Aperiodic structures cause significant challenges to subtractive manufacturing methods due to the common features such as inaccessible voids within the structure. Additive man- ufacturing presents an appealing alternative for this purpose. The aim of this research is to test analysis heuristics for validity through application to periodic structures. First, a...
Transmit beamforming is an important technique employed to improve efficiency and signal quality in wireless communication systems by steering signals towards their in- tended users. It often arises jointly with the antenna selection problem due to various reasons, such as limited number of radio frequency (RF) chains and energy/resource effi-...
Crowdsourcing is a popular paradigm to address the high demands for labeled data in big data deluge. It aims to produce accurate labels by effectively integrating noisy, non-expert labeling from crowdsourced workers (annotators). The machine learning community has been studying effective crowdsourcing methods for many years, and many models and...
Efficient time-series analysis can impact multiple application domains such as motif discovery in gene analysis or music data, extracting spectro-temporal patterns in acoustic scene analysis, or annotating and classifying electrical bio-signals (such as ECG, EEG, and EMG) for medical applications.
Time-series analysis involves a variety of tasks.
To predict future...
In this thesis, we introduce a novel Explanation Neural Network (XNN) to explain the predictions made by a deep network. The XNN works by embedding a high-dimensional activation vector of a deep network layer non-linearly into a low-dimensional explanation space while retaining faithfulness i.e., the original deep learning predictions can...
Motivation: Many robots such as legged robots and prosthetic hands/arms are designed to interact with uncertain and time-varying environments to accomplish their tasks.
Observations on humans and animals during their daily tasks suggest that they adapt their leg compliance while traversing with different velocities on different grounds and adjust their...
Investigating the structure-property relationships of solid state materials can help improve many of the materials we use each day in life. It can also lead to the discovery of materials with interesting and unforeseen properties. In this work the structure property relationships of newly discovered layered oxypnictide phases are presented...
This study uses an anthropological perspective
to discuss the cultural differences between Chinese
and Americans in business contexts. Through an
analysis of case studies related by businesspersons
involved in Sino-US trade, and by an analysis of
literature on the subject, it describes how cultural
differences contribute to the problems and...
Heatmap regression has became one of the mainstream approaches to localize facial landmarks. As Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) are becoming popular in solving computer vision tasks, extensive research has been done on these architectures. However, the loss function for heatmap regression is rarely studied. In...
Magnetic materials can be used in modern soft robotics as a method for external stimulus actuation and motion control. By combining aspects of biology and mechanics, devices are fabricated to create a structure capable of complex movement. Applications that these devices are subject to can be broken down into four...