Friday, September 27, 2019, 8:00 a.m. – 4:00 p.m., MU third floor
Registration, historical displays, graduate student posters contest
Friday, September 27, 2019, 8:30 – 9:00 a.m., MU Gallery Room
Welcome and opening remarks by Dean Schmittmann and Dr. Ciardo
Friday, September 27, 2019, 9:00 – 10:00 a.m., MU Gallery Room
Lecture: Mining Social Media to Aid Disaster Response
Dr. Doina Caragea, Ph.D. ’04 computer science, Iowa State University
Disaster-affected communities are increasingly becoming the source of big (crisis) data during and following major disasters. At the same time, big data have the potential to become an integral source of information for response organizations, as they can help enhance the situational awareness and facilitate faster response where is most needed. Despite such benefits, the challenges presented by big data preclude organizations from using them routinely. Manually sifting through voluminous streaming data to filter useful information in real time is inherently impossible. We study machine learning solutions to help emergency response organizations deal with the overload of relevant information, and improve situational awareness and crisis response. As an example, we have proposed a novel approach, based on convolutional neural networks and class activation mapping, to locate damage in disaster images and to quantify the degree of damage. Our proposed machine learning solutions have the potential to transform the way in which crisis response organizations operate, and, in turn, to provide better support to the victims of disasters in a timely fashion.
Doina Caragea is a Professor at Kansas State University. Her research and teaching interests are in the areas of machine learning, data mining, data science, information retrieval and text mining, with applications to crisis informatics, security informatics, recommender systems, and bioinformatics. Her projects build upon close collaborations with social scientists, security experts and life scientists, and aim to provide practical computational approaches to address real-world challenges. Dr. Caragea received her PhD in Computer Science from Iowa State University in August 2004, and was honored with the Iowa State University Research Excellence Award for her work. She has published more than 100 refereed conference and journal articles. Her research has been supported by several NSF grants.
Friday, September 27, 2019, 10:00 – 10:15 a.m.
BREAK with refreshments
Friday, September 27, 2019, 10:00 – 11:00 a.m.
Optional campus and departmental tour
Friday, September 27, 2019, 10:15 – 11:15 a.m., MU Gallery Room
Lecture: Google Maps – A Planet-scale Playground for Computer Scientists
Dr. Rajesh Parekh, MS ’93 computer science, Ph.D. ’98 computer science, Iowa State University
Google Maps provides useful directions, real-time traffic, and information on businesses to millions of people every day. This information has to constantly mirror the ever-changing world in order to provide the best experience for our users. Google leverages information from a variety of sources including StreetView cars that collect millions of images daily, satellites that provide valuable aerial imagery, and user submitted content in the form of text and photos. Processing this large volume of data and extracting meaningful information to maintain the coverage, accuracy, and freshness of the real-world data representation presents significant computer science challenges. This talk will present a view from the trenches on how large scale machine learning and computer vision algorithms can help to build a plant scale map. We will describe some core problems solved, lessons learned, and interesting research challenges that lie ahead.
Dr. Rajesh Parekh is Engineering Director at Google where he leads a talented team focusing on algorithmic data curation for Google’s Geo products. His team applies various Machine Learning and Computer Vision techniques to build trustworthy and useful understanding of the real world. He is passionate about solving challenging problems that deliver tremendous user impact. Prior to Google, Dr. Parekh led analytics for Facebook’s Video and Applied Machine Learning initiatives. Before Facebook, Dr. Parekh was the Vice President of Data Science at Groupon where he built products for personalization, sales automation, and marketing optimization. He also worked at Yahoo Labs building display advertising targeting products, at Blue Martini Software developing data mining products for e-commerce, and at Allstate solving insurance problems like cross-sell, retention, and fraud. Dr. Parekh earned his Ph.D. in Computer Science focusing on Artificial Intelligence from Iowa State University. He has published over 30 research papers and multiple international patents. He actively participates in the machine learning and data science community.
Friday, September 27, 2019, 11:30 a.m. – 12:45 p.m., MU Cardinal Room
Computer Science Student-Alumni Networking Luncheon
Current ISU computer science students are invited to join alumni for a casual deli buffet lunch to mingle, network, and gain some valuable insight and advice from our very talented computer science alumni. Alumni, we very much hope you will enjoy meeting with students – there will also be space for you to mix and mingle with your fellow alumni.
Friday, September 27, 2019, 1:00 – 2:00 p.m., MU Gallery Room
Lecture: Assuring Organic Programs: Software Engineering of the Future
Dr. Myra Cohen, professor in the department of computer science and Lanh & Oanh Nguyen endowed chair of software engineering at Iowa State University.
Over the past 20-30 years software engineering has struggled to handle an increasing complexity of programs and has turned to nature for inspiration to help improve software quality, utilizing approaches such as genetic algorithms which mimic biological evolution, to generate test suites and/or to refactor code. More recently, these same algorithms are being applied to automatically repair code, and to optimize code for objectives such as energy efficiency, or to automatically transplant functions from one program into another. In parallel, the field of synthetic biology has emerged as a discipline, where biological or chemical engineers use living organisms, or their DNA, as computing devices and through engineering principles program them with new behavior. Synthetic biology’s future is intended to bring customized drug delivery and cancer cures while also providing novel ways to perform large-scale environmental remediation and parallel computation. While these two fields remain distinct, there is an increasing overlap and there are many opportunities for both disciplines to benefit at their intersection. In this talk I show how programs are becoming biological, and how living programs behave in similar ways to traditional software. I present some recent work that applies software engineering principles to biology and discuss how we can apply what we have learned back to traditional software. I highlight the need for new techniques to validate that both types of programs behave as expected, and to be able to reason about the many variations or configurations of these systems in an abstract way. I end with the conjecture that these are all organic programs and assuring their correctness is the future of software engineering.
Prior to joining the university, Dr. Cohen was previously a Susan J. Rosowski Professor in Computer Science and Engineering at the University of Nebraska-Lincoln where she was a member of Laboratory for Empirically-based Software Quality Research and Development, ESQuaReD for 14 years. Her research interests are in software testing of highly-configurable software, search based software engineering, applications of combinatorial designs, and synergies between systems and synthetic biology, and software engineering.
Friday, September 27, 2019, 2:00 – 2:15 p.m.
BREAK with refreshments
Friday, September 27, 2019, 2:15 – 3:15 p.m., MU Gallery Room
Lecture: Learning from Context to Enhance Personalized Recommender Systems
Dr. Bamshad Mobasher, ’85 computer science and mathematics, MS ’89 computer science, Ph.D. ’94 computer science, Iowa State University
Intelligent personalized applications such as recommender systems help alleviate information overload by tailoring their output to users’ personal preferences. Some of the most effective providers of on-line information and services such as Amazon, LinkedIn, Netflix, Spotify, Facebook, YouTube, and others rely heavily on machine learning methods that predict user preferences and recommend or suggest personalized content. These systems, however, often do not take into account the fact that users interact with systems in a particular context and that user’ preferences change over time as they transition among different contexts. The role of context has been studied in many disciplines. In psychology, a change in context during learning has been shown to have an impact on recall. Research in linguistics has shown that context plays the important role of a disambiguation function. More recently, a variety of approaches and architectures have emerged for incorporating context or situational awareness in the recommendation process. I will provide a brief overview of the problem of context-aware recommendation and discuss some of the recently proposed solutions. I will particularly focus on approaches for modeling “interactional context,” where context is not directly represented using a pre-specified set of explicit variables, but is inferred automatically based on observations of users’ behaviors in their ongoing interactions with the system.
Dr. Bamshad Mobasher is a professor of Computer Science and the director of the Center for Web Intelligence at DePaul University College of Computing and Digital Media in Chicago. He is also the co-founder and the director of the Center for Data Mining and Predictive Analytics at DePaul University. He received his Ph.D. in Computer Science at Iowa State University in 1994. His general research areas include artificial intelligence and data mining. In particular, he is considered one of the leading authorities in Web mining, Web personalization, and recommender systems.
Friday, September 27, 2019, 3:30 – 4:30 p.m.
Campus and departmental tour
Friday, September 27, 2019, 6:00 – 9:00 p.m. Alumni Center
Reception (6:00 – 7:00 p.m.) followed by Anniversary banquet (7:00 – 9:00 p.m.)
Closing remarks by Dean Schmittmann.
Saturday, September 28, 2019, 9:00 a.m. – 12:00 p.m.
Computational Thinking Workshop for K-12
Do you have a child or teen interested learning more about becoming a computer scientist or computational thinking? Join us for this free workshop that offers children an opportunity to learn basic computing concepts and programming techniques, and to have fun with hands-on activities. Two main workshops are offered, one for beginners and the other for intermediate level students. The goal of both workshops is to impart computational thinking knowledge and skills at an age and preparedness appropriate level. For further details or if you have a child that would like to participate, please indicate that on the registration form, and we will get back to you once registration opens up!