Our Products
and Services

Data Mining:
What is it?
Who uses it?
In engineering &
  manufacturing

In financial services

Enterprise Risk Management

We have used Data Mining to solve engineering problems such as:

Control of anti-lock braking systems.
We developed adaptive control systems to learn what the road conditions were under all four wheels of an automobile during a panic stop. The system then sent appropriate control signals to the anti-lock braking system and the four wheel steering system that were able to safely bring the vehicle to a stop. This was an amazing system in that the whole process of learning and control took place in a small fraction of a second. This system is currently being tested on vehicles in Detroit. It should make cars much safer than they are currently.

Control of chemical plants.
We developed a patented method for adaptively learning the status and operating condition of a chemical plant, and we were able to control the output of the plant even if the plant entered into runaway regimes. This was a first for the chemical industry. Du Pont estimated the potential savings to be $500 Million per year if these methods were implemented throughout the company. We generalized this technique and applied it to the manufacture of integrated circuits, which experience some of the same difficulties as chemical plants. This allows the industry to build larger and faster chips.

Capture and codification of expert battlefield information.
We used these techniques as part of a command and control system for tank commanders. This helps reduce the confusion inherent in battlefield situations.

Traffic monitoring
We built systems that could classify vehicles into 13 different categories from standard road sensors. This significantly reduces the cost of transportation planning.

Control of high-energy accelerators.
We developed an adaptive system to automatically control the performance of a high energy particle accelerator. The purpose was to prepare the accelerator for operation in space.

Monitoring drowsy drivers.
We developed a system that analyzes data from an array of sensors, to determine when truck drivers are in danger of falling asleep, and alerts them in order to prevent accidents.