Artificial Fish Swarm Optimization with Deep Learning Enabled Opinion Mining Approach

Sentiment analysis or opinion mining(OM)concepts become familiar due to advances in networking technologies and social media.Recently,massive amount of text has been generated over Internet daily which makes the pattern recognition and decision making process difficult.Since OM find useful in business sectors to improve the quality of the product as well as services,machine learning(ML)and deep learning(DL)models can be considered into account.Besides,the hyperparameters involved in the DL models necessitate proper adjustment process to boost the classification process.Therefore,in this paper,a new Artificial Fish Swarm Optimization with Bidirectional Long Short Term Memory(AFSO-BLSTM)model has been developed for OM process.The major intention of the AFSO-BLSTM model is to effectively mine the opinions present in the textual data.In addition,the AFSO-BLSTM model undergoes pre-processing and TF-IFD based feature extraction process.Besides,BLSTM model is employed for the effectual detection and classification of opinions.Finally,the AFSO algorithm is utilized for effective hyperparameter adjustment process of the BLSTM model,shows the novelty of the work.A complete simulation study of the AFSO-BLSTM model is validated using benchmark dataset and the obtained experimental values revealed the high potential of the AFSO-BLSTM model on mining opinions.

Unmanned wave glider heading model identification and control by artificial fish swarm algorithm

We introduce the artificial fish swarm algorithm for heading motion model identification and control parameter optimization problems for the“Ocean Rambler”unmanned wave glider(UWG).First,under certain assumptions,the rigid-flexible multi-body system of the UWG was simplified as a rigid system composed of“thruster+float body”,based on which a planar motion model of the UWG was established.Second,we obtained the model parameters using an empirical method combined with parameter identification,which means that some parameters were estimated by the empirical method.In view of the specificity and importance of the heading control,heading model parameters were identified through the artificial fish swarm algorithm based on tank test data,so that we could take full advantage of the limited trial data to factually describe the dynamic characteristics of the system.Based on the established heading motion model,parameters of the heading S-surface controller were optimized using the artificial fish swarm algorithm.Heading motion comparison and maritime control experiments of the“Ocean Rambler”UWG were completed.Tank test results show high precision of heading motion prediction including heading angle and yawing angular velocity.The UWG shows good control performance in tank tests and sea trials.The efficiency of the proposed method is verified.

Development of an Artificial Fish Swarm Algorithm Based on aWireless Sensor Networks in a Hydrodynamic Background

The main objective of the present study is the development of a new algorithm that can adapt to complex and changeable environments.An artificial fish swarm algorithm is developed which relies on a wireless sensor network(WSN)in a hydrodynamic background.The nodes of this algorithm are viscous fluids and artificial fish,while related‘events’are directly connected to the food available in the related virtual environment.The results show that the total processing time of the data by the source node is 6.661 ms,of which the processing time of crosstalk data is 3.789 ms,accounting for 56.89%.The total processing time of the data by the relay node is 15.492 ms,of which the system scheduling and the Carrier Sense Multiple Access(CSMA)rollback time of the forwarding is 8.922 ms,accounting for 57.59%.The total time for the data processing of the receiving node is 11.835 ms,of which the processing time of crosstalk data is 3.791 ms,accounting for 32.02%;the serial data processing time is 4.542 ms,accounting for 38.36%.Crosstalk packets occupy a certain amount of system overhead in the internal communication of nodes,which is one of the causes of node-level congestion.We show that optimizing the crosstalk phenomenon can alleviate the internal congestion of nodes to some extent.

基于AFSA-SVM动态光谱的血液识别研究

血液是一种受管制的特殊遗传生物资源。针对传统血液光谱检测中易氧化变质的问题,采用基于仿生血管的动态共聚焦拉曼荧光光谱,开展了猪、马、鸽、鸡、鸭、鹅等六种家禽家畜的血液物种鉴别研究。原始光谱的预处理过程包括去基线、平滑和归一化等。采用线性判别分析对光谱数据进行降维处理,继而用支持向量机建立识别模型,选用高斯核函数,通过人工鱼群算法优化支持向量机的参数C和γ,使其分类准确率最高,最优的C和γ分别为0.2和0.134。人工鱼群-支持向量机模型识别准确率达到97.2%,基于仿生血管的动态共聚焦拉曼荧光光谱可以满足血液安全高效的检测要求,用人工鱼群算法优化支持向量机参数的算法模型表现出较好的分类效果。

基于改进AFSA算法的智慧农业监测网络研究

智慧化农业监测实际上是将无线传感器网络应用于农业监测场景中实时采集农田、气象、养殖等方面的数据。多个微小型嵌入式系统相互协作共同构成无线传感器网络,可实时监测、感知、收集和处理环境信息,并以无线通信方式进行信息交互。无线传感器网络覆盖是无线传感器网络监测的基础,直接影响网络感知质量。建立了面向农业场景的无线传感器网络覆盖问题模型,提出了一种基于改进人工鱼群算法的覆盖优化策略,提高了网络覆盖率和算法收敛性,得到最优网络传感器节点覆盖。

Approach to WTA in air combat using IAFSA-IHS algorithm

In this paper, a static weapon target assignment（WTA）problem is studied. As a critical problem in cooperative air combat,outcome of WTA directly influences the battle. Along with the cost of weapons rising rapidly, it is indispensable to design a target assignment model that can ensure minimizing targets survivability and weapons consumption simultaneously. Afterwards an algorithm named as improved artificial fish swarm algorithm-improved harmony search algorithm（IAFSA-IHS） is proposed to solve the problem. The effect of the proposed algorithm is demonstrated in numerical simulations, and results show that it performs positively in searching the optimal solution and solving the WTA problem.

基于M-AFSA的MPRM逻辑电路面积优化

现有基于传统智能优化算法的MPRM电路面积优化算法存在效果差的问题。由于MPRM电路面积优化属于组合优化问题,先提出一种多策略协同进化人工鱼群算法(MAFSA),该算法引入基于反向学习的种群初始化策略,以提高种群多样性及初始种群解的质量;引入觅食与追尾交互性策略,以加强人工鱼个体之间的信息交流、提高所提算法的收敛速度;引入自适应扰动策略,以增加人工鱼个体位置变异的随机性、避免所提算法陷入局部最优。此外,提出一种MPRM逻辑电路面积优化方法,利用所提算法来搜索电路面积最小的最佳极性。基于北卡罗莱纳州微电子中心(MCNC)Benchmark电路的实验结果表明:与遗传算法相比,所提算法优化电路平均面积百分比最高为57.24%,平均为39.57%;与人工鱼群算法相比,所提算法优化电路平均面积百分比最高为33.53%,平均为14.54%;与改进的人工鱼群算法相比,所提算法优化电路平均面积百分比最高为30.25%,平均为13.86%。

基于SAFSA-SVM的边坡稳定性预测模型

了解边坡的稳定状况是保证水利工程长期安全稳定运行的关键之一,对边坡稳定情况进行预测是当前研究的热点。目前边坡稳定性预测研究中普遍存在样本数据较少导致预测精度难以满足实际需求的问题,为此,将支持向量机模型引入边坡稳定性预测的研究,并利用改进人工鱼群算法对模型的参数进行优化,以实际工程的数据对模型进行测试,并将该模型与单一SVM模型的性能进行对比。结果表明,优化后的模型能够有效地改善预测精度。研究成果可以为水利工程的安全施工和管理提供参考。

基于AFSA-SVM的手势识别方法

为了提高表面肌电信号(sEMG)对手势识别的准确率,提出了一种人工鱼群算法优化支持向量机分类器(AFSA-SVM)方法。采集了10位受试者手势动作的sEMG信号,对sEMG信号进行预处理后,进行时域信号积分肌电值(iEMG)和均方根值(RMS)的特征提取,使用特征进行分类。实验结果表明,在特征iEMG上AFSA-SVM与SVM平均分类准确率分别为88.21%与84.29%,AFSA-SVM提高了3.92%;在特征RMS上AFSA-SVM与SVM平均分类准确率分别为86.85与83.69%,AFSA-SVM提高了3.16%。因此,AFSA-SVM相对SVM分类器的识别准确率更高,并且时域特征iEMG相对RMS更具识别度。

考虑系统稳定边界的同步调相机励磁与升压变参数联合优化

现有提升调相机动态无功特性的参数优化方法侧重于电磁参数的优化,这给生产企业带来较高的工艺要求和较大的成本压力。针对该问题提出考虑系统稳定约束的调相机励磁系统及升压变参数联合优化方法,分析其对电磁参数优化的可替代性。首先,推导了基于Park模型下调相机的无功频域特性,与6阶实用模型下的无功频域特性对比,基于调相机的Park模型可提升调相机动态无功特性的分析精度。然后,提出根据调相机并网系统的稳定边界确定参数的优化区间,采用频域灵敏度方法确定重点参数,并基于人工鱼群算法进行参数优化。最后,通过仿真结果表明,励磁系统与升压变参数的联合优化,可获得与仅优化电磁参数时相近的调相机动态无功性能,验证了电磁参数优化的可替代性,从而降低调相机的制造成本,扩大同步调相机的应用场合和范围。

基于改进小波神经网络的实时系统任务流量预测方法

针对当前航空装备实时系统对非周期实时任务无法预知难以实现可靠调度的困难,开展对航空装备实时系统非周期任务流量预测方法的研究。以小波神经网络为基础结合航空装备实时系统的特性建立任务流量预测模型,并提出利用人工鱼群算法对小波预测模型关键参数进行优化,避免陷入局部最优解,最终构建一种人工鱼群算法改进的小波神经网络任务流量预测系统。利用提出的预测模型开展实时任务流量预测对比仿真实验,实验结果表明,建立的基于改进小波神经网络的实时系统任务流量预测系统对非周期实时任务具有较高的预测精度,预测效果优于原始小波神经网络模型及T-S模糊神经网络模型。

基于人工鱼群-遗传算法的多品种小批量零件数控加工工艺优化研究

基于多品种小批量零件加工成本高的问题,基于人工鱼群-遗传算法(AFSA-GA)构建了数控机床能耗模型,以实现零件加工能耗下降。首先,将数控机床功率划分为各工序功率模型,基于功率模型与工作时间关系得出机床运转能耗模型,结合产品表面粗糙度模型,对各工序能耗模型及整体粗糙度进行归一化处理,形成整体能耗模型;其次,以能耗及粗糙度为目标函数,建立AFSA-GA算法,通过对各工序能耗求解得出最适当的机床功率及其所对应的能耗和表面粗糙度;最后,针对所获得的最优功率,进行优化结果的验证,为五轴机床的实际加工提供解决方案。

基于人工鱼群算法的篮球跳投轨迹实时跟踪

篮球运动轨迹跟踪方法由于轨迹特征提取效果差,导致跟踪误差高,提出一种基于人工鱼群算法的篮球跳投轨迹实时跟踪方法。提取三维坐标系下图像中篮球边缘轮廓信息,通过滤波函数消除篮球跳投图像噪声,基于人工鱼群算法提取图像中篮球跳投轨迹特征,寻找篮球运动轨迹的最优解集,改进篮球实时跟踪匹配路径,形成轨迹跟踪函数。实验结果可知,该方法的平均轨迹跟踪误差为18.28mm,与常规方法相比降低了6.22mm以上。因此,该跟踪方法的篮球轨迹跟踪精度更高,并且实时跟踪轨迹与真实轨迹更吻合。

Intelligent approach of score-based artificial fish swarm algorithm(SAFSA)for Parkinson’s disease diagnosis

Purpose-Conventional diagnostic techniques,on the other hand,may be prone to subjectivity since they depend on assessment of motions that are often subtle to individual eyes and hence hard to classify,potentially resulting in misdiagnosis.Meanwhile,early nonmotor signs of Parkinson’s disease(PD)can be mild and may be due to variety of other conditions.As a result,these signs are usually ignored,making early PD diagnosis difficult.Machine learning approaches for PD classification and healthy controls or individuals with similar medical symptoms have been introduced to solve these problems and to enhance the diagnostic and assessment processes of PD(like,movement disorders or other Parkinsonian syndromes).Design/methodology/approach-Medical observations and evaluation of medical symptoms,including characterization of a wide range of motor indications,are commonly used to diagnose PD.The quantity of the data being processed has grown in the last five years;feature selection has become a prerequisite before any classification.This study introduces a feature selection method based on the score-based artificial fish swarm algorithm(SAFSA)to overcome this issue.Findings-This study adds to the accuracy of PD identification by reducing the amount of chosen vocal features while to use the most recent and largest publicly accessible database.Feature subset selection in PD detection techniques starts by eliminating features that are not relevant or redundant.According to a few objective functions,features subset chosen should provide the best performance.Research limitations/implications-In many situations,this is an Nondeterministic Polynomial Time(NPHard)issue.This method enhances the PD detection rate by selecting the most essential features from the database.To begin,the data set’s dimensionality is reduced using Singular Value Decomposition dimensionality technique.Next,Biogeography-Based Optimization(BBO)for feature selection;the weight value is a vital parameter for finding the best features in PD classification.Originality/value-PD classification is done by using ensemble learning classification approaches such as hybrid classifier of fuzzy K-nearest neighbor,kernel support vector machines,fuzzy convolutional neural network and random forest.The suggested classifiers are trained using data from UCIMLrepository,and their results are verified using leave-one-person-out cross validation.The measures employed to assess the classifier efficiency include accuracy,F-measure,Matthews correlation coefficient.

超网络体系作战下的打击目标优选模型

针对当前进行海上作战体系目标优选分析与决策时对打击代价考虑不足的问题,提出综合考虑目标节点重要度和打击费效度的网络节点分析模型。利用超网络构建海上作战体系网络模型,通过度和介数等指标评估网络中节点的重要度;利用打击费效比为指标评估网络中节点的打击代价,进而将目标分析与选择问题转化为多目标优化问题,建立寻优模型,并通过人工鱼群算法进行寻优求解。最后对模型进行案例仿真应用,通过专家Delphi法评估检验,结果表明所建立的模型方法可行,对水面舰队体系的目标分析与选择具有借鉴作用。

PSO和AFSA混合优化算法

结合粒子群优化(PSO)算法和人工鱼群算法(AFSA)的优势,提出一种PSO-AFSA混合算法。将种群分为2个子群体,在每次迭代中,一个子群体利用PSO算法进化,另一个子群体利用AFSA进化,2个算法共享整个种群极值信息。通过混合算法对5个标准函数进行实验,并与标准PSO算法进行比较,结果表明混合算法具有更好的优化性能。

基于神经网络和人工鱼群算法的惯性延时微通道优化

为了保证中、小口径弹引信的炮口安全性控制要求,设计了具有肋板阻尼结构的惯性延时微通道,同时为了保证其具有稳定的延时性能,研究了该微通道在高离心转速下的延时响应性能。采用了神经网络模型和人工鱼群算法对蛇形微通道内肋板的结构位置进行优化设计。用两相流水平集模型以微通道的延迟时间为研究对象进行了模拟仿真,得到180组样本数据,分析发现肋板结构在微通道内的不同位置与延迟时间呈现出高度的非线性关系。根据样本数据建立神经网络模型用以拟合设计变量与优化目标之间的映射函数,并采用人工鱼群算法对神经网络模型拟合的映射函数的参数进行优化。结果表明,经过结构优化之后,在1 000 g离心环境下微通道中流体的延迟时间从最短的11.446 ms提升到了25.054 ms,延时效果得到了显著提升。最后研究了优化后的结构在中、小口径弹引信使用环境下的延时特性,验证了其满足大部分中、小口径弹引信的延时控制要求。

IAFSA-RBF神经网络在短期负荷预测中的应用

为了提高人工鱼群算法AFSA(artificial fish swarm algorithm)的全局搜索能力及加快其收敛速度,提出一种将其与免疫算法IA(immune algorithm)进行结合的新方法,形成了免疫人工鱼群算法IAFSA(immuneartificial fish swarm algorithm),并且利用该算法自动选取径向基函数RBF(radial basis function)神经网络中的输入变量,以及对网络中隐含层到输出层之间的权值进行训练,从而减少了RBF神经网络的工作量,提高了训练速度。用优化后的RBF神经网络进行短期负荷预测,结果表明,该方法具有较高的预测精度。

基于广义高斯随机混沌算法的AFSA在WSN覆盖中的研究

如何能够进行更好的覆盖优化是目前无线传感器网络研究的热点。针对目前的传感覆盖模型没有考虑覆盖范围、成本和连通性的问题进行改进,在人工鱼群算法(AFSA)的基础上,对初始阶段对人工鱼群采用广义高斯分布,在觅食阶段采用混沌算法,使得个体分布更加合理,有效减少了聚群行为的时间。仿真结果表明,改进后的人工鱼群能够有效地提高节点的覆盖率,降低了网络消耗和成本,为传感覆盖优化提供了一种新的方法。

基于AFSA-SVM的网络入侵检测模型

特征选择是网络入侵检测研究中的核心问题,为了提高网络入侵检测率,提出一种人工鱼群算法(AFSA)和支持向量机(SVM)相融合的网络入侵检测模型(AFSA-SVM)。将网络特征子集编码成人工鱼的位置,以5折交叉验证SVM训练模型检测率作为特征子集优劣的评价标准,通过模拟鱼群的觅食、聚群及追尾行为找到最优特征子集,SVM根据最优特征子集进行网络入侵检测,并采用KDD CUP 99数据集进行仿真测试。仿真结果表明,相对于粒子群优化算法、遗传算法和原始特征法,AFSA-SVM提高了入侵检测效率和检测率,是一种有效的网络入侵检测模型。