Engineering Commons^™

Emotion Detection Using An Ensemble Model Trained With Physiological Signals And Inferred Arousal-Valence States, Matthew Nathanael Gray

Electrical & Computer Engineering Theses & Dissertations

Affective computing is an exciting and transformative field that is gaining in popularity among psychologists, statisticians, and computer scientists. The ability of a machine to infer human emotion and mood, i.e. affective states, has the potential to greatly improve human-machine interaction in our increasingly digital world. In this work, an ensemble model methodology for detecting human emotions across multiple subjects is outlined. The Continuously Annotated Signals of Emotion (CASE) dataset, which is a dataset of physiological signals labeled with discrete emotions from video stimuli as well as subject-reported continuous emotions, arousal and valence, from the circumplex model, is used for …

Machine Learning Classification Of Digitally Modulated Signals, James A. Latshaw

Electrical & Computer Engineering Theses & Dissertations

Automatic classification of digitally modulated signals is a challenging problem that has traditionally been approached using signal processing tools such as log-likelihood algorithms for signal classification or cyclostationary signal analysis. These approaches are computationally intensive and cumbersome in general, and in recent years alternative approaches that use machine learning have been presented in the literature for automatic classification of digitally modulated signals. This thesis studies deep learning approaches for classifying digitally modulated signals that use deep artificial neural networks in conjunction with the canonical representation of digitally modulated signals in terms of in-phase and quadrature components. Specifically, capsule networks are …

Deep Cellular Recurrent Neural Architecture For Efficient Multidimensional Time-Series Data Processing, Lasitha S. Vidyaratne

Electrical & Computer Engineering Theses & Dissertations

Efficient processing of time series data is a fundamental yet challenging problem in pattern recognition. Though recent developments in machine learning and deep learning have enabled remarkable improvements in processing large scale datasets in many application domains, most are designed and regulated to handle inputs that are static in time. Many real-world data, such as in biomedical, surveillance and security, financial, manufacturing and engineering applications, are rarely static in time, and demand models able to recognize patterns in both space and time. Current machine learning (ML) and deep learning (DL) models adapted for time series processing tend to grow in …

Virtual Satcom, Long Range Broadband Digital Communications, Dennis George Watson

Electrical & Computer Engineering Theses & Dissertations

The current naval strategy is based on a distributed force, networked together with high-speed communications that enable operations as an intelligent, fast maneuvering force. Satellites, the existing network connector, are weak and vulnerable to attack. HF is an alternative, but it does not have the information throughput to meet the distributed warfighting need. The US Navy does not have a solution to reduce dependency on space-based communication systems while providing the warfighter with the required information speed.

Virtual SATCOM is a solution that can match satellite communications (SATCOM) data speed without the vulnerable satellite. It is wireless communication on a …

Demonstration Of Visible And Near Infrared Raman Spectrometers And Improved Matched Filter Model For Analysis Of Combined Raman Signals, Alexander Matthew Atkinson

Electrical & Computer Engineering Theses & Dissertations

Raman spectroscopy is a powerful analysis technique that has found applications in fields such as analytical chemistry, planetary sciences, and medical diagnostics. Recent studies have shown that analysis of Raman spectral profiles can be greatly assisted by use of computational models with achievements including high accuracy pure sample classification with imbalanced data sets and detection of ideal sample deviations for pharmaceutical quality control. The adoption of automated methods is a necessary step in streamlining the analysis process as Raman hardware becomes more advanced. Due to limits in the architectures of current machine learning based Raman classification models, transfer from pure …

Classification Of Digital Communication Signal Modulation Schemes In Multipath Environments Using Higher Order Statistics, Meena Sreekantamurthy

Electrical & Computer Engineering Theses & Dissertations

Automatic identification and classification of modulation schemes in communication signals and decoding of information from the captured signals has assumed great importance recently in the wireless communication industry. Advancements in communications have introduced a large variety of modulation schemes in the transmitted signals; consequently, reliable detection of the modulation scheme in the intercepted signal has become an important issue in communications. It is the aim of this thesis to address this issue of reliable detection. Therefore, this research is focused on modeling and simulation of an automatic modulation classifier and, in particular, on the development of algorithms to use higher …

Impact Of Primary User Activity On The Performance Of Energy-Based Spectrum Sensing In Cognitive Radio Systems, Sara L. Macdonald

Electrical & Computer Engineering Theses & Dissertations

Increasing numbers of wireless devices and mobile data requirements have led to a spectrum shortage. However spectrum utilization percentages are often low due to the current static spectrum allocation process where primary users (PUs) are given exclusive use to spectrum. Several mechanisms to increase spectrum utilization have been proposed including opportunistic spectrum access (OSA). Cognitive Radio (CR) is an emerging concept in wireless communication systems that aims to enable OSA in licensed frequencies by secondary users (SUs). CR systems are expected to sense the spectrum in order to determine if the PU is transmitting. Therefore OSA performance relies on the …

Embedding Gps Data Into Speech Signal, Kagan Can

Electrical & Computer Engineering Theses & Dissertations

Communication between deployed troops is very important on a battlefield. The real time knowledge of the location of the communicating patter is also very important in many situations because if you do not know the exact position of your units you cannot give correct orders. A minor error in an order can cause fatal results or lead to defeat. In many cases the position of the units is given through the speech channel by simply speaking the coordinates of the location. This can cause misunderstandings due to misinterpretation of the speech and makes it unsafe to rely on such communications. …

A Novel Digital Audio Watermarking Approach By Embedding Coefficients In Discrete Cosine Transform Domain, Erol Duymaz

Electrical & Computer Engineering Theses & Dissertations

Watermarking is a basic secure communication method. It is used for embedding a recognizable pattern in media in such a manner that modification of the media also modifies the pattern, thus making it easy to detect the modification. This technique and its variants have many practical applications pertaining to secure communications, media verification, etc. Digital audio watermarking is a technique for embedding data within an audio signal in such a way that the original and the modified audio signals are essentially identical. The embedded data can be used for various purposes such as secure communication in military applications, owner identification …

A Robust Method To Detect Concealed Weapons, Anand Gone

Electrical & Computer Engineering Theses & Dissertations

Concealed weapons detection is a large problem that is faced by the Police Department nowadays. There are many disasters caused by poor detection of the weapons. Since public safety is at risk there is a need to design an efficient detector that can detect the weapons hidden under the clothing. This thesis presents a novel method for detecting concealed weapons under clothing using image processing techniques. In this thesis IR imagery is used to capture an image which works on the principle of law of black body radiation. Image thresholding is performed on the captured data using Sauvola's adaptive thresholding …

Gaussian Mixture Models And Neural Networks For Automatic Speaker Identification, Usha Gayatri Chalkapally

Electrical & Computer Engineering Theses & Dissertations

Automatic Speaker Recognition is the process of automatically recognizing who is speaking on the basis of individual information contained in speech signals. This technique of Automatic Speaker Recognition makes it possible to use the speaker's voice to verify their identity and control access to services such as voice dialing, banking by telephone, telephone shopping, database access services, information services, voice mail, security control for confidential information areas, and remote access to computers.

In this thesis, the techniques of Gaussian Mixture Models and Neural Networks for Automatic Speaker Identification are presented. Algorithms for Speaker Identification using Gaussian Mixture Models were developed, …

Electromagnetic Wave Propagation Prediction For Wireless Networks Inside Boeing Fuselages, Mennatoallah Youssef

Electrical & Computer Engineering Theses & Dissertations

Commercial grade software is intended for electromagnetic predictions within office buildings; it was used to develop models to analyze propagation inside airplane fuselages. This study shows that Wireless XGTD and Insite software can accurately predict power propagation within airplane fuselages. Current work uses fuselage models, which contain additional internal components. A comparison was made between empty and full fuselage to examine the effects of internal components. Two propagation model types [Fast 3D and Full 3D] were also compared for accuracy to experimental study. It was concluded that completed fuselages are suggested for further simulation study as well as that the …

A Multiplier-Less Architecture For High Speed Computation Of Multi-Dimensional Convolution, Ming Zhu Zhang

Electrical & Computer Engineering Theses & Dissertations

One of the most computationally intensive operations in digital image/video processing systems is multi-dimensional convolution. Every image/video processor needs the convolution module in its pre-processing stage. Fast and efficient design of the convolution module in an application specific system is a great challenge in VLSI (Very Large Scale Integration) design. Convolution operator requires a large set of multipliers and accumulators. A high precision multiplier takes enormous amount of VLSI area and it consumes more power. Hence reduction of the number of multipliers is another important challenge in VLSI design. A multiplier-less architecture for the design of a multi-dimensional convolution module …

Electromagnetic Propagation Prediction Inside Aircraft Cabins, Genevieve Hankins

Electrical & Computer Engineering Theses & Dissertations

Electromagnetic propagation models for signal strength prediction within aircraft cabins are essential for evaluating and designing a wireless communication system to be implemented onboard aircraft. There are many commercially available software packages for predicting wireless system performance in conventional indoor environments. It is of interest to examine the available software to determine if the aircraft's electromagnetic environment (EME) can be modeled successfully without developing an aircraft specific prediction tool. EnterprisePlanner®, a registered product of Wireless Valley Communications, Incorporated, was selected for the present effort. The performance of the prediction model was evaluated through a comparison with field measurements taken on …

A Computer-Based Articulation Training Aid For Short Words (Cata), Mukund Devarajan

Electrical & Computer Engineering Theses & Dissertations

Several improvements in the vowel articulation training aid (VATA) are described, as well as the efforts to extend the visual feedback system to operate with short words in the form of consonant, vowel and consonant (CVC). The extended version of the visual feedback system is referred to as CATA (Computer-based Articulation Training Aid); the vowel version of the aid (VATA) only operates with ten American English monopthong vowels. Improvements in VATA include the use of a neural network (NN) recognizer method to prune a large database of vowel recordings to eliminate noisy and/or mispronounced tokens. The spectral jitter problem, previously …

Evaluation Of Distributed Effects In Field Effect Transistors For High Frequency Applications, Srinivas Rowjee Cuddapah

Electrical & Computer Engineering Theses & Dissertations

Metal Semiconductor Field Effect Transistors are at the heart of currently used microwave and millimeter-wave devices. CAD (Computer Aided Design) models for MESFET are used in the development and optimization of high-speed microwave devices. The increase in the chip density demands more accurate models. A distributed small signal model was developed for a GaAs MESFET account of the high frequency effects.

The lumped model of the MESFET is inadequate at frequencies where the wavelength of operation approaches device dimensions. This is because different regions in the device can experience different amplitudes and phases of the biasing signal. In this thesis, …

Phase-Sensitive Detection Electronics For Wavelength Modulation Spectroscopy Experiments, Tyrone Pate

Electrical & Computer Engineering Theses & Dissertations

Wavelength modulation spectroscopy (WMS) is a non-intrusive detection technique, which enables the measurement of several parameters such as pressure, concentration, and temperature of a species of interest by analyzing the latter's absorption lineshape profile. The method employs a synchronous modulation and detection apparatus to increase the signal to noise ratio and hence the sensitivity of the measurement. Phase-sensitive detection and demodulation of the signal is performed at the modulation frequency and its harmonics. Research at ODU demonstrates that each particular measurement can be performed optimally at an appropriate harmonic of the modulation frequency. The most suitable harmonic depends on many …

Yet Another Algorithm For Pitch Tracking (Yaapt), Kavita Kasi

Electrical & Computer Engineering Theses & Dissertations

This thesis presents a pitch detection algorithm that is extremely robust for both high quality and telephone speech. The kernel method for this algorithm is the Normalized Cross Correlation (NCCF) reported by David Talkin [16]. Major innovations include: processing of the original acoustic signal and a nonlinearly processed version of the signal to partially restore very weak F0 components; intelligent peak picking to select multiple F0 candidates and assign merit factors; and, incorporation of highly robust pitch contours obtained from smoothed versions of low frequency portions of spectrograms. Dynamic programming is used to find the ''best" pitch track among all …

Stability Analysis And Augmentation Of A Closed-Loop Computer Control System Subject To Electromagnetic Disturbances, Mustafa Doğan

Electrical & Computer Engineering Theses & Dissertations

Most electronic and electrical equipment is not only a potential source of electromagnetic interference (EMI) but can also malfunction when exposed to certain levels of ambient EMI. This phenomena becomes more significant for digital control-computers automating the command and control performances in complex plants. Such EM disturbances can introduce transient signals on analog sensor and actuator lines, change data values on digital buses and in memory, or even produce logic changes in the CPU. The result of these so called computer upsets is the introduction of some degree of degradation in the quality of the control signal ranging from a …

Coupled Electrodynamic-Monte Carlo Simulations Of Nanoscale Gaas Terahertz Optical Mixers, Jiang Li

Electrical & Computer Engineering Theses & Dissertations

The concept of mixing or heterodyning has traditionally been used for microwaves and for radio frequency communications. However, the concept can easily be extended into the optical frequency regime. By doing so, the photomixing process can serve as a very versatile tool for both the generation of ultrahigh frequency (terahertz) and the detection of weak optical signals.

The aim of this thesis is to perform a theoretical study of the photomixing process inside GaAs devices as the non-linear elements. A coupled approach which combines the Monte Carlo simulation scheme for the carrier transport, with Maxwell's equation for the electrodynamics, has …

Material Evaluation By Pulsed Diode Laser Optoacoustics, Xiaodong Xu

Electrical & Computer Engineering Theses & Dissertations

Pulsed diode laser optoacoustic diagnostics were carried out to characterize solid sample materials. The apparatus developed is compact, portable, cost-effective and therefore very promising for both industrial as well as laboratory applications. To our knowledge, this is the first time that optoacoustic characterization and measurement have been performed with a diode laser. The method was successfully applied to measure the thickness of a multilayer structure non-intrusively. Internal cracks of the material were detected by this technique.

A theory for optoacoustic signal generation, propagation and detection is given. A numerical analysis technique is developed to solve for the expected signal. In …

Building Lms Adaptive Filters With Register-Based Fpgas, Li Ding

Electrical & Computer Engineering Theses & Dissertations

In this thesis, an 8-bit least mean squares (LMS) adaptive digital filter with 16 coefficients is implemented on a single FPGA, using the MaxPlus+2 design environment. The system is constructed as a hierarchical structure, using four different levels of design hierarchy. Subdesigns at each level of the hierarchy project are complied, fitted and simulated to test and verify their functional correctness. The complete system is tested and verified by checking the MaxPlus+2 simulator results against fixed-point integer arithmetic simulations written in Matlab. The resulting adaptive filter is subsequently mapped to the Alters FLEX I OK20TC144-3 device, resulting in a 14,500 …

Development Of A Photon Counting System For Ozone Differential Absorption Lidar Signal Detection, Bradley Allen Eccles

Electrical & Computer Engineering Theses & Dissertations

A photon counting system was assembled and integrated into an existing ozone differential absorption lidar signal detection system to improve the range of ozone measurement. Results of data extraction from decaying ozone return signals are presented. Photomultiplier tube detector models EMI 9214Q and EMI 9B17Q are evaluated and characterized. Detector operating performance was based on tube quantum efficiency, gain, dark current, and linearity. The influence of photomultiplier tube characteristics on photon counting performance are discussed along with the recommended optimum photon counting operating conditions. Two photomultiplier gating schemes, focus grid and four dynode gating, are described for use in photon …

Visual Speech Recognition Using Multiple Deformable Lip Models, Devi Chandramohan

Electrical & Computer Engineering Theses & Dissertations

Motivated by the fact that human speech perception is a bimodal process (auditory and visual), several researchers have designed and implemented automatic speech recognition (ASR) systems consisting of both audio and visual subsystems, and shown improved performance relative to traditional purely auditory systems. Several visual speech reading approaches have used deformable templates to model the shape of a speaker's lips. Deformable templates are models of image objects, which can be deformed by adjusting a set of parameters to match the object in some optimal way, as defined by a cost function. Using a single deformable lip model has disadvantages such …

An Enhanced Signal Processing Strategy For Fetal Heart Rate Detection, Charles Brewton

Electrical & Computer Engineering Theses & Dissertations

The goal of the research was to improve the signal processing strategy for an acoustic fetal heart rate monitor. The theory, implementation, and testing of several possible signal processing strategies for fetal heart rate detection are presented. The enhanced signal processing strategy implemented is discussed and justified with off-line Matlab simulations and real-time experiments. A FIR matched filter was used as a preprocessor to increase the SNR of the acoustic fetal heart signal. The Teager energy operator and autocorrelation, used in the previous version of the monitor, were combined with a matched filter. Linear prediction and quadratic energy detection were …

Adaptive Integration Of Audio And Visual Information Using Discrete And Semi-Continuous Hidden Markov Models In Audiovisual Automatic Speech Recognition, Qin Su

Electrical & Computer Engineering Theses & Dissertations

An audiovisual semi-continuous hidden Markov model (HMM)-based Automatic Speech Recognition (ASR) system and an improved method of integrating audio and visual information in an audiovisual discrete HMM-based ASR system are investigated.

In the audiovisual discrete HMM, an adaptive integration formulation is employed, which incorporates the integration into the HMM at a pre-categorical stage. A visual weighting parameter is determined automatically, which allows the relative contribution of audio and visual information to be adjusted adaptively. Using an adaptive weight, the accuracy increased by 13% compared to the same model with no adaptive weight.

The semi-continuous HMM is a class of models …

Comparison Of System Identification Techniques For The Dexterous Orbital Servicing System (Doss), Allan Terrence Morris

Electrical & Computer Engineering Theses & Dissertations

The major contribution of system identification is the development of analytical models of a system. Many identification techniques can adequately describe the input and output map. One of the challenges of these techniques is to correctly infer from the measured data the characteristics of the individual, contributing components producing a more accurate system model.

In this thesis linear, dynamic, multivariable state-space models for three joints of the Dexterous Orbital Servicing System (DOSS) are identified. DOSS is a representative space station manipulator at the NASA Langley Research Center. The dynamic models of the manipulator will first be estimated by applying nonparametric …

Fetal Heart Rate Detection With A Passive Acoustic Sensor System, Zongyao Zhou

Electrical & Computer Engineering Theses & Dissertations

Research and development is presented of real time signal processing methodologies for the detection of fetal heart tones from noise contaminated signals obtained from passive acoustic sensors. A nonlinear Teager energy operator is utilized for detection of the fetal heart tone event. Autocorrelation and a parallel redundancy correction algorithm derives fetal heart rates. A real time monitoring system is described which records and plots the time history of both the fetal heart rate and the acoustic fetal heart signal. The system is validated in the context of the fetal nonstress test. Comparisons are made with ultrasonic nonstress tests on a …

Optimization Of Electron-Beam Activated Gaas Switches, Raymond Jack Allen Iii

Electrical & Computer Engineering Theses & Dissertations

The use of electron induced luminescence (cathodoluminescence) in gallium arsenide offers the possibility to modulate the conductance of the material on a timescale of nanoseconds and with a pulse rate of MHz, through modulation of an electron-beam current. This ionization mechanism allows the utilization of semi-insulating GaAs in fast, high power closing and opening switches. The efficiency of the switches is determined by the hold-off voltage of the GaAs switches, and by the conversion efficiency of electron energy into (useful) photon energy. Studies of the dark-current and the electron-beam induced conductance in semi-insulating GaAs have been performed in order to …

Acoustic Correlates Of Vowel Perception As Determined From Synthesis Experiments With Multi-Tone Stimuli, Zhongjiang Zhang

Electrical & Computer Engineering Theses & Dissertations

An essential requirement of speech signal processing is to extract information (features or parameters) from the speech signal which encode the information carried by the signal. The objective of this thesis work was to examine and evaluate two feature sets as acoustic correlates for vowel perception. They are formants and DCTCs. Formants are the frequencies of spectral peaks of the speech signal. DCTCs are the Discrete Cosine Transform Coefficients of the magnitude spectrum and are thus features which encode the global spectral shape of speech signal.

There are different opinions regarding which feature set is a more accurate representation for …