Radio Frequency Machine Learning (RFML) techniques for the classification tasks of Specific Emitter Identification (SEI) and Automatic Modulation Classification (AMC) have seen rapid improvements in recent years. The applications of SEI, a technique used to associate a received signal to an emitter, and AMC, a technique for determining the modulation scheme present within a transmission, are necessary for a variety of defense applications such as early warning systems and emitter tracking. Existing works studying SEI and AMC have sought to perform and improve classification through the use of various different machine learning (ML) model architectures. In ideal conditions, these efforts have shown strong classification results, however, when robust real-world data is applied to these models, performance notably decreases. Further efforts, therefore, are required to understand why each of these models fails in adverse conditions. With this understanding, robust architectures that are able to maintain performance in the presence of various data conditions can be created. The work presented in this thesis seeks to improve upon SEI and AMC models by furthering the understanding of how certain model architectures fail under varying data conditions, then applies Transfer Learning (TL) and Ensemble Learning techniques in an effort to mitigate discovered failures and improve the applicability of trained models to various types of data. Each of the approaches presented in this work utilize real-world datasets, collected in a way that emulate a variety of possible real life use conditions of RFML systems. Results show that existing AMC approaches are fairly robust to varying data conditions, while SEI approaches suffer a significant degradation in performance under conditions that differ than that used to train a given model. Further, TL and ensemble techniques can be utilized to improve the robustness of RFML models. This thesis helps isolate the rate and features of those SEI degradations, hopefully setting a foundation for future improvements. / Master of Science / Radio Frequency (RF) signals are produced by many different emitters encountered on a daily basis, including phones, networks, radar, and radios. These signals are used to transfer information from an emitter to a receiver, and contain a plethora of information that need be protected for defense practices in the RF domain. On the other hand, the information contained in these signals can be intercepted and utilized to discover information about potentially malicious transmissions. Two practices to determine information about received signals include Specific Emitter Identification (SEI), which relates an emitter to a received signal, and Automatic Modulation Classification (AMC), which determines the modulation scheme in which a signal is transmitted. A signal is made up of information, expressed in bits, and a modulation scheme is the method used to map those bits to express information. In recent years, Machine Learning (ML) techniques have been applied to SEI and AMC in an effort to improve the efficiency and accuracy results of classification. These ML approaches have shown high accuracy results when applied to data that is collected in the same environment as that used for training. When applied to data with different variables, however, model accuracy notably drops. This performance decrease motivates the need to discover more variables that negatively impact model performance, and further to create models that do not suffer from the same weaknesses. This work examines four different real-world variables that are common in deployed radio frequency machine learning (RFML) usage environments, and using the information learned about model failures, implements two approaches to create models that are more robust to variances in data. This work finds that model performance varies when exposed to variations in temperature, signal-to-noise ratio (SNR), training data quantity, and receiver hardware. Further, this work finds that Transfer Learning (TL) and Ensemble Learning can be used to create models that mitigate these discovered weaknesses.

Call number: LD2668 .T4 1932 H65

International Telemetering Conference Proceedings / October 25-28, 1993 / Riviera Hotel and Convention Center, Las Vegas, Nevada / This paper analyzes the feature of frequency stability and modulation of airborne telemetry transmitters. According to the characteristic of telemetry information transmission, several methods for frequency stabilization and modulation are briefly compared. Emphasis is given to discuss frequency dividing phase- locked frequency modulation and on-off keying modulation and FM/on- off keying double modulation. With the view of raising frequency stability and modulation sensibility, extending the linear range of modulation, the contradiction between frequency stabilization and modulation should be coordinated properly. In addition, a compatible method between conventional telemetry channel and super fast signal telemetry channel is introduced. A satisfactory result has been acquired with those views and methods used in engineering application.

published_or_final_version / Electrical and Electronic Engineering / Doctoral / Doctor of Philosophy

published_or_final_version / Zoology / Doctoral / Doctor of Philosophy

No description available.

The topics covered in this dissertation are all areas of study involving observations at low radio frequencies. There are three main subject areas: a study of the twin-tailed radio galaxy 3C3.1; a study of both an old and a new sample of radio sources that exhibit very steep radio spectra at low frequency; the design and construction of a new radio telescope operating at low radio frequency together with the making of a new radio source survey. 3C3.1 has been studied by other authors but new high angular resolution, high sensitivity observations at low radio frequency have allowed further progress to be made in understanding the behaviour of this source. It has been thought that 3C3.1 type sources would be responsible for most (if not all) of the very steep spectrum radio sources. 3C3.1 is relatively close, hence easy to study. A model has been developed which explains the previously not understood brightness distribution along the long luminous jets. In order to quantify the predicted behaviour more precisely a set of simple numerical simulations was performed. Very steep spectrum radio sources are by their nature easier to detect at low radio frequencies. In the past, it has been shown that most, if not all, very steep spectrum sources are associated with clusters of galaxies. Both optical and further radio observations of a sample of sources prepared by the author, and a sample prepared by other workers were undertaken. The optical observations of high sensitivity have greatly strengthened the hypothesis that all of such sources are indeed associated with clusters of galaxies. The radio observations, both performed at high and low radio frequencies, have shown that such sources seem to have in general evolved from conventional sources with both 'tailed' and 'double' radio structure. A serious limitation for further work at low radio frequencies is the availibility of high sensitivity, high resolution instruments. A twenty five element interferometer with a one mile baseline operating at 38 MHz was designed and constructed. This allowed an appraisal of the operating conditions at such low frequency. A deep radio survey of the north pole was performed and a new sample of very steep spectrum constructed.

No description available.

No description available.

No description available.