邻域等价关系诱导的改进ID3决策树算法

经典ID3决策树算法适用于离散型数据分类,但用于连续处理时需要数据离散化容易导致信息损失。提出邻域等价关系从而诱导邻域ID3(NID3)决策树算法,NID3算法改进了ID3决策树算法,能够直接实施连续预测并获取更好的分类效果。在邻域决策系统中,挖掘一种邻域等价关系;基于邻域等价粒化,构建邻域信息度量;基于邻域信息增益,设计NID3决策树算法。实例分析与数据实验均表明,NID3算法具有连续数据分类预测有效性,在分类机器学习中优于ID3算法。     

A comparative study between dynamic adapted PSO and VNS for the vehicle routing problem with dynamic requests

Combinatorial optimization problems are usually modeled in a static fashion. In this kind of problems, all data are known in advance, i.e. before the optimization process has started. However, in practice, many problems are dynamic, and change while the optimization is in progress. For example, in the dynamic vehicle routing problem (DVRP), new orders arrive when the working day plan is in progress. In this case, routes must be reconfigured dynamically while executing the current simulation. The DVRP is an extension of a conventional routing problem, its main interest being the connection to many real word applications (repair services, courier mail services, dial-a-ride services, etc.). In this article, a DVRP is examined, and solving methods based on particle swarm optimization and variable neighborhood search paradigms are proposed. The performance of both approaches is evaluated using a new set of benchmarks that we introduce here as well as existing benchmarks in the literature. Finally, we measure the behavior of both methods in terms of dynamic adaptation.     

自适应变步长最大风能捕获算法

风能具有随机性、不稳定性的特点,为了提高风力发电系统中风能的利用效率,在比较各种最大风能捕获算法的基础上,分析了爬山搜索法和叶尖速比法的不足,提出了自适应变步长搜索算法来捕获最大风能.通过改进爬山搜索法的变步长策略,明显加快了搜索速度,通过引入初始估计叶尖速比值,大大缩小了搜索范围.该算法不需要实时检测准确风速,不依赖风力机最佳功率曲线,有效地降低了成本,提高风力发电的效率.文中重点分析了算法的自适应性和变步长策略,仿真结果表明,该算法能够使风力机更快速到达最大功率点,动态响应快,收敛性好.     

压力机八杆内滑块机构的优化设计

提出用拉深区速度波动量、拉深速度、拉深深度、拉深角为评价压力机八杆内滑块机构性能优劣的指标。根据机构优化设计理论，用步长搜索法对其进行了优化设计，优化出多组以上指标均好于原机构的方案，并且最大压力角比原机构减小很多，其运动学性能超过原机构水平。     

超声波压力检测中回波搜索算法

通过对超声波压力测量中回波信号特征的分析，提出了回波自动搜索算法。该方法把快速傅立叶变换方法和小波多分辨率信号分解相结合，精确地检测出回波的包络信号，从而准确地搜索到回波，为后续的压力信号处理及提高压力测量的精度奠定了基础。     

一种限制搜索区域的多比例尺最优路径规划算法*

针对现有大区域范围路径规划算法存在的一些问题,提出一种限制搜索区域的多比例尺最优路径规划算法。该算法在进行路径规划时,一方面根据路网的多比例尺信息对路网进行分级,另一方面对搜索区域进行合理限制。测试实验表明此算法可以提高路径规划的效率。     

基于邻域彩色变化矢量场的图像边缘检测技术研究*

首先进行了边缘检测系统结构设计,建立了图像邻域彩色变化矢量场的数理模型,提出了用图像邻域彩色变化方向锐度描述图像边缘,进而应用模糊聚类自适应检测边缘.实验表明:与基于梯度的边缘检测技术相比,该方法在噪声抑制以及边缘准确定位上均取得了好的效果,是一种应用广泛的优秀边缘检测算法.     

Olfactory Responses of Banana Weevil Predators to Volatiles from Banana Pseudostem Tissue and Synthetic Pheromone

As a response to attack by herbivores, plants can emit a variety of volatile substances that attract natural enemies of these insect pests. Predators of the banana weevil, Cosmopolites sordidus (Germar) (Coleoptera: Curculionidae) such as Dactylosternum abdominale (Coleoptera: Hydrophilidae) and Pheidole megacephala (Hymenoptera: Formicidae), are normally found in association with weevil-infested rotten pseudostems and harvested stumps. We investigated whether these predators are attracted to such environments in response to volatiles produced by the host plant, by the weevil, or by the weevil–plant complex. We evaluated predator responses towards volatiles from banana pseudostem tissue (synomones) and the synthetic banana weevil aggregation pheromone Cosmolure+ in a two-choice olfactometer. The beetle D. abdominale was attracted to fermenting banana pseudostem tissue and Cosmolure+, whereas the ant P. megacephala was attracted only to fermented pseudostem tissue. Both predators were attracted to banana pseudostem tissue that had been damaged by weevil larvae irrespective of weevil presence. Adding pheromone did not enhance predator response to volatiles from pseudostem tissue fed on by weevils. The numbers of both predators recovered with pseudostem traps in the field from banana mats with a pheromone trap were similar to those in pseudostem traps at different distance ranges from the pheromone. Our study shows that the generalist predators D. abdominale and P. megacephala use volatiles from fermented banana pseudostem tissue as the major chemical cue when searching for prey.     

基于区域生长的多源遥感图像配准

多源遥感图像由于成像设备、所用光谱、拍摄时间等因素的不同,给配准带来极大的困难.尽管已经提出了多种匹配方法,但已有方法一般只能适用于特定的应用环境,开发出更加稳定和适用的配准算法仍然是一个极具挑战性的研究课题.提出一种基于区域生长的配准方法,首先,提取改进后的尺度不变特征,通过全局匹配确定种子点和种子区域并完成变换模型的初始化;然后,运用迭代区域生长和双向匹配策略,得到整个图像的可靠匹配点,从而实现多源遥感图像之间的配准.实验表明,该方法提取的匹配点的数量和正确率均远高于已有方法,能够对存在严重灰度差异的多源遥感图像实现高精度的配准,充分证明了该方法的鲁棒性和适用性.     

动态格点搜索的改进算法用于团簇结构快速优化

结合高效的动态格点搜索(DLS)算法与扰动操作(Perturbation Operation)提出一种新的改进方法(DLS-PO),用于确定团簇的最低能量结构。针对一个特定构型,DLS算法总能给出其对应搜索空间的最规则结构。然而,一次失败的DLS优化将消耗大量的运算资源。为此,采取原子移动和结构旋转的扰动操作成功地改变了构型,再结合后续的DLS操作,提高了优化效率。将该算法用于原子数高达309的Lennard-Jones团簇及100原子NP-B函数铝团簇的结构优化。优化结果显示相比于DLS算法,DLS-PO算法更为高效。