The Center for Advanced Knowledge Enablement (CAKE) studies the representation, management, storage, analysis, search, and social aspects of large and complex data. The research is applicable to many fields including biomedicine, defense, disaster mitigation, homeland security, environmental science, real estate, health records management, finance, and technology service. CAKE faculty members carry out research in performance studies, benchmark evaluations, and the application of novel algorithms, routines, data models, network analyses, and software tools to large-scale datasets.
Unprecedented volumes of data have been generated by the explosive growth in the number and resolution of sensors and scientific instruments, in the number of enterprise and scientific databases, and in the volume of internet traffic and activity. The frameworks, metadata structures, algorithms, datasets, and search and data-mining solutions being used to manage the volumes of data are largely ad hoc. The research being carried out in this area and more broadly in information technology underpins advances in virtually every other area of science and technology and provides new capacity for economic productivity.
Application of common machine-learning algorithms for use cases in auto industry
This project leverages machine learning and JM Family Enterprises' data sources to enable better decisions and smart actions in identified business domains and use cases. Currently, machine learning is not used in these targeted areas even though the potential benefits may be significant.
Automatic asset identification in data centers
CAKE developed an innovative solution for visual asset identification using visual features of an image. Visual features of asset images are computed using complex mathematical methods. These visual features are used to identify and match asset images.
Brain research: instrumentation, neuroimaging, and curative protocols for neurological disorders
This project develops multimodal imaging designs for diagnosis and curative/therapeutic interventions, integrating hardware designs with software algorithms that exploit space and time alignments, as well as multidimensional pattern classification and decision schemes.
Driver's drowsiness detection system
CAKE has developed and implemented a driver-drowsiness detection system based on visual input, such as the driver's face and head. CAKE's innovative algorithm combines software components for face detection, and the classification algorithm for the eye state (open versus closed eyes).
Geospatial monitoring of moving objects
This research involves TerraFly moving object and sensor modules enabling cloud storage and map-synchronized playback of videos and stills recorded by moving cameras (mounted on a car or airborne), real-time geolocated streams, tracking, navigation, and simulation of moving objects.
Gesture recognition for augmented and virtual reality
This research project develops methodologies for comprehensive, real-time gesture detection that uses multitouch inputs and is capable of additional inputs, such as motion- and vision-based systems.
Medical image analysis using deep-learning techniques
There are many relevant open problems in medical imaging for which the human expert (e.g., physician, radiologist) could benefit from intelligent tools, implemented using the latest trend in artificial intelligence, which CAKE is researching: deep-learning methods.
Modeling garage parking
CAKE is proposing a system that will recommend available parking in controlled-access parking sites to individual drivers. The system will offer real-time and predictive advice on which parking garage and which area of that garage to park in.
System for early melanoma detection
CAKE's system can detect melanoma early. Melanoma, also known as malignant melanoma, is a type of skin cancer caused by abnormal multiplication of pigment-producing cells. When left undiagnosed, melanoma is a particularly fatal form of skin cancer.
Travel assistance for people with disabilities
CAKE is studying the feasibility of designing and developing an automated, human-assisted transportation concierge system that would provide pre-travel and en-route traveler guidance, recommendations, and concierge services. The system would be designed for people with cognitive impairments, low vision, hearing impairments, or mobility impairments.