement>
37
Adding Meta-Data to Regulations
Regulation taggedwith meta-data
Add LegalInterpretation
Reference Extraction
Add LogicalInterpretation
Add Concepts
Original XMLdocument
Document
Program
38
Parsing ReferencesPART 279—Standards For The Management Of Used Oil
Subpart B – Applicability
…§ 279.12 Prohibitions.(a) Surface impoundment prohibition. Used oil shall not be managed in surface impoundments or waste piles unless the units are subject to regulation under parts 264 or 265 of this chapter. (b) Use as a dust suppressant. The use of used oil as a dust suppressant is prohibited, except when such activity takes place in one of the states listed in § 279.82(c).(c) Burning in particular units. Off-specification used oil fuel may be burned for energy recovery in only the following devices: (1) Industrial furnaces identified in § 260.10 of this chapter; (2) Boilers, as defined in § 260.10 of this chapter, that are identified as follows: (i) Industrial boilers located on the site of a facility engaged in a manufacturing process where substances are transformed into new products, including the component parts of products, by mechanical or chemical processes; (ii) Utility boilers used to produce electric power, steam, heated or cooled air, or other gases or fluids for sale; or (iii) Used oil-fired space heaters provided that the burner meets the provisions of § 279.23. (3) Hazardous waste incinerators subject to regulation under subpart O of parts 264 or 265 of this chapter.
§ 262.11 Used Oil Specification.…..
39
<regText>(a) Surface impoundment prohibition. Used oil shall not be managed in surface impoundments or waste piles unless the units are subject to regulation under parts 264 or 265 of this chapter.</regText>
Before:
<regText>(a) Surface impoundment prohibition. Used oil shall not be managed in surface impoundments or waste piles unless the units are subject to regulation under parts 264 or 265 of this chapter.</regText><reference id = "ref.40.cfr.264" /><reference id = "ref.40.cfr.265" />
After:
Parsing References
Original XMLdocument
XML withReference List
Reference Extraction
40
What is a “Concept”?
• Examples:– emission requirement
– leaked hazardous substance
– disposal of solvents
– principal hazardous constituent
• Why are they useful?– identify similar regulations even when they do not
reference each other
– provide a “context” for the regulation provision
41
Regnet Taxonomy
42
Tagging with Concepts
<regText>Used oil shall not be managed in surface impoundments or waste piles unless the units are subject to regulation under parts 264 or 265 of this chapter. </regText>
<regText>Used oil shall not be managed in surface impoundments or waste piles unless the units are subject to regulation under parts 264 or 265 of this chapter. </regText>
<concept name = “waste pile” /><concept name = “surface impoundment” />
43
XML Embedded Logic
<logic_sentence> all _o (usedOil(_o) -> -(dustSuppressant(_o))).</logic_sentence>
Rule logic represents the rules specified by the regulation:
40.CFR.279.12.b – Use as a dust suppressant:
“The use of used oil as a dust suppressant is prohibited…”
Option elements define the user interface:<logic_option> <question> Is the used-oil used as a dust suppressant? </question> <logic_opt answer = "yes"> (usedOil(oil1) & dust_suppressant(oil1)). </logic_opt> <logic_opt answer = "no"> (usedOil(oil1) & (-(dust_suppressant(oil1))). </logic_opt></logic_option>
Control statements specify processing instructions for compliance-checking:<control> <goto target = “ref.40.cfr.279.65” /> <switchTo target = “ref.40.cfr.279.73” /></control>
<control> <end target = “ref.40.cfr.279.12” /></control>
44
XML-based Regulations
Additional Input Files
Interactive User Input
Regulation Compliance
Decision
Logic input file Found proof / no proof found
RASweb•Provides web interface
•Displays regulation information
RCCsession•Implements compliance checking procedure
User input Results / requested information
RAS System Structure
* Otter is an automated-deduction program developed by William McCune at Argonne National Laboratory
Otter*
•Attempts to find proof by contradiction from input file
45
Regulation Assistance System
Demonstration Session
• Display regulations with meta-data• Compliance example• Non-compliance example• Use of control elements• Use of “I don’t know” to check multiple paths
46
Summary
• Can decompose regulations into a structured XML document
• Adding rich meta-data about regulations enables more sophisticated interaction with the documents
• Automated assistance with environmental compliance-checking may be possible
47
Similarity Analysis (Ms. Gloria Lau)
measurements
exceptions
definitions
author-prescribed
indices
glossary terms
feature matchingbase score
near-tree refinement
refined score
reference distribution
final score
Similarity Analysis Core
trash belowthreshold pairs
Conflict Analysis Corepart-of-speech tagger
list of senses:(1) flush, adj: => even (vs uneven) => rich (vs poor)(2) lip => edge(3) beveled => inclined(4) transition => passage
WordNet
knowledge engineer
section matcher
machine-generated
rules
human-generated
rules
conflicting pairs
refined XML regulations
related pairs
48
Similarity analysis core• Our goal
– Suggest to the user a ranked list of related provisions
– Sieve out below threshold pairs for conflict analysis
• Assumption: conflicting sections are similar
Measure Similarity score f(secA, secU) 0..1
secA and secU are sections from two different regulation trees
49
Preliminary results
• Based on concept match and similarity scoring • ADAAG vs UFAS (Very similar documents)
ADA4.1.6(3)(d) Doors(i) Where it is technically infeasible to comply with clear
opening width requirements of 4.13.5, a projection UFAS4.14 Entrances4.14.1 Minimum NumberEntrances required to be accessible by 4.1 shall be part of an
accessible route and shall comply
50
4.13 Doors 12.5.4 Doors
4.13.9Door Hardware
12.5.4.2Door Furniture
12.5.4.14.13.1
4.13.3
4.13.2
4.13.12
UFAS BS8300
parent
sibling
UFAS 4.13 Doors4.13.1 General…4.13.9 Door HardwareHandles, pulls, latches, locks, and other operating devices on accessible doors
shall have a shape …4.13.12 Door Opening ForceBS8300 12.5.4 Doors12.5.4.1 Clear Widths of Door Openings12.5.4.2 Door FurnitureDoor handles on hinged and sliding doors in accessible bedrooms should be
easy to grip and ….
51
Thank You!
Questions?
52
Discussion Questions
• How will such a system be useful?
• What are examples of how you could use such a system?
• What would make the system more useful?
• Do you have suggestions for people/fields we should contact that might be interested in what we are doing?
• How are the problems addressed currently dealt with?
• What are some existing technologies we should investigate?
• What are recommendations for issues we should address?
• What might be complementary tools to develop next?