城市GPS控制网的分级布设

为了满足城市建设和发展的需要，提出了应用全球定位系统（ＧＰＳ）技术分级布设城市控制网的方法和相应的数据处理手段，通过对实例的计算，充分说明了在大中城市中ＧＰＳ控制网分级布设的优越性和必要性洞时，还探讨了分级布网对点位精度的影响，通过对不同布网方案的比较、分析，得出分级布网不但能保证全网的精度均匀、一致性，而且能明显地改善点位精度，特别是当首级网布设均匀、合理时，效果尤其显著．因此，建议在今后的大中城市测量中，ＧＰＳ控制网应该分级布设，提出的方法适用于各种大型工程建设．

一种基于GPS/INS全组合的航向自适应滤波算法

首先基于陆地导航讨论了GPS/INS全组合系统,分别在载体动态和静态两种情况下对比分析了全组合和紧组合的姿态矫正效果。实验结果表明全组合模式的航向角精度较紧组合有明显提升,且当载体由动态转为静态时,全组合模式能够克服紧组合航向角缓慢发散的现象。其次针对载体大角度转向时组合系统动力学模型异常增大的问题,提出了一种对航向角进行自适应修正的全组合滤波算法,仿真实验结果表明:该方法能够一定程度上削弱载体大角度转向时动力学模型异常的影响,航向精度有一定提高。

GPS及AVHRR资料在浅海潮间带测量中的应用

通过利用 GPS及渔探器实测 ,并进行潮位订正 ,获得南通浅海海域大量测点的高程资料 ;通过对多时相各通道 NOAA卫星照片进行筛选 ,挑选能反映浅海地貌的通道资料 ,从中读取各测点相对应的灰度值 ,在此基础上利用分级线性回归 ,建立不同高程范围内的高程、灰度线性回归方程 ,确定不同高程的灰度阈值 ,从而测量出南通市浅海海域不同高程以上的潮间带面积、分布。

基于正交局部保持映射和成本优化的多变量时间序列早期分类模型

时间序列早期分类(ETSC)有两个矛盾的目标:早期性和准确率。分类早期性的实现,总是以牺牲它的准确率为代价。现有基于优化的多变量时间序列(MTS)早期分类方法,虽然在成本函数中考虑了错误分类成本和延迟决策成本,却忽视了MTS数据集样本之间的局部结构对分类性能的影响。针对这个问题,提出一种基于正交局部保持映射(OLPP)和成本优化的MTS早期分类模型(OLPPMOAE)。首先,使用OLPP将MTS样本前缀映射到低维空间,保持原数据集的局部结构;其次,在低维空间训练一组高斯过程(GP)分类器,生成训练集每个时刻的类概率;最后,使用粒子群优化(PSO)算法从这些类概率中学习停止规则中的最优参数。在6个MTS数据集上的实验结果表明,在早期性基本持平的情况下,OLPPMOAE的准确率显著高于基于成本的R1_C_(lr)(stopping Rule and Cost function with regularization term l_(1)and l_(2))模型,平均准确率能够提升11.33%~15.35%,调和均值(HM)能够提升4.71%~9.01%。因此,所提模型能够以较高的准确率尽早地分类MTS。

基于高斯过程分类的串联直流电弧故障检测

随着可再生能源和电力电子技术的飞速发展,直流系统在各个领域都得到了广泛应用。但由绝缘损坏、接头松动等原因引起的直流电弧故障是威胁直流系统正常运行的主要因素。为了解决直流电弧故障由于不存在过零点和平肩现象而难以检测的问题,文中将高斯过程模型引入电弧故障研究,进行不同负载下串联直流电弧故障试验。通过提取电流差均值、谐波能量和组成特征向量,利用高斯过程分类进行电弧故障训练、预测分类。试验结果表明,该检测方法能够准确识别电弧故障。

道路线形特征自动分类方法

为了可持续性地更新道路信息数据库,利用车载全球卫星定位系统(GPS)产生的大量路径跟踪轨迹信息,快速捕捉道路信息变化,提出一个基于LVQ-Boosting的道路线形识别模型。该模型以学习向量量化(LVQ)为基础分类器,采用改进的Boosting算法进行网络集成,进一步提高LVQ的泛化能力,从而获得一个使用弱分类算法却具有强分类性能的分类器。该模型以GPS定位点坐标、速度和道路水平曲率为基本识别特征和输入变量,以道路线形特征为输出变量,实现自动识别道路线形特征,快速分组道路特征类型的目的。实验结果表明,该方法具有较高的道路线形的识别效率和精度。

GPS/BDS/INS tightly coupled integration accuracy improvement using an improved adaptive interacting multiple model with classified measurement update

An Extended Kalman Filter（EKF） is commonly used to fuse raw Global Navigation Satellite System（GNSS） measurements and Inertial Navigation System（INS） derived measurements. However, the Conventional EKF（CEKF） suffers the problem for which the uncertainty of the statistical properties to dynamic and measurement models will degrade the performance.In this research, an Adaptive Interacting Multiple Model（AIMM） filter is developed to enhance performance. The soft-switching property of Interacting Multiple Model（IMM） algorithm allows the adaptation between two levels of process noise, namely lower and upper bounds of the process noise. In particular, the Sage adaptive filtering is applied to adapt the measurement covariance on line. In addition, a classified measurement update strategy is utilized, which updates the pseudorange and Doppler observations sequentially. A field experiment was conducted to validate the proposed algorithm, the pseudorange and Doppler observations from Global Positioning System（GPS） and Bei Dou Navigation Satellite System（BDS） were post-processed in differential mode.The results indicate that decimeter-level positioning accuracy is achievable with AIMM for GPS/INS and GPS/BDS/INS configurations, and the position accuracy is improved by 35.8%, 34.3% and 33.9% for north, east and height components, respectively, compared to the CEKF counterpartfor GPS/BDS/INS. Degraded performance for BDS/INS is obtained due to the lower precision of BDS pseudorange observations.

Combining Committee-Based Semi-Supervised Learning and Active Learning

Many data mining applications have a large amount of data but labeling data is usually difficult, expensive, or time consuming, as it requires human experts for annotation. Semi-supervised learning addresses this problem by using unlabeled data together with labeled data in the training process. Co-Training is a popular semi-supervised learning algorithm that has the assumptions that each example is represented by multiple sets of features （views） and these views are sufficient for learning and independent given the class. However, these assumptions axe strong and are not satisfied in many real-world domains. In this paper, a single-view variant of Co-Training, called Co-Training by Committee （CoBC） is proposed, in which an ensemble of diverse classifiers is used instead of redundant and independent views. We introduce a new labeling confidence measure for unlabeled examples based on estimating the local accuracy of the committee members on its neighborhood. Then we introduce two new learning algorithms, QBC-then-CoBC and QBC-with-CoBC, which combine the merits of committee-based semi-supervised learning and active learning. The random subspace method is applied on both C4.5 decision trees and 1-nearest neighbor classifiers to construct the diverse ensembles used for semi-supervised learning and active learning. Experiments show that these two combinations can outperform other non committee-based ones.

Semi-Supervised Learning in Large Scale Text Categorization

The rapid development of the Internet brings a variety of original information including text information, audio information, etc. However, it is difficult to find the most useful knowledge rapidly and accurately because of its huge number. Automatic text classification technology based on machine learning can classify a large number of natural language documents into the corresponding subject categories according to its correct semantics. It is helpful to grasp the text information directly. By learning from a set of hand-labeled documents,we obtain the traditional supervised classifier for text categorization(TC). However, labeling all data by human is labor intensive and time consuming. To solve this problem, some scholars proposed a semi-supervised learning method to train classifier, but it is unfeasible for various kinds and great number of Web data since it still needs a part of hand-labeled data. In 2012, Li et al. invented a fully automatic categorization approach for text(FACT)based on supervised learning, where no manual labeling efforts are required. But automatically labeling all data can bring noise into experiment and cause the fact that the result cannot meet the accuracy requirement. We put forward a new idea that part of data with high accuracy can be automatically tagged based on the semantic of category name, then a semi-supervised way is taken to train classifier with both labeled and unlabeled data,and ultimately a precise classification of massive text data can be achieved. The empirical experiments show that the method outperforms the supervised support vector machine(SVM) in terms of both F1 performance and classification accuracy in most cases. It proves the effectiveness of the semi-supervised algorithm in automatic TC.

一种应用稀疏高斯过程回归模型的半监督分类算法

高斯过程（GPS）是一种良好的贝叶斯分类方法和回归过程，也可应用于半监督聚类方面，就此提出了一个新的算法：使用稀疏高斯过程回归模型来解决半监督二元分类问题，它是基于支持向量回归（SVR）和最大空间聚类（MMC）的半监督分类方法，此算法简单且易于实现，不同于SVR算法的稀疏解决方案。另外，超参数的估计也不再使用复杂的交叉验证技术，利用稀疏高斯回归模型有助于提高算法的可扩展性：使用合成的和真实世界的数据集初步验证了该算法的有效性。

利用预测残差和选权滤波构造的分类因子在GPS/INS组合导航中的应用

针对组合导航观测个数少、采用单因子自适应滤波会损失间接可测参数精度的问题,利用预测残差和选权滤波思想构造了分类自适应因子。实测算例计算结果表明,该算法不仅能够很好地控制状态扰动异常影响,而且还能避免损失间接可测参数的精度,进一步提高了导航精度。

利用DUFCOM和DC算法的GPS单历元双差整周模糊度快速确定算法

为解决DUFCOM方法单历元解算GPS双差整周模糊度因观测卫星数多导致解算效率低而影响GPS高频数据实时动态解算这一问题,同时考虑到DC算法解算效率高的优点,对观测卫星进行筛选分级处理,提出了一种快速确定算法。算例表明,该算法可避免在应用DUFCOM方法中二级卫星对一级卫星双差整周模糊度解算效率的影响,使得GPS单历元确定双差整周模糊度的效率显著提高,达到了GPS高频数据实时动态解算的目的。