arXiv subjects

T. Charles Clancy

Publications and source records attributed to T. Charles Clancy.

At least 19 recordsLinked to original sources

arXiv2020

Deep Learning for Wireless Communications

Existing communication systems exhibit inherent limitations in translating theory to practice when handling the complexity of optimization for emerging wireless applications with high degrees of freedom. Deep learning has a strong potential to overcome this challenge via data-driven solutions and improve the performance of wireless systems in utilizing limited spectrum resources. In this chapter, we first describe how deep learning is used to design an end-to-end communication system using autoencoders. This flexible design effectively captures channel impairments and optimizes transmitter and receiver operations jointly in single-antenna, multiple-antenna, and multiuser communications. Next, we present the benefits of deep learning in spectrum situation awareness ranging from channel modeling and estimation to signal detection and classification tasks. Deep learning improves the performance when the model-based methods fail. Finally, we discuss how deep learning applies to wireless communication security. In this context, adversarial machine learning provides novel means to launch and defend against wireless attacks. These applications demonstrate the power of deep learning in providing novel means to design, optimize, adapt, and secure wireless communications.

cs.NI↗

arXiv2019

Intelligent Knowledge Distribution: Constrained-Action POMDPs for Resource-Aware Multi-Agent Communication

This paper addresses a fundamental question of multi-agent knowledge distribution: what information should be sent to whom and when, with the limited resources available to each agent? Communication requirements for multi-agent systems can be rather high when an accurate picture of the environment and the state of other agents must be maintained. To reduce the impact of multi-agent coordination on networked systems, e.g., power and bandwidth, this paper introduces two concepts for partially observable Markov decision processes (POMDPs): 1) action-based constraints which yield constrained-action POMDPs (CA-POMDPs); and 2) soft probabilistic constraint satisfaction for the resulting infinite-horizon controllers. To enable constraint analysis over an infinite horizon, an unconstrained policy is first represented as a Finite State Controller (FSC) and optimized with policy iteration. The FSC representation then allows for a combination of Markov chain Monte Carlo and discrete optimization to improve the probabilistic constraint satisfaction of the controller while minimizing the impact to the value function. Within the CA-POMDP framework we then propose Intelligent Knowledge Distribution (IKD) which yields per-agent policies for distributing knowledge between agents subject to interaction constraints. Finally, the CA-POMDP and IKD concepts are validated using an asset tracking problem where multiple unmanned aerial vehicles (UAVs) with heterogeneous sensors collaborate to localize a ground asset to assist in avoiding unseen obstacles in a disaster area. The IKD model was able to maintain asset tracking through multi-agent communications while only violating soft power and bandwidth constraints 3% of the time, while greedy and naive approaches violated constraints more than 60% of the time.

cs.MA↗

arXiv2017

Over the Air Deep Learning Based Radio Signal Classification

We conduct an in depth study on the performance of deep learning based radio signal classification for radio communications signals. We consider a rigorous baseline method using higher order moments and strong boosted gradient tree classification and compare performance between the two approaches across a range of configurations and channel impairments. We consider the effects of carrier frequency offset, symbol rate, and multi-path fading in simulation and conduct over-the-air measurement of radio classification performance in the lab using software radios and compare performance and training strategies for both. Finally we conclude with a discussion of remaining problems, and design considerations for using such techniques.

cs.LG↗

arXiv2017

Deep Learning Based MIMO Communications

We introduce a novel physical layer scheme for single user Multiple-Input Multiple-Output (MIMO) communications based on unsupervised deep learning using an autoencoder. This method extends prior work on the joint optimization of physical layer representation and encoding and decoding processes as a single end-to-end task by expanding transmitter and receivers to the multi-antenna case. We introduce a widely used domain appropriate wireless channel impairment model (Rayleigh fading channel), into the autoencoder optimization problem in order to directly learn a system which optimizes for it. We considered both spatial diversity and spatial multiplexing techniques in our implementation. Our deep learning-based approach demonstrates significant potential for learning schemes which approach and exceed the performance of the methods which are widely used in existing wireless MIMO systems. We discuss how the proposed scheme can be easily adapted for open-loop and closed-loop operation in spatial diversity and multiplexing modes and extended use with only compact binary channel state information (CSI) as feedback.

cs.IT↗

arXiv2017

Learning Approximate Neural Estimators for Wireless Channel State Information

Estimation is a critical component of synchronization in wireless and signal processing systems. There is a rich body of work on estimator derivation, optimization, and statistical characterization from analytic system models which are used pervasively today. We explore an alternative approach to building estimators which relies principally on approximate regression using large datasets and large computationally efficient artificial neural network models capable of learning non-linear function mappings which provide compact and accurate estimates. For single carrier PSK modulation, we explore the accuracy and computational complexity of such estimators compared with the current gold-standard analytically derived alternatives. We compare performance in various wireless operating conditions and consider the trade offs between the two different classes of systems. Our results show the learned estimators can provide improvements in areas such as short-time estimation and estimation under non-trivial real world channel conditions such as fading or other non-linear hardware or propagation effects.

cs.LG↗

arXiv2017

Coexistence Analysis between Radar and Cellular System in LoS Channel

Sharing spectrum with incumbents such as radar systems is an attractive solution for cellular operators in order to meet the ever growing bandwidth requirements and ease the spectrum crunch problem. In order to realize efficient spectrum sharing, interference mitigation techniques are required. In this letter we address techniques to mitigate MIMO radar interference at MIMO cellular base stations (BSs). We specifically look at the amount of power received at BSs when radar uses null space projection (NSP)-based interference mitigation method. NSP reduces the amount of projected power at targets that are in-close vicinity to BSs. We study this issue and show that this can be avoided if radar employs a larger transmit array. In addition, we compute the coherence time of channel between radar and BSs and show that the coherence time of channel is much larger than the pulse repetition interval of radars. Therefore, NSP-based interference mitigation techniques which depends on accurate channel state information (CSI) can be effective as the problem of CSI being outdated does not occur for most practical scenarios.

cs.NI↗

arXiv2017

Semi-Supervised Radio Signal Identification

Radio emitter recognition in dense multi-user environments is an important tool for optimizing spectrum utilization, identifying and minimizing interference, and enforcing spectrum policy. Radio data is readily available and easy to obtain from an antenna, but labeled and curated data is often scarce making supervised learning strategies difficult and time consuming in practice. We demonstrate that semi-supervised learning techniques can be used to scale learning beyond supervised datasets, allowing for discerning and recalling new radio signals by using sparse signal representations based on both unsupervised and supervised methods for nonlinear feature learning and clustering methods.

cs.LG↗

arXiv2016

Applying Bag of System Calls for Anomalous Behavior Detection of Applications in Linux Containers

In this paper, we present the results of using bags of system calls for learning the behavior of Linux containers for use in anomaly-detection based intrusion detection system. By using system calls of the containers monitored from the host kernel for anomaly detection, the system does not require any prior knowledge of the container nature, neither does it require altering the container or the host kernel.

cs.CR↗

arXiv2016

Recurrent Neural Radio Anomaly Detection

We introduce a powerful recurrent neural network based method for novelty detection to the application of detecting radio anomalies. This approach holds promise in significantly increasing the ability of naive anomaly detection to detect small anomalies in highly complex complexity multi-user radio bands. We demonstrate the efficacy of this approach on a number of common real over the air radio communications bands of interest and quantify detection performance in terms of probability of detection an false alarm rates across a range of interference to band power ratios and compare to baseline methods.

cs.LG↗

arXiv2016

Learning to Communicate: Channel Auto-encoders, Domain Specific Regularizers, and Attention

We address the problem of learning efficient and adaptive ways to communicate binary information over an impaired channel. We treat the problem as reconstruction optimization through impairment layers in a channel autoencoder and introduce several new domain-specific regularizing layers to emulate common channel impairments. We also apply a radio transformer network based attention model on the input of the decoder to help recover canonical signal representations. We demonstrate some promising initial capacity results from this architecture and address several remaining challenges before such a system could become practical.

cs.LG↗

arXiv2016

Convolutional Radio Modulation Recognition Networks

We study the adaptation of convolutional neural networks to the complex temporal radio signal domain. We compare the efficacy of radio modulation classification using naively learned features against using expert features which are widely used in the field today and we show significant performance improvements. We show that blind temporal learning on large and densely encoded time series using deep convolutional neural networks is viable and a strong candidate approach for this task especially at low signal to noise ratio.

cs.LG↗

arXiv2016

Deep Reinforcement Learning Radio Control and Signal Detection with KeRLym, a Gym RL Agent

This paper presents research in progress investigating the viability and adaptation of reinforcement learning using deep neural network based function approximation for the task of radio control and signal detection in the wireless domain. We demonstrate a successful initial method for radio control which allows naive learning of search without the need for expert features, heuristics, or search strategies. We also introduce Kerlym, an open Keras based reinforcement learning agent collection for OpenAI's Gym.

cs.LG↗

arXiv2016

Radio Transformer Networks: Attention Models for Learning to Synchronize in Wireless Systems

We introduce learned attention models into the radio machine learning domain for the task of modulation recognition by leveraging spatial transformer networks and introducing new radio domain appropriate transformations. This attention model allows the network to learn a localization network capable of synchronizing and normalizing a radio signal blindly with zero knowledge of the signals structure based on optimization of the network for classification accuracy, sparse representation, and regularization. Using this architecture we are able to outperform our prior results in accuracy vs signal to noise ratio against an identical system without attention, however we believe such an attention model has implication far beyond the task of modulation recognition.

cs.LG↗

arXiv2016

Unsupervised Representation Learning of Structured Radio Communication Signals

We explore unsupervised representation learning of radio communication signals in raw sampled time series representation. We demonstrate that we can learn modulation basis functions using convolutional autoencoders and visually recognize their relationship to the analytic bases used in digital communications. We also propose and evaluate quantitative met- rics for quality of encoding using domain relevant performance metrics.

cs.LG↗

arXiv2016

Position Estimation of Robotic Mobile Nodes in Wireless Testbed using GENI

We present a low complexity experimental RF-based indoor localization system based on the collection and processing of WiFi RSSI signals and processing using a RSS-based multi-lateration algorithm to determine a robotic mobile node's location. We use a real indoor wireless testbed called w-iLab.t that is deployed in Zwijnaarde, Ghent, Belgium. One of the unique attributes of this testbed is that it provides tools and interfaces using Global Environment for Network Innovations (GENI) project to easily create reproducible wireless network experiments in a controlled environment. We provide a low complexity algorithm to estimate the location of the mobile robots in the indoor environment. In addition, we provide a comparison between some of our collected measurements with their corresponding location estimation and the actual robot location. The comparison shows an accuracy between 0.65 and 5 meters.

cs.NI↗

arXiv2015

Application-Aware Resource Block and Power Allocation for LTE

In this paper, we implement an application-aware scheduler that differentiates users running real-time applications and delay-tolerant applications while allocating resources. This approach ensures that the priority is given to real-time applications over delay-tolerant applications. In our system model, we include realistic channel effects of Long Term Evolution (LTE) system. Our application-aware scheduler runs in two stages, the first stage is resource block allocation and the second stage is power allocation. In the optimal solution of resource block allocation problem, each user is inherently guaranteed a minimum Quality of Experience (QoE) while ensuring priority given to users with real-time applications. In the power allocation problem, a new power allocation method is proposed which utilizes the optimal solution of the application-aware resource block scheduling problem. As a proof of concept, we run a simulation comparison between a conventional proportional fairness scheduler and the application-aware scheduler. The simulation results show better QoE with the application-aware scheduler.

cs.NI↗

arXiv2015

Towards an Application-Aware Resource Scheduling with Carrier Aggregation in Cellular Systems

In this paper, we introduce an application-aware approach for resource block scheduling with carrier aggregation in Long Term Evolution Advanced (LTE-Advanced) cellular networks. In our approach, users are partitioned in different groups based on the carriers coverage area. In each group of users, users equipments (UE)s are assigned resource blocks (RB)s from all in band carriers. We use a utility proportional fairness (PF) approach in the utility percentage of the application running on the UE. Each user is guaranteed a minimum quality of service (QoS) with a priority criterion that is based on the type of application running on the UE. We prove that our scheduling policy exists and therefore the optimal solution is tractable. Simulation results are provided to compare the performance of the proposed RB scheduling approach with other scheduling policies.

cs.NI↗

arXiv2015

Network MIMO with Partial Cooperation between Radar and Cellular Systems

To meet the growing spectrum demands, future cellular systems are expected to share the spectrum of other services such as radar. In this paper, we consider a network multiple-input multiple-output (MIMO) with partial cooperation model where radar stations cooperate with cellular base stations (BS)s to deliver messages to intended mobile users. So the radar stations act as BSs in the cellular system. However, due to the high power transmitted by radar stations for detection of far targets, the cellular receivers could burnout when receiving these high radar powers. Therefore, we propose a new projection method called small singular values space projection (SSVSP) to mitigate these harmful high power and enable radar stations to collaborate with cellular base stations. In addition, we formulate the problem into a MIMO interference channel with general constraints (MIMO-IFC-GC). Finally, we provide a solution to minimize the weighted sum mean square error minimization problem (WSMMSE) with enforcing power constraints on both radar and cellular stations.

cs.IT↗