acm-header
Sign In

Communications of the ACM

ACM TechNews

Algorithm Helps Analyze Images to Improve Health Care, Manufacturing


View as: Print Mobile App Share:
The researchers said the new methodology can improve predictive models for the quality of ultra-precision machined surface finishes to enhance the quality of manufacturing.

Researchers in the Penn State College of Engineering have developed a novel algorithm to help humans to recognize and analyze patterns in both natural and human-made systems.

Credit: Hui Yang, Soundar Kumara

Researchers at Penn State University have developed an algorithm that makes it easier for humans to recognize and analyze patterns that appear in both natural and manufactured systems.

The team focused on understanding patterns in nonlinear, dynamic systems, because these are especially difficult as they fluctuate over multiple dimensions and are nearly impossible to understand via human observation.

The researchers created the algorithm by analyzing spatial data in complex microscopic images produced by ultra-precision machining (UPM).

The spatial data showed a variety of surfaces over the UPM images, ranging from flat to rough to severely rugged.

The algorithm allowed the surface roughness to be approximated, resulting in cost savings and resource conservation.

Said Penn State researcher Hui Yang, "You can use this algorithm on complex-structured data that is measurable or observable and is represented in two-dimensional, three-dimensional, or high-dimensional images."

From Penn State News
View Full Article

 

Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account