Artificial Intelligence

Artificial Intelligence

Artificial Intelligence (or AI for short) has three main components, sensing, computing and connectivity. FAU is incorporating all of these into engineering, medical and other areas of research and education.

[Sensing]

Sensors measure information about physical and sometimes virtual environments.

[Computing]

Computing leverages advancements in hardware, software, and algorithm design to solve increasingly complex tasks.

[Connectivity]

Connectivity aggregates the power of individual devices to create a whole greater than the sum of its parts.

What is Machine Learning?

Machine learning algorithms identify patterns, trends, and rules that are too complex for humans to see. But since machines do not learn like humans, these algorithms require a large amount of data to use as learning examples. Sensor systems are among the most useful data sources in constructing these examples.

What is AI?

Artificial intelligence mimics aspects of human intelligence, like learning. It is generated by giving computers step-by-step instructions known as algorithms. AI can take a digital form, like a chatbot, or engineers can combine it with robotics, sensors and wireless communication to create things like self-driving cars or package-delivering drones.

FAU already has significant expertise in place. Research at the Institute for Sensing and Embedded Network Systems Engineering (I-SENSE), for example, focuses on sensing the environment and interpreting that data with AI — the sort of technology that could enable self-driving cars to detect road conditions and navigate safely. Meanwhile, researchers in the college and across the university are developing and applying AI in many ways, even exploring its ethical implications.

The university is implementing new degree options for students, including a Master of Science with a major in AI, the first such degree in the state; a multidisciplinary Master of Science in Data Science and Analytics; and a joint degree that funnels students from the Harriet L. Wilkes Honors College to a Master of Science in Data Science.

Compared to its inspiration, the human brain, state-of-the-art AI’s capabilities are limited. The technology’s greatest potential arises when used within autonomous machines that work together — like self-driving cars optimizing traffic flow, or a swarm of drones re-establishing a wireless network after a disaster.

In addition, FAU’s Wimberly Library will soon be home to The Rubin and Cindy Gruber Sandbox, a 3,400 square-foot state-of-the-art artificial intelligence lab.

How will AI affect me?

AI is being referred to as the fourth industrial revolution because of the impact it will have on our daily lives ranging from medical to defense, communication and traffic. Examples include sensors that determine when your lawn needs water or fertilizer, thus helping conserve a dwindling fresh water supply. Traffic light sensors will communicate with cars … and cars will communicate with other cars, resulting in fewer accidents and less traffic congestion that improves your daily commute. You will soon be able to communicate from anywhere including underwater, underground and even in space.

Questions about AI

Will AI cost people their jobs?

While some jobs will be replaced by technology, others will be created. AI is most beneficial as an augment to existing jobs vs a replacement to human beings.

Where is AI being used most?

AI is being used in navigation apps like Google Maps, as well as in digital assistants like Apple’s SIRI and Amazon’s ALEXA. The AI is programmed with a database then “learns” as it is used.

What are the advantages of AI?

AI devices make fewer errors than humans. In some cases, where the task is repetitive, the error rate is exceptionally low. AI takes less time to search billions of options (seconds or minutes compared to years or not possible).

Environment

image of the wind turbines

-

Oscar Curet, Ph.D., and other researchers reinforced learning for navigation and coordination of bioinspired underwater vehicles in close formation - “A School of Robotic Fish.” The aim is to investigate optimal control mechanisms for robots that use fin-based propulsion. The goal is to implement an autonomous controller that would allow the robotic swimmer to perform high-level tasks such as station-keeping, trajectory-following or performing collaborative tasks in groups, especially in the presence of external disturbances. The novel aspect of the ongoing work is the ability of the robotic swimmer (and eventually, of swarms) to take decisions completely autonomously in order to attain a specified high-level goal. The range of potential applications include long-term environmental monitoring, deep water observation of aquatic animals, surveillance for coastal protection, and most-importantly, underwater search-and-rescue operations. The biggest benefit of using an autonomous controller is that individuals as well as swarms would be able to respond to unfamiliar situations and unexpected environmental disturbances. Autonomy is crucial since it may not be feasible for a human to monitor the robotic devices 24x7, or the time-delay in communication may be significant as is the case for underwater communication. Curet is an assistant professor in the department of Ocean and Mechanical Engineering in the College of Engineering and Computer Science.

Curet was awarded $500,000 from the National Science Foundation for the Bio-Inspired Underwater Vessels for Coastal Monitoring, Inspection and Station Keeping project.

Secure Communication

flat map of world with glowing white lines connecting continents

photo Xingquan “Hill” Zhu,Ph.D.

-

Xingquan “Hill” Zhu, Ph.D., a professor in the College of Engineering and Computer Science, uses AI to examine large sets of interconnected data — think of social media users linked by comments and likes. Based on these connections, Zhu builds a map, or network, of the data and uses it to make inferences and predictions. He and colleagues, for example, built a network representing clinical trials involving infectious diseases, mapping the connections between thousands of researchers and diseases. He plans to use it to predict which trials will terminate early. In another project, he developed AI to analyze health records to anticipate which hospital patients will be readmitted. He also works on detecting changes in data, like temperature, collected continuously by sensors. Zhu recently received a $652,850 grant from the National Science Foundation for his work in the Acquisition of Artificial Intelligence and Deep Learning (AIDL) Training and Research Laboratory.
photo Dimitris Pados Ph.D.

-

Dimitris Pados, Ph.D., is developing new wireless technology that allows a team of machines to communicate dynamically with no human intervention, even in problematic places such as underwater. The machines sense their environments, determine the most effective means to communicate and adapt to challenges. Pados is a professor in the College of Engineering and Computer Science, an I-SENSE fellow and director of the ExtremeComms Laboratory. The project, called All-spectrum Interference-avoiding Communications: Theory and Software-defined-radio Implementations, received a grant for $25,000 from the Air Force Research Laboratory.

-

Stella Batalama, Ph.D., the dean and professor of the College of Engineering and Computer Science, is designing a first-of-its-kind software-defined testbed for real-time undersea wireless communication that can be used for commercial, scientific and a variety of military applications; ranging from monitoring subsea machinery to disaster prevention. The software is designed to maximize flexibility and minimize form-factor and cost for modules of the undersea network. Batalama received a $500,000 grant from the National Science Foundation for the Cognitive Networking of the Oceans: Localization and Tracking Fundamentals project.

Intelligent Transportation

busses at bus station with city in background

Evangelos I. Kaisar

-

Evangelos I. Kaisar, Ph.D., is an expertise in freight, network modeling, sustainability and intelligent transportation systems. His work will help address critical issues affecting the operation and safety of freight transportation systems around the nation. Kaisar is an associate professor for the FAU Department of Civil, Environment and Geomatics Engineering, and the director of Multimodal Intelligent Transportation Systems Laboratory. Kaisar is funded with $1.4 million from the United States Department of Transportation (USDOT) for the Freight Mobility Research Institute project.

Cyberphysical Systems and Energy

image of Earth from space at night

Photo of Reza Azarderakhsh, Ph.D.

-

Reza Azarderakhsh, Ph.D., an assistant professor in the College of Engineering and Computer Science and an I-SENSE fellow, collaborated with the National Institute of Standard and Technology (NIST) to minimize attacks on quantum computers. His work is a part of the competition for standardization of post-quantum cryptography and it has been moved to the second round of evaluations.

-

Mehrdad Nojoumian, Ph.D., plans to integrate his knowledge and experience gained through research to into novel curricula of cryptographic engineering courses and provide independent research opportunities to students. He will also focus on efficient hardware and software implementations as well as side-channel investigations of quantum-safe candidates. Nojoumian is an assistant professor in the Department of Computer and Electrical Engineering and Computer Science.
Nojoumian was awarded $300,135 from the Army for his work with the Incentivizing Blockchain Miners to Avoid Dishonest Mining Strategies by a Reputation-Based Paradigm.

-

Hanqi Zhuang, Ph.D., lead author published in the Journal of the Acoustical Society of America, observes the reproductive cycle of fishes, including groupers using deep neural networks – a set of algorithms modeled after the human brain to classify grouper species by their sounds. Zhuang is an Associate Chair and professor in the Department of Computer and Electrical Engineering and Computer Science and in the College of Engineering and Computer Science.

-

Nurgun Erdol, Ph.D., developed an automated classification algorithm – Fish Acoustic detection Algorithm Research (FADAR), capable of identifying species of groupers in their natural environment with a classification accuracy. Erdol is a professor and Department Chair in the Computer and Electrical Engineering and Computer Science.

Emergency Planning and Resilience

image fire and rescue trucks

-

Laurent Cherubin,Ph.D., and other researchers, are developing a novel smart-sensing system that will remotely alert authorities of incoming manned and unmanned underwater vehicles. This new bio-centric Persistent Aquatic Living Sensors (PALS) technology will augment the United States Department of Defense’s existing, hardware-based maritime monitoring systems and greatly extend the range, sensitivity and lifetime of the military’s undersea surveillance capabilities. Cherubin is an associate research professor at FAU’s Harbor Branch Oceanographic Institute.
Learn More

Active Projects:

Emergency Planning and Resilience Projects

Cybersecurity

  • Detecting deep fake speech (in partnership with Los Alamos National Laboratory)

Mobile Phone Security

  • Kristen Crawford, Logan Arrandale, and William Hahn. All Ears: Can Ear Recognition Software be a Solution for Mobile Phone Security? 2019 First Place Cross-Disciplinary FAU Wave Undergraduate Research Award

Human Pose Analysis

  • Classifying criminal human behavior from skeletal key points with deep neural network

Healthcare Diagnostics and IT

model of human heart laying on top of an open book

photo Benhaz Ghoraani Ph.D.

-

Benhaz Ghoraani, Ph.D., has combined an algorithm with wearable motion sensors to monitor Parkinson’s Disease patients’ response to medication. With this information, it is possible to better adjust treatment to account for the progression of the disease. Ghoraani is an assistant professor in the College of Engineering and Computer Science, and a fellow of I-SENSE and the Brain Institute.

In addition, Ghoraani and other researchers, developed the first algorithm that can locate patient-specific ablation targets within the atria that does not require specialized catheters or 3D electro-anatomic maps of the heart. The new algorithm – the iterative catheter navigation (ICAN) – is fundamentally different from existing approaches.

Ghoranni was funded $259,426 from the National Institutes of Health for her work on the Catheter Guidance Algorithm for Identification of Atrial Fibrillation Ablation Targets.
photo of Taghi Khoshgoftaar in lab

-

Taghi Khoshgoftaar, Ph.D., is applying AI capable of learning to a number of medicine-related problems. His projects include testing a new tool to assess cognitive impairment associated with Alzheimer’s disease, and identifying Medicare fraud. He uses the National Provider Identifier (NPI) to match fraud labels the Medicare Part B data. This detection method is branching out to other types of fraud such as insurance, banking and finance. Khoshgoftaar is the Motorola Professor in the College of Engineering and Computer Science. He was awarded $73,266.70 for the Center for Advanced Analytics (Phase one).
photo of Stella Batalama

-

Stella Batalama, Ph.D., and researchers from FAU’s College of Engineering and Computer Science, Schmidt College of Medicine and FAU’s Harbor Branch Oceanographic Institute, received a grant from the National Science Foundation to establish the first NSF-funded Major Research Instrumentation Artificial Intelligence and Deep Learning (AIDL) Training and Research Laboratory in Florida. Hosted at the university, FAU’s AIDL laboratory will significantly advance FAU’s role in artificial intelligence and deep learning-based intelligent information analysis. Batalama is the dean of FAU’s College of Engineering and Computer Science.

Batalama received a $500,000 grant from the National Science Foundation for the Cognitive Networking of the Oceans: Localization and Tracking Fundamentals project.
photo of Michael Bergern, Ph.D.

-

Michael Bergern, Ph.D., lead author published in the American College of Sports Medicine’s journal, Medicine & Science in Sports & Exercise, uses his research to aide clinicians in developing individualized treatment for injured athletes. Bergern is the senior vice president of development and applications at SIOVTEC Analytics.
photo of Sara Landset

-

Sara Landset, co-author, examined data from the National Athletics Treatment, Injury and Outcomes Network (NATION) on 2,004 concussion incidents in 22 sports and found more than half of the concussions happened in American football. This research is part of a bigger effort to develop machine learning models to help diagnose, track and treat many brain issues. Landset is a doctoral student at FAU.

Active Projects:

Machine Olfaction (Emily Stark)

  • Melanoma detection from non-invasive gas sampling (in partnership with University of Warwick)
  • Deep-learning based classification for small datasets of high resolution data
  • Deep-learning investigation of VOC patterns as biomarkers of respiratory infections (in partnership with IMSPEX Corporation)
  • Autonomous broiler house monitoring for commercial growers (in partnership with Auburn University and Kansas State University)

Computational Biology (Paul Morris, Danny DaSilva, Rachael St. Clair)

  • Convolutional neural networks for predicting molecular binding affinity to HIV-1 proteins
  • Suppressing and modeling autoimmune disorders via primary protein sequences
  • A deep learning approach to virtual high throughput screening (vHTS) for drug discovery
  • Predicting neuronal orphan receptor ligand binding
  • Automatic tracking and analysis of C. elegans during high throughput seizure assays

Human Pose Analysis

  • Detecting drug impairment with deep learning (collaboration with Banyan Detox Facility)
  • AI-based feedback for prevention of body-focused repetitive behaviors
  • Predicting therapy interaction success (in collaboration with Paul Peluso)
  • Using gait estimation for early detection of dementia
  • Good posture application: feedback for postural improvement

Prevention of Body-focused Repetitive Behaviors

  • Stefani Moccia, Elan Barenholtz, and William Hahn. AI-based Feedback for Prevention of Body-focused Repetitive Behaviors 2019 Second Place Behavioral, Educational & Social Science FAU Wave Undergraduate Research Award

deep learning and their applied utility toward chemical informatics

  • Evan Clark, Rachel St Clair, Mike Teti, Elan Barenholtz and William Hahn. Advances in deep learning and their applied utility toward chemical informatics and drug discovery. ACS Conference 2019 Accepted with Talk.

Virtual high-throughput screening

  • Paul Morris, Rachel St Clair, Mike Teti, Elan Barenholtz and William Hahn. Virtual high-throughput screening; A combined deep-learning approach. ACS Conference 2019 Accepted with Talk.

Predicting Molecular Binding Affinity to HIV-1 Proteins

  • Morris, Paul & DaSilva, Yahchayil & Clark, Evan & Hahn, William & Barenholtz, Elan. (2018). Convolutional Neural Networks for Predicting Molecular Binding Affinity to HIV-1 Proteins. Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics. ACM, 2018.

Transcriptome Sequence Analysis of Primary Tumors

  • Wilson, Kelsey & Augustin, Regynald & Morris, Paul & Clark, Evan & Hahn, William & Barenholtz, Elan. (2018). Deep Learning Guided Transcriptome Sequence Analysis of Primary Tumors for Differentiation and Diagnosis of Multiple Cancers. GPU Technology Conference, DOI:10.13140/RG.2.2.26273.71521

Prediction for Synthetic Biology and Genetic Engineering

  • Teti, Michael, Rachel St Clair, Abrian Miller and William Edward Hahn. Deep Learning Sequence Prediction for Synthetic Biology and Genetic Engineering. iGem 2017 Accepted with Talk.

Emotion Recognition from Photographs

  • Geela Ramos, Fabio Ibanez, and William Hahn. Deep Learning Emotion Recognition from Photographs. 2018 1st Place Broward County Regional Science and Engineering Fair and 2nd Place Florida State County Science Fair

Mood Disorder Classification Using Eye Movements

  • Developing a Model for Mood Disorder Classification Using Eye Movements. Michael Kleiman, Evita Conway, Elan Barenholtz and William Hahn. 2018 FAU Wave Competition. (First Place)

Machine Olfaction

  • Machine Olfaction Using Deep Learning Artificial Neural Networks, Stephen Hoover, Biomedical engineering oral presentation presented the National Council on Undergraduate Research, April 2

Connected Autonomy and Robotics

robotic hand

Oscar Curet

-

Oscar Curet, Ph.D., and other researchers reinforced learning for navigation and coordination of bioinspired underwater vehicles in close formation - “A School of Robotic Fish.” The aim is to investigate optimal control mechanisms for robots that use fin-based propulsion. The goal is to implement an autonomous controller that would allow the robotic swimmer to perform high-level tasks such as station-keeping, trajectory-following or performing collaborative tasks in groups, especially in the presence of external disturbances. The novel aspect of the ongoing work is the ability of the robotic swimmer (and eventually, of swarms) to take decisions completely autonomously in order to attain a specified high-level goal. The range of potential applications include long-term environmental monitoring, deep water observation of aquatic animals, surveillance for coastal protection, and most-importantly, underwater search-and-rescue operations. The biggest benefit of using an autonomous controller is that individuals as well as swarms would be able to respond to unfamiliar situations and unexpected environmental disturbances. Autonomy is crucial since it may not be feasible for a human to monitor the robotic devices 24x7, or the time-delay in communication may be significant as is the case for underwater communication. Curet is an assistant professor in the department of Ocean and Mechanical Engineering in the College of Engineering and Computer Science.

Curet was awarded $500,000 from the National Science Foundation for the Bio-Inspired Underwater Vessels for Coastal Monitoring, Inspection and Station Keeping project.

Active Projects:

Connected Autonomy & Robotics Projects

Autonomous Navigation

  • Autonomous wheelchair, Autonomous navigation and voice control (Matt Trask)
  • Autonomous golf cart, add autonomous navigation and control (Matt Trask)
  • Autonomous ocean trash collection robot (with Department of Mechanical Engineering)
  • Evaluation of deep neural networks in an autonomous robot (Mike Teti)

Machine Olfaction

  • Autonomous broiler house monitoring for commercial growers (in partnership with Auburn University and Kansas State University)

Sparse Coding and Compressed Sensing

  • Learning attention through unsupervised sparse coding in an autonomous robot

Q-Learning

  • Utilizing OpenCV for Q-Learning State Space Reduction in Re-Purposed Off-The-Shelf FPV Rovers” Paul Morris, Marcus McGuire, Shawn Martin, Nicolas Tutuianu, Washington Garcia, William Hahn and Elan Barenholtz. FAU Undergraduate Research Symposium, 2017. (First Place)

Air Gapped Video Steam

  • Rodrigo Castellon, and William Hahn. End-to-end Vehicle Control from Air Gapped Video Steam. 2018 1st Place Broward County Regional Science and Engineering Fair, 3rd Place Florida State Science and Engineering Fair, and NASA Special Recognition Award

Deep Learning Architectures in an Autonomous-Vehicle

  • Teti, Michael, Elan Barenholtz and William Hahn. A Systematic Comparison of Deep Learning Architectures in an Autonomous-Vehicle. GTC 2018. Accepted with Talk.

Social Science

group of people jumping in the air on the beach at sunrise

photo of Sameer Hinduja, Ph.D.

-

Sameer Hinduja, Ph.D., combines behavioral and computer science to better identify and control cyberbullying on social media. His work helps to inform the reconsider making hurtful posts. Hinduja is a professor in the School of Criminology and Criminal Justice and co-director of the Cyberbullying Research Center.

Active Projects:

Social Science Projects

Human Pose Analysis

  • Assessing level of interest and engagement during video viewing (Nicole Perez)
  • Classifying criminal human behavior from skeletal key points with deep neural networks

The Ethics of Robotic Olfaction

  • Stark, Emily & Pitt, Jeremy & Nur Wicaksono, Alfian & Milanovic, Kristina & Lush, Victoria & Hoover, Stephen. (2018). Odorveillance and the Ethics of Robotic Olfaction [Opinion]. IEEE Technology and Society Magazine

FAU Research

Florida Atlantic is an R1 research institution where scientists and students collaborate toward common goals of improving human health, protecting our oceans and creating smarter spaces through artificial intelligence. Learn more about our four institutes, our accomplishments and our latest discoveries.

Connect with Florida Atlantic Research