Machine Learning (ML) for accurately modeling and predicting the wireless channel for various application especially in vehicle is essential for increased safety. In some scenarios we need long distance communication without increasing the congestion factor for the V2V communication. Beam forming is a method of increasing the range but choosing the beam is a critical where machine learning shall be used to predict which beam to choose and predict the power level. In this paper, we design an ensemble machine learning of time series based on three machine learning concepts which are LSTM, ARIMA and Random Forest. Each machine learning concept as a standalone has a unique advantage and our ensemble approach provides the better accuracy of prediction. The ensemble approach is set for multi-step prediction where as one step prediction is more of following rather than predicting. We evaluate our ensemble approach with the standalone algorithm.

In this paper, we propose a novel hierarchical radio-frequency identification (RFID) tag-recognition method based on blind source separation (BSS), graph-based automatic modulation classification (AMC), and direct-sequence spread-spectrum (DSSS). In our proposed method, RFID tags can be modulated using different modulation schemes according to different scenarios (e.g., different users or different tag devices). For each modulation scheme, the direct-sequence spread-spectrum strategy is employed to allow simultaneous transmissions of multiple commands. In the signal separation phase, BSS is employed to separate different transmitted signals. Then in the first hierarchy of the recognition phase, different modulation types are adopted to distinguish different users, the graph-based AMC is built upon the periodicity of the modulated signals: the cyclic spectrum of the received signal is established; the graph representation is then constructed according to the cyclic spectrum. Ultimately, robust features are extracted from the graph representation. In the second hierarchy of the recognition phase, the DSSS scheme is utilized to differentiate the control or sensed data carried by individual tags; the signature sequence set with low cross-correlations can be generated from Kasami sequences. In the third hierarchy of the recognition phase, the information data are thus spread by these signature sequences. In our proposed new RFID framework, multiple tags can transmit signals simultaneously in the same frequency band where each tag signal can still be separated and identified and its carried information can be recovered. Monte Carlo simulation results demonstrate the promising performance of our proposed new RFID scheme.

GPS accuracy is affected by multiple factors, such as satellite clock error, atmospheric delay and multipath fading. Traditionally, develop an algorithm to increase GPS accuracy requires complicated analytical modeling on each error source. Instead, this paper aims to present an approach to improve the accuracy by utilizing deep learning technique. A Long Short-Term memory (LSTM) based prediction method is presented to predict the GPS errors. A well trained model can learn and detect the underlying patterns of the GPS errors in the past time series and thus predict the future errors. Data smoothing preprocess is performed by a digital filter, which is designed and integrated into our approach, this preprocess increases the accuracy and the stability of the system by reducing the impact of unpredictable random noise. The system is set for 10 future steps prediction, with the performances been evaluated by comparing with traditional prediction models. Based on our experimental results, the overall prediction accuracy is increased by 16%, and 37.7% at the furthest prediction step.

This paper presents a real-time long short-term memory (LSTM) recurrent neural network (RNN) to trace and predict the GPS positioning errors within next one to several seconds, offering an enhance GPS positioning. The proposed LSTM prediction model was further verified over extensive experimental data captured in cities and metropolitans, urbans and highways across several middle and eastern States of the United States. The prediction accuracy of the proposed real-time LSTM can be within less than 1-3% of its ground true values outperforms those results gained by conventional statistics and linear prediction models.

Low transmission latency and packet drop rate (PDR) are two of the most important characteristics of vehicular communications and the major indexes in evaluating the performance of their associated technologies. The two most competitive candidate technologies are Dedicated Short-Range Communications (DSRC) and Long-Term Evolution (LTE), it is essential to compare their performances, thus clarify which one fits better for active safety applications. Most of the related studies focused on the computer simulation using theoretical models and were in lack of real-world data to back up their results. It is thus necessary to build a measurement platform for practical data collection and analysis. In this study, a Vehicle-to-Vehicle (V2V) communication test platform was established, which integrated two DSRC On-Board Units (OBUs) and two LTE-4G cellular terminals. Associated software tools were developed for performance measurement. An accurate two-way time-of-flight measurement scheme was adopted to estimate packet latency in the resolution of microseconds for DSRC links and nanosecond for LTE links. The experiments were carried out under several typical weather and road conditions, including Mcity, campuses, highways, downtown, residential, rural areas and many others. The experiments focused on road safety applications with relatively close distances between two testing vehicles, ranging from 1 to 20 meters. According to experimental results, only DSRC meets all the latency requirements for safety applications such as pre-crash sensing, while LTE-4G communications with network outperform DSRC in terms of packet drop rate and coverage.

This paper presents blind modulation classification algorithm of circular linearly modulated signals using cyclic cumulant. The classification uses positions of non-zero cyclic frequencies (symbol rate frequency or carrier frequency) of the received signals. The method works over flat and frequency selective fading channels without having any knowledge of the signal parameters and channel statistics. The proposed method is used for classifying circular constellation modulation format which has not been addressed before. It requires lower complexity than the maximum likelihood approach. The performance of this novel algorithm is compared with the existing methods. In this paper, we have considered a four-class problem including quadrature phase-shift keying (QPSK), offset-QPSK, π/4-QPSK, minimum shift keying.

Fine-scale classification in form of object extraction or segmentation for high resolution SAR images is a challenging task due to the existing local noises, object deformation and part missing. A novel SAR classification method based on CRFs which combines low-level features, label context and object structure priors is presented in this paper. Local label pattern is proposed in this paper to model the object structures by measuring the local label configuration on the grid layer of SAR images. We build a new CRFs model with label context and object structure priors for image classification. Besides, we adopt Mean Field approximation for efficient inference of our CRFs model. This work intends to implement an efficient classification framework by integrating high-level label context and object priors and apply it to fine-scale object extraction of SAR images. The framework demonstrates good performance in both accuracy and efficiency for object extraction or segmentation of simulated images and high resolution SAR images.

The variational inversion for synthetic aperture radar (SAR) wind retrieval can take errors of all sources involved into account, but the complexity of ascertaining errors of wind vectors is high and the iteration process is very time-consuming. In this paper, we modify the decomposition of wind vectors into speed and direction, and adopt a damped Newton method (DNVAR) to solve the cost function, which is based on inexact line search condition. Experimental results show that DNVAR can effectively reduce background wind vector errors, and the average number of iterations for DNVAR descends greatly. For practical applications, when the background wind speed is higher than 10 m/s, the accuracy of DNVAR is higher than direct SAR wind retrieval (DIRECT), otherwise, DIRECT performs better.

In this demonstration, we present a software defined radio (SDR) prototype, xRadio, for next generation machine to machine (M2M) radio based on long term evolution (LTE) and/or smart utility network (SUN, the IEEE 802.15.4g standard), both adopting orthogonal frequency multiplexing division modulation (OFMD). The M2M radios occupy bandwidths of less than 1MHz offering data rates from several to hundreds of kilobits per second. The LTE and SUN baseband processing algorithms are all realized by C codes operating in the Linux operation system over a Raspberry Pi mini PC.

In this paper, by modeling a narrowband interference (NBI) as a wide-sense stationary (WSS), zero-mean Gaussian bandpass random process, a systematic theoretical framework is developed for the first time to characterize the operation and performance improvement of energy detection (ED) based impulse radio ultra-wideband (IR-UWB) receivers that employ a nonlinear Teager-Kaiser operator (TKO) and a highpass filter. Furthermore, through both theoretical analysis and simulations, we have identified (1) that the TKO technique can effectively mitigate not only the performance degradation caused by an NBI but also that caused by additive white Gaussian noise and (2) that a larger bandwidth of the UWB signal leads to better mitigation. Therefore, the TKO technique is considered as a very promising technique to improve the overall performance of ED-based IR-UWB receivers no matter an NBI is present or not.

Cognitive radio (CR) implements dynamic spectrum access (DSA) mainly through performing spectrum sensing. In some circumstances, spectrum sensing is regarded as not sufficient for CR systems without generating unacceptable impact on primary users. For example, for wireless microphone (WM) systems when the transmitters either are turned off or stay idle while receivers are actively listening, CR systems decide to transmit message over the idle channel after spectrum sensing. At this moment, active WM receivers still can detect narrow-band BPSK/QPSK signals transmitted by customer premise equipments (CPEs) leading to unexpected audio signals. In this paper, we first address and study such a hidden busy channel (HBC) situation. The degree of audio interferences generated by narrow-band BPSK/QPSK signals on HBCs is evaluated through field testing. To detect HBCs, we propose a novel technique named iSens. Experiments show that detection the rate of iSens is higher than 90% while the false alarm rate is lower than 10%.

Blind symbol or baud rate estimation is one of the most important parts of the blind signal detection process. Most of the blind symbol rate estimation algorithms provided in the literature either estimate symbol rate from the baseband signal or require prior knowledge of transmitted signal parameters. Moreover, these algorithms had been mostly limited to theoretical studies. In this paper, a cyclic correlation based blind symbol rate estimation is considered for linearly modulated signals. The estimation is performed directly from an intermediate frequency (IF) signal and without having prior knowledge of transmitted signal parameters. The algorithm is implemented on a National Instruments (NI) hardware to measure its performance in a realistic environment. Theoretical and experimental results are provided and compared with existing methods.

In this paper, a novel combining weight estimation algorithm including a capability for inter-symbol interference (ISI) cancelation is proposed for monobit impulse radio (IR) ultra wideband (UWB) receivers. By applying the proposed algorithm to a monobit weighted transmitted-reference IR-UWB receiver as a case study, we have demonstrated through computer simulations that the algorithm can effectively mitigate the destructive effects of ISI and achieve considerable performance improvement over the algorithm without ISI cancellation capability. Furthermore, because most calculations required by the proposed algorithm can be performed offline and the obtained results can be saved into lookup tables for online operations, the system complexity to implement the algorithm is low. Therefore, this ISI-included combining weight estimation algorithm enables the employment of monobit IR-UWB receivers for high data rate applications under non-line-of-sight channels, and can be considered as a promising technology for IR-UWB applications demanding for low system complexity, low power consumption, and high data rates.

Exploiting the unique properties of the physical layer to enhance or complement authentication strength in wireless networks has attracted a lot of research attention recently. In this paper, we propose a novel PHYsical layer Challenge-Response Authentication Mechanism (PHY-CRAM) for wireless networks. PHY-CRAM is suitable for both one-way and mutual authentication. It fully utilizes the randomness, reciprocal, and location decorrelation features of the wireless fading channel, and is immune to various passive and active attacks. In the authentication procedure, challenge-response signals are exchanged at the physical layer, which allow two devices to verify their shared secrets while not revealing these secrets to attackers. PHY-CRAM adopts orthogonal frequency-division multiplexing (OFDM) technique which separately modulates the higher layer information and shared keys on subcarriers' phases and amplitudes respectively, in order to prevent channel probing from traffic-related information. We conduct extensive simulation study and develop a prototype using field-programmable gate array (FPGA) and discrete radio frequency (RF) components to evaluate PHY-CRAM in real-world environments. It shows that PHY-CRAM achieves both high successful authentication rate and low false acceptance rate in various channel conditions and under various attacks.

Tail-biting codes are efficient coding techniques to eliminate the rate loss in conventional known-tail convolutional codes at a cost of increased complexity in decoders. In addition, tail-biting trellis representation of block codes makes the trellis-based maximum likelihood (ML) decoder desirable for implementation. Circular Viterbi algorithm (CVA) is introduced to decode the tail-biting codes for its decoding efficiency. However, its decoding process suffers from circular traps, which degrade the decoding efficiency. In this paper, we propose an efficient checking rule for the detection of circular traps. Based on this rule, a novel maximum likelihood (ML) decoding algorithm for tail-biting codes is presented. On tail-biting trellis, computational complexity and memory consumption of this decoder are significantly reduced comparing to other available ML decoders, such as the two-phase ML decoder. To further reduce the decoding complexity, we propose a new near-optimal decoding algorithm based on a simplified trap detection strategy. The performance of the above algorithms is validated with simulation.

ABSTRACT Solving wireless packet retransmission problems (WPRTPs) using network coding (NC) approach is increasingly attracting research efforts. However, existing researches are almost all focused on solutions in Galois field GF(2), and consequently, the solutions found by these schemes are usually less optimal. In this paper, we focus on optimal NC‐based scheme for perfect WPRTPs (P‐WPRTPs) where, with respect to each receiver, a packet is either requested by or already known to it. The number of retransmitted packets in optimal NC‐based solutions to P‐WPRTPs is firstly analyzed and proved. Then, random network coding‐based optimal scheme (RNCOPT) is proposed for P‐WRPTPs. RNCOPT is optimal in the sense that it guarantees to obtain a valid solution with minimum number of packet retransmissions. Furthermore, in RNCOPT, each coding vector is generated using a publicly known pseudorandom function with a randomly selected seed. The seed, instead of the coding vector, is used as decoding information to be retransmitted together with the coded packet. Thus, packet overhead of RNCOPT is reduced further. Extensive simulations show that RNCOPT distinctively outperforms some previous typical schemes for P‐WPRTPs in saving the number of retransmitted packets. Copyright © 2011 John Wiley & Sons, Ltd.

In this demonstration, we will reveal a full functional wireless access for vehicular environments (WAVE) prototype, which achieves the complete functions defined by the IEEE 802.11p standard through integrating effective and novel base-band algorithms including fast time-synchronization, multiple-stage multiple Doppler detection, accurate channel estimate, and joint QAM demodulation and convolution decoding, all upon the Cyclone III field programmable gate array (FPGA) development kit from the Terasic Company. The WAVE prototype has been extensively tested under various road conditions showing satisfied performances. The WAVE prototype has an Ethernet interface to connect with a computer, upon which media control access (MAC) protocols and a vehicular network simulator operate. Meanwhile, the prototype can also connect with an Acer Iconia Tablet running on the Android system through a universal series bus (USB) to support various intelligent transportation system (ITS) applications based on vehicular communications and networks. This activity is funded by several NSF grants and the CISCO Research Grant.

In this paper, a low complexity suboptimal monobit receiver, denoted as Q-function estimation (QFE) based monobit receiver, is proposed for transmitted-reference (TR) based impulse radio (IR) ultra wideband (UWB) systems to mitigate the performance degradation caused by severe quantization noise due to employing monobit ADCs. Through accumulating reference samples over multiple blocks, the QFE-based monobit receiver can considerably reduce the noise-on-noise effect and optimize the contribution of each sample to the decision statistic. Computer simulations demonstrate that in both line-of-sight (LOS) and non-LOS (NLOS) channels the QFE-based monobit weighted TR receiver can achieve a close-to-optimal bit-error rate (BER) performance without requiring full channel state information. Furthermore, because the optimal combining weights can be obtained offline and saved into a lookup table, the complexity of the proposed suboptimal monobit receiver is quite low. Therefore, it is considered as a promising technology for IR-UWB applications requiring low system complexity and low power consumption.

In this paper, two novel digital signal processing technologies, denoted as polarity-invariant square law (PISL) technology and forgetting factor based successive reference enhancement (SRE) technology, are proposed for transmitted reference (TR) based monobit receivers to compensate the quantization noise and enhance the quality of reference pulses. Since weighted TR (WTR) system can achieve a superior performance as well as a high data-rate under severe multipath environments, the PISL and SRE technologies are applied to the WTR receiver over intra-vehicle channels. The results show that compared to the SRE technology, the PISL technology enables a fixed summation time for all multipath channels, and significantly enhances the performance of the monobit ADC WTR receiver. Therefore, PISL technology is a promising technology to compensate the information loss caused by monobit quantization insuring high-performance, power efficient, and low complexity implementation for TR-based UWB receivers.

The paper describes information theoretic capacity of orthogonal pulse based modulation schemes for time hopping ultra wideband (TH-UWB) systems over a multiple access and multipath fading channel. Orthogonal pulse based modulation schemes such as pulse shape modulation (PSM), biorthogonal PSM (BPSM) and a combination of orthogonal pulse position modulation (OPPM) and BPSM have been proposed for reducing inter symbol interference (ISI) and multiple access interference (MAI) as well as for improving system performance. System capacity of TH-UWB systems can be increased by employing these modulations for higher level modulation schemes. The capacity of OPPM-BPSM outperforms PSM and BPSM schemes over a multipath fading channel. The complete mathematical analysis and theoretical simulation results are provided in detail.

Inspired by the overwhelming popularity of nowadays wireless local area networks (wireless LAN, or Wi-Fi), researchers and developers have uncovered their wide application perspectives in a vehicular environment. Currently, several prototypes of dedicated short range communications (DSRC) for vehicular networks have been developed by some companies for both intelligent transportation systems (ITS) and vehicular infrastructure integration (VII). However, most of the designers simply apply the existing indoor wireless technologies, such as Wi-Fi, into a vehicular environment without redesigning them for a vehicular environment. The vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) channels feature with doubly selective fading due to the high mobility of vehicles. Both theoretical analysis and experiments have verified that the indoor wireless technologies are unable to achieve optimized and robust performance when applied to a vehicular environment. Industry is calling for new physical and MAC layer protocols for ITS and VII. The IEEE 802.11p workgroup is currently working on standardizing the wireless access for vehicular environment (WAVE), which is anticipated to be ratified in 2009. In this paper, we brief the design of a WAVE prototype based on the IEEE 802.11p protocol, which allows us to implement and evaluate the performance of the IEEE 802.11p standard in a practical approach.

It has been widely known that one of the key design parameters in orthogonal frequency division multiplexing (OFDM) systems is the distribution of peak-to-average power ratio (PAPR). Recently some theoretical approaches to determine the PAPR distribution have been proposed based on the assumption that all subcarriers are allocated with equal power. However, this assumption may not be valid due to the following facts. First, in all realistic OFDM systems, usually only a subset: of subcarriers are used to carry information (active subcarriers) and the rest (inactive subcarriers) are set to zero. Second, due to the efficiency concerns transmission power should be allocated to active subcarriers. Third, power allocation may vary depending on different constellations used by different active subcarriers and their signal-to-noise-ratios. In this paper, we propose a general approach to identify PAPR distribution in OFDM systems. Specifically, a more accurate analytical expression of the PAPR distribution is derived with the help of Extreme Value Theory for Chi-squared-2 process in OFDM systems with unequal power distribution strategy. To validate the analytical results, extensive simulations have been conducted, showing a very good match between the identified PAPR distribution and that of real OFDM systems.

Cognitive radio (CR) is a dynamic spectrum access technology as a solution to spectrum under-utilization problem in some licensed bands. Operating over an exceedingly wide spectrum, CR systems usually adopt multi-carrier modulation (MCM) to implement flexible channelization. Consequently, efficient channel allocation scheme becomes extremely important to an MCM based CR (MCM-CR) system. In this paper, a maximum likelihood detection model is developed to detect the presence and locations of licensed users (LUs) signals in the frequency domain. Performance of the detection model, including the optimal detection region, detection probability and false alarm probability, is analyzed. A one-order two-state Markovian chain model is proposed to predict channel status information. In particular, a novel subcarrier allocation scheme for MCM-CR systems is proposed, taking into account the confidence of channel estimation, quality of services (QoS) of rental users (RUs) and throughput. To validate the analytical results, simulations have been conducted to show effectiveness of the proposed scheme.

In this paper, we first discuss multicarrier modulation (MCM) based cognitive radio (CR) systems. A maximum likelihood ratio spectrum detection model is then presented to detect the occurrence and spectrum gap of licensed users (LUs) signals. Next, we theoretically study the proposed model by deducing an optimal decision region and the detection probability and false alarm probability. Simulation results validate the derived performances of the proposed model for MCM based CR systems.

Future wireless intra-vehicle communications (IVC) systems adopting ultra-wideband (UWB) radio are proposed in this paper, which provide onboard passengers with high-speed duplex data exchange services. In this paper, a vehicular UWB channel model is first developed by modifying the IEEE 802.15.3a indoor model to fit into the vehicular environments with dense and concentrated clusters and rays. The main channel statistical parameters, such as maximum excess delay, root mean square delay and the number of multipath components are then theoretically deduced. Next, the proposed vehicular model is verified by experimental data gained from a measurement campaign conducted within a pickup truck, which lays down a solid foundation for theoretical analysis and system design for future wireless IVC systems.

In this paper, we provide the design criteria of the nonlinear companding transforms for reduction in peak-to-average power ratio (PAPR) of multi-carrier modulation (MCM) signals, which can enable the original MCM signals to be transformed into the desirable distribution. As examples, some novel nonlinear companding transforms have been proposed to transform the amplitude or power of the original MCM signals into uniform distribution, which can effectively reduce the PAPR for different modulation formats and subcarrier sizes without any complexity increase and bandwidth expansion. It has been shown by computer simulations that the proposed schemes can significantly improve the performance of MCM systems including bit-error-rate and PAPR reduction.

At first, this paper presents an overview on the background and technical merits of wireless access for vehicular environments (WAVE) systems. Next, a WAVE testbed was setup and the preliminary experimental results are reported. The WAVE testbed operates at the center frequency of 5.9 GHz and adopts a signal format defined by a draft of the IEEE 802.11p standard. Based on the experimental data captured in a typical vehicle-to-roadside access point environment, related channel impulse responses and capacities are extracted and analyzed

This paper aims to lay a solid foundation for the application of ultra-wideband (UWB) radio in vehicle environments by exploring the characteristics of UWB channels within a vehicle. A comprehensive measurement campaign was conducted to gather a set of channel impulse responses of UWB links within and outside an armored vehicle. Based on the experimental data, the channel's temporal characteristics, path loss, and capacities are analyzed. The distributions of delay spread and amplitudes of multipath signals are also studied, showing correspondence with the IEEE 802.15.3a UWB channel model. The UWB channels within the vehicle are then modeled by extracting relevant cluster and ray arrival rates and cluster and ray decay factors.

This paper describes the results from a real-time network test bed for a Linux-based control system with event-driven message traffic. Interest has grown in the use of Linux as a cost-effective alternative to expensive proprietary real-time operating systems. However, kernel tasks in Linux can cause random delays in message transmissions. Event-driven traffic can result in unpredictable message inter-arrival rates. Nondeterministic delays in message transmissions and sporadic message arrival times complicate the design of the network as they require the use of an estimation technique to analyze feasibility. Random temporal behavior can lead to network overloads, where it becomes unavoidable that some messages will be late. We discuss the design and feasibility analysis for the network and evaluate the network's performance in the presence of random kernel delay and sporadic message arrivals. Three message scheduling approaches are evaluated using different Linux configurations at different levels of network loading

The paper proposes a simple cascade estimation method to detect both carrier frequency and sampling clock offsets for orthogonal frequency-division multiplex (OFDM) systems. The new approach needs much less computation than the typical maximum likelihood (ML) method and generates a satisfactory estimate, which is validated by simulation results.

This paper studies the statistical properties of the conventional frequency offset estimation algorithm. Analytical expressions describing the mathematic expectation and the variance are derived for both the integer and the fractional frequency offset estimation algorithms. The theoretical equations presented in this paper provide improved agreement with simulation results in comparison to those previously reported in the literature.