In this paper, a machine learning (ML) framework is devised for physical layer (PHY) authentication in mobile orthogonal frequency-division multiplexing (OFDM) transceivers. The ML framework utilizes various classification models that exploit features extracted to capture the unique hardware behavior of different transmitters, namely: coarse carrier frequency offset (CFO), fine CFO, and residual CFO. These features are leveraged to train various classification models to distinguish between legitimate and non-legitimate transmitters. Since these features are mainly dependent of the hardware behavior more than the channel behavior, they are more resilient in mobility scenarios where channels are more dynamic. For validation, we adopt a software-defined radio (SDR) testbed to record the pertinent measurements in indoor and outdoor mobility environments. It is shown that the proposed approach can distinguish between legitimate and malicious transmitters effectively. Among various classifiers adopted, support vector machine (SVM) gives a true positive rate (TPR) classification of 0.97 with a false positive rate (FPR) of 0.02 in indoor environment; and a TPR of 0.93 with an FPR of 0.05 in outdoor environment.

Unmanned Aerial Systems (UAS) have received a huge interest in military and civil applications. Applications of UAS are dependent on successful communications of these systems with different entities in their networks. A UAS network can include the UAS, ground control station, navigation satellite system, and automatic dependent surveillance-broadcast (ADS-B) receiver. Through these entities, a UAS is vulnerable to different cyber-attacks such as GPS spoofing. In this attack, a malicious user transmits fake signals to the GPS receiver on the UAS. The fake signals can mislead not only the aircraft but also air traffic controllers, leading to serious problems. These problems range from aircraft hijacking to collisions and human casualties. This paper proposes a supervised machine learning method based on the artificial neural network to detect GPS spoofing signals. Different features such as pseudo range, Doppler shift, and signal-to-noise ratio (SNR) are used to perform the classification of GPS signals. We examine and compare the efficiency of one-and two-hidden-layer neural networks with various numbers of hidden neurons. The results show that our proposed method provides a high probability of detection and a low probability of false alarm.

We consider the problem of analyzing timestamped relational events between a set of entities, such as messages between users of an on-line social network. Such data are often analyzed using static or discrete-time network models, which discard a significant amount of information by aggregating events over time to form network snapshots. In this paper, we introduce a block point process model (BPPM) for continuous-time event-based dynamic networks. The BPPM is inspired by the well-known stochastic block model (SBM) for static networks. We show that networks generated by the BPPM follow an SBM in the limit of a growing number of nodes. We use this property to develop principled and efficient local search and variational inference procedures initialized by regularized spectral clustering. We fit BPPMs with exponential Hawkes processes to analyze several real network data sets, including a Facebook wall post network with over 3,500 nodes and 130,000 events.

In a cognitive radio network, what is the trade off between statistical signal processing and machine learning algorithms that perform the same task? When should a system use the former and when should it use the latter? In this paper we present an empirical comparison study of different techniques for two tasks: detecting multiple transmitters in the same time-frequency domain, and automatic modulation classification. We develop and improve upon an unsupervised learning technique for the former, based on the log-Rayleigh distribution. Results are based on data generated from GNU Radio Companion, and implementations of these algorithms in software. They show that there is a tradeoff between accuracy and computation/implementation complexity - signal processing has a several orders of magnitude advantage over machine learning, but slightly lower accuracy. Thus, there is a need for an overarching framework that can meld machine learning and statistical signal processing.

An emerging topic in human-computer interaction research involves optimal collaboration between humans and machines to achieve a particular goal. One approach to such a goal involves sliding-scale autonomy, in which a machine dynamically adjusts between different levels of autonomy based on a variety of measurements. In this paper, we propose a system to predict skill level and workload for aircraft pilots using machine learning algorithms. Our proposed system uses the pilot's heart rate variability and flight control data, including pilot inputs such as throttle and aileron, and flight sensor data such as latitude and longitude. We conduct a user study on 15 pilots, each flying the same 5 pre-defined routes on a flight simulator. Our results indicate that the flight control data alone are sufficient to provide a near-perfect classification of a pilot's skill level into expert or novice. On the other hand, predicting mental workload is much more difficult, and a combination of flight control and heart rate data is required to obtain an accurate estimate of mental workload. Our findings provide the first step towards a sliding-scale autonomous system for aviation.

Computing and intelligence are substantial requirements for the accurate performance of autonomous ground vehicles (AGVs). In this context, the use of cloud services in addition to onboard computers enhances computing and intelligence capabilities of AGVs. In addition, the vast amount of data processed in a cloud system contributes to overall performance and capabilities of the onboard system. This research study entails a qualitative analysis to gather insights on the applicability of the leading cloud service providers in AGV operations. These services include Google Cloud, Microsoft Azure, Amazon AWS, and IBM Cloud. The study begins with a brief review of AGV technical requirements that are necessary to determine the rationale for identifying the most suitable cloud service. The qualitative analysis studies and addresses the applicability of the cloud service over the proposed generalized AGV's architecture integration, performance, and manageability. Our findings conclude that a generalized AGV architecture can be supported by state-of-the-art cloud service, but there should be a clear line of separation between the primary and secondary computing needs. Moreover, our results show significant lags while using cloud services and preventing their use in real-time AGV operation.

Summary This paper discusses the implementation, architecture, and use of a graphical web‐based application called ReliaCloud‐NS that allows users to (1) evaluate the reliability of a cloud computing system (CCS) and (2) design a CCS to a specified reliability level for both public and private clouds. The software was designed with a RESTful application programming interface for performing nonsequential Monte Carlo simulations to perform reliability evaluations of a CCS. Simulation results are stored and presented to the user in the form of interactive charts and graphs from within a web browser. The software contains multiple types of CCS components, simulations, and virtual machine allocation schemes. ReliaCloud‐NS also contains a novel feature that evaluates CCS reliability across a range of varying virtual machine allocations and establishes and graphs a CCS reliability curve. This paper discusses the software architecture, the interactive web‐based interface, and the different types of simulations available in ReliaCloud‐NS and presents an overview of the results generated from a simulation.

The cloud computing paradigm has ushered in the need for new methods of evaluating the performance in a given cloud computing systems (CCS) in order to ensure customer and service level agreement satisfaction. This study proposes a method for evaluating the reliability of a CCS alongside the corresponding performance metrics. Specifically, and for the first time, non-sequential Monte Carlo simulation (MCS) is used to evaluate CCS reliability at a system-wide scale. Results demonstrate that the proposed method is promising and may apply to systems at a large scale.

Cognitive radio relies on accurate spectrum sensing for increasing the spectral efficiency of wireless networks. A novel array processing scheme is proposed based on a uniform linear array (ULA) of circularly-polarized spiral antennas having frequency range 2–6 GHz, which is used in conjunction with digital beam filters having 2-D IIR transfer functions for accurately and efficiently placing radio sources in wireless environment. Algorithms such as cyclostationary feature extraction is employed at beamformer to measure energy and realize feature/modulation detection, which in turn allows classification of a wireless environment. Simulation examples are provided for demonstrating the low-complexity directional feature detector with applications towards enhancing access to radio spectrum. Examples showing classification of sources by direction, frequency channels and modulation type in the 2–4 GHz band at SNR=6 dB are given.

The application of multi-dimensional (MD) infinite impulse response (IIR) space-time beam filters in radio source localization in cognitive radio (CR) environments is investigated. Knowledge of the position of radio sources in a CR network leads to the detection of white spaces in the MD frequency domain, thereby creating more opportunistic links for the secondary users. The use of MD IIR beam filters is motivated by their very low computational complexity and small side lobe levels compared to digital phased arrays. As a proof-of-concept, the two dimensional (2-D) propagation scenario including at least two receiver stations and a data fusion station, which combines the direction of arrival (DOA) estimates from the two receiver stations, to yield a position estimate, is considered. Each receiver station employs a uniform linear array (ULA) of antennas and a steerable 2-D IIR beam filter and provides information pertaining to peak energy directions. First order 2-D IIR beam filters are shown to provide acceptable DOA estimates with a SNR of 6 dB. The peak energy direction information leads to both position and MD white space detection.

It is well established that the function of human gene can be identified by working on the corresponding gene in a model organism. Such comparative genomic studies have provided new insights into human biology and gene expression. Due to the explosion of genomic data in recent times, highly effective computational comparative genomic algorithms are in greater demand. In this research, a digital signal processing approach using statistically optimal null filter (SONF) is developed for comparative genomic analysis. The instantaneous matched filter in SONF determines the degree of local alignment between the genomic sequences being compared. Through examples the effectiveness of the proposed approach is illustrated in comparison with the other existing convolution based method. In particular, the proposed method is highly efficient in locating a short motif in a large genomic sequence.

Prediction of the protein-coding regions (exons) is one of the central issues of DNA sequence analysis. Most of the existing computational methods exploit the period-3 property of the coding-regions to distinguish exons from noncoding regions (introns). However, the current Discrete Fourier Transform (DFT) based methods are inadequate in predicting short exons. In this paper, we present a model-based exon detection approach using statistically optimal null filter. The proposed method employs a model of the period-3 characteristic to maximize signal-to-noise ratio, and least-squares optimization criteria to rapidly detect the presence of exons in the input DNA sequence. Through examples, it is shown that the proposed method is highly effective as compared to the DFT technique, especially in identifying short exons and successive exons separated by short introns.

Accurate modeling of devices is critical to efficient computer aided design and optimization. Commonly encountered modeling techniques include empirical formulae, equivalent circuits, and black-box models (eg. neural networks). Important criteria in device modeling are model accuracy, computational simplicity, generality of the modeling approach, and so forth. In this paper, we present a new and systematic CAD algorithm to device modeling based on a concept often referred to as binning. For a given set of data either from measurements or simulations, the proposed algorithm leads to an accurate model comprising of a set of sub-models with best possible accuracy, while keeping the model structure simple. The proposed algorithm is general and can be applied in the context of any black-box modeling technique. In this paper, the algorithm is illustrated for the case of neural network modeling. Resulting models are shown to exhibit relatively better accuracies compared to those developed using a standard modeling approach. Both active and passive modeling examples are presented.

Neural networks as an emerging modeling technique have gained much attention in the microwave area. Due to the convergence difficulty of simulators or equipment limits where parameters are sampled at extremes, the simulated or measured training data often have both gross errors and small errors. A new training method is presented in this paper which incorporates the Huber concept into a quasi-Newton method. The proposed method can recognize the gross errors and small errors and treat them differently. Therefore this Huber training method is much more robust than traditional least-square l/sub 2/ methods, which is demonstrated through two examples, modeling of a quadratic function and transmission lines.