# Remotely-sensed TOA interpretation of synthetic UWB based on neural networks

- Hao Zhang
^{1, 3}Email author, - Xue-rong Cui
^{1, 2}and - T Aaron Gulliver
^{3}

**2012**:185

**DOI: **10.1186/1687-6180-2012-185

© Zhang et al.; licensee Springer. 2012

**Received: **12 July 2011

**Accepted: **2 August 2012

**Published: **25 August 2012

## Abstract

Because of the good penetration into many common materials and inherent fine resolution, Ultra-Wideband (UWB) signals are widely used in remote sensing applications. Typically, accurate Time of Arrival (TOA) estimation of the UWB signals is very important. In order to improve the precision of the TOA estimation, a new threshold selection algorithm using Artificial Neural Networks (ANN) is proposed which is based on a joint metric of the skewness and maximum slope after Energy Detection (ED). The best threshold based on the signal-to-noise ratio (SNR) is investigated and the effects of the integration period and channel model are examined. Simulation results are presented which show that for the IEEE802.15.4a channel models CM1 and CM2, the proposed ANN algorithm provides better precision and robustness in both high and low SNR environments than other ED-based algorithms.

### Keywords

Artificial Neural Network (ANN) Remote sensing Ultra-Wideband (UWB) TOA estimation Ranging Skewness## Introduction

As a new wireless communications technology, Ultra-Wideband (UWB) has generated considerable research interest due to the many potential applications. One of the most promising areas is remote sensing [1, 2]. For example, Defense Research and Development Canada (DRDC) Ottawa has conducted numerous experiments on indoor through-wall imaging, snow penetration, stand-off remote sensing of human subjects, and mine detection using high-resolution UWB signals [1]. In [2], UWB propagation channel characterization was performed to test the feasibility of using UWB technology in underground mining to monitor and communicate with remote sensors.

UWB technology offers many advantages for remote sensing [1]. First, some frequency components may be able to penetrate obstacles to provide a Line-Of-Sight (LOS) signal. Second, the transmission of very short pulses makes high time resolution (sub-nanosecond to nanosecond) possible. Third, the wide signal bandwidth means a very low power spectral density, which reduces interference to other Radio Frequency systems.

Among the potential applications, precision ranging or Time of Arrival (TOA) estimation is the most important for remote sensing. However, this is a very challenging problem due to the severe environments encountered, e.g., thermal noise, multi-path fading, reflection interference, and inter-symbol interference. The TOA estimation problem has extensively been studied [3–6]. There are two approaches applicable to UWB technology, a Matched Filter (MF) [3] (such as a Rake or correlation receiver) with a high sampling rate and high-precision correlation, or an Energy Detector (ED) [4–6] with a lower sampling rate and low complexity. An MF is the optimal technique for TOA estimation, where a correlator template is matched exactly to the received signal. However, an UWB receiver operating at the Nyquist sampling rate makes it very difficult to align with the multipath components of the received signal [7]. In addition, an MF requires *a priori* estimation of the channel, including the timing, amplitude, and phase of each multipath component of the impulse [7]. Because of the high sampling rates and channel estimation, an MF may not be practical in many applications. As opposed to a more complex MF, an ED is a non-coherent approach to TOA estimation. It consists of a square-law device, followed by an integrator, sampler, and a decision mechanism. The TOA estimate is made by comparing the integrator output with a threshold and choosing the first sample to exceed the threshold. It is a practical solution as it directly yields an estimate of the start of the received signal. An ED is thus a low complexity, low sampling rate receiver that can be employed without the need for *a priori* channel estimation.

The major challenge with ED is the selection of an appropriate threshold based on the received signal samples. Threshold selection for different signal-to-noise ratios (SNRs) has been investigated via simulation. In [4], a normalized threshold selection technique for TOA estimation of UWB signals was proposed which uses exponential and linear curve fitting of the kurtosis of the received samples. In [5], an approach based on the minimum and maximum sample energy was introduced. These approaches have limited TOA precision, as the strongest path is not necessarily the first arriving path.

Neural networks (NNs) have extensively been used in signal processing applications. The weights between the input and output layers can be adjusted to minimize the error between the input and output. Because of the complexity of wireless environments, it is difficult to derive a closed-form expression to estimate the TOA. On the other hand, an artificial neural network (ANN) can provide a very flexible mapping based on the training input. The ANN here intends to solve a regression problem being *J* the input and optimal threshold the output.

In this article, we consider the relationship between the SNR and the statistics of the integrator output including skewness, maximum slope, kurtosis and standard deviation. A metric based on skewness and maximum slope is then used as the ANN input. A back propagation (BP) NN is used which is a feed forward NN. It approximates the relationship between the joint metric and the optimal threshold by using a nonlinear continuum rational function. Performance results are presented which show that in the IEEE 802.15.4a channel models CM1 and CM2, this ANN provides robust estimates with high precision for both high and low SNRs.

The remainder of this article is organized as follows. In the following section, the system model is presented. Section “TOA estimation based on ED” discusses TOA estimation algorithms based on ED. Section “Statistical characteristics of the signal energy” considers the statistical characteristics of the energy values, and a joint metric based on skewness and maximum slope is proposed. In Section “Optimal normalized threshold with respect to *J*”, the relationship between the joint metric and optimal normalized threshold is established. Section “Threshold selection using an ANN based on skewness and maximum slope” introduces a novel TOA estimation algorithm based on an ANN. Some performance results are presented in Section “Performance results and discussion”, and Section “Conclusions” concludes the article.

## System model

IEEE 802.15.4a [8] is the first international standard that specifies a wireless physical layer to enable precise TOA estimation and wireless ranging. It includes channel models for indoor residential, indoor office, industrial, outdoor, and open outdoor environments, usually with a distinction between LOS and non-LOS (NLOS) properties. In this article, a Pulse Position Modulation Time Hopping UWB (PPM-TH-UWB) signal [9] is employed for transmission between the transmitter and receiver.

### UWB signal

*i*and

*T*

_{ f }are the frame index and frame duration, respectively. The time hopping TH is provided by a pseudorandom integer-valued sequence

*c*

_{ i }, which differs for each user to allow for multiple access communications.

*T*

_{ c }is the chip time, and the PPM time shift is

*ϵ,*with the data

*a*

_{ i }either 0 or 1. If

*a*

_{ i }=1, the signal is shifted in time, otherwise there is no PPM shift. The pulse is given by

*p*(

*t*). For example, the second derivative Gaussian pulse is given by

where *α* is the shape factor and *f*(*t*) is the Gaussian pulse. A smaller value of *α* results in a shorter pulse duration and thus a larger bandwidth.

### Multipath fading channel

*N*is the number of received multipath components,

*α*

_{ n }and

*τ*

_{ n }denote the amplitude and delay of the

*n*th path, respectively, and

*n*(

*t*) is additive white Gaussian noise with zero mean and two-sided power spectral density

*N*

_{0}/2. Equation (3) can be rewritten as

*s*(

*t*) is the transmitted signal, and

*h*(

*t*) is the channel impulse response given by

where *X* is a log-normal random variable representing the amplitude gain of the channel, *N*_{
c
} is the number of observed clusters, *K*(*n*) is the number of multipath components received within the *n* th cluster, *α*_{
nk
} is the coefficient of the *k* th component of the *n* th cluster, *T*_{
n
} is the TOA of the *n* th cluster and *τ*_{
nk
} is the delay of the *k* th component within the *n* th cluster.

### Energy detector

*T*

_{ b }. Because of the inter-frame leakage due to multipath signals, the integration duration is set to 3

*T*

_{f}/2 [4], so the number of signal values for ED is

*N*

_{b}= (3

*T*

_{f})/(2

*T*

_{b}). The integrator output can then be expressed as

*n*= 1, 2, …,

*N*

_{b}is the sample index with respect to the start of the integration period and

*N*

_{ s }is the number of pulses per symbol. Here,

*N*

_{ s }is set to 1, so the integrator output is

*z*

*n*is the integration of noise only, it has a centralized Chi-square distribution, while it has a non-centralized Chi-square distribution if a signal is present. The mean and variance of the noise and signal values are given by [4]

respectively, where *E*_{
n
} is the signal energy within the *n* th integration period and *F* is the number of degrees of freedom given by *F =* 2*BT*_{
b
}*+* 1. *B* is the signal bandwidth.

## TOA estimation based on ED

### TOA estimation algorithms

*z*$\widehat{n}$ is located before the maximum z

*n*

_{max}, i.e., $\widehat{n}$≤

*n*

_{max}. Thus, Threshold Crossing (TC) TOA estimation has been proposed where the received energy values are compared to an appropriate threshold

*ξ*. In this case, the TOA estimate is given by

*ξ*directly, so a normalized threshold

*ξ*

_{norm}is usually employed with

The TOA estimate is then obtained using Equation (11). The problem in this case becomes one of how to set the threshold, i.e., how to establish the relationship between the received energy values and *ξ*_{norm}. There are two main methods in the literature, curve fitting and fixed threshold (FT). In [4], a normalized threshold selection technique for TOA estimation of UWB signals was proposed which uses exponential and linear curve fitting of the kurtosis of the received samples. A simpler approach is the FT algorithm where the threshold is set to a fixed value, for example *ξ*_{norm} = 0.4. If *ξ*_{norm} is set to 1, the algorithm is the same as MES. In this article, an ANN algorithm is employed to obtain the normalized threshold based on the signal energy statistics.

### TOA estimation error

where *t*_{
n
} is the *n* th actual propagation time,${\widehat{t}}_{n}$ is the *n* th TOA estimate, and *N* is the number of TOA estimates.

## Statistical characteristics of the signal energy

In this section, the skewness**,** maximum slope, kurtosis and standard deviation of the energy values are analyzed.

### Kurtosis

where $\overline{x}$ is the mean, and *σ* is the standard deviation. The kurtosis for a standard normal distribution is three. For this reason, *k* is often redefined as *K* = *k* - 3 (referred to as excess kurtosis), so that the standard normal distribution has a kurtosis of zero. Positive kurtosis indicates a “peaked” distribution, while negative kurtosis indicates a “flat” distribution. For noise only (or for a low SNR) and sufficiently large *F* (degrees of freedom of the Chi-square distribution), *z*[n] has a Gaussian distribution and *K* = 0. On the other hand, as the SNR increases, *K* tends to increase.

*T*

_{b}= 4 ns, and a linear function for

*T*

_{b}=1 ns with

*K*as the

*x*-coordinate and

*ξ*

_{best}as the

*y*-coordinate. The resulting expressions are

The model coefficients were obtained using data from both the CM1 and CM2 channels.

### Skewness

where $\overline{x}$ is the mean, and *σ* is the standard deviation of the energy values. The skewness for a normal distribution is zero, in fact any symmetric data will have a skewness of zero. Negative values of skewness indicate that the data are skewed left, while positive values indicate data that are skewed right. Skewed left indicates that the left tail is long relative to the right tail, while skewed right indicates the opposite. For noise only (or very low SNRs), and sufficiently large *F*, *S* ≈ 0. As the SNR increases, *S* tends to increase.

*T*

_{ b }= 1 ns and

*T*

_{ b }= 4 ns, with

*S*as the

*x*-coordinate and

*ξ*

_{best}as the

*y*-coordinate. The resulting functions are

### Maximum slope

*N*

_{b}-

*M*

_{b}+ 1) groups, with

*M*

_{ b }values in each group. The slope for each group is calculated using a least squares line fit. The maximum slope (

*M*) can then be expressed as

*M*

_{b}= 4, so there are 8-4 + 1 = 5 lines with 5 corresponding slopes.

### Standard deviation

### Joint metric

In order to examine the characteristics of the four statistical parameters (skewness**,** maximum slope, kurtosis, and standard deviation), the CM1 (residential LOS) and CM2 (residential NLOS) channel models from the IEEE802.15.4a standard are employed. For each SNR value, 1,000 channel realizations were generated and sampled at *F*_{
c
} = 8 GHz. A second derivative Gaussian pulse is employed with *T*_{
f
} = 200 ns, *T*_{
c
} = 1 ns, *T*_{
b
} = 4 ns, and *N*_{
s
} = 1. Each realization has a TOA uniformly distributed within (0, *T*_{
f
}).

*S*is the skewness and

*M*is the maximum slope.

**Standard Deviation of the Statistics**

SNR | Skewness | Kurtness | Maximum Slope | Standard Deviation |
---|---|---|---|---|

(10E-7) | (10E-15) | |||

4 | 0.30 | 0.92 | 4.90 | 1.16 |

6 | 0.31 | 0.95 | 3.02 | 0.72 |

8 | 0.31 | 0.93 | 1.83 | 0.46 |

10 | 0.32 | 0.97 | 1.25 | 0.29 |

12 | 0.35 | 1.22 | 0.85 | 0.19 |

14 | 0.46 | 2.23 | 0.65 | 0.13 |

16 | 0.73 | 4.36 | 0.62 | 0.10 |

18 | 1.09 | 7.82 | 0.60 | 0.09 |

20 | 1.39 | 12.04 | 0.62 | 0.10 |

22 | 1.39 | 13.46 | 0.58 | 0.09 |

24 | 1.41 | 15.11 | 0.58 | 0.10 |

26 | 1.36 | 15.20 | 0.57 | 0.09 |

28 | 1.36 | 15.73 | 0.56 | 0.09 |

30 | 1.34 | 15.65 | 0.56 | 0.09 |

32 | 1.34 | 15.76 | 0.56 | 0.09 |

*J*is sensitive to both high and low SNRs, 1,000 channel realizations were generated for many SNR values in each IEEE802.15.4a channel. In the simulations, because of the random signal, the

*J*values are not unique for one SNR, but in order to draw Figure 6, the average

*J*value with respect to SNR were calculated for each channel model and integration period. Because there were 29 SNR values simulated, there are 29

*J-SNR*pairs for each channel model and integration period. Figure 6 shows that

*J*is a monotonic function for a large range of SNR values, and that

*J*is more sensitive to the changes in SNR than any single parameter. The four curves differ somewhat due to the channel model and integration period used. The figure shows that the metric is more sensitive to

*T*

_{b}than the channel model.

## Optimal normalized threshold with respect to *J*

*J*and the optimal normalized threshold

*ξ*

_{opt}must be established. According to Figure 6, the curves for channel models CM1 and CM2 for a given value of

*T*

_{b}are similar, so models are derived only for

*T*

_{b}=1 ns and

*T*

_{b}=4 ns. There are four steps to establish the relationship between

*J*and

*ξ*

_{opt}.

- (1)
Generate a large number of channel realizations for each channel model, integration period, and SNR value in the range [4, 32] dB.

- (2)
Calculate the average MAE value with respect to normalized threshold

*ξ*_{norm}for each*J*value, channel model, and integration period as shown in Section “Average MAE with respect to the normalized threshold”. In the simulation, because of the random signal, there are many MAE values with respect to one normalized threshold, so the average MAE should be calculated. At the same time, because*J*is a real value,*J*should be rounded to the nearest discrete value, for example integer value or half-integer value. - (3)
Select the normalized threshold with the lowest MAE as the best threshold

*ξ*_{best}with respect to*J*for each channel model and integration period, as shown in Section “Optimal thresholds”. - (4)
Calculate the average normalized thresholds of channels CM1 and CM2 for each

*J*as the optimal normalized threshold*ξ*_{opt}, as shown in Section “Optimal thresholds”.

### Average MAE with respect to the normalized threshold

To determine the optimal threshold *ξ*_{opt} based on *J*, the relationship between the average MAE and the normalized threshold *ξ*_{norm} for different *J*, channel model and *T*_{b} was determined. *ξ* is the threshold which is compared to the energy values to find the first TC, as defined (12). When *ξ* is larger than the maximum energy value *z*_{max}, no value is found for *τ*, so in this case *ξ* is set to *z*_{max}, and *ξ*_{norm} is set to 1.

*J*values were rounded to the nearest integer and half-integer values for all SNR values, that is, the range [−9, 16] and [−4, 8] for

*T*

_{ b }=1 ns and

*T*

_{ b }=4 ns. Figures 7, 8, 9 and 10 only show the MAE for integer

*J*= 1 to 8 for the CM1 and CM2 channels, and

*T*

_{ b }= 1 ns and

*T*

_{ b }= 4 ns. The relationship is always that the MAE decreases as

*J*increases. In addition, the minimum MAE is lower as

*J*increases.

### Optimal thresholds

*ξ*

_{norm}with respect to the minimum MAE is called the best threshold

*ξ*

_{best}for a given

*J*. Therefore, the lowest points of the curves in Figures 7, 8, 9, and 10 for each

*J*are selected as the

*ξ*

_{best}. These best thresholds are given in Figures 11 and 12.

## Threshold selection using an ANN based on skewness and maximum slope

### Structure of the ANN

*T*

_{ b }= 1 ns, when the number of neurons in the hidden layer is more than 20, the percentage is greater than 90% and changes only slightly with increasing values, so 20 is selected as the number of neurons in the proposed ANN. For

*T*

_{ b }= 4 ns, when this number of neurons is more than 10, the percentage is greater than 95% and changes very little with increasing values, so 10 is selected in this case.

The value of *ξ*_{norm} ranges from 0 to 1, so the logsig function is selected as the transfer function for the neurons of both the hidden and output layers. This function is defind as logsig(x) = 1/(1 + exp(−x)). The Levenberg-Marquardt (LM) algorithm is used in the network training to update the weight and bias values according to LM optimization [12]. Although this algorithm requires more memory than other algorithms, it is often the fastest BP algorithm. Because there is only one input and one output element in the proposed ANN, and only 39 *ξ*_{norm}*J* pairs (*J* = −9 to 16 for *T*_{
b
} =1 ns and *J* = −4 to 8 for *T*_{
b
} =4 ns), the memory requirements are modest. The weight and bias values before training were set to random values uniformly distributed between −1 and 1.

### ANN training

In order to train the ANN, i.e., to determine the relationship between *J* and the normalized threshold *ξ*_{norm}, 1,000 CM1 and CM2 channel realizations for each value of SNR from 4 to 32 dB were generated for both *T*_{b} = 1 ns and *T*_{b} = 4 ns. The integer *J* values in the range [−9, 16] and [−4, 8] for *T*_{b} =1 ns and *T*_{b} =4 ns, respectively, were used to train the ANN. Thus, there were 39 samples to train the ANN. On the other hand, the half-integer *J* values in the range [−0.85, 15.5] and [−3.5, 7.5] for *T*_{b} =1 ns and *T*_{b} =4 ns, respectively, were used to conduct the external validation for the trained ANN. To obtain the best ANN, 100 separate training iterations were conducted for each value of *T*_{b}, and the one with the lowest MSE was selected.

### Validation of the ANN

*J*values from −9 to 16 for the internal validation with

*T*

_{b}=1 ns, from −8.5 to 15.5 for the external validation with

*T*

_{b}=1 ns, from −4 to 8 for the internal validation with

*T*

_{b}=4 ns and from −3.5 to 7.5 for the external validation with

*T*

_{ b }=4 ns were input to the ANN to get the estimated normalized thresholds. As shown in Table 2, the two coefficients of determination of the internal validation for

*T*

_{b}=1 ns and

*T*

_{b}=4 ns are both nearly equal to 1 and the two coefficients of determination of the external validation for

*T*

_{b}=1 ns and

*T*

_{b}=4 ns are both more than 0.97, so the trained ANN output fits well with the optimal normalized thresholds for

*T*

_{b}=1 ns and

*T*

_{b}=4 ns. However, the ANN is able to provide values for any

*J*, and not just discrete values. The ANN also eliminates the complicated and time-consuming optimization process used in Section “Optimal normalized threshold with respect to

*J*”. The IEEE802.15.4a channel models reflect the statistical properties in specific environments, and the choice of ANN parameters depends on the characteristics of the channel. Our ANN can easily be employed with any channel, and the parameters adjusted to fit any environment. This is particularly useful when the channel is not static.

**Validation Results of the ANN**

Validation | T | Input of ANN (J) | Coefficient of Determination |
---|---|---|---|

Internal |
| [-9, -8, .., 15, 16] | 1 |

External |
| [-8.5, -7.5, .. , 14.5, 15.5] | 0.9774 |

Internal |
| [-4, -3, .. , 7, 8] | 1 |

External |
| [-3.5, -2.5, .. , 6.5, 7.5] | 0.9727 |

## Performance results and discussion

In this section, the MAE is examined for different ED based TOA estimation algorithms in the IEEE 802.15.4a channel model CM1 and CM2. As before, 1,000 channel realizations were generated for each case. A second derivative Gaussian pulse with a 1 ns pulse width was employed, and the received signal sampled at *F*_{
c
} = 8 Ghz. The other system parameters were *T*_{
f
} = 200 ns and *N*_{
s
} =1. Each realization had a TOA uniformly distributed within (0, *T*_{
f
}).

*T*

_{b}= 1 ns and 4 ns. This shows that the ANN algorithm performs well at high SNRs. The performance in CM1 is better than in CM2 by at most 18 ns. When SNR > 22 dB, the MAE for CM1 is less than 3.85 ns while for CM2 it is less than 11 ns. In most cases, the performance with

*T*

_{b}= 1 ns is better than that with

*T*

_{b}= 4 ns, regardless of the channel, but the difference is less than 4 ns.

**MAE averaged over all the simulated realizations**

Channel model |
T
| MAE (ns) | |||
---|---|---|---|---|---|

ANN | Fixed-Threshold | MES | Kurtosis | ||

CM1 | 1 ns | 29.54 | 50.48 | 38.09 | 42.74 |

4 ns | 29.66 | 50.13 | 38.93 | 63.57 | |

CM2 | 1 ns | 37.88 | 58.51 | 47.12 | 50.12 |

4 ns | 36.64 | 57.03 | 46.00 | 69.20 |

The performance of the proposed algorithm is more robust than the other algorithms, as the difference between *T*_{b} = 1 ns and 4 ns is very small compared to the difference with the Kurtosis algorithm. For almost all SNR values the proposed algorithm is the best. Conversely, the performance of the Kurtosis algorithm varies greatly with respect to the other algorithms, and is very poor for low to moderate SNR values.

## Conclusions

A low complexity ANN-based (TOA) estimation algorithm has been developed for UWB remote sensing applications. Four statistical parameters were investigated, and from the results obtained, a joint metric based on skewness and maximum slope was developed for TC TOA estimation. The optimal normalized threshold was determined using performance results for the CM1 and CM2 channels. The effects of the integration period and channel model were investigated. It was determined that the proposed threshold selection technique is largely independent of the channel model. The performance of the proposed algorithm is shown to be better than several well-known algorithms. In addition, the proposed algorithm is more robust to changes in the SNR and integration period.

## Declarations

### Acknowledgments

This study was supported by the Nature Science Foundation of China under grant No. 60902005, the Outstanding Youth Foundation of Shandong Province under grant No. JQ200821, and the Program for New Century Excellent Talents of the Ministry of Education under grant No. NCET-08-0504.

**Author details**

^{1}Department of Information Science and Engineering, Ocean University of China, Qing Dao, China. ^{2}Department of Computer and Communication Engineering, China University of Petroleum (East Chinxa), Qing Dao, China.^{3}Department of Electrical Computer Engineering, University of Victoria, Victoria, Canada.

## Authors’ Affiliations

## References

- Foo S, Walsh A, Kashyap S:
*Ultra-wideband (UWB) remote sensing and radar imaging*. 2004. /PDFS/unc36/p521851.pdf. Accessed 23 Feb 2011 http://pubs.drdc.gc.caGoogle Scholar - L Talbi, Y Rissafi, A Lakhssassi, UWB measurement investigation for remote sensing in underground mining environment:
*In Proceedings of the International Conference on Electromagnetics in Advanced Applications*. 2009, 11: 1030-1033. Torino, Italy, 14-18 September http://dx.doi.org/10.1109/ICEAA.2009.5297778Google Scholar - AY-Z Xu, EKS Au, AK-S Wong, Q Wang, A novel threshold-based coherent TOA estimation for IR-UWB systems. IEEE Trans:
*Vehic. Technol*. 2009, 58: 4675-4681. doi.org/10.1109/TVT.2009.2020990View ArticleGoogle Scholar - I Guvenc, Z Sahinoglu, Threshold selection for UWB TOA estimation based on kurtosis analysis:
*IEEE Commun. Letters*. 2005, 9: 1025-1027. 10.1109/LCOMM.2005.1576576 10.1109/LCOMM.2005.1576576View ArticleGoogle Scholar - I Guvenc, Z Sahinoglu, Threshold-based TOA estimation for impulse radio UWB systems:
*Proceedings of the IEEE International Conference on Ultra-wideband, Zurich*. 2005, 2005: 420-425. 5–8 September doi.org/10.1109/ICU.2005.15700245 5–8 SeptemberGoogle Scholar - H Zhang, X-R Cui, TA Gulliver, Threshold selection for ultra-wideband TOA estimation based on skewness analysis:
*Proceedings of the 8th International Conference on Ubiquitous Intelligence and Computing. Banff, AB*. 2011, 6905 LNCS: 503-513. 2–4 September doi.org/10.1007/978-3-642-23641-9_40 2–4 SeptemberGoogle Scholar - I Guvenc, Z Sahinoglu, Multiscale energy products for TOA estimation in IR-UWB systems:
*Proceedings of the IEEE Global Telecommunications Conference, St. Louis, MO*. 2005, 1: 209-213. 28 November - 2 December doi.org/10.1109/GLOCOM.2005.1577382Google Scholar - AF Molisch, K Balakrishnan, D Cassioli, C-C Chong, S Emanmi, A Fort, F Karedal, J Kunisch, H Schantz, U Schuster, K Siwiak:
*IEEE 802.15.4a Channel Model—Final Report*. 2006. IEEE P802.15-04-0662-00-004aGoogle Scholar - H Zhang, TA Gulliver, Capacity of time-hopping PPM and PAM UWB multiple access communications over indoor fading channels:
*Eurasip J. Wireless Commun. and Networking*. 2008, 2008: 1-9. doi.org/10.1155/2008/273018Google Scholar - S Haykin:
*Neural Networks: A Comprehensive Foundation*. 2nd edition. Prentice-Hall, London; 1999.Google Scholar - R Vicen-Bueno, R Carrasco-Alvarez, M Rosa-Zurera, JC Nieto-Borge, MP Jarabo-Amores, Artificial neural network-based clutter reduction systems for ship size estimation in maritime radars:
*EURASIP J. Advances in Signal Processing*. 2010, 2010: 1-15. 10.1155/2010/380473Google Scholar - G Lera, M Pinzolas, Neighborhood based Levenberg-Marquardt algorithm for neural network training, IEEE Trans:
*Neural Networks*. 2002, 13: 1200-1203. 10.1109/TNN.2002.1031951 10.1109/TNN.2002.1031951View ArticleGoogle Scholar

## Copyright

This article is published under license to BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.