Presentation on CenSCIR seminar

Today I gave a talk on the graduate seminar of CenSCIR, which is a research center about the application of sensor network for infrastructure management. I talked about my Bombardier research project, which is about using laser scanning technology for civil engineering system geometric defect detection.

I got a lot of feedback from faculty members from other research areas and students from other disciplines, that is a very good experience.

Matt talked about the scanner height and asked whether the height of scanner matters, Omer said something about generate 3D depth information from two cameras instead of using a scanner.

Ideas about stuff organization

I really need to organize two groups of my stuffs from now on:

1. The programs I have written: I need to design an architecture for my codes now since I have accumulated a bunch of codes and it is time consuming to find some codes when I need them. If I designed a architecture, separate foundation classes and client codes, create a framework, then I will know which code I have already developed and which I need to implement for saving time for future research.

2. The documents of previous research. Since I have so many documents accumulated and I have put most of them in my weekly notes directories. I need to look over those documents and try to summarize them into technical reports so that I will get more sense about what I have done and where I am in the whole research process. Summarizing those stuffs will also provide me an opportunity to rethink about my research and save time for future research once I need some stuff which I have created. If I did not archive those stuffs, some of them may be lost and in them future I need to redo some work. That is too bad.

To do regarding these two tasks:

For code:
1. Create a functionality requirements of codes based on my understanding about the research.
2. Design an architecture based on the functionality requirements;
3. Place my previous codes to a proper place in the architecture, and improve program documentation when necessary, so in the future, other people need to use my code for their research will benefit from it;
4. Develop a to-develop list and start to work on my tool for research, and keep on updating the architecture when necessary, and accumulate code in a systematical way;

For stuffs:
1. look over previous research notes and classify them according to my "type_time_project_description" template;

2. Grouping related stuffs and develop a list of tentative research report titles. that is a framework for all the works I have done and want to do;

3. Give each report a proper code and manage all my stuffs according in the units of "report";

4. Continue my work according to the framework structured by a number of reports and accumulate the works in a systematical manner;

Geometric Decomposition: IFC? COmponent Based?

Chris Gordon used component-based approach to represent inspection goal for developing inspection plans, but I find that is not a valid approach for inspection goals involving multiple components such as under-clearance of a bridge.

Is IFC's geometric representation good enough for bridge component recognition from 3D point clouds? since I am thinking about a way to represent the relationship between primitives and semantically meaningful objects. IFC represent a component's geometry, so I think I can develop geometric template based on IFC's approach. And the use the semantic relationship in IFC to develop a valid representation for geometric inspection goal involving multiple bridge components.

Data Visualization

Finally I have reduced the size of my IABSE 2007 paper within 8 pages. Hopefully this will be my first paper published on a influential conference and a good start for my academic career.

So what is today's new idea? Well, yesterday I read some slides on the TRB web page. That presentation is talking about highway safety. One thing impressed me is that they are trying to visualize the safety status of highways: red means dangerous, white means pretty safe. I do not know any details about how they define the safety level of a section of highway, but I find that data visualization is such a simple and effective way for data interpretation and information management.

We can generate a map labeled by the accident rate, and another map labeled with the population density, the curvature of the road etc. Then we can compute the correlation of accidents and various factors using these labeled maps. In my mind, those maps are images and can be processed by any image processing techniques and pattern classification algorithms for data interpretation. I do not know whether this is data mining and knowledge discovery, but I think image processing will be a powerful tool for us to digest huge amount of data and find patterns and knowledge hiding behind them.

Accident map can have different views. We can classify the accidents into several categories according to a specified taxonomy, and we can even compare different taxonomy based on the generated image and its processing results: a better taxonomy will generate images which can explain existing phenomenons and predict some accident correctly. We can also have hierarchy of the visualization: high level taxonomy can generate high-level images shows high-level trends and sub-taxonomy can zoom in to a specific level and view the data in a specific perspective.

These maps will be very useful for accident reducing since people can use it to guide better transportation planning, drivers can use it to generate a "safer path" based on the start point and the target information. Transportation agencies can use it to manage transportation system maintenance and replacement, and they can also provide guidance to drivers so that keep the traffic on deteriorated highway at a low level.

Visualization, such a good idea!

The link of that presentation is:
http://www.trb.org/conferences/e-session/2007am.htm#DATA

Idea of today

Knowledge language for civil engineers so that people can formalize the drawings, engineering knowledge and construction documents to efficiently extract information from thousands of engineering documents with the help of existing knowledge.

Knowledge language represent the engineering knowledge, document are organized and labled using this language, then a knowledge engine will extract the knowledge or engineering data at a proper level of detail for engineers so that engineers can get what they want to know for making an important decision for bridge maintenance, for construction method selection, for construction schedule change management.

A new start

I met Huaiwei yesterday, and he talked about the trend of the science development and I am impressed by his ideas.

I have been focusing only on my own research topic and projects for such a long time and never care what is happening out there. However, as a scientist, it is not good to just work alone and just finish the work assigned by the boss, I must explore my own area and find my own passion. So from now on, I will post at least one new idea, or new discovery or new interesting thing to me, a new communication with others everyday. I need to actively communicate with other and outreach the outside world: organizations such as TRB, ACM are good place for me, so I will read the pulications actively and use the resources from these two organizations efficiently.

Today, I just wrap up everything of my past: finish the Bombardier report, finish editing my IABSE2007 paper, organize my notes and papers. In the next week, I will find one or two interesting books as a start point for my adventure.

As a scientist, I want to start at these points: first, classic mathematic logic; second, astronauts; third, geography; fourth, artificial intelligence.

Cheers, for my new start.

Diagnostics and Data Fusion of Robotic Sensors

One section of this paper talks about "geometric hashing" idea for object recognizing.