基于遗传算法的最优证券投资组合模型

为了研究能使风险损失率最小、收益最大的最优证券投资组合问题，首先提出了多目标规划模型，并采用模糊优选法将多目标模型单目标化。随后尝试采用遗传算法来对其求解，给出了模型的遗传算法编码规则和算法步骤。最后通过实例论证了模型的合理性及遗传算法的有效性。     

A hybrid ensemble method for improved prediction of slope stability

Accurate prediction of slope stability is a significant issue in geomechanics with many artificial intelligence (AI) techniques being utilised. However, the application of AI has not reached its full potential because of the lack of more robust algorithms. In this paper, we proposed a hybrid ensemble method for the improved prediction of slope stability using classifier ensembles and genetic algorithm. Gaussian process classification, quadratic discriminant analysis, support vector machine, artificial neural networks, adaptive boosted decision trees, and k‐nearest neighbours were chosen to be individual AI techniques, and the weighted majority voting was used as the combination method. Validation method was chosen to be the 10‐fold cross‐validation, and performance measures were selected to be the accuracy, the receiver operating characteristic curve, and the area under the receiver operating characteristic curve (AUC). Grid search and genetic algorithm were used for the hyperparameter tuning and weight tuning respectively. The results show that the proposed hybrid ensemble method has great potential in improving the prediction of slope stability. Compared with individual classifiers, the optimum ensemble classifier achieved the highest AUC value (0.943) and the highest accuracy (0.902) on the testing set, denoting that the predictive performance has been improved. The optimum ensemble classifier with the Youden's cut‐off was recommended for slope stability prediction with respect to the AUC value, the accuracy, the true positive rate, and the true negative rate. This research indicates that the use of the classifier ensembles, rather than the search for the ideal individual classifiers, might help for the slope stability prediction.     

星载合成孔径雷达成像处理

合成孔经雷达(Synthetic Aperture Radar,SAR)是当今微波遥感领域的研究热点,其全天候、全天时、高分辨率以及穿透地表等特点使其具备其他传感器不可比拟的优势,因此得到了极其广泛的应用。成像处理是SAR技术的核心部分。分析了星载SAR点目标回波信号模型和几种常用的星载SAR数字成像处理算法。以距离-多普勒算法为例,阐述了距离压缩和方位压缩的实质,详细讨论了多普勒参数估计、距离徙动校正和斑点噪声的去除等几个关键的问题。采用ERS-1卫星数据做了成像实验,并对SAR成像技术加以总结。     

Intermediate term earthquake prediction in the area of Greece: Application of the algorithm M8

The 3 strongest earthquakes,M7.0, which have occurred since 1973 in the area of Greece were preceded by a specific increase of the earthquake activity in the lower magnitude range. This activation is depicted by algorithm M8. This algorithm of intermediate term earthquake prediction was originally designed for diagnosis by Times of Increased Probability (TIPs) of the strongest earthquake,M8.0 worldwide (Keilis-Borok andKossobokov, 1984). At present the algorithm is retrospectively tested for smaller magnitudes in different seismic regions (Keilis-Borok andKossobokov, 1986, 1988). A TIP refers to a time period of 5 years and an area whose linear size is proportional and several times larger than that of the incipient earthquake source. Altogether the TIPs diagnosed by the algorithm M8 in the area of Greece occupy less than 20% and the Times of Expectation (TEs) about 10% of the total space-time domain considered. Also there is a current TIP for the southeastern Aegean sea and 1988–1992. It may specify the long-term prediction given inWyss andBaer (1981a,b).The results of this study are further evidence favoring applicability of algorithm M8 in diverse seismotectonic environment and magnitude ranges and support indirectly the hypothesis of self-similarity of the earthquake activity. It also implies the possibility of intermediate term prediction of the strongest earthquakes in the area of Greece.     

基于数据挖掘CART算法的区域夏季降水日数分类与预测模型研究

夏季降水日数的准确预测,对于保障农业、运输业、电力等行业的有序进行具有重要现实意义.利用连云港市气象局提供的1951—2012年夏季降水数据对连云港地区的降水日数特征进行分析,难以直观地发现夏季降水日数随时间分布的规律.为进一步探索降水日数的发生规律,结合国家气候中心网站提供的多种气候因子数据,基于CART决策树算法构建了连云港地区夏季降水日数是否偏多与是否偏少的分类与预测模型.该模型可以发现在多种气候因子不同条件下,夏季降水日数是否偏多（偏少）的规律,模型的分类与预测都具有良好的效果.利用52 a的数据样本训练模型,模型的训练准确率为90.38%（86.54%）,再用剩余10 a数据样本检验模型,测试准确率为80%（80%）,并且得到规则集,方便气象业务人员使用以及决策服务人员参考.同时,为降水日数的预测提供了数据挖掘的新思路.     

Relocation optimization of electric cars in one-way car-sharing systems: modeling,exact solving and heuristics algorithms

Car-sharing system with electric cars is a very convenient service for urban transportation: it allows users to pick up a vehicle at a station and rent it during a short time. To manage this kind of system in the best way, it is necessary to solve the critical problem of vehicle stock imbalance across the stations. Several decision levels must be considered to balance the car distribution by taking into account the quality of service and the system operation cost. To this end, a linear programming model is proposed to formalize the problem in a mathematical framework, which allows the computation of optimal vehicle distribution strategies. To make our solution time efficient and usable for solving large problems, a greedy algorithm and a tabu search algorithm are proposed. These two algorithms are applied to the Auto Bleue network in Nice and its surrounding (France) using extensive simulations. Besides, an integrated mapping method is provided within the Geographical Information System QGIS to estimate flows and their locations. Numerical results demonstrate that the tabu search algorithm is able to find near-optimal solutions and good compromises between client satisfaction, number of staff agents and vehicles used, and computing time.     

江西地区地震动非弹性衰减和场地响应特征研究

以2009年以来江西省地震台网记录到的86个M_L2.5以上地震事件的波形资料为研究对象,通过遗传算法获得介质的品质因子和台站场地响应,并在此基础上计算地震的震源谱参数。结果显示,江西地区Q值与频率f的关系式为Q（f）=323.1f^{0.505 9};大部分台站的场地响应在频率域表现为平坦型,整体上与台站基岩性质相符;近震级M_L与地震矩M₀在单对数坐标下呈线性关系,地震矩与拐角频率呈负相关特征,应力降与地震矩之间没有显著相关性;震源半径与应力降存在显著的双对数关系。     

一种由粗到精的光学与SAR遥感图像配准算法

由于光学遥感图像和SAR图像具有明显的非线性强度差异,且SAR图像存在斑点噪声,使得其配准存在较大难度。为此,本文结合基于特征和基于区域图像配准方法的优点,并组合为混合模型,提出一种由粗到精的自动配准算法。以光学遥感图像和SAR图像分别为参考图像和待配准图像,先以基于特征点的SAR-SIFT完成粗配准,再以基于区域的ROEWA-HOG完成精配准。① 采用SAR-SIFT算法进行特征点检测和特征匹配来计算图像的仿射变换模型,以消除参考图像和待配准图像之间明显的旋转、尺度和平移差异,至此完成图像粗配准;② 在此基础上利用分块Harris角点检测在参考图像上获得特征点,并根据特征点确定待配准图像上的同名点搜索区域;③ 计算图像的ROEWA梯度,构造以特征点为中心的模板区域内的HOG特征向量,以SSD作为相似性测度搜索待配准图像上的同名点,完成高精度的图像配准;④ 进行图像配准实验,对配准结果进行目视检查和精度评估。经过多组光学与SAR图像配准实验,验证本文算法能够结合基于特征和基于区域的图像配准方法的优点,较好地抵抗光学与SAR图像之间的非线性强度、旋转、尺度、平移差异和SAR图像的噪声影响,并逐步提高配准精度,最终配准精度达到1个像素左右,实现了光学与SAR图像的高精度自动配准,能够满足光学与SAR图像后续综合应用。     

基于多目标遗传算法和FLUS模型的西北农牧交错带土地利用优化配置

西北农牧交错带生态环境脆弱,区位特殊性和生态重要性使其在我国社会经济发展和生态环境保护方面具有重要战略意义。通过对该区域进行土地利用优化配置,使有限的土地资源支撑起生态环境保护和经济发展的重任是本文的出发点。多目标遗传算法和FLUS模型的应用可以从多方面（数量结构、空间布局、综合效益）完善土地利用优化配置,为土地利用优化配置提供更多的选择方案。本文选用多目标遗传算法和FLUS模型对该区域进行2025年的土地利用变化模拟,通过设置自然发展、生态保护优先、经济发展优先、生态-经济均衡4种情景,探讨了如何在兼顾生态环境保护与社会经济发展的情况下进行土地利用的优化配置。结果表明,基于生态-经济均衡情景下的优化方案,土地利用类型的数量结构和空间布局更为合理,其综合效益优于另外3种情景。该情景在合理限制经济发展速度的前提下,使生态建设获得稳定发展,其经济效益较生态保护优先情景下增长了8.96%,生态效益较经济发展优先情景下增长了0.77%,在生态保护与经济发展2种目标之间达到平衡,为西北农牧交错带的土地利用规划提供了决策辅助。     

基于DEM的一体化山地特征要素提取

山顶点和山脊线等特征地形要素是构成地表地形及其起伏变化的基本框架,对地形在地表的空间分布具有控制作用。基于DEM研究山顶点、山脊线及其空间组合关系,是DEM地表形态特征研究的重要内容,也是衔接从地形特征分析向山峰等地貌学本源语言的途径之一。本文以四川盆地西南缘与青藏高原过渡地带的川西凉山山原为例,基于山峰-山脊线-控制范围一体化构建的算法策略,识别了山峰和山脊线及其等级、主山脊及其范围。结果表明,研究区内有主峰9座,次峰53座,平均高程2540 m;山脊线230条,其中主山脊9条,平均长度60 km;9大山系,近南北走向,平均控制面积1017 km^2。研究用模糊隶属度方法对算法所提取的主峰、主脉进行精度验证,隶属度介于0.98~1.00和0.37~0.57时提取的主峰、主脉基本吻合算法提取的结果。研究采用一体化山地特征要素提取方法,实现了各山地要素间紧密联系、总体结构与区域地貌特征相对吻合的目标;完成了由栅格单元向地理对象的转变;可以应用于协助地貌类型划分,协同区域地理规划等。