Signal Processing Commons^™

Transcranial Ac Modulation Of Cerebellar Nuclear Activity In Awake Animals, Nuran Kavakli

Dissertations

Entrainment of cerebellar nuclear (CN) cells via cerebellar transcranial alternating current stimulation (ctACS) has been reported in animals under ketamine/xylazine anesthesia. Our main objective was to demonstrate modulation of CN activity in unanesthetized, freely moving animals using ctACS. Multi-channel carbon-fiber electrodes were implanted into the interpositus nucleus for recording multi-unit (MU) activity, and thin-film electrodes were implanted subcutaneously over the posterior cerebellum for stimulation. A frequency-domain-based metric was developed to quantify modulation from MU signals. The results demonstrated modulation in a wide range of frequencies (4 Hz-300 Hz) as in anesthetized animals. In contrast, the amplitude of the peak in …

Machine Learning-Based Design Of Doppler Tolerant Radar, Kyle Peter Wensell

Dissertations

In this work, machine learning theory is applied to the design of a radar detector in order to train a machine learning-based detector that is robust against Doppler shifts. The radar system is designed to work with data that would be otherwise intractable to conventional optimal detector design, such as transmitted noise waveforms and the effects of one-bit quantization at the receiver. The detection performance of the one-bit receiver is shown to match the performance of the derived square-law sign correlator detector. The resulting learning-based detector also introduces Doppler tolerance to the system, which allows for the successful detection of …

Enhancing Rotating Machinery Fault Diagnosis: A Dual-Head Attention Mechanism In Deep Learning Neural Networks, Qing Snyder

Dissertations

Rotating machinery is crucial to production efficiency and safety in manufacturing industries for an extended time. Ensuring machinery reliability necessitates effective diagnostic systems, particularly for rotating bearings, the key components of such equipment. Fault diagnosis in rotating machinery is essential to prevent failures and minimize downtime, thereby playing an important role in industrial operations. The application of advanced neural network techniques in industry has risen recently. Among these, attention-based neural networks, especially the Transformer models, are originally noteworthy for their sequential data handling capability. This research delves into attention-based algorithms for rotating machinery fault diagnosis, signifying a substantial advancement in …

On Explainability Of Neural Networks, Cem Benar

Dissertations

It is widely reported that deep neural networks outperform most competitors for a range of applications. The state-of-the-art neural networks have built-in inductive bias of architectural choices, regularizations, optimizer types, and initialization methods. Using inductive bias is intuitive to enhance the model approximation. Deep neural networks are mostly dense and heavily overparameterized. They tend to be biased towards low-rank solutions to reduce complexity and improve generalization performance, known as implicit regularization. The implicit regularization as observed in specific architectures and various real-world data sets suggests to overparameterize neural networks judiciously and learn compressed representations (lower rank approximation) with improved performance. …

Motion-Resistant Pulse Oximetry, Ludvik Alkhoury

Dissertations

The measurement of vital signs ? such as peripheral capillary oxygen saturation (SpO₂) and heart rate (HR) levels ? by a pulse oximeter is studied. The pulse oximeter is a non-invasive device that measures photoplethysmography (PPG) signals and extracts vital signs from them. However, the quality of the PPG signal measured by oximetry sensors is known to deteriorate in the presence of substantial human and sensor movements contributing to the measurement noise. Methods to suppress such noise from PPG signals measured by an oximeter and to calculate the associated vital signs with high accuracy even when the wearer …

Sparse Methods For Blind Source Separation Of Frequency Hopping Rf Sources, Anushreya Ghosh

Dissertations

Blind source separation (BSS) is performed on frequency hopping (FH) sources. These radio frequency (RF) signals are observed by a uniform linear array (ULA) over a Spatial Channel Model (SCM) in four different propagation environments: (i) line-of-sight (LOS), (ii) single-cluster, (iii) multiple-cluster, and (iv) LOS with interference. The sources are spatially sparse, and their activity is intermittent and assumed to follow a hidden Markov model (HMM). BSS is achieved by utilizing direction of arrival (DOA) of the sources and clusters. A sparse detection framework is applied to obtain estimates of the sources' FH and DOA patterns. The solutions are binned …

Machine Learning Techniques For Network Analysis, Irfan Lateef

Dissertations

The network's size and the traffic on it are both increasing exponentially, making it difficult to look at its behavior holistically and address challenges by looking at link level behavior. It is possible that there are casual relationships between links of a network that are not directly connected and which may not be obvious to observe. The goal of this dissertation is to study and characterize the behavior of the entire network by using eigensubspace based techniques and apply them to network traffic engineering applications.

A new method that uses the joint time-frequency interpretation of eigensubspace representation for network statistics …

Development Of Sensor, Sensory System And Signal Processing Algorithm For Intelligent Sensing Applications, Xingzhe Zhang

Dissertations

Sensors have been receiving significant attention in the last decade and the demand for sensory systems has increased in recent years due to the rapid growth in the field of artificial intelligence (AI). Sensors can improve people’s awareness by providing them with real-time information on the environment and their immediate health conditions. This dissertation presents the fulfilment of three main projects and focuses on the development of a sensor, a sensory system, and a sensor signal recognition system for AI applications by employing printed electronics, analog circuit design, and digital signal processing techniques.

In the first project, a multi-channel stethograph …

Atmospheric Turbulence Distortion In Video: Restoration Utilizing Sparse Analysis, Benjamin J. Sanda

Dissertations

The removal of atmospheric turbulence (AT) distortion in long range imaging is one of the most challenging areas of research in imaging processing with an immediate need for solutions in several applications such as in military and transportation systems. AT exacerbates distortion due to non-linear geometric blur and scintillations in long-distance images and videos, severely reducing image quality and information interpretation. AT negatively impacts both human and computer vision systems, compromising visibility essential for accurate object identification and tracking.

In this dissertation, a novel sparse analysis framework is developed to address efficient AT blur and scintillation removal in video. Operating …

An Adaptive Kalman Filter For Voltage Sag Detection In Power Systems, Hisham Odeh Alrawashdeh

Dissertations

The exact values of the noise covariance matrix of the Kalman filter state vector Q and the measured signal noise covariance matrix R must be obtained in order to achieve the optimal performance of the Kalman filter. There have been many techniques and assumptions made to evaluate and compute Q and R. The effects of Q and R are investigated in detail in this dissertation. Based on these investigations, the Kalman filter has been modeled to detect the fundamental signal amplitude variations of power system signals. This technique helps in evaluating voltage sags in power systems.

Two algorithms are …

Cmos Rotary Traveling Wave Oscillators (Rtwos), Marvin Aidoo

Dissertations

Rotary Traveling Wave Oscillator (RTWO) represents a transmission line based technology for multi-gigahertz multiple phase clock generation. RTWO is known for providing low jitter and low phase noise signals but the issue of high power consumption is a major drawback in its application. Direction of wave propagation is random and is determined by the least resistance path in the absence of an external direction control circuit. The objective of this research is to address some of the problems of RTWO design, including high power consumption, uncertainty of propagation direction and optimization of design variables. Included is the modeling of RTWO …