Jean-Claude Bradley presents on "SMIRP: Effective use of a self-evolving database for information capture and retrieval in an R&D environment" on August 14, 2002 at the Barnett International Conference on Laboratory Notebooks. Specific implementations of integrating human and automated workflows in chemistry and nanotechnology applications are detailed.
6. Two approaches to the development of databases
Communicate
anticipated
need
Design
database
structure
Let database structure
evolve
through useSMIRP
http://smirp.drexel.edu
7. Fundamental Information Representation in SMIRP
Module 1 Module 2
Parameter 1
Parameter 2
Parameter 4
Parameter 5
instance
Record 1
instance
Record 2
http://smirp.drexel.edu
(People)
(Name)
(Employee of)
(Company)
(Name)
Parameter 3(email)
(Address)
Bill Gates Microsoft
8. Case-study:
Evolution of SMIRP structure in a chemistry laboratory
Location Drexel University
Department of Chemistry
Users faculty, undergraduate students, graduate
students, librarians and other university
personnel
Period Feb 1999 – April 2001, with a detailed focus on
last 7 months (Sept 2000-April 2001)
Total accounts (last 7 months) 78
Active Accounts (added records) 50
Administrators (changed database
structure)
9
http://smirp.drexel.edu
10. Most Active Knowledge Processing Modules
Journal 9%
Knowledge
Filter 3%
Reformat
Reference
requests
20%
Find
Reference
66%
Publisher
Document Production
Reference Processing
Parameter Correlation
Data source files
Experimental Conclusion Generation
Knowledge consolidation
http://smirp.drexel.edu
11. Most Active Laboratory Modules
Preparation of Silver rods for SCBE
TEM Micrographs Of Pd on C
SCBE on membranes
Hydrogenation of Crotonaldehyde using Pd Catalysts
Reduction of Methylene blue by Pd
Metal Particles in a Field
Electrodeposition of
Pd on Graphite
29%
Protocol Prototyping
25%
Pd onto Carbon
Nanofibers
17%
Electroless plating
on Membranes
9%
Synthesis of Pd catalysts
by Bipolar electrochemistry
5%
TEM Micrographs
Of Pd on C
3%
Pd particle size
analysis using TEM
3%
http://smirp.drexel.edu
13. Most Active Maintenance Modules
SMIRP
Problems
22%
Orders
19%
Invoice (TEM/SEM and
other instrument charges)
19%
Laboratory
materials
16%
Vendor
15%
Order
forms
9%
http://smirp.drexel.edu
14. Activity Analysis by Category over Time
2000-10-3
2000-10-17
2000-10-30
2000-11-12
2000-11-25
2000-12-8
2000-12-21
2001-1-3
2001-1-16
2001-1-30
2001-2-12
2001-2-25
2001-3-10
2001-3-23
2001-4-5
2001-4-18
Maintenance
Human Resource Management
Laboratory Work
Knowledge Processing
0
1000
2000
3000
4000
5000
6000
7000
8000
http://smirp.drexel.edu
15. For agents to make a decision to:
ACT NOT ACT
Generally for quality controlExpected information:
Retrieve details and execute
from a menu of predefined tasks
Unexpected information:
Redesign tasks
This could be absence of information:
“No News is Good News”
WHY retrieve information?
16. Active
Passive
Negative
(implied)
Pre-emptive
I want to know something
NOW
Keep me updated
regularly with new
information
No news is good news
Tell me things I
SHOULD
want to know but have
not asked for
Burden
on Agent
Highest
Lowest
Are your closest family
members alive?
A competitor has
initiated research in
my market space
New experiments in a
particular project
Obtaining a phone
number
Description ExampleMode
HOW Agents Retrieve Information
27. Passive Information Retrieval: Email Alerts
Space Level Module Level
All Activity
New Entries
When link to article has been found
Monitor progress of software
development
Keep track of which software
version users have downloaded
Monitor which experiments are
being investigated
Keep track of special users:
Job applicants
Former users
Collaborators
Updates on report or article being
written
(general) (specific)
New activity related to keywords
Quality control of autonomous
agent activity
Quality Control of workflows
38. Leveraging and Extending Bot Implementation
Citation bot in other laboratory research and teaching spaces
In online class SMIRPspace: Plagiobot System
Automatic Content Summarization Tools
Analysis/verification of experimental data analysis
Conversion from Passive to Negative Information Mode:
Bot Monitoring of other Bots
Monitoring of competitor/collaborator activity (patents/papers)
Automatic Keyword Generation from most frequently
used or read words
39. Conclusions
This is still a “Human World”
SMIRP can serve as a framework to allow Human and
Autonomous Agents to operate freely within a
Laboratory Research Collaborative Space
Automation within workflows can be accelerated by
creating Autonomous Agents that are more Human-
like in how they retrieve and store information