The AOLME project has demonstrated successful implementation of an integrated curriculum for teaching computing foundations based on middle-school mathematics. Current educational research is focused on the development of learning models to understand how students acquired computing knowledge by participating in the project. Current engineering research is focused on the development of automated video analysis methods to support the development of the learning models.
Multidimensional Amplitude Modulation - Frequency Modulation (AM-FM) representations provide non-stationary representations of image and video content. AM-FM representations capture unique image and video features that can lead to exciting applications in image and video analysis (e.g., in computer aided diagnosis).
This is an interdisciplinary effort -from faculty with areas of expertise in bilingual education, mathematics education (Prof. Sylvia Celedón-Pattichis and Prof. Carlos A. LópezLeiva), and electrical and computer engineering (Prof. Marios Pattichis and Dr. Daniel Llamocca)- designed to support interactive and visual learning in engineering and mathematics of middle school students, especially from underrepresented groups.
DRASTIC is focused on the development of adaptive video processing systems that can change in response to content, their environment, or user needs. The DRASTIC platform allows changes in both the software and the hardware that is used to process the videos.
By developing hardware architectures for specific signal, image, and video processing operations, it is possible to achieve very high performance while reducing power requirements. There is strong interest in developing efficient architectures for computing fast convolutions and implementing 2D filterbanks for real-time video processing applications. Also refer to the DRASTIC project for related research.
Over the years, the lab has contributed signal and image analysis components of several projects in computer aided diagnosis (CAD). A summary of CAD projects includes: stroke ultrasound image analysis, brain image analysis, hysteroscopic image analysis, eye image analysis, biomedical signal analysis, chest radiograph image analysis, and electron microscopy image analysis.
Solar image analysis research requires the development of reliable coronal hole segmentation methods that are validated by manual segmentations from at-least two different independent experts. UNM developed the manual segmentation software that was used for validation of automated segmentation methods. UNM senior design teams have and continue working on a WebApp to support manual segmentations from a large number of users. Current research is also focused on developing matching algorithms for driving physical models from accurate coronal hole detection from solar observation images.
We are very interested in finding commercial partners to help commercialize our research.
Please do not hesitate to contact us to discuss potential partnerships. We are eager to help!
official email: firstname.lastname@example.org
phone: (505) 277-0486