: This thesis applies neural network feature selection techniques to multivariate time series data to improve prediction of a target time series. Two approaches to feature selection are used. First, a subset enumeration method is used to determine which financial indicators are most useful for aiding in prediction of the S&P 500 futures daily price. The candidate indicators evaluated include RSI, Stochastics and several moving averages. Results indicate that the Stochastics and RSI indicators result in better prediction results than the moving averages. The second approach to feature selection is calculation of individual saliency metrics. A new decision boundary-based individual saliency metric, and a classifier independent saliency metric are developed and tested. Ruck's saliency metric, the decision boundary based saliency metric, and the classifier independent saliency metric are compared for a data set consisting of the RSI and Stochastics indicators as well as delayed closing price values. The decision based metric and the Ruck metric results are similar, but the classifier independent metric agrees with neither of the other metrics. The nine most salient features, determined by the decision boundary based metric, are used to train a neural network and the results are presented and compared to other published results. (AN)

/pdf/nonlinear-time-series-analysis-1j3a35n4y3.pdf

Nonlinear Time Series Analysis.

Gallium-nitride power transistor (GaN HEMT) and integrated circuit technologies have matured dramatically over the last few years, and many hundreds of thousands of devices have been manufactured and fielded in applications ranging from pulsed radars and counter-IED jammers to CATV modules and fourth-generation infrastructure base-stations. GaN HEMT devices, exhibiting high power densities coupled with high breakdown voltages, have opened up the possibilities for highly efficient power amplifiers (PAs) exploiting the principles of waveform engineered designs. This paper summarizes the unique advantages of GaN HEMTs compared to other power transistor technologies, with examples of where such features have been exploited. Since RF power densities of GaN HEMTs are many times higher than other technologies, much attention has also been given to thermal management-examples of both commercial “off-the-shelf” packaging as well as custom heat-sinks are described. The very desirable feature of having accurate large-signal models for both discrete transistors and monolithic microwave integrated circuit foundry are emphasized with a number of circuit design examples. GaN HEMT technology has been a major enabler for both very broadband high-PAs and very high-efficiency designs. This paper describes examples of broadband amplifiers, as well as several of the main areas of high-efficiency amplifier design-notably Class-D, Class-E, Class-F, and Class-J approaches, Doherty PAs, envelope-tracking techniques, and Chireix outphasing.

/pdf/a-review-of-gan-on-sic-high-electron-mobility-power-4mjzeqemry.pdf

A Review of GaN on SiC High Electron-Mobility Power Transistors and MMICs

A nitride semiconductor device including a light emitting device comprises a n-type region of one or more nitride semiconductor layers having n-type conductivity, a p-type region of one or more nitride semiconductor layers having p-type conductivity and an active layer between the n-type region and the p-type region. In such devices, there is provided with a super lattice layer comprising first layers and second layers which are nitride semiconductors having a different composition respectively. The super lattice structure makes working current and voltage of the device lowered, resulting in realization of more efficient devices.

Nitride semiconductor device

This paper presents a comparative overview of the most important approaches presented to address the behavioral modeling of microwave and wireless power amplifiers (PAs). Starting from a theoretical framework of recursive and nonrecursive nonlinear filters, it proposes a classification of the various PA behavioral models, discussing their abilities to represent the different effects observed in practical circuits. Using that formal procedure, one explains how it was possible to integrate a wide range of behavioral modeling activities and to show that some of them, which at first glance seemed to be quite different, are, indeed, identical in their modeling capabilities.

A comparative overview of microwave and wireless power-amplifier behavioral modeling approaches

A comparative study of nonlinear behavioral models with memory for radio-frequency power amplifier (PAs) is presented. The models are static polynomial, parallel Hammerstein (PH), Volterra, and radial basis-function neural network (RBFNN). Two PAs were investigated: one was designed for the third-generation (3G) mobile telecommunication systems and one was designed for the second-generation (2G). The RBFNN reduced the total model error slightly more than the PH, but the error out of band was significantly lower for the PH. The Volterra was found to give a lower model error than did a PH of the same nonlinear order and memory depth. The PH could give a lower model error than the best Volterra, since the former could be identified with a higher nonlinear order and memory depth. The qualitative conclusions are the same for the 2G and 3G PAs, but the model errors are smaller for the latter. For the 3G PA, a static polynomial gave a low model error as low as the best PH and lower than the RBFNN for the hardest cross validation. The models with memory, PH, and RBFNN, showed better cross-validation performance, in terms of lower model errors, than a static polynomial for the hardest cross validation of the 2G PA

A comparative analysis of behavioral models for RF power amplifiers

For more than a quarter of a century, microwave engineers have had the benefit of a foundation of mutually interacting components of measurement, modeling, and simulation to design and test linear components and systems. S-parameters are perhaps the most successful behavioral models ever. They have the powerful property that the S-parameters of individual components are sufficient to determine the S-parameters of any combination of those components. S-parameters of a component are sufficient to predict its response to any signal, provided only that the signal is of sufficiently small amplitude. We have presented the PHD modeling approach. It is a black-box frequency-domain model that provides a foundation for measurement, modeling, and simulation of driven nonlinear systems. The PHD model is very accurate for a wide variety of nonlinear characteristics, including compression, AM-PM, harmonics, load-pull, and time-domain waveforms. The PHD model faithfully represents driven nonlinear systems with mismatches at both the fundamental and harmonics. This enables the accurate simulation of distortion through cascaded chains of nonlinear components, thus providing key new design verification capabilities for RF and microwave modules and subsystems

/pdf/polyharmonic-distortion-modeling-18qo1vhwxt.pdf

Polyharmonic distortion modeling

We present an optimal experiment design methodology and a superior and fully automated model generation procedure for identifying a class of broad-band multiharmonic behavioral models in the frequency domain. The approach reduces the number of nonlinear measurements needed, minimizes the time to generate the data from simulations, reduces the time to extract the model functions from data, and when used for simulation-based models, takes maximum advantage of specialized simulation algorithms. The models have been subject to extensive validation in applications to real microwave integrated circuits. The derived model is valid for both small and large amplitude drive signals, correctly predicts even and odd harmonics through cascaded chains of functional blocks, simulates accurately load-pull behavior away from 50 /spl Omega/, and predicts adjacent channel power ratio and constellation diagrams in remarkably close agreement to the circuit model from which the behavioral model was derived. The model and excitation design templates for generating them from simulations are implemented in Agilent Technologies' Advanced Design System.

/pdf/broad-band-poly-harmonic-distortion-phd-behavioral-models-45touh0q9o.pdf

Broad-band poly-harmonic distortion (PHD) behavioral models from fast automated simulations and large-signal vectorial network measurements

This paper describes a new, general and accurate, large signal GaAs FET model for nonlinear (e.g. harmonic balance) circuit simulation, its fast and unambiguous construction (model generation) by explicit calculations applied to the raw device data, and the adaptive, automated data acquisition system used to characterize the device. The model implementation in a harmonic balance simulator, the model generation procedure, and the automated data acquisition system form an efficient, practical, commercially available package. for state-of-the-art nonlinear circuit design.

Technology Independent Large Signal Non Quasi-Static FET Models by Direct Construction from Automatically Characterized Device Data

This is the definitive guide to X-parameters, written by the original inventors and developers of this powerful new paradigm for nonlinear RF and microwave components and systems Learn how to use X-parameters to overcome intricate problems in nonlinear RF and microwave engineering The general theory behind X-parameters is carefully and intuitively introduced, and then simplified down to specific, practical cases, providing you with useful approximations that will greatly reduce the complexity of measuring, modeling and designing for nonlinear regimes of operation Containing real-world case studies, definitions of standard symbols and notation, detailed derivations within the appendices, and exercises with solutions, this is the definitive stand-alone reference for researchers, engineers, scientists and students looking to remain on the cutting-edge of RF and microwave engineering

X-Parameters: Characterization, Modeling, and Design of Nonlinear RF and Microwave Components

A modeling system for active semiconductor devices, such as gallium arsenide field effect transistors, for nonlinear (e.g., harmonic balance) circuit simulation. The model enables fast and unambiguous construction (model generation) by explicit calculations applied to raw device response data obtained using an adaptive, automated data acquisition system employed to characterize the device. The automated data acquisition system obtains the data adaptively, taking more data where nonlinearities are most severe and within a calculated, safe operating range of the device. The system converts conventional d.c. and S-parameter data directly into a detailed, device-specific, large-signal model. The system is extremely fast and replaces the need for conventional parameter extraction based on circuit simulation and optimization techniques. The measurement-based model improves large-signal simulation accuracy over an extended operating frequency range, because the model nonlinearities are explicitly constructed from device response data. The model is non quasi-static in that it accounts for frequency dispersion effects. Scaling rules allow devices of various geometries to be simulated from measurements on a single device. Therefore, the model is general, being technology and process independent in that the same calculation procedure applies to any device for which the equivalent circuit is valid. The model implementation in the automated data acquisition system, model generator, and harmonic balance (nonlinear) circuit simulator provides an efficient, practical system for state-of-the-art nonlinear circuit design.

David E. Root

Papers

Polyharmonic distortion modeling

Broad-band poly-harmonic distortion (PHD) behavioral models from fast automated simulations and large-signal vectorial network measurements

Technology Independent Large Signal Non Quasi-Static FET Models by Direct Construction from Automatically Characterized Device Data

X-Parameters: Characterization, Modeling, and Design of Nonlinear RF and Microwave Components

Measurement-based system for modeling and simulation of active semiconductor devices over an extended operating frequency range