Dr. Anna Little, a postdoc in the Department of Computational Mathematics, Science, and Engineering at Michigan State University, will present her talk, “Robust Statistical Procedures for Clustering in High Dimensions,” on Friday, October 18, 2019, at 1:00 p.m., in Fisher Hall Room 327B.
Dr. Little completed a PhD in mathematics at Duke University in 2011. She has been at Michigan State since 2018. Visit her website at www.anna-little.com.
Lecture Abstract: This talk addresses multiple topics related to robust statistical procedures for clustering in high dimensions, including path-based spectral clustering (a new method), classical multidimensional scaling (an old method), and clustering in signal processing. Path-based spectral clustering is a novel approach which combines a data driven metric with graph-based clustering. Using a data driven metric allows for fast algorithms and strong theoretical guarantees when clusters concentrate around low-dimensional sets.
Another approach to high-dimensional clustering is classical multidimensional scaling (CMDS), a dimension reduction technique widely popular across disciplines due to its simplicity and generality. CMDS followed by a simple clustering algorithm can exactly recover all cluster labels with high probability when the signal to noise ratio is high enough. However, scaling conditions become increasingly restrictive as the ambient dimension increases, illustrating the need for robust unbiasing procedures in high dimensions. Clustering in signal
processing is the final topic; in this context each data point corresponds to a corrupted signal. The classic multireference alignment problem is generalized to include random dilation in addition to random translation and additive noise, and a wavelet based approach is used to define an unbiased representation of the target signal(s) which is robust to high frequency perturbations.
Dr. Timothy Wilkin, associate professor of computer science and associate head of school (student learning) within the School of Information Technology, Deakin University, Australia, will present a talk at Michigan Tech on Monday, October 7, from 4:00-5:00 p.m., in ME-EM 112. A reception and refreshments will follow.
Dr. Wilkin’s talk, “Adventures of a Cyber-Physical Cow,” will present findings from his recent industry-based research into the use of wearable technologies in livestock farming.
Talk Abstract: Fitness and activity trackers, and other wearable sensors have revolutionised both professional sports and the general health & wellbeing market. On the other hand, wearables to support precision livestock farming and general animal health and wellbeing tracking are virtually non-existent. There are significant opportunities to support and grow concepts such as “paddock to plate” food provenance, particularly in the meat and livestock sector, through the use of wearable technologies. In this talk I will present some recent industry-based research between Deakin University and Agersens Pty Ltd, an Australian manufacturer of a world-leading geofencing technology for livestock. Real-time behaviour classification and analytics were used to both improve the existing product, as well as to create new data products for farmers and a greatly enhanced marketability for their smart collar. I will also highlight how this industry-based research has led to several interesting and challenging research questions that have driven ongoing fundamental research in data science at Deakin.
Dr. Wilkin’s Bio: Dr Wilkin’s research interests cover problems in computational and artificial intelligence to support sensor and data analytics, with applications in intelligent control for robotics and autonomous systems, embedded/edge AI, and intelligent sensing. His research has been applied in diverse areas, from marine ecology to childhood health, farming, defence and commercial robotics. Dr Wilkin is also an innovative, award-winning teacher and academic leader. As Associate Head of School he overseas teaching and learning activities of over 100 full-time academic staff and 3500 students enrolled in 16 undergraduate and postgraduate programs.
Charles Wallace, Associate Professor of Computer Science and member of the ICC’s Center for Human-Centered Computing, has been appointed Associate Dean for Curriculum and Instruction for the College of Computing, effective immediately. Wallace has been teaching in the Department of Computer Science for 19 years, and he has a long track record of education research and building collaboration with Cognitive & Learning Sciences, Engineering, Humanities, and Social Sciences.
“Chuck brings to his new role an extensive breadth of experience that spans from outreach to curricular development to collaborations with multiple units across campus,” says Adrienne Minerick, dean of the College of Computing. “In this new role, he will help build campus collaborations to create additional pathways for Michigan Tech students to engage with computing curricula, and facilitate conversations within the College of Computing that enable creative, agile options for our students.”
“Barriers between computing and other disciplines are artificial and unproductive,” Wallace says. “Computing competencies are essential for Michigan Tech graduates in all fields, and the College and University should commit to building educational options housed in the College of Computing but available and accessible to all students.”
Wallace adds that students in the College of Computing should be free – and actively encouraged – to explore application areas where their skills can be used. He also wants to explore ways to build flexibility into Computing academic programs, maintaining the solid technical core that Michigan Tech graduates are known for, but also allowing students to pursue applications of their computing competencies in other disciplines.
Vision Statement from Charles Wallace:
Here are a few points that I consider vital to the future of computing education, based on 19 years of experience in the Computer Science Department, a long track record of education research, and extensive collaboration with Cognitive & Learning Sciences, Engineering, Humanities, and Social Sciences.
Barriers between computing and other disciplines are artificial and unproductive. Computing competencies are essential for Michigan Tech graduates in all fields. The College and University should commit to building educational options housed in the College of Computing but available and accessible to all students. This will require an earnest and focused investment in personnel – we cannot do it solely with the current cohort of instructors, who are already stretched thinly with increased enrollment in core computing programs.
Conversely, students in the College of Computing should be free and even encouraged to explore application areas where their skills can be brought to bear. Complex degree requirements can hinder such exploration. We should explore ways to build flexibility into our programs, maintaining the solid technical core that Michigan Tech graduates are known for, but also allowing students to pursue applications of their computing competencies in other disciplines.
Computing students are citizens, not just producers. The degree programs in Michigan Tech’s Computer Science Department have a long and venerable tradition of preparing students who can “produce” – hit the ground running in the workplace and build high quality solutions. That is a precious gift, and we should not deprive future students of it – but the future demands more. Our world is increasingly dominated by computing – and by extension, dominated by human beings who understand computing. Michigan Tech graduates of the College of Computing must be known not only for the technical “value” that they produce, but also the ability to question and critique digital technology, to be empathetic and articulate ambassadors and leaders in the new digital order of the future.
There are two promising ways in which we can build better computing citizens. First, an awareness of the social and ethical consequences of computing must be woven into our curricula, not just taught as external service courses. Second, service learning is a way to expose students to the human contexts of computing technology. There are many ways to get students involved in our community, but these have not been harnessed outside of ad hoc outreach efforts. Interaction with the community should be built into the academic experience of computing students.
Computing competencies include values and attitudes, not just skills and knowledge. Alumni of our degree programs acknowledge that collaboration and communication are essential components of their professional lives. These competencies involve not only skills but also values and attitudes – willingness and even eagerness to engage with others, resilience in the face of uncertainty or ambiguity, and adaptability in the face of changing requirements. To prepare students for the highly collaborative computing workplace, courses in the College of Computing should embrace the opportunities and challenges of working in diverse teams. As with ethics, issues of teamwork and communication must be integrated into “disciplinary” courses, not left to service courses or external experiences like internships.
These curricular pathways hold promise not only to develop competent computing professionals of the future, but also to attract a more diverse constituency to the College of Computing student body.
An article by Mark Rouleau, associate professor of social sciences and member of the ICC’s Center for Data Sciences, was recently published in the journal Landscape and Urban Planning, published by Elsevier. The article, titled, “Agent-based modeling for bioenergy sustainability assessment,” is co-authored by Robert J. Zupko II.
Article Abstract: Woody biomass bioenergy is an important renewable alternative to conventional fossil fuels. However, the negative land-use change impacts of biomass harvesting necessary for bioenergy production can potentially outweigh its positive benefits if poorly managed. In this paper, we explain how Agent-Based Modeling (ABM), a form of computer simulation, can be used to conduct a comprehensive bioenergy sustainability assessment to identify possible gains and trade-offs necessary to develop bioenergy in regions with large numbers of private family forest owners or smallholders who own a significant share of available biomass. We discuss how ABM simulation can overcome the barriers of existing sustainability assessment tools and provide a demonstration of the sustainability assessment capabilities of an ABM using a hypothetical case study that explores the introduction of a bioenergy conversion facility in the Western Upper Peninsula of Michigan, United States. We conduct a series of alternative futures scenarios and compare the sustainability outcomes of three alternative policy regimes using voluntary incentive programs to encourage smallholders to harvest biomass.
Recommended Citation: Rouleau, M., & Zupko II, R. J. (2019). Agent-based modeling for bioenergy sustainability assessment. Landscape and Urban Planning, 188, 54-63.http://dx.doi.org/10.1016/j.landurbplan.2019.04.019
Keith Vertanen (CS/ICC-HCC) is the principal investigator on a three-year project that has received a $225,663 research and development grant from the National Science Foundation. The project is entitled, “CHS: Small: Collaborative Research: Improving Mobile Device Input for Users Who are Blind or Low Vision.”
Abstract: Smartphones are an essential part of our everyday lives. But for people with visual impairments, basic tasks like composing text messages or browsing the web can be prohibitively slow and difficult. The goal of this project is to develop accessible text entry methods that will enable people with visual impairments to enter text at rates comparable to sighted people. This project will design new algorithms and feedback methods for today’s standard text entry approaches of tapping on individual keys, gesturing across keys, or dictating via speech. The project aims to: 1) help users avoid errors by enabling more accurate input via audio and tactile feedback, 2) help users find errors by providing audio and visual annotation of uncertain portions of the text, and 3) help users correct errors by combining the probabilistic information from the original input, the correction, and approximate information about an error’s location. Improving text entry methods for people who are blind or have low vision will enable them to use their mobile devices more effectively for work and leisure. Thus, this project represents an important step to achieving equity for people with visual impairments.
This project will contribute novel interface designs to the accessibility and human-computer interaction literature. It will advance the state-of-the-art in mobile device accessibility by: 1) studying text entry accessibility for low vision in addition to blind people, 2) studying and developing accessible gesture typing input methods, and 3) studying and developing accessible speech input methods. This project will produce design guidelines, feedback methods, input techniques, recognition algorithms, user study results, and software prototypes that will guide improvements to research and commercial input systems for users who are blind or low-vision. Further, the project’s work on the error correction and revision process will improve the usability and performance of touchscreen and speech input methods for everyone.
Timothy Schulz, professor of electrical and computer engineering and member of the ICC Center for Data Science, has been awarded the prestigious University Professor title, which recognizes faculty members who have made outstanding scholarly contributions to the University and their discipline over a substantial period of time.
The University’s most prestigious faculty awards–announced last spring–were presented Wednesday, September 18, at a ceremony in the Van Pelt and Opie Library. Making the presentations were University President Richard Koubek, Provost and Senior Vice President for Academic Affairs Jacqueline Huntoon and Vice President for Research David Reed.
Kuilin Zhang (CEE/MTTI), a member of the ICC Center for Cyber-Physical Systems (CPS), is the primary investigator on a project that has received a $567,230 contract with the Federal Railroad Administration. This project is entitled, “Developing Safe and Efficient Driving and Routing Strategies at Railroad Grade Crossings Based on Highway-Railway Connectivity.” Pasi Lautala (CEE) is the Co-PI on this potential two-year project.
College of Computing Professor Alex Sergeyev (DataS) presented his research article, “University, Community College and Industry Partnership: Revamping Robotics Education to Meet 21st Century Workforce Needs – NSF Sponsored Project Final Report,” at the 2019 American Society of Engineering Education (ASEE) annual conference, receiving the Best Paper Award in the Engineering Technology Division.
The conference took place June 16-19 in Tampa, Florida.
Co-authors of the publication are S. Kuhl, N. Alaraje, M. Kinney, M. HIghum, and P. Mehandiratta. The paper will be published in the fall issue of the prestigious Journal of Engineering Technology (JET).
The Institute of Computing and Cybersystems (ICC) and the Michigan Tech Visiting Professor Program will present a seminar by Dr. Anna Wilbik on Thursday, October 3, starting at 3:00 p.m., in ME-EM 112 . A reception will follow and refreshments will be served. The title of Dr. Wilbik’s seminar is, “The explainability challenge in descriptive analytics: do we understand the data?”
The seminar is presented by the Institute of Computing and Cybersystems and the Michigan Tech Visiting Professor Program, which is funded by a grant to the Michigan Tech Provost Office from the State of Michigan’s King-Chavez-Parks Initiative.
Dr. Anna Wilbik is an assistant professor in the Information Systems Group of the Department of Industrial Engineering and Innovation Sciences at Eindhoven University of Technology (TU/e) in the Netherlands. She received her PhD in Computer Science from the Systems Research Institute, Polish Academy of Science, Warsaw, Poland, in 2010. In 2011, she was a Postdoctoral Fellow with the Department of Electrical and Computer Engineering at the University of Missouri, Columbia, USA. Her research interests are in business intelligence, especially focused on linguistic summaries and computing with words. With her research she tries to bridge the gap between the fuzzy sets theory and industrial applications. She makes this connection in research projects collaborating with industry both on the national and the European level. She has published over 80 papers in international journals and conferences.
Seminar Abstract: Nowadays, ever more data are collected, for instance in the healthcare domain. The amount of patients’ data has doubled in the previous two years. This exponential growth creates a data flood that is hard to handle by decision makers. In many domains, humans are collaborating with machines for decision making purposes to cope with the resulting data complexity and size. This collaboration can be realized through machine learning, visual analytics, or online analytical processing, where a machine is just a tool – but often used to make important decisions. The question now is: do we really understand the data by using the tool this way?
Explainability is a great challenge in data analytics, with the aim to explain to the user why certain decisions have been recommended or made. This challenge is especially important in predictive and prescriptive analytics. Less attention in this respect is payed to less mature analytics levels, descriptive and diagnostics, although they are the first steps for understanding data.
Data analysis methods use numbers, figures, or mathematical equations to show data, decision recommendations, and patterns. Yet for a human, the natural way of communication is natural language: words, not numbers or figures. This causes a gap between the meaning of data and human understanding. The challenge is: How to make data more understandable for humans?
Fuzzy techniques, or the application of the computing with words paradigm, have the potential to close the gap by using natural language as the communication means. In this talk, I will focus on descriptive analytics and show with a set of examples how fuzzy techniques can provide better insight of data to the user. I pay special attention to the technique of linguistic summaries.
The Institute of Computing and Cybersystems (ICC) and the Michigan Tech Visiting Professor Program will present a seminar by Dr. Anna Wilbik on Thursday, October 3, starting at 3:00 p.m., in ME-EM 112 . A reception will follow and refreshments will be served. The title of Dr. Wilbik’s seminar is, “The explainability challenge in descriptive analytics: do we understand the data?”