New immune multiobjective optimization algorithm and its application in boiler combustion optimization

In order to meet the requirements of combustion optimization for saving energy and reducing pollutant emission simultaneously,an immune cell subsets based multiobjective optimization algorithm（ICSMOA）is proposed.In the ICSMOA,the subset division operator and the immunological tolerance operation are defined.Preference can be easily addressed by using the subset division operator,and the distribution of the solutions can be guaranteed by the immunological tolerance operation.Using the ICSMOA,a group of Pareto optimal solutions can be obtained.However,by the traditional weighting method（WM）,only one solution can be obtained and it cannot be judged as Pareto optimal or not.In contrast to the solutions obtained by the repeatedly performed WM,the simulation results show that most solutions obtained by the ICSMOA are better than the solutions obtained by the WM.In addition,the Pareto front obtained by the ICSMOA is not as uniform as most classical multiobjective optimization algorithms.More optimal solutions which meet the preference set by the decision-maker can be obtained and they are very useful for industrial application.

Development of Granular Fuzzy Relation Equations Based on a Subset of Data

Developing and optimizing fuzzy relation equations are of great relevance in system modeling,which involves analysis of numerous fuzzy rules.As each rule varies with respect to its level of influence,it is advocated that the performance of a fuzzy relation equation is strongly related to a subset of fuzzy rules obtained by removing those without significant relevance.In this study,we establish a novel framework of developing granular fuzzy relation equations that concerns the determination of an optimal subset of fuzzy rules.The subset of rules is selected by maximizing their performance of the obtained solutions.The originality of this study is conducted in the following ways.Starting with developing granular fuzzy relation equations,an interval-valued fuzzy relation is determined based on the selected subset of fuzzy rules(the subset of rules is transformed to interval-valued fuzzy sets and subsequently the interval-valued fuzzy sets are utilized to form interval-valued fuzzy relations),which can be used to represent the fuzzy relation of the entire rule base with high performance and efficiency.Then,the particle swarm optimization(PSO)is implemented to solve a multi-objective optimization problem,in which not only an optimal subset of rules is selected but also a parameterεfor specifying a level of information granularity is determined.A series of experimental studies are performed to verify the feasibility of this framework and quantify its performance.A visible improvement of particle swarm optimization(about 78.56%of the encoding mechanism of particle swarm optimization,or 90.42%of particle swarm optimization with an exploration operator)is gained over the method conducted without using the particle swarm optimization algorithm.

An Efficient Allocation for Lung Transplantation Using Ant Colony Optimization

A relationship between lung transplant success and many features of recipients’/donors has long been studied.However,modeling a robust model of a potential impact on organ transplant success has proved challenging.In this study,a hybrid feature selection model was developed based on ant colony opti-mization(ACO)and k-nearest neighbor(kNN)classifier to investigate the rela-tionship between the most defining features of recipients/donors and lung transplant success using data from the United Network of Organ Sharing(UNOS).The proposed ACO-kNN approach explores the features space to identify the representative attributes and classify patients’functional status(i.e.,quality of life)after lung transplantation.The efficacy of the proposed model was verified using 3,684 records and 118 input features from the UNOS.The developed approach examined the reliability and validity of the lung allocation process.The results are promising regarding accuracy prediction to be 91.3%and low computational time,along with better decision capabilities,emphasizing the potential for automatic classification of the lung and other organs allocation pro-cesses.In addition,the proposed model recommends a new perspective on how medical experts and clinicians respond to uncertain and challenging lung alloca-tion strategies.Having such ACO-kNN model,a medical professional can sum-marize information through the proposed method and make decisions for the upcoming transplants to allocate the donor organ.

基于VPNRS-RF的飞机液压系统故障诊断模型

针对飞机液压系统故障诊断特征值冗余难以精准获取和准确率不高的问题,提出一种基于变精度邻域粗糙集(Variable Precision Neighborhood Rough Set,VPNRS)和随机森林(Random Forest,RF)相结合的特征选择算法,并以此为基础建立飞机液压系统故障诊断模型。VPNRS-RF算法主要是利用随机森林算法分别对变精度邻域和模糊熵粗糙集约简后的特征进行重要度排序,再次筛选后确定最优特征子集,使用最优特征子集对在线贯序极限学习机(OSELM)分类模型进行训练,从而提高故障信息获取准确率。最后以飞机起落架收放系统为例进行仿真研究,验证了VPNRS-RFOSELM模型的优越性。

复合材料风力机叶片参数化设计及优化

风力机叶片重量过大不仅会影响叶片的结构性能,还会增加运输、维修等成本。为解决叶片质量问题,本文选取经典的1.5 MW复合材料风力机叶片,叶片主梁、腹板、前缘和后缘分区铺设不同的复合材料。由于复合材料的铺设厚度从叶根向叶尖呈现递减趋势,且失效位置也多位于叶根处,故取距离叶根约1/3部分为研究对象来简化问题。为便于后期优化,采用ANSYS APDL参数化构建复合材料风力机叶片模型。考虑到陷入局部最优的情况,选择子集模拟优化方法进行随机优化。设计变量为腹板位置,约束函数为极限载荷下叶片满足位移及Tsai-Wu准则校核,目标为叶片重量最小。通过30组子集模拟优化统计结果可知:当腹板位置约在29.4%、53.3%弦长处时,相较于确定性设计,叶片减重约15.4%。最终结果表明,该优化方法在风力机叶片结构优化方面具有可行性,且优化结果对工程设计具有参考价值。

An Improved Binary Quantum-based Avian Navigation Optimizer Algorithm to Select Effective Feature Subset from Medical Data:A COVID-19 Case Study

Feature Subset Selection(FSS)is an NP-hard problem to remove redundant and irrelevant features particularly from medical data,and it can be effectively addressed by metaheuristic algorithms.However,existing binary versions of metaheuristic algorithms have issues with convergence and lack an effective binarization method,resulting in suboptimal solutions that hinder diagnosis and prediction accuracy.This paper aims to propose an Improved Binary Quantum-based Avian Navigation Optimizer Algorithm(IBQANA)for FSS in medical data preprocessing to address the suboptimal solutions arising from binary versions of metaheuristic algorithms.The proposed IBQANA’s contributions include the Hybrid Binary Operator(HBO)and the Distance-based Binary Search Strategy(DBSS).HBO is designed to convert continuous values into binary solutions,even for values outside the[0,1]range,ensuring accurate binary mapping.On the other hand,DBSS is a two-phase search strategy that enhances the performance of inferior search agents and accelerates convergence.By combining exploration and exploitation phases based on an adaptive probability function,DBSS effectively avoids local optima.The effectiveness of applying HBO is compared with five transfer function families and thresholding on 12 medical datasets,with feature numbers ranging from 8 to 10,509.IBQANA's effectiveness is evaluated regarding the accuracy,fitness,and selected features and compared with seven binary metaheuristic algorithms.Furthermore,IBQANA is utilized to detect COVID-19.The results reveal that the proposed IBQANA outperforms all comparative algorithms on COVID-19 and 11 other medical datasets.The proposed method presents a promising solution to the FSS problem in medical data preprocessing.

Solving the subset sum problem by the quantum Ising model with variational quantum optimization based on conditional values at risk

The subset sum problem is a combinatorial optimization problem,and its complexity belongs to the nondeterministic polynomial time complete(NP-Complete)class.This problem is widely used in encryption,planning or scheduling,and integer partitions.An accurate search algorithm with polynomial time complexity has not been found,which makes it challenging to be solved on classical computers.To effectively solve this problem,we translate it into the quantum Ising model and solve it with a variational quantum optimization method based on conditional values at risk.The proposed model needs only n qubits to encode 2ndimensional search space,which can effectively save the encoding quantum resources.The model inherits the advantages of variational quantum algorithms and can obtain good performance at shallow circuit depths while being robust to noise,and it is convenient to be deployed in the Noisy Intermediate Scale Quantum era.We investigate the effects of the scalability,the variational ansatz type,the variational depth,and noise on the model.Moreover,we also discuss the performance of the model under different conditional values at risk.Through computer simulation,the scale can reach more than nine qubits.By selecting the noise type,we construct simulators with different QVs and study the performance of the model with them.In addition,we deploy the model on a superconducting quantum computer of the Origin Quantum Technology Company and successfully solve the subset sum problem.This model provides a new perspective for solving the subset sum problem.

基于长短期记忆及自适应Kriging子集模拟优化的风电功率预测方法

风电功率的准确预测是目前践行各类监管和运营战略,发展智能电网和先进控制系统等重要技术的前提。提出一种基于长短期记忆及自适应Kriging子集模拟优化的风电功率预测方法。在风电场数据特征提取的基础上,以长短期记忆预测均方根误差为目标,超参数为设计变量,通过基于期望改善的深度耦合自适应Kriging子集模拟优化,进行超参数的高效优化设计,输出最优预测功率。最后,通过案例验证所提方法的预测性能。

融合SBAS-InSAR和WaOA-LSTM的上海浦东国际机场沉降监测与预测

为了监测上海浦东国际机场(SPIA)的沉降现状并提高长短时记忆(LSTM)网络模型预测精度,本文基于短基线集合成孔径雷达干涉测量(SBAS-InSAR)技术和32景Sentinel-1A影像,获取了上海浦东国际机场2020年9月—2023年8月的时间序列沉降信息;构建了基于海象优化算法(WaOA)优化的WaOALSTM沉降预测模型,并将预测结果与合成孔径雷达干涉测量(InSAR)监测值进行对比分析。结果表明,上海浦东国际机场近三年最大沉降速率为-52.21 mm/a,最大累积沉降量达到-159.30 mm,沉降主要集中在填海区的二号、四号和五号跑道,其中五号跑道北部周围护岸区域及沿海堤坝区域最为严重;WaOA-LSTM模型预测值与监测真实值的均方根误差为2.63 mm,平均绝对误差为2.06 mm,相较于传统LSTM模型分别提升了52.87%和53.29%。研究结果为上海浦东国际机场的安全运营提供了参考。

基于灰色关联分析法的物联网数据异常检测方法

物联网数据具有构成复杂、规模庞大、异常形式多样化的特征,导致基于传统异常检测方法得到的结果正确率偏低。文中提出了一种基于灰色关联分析法的物联网数据异常检测方法。该方法利用灰色关联模型计算得到灰色关联系数,对原始物联网数据中的自有变量相关性进行排序,随后采用前向选择法进行变量排序选择,确定反推得到的特征参数误差达到最小值时的变量,并将其作为最优变量子集;在异常检测阶段,用最优变量子集对物联网数据进行异常位置寻优,实现异常检测。测试结果表明,该方法在不同攻击下,异常数据检测结果的F1值未出现明显的波动,对应的F1值为0.84~0.90。

基于蚁群优化的特征选择新方法

利用蚁群优化算法解决特征选择问题,以获得能代表问题空间的较优特征子集,并能降低分类系统的搜索空间。以航空纹理影像的特征选择和分类问题为例,利用主分量变换和蚁群优化算法分别对原始纹理影像特征集合进行特征提取、选择和分类。结果表明,本文方法不仅能够降低图像特征空间维数,减少图像分类的工作量,而且还可以提高分类识别的正确率。

最优子集回归方法在季节气候预测中的应用

利用DEMETER计划多个模式的模拟资料研究1959～2001年多模式集合预报的季节降水在中国区域的表现,并结合最优子集回归（OSR）方法对中国区域的季节降水进行降尺度预报,比较其与多模式集合预报的技巧。研究表明：多个单模式在中国区域对季节降水的模拟性能普遍较差,多元线性回归（MLR）集合的预报技巧不如集合平均（EM）。利用OSR方法进行降尺度预报可以极大改善中国区域季节降水的预报技巧。夏季,降水距平相关系数（ACC）在长江以南、西藏以及内蒙古中部等地区提高很显著,ACC在中国区域的平均达到0.29,明显高于多模式集合平均与多元线性回归集合。冬季,OSR方法可以改善多模式集合在中国北方地区较低的预报技巧。概率Brier技巧评分（BSS）也表明了OSR方法对季节降水预报的改善。需要说明的是,虽然OSR方法在中国区域能明显提高季节降水的预报技巧,但是其选取的预报因子与中国区域季节降水的物理机制问题仍有待于进一步的研究。

基于均生函数-最优子集回归预测模型的青藏高原气温和降水短期预测

以青藏高原78个站点50年的逐年降水和温度数据为基础,使用SOFM人工神经网络模型对高原的降水和温度变化进行了分区,并采用均生函数-最优子集回归(MGF-OSR)预测模型对青藏高原的降水和温度进行了5年情景的预测。预测结果表明:总体而言,今后5年青藏高原的降水年际波动较大,并没有显著的趋势;但青海东南和西藏东部部分地区有明显的减少。青藏高原的总体温度变化增加趋势显著,仅高原东南部明显降温。

基于模糊连接度的图像分割及算法

提出了一种基于模糊连接度图像分割的方法,在模糊连接度分割的基础上增加了最优路径(即与种子点的所有路径中连接度最大的路径)上各点相对于种子点的属性相似度的检验,使之能在待分割对象边界比较模糊的情况下取得理想的分割结果.同时提出了一种基于图像扫描机制的算法,它以种子点为中心,逐个计算邻居点相对于种子点的模糊连接度,该算法充分利用模糊连接度和属性相似度的性质,能简单、快速地找到两点间的最优路径.实验结果表明,该方法快速、有效地提高了图像分割的质量.

最优子集的神经网络预报建模研究

作者尝试用最优子集方法进行神经网络长期预报模型的建模方法研究。结果表明，在很多情况下，由于最优子集方法比逐步回归方法能选取更好的预报因子，因此所构造的神经网络预报模型具有更好的拟合和预报效果，这为神经网络在长期预报的应用研究提供了新的思路和方法。

2002～2004年广东电力负荷的变化特征及预测

利用2002～2004年广东逐日电力负荷资料,采用小波分析、相关分析等方法研究了广东电力负荷的变化特征及与气象因子的关系,并采用最优子集回归方法建立了预测方程。结果表明,广东电力负荷具有非常明显的线性增长趋势,季节变化明显。存在明显的5～7天的准单周振荡,10～20天的准双周振荡及30～60天左右的季节内振荡。它们主要由大气低频振荡及节假日的影响所致。广东电力负荷在周日具有较明显的下降,春节期间呈明显的漏斗状分布,“五一”、“国庆”长假期间最低值主要出现在1～2日,3日以后逐渐恢复到正常状态。与我国其它地区一样,广东电力负荷对温度的变化最敏感,温度是其主要的影响因子,在不同的季节与不同的气象因子还有一定的关系。用最优子集回归方法建立的回归方程并考虑工作日、节假日期间的影响,对夏季峰值、春节谷值、“五一”、“国庆”期间的变化均有较好的拟合与预测。

基于SAR极化分解与Landsat数据的森林生物量遥感估测

【目的】森林生物量是评价森林生态系统结构、功能和生产力的重要指标之一,区域尺度上的森林生物量的准确估测对了解森林现状和科学经营森林具有重要指导意义。本文旨在利用SAR影像结合Landsat5 TM影像对区域尺度上的森林生物量进行定量估测。【方法】首先利用极化分解的方法对极化合成孔径雷达(SAR)数据进行处理获得45个极化分解参数,然后将45个极化分解参数与6个Landsat5 TM波段参数共51个参数作为自变量,森林生物量W作为因变量构建统计回归模型,最后利用最优模型反演研究区的森林生物量。【结果】使用两种方法进行模型构建:(1)逐步回归法,利用逐步回归进行变量筛选,选出2个参数构建模型,模型R2为0.534,拟合精度为67.51%,RMSE为43.21 t/hm^2;(2)最优子集法,用Bootstrap法进行变量筛选,共筛选出9个参数,然后用这9个参数进行最优子集回归,获得511个选模型,然后选择出最优子集模型,并用交叉验证法对模型进行验证,最终选出的最优子集模型包含的参数为TM_band4、Neumann_delta_mod、Neumann_psi、TSVM_psi、TSVM_tau_m3,模型R2为0.768 2,拟合精度为88.32%,拟合RMSE为14.98 t/hm^2,验证精度为86.21%,验证RMSE为19.14 t/hm^2,CP指数为5.249 5,赤池信息量AIC为256.504 5。本文最终使用最优子集法获得的模型进行反演,获得研究区的森林生物量分布图。【结论】结果表明:全极化C波段SAR数据结合Landsat5 TM光学数据构建遥感信息模型可以准确反演森林生物量。

基于粒子群优化算法和相关性分析的特征子集选择

特征选择是模式识别与数据挖掘等领域的重要问题之一。针对此问题,提出了基于离散粒子群和相关性分析的特征子集选择算法,算法中采用过滤模式的特征选择方法,通过分析网络入侵数据中所有特征之间的相关性,利用离散粒子群算法在所有特征的空间里优化搜索,自动选择有效的特征子集以降低数据维度。1999KDD Cup Data中IDS数据集的实验结果表明了提出算法的有效性。

基于微粒群算法和支持向量机的特征子集选择方法

在模式分类系统中,大量无关或冗余的特征往往会降低分类器的性能,因此需要特征选择.本文提出了基于离散微粒群(BPSO)和支持向量机(SVM)封装模式的特征子集选择方法,首先随机产生若干种群(特征子集),然后用BPSO算法对特征进行优化,并用SVM的10阶交叉验证结果指导算法的搜索,最后选出最佳适应度的子集对SVM进行训练.两个UC I机器数据集(户外图像和电离层)的实验结果表明了提出算法的有效性.

基于CFS预报产品的广东省季节降水统计降尺度预测

美国国家环境预报中心(NCEP)开发的气候预报系统(CFS)预报数据资料有1981—2008年共28年历史预报数据,有实时的预报产品(含有未来9个月的预报值)。与NCEP资料相比,CFS能较好模拟季风环流的季节变化,能超前几个月模拟出ENSO发展和衰减时期的海温异常发展,可以用于广东季节降水预测。采用CFS预报产品开发基于最优子集回归和多元均生函数的广东季节降水的两种统计降尺度预报方法。经过分析检验,分别选取海平面气压场、风场和位势高度场显著影响区域作为同期预报因子,从多年(2001—2008年)的历史回报检验来看,虽然两种预测模型对于个别季节存在年内预报效果不稳定性,但综合而言,大部分季节降水的气候预测评分总体平均在64分以上。2009/2010年的实时预报检验表明,两种预测模型均达到较好的预测水平,降水预测结果与实况较接近。与基于NCEP观测资料的传统统计方法比较,CFS预报产品具有实时性、更新快等优点。基于CFS预报产品的降尺度统计方法可以超前三个季预报广东降水,丰富了传统统计方法,但预报的稳定性还需进一步改进。