Embedded Files
Publications
R. S. Annaluru, P. Santacruz, N.K. Telang, C. Julien, "Learning the impact of diversity, equity, and inclusion modules in an undergraduate electrical engineering classroom"Proc. of American Society for Engineering Education (ASEE) Annual Conference 2023 (In Progress)
R. S. Annaluru, C. Julien, Darla Castelli, J. Payton "A framework for integrating artificial intelligence with physical activity for elementary school learners" Proc. of American Society for Engineering Education (ASEE) Annual Conference 2023 (In Progress)
J.Grose, R.S.Annaluru, C.S. Foong, Michael Cullinan "Regression- based surrogate model for rapid prediction of temperature evolution in a microscale selective laser sintering system", International Manufacturing Science and Engineering Conference American Society of Mechanical Engineers, 2023. (In Progress)
N. K. Telang, N. Abraham, M. Seelan, R. S. Annaluru, “Traditional Lecture Format vs. Active Teaching Format in an Online Freshman Engineering Course”, Proc. of American Society for Engineering Education (ASEE) Virtual Annual Conference 2021 https://peer.asee.org/37925
R. S. Annaluru, K.U. Mazher, R.W. Heath, “Deep learning based range and DoA estimation using low resolution FMCW radars”, Proc. of SSP Workshop 2021 pp. 366-370
K. U. Mazher, R. S. Annaluru, and R. W. Heath, “Exploiting structural information in camera aided radar parameter estimation,” in Proc. of Global Conference on Signal and Image Processing (GlobalSIP), 2019
Posters
R. S. Annaluru, C. Julien, J. Payton, “Linking learning fundamental reinforcement learning concepts with being physically active”, Proc of the 52nd ACM Technical Symposium on Computer Science Education (SIGCSE '23). Association for Computing Machinery, Toronto, CA
Linking learning fundamental reinforcement learning concepts with being physically active
Linking learning fundamental reinforcement learning concepts with being physically active
More and more learning standards for computational thinking and computer science have been developed in schools across the world. This growth has resulted in an increase of learning activities for elementary school children. Furthermore, there has also been an explosion of artificial intelligence activities geared towards the same population. To supplement these current trends, in this work, we presented a reinforcement learning activity, a branch of artificial intelligence, designed to be played in the context of a physical education class along with a step-by-step lesson plan for teachers and purpose built assessments for the student participants.
Deep Learning Based Range and DoA Estimation Using Low Resolution FMCW Radars
Deep Learning Based Range and DoA Estimation Using Low Resolution FMCW Radars
Automotive Radar is essential for several vehicular applications due to its high resolution in range and velocity along with a robustness to difficult weather conditions. In particular, we worked on learning the range and direction of arrival of vehicles through training neural networks on simulated targets and testing them under realistic settings in terms of signal-to-noise ratio and computation. We were able to show that compared to FFT based processing, our solution's deviation from the true position was much lower. In addition, we showed that training on simulated targets sufficed with regards to detecting real targets.
Page updated
Google Sites
Report abuse