Efficient Numerical Optimization Algorithm Based on New Real-Coded Genetic Algorithm, AREX + JGG, and Application to the Inverse Problem in Systems Biology

In Systems Biology, system identification, which infers regulatory network in genetic system and metabolic pathways using experimentally observed time-course data, is one of the hottest issues. The efficient numerical optimization algorithm to estimate more than 100 real-coded parameters should be developed for this purpose. New real-coded genetic algorithm (RCGA), the combination of AREX (adaptive real-coded ensemble crossover) with JGG (just generation gap), have applied to the inference of genetic interactions involving more than 100 parameters related to the interactions with using experimentally observed time-course data. Compared with conventional RCGA, the combination of UNDX (unimodal normal distribution crossover) with MGG (minimal generation gap), new algorithm has shown the superiority with improving early convergence in the first stage of search and suppressing evolutionary stagnation in the last stage of search.

Technique of Error Concealment for Block-Based Image Coding Using Genetic Algorithm

Since real world communication channels are not error free, the coded data transmitted on them may be corrupted, and block based image coding systems are vulnerable to transmission impairment. So the best neighborhood match method using genetic algorithm is used to conceal the error blocks. Experimental results show that the searching space can be greatly reduced by using genetic algorithm compared with exhaustive searching method, and good image quality is achieved. The peak signal noise ratios(PSNRs) of the restored images are increased greatly.

Real-coded genetic algorithm for optimal vibration controlof flexible structure

Presents the study on the optimum location of actuators/sensors for active vibration control in aerospace flexible structures with the performance function first built by maximization of dissipation energy due to control action and a real coded genetic algorithm then proposed to produce a global optimum solution, and proves the feasibility and advantages of this algorithm with the example of a standard test function and a two collocated actuators/sensors cantilever, and comparing the results with those given in the literatures.

Adaptive Real-Coded Genetic Algorithm for Identifying Motor Systems

In this paper, the main objective is to identify the parameters of motors, which includes a brushless direct current (BLDC) motor and an induction motor. The motor systems are dynamically formulated by the mechanical and electrical equations. The real-coded genetic algorithm (RGA) is adopted to identify all parameters of motors, and the standard genetic algorithm (SRGA) and various adaptive genetic algorithm (ARGAs) are compared in the rotational angular speeds and fitness values, which are the inverse of square differences of angular speeds. From numerical simulations and experimental results, it is found that the SRGA and ARGA are feasible, the ARGA can effectively solve the problems with slow convergent speed and premature phenomenon, and is more accurate in identifying system’s parameters than the SRGA. From the comparisons of the ARGAs in identifying parameters of motors, the best ARGA method is obtained and could be applied to any other mechatronic systems.

On grey relation projection model based on projection pursuit

Multidimensional grey relation projection value can be synthesized as one-dimensional projection value by using projection pursuit model. The larger the projection value is,the better the model. Thus,according to the projection value,the best one can be chosen from the model aggregation. Because projection pursuit modeling based on accelerating genetic algorithm can simplify the implementation procedure of the projection pursuit technique and overcome its complex calculation as well as the difficulty in implementing its program,a new method can be obtained for choosing the best grey relation projection model based on the projection pursuit technique.

基于改进实数编码遗传算法的神经网络超参数优化

针对神经网络超参数优化效果差、容易陷入次优解和优化效率低的问题,提出一种基于改进实数编码遗传算法(IRCGA)的深度神经网络超参数优化算法——IRCGA-DNN(IRCGA for Deep Neural Network)。首先,采用实数编码方式表示超参数的取值,使超参数的搜索空间更灵活;然后,引入分层比例选择算子增加解集多样性;最后,分别设计了改进的单点交叉和变异算子,以更全面地探索超参数空间,提高优化算法的效率和质量。基于两个仿真数据集,验证IRCGA-DNN的毁伤效果预测性能和收敛效率。实验结果表明,在两个数据集上,与GA-DNN(Genetic Algorithm for Deep Neural Network)相比,所提算法的收敛迭代次数分别减少了8.7%和13.6%,均方误差(MSE)相差不大;与IGA-DNN(Improved GA-DNN)相比,IRCGA-DNN的收敛迭代次数分别减少了22.2%和13.6%。实验结果表明,所提算法收敛速度和预测性能均更优,能有效处理神经网络超参数优化问题。

基于改进实数遗传算法的桑叶采摘机结构参数优化

针对遗传算法在求解桑叶采摘机结构优化问题时容易陷入局部最优和求解精度低等问题,提出一种改进实数遗传算法。首先是给出一种基于序的组合适应度函数的轮盘赌选择算子,该算子在轮盘赌的基础上,通过一个自适应变化的参数在两种适应度函数中选择一个,再去计算适应度值;然后设计一种基于方向的改进启发式交叉算子,该算子既保留两个父代个体中较优个体对子代个体的影响,又增加种群中最优个体对子代个体的影响,提高交叉产生有潜力子代的可能性。接着将改进算法应用于摇杆式桑叶采摘机的优化参数设计中,通过与其他算法作仿真对比试验验证算法的优越性,获得采摘机最优参数组合:行走结构速度为24 mm/s、拨动结构角速度为1.2 rad/s、采摘结构速度为440 mm/s,并由运行结果可知整机性能与优化前相比提高13%。最后用优化得到的参数组合进行实地试验,结果显示桑叶采摘机性能提升10.9%,误差较小为2.1%。可见,所提改进实数遗传算法是优化采摘机参数的一种有效算法。

Apple leaf disease identification using genetic algorithm and correlation based feature selection method

Apple leaf disease is one of the main factors to constrain the apple production and quality.It takes a long time to detect the diseases by using the traditional diagnostic approach,thus farmers often miss the best time to prevent and treat the diseases.Apple leaf disease recognition based on leaf image is an essential research topic in the field of computer vision,where the key task is to find an effective way to represent the diseased leaf images.In this research,based on image processing techniques and pattern recognition methods,an apple leaf disease recognition method was proposed.A color transformation structure for the input RGB(Red,Green and Blue)image was designed firstly and then RGB model was converted to HSI(Hue,Saturation and Intensity),YUV and gray models.The background was removed based on a specific threshold value,and then the disease spot image was segmented with region growing algorithm(RGA).Thirty-eight classifying features of color,texture and shape were extracted from each spot image.To reduce the dimensionality of the feature space and improve the accuracy of the apple leaf disease identification,the most valuable features were selected by combining genetic algorithm(GA)and correlation based feature selection(CFS).Finally,the diseases were recognized by SVM classifier.In the proposed method,the selected feature subset was globally optimum.The experimental results of more than 90%correct identification rate on the apple diseased leaf image database which contains 90 disease images for there kinds of apple leaf diseases,powdery mildew,mosaic and rust,demonstrate that the proposed method is feasible and effective.

REAL CODED GENETIC ALGORITHM FOR STOCHASTIC HYDROTHERMAL GENERATION SCHEDULING

The intent of this paper is to schedule short-term hydrothermal system probabilistically considering stochastic operating cost curves for thermal power generation units and uncertainties in load demand and reservoir water inflows. Therefore, the stochastic multi-objective hydrothermal generation scheduling problem is formulated with explicit recognition of uncertainties in the system production cost coefficients and system load, which are treated as random variable. Fuzzy methodology has been exploited for solving a decision making problem involving multiplicity of objectives and selection criterion for best compromised solution. A real-coded genetic algorithm with arithmetic-average-bound-blend crossover and wavelet mutation operator is applied to solve short-term variable-head hydrothermal scheduling problem. Initial feasible solution has been obtained by implementing the random heuristic search. The search is performed within the operating generation limits. Equality constraints that satisfy the demand during each time interval are considered by introducing a slack thermal generating unit for each time interval. Whereas the equality constraint which satisfies the consumption of available water to its full extent for the whole scheduling period is considered by introducing slack hydro generating unit for a particular time interval. Operating limit violation by slack hydro and slack thermal generating unit is taken care using exterior penalty method. The effectiveness of the proposed method is demonstrated on two sample systems.

基于模糊认知图的智能汽车驾驶权交互决策建模方法

针对人机共驾中的由自动驾驶接管到驾驶人接管切换的动态问题,提出一种基于模糊认知图(fuzzy cognitive map,FCM)的驾驶权交互决策模型。首先分别分析影响驾驶风险的车辆和人的动态风险因素,并选取车距、加速度、方向盘转向熵、驾驶员眼动信息、心脑电波信息等相关影响指标构建基于FCM的车辆动态风险模型与人的动态风险模型,再结合环境因素,车辆状况以及驾驶员水平构建基于FCM的驾驶员交互决策模型。为降低对专家知识的依赖,运用基于实数编码的遗传算法(real coded genetic algorithm,RCGA)对模型进行优化,进一步提高模型决策的准确性。仿真结果表明,经RCGA优化后模型适应度值达到0.979,可见该模型能够较好地应对动态、复杂的驾驶环境。

结合遗传算法的水库汛限水位动态控制模型研究

针对水库汛限水位动态控制问题,提出一种新的自适应交叉变异遗传算法,解决了水库防洪效益与发电效益之间的矛盾问题,实现了水库水位的调整,缓解了防洪效益与发电效益的冲突。遗传算法使原始汛期水位提升了0.7m,蓄水量提升了2947m^(3),同时增加了发电量233.33×10^(4) kW·h。基于峡山水库实例试验的研究结果表明,结合遗传算法的水库汛限水位动态控制模型,不仅可对水位进行实时性调节,还能提升水库效益,研究结果可应用于各水库防洪系统。

智能仓储多机器人动态任务分配方法

针对智能仓储系统中多机器人任务分配方法进行研究,根据智能仓储中物流任务数量庞大且实时新增的动态特点,创新地提出了一种总体分配并根据当前工况实时插入的动态任务分配方法,将一定时间阈值内的物流任务集合利用综合时间代价、路径代价、空载代价和任务均衡度代价的自适应多层编码遗传算法进行任务整体规划,为智能仓储系统中每个机器人分配需执行的物流任务序列及执行顺序。任务执行过程中,各机器人通过对当前自身剩余任务量成本及插入实时任务后路径成本的判断,在不影响当前任务完成总时间的情况下,对下一时间阈值内产生的实时物流任务是否插入当前执行任务序列展开竞争,实现任务的实时插入,未被实时插入的物流任务则等待下一次总体分配。实验结果表明,该方法能在缩短系统运行总时间和总路程的基础上,极大的降低机器人无任务空载等待的时间,提高系统运行效率。

用APRGA求解二维导体柱电磁逆散射

从电磁散射的积分方程出发 ,利用点匹配法和脉冲基函数求解电磁散射问题 ,以测量的散射场和计算的散射场的偏差程度为目标函数 ,将待优化变量设置为描述导体柱轮廓的形状函数的傅立叶展开式系数 ,Ai0 ,Ai1…AiN/ 2 ,Bi1,Bi2 …BiN/ 2 ,k =1,2…k ,通过参数自适应实数遗传算法 (APRGA)对待优化变量进行优化 ,使目标函数达到最小值来对自由空间中导体柱族进行电磁成像。证实了APRGA比BRGA有更好的收敛性能和成像精度、更强的抗随机噪声干扰能力。

基于量子遗传模糊推理系统的煤与瓦斯突出预测模型

为提高煤与瓦斯突出危险程度预测的准确性,提出一种基于自适应神经模糊推理系统(ANFIS)结合改进实数编码量子遗传算法(IRQGA)的预测模型IRQGA-ANFIS。用基于数据驱动的方法从样本数据直接提取模糊规则,建立煤与瓦斯突出ANFIS预测模型。针对ANFIS预测准确率较低以及模糊推理系统参数量大的特点,采用IRQGA对模糊推理系统进行训练。IRQGA引入秃鹰算法的阿基米德螺线空间搜索机制更新个体;用差分变异策略更新种群最差个体,保持种群多样性;用高斯-柯西变异策略扰动优秀个体使其快速脱离局部极值区,加快算法收敛速度。实验结果表明,IRQGA在高维复杂问题优化中比实验对比算法具有更好的优化性能;IRQGA-ANFIS模型的预测准确率达94.44%;所建模型30次独立运行的MAE均值相较对比模型分别降低了0.0245和0.1184,MSE均值分别降低了0.0162和0.1849,RMSE均值分别降低了0.0172和0.1721。IRQGA-ANFIS具有更高的预测准确率和更好的预测能力。

舰载机模块化弹药调度方案优化设计

舰载机模块化弹药存储和调度是未来发展的主要趋势之一。模块化弹药调度与整弹调度相比,调度对象的数量成倍增加并且多了一个弹药装配环节,使调度工作的难度呈指数级增长。针对模块化弹药调度问题,建立以任务完成时间最小化和各舱室与升降机平均工作时间最小化为优化目标,以各模块调度次序、机器选择和调度起始时间为约束条件的舰载机模块化弹药调度模型,设计递推法计算任务完成时间,并使用改进的遗传算法对模型进行求解,结合模块化弹药特点优化多层编码方式,使染色体更加完整地表达弹药在各个阶段的信息。通过仿真验证,所提的舰载机模块化弹药调度方法生成的调度方案具有可行性。

城市群综合承灾能力评价的RAGA-PP模型

为解决已有模型普遍存在的难以动态评价非线性寻优的现实问题,引入投影寻踪(PP)模型进行城市群综合承灾能力评价,并运用基于实数编码的加速遗传算法(RAGA)优化辅助多维数据空间拓扑结构的投影方向,对长三角城市群(YRDUA)地区进行实证研究。结果表明:RAGA-PP模型与典型的熵权法(EWM)、灰色关联分析法(GRA)评价结果具有高度一致性,且RAGA-PP评价结果更符合实际,表明RAGA-PP模型具有较强的精确性、稳健性和抗干扰性,不仅能够聚焦于优秀个体的取值区间来实现全局搜索和加速评估,也在较大程度上避免传统方法长期存在的权重设置主观性较强、高维数据不易处理的现实问题;另外,各子系统维度的目标投影值平均水平排序为:抗灾维度>防灾维度>救灾维度>恢复维度,表明抗灾维度指标对综合承灾力影响程度最大。

基于改进遗传算法的沥青路面再生工厂布局优化

为了帮助沥青路面再生工厂获得更好的经济与环境效益,提出一种基于改进遗传算法的布局优化方法。首先,确定再生工厂布局的约束条件,并以非物流相关性最大、物料搬运成本最低和碳排放最少作为优化目标建立工厂布局优化模型;其次,基于初始布局方案,采用实数分层编码及排列组合方法对各功能区的初始位置进行交叉互换,并根据约束条件进行筛选,得到合适的初始种群;再次,针对横坐标层与纵坐标层进行算数交叉,变异时坐标层采用多点变异,放置方式层采用单点变异,并引入模拟退火算子;最后,以某再生工厂为例对改进算法进行验证。结果表明:改进后的遗传算法迭代次数较传统遗传算法减少34次,目标函数值较文献中遗传算法减小0.0099,提高了算法的寻优能力;优化后的方案每日物料搬运成本减少14468.85元,碳排放减少30.59 kg,验证了方法的有效性。研究中所提出的优化方法效率较高,可为沥青路面再生工厂的建设提供技术支持。

基于实数编码的加速遗传算法

:针对标准遗传算法 (SGA)在实际应用中存在的早熟收敛、全局优化速度缓慢和解的精度差等缺点 ,提出了基于实数编码的加速遗传算法 (RAGA)。

遗传算法编码方案比较

对具体问题设计合理的编码方案是遗传算法的应用难点之一,目前尚无统一的解决方法。在分析和比较二进制编码、实数编码、矩阵编码、树型编码和量子比特编码的基础上,总结出这些常用的遗传算法编码方案的原理、优缺点、适用范围和应用趋势等规律,并进一步探讨了遗传算法编码方案未来的研究方向。

投影寻踪模型的改进及其在生态农业建设综合评价中的应用

为提高生态农业建设综合评价模型的分辨率,提出了一种有效的和通用的模型——投影寻踪模型(PP)。模型中密度窗宽R是求解局部密度的窗口半径,是由样本数据本身特性确定的局部宽度参数,主要通过试算或经验来确定,缺乏理论根据,该文对模型中密度窗宽R进行了理论改进,推导得出了计算的经验公式,使模型更具有科学性和稳定性。采用基于实码的加速遗传算法寻找最优的投影方向,同时用投影方向信息研究了各因子对生态农业建设综合评价的影响水平,取得了符合客观实际的分类结果,为生态农业合理建设提供了决策依据。