Electrical and Computer Engineering Commons^™

Spatiotemporal Pattern Detection With Neuromorphic Circuits, Robert C. Ivans

Boise State University Theses and Dissertations

In this dissertation, neuromorphic circuits are used to implement spiking neural networks in order to detect spatiotemporal patterns. Unsupervised training and detection-by-design techniques were used to attain the appropriate connectomes and perform pattern detection.

Unsupervised training was performed by feeding random digital spikes with a repeating embedded spatiotemporal pattern to a spiking neural network composed of leaky integrate-and-fire neurons and memristor-R(t) element circuits which implement spike-timing-dependent plasticity learning rules.

Detection-by-design was achieved using neuromporphic circuits and digital logic gates. When detection-by-design was achieved using both neuromorphic circuits and digital logic gates, a network was created of spatiotemporal pattern detector circuits, …

Partial Discharge Testing And Detection Under Pwm Voltage, John Meadors

Masters Theses

Partial Discharge detection and measurement is an important part of electric insulation design. However, in PWM (pulse width modulation) voltage source converter environments, the noise resulting from switching voltage (rise and fall times of tens of nanoseconds) makes detection and extraction of partial discharge difficult. Unique methods of partial discharge detection are needed to address and decouple the noise from partial discharge measurements. PWM voltage can feature high switching speeds and high dv/dt during voltage switching. These PWM voltage behaviors are not found in traditional utility high voltage applications, and the effects that this type of voltage has on insulation …

Distributed Neural Network Based Architecture For Ddos Detection In Vehicular Communication Systems, Nicholas Jaton

Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research

With the continued development of modern vehicular communication systems, there is an ever growing need for cutting edge security in these systems. A misbehavior detection systems (MDS) is a tool developed to determine if a vehicle is being attacked so that the vehicle can take steps to mitigate harm from the attacker. Some attacks such as distributed denial of service (DDoS) attacks are a concern for vehicular communication systems. During a DDoS attack, multiple nodes are used to flood the target with an overwhelming amount of communication packets. In this thesis, we investigated the current MDS literature and how it …

Real-Time Machine Learning For Quickest Detection, Yongxin Liu

Doctoral Dissertations and Master's Theses

Safety-critical Cyber-Physical Systems (CPS) require real-time machine learning for control and decision making. One promising solution is to use deep learning to discover useful patterns for event detection from heterogeneous data. However, deep learning algorithms encounter challenges in CPS with assurability requirements: 1) Decision explainability, 2) Real-time and quickest event detection, and 3) Time-eficient incremental learning.

To address these obstacles, I developed a real-time Machine Learning Framework for Quickest Detection (MLQD). To be specific, I first propose the zero-bias neural network, which removes decision bias and preferabilities from regular neural networks and provides an interpretable decision process. Second, I discover …

Wildfire Early Detection System (Weds), Mason Mciver, Vincent Liang, Jeanreno Racines

Electrical Engineering

With climate change causing an increase in temperature over the past several decades, wildfires have been burning hotter and moving quicker leaving a trail of destruction in their path. Detecting a wildfire early allows firefighters to respond efficiently and effectively to ensure containment. With the rise of advanced computer vision and algorithms, autonomous systems can be used to monitor and report any fire activity. Having multiple devices spread out across a large area will allow first responders to map out the fire location and track the fire. By utilizing smart technologies, property damage can be minimized and residents living in …

Early Wildfire Detection With Line Sensors, Virginia Yan

Master's Theses

Over the last few years, wildfires have become more devastating to communities as the fires are inevitably destructive to many homes, businesses, and ecosystems. Frequent wildfires also pose a significant threat to power grids and nearby residents as they can damage transmission lines and other electrical equipment, which in turn can cause major power shutdowns. Especially in western U.S., severe drought conditions and weather variability cause residents to become more vulnerable to wildfire disasters as their safety is threatened. We are incompetent to control the wildfires effectively despite existing advanced technologies. Hence, an algorithm based on energy conservation and heat …

Concusion Detection Headband Design, John Durkin, Noah Lewis, John Michel

Williams Honors College, Honors Research Projects

Concussion in sports is a prevalent medical issue. It can be difficult for medical professionals to diagnose concussions. With the fast pace nature of many sports, and the damaging effects of concussions, it is important that any concussion risks are assessed immediately. There is a growing trend of wearable technology that collects data such as steps, and provides the wearer with in-depth information regarding their performance. The Smart Headband project created a wearable that can record impact data and provide the wearer with a detailed analysis on their risk of sustaining a concussion. The Smart Headband uses accelerometers and gyroscopes …

Transform Based Approaches For The Detection Of Astrophysical Signals, Marwan Mahfud Alkhweldi

Graduate Theses, Dissertations, and Problem Reports

Development of new algorithms for the detection of isolated astrophysical pulses is of interest to radio astronomers. Both Fast Radio Bursts (FRBs) and several Rotating Radio Transients (RRATs) were detected through the application of a single pulse search algorithm. The conventional approach to detect astronomical pulses requires an exhaustive search for the correct dispersion measure. Its accelerated versions involve signal processing in Fourier transform space.

In this dissertation, we present several new transform-based approaches for the detection and analysis of astrophysical signals with the latest being the most effective and advanced of all. It is implemented in several steps. First, …

Deep Learning-Based Covid-19 Detection System Using Pulmonary Ct Scans, Rajit Nair, Adi Alhudhaif, Deepika Koundal, Rumi Iqbal Doewes, Preeti Sharma

Turkish Journal of Electrical Engineering and Computer Sciences

One of the most significant pandemics has been raised in the form of Coronavirus disease 2019 (COVID19). Many researchers have faced various types of challenges for finding the accurate model, which can automatically detect the COVID-19 using computed pulmonary tomography (CT) scans of the chest. This paper has also focused on the same area, and a fully automatic model has been developed, which can predict the COVID-19 using the chest CT scans. The performance of the proposed method has been evaluated by classifying the CT scans of community-acquired pneumonia (CAP) and other non-pneumonia. The proposed deep learning model is based …

Deep Learning Assisted Intelligent Visual And Vehicle Tracking Systems, Liang Xu

Theses and Dissertations

Sensor fusion and tracking is the ability to bring together measurements from multiple sensors of the current and past time to estimate the current state of a system. The resulting state estimate is more accurate compared with the direct sensor measurement because it balances between the state prediction based on the assumed motion model and the noisy sensor measurement. Systems can then use the information provided by the sensor fusion and tracking process to support more-intelligent actions and achieve autonomy in a system like an autonomous vehicle. In the past, widely used sensor data are structured, which can be directly …

Fault Protection Considerations For Mvdc Shipboard Power Systems Operating With Pulsed-Power Loads, Marounfa Djibo, Paul Moses, Ike Flory

Electrical & Computer Engineering Faculty Publications

Medium Voltage Direct Current (MVDC) power distribution architectures are of immense interest for various shipboard power applications due to their advantages over classical MVAC distribution systems with respect to power quality, power density, and efficiency. However, MVDC are far away from maturity when compared to MVAC with respect to fault detection and isolation. Currently, there are no standards available for applying MVDC protection systems in shipboard applications. Furthermore, due to the absence of zero crossings in DC waveforms and unique transient fault signatures, it is challenging to design effective protection system schemes to isolate faults via conventional protection systems. This …