Engineering Commons^™

Incorporating Machine Learning With Satellite Data To Support Critical Infrastructure Measurement And Sustainable Development, Aggrey Muhebwa

Doctoral Dissertations

Under the umbrella concept of Artificial Intelligence (AI) for good, recent advances in machine learning and large-scale data analysis have opened new opportunities to solve humanity’s most pressing challenges. Improvements in computation complexity and advances in AI (e.g., Vision Transformers) have led to faster and more effective techniques for extracting high-dimensional patterns from large-scale heterogeneous datasets (big data). Further, as satellite data become increasingly available at varying temporal-spatial resolutions, AI tools are helping us to better understand the underlying causes of environmental and socioeconomic changes at an unprecedented scale, ushering in an era of data-driven decision-making to support sustainable and …

Machine Learning Applications In Plant Identification, Wireless Channel Estimation, And Gain Estimation For Multi-User Software-Defined Radio, Viraj K. Gajjar

Doctoral Dissertations

"This work applies machine learning (ML) techniques to selected computer vision and digital communication problems. Machine learning algorithms can be trained to perform a specific task without explicit programming. This research applies ML to the problems of: plant identification from images of leaves, channel state information (CSI) estimation for wireless multiple-input-multiple-output (MIMO) systems, and gain estimation for a multi-user software-defined radio (SDR) application.

In the first task, two methods for plant species identification from leaf images are developed. One of the methods uses hand-crafted features extracted from leaf images to train a support vector machine classifier. The other method combines …

Machine Learning With Topological Data Analysis, Ephraim Robert Love

Doctoral Dissertations

Topological Data Analysis (TDA) is a relatively new focus in the fields of statistics and machine learning. Methods of exploiting the geometry of data, such as clustering, have proven theoretically and empirically invaluable. TDA provides a general framework within which to study topological invariants (shapes) of data, which are more robust to noise and can recover information on higher dimensional features than immediately apparent in the data. A common tool for conducting TDA is persistence homology, which measures the significance of these invariants. Persistence homology has prominent realizations in methods of data visualization, statistics and machine learning. Extending ML with …

Data Fusion Techniques For Biomedical Informatics And Clinical Decision Support, Peng Guo

Doctoral Dissertations

"Data fusion can be used to combine multiple data sources or modalities to facilitate enhanced visualization, analysis, detection, estimation, or classification. Data fusion can be applied at the raw-data, feature-based, and decision-based levels. Data fusion applications of different sorts have been built up in areas such as statistics, computer vision and other machine learning aspects. It has been employed in a variety of realistic scenarios such as medical diagnosis, clinical decision support, and structural health monitoring. This dissertation includes investigation and development of methods to perform data fusion for cervical cancer intraepithelial neoplasia (CIN) and a clinical decision support system. …

Adaft: A Resource-Efficient Framework For Adaptive Fault-Tolerance In Cyber-Physical Systems, Ye Xu

Doctoral Dissertations

Cyber-physical systems frequently have to use massive redundancy to meet application requirements for high reliability. While such redundancy is required, it can be activated adaptively, based on the current state of the controlled plant. Most of the time the physical plant is in a state that allows for a lower level of fault-tolerance. Avoiding the continuous deployment of massive fault-tolerance will greatly reduce the workload of CPSs. In this dissertation, we demonstrate a software simulation framework (AdaFT) that can automatically generate the sub-spaces within which our adaptive fault-tolerance can be applied. We also show the theoretical benefits of AdaFT, and …

Intrinsic Functions For Securing Cmos Computation: Variability, Modeling And Noise Sensitivity, Xiaolin Xu

Doctoral Dissertations

A basic premise behind modern secure computation is the demand for lightweight cryptographic primitives, like identifier or key generator. From a circuit perspective, the development of cryptographic modules has also been driven by the aggressive scalability of complementary metal-oxide-semiconductor (CMOS) technology. While advancing into nano-meter regime, one significant characteristic of today's CMOS design is the random nature of process variability, which limits the nominal circuit design. With the continuous scaling of CMOS technology, instead of mitigating the physical variability, leveraging such properties becomes a promising way. One of the famous products adhering to this double-edged sword philosophy is the Physically …

On Physical Disorder Based Hardware Security Primitives, Arunkumar Vijayakumar

Doctoral Dissertations

With CMOS scaling extending transistors to nanometer regime, process variations from manufacturing impacts modern IC design. Fortunately, such variations have enabled an emerging hardware security primitive - Physically Unclonable Function. Physically Unclonable Functions (PUFs) are hardware primitives which utilize disorder from manufacturing variations for their core functionality. In contrast to insecure non-volatile key based roots-of-trust, PUFs promise a favorable feature - no attacker, not even the PUF manufacturer can clone the disorder and any attempt at invasive attack will upset that disorder. Despite a decade of research, certain practical problems impede the widespread adoption of PUFs. This dissertation addresses the …

Neuron Clustering For Mitigating Catastrophic Forgetting In Supervised And Reinforcement Learning, Benjamin Frederick Goodrich

Doctoral Dissertations

Neural networks have had many great successes in recent years, particularly with the advent of deep learning and many novel training techniques. One issue that has affected neural networks and prevented them from performing well in more realistic online environments is that of catastrophic forgetting. Catastrophic forgetting affects supervised learning systems when input samples are temporally correlated or are non-stationary. However, most real-world problems are non-stationary in nature, resulting in prolonged periods of time separating inputs drawn from different regions of the input space.

Reinforcement learning represents a worst-case scenario when it comes to precipitating catastrophic forgetting in neural networks. …