Engineering Commons^™

Skynet: Memristor-Based 3d Ic For Artificial Neural Networks, Sachin Bhat

Masters Theses

Hardware implementations of artificial neural networks (ANNs) have become feasible due to the advent of persistent 2-terminal devices such as memristor, phase change memory, MTJs, etc. Hybrid memristor crossbar/CMOS systems have been studied extensively and demonstrated experimentally. In these circuits, memristors located at each cross point in a crossbar are, however, stacked on top of CMOS circuits using back end of line processing (BOEL), limiting scaling. Each neuron’s functionality is spread across layers of CMOS and memristor crossbar and thus cannot support the required connectivity to implement large-scale multi-layered ANNs.

This work proposes a new fine-grained 3D integrated circuit technology …

Convolutional Neural Network Based Localized Classification Of Uterine Cervical Cancer Digital Histology Images, Haidar A. Almubarak, R. Joe Stanley, Rodney Long, Sameer Antani, George Thoma, Rosemary Zuna, Shelliane R. Frazier

Electrical and Computer Engineering Faculty Research & Creative Works

In previous research, we introduced an automated localized, fusion-based algorithm to classify squamous epithelium into Normal, CIN1, CIN2, and CIN3 grades of cervical intraepithelial neoplasia (CIN). The approach partitioned the epithelium into 10 segments. Image processing and machine vision algorithms were used to extract features from each segment. The features were then used to classify the segment and the result was fused to classify the whole epithelium. This research extends the previous research by dividing each of the 10 segments into 3 parts and uses a convolutional neural network to classify the 3 parts. The result is then fused to …

Can Deep Learning Techniques Improve The Risk Adjusted Returns From Enhanced Indexing Investment Strategies, Anthony Grace

Dissertations

Deep learning techniques have been widely applied in the field of stock market prediction particularly with respect to the implementation of active trading strategies. However, the area of portfolio management and passive portfolio management in particular has been much less well served by research to date. This research project conducts an investigation into the science underlying the implementation of portfolio management strategies in practice focusing on enhanced indexing strategies. Enhanced indexing is a passive management approach which introduces an element of active management with the aim of achieving a level of active return through small adjustments to the portfolio weights. …

A Novel Application Of Machine Learning Methods To Model Microcontroller Upset Due To Intentional Electromagnetic Interference, Rusmir Bilalic

Electrical and Computer Engineering ETDs

A novel application of support vector machines (SVMs), artificial neural networks (ANNs), and Gaussian processes (GPs) for machine learning (GPML) to model microcontroller unit (MCU) upset due to intentional electromagnetic interference (IEMI) is presented. In this approach, an MCU performs a counting operation (0-7) while electromagnetic interference in the form of a radio frequency (RF) pulse is direct-injected into the MCU clock line. Injection times with respect to the clock signal are the clock low, clock rising edge, clock high, and the clock falling edge periods in the clock window during which the MCU is performing initialization and executing the …

Thermophysical Properties Of Thin Fibers Via Photothermal Quantum Dot Fluorescence Spectral Shape-Based Thermometry, Troy Munro, Liwang Liu, Heng Ban, Christ Glorieux

Faculty Publications

To improve predictions of composite behavior under thermal loads, there is a need to measure the axial thermophysical properties of thin fibers. Current methods to accomplish this have prohibitively long lead times due to extensive sample preparation. This work details the use of quantum dots thermomarkers to measure the surface temperature of thin fibers in a non-contact manner and determine the fibers’ thermal diffusivity. Neural networks are trained on extracting the temperature of a sample from fluorescence spectra in calibrated, steady-state conditions, based on different spectral features such as peak intensity and peak wavelength. The trained neural networks are then …

Ecg Classification Using Adaptive Neuro-Fuzzy Inference System, Jason N. Rivera, Kelsey C. Rodriguez

Electrical Engineering

ECG classification using Adaptive Neuro-Fuzzy Inference System (ANFIS), sponsored by Professor Yu, involves the diagnosis of six cardiovascular conditions by analyzing one single neural network. Today’s ECG signal instrumentation does not have the ability to characterize cardiovascular diseases without a doctor’s complete evaluation and diagnosis. Our project gives a promising solution to the inability in the current market’s ECG signal instrumentation to correctly evaluate and diagnose cardiovascular diseases. ECG signal reportings is a non-invasive process that will lead to many more applications of advanced signal processing and data analysis/diagnosis of cardiovascular diseases. The inputs to the ANFIS are annotations of …

A Leaky Integrate-And-Fire Neuron With Adjustable Refractory Period And Spike Frequency Adaptation, Jacob N. Healy

Electrical and Computer Engineering ETDs

As standard CMOS technology approaches its physical limitations there is increased motivation to explore new computing paradigms. One possible path forward is to develop an array of computational architectures which specialize in distinct tasks. Neural computing architectures excel at pattern recognition and processing low-fidelity sensory input, but one of the biggest challenges in the field has been implementing architectures which strike an appropriate balance between biologically-plausible performance and the simplicity needed to make large neural systems practical. This work proposes a new VLSI neural architecture which seeks to provide such a balance.

The design described here builds on an implementation …

Neural Collaborative Filtering, Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

In recent years, deep neural networks have yielded immense success on speech recognition, computer vision and natural language processing. However, the exploration of deep neural networks on recommender systems has received relatively less scrutiny. In this work, we strive to develop techniques based on neural networks to tackle the key problem in recommendation --- collaborative filtering --- on the basis of implicit feedback.Although some recent work has employed deep learning for recommendation, they primarily used it to model auxiliary information, such as textual descriptions of items and acoustic features of musics. When it comes to model the key factor in …

Development Of An Analysis And Design Optimization Framework For Marine Propellers, Ashish C. Tamhane

Mechanical & Aerospace Engineering Theses & Dissertations

In this thesis, a framework for the analysis and design optimization of ship propellers is developed. This framework can be utilized as an efficient synthesis tool in order to determine the main geometric characteristics of the propeller but also to provide the designer with the capability to optimize the shape of the blade sections based on their specific criteria.

A hybrid lifting-line method with lifting-surface corrections to account for the three-dimensional flow effects has been developed. The prediction of the correction factors is achieved using Artificial Neural Networks and Support Vector Regression. This approach results in increased approximation accuracy compared …

Impact Of Reviewer Social Interaction On Online Consumer Review Fraud Detection, Kunal Goswami, Younghee Park, Chungsik Song

Faculty Publications

Background Online consumer reviews have become a baseline for new consumers to try out a business or a new product. The reviews provide a quick look into the application and experience of the business/product and market it to new customers. However, some businesses or reviewers use these reviews to spread fake information about the business/product. The fake information can be used to promote a relatively average product/business or can be used to malign their competition. This activity is known as reviewer fraud or opinion spam. The paper proposes a feature set, capturing the user social interaction behavior to identify fraud. …

A Cooperative Neural Network Approach For Enhancing Data Traffic Prediction, Salihu Aish Abdulkarim, Isa Abdullahi Lawal

Turkish Journal of Electrical Engineering and Computer Sciences

This paper addresses the problem of learning a regression model for the prediction of data traffic in a cellular network. We proposed a cooperative learning strategy that involves two Jordan recurrent neural networks (JNNs) trained using the firefly algorithm (FFA) and resilient backpropagation algorithm (Rprop), respectively. While the cooperative capability of the learning process ensures the effectiveness of the regression model, the recurrent nature of the neural networks allows the model to handle temporally evolving data. Experiments were carried out to evaluate the proposed approach using high-speed downlink packet access data demand and throughput measurements collected from different cell sites …