7. We collect enough data.
We need to focus on
1- connecting
2 – identifying patterns
3- giving confidence level
Multiple data sources:
Books
Experts in the field
Information systems
Tests and surveying
Data repositories
Real time sensors
8. Data quality
• Processing is cheap and access is easy, the
big problem is data quality.
• Considerable research but highly
fragmented
9. Classic definition of Data Quality
• Accuracy
– The data was recorded correctly.
• Completeness
– All relevant data was recorded.
• Uniqueness
– Entities are recorded once.
• Timeliness
– The data is kept up to date.
• Special problems in federated data: time consistency.
• Consistency
– The data agrees with itself.
10. Finding a modern definition
• Data quality must
– Reflect the use of the data
– Lead to improvements in processes
– Be measurable
• No silver bullets: Use several data quality
metrics.
11. What is the problem to solve?
• Do you have a bunch of data and want to:
– Estimate an unknown parameter from it?
• True rainfall based on radar observations?
• Amount of liquid content from in-situ measurements of
temperature, pressure, etc?
• Regression
– Classify what the data correspond to?
• A water surge?
• A temperature inversion?
• A boundary?
• Classification
• Regression and classification aren’t that
different 11
12. Case 1: Neural networks for flood
• Neural networks modelling of the rainfall-runoff
relationship
• No physical model, just data driven model.
• Result: flow forecasting
13. Case 1: Neural networks for flood
• Input: several past rain gauges
and flow gauges
• Result: Flow model
14. Case 1: Neural networks for flood
Training with 1st (larger) set of data
15. Case 1: Neural networks for flood
Verification with 2nd (smaller) set of data
17. How can IT help in maintenance ?
• Information Technology has also found applications in
post commission period of the project.
• IT can provide easy access to various statistics, drawing
& various other data concerning the project.
• Self check tools can identify the problems in various
systems like fire fighting, air conditioning & can
automatically inform concerned service provider.
• IT can also help in prompt reporting of problem & its
rectification.
18. Case 2: Bridge Management Systems
• Double click on the
icon on your desktop
– Introductory screen is
displayed
– Click OK button to
continue to the Data
collection form
Page 18
20. Bridges in the U.S.
25% are structurally or functionally deficient
according to ASCE
140000
120000
100000
80000
60000
40000
20000
0
Pre-1909
10s
20s
30s
40s
50s
60s
70s
80s
90s
Bridge Construction by Decade
21. Case 2: Bridge Management Systems
Typical BMS Expectations
A tool to evaluate:
• Bridge condition and serviceability
• Implications of project decisions
• Priorities and schedules
• Expected budget
• Cost of alternative standards
• Value of preventive maintenance
24. Desktop PCs are idle half the day
Desktop PCs tend to be active But at night, during most of
during the workday. the year, they’re idle. So
we’re only getting half their
value (or less).
24
25. Finally ,
it is argued that IT can readily be
used by civil engineers given the low
capital investment levels required.
The “only” requirement is investment in
education among the civil engineers &
recognition of the enormous potential
lying beneath.