Advancing AI @ WSU
a virtual AI mini summit
Wednesday, October 14, 2020
Click here to RSVP
As a Featured Event at the WSU Research Week 2020, the Artificial Intelligence @ WSU initiative is hosting a virtual mini summit on AI and applications to showcase recent advancements, foster collaborations, and initiate conversations. The event features six invited speakers from WSU, the Pacific Northwest National Laboratory and Microsoft Research who are leading major AI-related research activities in their groups and institutions. Topics covered include the interaction of AI and machine learning with mobile health, agriculture, plant pathology, augmented reality, power systems control, and scientific discovery. Each presentation will be 10 to 15 minutes long, and will be followed by up to 5 minutes of discussion time.
You are warmly invited to join us for what promises to be an exciting and engaging event!
Electrical Engineering and Computer Science
Introduction (watch video)
Assefaw Gebremedhin is an associate professor in the School of Electrical Engineering and Computer Science at Washington State University, where he leads the Scalable Algorithms for Data Science (SCADS) Lab. He also serves as WSU Point-of-Contact for AI research. His current research interests include: data science and AI, network science, high-performance computing, and applications in cyber security, energy systems, and bioinformatics.
Pacific Northwest National Laboratory
AI and Machine Learning for Scientific Discovery (watch video)
Artificial intelligence (AI) and machine learning (ML) offer new and exciting opportunities to accelerate scientific discovery. However, the successful use of AI/ML in science requires algorithms and models which are domain-aware, scalable, reproducible and interpretable. In this talk we will discuss the challenges and opportunities related to the application of AI/ML in several scientific and engineering domains of interest to DOE.
Robert Rallo is the Director of the Advanced Computational, Mathematics, and Data Division at Pacific Northwest National Laboratory and Affiliate Professor in the Chemical Engineering Department at University of Washington. Prior to joining PNNL, he was an Associate Professor in Computer Science and Artificial Intelligence and Director of the Advanced Technology Innovation Center (ATIC) at the Universitat Rovira i Virgili (Spain).
Towards Privacy-Preserving Spatial AI (watch video)
Spatial AI systems use cameras for geometric and semantic 3D scene understanding. Such systems are aimed at applications in robotics, augmented reality and pervasive computing and often construct persistent 3D spatial maps of the environment for tasks such as camera localization and navigation. However, such systems often require uploading image features to the cloud for processing and storage. These features can be exploited to recover sensitive information about the scene or subjects, e.g., by reconstructing the appearance of query images. To address this privacy concern, we have proposed new techniques for camera localization that are based on privacy-preserving features and map representations. We show that these techniques avoid disclosing potentially conﬁdential information in the images or in the scene and yet allow reliable 6-dof camera pose estimation and camera localization. I will also discuss our work on recovering camera ego-motion using extremely low resolution cameras which is another way to enhance the user’s privacy.
Sudipta Sinha is a principal researcher at Microsoft working on HoloLens and Augmented Reality. His research interests lie in computer vision, robotics and machine learning. He received his M.S. and Ph.D. from the University of North Carolina at Chapel Hill in 2005 and 2009 respectively.
Washington State University
Machine Learning and Mobile Health (watch video)
Machine learning is a key component of mobile health systems. Machine learning algorithms are commonly used to extract markers of health associated with physical activity, diet, mobility, and mental health from data collected with mobile devices and wearable sensors. However, deployment of these technologies in clinical settings is challenging. In this talk, we will first discuss several mobile health technologies that we have developed in the WSU Embedded & Pervasive Systems Lab (http://epsl.eecs.wsu.edu/). We will then discuss challenges associated with utilizing such systems in uncontrolled environments. The talk will then outline several computational approaches that we have developed to address these challenges.
Hassan Ghasemzadeh is an associate professor of Computer Science and the director of Embedded & Pervasive Systems Lab in the School of Electrical Engineering and Computer Science at Washington State University. His research interests include algorithm design, machine learning, and system-level optimization for embedded and pervasive systems, wearable computing, and mobile health.
Washington State University
Artificial Intelligence, Cyber-Physical Systems and Robotics for Agriculture (watch video)
In this presentation, the author will first discuss the importance of precision and automated/robotic systems for the future of farming (Smart Farming, Ag 4.0). He will then summarize past efforts and current status of agricultural automation and robotics, particularly for fruit crop production, followed by an introduction of the novel systems being developed in his program. The technologies to be introduced include robotic fruit harvesting, fruit tree pruning, and crop thinning. At the end, major challenges and opportunities in agricultural robotics and related areas as well as potential future directions in research and development will be discussed.
Dr. Manoj Karkee is an Associate Professor in the Biological Systems Engineering Department at Washington State University (WSU). He received his PhD in Agricultural Engineering and Human Computer Interaction from Iowa State University in 2019. Dr. Karkee leads a strong research program in the area of sensing, machine vision and agricultural robotics at the WSU Center for Precision and Automated Agricultural Systems. He has published widely in such journals as ‘Journal of Field Robotics’, ‘Computers and Electronics in Agriculture’, and ‘Transactions of the ASABE’, and has been an invited speaker at numerous national and international conferences and universities. Dr. Karkee was awarded ‘2020 Railbird Engineering Concept of the Year’ by American Society of Agricultural and Biological Engineers, and was recognized as ‘2019 Pioneer in Artificial Intelligence and IoT’ by Connected World magazine.
Pacific Northwest National Laboratory
Deep Learning for Model Predictive Control (watch video)
Many real-world systems have unknown dynamics and operate in uncertain environments. Data-driven deep learning methods offer a pathway to introduce advanced control to complex systems. We introduce our recent work that uses multiple methods to embed domain knowledge in deep learning representations and trains deep learning predictive controllers. We illustrate performance comparisons between deep learning control, traditional model predictive control and reinforcement learning methods, on a classical linear time-invariant system. Finally, we outline future research avenues.
Draguna Vrabie is chief scientist at Pacific Northwest National Laboratory. Her work at the intersection of control system theory and machine learning is aimed at design of adaptive decision and control systems. Her current focus is on methodologies and algorithms for design and operation of high-performance cyber-physical systems. Prior to joining PNNL in 2015 she was a senior scientist at United Technologies Research Center, East Hartford, Connecticut. She holds a doctorate in electrical engineering from the University of Texas at Arlington, and an ME and BE in automatic control and computer engineering from Gheorghe Asachi Technical University, Iaşi, Romania.
Washington State University
Harnessing AI for Food Security (watch video)
The continuous shrinkage of agricultural land combined with increased urbanization and population pressure pose serious challenges to feeding the billions and ensuring food security. Diseases cause as much as 40% yield losses in food, feed and fiber crops on a worldwide basis and the cost of controlling diseases runs into billions of dollars annually. AI has tremendous potential in reducing the cost of production, helping more judicious use of agricultural inputs, environmental stewardship, and enhancing the sustainability of food production.This talk will highlight select examples of this potential.
Hanu R. Pappu is the President Sam Smith Distinguished Professor and the Chuey Endowed Chair in Department of Plant Pathology, and a member of the interdisciplinary PhD program in Molecular Plant Sciences. Dr. Pappu’s research interests and expertise include molecular virology, and development of environmentally friendly and sustainable strategies for reducing the impact of destructive viral diseases of crops. Ongoing research includes the use of genome editing technologies and AI for trait improvement with special emphasis on virus management.