Robert J. Marks

Samuel Haug, Austin Egbert, Robert J. Marks et al.

Radar must adapt to changing environments, and we propose changepoint detection as a method to do so. In the world of increasingly congested radio frequencies, radars must adapt to avoid interference. Many radar systems employ the prediction action cycle to proactively determine transmission mode while spectrum sharing. This method constructs and implements a model of the environment to predict unused frequencies, and then transmits in this predicted availability. For these selection strategies, performance is directly reliant on the quality of the underlying environmental models. In order to keep up with a changing environment, these models can employ changepoint detection. Changepoint detection is the identification of sudden changes, or changepoints, in the distribution from which data is drawn. This information allows the models to discard "garbage" data from a previous distribution, which has no relation to the current state of the environment. In this work, bayesian online changepoint detection (BOCD) is applied to the sense and predict algorithm to increase the accuracy of its models and improve its performance. In the context of spectrum sharing, these changepoints represent interferers leaving and entering the spectral environment. The addition of changepoint detection allows for dynamic and robust spectrum sharing even as interference patterns change dramatically. BOCD is especially advantageous because it enables online changepoint detection, allowing models to be updated continuously as data are collected. This strategy can also be applied to many other predictive algorithms that create models in a changing environment.

Glauco Amigo, Daniel Andrés Díaz-Pachón, Robert J. Marks et al.

The outcome of all time series cannot be forecast, e.g. the flipping of a fair coin. Others, like the repeated {01} sequence {010101...} can be forecast exactly. Algorithmic information theory can provide a measure of forecastability that lies between these extremes. The degree of forecastability is a function of only the data. For prediction (or classification) of labeled data, we propose three categories for forecastability: oracle forecastability for predictions that are always exact, precise forecastability for errors up to a bound, and probabilistic forecastability for any other predictions. Examples are given in each case.

Rebekah Edwards, Taylor Martini, Jonathan E. Swindell et al.

Accurate antenna array calibrations and measurements of aspects such as active element pattern (AEP) are critical for enabling integrated sensing and communication (ISAC) technologies such as directional modulation. One reliable way of obtaining accurate and repeatable AEP measurements is to spin the antenna array on a turntable, but many turntables designed for antenna array measurements are prohibitively expensive for small labs and may not be designed with RF considerations, such as cable phase stability, in mind. This paper details the design of a motorized 3D printed turntable for use in directional modulation and in-situ measurement experiments that will allow for rotation of an antenna array around a point, such that the far field of the antenna pattern can be measured by a stationary receiver.

Karan Ruparell, Robert J. Marks, Andy Wood et al.

Long Short Term Memory networks (LSTMs) are used to build single models that predict river discharge across many catchments. These models offer greater accuracy than models trained on each catchment independently if using the same data. However, the same data is rarely available for all catchments. This prevents the use of variables available only in some catchments, such as historic river discharge or upstream discharge. The only existing method that allows for optional variables requires all variables to be considered in the initial training of the model, limiting its transferability to new catchments. To address this limitation, we develop the Hydra-LSTM. The Hydra-LSTM processes variables used across all catchments and variables used in only some catchments separately to allow general training and use of catchment-specific data in individual catchments. The bulk of the model can be shared across catchments, maintaining the benefits of multi-catchment models to generalise, while also benefitting from the advantages of using bespoke data. We apply this methodology to 1 day-ahead river discharge prediction in the Western US, as next-day river discharge prediction is the first step towards prediction across longer time scales. We obtain state-of-the-art performance, generating more accurate median and quantile predictions than Multi-Catchment and Single-Catchment LSTMs while allowing local forecasters to easily introduce and remove variables from their prediction set. We test the ability of the Hydra-LSTM to incorporate catchment-specific data by introducing historical river discharge as a catchment-specific input, outperforming state-of-the-art models without needing to train an entirely new model.

Glauco Amigo, Pablo Rivas Perea, Robert J. Marks

Biased datasets are ubiquitous and present a challenge for machine learning. For a number of categories on a dataset that are equally important but some are sparse and others are common, the learning algorithms will favor the ones with more presence. The problem of biased datasets is especially sensitive when dealing with minority people groups. How can we, from biased data, generate algorithms that treat every person equally? This work explores one way to mitigate bias using a debiasing variational autoencoder with experiments on facial expression recognition.

Justin M. Bui, Glauco A. Amigo, Robert J. Marks

The identification of out-of-distribution data is vital to the deployment of classification networks. For example, a generic neural network that has been trained to differentiate between images of dogs and cats can only classify an input as either a dog or a cat. If a picture of a car or a kumquat were to be supplied to this classifier, the result would still be either a dog or a cat. In order to mitigate this, techniques such as the neural network watchdog have been developed. The compression of the image input into the latent layer of the autoencoder defines the region of in-distribution in the image space. This in-distribution set of input data has a corresponding boundary in the image space. The watchdog assesses whether inputs are in inside or outside this boundary. This paper demonstrates how to sharpen this boundary using generative network training data augmentation thereby bettering the discrimination and overall performance of the watchdog.

Glauco Amigo, Justin M. Bui, Charles Baylis et al.

The identification of out-of-distribution content is critical to the successful implementation of neural networks. Watchdog techniques have been developed to support the detection of these inputs, but the performance can be limited by the amount of available data. Generative adversarial networks have displayed numerous capabilities, including the ability to generate facsimiles with excellent accuracy. This paper presents and empirically evaluates a multi-tiered watchdog, which is developed using GAN generated data, for improved out-of-distribution detection. The cascade watchdog uses adversarial training to increase the amount of available data similar to the out-of-distribution elements that are more difficult to detect. Then, a specialized second guard is added in sequential order. The results show a solid and significant improvement on the detection of the most challenging out-of-distribution inputs while preserving an extremely low false positive rate.

C. Tanner Fredieu, Justin Bui, Anthony Martone et al.

In this paper, we examine the use of a deep multi-layer perceptron model architecture to classify received signal samples as coming from one of four common waveforms, Single Carrier (SC), Single-Carrier Frequency Division Multiple Access (SC-FDMA), Orthogonal Frequency Division Multiplexing (OFDM), and Linear Frequency Modulation (LFM), used in communication and radar networks. Synchronization of the signals is not needed as we assume there is an unknown and uncompensated time and frequency offset. An autoencoder with a deep CNN architecture is also examined to create a new fifth classification category of an unknown waveform type. This is accomplished by calculating a minimum and maximum threshold values from the root mean square error (RMSE) of the radar and communication waveforms. The classifier and autoencoder work together to monitor a spectrum area to identify the common waveforms inside the area of operation along with detecting unknown waveforms. Results from testing showed the classifier had 100\% classification rate above 0 dB with accuracy of 83.2\% and 94.7\% at -10 dB and -5 dB, respectively, with signal impairments present. Results for the anomaly detector showed 85.3\% accuracy at 0 dB with 100\% at SNR greater than 0 dB with signal impairments present when using a high-value Fast Fourier Transform (FFT) size. Accurate detection rates decline as additional noise is introduced to the signals, with 78.1\% at -5 dB and 56.5\% at -10 dB. However, these low rates seen can be potentially mitigated by using even higher FFT sizes also shown in our results.

Justin Bui, Robert J. Marks

Neural networks are largely black boxes. A neural network trained to classify fruit may classify a picture of a giraffe as a banana. A neural network watchdog's job is to identify such inputs, allowing a classifier to disregard such data. We investigate whether the watchdog should be separate from the neural network or symbiotically attached. We present empirical evidence that the symbiotic watchdog performs better than when the neural networks are disjoint.