Learning to recognize objects is a fundamental and essential step in human perception and understanding of the world. Accordingly, research of object discovery across diverse modalities plays a pivotal role in the context of computer vision. This field not only contributes significantly to enhancing our understanding of visual information but...
Although there are considerable site-based data for individual or groups of ecosystems, these datasets are widely scattered, have different data formats and conventions, and often have limited accessibility. At the broader scale, national datasets exist for a large number of geospatial features of land, water, and air that are needed...
Analysis of observations on sequential events over time is common in real life. Sequential measurements over time describing the behavior of systems are usually called time series data, which have been collected in a wide range of disciplines. Over the years there have been multiple research areas in studying stochastic...
We present a method for decentralized, multi-robot exploration in adverse environments where communication is minimal. A key conceptual feature of our method is enabling implicit coordination between robots by training a Convolutional Neural Network (CNN) as a heuristic for planning using Monte Carlo Tree Search (MCTS). Our method consists of...
General-purpose Graphics Processing Units (GPGPUs) have become a critical component in high-performance computing (HPC) systems in executing modern computational workloads. The high thread level parallelism (TLP) and programmable shader cores allow thousands of threads to execute in Parallel. The fast-scaling of GPGPUs have increased the demand for performance optimizations on...
The high level of parallelism in throughput processors such as GPGPUs has resulted in significantly changed on-chip data traffic behaviors. This demands new research to identify and address the limiting factors of networks-on-chip (NoCs) in the context of throughput processors. In this work, we first quantitatively analyze the performance of...
In this dissertation, the primary objective is to discover more sustainable electrode materials and study new reaction mechanisms using aqueous electrolytes. The first study conducted reveals a reversible conversion reaction from copper to Cu2CO3(OH)2. The reaction mechanism uses OH- and CO32- as charge carriers at the cathode. The results open...
The Machine Learning (ML) algorithms are increasingly explored in varies of fields including designing and optimizing computer systems. Recent research, such as optimizing memory/cache prefetching by ML training or predicting traffic pattern in throughput processors, also exhibits a promising future of introducing ML into computer system design and optimization. Throughput...
Increasingly congested surface transportation network in urban areas and grow-ing land values make underground transportation systems more attractive for high-ways (i.e., tunnels) and metro system compared to other options [1]. An underground transportation system can preserve the land above for recreational parks, commer-cial buildings, residential homes, or other purposes while...
This dissertation addresses the problem of video labeling at both the frame and pixel levels using deep learning. For pixel-level video labeling, we have studied two problems: i) Spatiotemporal video segmentation and ii) Boundary detection and boundary flow estimation. For the problem of spatiotemporal video segmentation, we have developed recurrent...