Engineering Commons^™

Using Multifactor Inputs Bp Neural Network To Make Power Consumption Prediction, Hao Song

Graduate Dissertations and Theses

With the development of modern information and technology (IT), smart grids became one of the major components of smart cities, to take full advantage of the smart grid, the capability of intelligent scheduling and planning of electricity delivery is essential. For this purpose, researchers have investigated methodologies for power consumption prediction and demand side management (DSM). In addition, conducting a comprehensive analysis and obtaining an accurate evaluation of power consumption are the premise and basis for a more robust and efficient power grid design and transformation. Therefore, it is meaningful to explore forecasting models that are able to reflect the …

Cyber-Physical Embedded Systems With Transient Supervisory Command And Control: A Framework For Validating Safety Response In Automated Collision Avoidance Systems, Daniel K. Trembley

Graduate Dissertations and Theses

The ability to design and engineer complex and dynamical Cyber-Physical Systems (CPS) requires a systematic view that requires a definition of level of automation intent for the system. Since CPS covers a diverse range of systemized implementations of smart and intelligent technologies networked within a system of systems (SoS), the terms “smart” and “intelligent” is frequently used in describing systems that perform complex operations with a reduced need of a human-agent. The difference between this research and most papers in publication on CPS is that most other research focuses on the performance of the CPS rather than on the correctness …

Image Series Prediction Via Convolutional Recurrent Neural Networks With Limited Training Data, Zao Zhang

Graduate Dissertations and Theses

This thesis focuses on developing deep learning algorithms that can be used to forecast the image series under limited training data. Specifically, we study the problem of using a pine tree's existing appearance images to predict its future appearance images.

Side-Information For Steganography Design And Detection, Tomas Denemark

Graduate Dissertations and Theses

Today, the most secure steganographic schemes for digital images embed secret messages while minimizing a distortion function that describes the local complexity of the content. Distortion functions are heuristically designed to predict the modeling error, or in other words, how difficult it would be to detect a single change to the original image in any given area. This dissertation investigates how both the design and detection of such content-adaptive schemes can be improved with the use of side-information.

We distinguish two types of side-information, public and private: Public side-information is available to the sender and at least in part also …

Detection And Interpretation Of Fluorescence Signals Generated By Excitable Cells And Tissues, Anthony J. Costantino

Graduate Dissertations and Theses

Part 1: High-Sensitivity Amplifiers for Detecting Fluorescence
Monitoring electrical activity and Cai 2+ transients in biological tissues and individual cells increasingly utilizes optical sensors based on voltage-dependent and Cai 2+-dependent fluorescent dyes. However, achieving satisfactory signal-to-noise ratios (SNR) often requires increased illumination intensities and/or dye concentrations, which results in photo-toxicity, photo-bleaching and other adverse effects limiting the utility of optical recordings. The most challenging are the recordings from individual cardiac myocytes and neurons. Here we demonstrate that by optimizing a conventional transimpedance topology one can achieve a 10-20 fold increase of sensitivity with photodiode-based recording systems (dependent on …