Dr. Yin Wang of LTU Computer Science is organizer and chair of a special track in MobiMedia 2015. The track will focus on Data Mining in Multimedia, and will serve as platform of communication between some of the leading experts in the field. He will also present two papers at the conference. The conference will take place in Chengdu, China.
Computational analysis of American pioneering artist Jackson Pollock performed at Lawrence Technological University has already attracted substantial attention. Recent discoveries made at LTU identified mathematical features unique to Jackson Pollock artistic style. The study was featured on the world’s premier popular press such as The Smithsonian Magazine, Wired, The Times, Computer Magazine, Fox News, The Atlantic, and more.
Mansour Hammad, a math major undergraduate at LTU developed a novel expansion approach designed to provide a simplified approach to a common form of equations. Mansour’s expansion addresses equations of a certain common form, and makes a simplified solution than Lagrange and Taylor expansion. The work can be used to improve analysis of medical data, but also has application to engineering and even sports. Mansour published his discovery in the International Journal on Numerical and Analytical Methods in Engineering. The discovery also attracted attention of the popular press in his home country Saudi Arabia.
Nine LTU students in three teams of three participated in the 96-hour international Mathematical Contest in Modeling (MCM) from Feb. 5 – 9, 2015.
Each year the teams have a choice of two open-ended applied problems to solve, using mathematics, computer science, various sciences, and writing skills. This year’s problems were very current. Problem A involved modeling a realistic strategy to eradicate Ebola, given a new medication, and including vaccine development and distribution and other factors. Problem B involved modeling a useful search for an airplane lost in an ocean, assuming no signals generated, and taking into account different types of search planes and sensors. Details can be found at www.comap.com.
The teams are: Eric Beyer, Bob Gandolfo, Tyler Pleasant; David Inwald, Jose Rodrigo Sanchez-Vicarte, Mark Kenney; Mitzi Cruz, Kristin Jordan, Mohit Bansil.
Results will be available at the end of April. The teams are ranked as Successful Participant, Honorable Mention, Meritorious, Finalist, and Outstanding. Last year over 6,700 teams participated, from the U. S., China, and 12 other countries.
The 2014 MATH Challenge took place on Saturday, Nov. 1. LTU fielded three teams, in this three hour ten question undergraduate team math contest. This year a new high of 31 colleges signed up, 16 from Michigan. We expect the results by the end of the semester.
LTU has participated for the past 19 years, since the contest started in 1994 (no contest held in 2008), and has had a team in the top 10 in 8 of these years.
Eric Beyer, Bob Gandolfo, Braden Lyford;
Dave Inwald, Jose Rodrigo Sanchez-Vicarte;
Kathm Alismail, Ryan Holland, Mark Kenney
LTU undergraduate student Bob Strange likes football, and as computer science major decided to apply computational analysis to his favorite sport game. With assistance of LTU faculty he developed a computational model that analyzed all football plays of all NFL teams in the past 10 seasons. The model was then able to predict the type of the next football play (pass or run) based on the status of the game such as the time left, down, distance to the goal, etc’. His model was able to predict the type of play with accuracy significantly higher than random guessing. He also discovered that while some teams are more consistent and therefore easier for the computer to predict, other teams are less predictable and the computer was not able to analyze with accuracy higher than just a random guess. The method can be used by teams during game to better predict the offensive play of the opponent, or to simulate the play of the opponent during practice for a game. Bob Strange’s study was reviewed by expert scientists and was accepted for publication in International Journal of Computer Science in Sport.
An article recently accepted for publication in Journal of Stress describes a novel algorithm and software developed by LTU student Saundra Manning with the assistance of LTU faculty. The software scans through thousands of microscopy images and identifies “peculiar” cells – cells that are different from the “normal” cells. The use of the software is for analyzing data acquired by robotic microscopes that can image hundred thousands of cells in a single day, making it practically impossible to analyze the data manually. One of the advantages of the software is its generality, and its ability to adjust itself automatically to analyze different types of data. The software has a broad range of application in science, as well as public health such as food control and outbreak prevention (where the detection of unknown pathogens is critical for the early identification of potential outbreak risks).
LTU Computer Science student Joe George has been studying computational methods for analyzing music. With assistance from LTU faculty, he digitally processed songs and albums of some well-known popular music bands, and applied novel computational tools to study the machine perception of their music, quantifying the differences between their albums. By doing that he was able to make a dramatic scientific breakthrough, demonstrating that computers can profile the progression of the artistic styles of popular music bands. For instance, his algorithm was able to sort all of the Beatles albums in their chronological order by just processing the music data, and without using any information other than the sound itself.
The work published in the scientific journal “Pattern Recognition Letters” – one of the world’s most prestigious machine learning journal. It was also featured by numerous articles published in the world’s premier popular press such as NBC News, Discovery, Scientific American, Science, Yahoo News, Bloomberg Business Week, and many more, including daily newspaper and TV stations all over the world, from Trinidad to Kazakhstan.
LTU received a $293K grant for developing innovative educational programs that will embed actual information science research in its undergraduate programs. The undergraduate research will be interdisciplinary, and in the first stage will combine computer science research with art, biology, and psychology. The unique education programs aims at changing core courses such that instead of focusing on lectures, assignments, and exams, the students will have the opportunity to learn the foundations of these disciplines by conducting actual research using computational and information science tools.
Previous studies, including the US President’s Council of Advisors on Science and Technology (PACT), show that participation in research is a primary contributor to student engagement and student satisfaction, and consequently to student retention in STEM disciplines. It is therefore expected that research-based education will gradually offer an alternative to the traditional lecture-based education. The new LTU programs will utilize the power of undergraduate research experience and will make research accessible to a broad population of students as part of their formal education. According to the program computer science students and students from other disciplines will team up to tackle scientific questions using computer methodologies that have not been applied before to these problems with the goal of making new discoveries in the field.
In addition to research experience, the new programs will provide knowledge and experience in information science also to non-computer science students. That experience will improve computer literacy and enhance the computer skills of students who do not have computer science as their major, but their efficacy as professionals in their discipline can be substantially improved by having strong computer skills and ability to solve problems using computational tools.
LTU was one of 14 colleges and universities selected by AACU (Association of American Colleges and Universities) as recipient of the grant from almost 200 academic institutes that participated in the competition.
Nine LTU students in three teams of three participated in the 96-hour international Mathematical Contest in Modeling (MCM) from Feb. 6 – 10, 2014.
Each year the teams have a choice of two open-ended applied problems to solve, using mathematics, computer science, various sciences, and writing skills. For 2014, problem A, “Keep Right Except to Pass Rule”, involved analyzing the performance of
this rule in different traffic situations, and also if the road was under the control of an intelligent system. Problem B, “Choose the Best College Coach”, involved modeling how to choose the best coaches in several different sports, past or present, male or female. Details can be found at www.comap.com. All of our teams chose problem A.
The teams are: David Inwald, Daniel (Orlando) Anderegg, Anqi Du; Jose Rodrigo Sanchez-Vicarte, Mark Kenney,
Steven Gonzalez; Ceré Rettig, Braden Lyford, Connor Seay.
Results will be available at the end of April. The teams are ranked as Successful Participant, Honorable Mention, Meritorious, Finalist, and Outstanding. Last year over 5,600 teams participated, from the U. S., China, and 12 other countries.