Electrical and Computer Engineering Commons^™

Machine Learning Land Cover And Land Use Classification Of 4-Band Satellite Imagery, Lorelei Turner, Torrey J. Wagner, Paul Auclair, Brent T. Langhals

Faculty Publications

Land-cover and land-use classification generates categories of terrestrial features, such as water or trees, which can be used to track how land is used. This work applies classical, ensemble and neural network machine learning algorithms to a multispectral remote sensing dataset containing 405,000 28x28 pixel image patches in 4 electromagnetic frequency bands. For each algorithm, model metrics and prediction execution time were evaluated, resulting in two families of models; fast and precise. The prediction time for an 81,000-patch group of predictions wasmodels, and >5s for the precise models, and there was not a significant change in prediction time when a …

Security Hardening Of Intelligent Reflecting Surfaces Against Adversarial Machine Learning Attacks, Ferhat Ozgur Catak, Murat Kuzlu, Haolin Tang, Evren Catak, Yanxiao Zhao

Engineering Technology Faculty Publications

Next-generation communication networks, also known as NextG or 5G and beyond, are the future data transmission systems that aim to connect a large amount of Internet of Things (IoT) devices, systems, applications, and consumers at high-speed data transmission and low latency. Fortunately, NextG networks can achieve these goals with advanced telecommunication, computing, and Artificial Intelligence (AI) technologies in the last decades and support a wide range of new applications. Among advanced technologies, AI has a significant and unique contribution to achieving these goals for beamforming, channel estimation, and Intelligent Reflecting Surfaces (IRS) applications of 5G and beyond networks. However, the …

Non-Parametric Stochastic Autoencoder Model For Anomaly Detection, Raphael B. Alampay, Patricia Angela R. Abu

Department of Information Systems & Computer Science Faculty Publications

Anomaly detection is a widely studied field in computer science with applications ranging from intrusion detection, fraud detection, medical diagnosis and quality assurance in manufacturing. The underlying premise is that an anomaly is an observation that does not conform to what is considered to be normal. This study addresses two major problems in the field. First, anomalies are defined in a local context, that is, being able to give quantitative measures as to how anomalies are categorized within its own problem domain and cannot be generalized to other domains. Commonly, anomalies are measured according to statistical probabilities relative to the …

Explainable Data-Driven Motor Condition Monitoring And Fault Disgnosis, Yuming Wang

Theses and Dissertations--Electrical and Computer Engineering

Industrial motors are widely used in various fields such as power generation, mining, and manufacturing. Motor faults and time-consuming maintenance process will lead to serious economic losses in this context. To monitor motor faults and detect motor conditions, different types of sensors that can test vibration and current signals are mounted on motors. However, the main challenge was how to use information gained by sensors to analyze or diagnose motor conditions.

Machine learning is a popular technology in recent years, and it's very suitable for crunching and analyzing data. As an important subset of machine learning, deep learning is suitable …

Arithfusion: An Arithmetic Deep Model For Temporal Remote Sensing Image Fusion, Md Reshad Ul Hoque, Jian Wu, Chiman Kwan, Krzysztof Koperski, Jiang Li

Electrical & Computer Engineering Faculty Publications

Different satellite images may consist of variable numbers of channels which have different resolutions, and each satellite has a unique revisit period. For example, the Landsat-8 satellite images have 30 m resolution in their multispectral channels, the Sentinel-2 satellite images have 10 m resolution in the pan-sharp channel, and the National Agriculture Imagery Program (NAIP) aerial images have 1 m resolution. In this study, we propose a simple yet effective arithmetic deep model for multimodal temporal remote sensing image fusion. The proposed model takes both low- and high-resolution remote sensing images at t₁ together with low-resolution images at a …

Uptpu: Improving Energy Efficiency Of A Tensor Processing Unit Through Underutilization Based Power-Gating, Pramesh Pandey, Noel Daniel Gundi, Koushik Chakraborty, Sanghamitra Roy

Electrical and Computer Engineering Faculty Publications

The AI boom is bringing a plethora of domain-specific architectures for Neural Network computations. Google's Tensor Processing Unit (TPU), a Deep Neural Network (DNN) accelerator, has replaced the CPUs/GPUs in its data centers, claiming more than 15 × rate of inference. However, the unprecedented growth in DNN workloads with the widespread use of AI services projects an increasing energy consumption of TPU based data centers. In this work, we parametrize the extreme hardware underutilization in TPU systolic array and propose UPTPU: an intelligent, dataflow adaptive power-gating paradigm to provide a staggering 3.5 ×-6.5× energy efficiency to TPU for different input …

Deep Learning Based Speech Enhancement And Its Application To Speech Recognition, Ju Lin

All Dissertations

Speech enhancement is the task that aims to improve the quality and the intelligibility of a speech signal that is degraded by ambient noise and room reverberation. Speech enhancement algorithms are used extensively in many audio- and communication systems, including mobile handsets, speech recognition, speaker verification systems and hearing aids. Recently, deep learning has achieved great success in many applications, such as computer vision, nature language processing and speech recognition. Speech enhancement methods have been introduced that use deep-learning techniques, as these techniques are capable of learning complex hierarchical functions using large-scale training data. This dissertation investigates the deep learning …

Fabrication Of Oxide-Based Memristors For Neural Networks, Jamison E. Wagner

Electrical and Computer Engineering ETDs

This thesis discusses what a memristor is, how it is hypothesized to work and the fabrication work undertaken with hafnia and titania-based ultrathin oxide films. In addition, the electrical tests utilized to characterize the physical performance of the memristors including but not limited to, their IV hysteresis responses, yield rates and overall reliability. The results and discussion of this work are aimed at better understanding how fabrication of memristive devices can be further improved for future work.

Adaptive Activations And Shift Invariance In Shallow Convolutional Neural Networks, Chinmay Appa Rane

Electrical Engineering Dissertations - Archive

Deep learning training training algorithms are a huge success in recent years in many fields including speech, text,image video etc. Deeper and deeper layers are proposed with huge success with resnet structures having around 152 layers. Shallow convolution neural networks(CNN's) are still an active research, where some phenomena are still unexplanined. CNN's are assumed to be invariant to shift due to its architecture, but recent studies have shown other wise. Apart from shift invariance, activation functions used in the network are of utmost importance, as they provide non linearity to the networks. Relu's are the most commonly used activation function. …

Flying Free: A Research Overview Of Deep Learning In Drone Navigation Autonomy, Thomas Lee, Susan Mckeever, Jane Courtney

Articles

With the rise of Deep Learning approaches in computer vision applications, significant strides have been made towards vehicular autonomy. Research activity in autonomous drone navigation has increased rapidly in the past five years, and drones are moving fast towards the ultimate goal of near-complete autonomy. However, while much work in the area focuses on specific tasks in drone navigation, the contribution to the overall goal of autonomy is often not assessed, and a comprehensive overview is needed. In this work, a taxonomy of drone navigation autonomy is established by mapping the definitions of vehicular autonomy levels, as defined by the …

Unsupervised Data Driven Machine Learning In Hyperspectral Imaging And Echocardiography Videos, Kazi Tanzeem Shahid

Electrical Engineering Dissertations - Archive

This work discusses the problem of unsupervised classification in images. Conventional methods approached this problem with the naive assumption that the relationship among the pixels' information can be expressed sufficiently in a linear manner. However, higher accuracy was established by implementing kernel-based expressions of data to express the non-linear relationship of that data in a linear manner, when mapped in a higher dimensional space. This process allows much more effective clustering performances by increasing the informativeness of the data. Hyperspectral images, being limited in spatial resolution as a tradeoff for the significantly higher number of channels compared to traditional images, …

Constructing And Analyzing Neural Network Dynamics For Information Objectives And Working Memory, Elham Ghazizadeh Ahsaei

McKelvey School of Engineering Graduate Student Theses & Dissertations

Creation of quantitative models of neural functions and discovery of underlying principles of how neural circuits learn and compute are long-standing challenges in the field of neuroscience. In this work, we blend ideas from computational neuroscience, information and control theories with machine learning to shed light on how certain key functions are encoded through the dynamics of neural circuits. In this regard, we pursue the ‘top-down’ modeling approach of engineering neuroscience to relate brain functions to basic generative dynamical mechanisms. Our approach encapsulates two distinct paradigms in which ‘function’ is understood. In the first part of this research, we explore …

Evolutionary Neural Networks For Improving The Prediction Performance Ofrecommender Systems, Berna Şeref, Gazi̇ Erkan Bostanci, Mehmet Serdar Güzel

Turkish Journal of Electrical Engineering and Computer Sciences

Recommender systems provide recommendations to users using background data such as ratings of users about items and features of items. These systems are used in several areas such as e-commerce, news websites, and article websites. By using recommender systems, customers are provided with relevant data as soon as possible and are able to make good decisions. There are more studies about recommender systems and improving their performance. In this study, prediction performances of neural networks are evaluated and their performances are improved using genetic algorithms. Performances obtained in this study are compared with those of other studies. After that, superiority …

Formal Verification Of The Adversarial Robustness Property Of Deep Neural Networks Through Dimension Reduction Heuristics, Refutation-Based Abstraction, And Partitioning, Joshua Smith

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

Neural networks are tools that are often used to perform functions such as object recognition in images, speech-to-text, and general data classification. Because neural networks have been successful at approximating these functions that are difficult to explicitly write, they are seeing increased usage in fields such as autonomous driving, airplane collision avoidance systems, and other safety-critical applications. Due to the risks involved with safety-critical systems, it is important to provide guarantees about the networks performance under certain conditions. As an example, it is critically important that self driving cars with neural network based vision systems correctly identify pedestrians 100% of …

Analysis Of Information Security Methods In Biosystems And Application Of Intelligent Tools In Information Security Systems, Sherzod Sayfullaev

Chemical Technology, Control and Management

In this paper, the methods of information protection in bio systems are studied. The paper considers the use of intelligent tools in information security systems and the use of adaptive information security systems. Several articles on the field of information protection in bio systems are analyzed. Disadvantages and advantages of neural network technologies in modern information security systems are described. The characteristics of bio systems and the specificity of DNA, the main features of the DNA code that provide information security and functional stability of bio systems data protection structure. Application of intelligent tools to create a comprehensive adaptive protection …

Continuous Learning In A Single-Incremental-Task Scenario With Spike Features, Ruthvik Vaila, John Chiasson, Vishal Saxena

Electrical and Computer Engineering Faculty Publications and Presentations

Deep Neural Networks (DNNs) have two key deficiencies, their dependence on high precision computing and their inability to perform sequential learning, that is, when a DNN is trained on a first task and the same DNN is trained on the next task it forgets the first task. This phenomenon of forgetting previous tasks is also referred to as catastrophic forgetting. On the other hand a mammalian brain outperforms DNNs in terms of energy efficiency and the ability to learn sequentially without catastrophically forgetting. Here, we use bio-inspired Spike Timing Dependent Plasticity (STDP) in the feature extraction layers of the network …

Learning Set Representations For Lwir In-Scene Atmospheric Compensation, Nicholas M. Westing, Kevin C. Gross, Brett J. Borghetti, Jacob A. Martin, Joseph Meola

Faculty Publications

Atmospheric compensation of long-wave infrared (LWIR) hyperspectral imagery is investigated in this article using set representations learned by a neural network. This approach relies on synthetic at-sensor radiance data derived from collected radiosondes and a diverse database of measured emissivity spectra sampled at a range of surface temperatures. The network loss function relies on LWIR radiative transfer equations to update model parameters. Atmospheric predictions are made on a set of diverse pixels extracted from the scene, without knowledge of blackbody pixels or pixel temperatures. The network architecture utilizes permutation-invariant layers to predict a set representation, similar to the work performed …

Improving Aeromagnetic Calibration Using Artificial Neural Networks, Mitchell C. Hezel

Theses and Dissertations

The Global Positioning System (GPS) has proven itself to be the single most accurate positioning system available, and no navigation suite is found without a GPS receiver. Even basic GPS receivers found in most smartphones can easily provide high quality positioning information at any time. Even with its superb performance, GPS is prone to jamming and spoofing, and many platforms requiring accurate positioning information are in dire need of other navigation solutions to compensate in the event of an outage, be the cause hostile or natural. Indeed, there has been a large push to achieve an alternative navigation capability which …

Neuro-Fuzzy Modeling For Predictive Control Systems With Complex Technological Processes And Production, Yusupbekov Nodirbek, Shukhrat Gulyamov, Malika Doshchanova

Chemical Technology, Control and Management

The paper implements a modification of a fuzzy neural network, which is suitable for predictive control purposes. Adaptation of a multidimensional programmable controller based on a neural algorithm for the back propagation of forecasting errors is proposed, as well as neural parametric identification of a fuzzy mathematical model of complex technological processes and production based on experimental data and expert estimates.

Context-Aware System For Glycemic Control In Diabetic Patients Using Neural Networks, Owais Bhat, Dawood A. Khan

Turkish Journal of Electrical Engineering and Computer Sciences

Diabetic patients are quite hesitant in engaging in normal physiological activities due to difficulties associated with diabetes management. Over the last few decades, there have been advancements in the computational power of embedded systems and glucose sensing technologies. These advancements have attracted the attention of researchers around the globe developing automatic insulin delivery systems. In this paper, a method of closed-loop control of diabetes based on neural networks is proposed. These neural networks are used for making predictions based on the clinical data of a patient. A neural network feedback controller is also designed to provide a glycemic response by …

Crash Course Learning: An Automated Approach To Simulation-Driven Lidar-Basedtraining Of Neural Networks For Obstacle Avoidance In Mobile Robotics, Stanko Kruzic, Josip Music, Mirjana Bonkovic, Frantisek Duchon

Turkish Journal of Electrical Engineering and Computer Sciences

This paper proposes and implements a self-supervised simulation-driven approach to data collection used for training of perception-based shallow neural networks for mobile robot obstacle avoidance. In the approach, a 2D LiDAR sensor was used as an information source for training neural networks. The paper analyzes neural network performance in terms of numbers of layers and neurons, as well as the amount of data needed for reliable robot operation. Once the best architecture is identified, it is trained using only data obtained in simulation and then implemented and tested on a real robot (Turtlebot 2) in several simulations and real-world scenarios. …

Amodal Instance Segmentation And Multi-Object Tracking With Deep Pixel Embedding, Yanfeng Liu

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

This thesis extends upon the representational output of semantic instance segmentation by explicitly including both visible and occluded parts. A fully convolutional network is trained to produce consistent pixel-level embedding across two layers such that, when clustered, the results convey the full spatial extent and depth ordering of each instance. Results demonstrate that the network can accurately estimate complete masks in the presence of occlusion and outperform leading top-down bounding-box approaches.

The model is further extended to produce consistent pixel-level embeddings across two consecutive image frames from a video to simultaneously perform amodal instance segmentation and multi-object tracking. No post-processing …

Bitcoin Price Prediction Using Neural Networks, Vladislav Killiakov

Electrical Engineering

In this project, I will investigate the performance of several major neural network architectures for the task of Bitcoin price prediction. Bitcoin is a cryptocurrency that is recently becoming increasingly more popular, and more widely adopted as a financial instrument. As a result, more efforts have been made in the past several years to model and predict its price. However, to this moment a large portion of work on Bitcoin price modeling was done using statistical or classical machine learning techniques. At the same time, other artificial intelligence based prediction techniques, and specifically neural networks, have not been explored to …

Stochastic Resonance Enables Bpp/Log∗ Complexity And Universal Approximation In Analog Recurrent Neural Networks, Emmett Redd, A. Steven Younger, Tayo Obafemi-Ajayi

Electrical and Computer Engineering Faculty Research & Creative Works

Stochastic resonance (SR) is a natural process that without limit increases the precision of signal measurements in biological and physical sciences. Most artificial neural networks (NNs) are implemented on digital computers of fixed precision. A NN accessing universal approximation and a computational complexity class more powerful that of a Turing machine needs analog signals utilizing SR's limitless precision increase. This paper links an analog recurrent (AR) NN theorem, SR, BPP/log∗ (a physically realizable, super-Turing computation class), and universal approximation so NNs following them can be made computationally more powerful. An optical neural network mimicking chaos indicates super-Turing computation has been …

Receptive Fields Optimization In Deep Learning For Enhanced Interpretability, Diversity, And Resource Efficiency., Babajide Odunitan Ayinde

Electronic Theses and Dissertations

In both supervised and unsupervised learning settings, deep neural networks (DNNs) are known to perform hierarchical and discriminative representation of data. They are capable of automatically extracting excellent hierarchy of features from raw data without the need for manual feature engineering. Over the past few years, the general trend has been that DNNs have grown deeper and larger, amounting to huge number of final parameters and highly nonlinear cascade of features, thus improving the flexibility and accuracy of resulting models. In order to account for the scale, diversity and the difficulty of data DNNs learn from, the architectural complexity and …

Convolutional Neural Network Architecture Study For Aerial Visual Localization, Jedediah M. Berhold

Theses and Dissertations

In unmanned aerial navigation the ability to determine the aircraft's location is essential for safe flight. The Global Positioning System (GPS) is the default modern application used for geospatial location determination. GPS is extremely robust, very accurate, and has essentially solved aerial localization. Unfortunately, the signals from all Global Navigation Satellite Systems (GNSS) to include GPS can be jammed or spoofed. To this response it is essential to develop alternative systems that could be used to supplement navigation systems, in the event of a lost GNSS signal. Public and governmental satellites have provided large amounts of high-resolution satellite imagery. These …

Supervised Machine Learning Techniques For Short-Term Load Forecasting, Harish Amarasundar

Electronic Theses and Dissertations

Electric Load Forecasting is essential for the utility companies for energy management based on the demand. Machine Learning Algorithms has been in the forefront for prediction algorithms. This Thesis is mainly aimed to provide utility companies with a better insight about the wide range of Techniques available to forecast the load demands based on different scenarios. Supervised Machine Learning Algorithms were used to come up with the best possible solution for Short-Term Electric Load forecasting. The input Data set has the hourly load values, Weather data set and other details of a Day. The models were evaluated using MAPE and …

Feature Extraction Using Spiking Convolutional Neural Networks, Ruthvik Vaila, John Chiasson, Vishal Saxena

Electrical and Computer Engineering Faculty Publications and Presentations

Spiking neural networks are biologically plausible counterparts of the artificial neural networks, artificial neural networks are usually trained with stochastic gradient descent and spiking neural networks are trained with spike timing dependant plasticity. Training deep convolutional neural networks is a memory and power intensive job. Spiking networks could potentially help in reducing the power usage. There is a large pool of tools for one to chose to train artificial neural networks of any size, on the other hand all the available tools to simulate spiking neural networks are geared towards computational neuroscience applications and they are not suitable for real …

An Automated Snick Detection And Classification Scheme As A Cricket Decision Review System, Aftab Khan, Syed Qadir Hussain, Muhammad Waleed, Ashfaq Khan, Umair Khan

Turkish Journal of Electrical Engineering and Computer Sciences

Umpire decisions can greatly affect the outcome of a cricket game. When there is doubt about the umpire?s call for a decision, a decision review system (DRS) may be brought into play by a batsman or bowler to validate the decision. Recently, the latest technologies, including Hotspot, Hawk-eye, and Snickometer, have been employed when there is doubt among the on-field umpire, batsman, or bowlers. This research is a step forward in gaging the true class of a snick generated from the contact of the cricket ball with either (i) the bat, (ii) gloves, (iii) pad, or (iv) a combination of …

Robust Engineering Of Dynamic Structures In Complex Networks, Walter Botongo Bomela

McKelvey School of Engineering Graduate Student Theses & Dissertations

Populations of nearly identical dynamical systems are ubiquitous in natural and engineered systems, in which each unit plays a crucial role in determining the functioning of the ensemble. Robust and optimal control of such large collections of dynamical units remains a grand challenge, especially, when these units interact and form a complex network. Motivated by compelling practical problems in power systems, neural engineering and quantum control, where individual units often have to work in tandem to achieve a desired dynamic behavior, e.g., maintaining synchronization of generators in a power grid or conveying information in a neuronal network; in this dissertation, …