Feature Relationships Learning Incorporated Age Estimation Assisted by Cumulative Attribute Encoding

The research of human facial age estimation(AE)has attracted increasing attention for its wide applications.Up to date,a number of models have been constructed or employed to perform AE.Although the goal of AE can be achieved by either classification or regression,the latter based methods generally yield more promising results because the continuity and gradualness of human aging can naturally be preserved in age regression.However,the neighbor-similarity and ordinality of age labels are not taken into account yet.To overcome this issue,the cumulative attribute(CA)coding was introduced.Although such age label relationships can be parameterized via CA coding,the potential relationships behind age features are not incorporated to estimate age.To this end,in this paper we propose to perform AE by encoding the potential age feature relationships with CA coding via an implicit modeling strategy.Besides that,we further extend our model to gender-aware AE by taking into account gender variance in aging process.Finally,we experimentally validate the superiority of the proposed methodology.

ADAPTIVE ALGORITHM FOR CONSISTENTMA PARAMETER ESTIMATION VIATHIRD ORDER CUMULANT

This paper addresses the problem of adaptive,consistent parameter estimation for a MA model from the 3rd order cumulant of the system output. The proposed adaptive algorithm is derived by using the new linear equation system (J. K. Tugnait, 1990), which is proved to have unique solution,and hence guarantees the consistence of the MA parameters. Simulation results are provided to show the performance of the new algorithm.

A MODIFIED HIGH-ORDER CUMULANT MUSIC ALGORITHM FOR SIGNAL DOA ESTIMATION

This paper gives a MUSIC signal DOA estimation algorithm based on the modified high-order cumulant matrix which is constructed by the recieved data and their conjugate rearrangements. When the snapshot number is limited, this algorithm can improve the signal DOA estimation performances obviously, and its computational complexity scarcely increases. Finally, some simulation results to verify the theoretical analyses are presented.

Uniformly Minimum-Variance Unbiased Estimator (UMVUE) for the Gamma Cumulative Distribution Function with Known and Integer Scale Parameter

Uniformly minimum-variance unbiased estimator (UMVUE) for the gamma cumulative distribution function with known and integer scale parameter. This paper applies Rao-Blackwell and Lehmann-Scheffeé Theorems to deduce the uniformly minimum-variance unbiased estimator (UMVUE) for the gamma cumulative distribution function with known and integer scale parameters. The paper closes with an example comparing the empirical distribution function with the UMVUE estimates.

Parameter estimation of DSSS signals in non-cooperative communication system

A new adaptive estimator for direct sequence spread spectrum （DSSS） signals using fourth-order cumulant based adaptive method is considered. The general higher-order statistics may not be easily applied in signal processing with too complex computation. Based on the fourth-order cumulant with 1-D slices and adaptive filters, an efficient algorithm is proposed to solve the problem and is extended for nonstationary stochastic processes. In order to achieve the accurate parameter estimation of direct sequence spread spectrum （DSSS） signals, the fast step uses the modified fourth-order cumulant to reduce the computing complexity. While the second step employs an adaptive recursive system to estimate the power spectrum in the frequency domain. In the case of intercepted signals without large enough data samples, the estimator provides good performance in parameter estimation and white Gaussian noise suppression. Computer simulations are included to corroborate the theoretical development with different signal-to-noise ratio conditions and recursive coefficients.

A Mo LC+Mo M-based G^0 distribution parameter estimation method with application to synthetic aperture radar target detection

The accuracy of background clutter model is a key factor which determines the performance of a constant false alarm rate(CFAR) target detection method. G0 distribution is one of the optimal statistic models in the synthetic aperture radar(SAR) image background clutter modeling and can accurately model various complex background clutters in the SAR images. But the application of the distribution is greatly limited by its disadvantages that the parameter estimation is complex and the local detection threshold is difficult to be obtained. In order to solve the above-mentioned problems, an synthetic aperture radar CFAR target detection method using the logarithmic cumulant(Mo LC) + method of moment(Mo M)-based G0 distribution clutter model is proposed. In the method, G0 distribution is used for modeling the background clutters, a new Mo LC+Mo M-based parameter estimation method coupled with a fast iterative algorithm is used for estimating the parameters of G0 distribution and an exquisite dichotomy method is used for obtaining the local detection threshold of CFAR detection, which greatly improves the computational efficiency, detection performance and environmental adaptability of CFAR detection. Experimental results show that the proposed SAR CFAR target detection method has good target detection performance in various complex background clutter environments.

Resolution performance analysis of cumulants-based rank reduction estimator in presence of unexpected modeling errors

Compared to the rank reduction estimator （RARE） based on second-order statistics （called SOS-RARE）, the RARE employing fourth-order cumulants （referred to as FOC-RARE） is capable of dealing with more sources and mitigating the negative influences of the Gaussian colored noise. However, in the presence of unexpected modeling errors, the resolution behavior of the FOC-RARE also deteriorate significantly as SOS-RARE, even for a known array covariance matrix. For this reason, the angle resolution capability of the FOC-RARE was theoretically analyzed. Firstly, the explicit formula for the mathematical expectation of the FOC-RARE spatial spectrum was derived through the second-order perturbation analysis method. Then, with the assumption that the unexpected modeling errors were drawn from complex circular Gaussian distribution, the theoretical formulas for the angle resolution probability of the FOC-RARE were presented. Numerical experiments validate our analytical results and demonstrate that the FOC-RARE has higher robustness to the unexpected modeling en＇ors than that of the SOS-RARE from the resolution point of view.

Performance of cumulant-based rank reduction estimator in presence of unexpected modeling errors

Compared with the rank reduction estimator(RARE) based on second-order statistics(called SOS-RARE), the RARE based on fourth-order cumulants(referred to as FOC-RARE) can handle more sources and restrain the negative impacts of the Gaussian colored noise. However, the unexpected modeling errors appearing in practice are known to significantly degrade the performance of the RARE. Therefore, the direction-of-arrival(DOA) estimation performance of the FOC-RARE is quantitatively derived. The explicit expression for direction-finding(DF) error is derived via the first-order perturbation analysis, and then the theoretical formula for the mean square error(MSE) is given. Simulation results demonstrate the validation of the theoretical analysis and reveal that the FOC-RARE is more robust to the unexpected modeling errors than the SOS-RARE.

基于高阶累积量ESPRIT算法的指数衰减正弦信号参数估计

工程应用中环境噪声多表现为高斯有色噪声,而针对高斯白噪声进行处理的算法失效问题,提出了一种高斯色噪声环境中用于多分量衰减正弦信号频率和衰减因子估计的四阶累积量ESPRIT算法。首先,推导出四阶累积量与观测样本中的自相关矩阵和互相关矩阵之间的关系,求出其四阶累积量矩阵。其次,通过对四阶累积量进行广义特征值分解,根据广义特征值即可得到信号衰减因子和频率的估计值。最后对所提算法进行了仿真实验验证,在混合信噪比为0 dB时,所提算法针对多分量衰减正弦信号角频率和衰减因子的平均估计误差分别为0.002 0πrad和0.002 0。在高斯白噪声和高斯色噪声背景下与ESPRIT算法和Prony算法相比具有更强的噪声抑制能力和更高的估计精度。

基于RARE-Cumulant的互耦校正和DOA估计

基于四阶累计量及RARE(RAnk reducee quation)变换,结合均匀线阵互耦矩阵的特殊性,提出了一种新的互耦校正及波达方向估计算法。虽然四阶累计量比传统的二阶方法算法复杂,却扩展了阵列孔径,提高了在色噪声背景下DOA估计精度,而互耦系数并未因增加了虚拟阵元而增多。RARE变换将互耦系数与波达方向参量分离,有效地实现了多维参数估计的降维处理,减小了多维参量估计的计算量。仿真实验表明,在高斯色噪声背景下,本文方法计算量小,而且估计能力明显优于二阶去耦算法和传统的四阶方法。

强干扰下基于三阶互累积量的FMCW雷达信号DOA估计算法

针对车载调频连续波雷达存在相互干扰的实际情况,本文提出了一种基于三阶互累积量的多目标波达方向超分辨估计方法.该方法利用同步采集的阵列信号并根据回波信号和干扰信号的非相关特性,构造三阶互累积量矩阵,随后根据子空间方法获得二维空间谱,实现距离和方位的联合估计.计算机仿真结果表明,本文所提方法能够在抑制强干扰影响的同时实现3°以内多目标识别,与现有超分辨法和重构法相比,具有更高的角度分辨率和估计精度.

基于高阶累积量的不规则阵列内插变换波达方向估计算法

对传感器阵列信号波达方向(DOA,direction of arrival)估计算法研究多集中在均匀线阵、圆阵等规则阵型阵列,但在水下传感网络等应用环境中阵元分布具有一定随机性,阵列呈现不规则特点.论文利用虚拟阵元思想,通过对不规则阵列的虚拟内插,在逻辑上构建多个具有相同配置参数的子阵列;对多个结构相同的子阵,利用空间平滑技术进行相关目标方位估计;为消除内插引入的非高斯有色噪声影响,引入信号高阶累积量,用累积量矩阵代替协方差矩阵,保证算法精确高效.通过计算机仿真,首先对比了不同信噪比和快拍数条件下提出的算法与传统算法性能,其次研究了构建子阵时角度间隔的取值对估计结果的影响,最后定量分析了特定信噪比和快拍数下新算法DOA估计的平均偏差和标准差,结果显示,新算法能有效提高估计精度.

考虑积累效应的弹药毁伤效能评估方法

为提高多发弹药对地面目标毁伤效能评估的精度,提出了一种考虑毁伤积累效应的多发弹药对地面装备目标毁伤效能评估方法。以典型地面装备为例,分析了地面装备的易损性,建立了杀爆类弹药对地面目标的毁伤能力表征方法及弹药毁伤效能评估模型;在此基础上,研究了毁伤积累效应对弹药毁伤能力的影响规律,实现了考虑毁伤积累效应的多发弹药毁伤效能评估。结果表明:考虑积累效应后,弹药对目标的毁伤效能指数不再是定值,而是随着弹药数的增加而逐渐增大,对目标的毁伤概率也随之增大,相较于不考虑毁伤积累效应时增大6%以上。

基于四阶累积量的改进传播算子DOA估计算法

针对四阶累积量在多重信号分类(multiple signal classification, MUSIC)算法中计算复杂度高和在低信噪比情况下性能差的问题,提出一种去冗余后平均的四阶累积量传播算子算法(modified fourth-order cumulant propagator method, MFOC-PM)。该算法通过引入传播算子算法线性地获得噪声子空间,避免了特征值分解造成的计算量,然后在保持四阶累积量阵列孔径扩展和抑制高斯噪声的优势下,通过求平均后去除的方法将四阶累积量中冗余的部分去除,降低了算法的复杂度。实验结果表明,所提算法显著减少了算法的计算量,可以实现角度的精确估计,在低信噪比的情况下表现良好,具有较好的实用价值。

智能变电站便携式变压器油色谱分析技术研究

变压器油色谱分析涉及因素较多,导致分析结果与实际情况的误差难以得到有效控制。为此,提出智能变电站便携式变压器油色谱分析技术。分别将关系到变压器性能和安全的气体成分浓度、影响油中气体溶解度的变压器内部温度以及影响油中气体浓度的变压器内部压力作为具体的特征参量,并将变压器油色谱原始数据特征参量累积方差贡献率之和为1作为约束,设置主因子;在分析阶段,考虑到气体浓度与选择的特征变量之间存在线性关系,引入线性回归模型对主因子进行分析,并通过迭代加权最小二乘估计回归系数,利用回归残差对变压器油色谱原始数据中气体含量进行分析。测试结果表明,设计的智能变电站便携式变压器油色谱分析技术可实现对变压器油中不同溶解气体含量的精准分析,误差稳定在3.00μL/L以内。

Identification of multiple inputs single output errors-in-variables system using cumulant

A higher-order cumulant-based weighted least square（HOCWLS） and a higher-order cumulant-based iterative least square（HOCILS） are derived for multiple inputs single output（MISO） errors-in-variables（EIV） systems from noisy input/output data. Whether the noises of the input/output of the system are white or colored, the proposed algorithms can be insensitive to these noises and yield unbiased estimates. To realize adaptive parameter estimates, a higher-order cumulant-based recursive least square（HOCRLS） method is also studied. Convergence analysis of the HOCRLS is conducted by using the stochastic process theory and the stochastic martingale theory. It indicates that the parameter estimation error of HOCRLS consistently converges to zero under a generalized persistent excitation condition. The usefulness of the proposed algorithms is assessed through numerical simulations.

JOINTLY ESTIMATING BOTH RANGE AND DOA OF NEAR FIELD SOURCE

A computationally efficient method for jointly estimating both Directions Of Arrival (DOA) and ranges of near field sources is presented. The proposed algorithm does not need any spectral peak searching and the 2-D parameters are automatically paired. It is suitable for arbitrary additive Gaussian noise environment. Furthermore, its performances are confirmed by computer simulations.

STRONG REPRESENTATIONS OF THE SURVIVAL FUNCTION ESTIMATOR ON INCREASING SETS FOR TRUNCATED AND CENSORED DATA

In this paper, based on random left truncated and right censored data, the authors derive strong representations of the cumulative hazard function estimator and the product-limit estimator of the survival function. which are valid up to a given order statistic of the observations. A precise bound for the errors is obtained which only depends on the index of the last order statistic to be included.

Harmonic Retrieval Embedded in Hybrid Colored Noise: a Novel Pisarenko Method Based on Cross high order Cumulant

Spectral estimation method is an effective method in the case of parameter estimation of sinusoid signal in noises.It always applies cross spectral estimation theory and high order self spectral estimation methods up to now.Yule Walker equation based on cross fourth order cumulant is developed and Pisarenko method is provided in this paper.Simulation results show that the method is effective to retrieve sinusoid signal frequencies from hybrid colored noises and has good performance.