A self region based real-valued negative selection algorithm

Point-wise negative selection algorithms,which generate their detector sets based on point of self data,have lower training efficiency and detection rate.To solve this problem,a self region based real-valued negative selection algorithm is presented.In this new approach,the continuous self region is defined by the collection of self data,the partial training takes place at the training stage according to both the radius of self region and the cosine distance between gravity of the self region and detector candidate,and variable detectors in the self region are deployed.The algorithm is tested using the triangle shape of self region in the 2-D complement space and KDD CUP 1999 data set.Results show that,more information can be provided when the training self points are used together as a whole,and compared with the point-wise negative selection algorithm,the new approach can improve the training efficiency of system and the detection rate significantly.

Always-optimally-coordinated candidate selection algorithm for peer-to-peer files sharing system in mobile self-organized networks

In order to improve the performance of peer-to-peer files sharing system under mobile distributed en-vironments,a novel always-optimally-coordinated(AOC)criterion and corresponding candidate selectionalgorithm are proposed in this paper.Compared with the traditional min-hops criterion,the new approachintroduces a fuzzy knowledge combination theory to investigate several important factors that influence filestransfer success rate and efficiency .Whereas the min-hops based protocols only ask the nearest candidatepeer for desired files,the selection algorithm based on AOC comprehensively considers users' preferencesand network requirements with flexible balancing rules.Furthermore,its advantage also expresses in theindependence of specified resource discovering protocols,allowing for scalability.The simulation resultsshow that when using the AOC based peer selection algorithm,system performance is much better thanthe min-hops scheme,with files successful transfer rate improved more than 50% and transfer time re-duced at least 20%.

Unsupervised Feature Selection Using Structured Self-Representation

Unsupervised feature selection has become an important and challenging problem faced with vast amounts of unlabeled and high-dimension data in machine learning. We propose a novel unsupervised feature selection method using Structured Self-Representation( SSR) by simultaneously taking into account the selfrepresentation property and local geometrical structure of features. Concretely,according to the inherent selfrepresentation property of features,the most representative features can be selected. Mean while,to obtain more accurate results,we explore local geometrical structure to constrain the representation coefficients to be close to each other if the features are close to each other. Furthermore,an efficient algorithm is presented for optimizing the objective function. Finally,experiments on the synthetic dataset and six benchmark real-world datasets,including biomedical data,letter recognition digit data and face image data,demonstrate the encouraging performance of the proposed algorithm compared with state-of-the-art algorithms.

Selection Method of Multi-Objective Problems Using Genetic Algorithm in Motion Plan of AUV

To research the effect of the selection method of multi-objects genetic algorithm problem on optimizing result, thismethod is analyzed theoretically and discussed by using an autonomous underwater vehicle(AUV) as an object. A changingweight vtlue method is put forward and a selection formula is modified. Some experiments were implemented on an AUV.TwinBurger. The results shows that this method is effective and feasible.

基于mRMR-SOM的异步电机轴承故障诊断研究

针对异步电机轴承故障诊断问题,提出了一种融合最大相关最小冗余特征选择算法(mRMR)和自组织映射神经网络(SOM)的故障诊断方法,并将其应用于轴承故障诊断的不同阶段。首先,在实验室环境下搭建了异步电机故障诊断试验平台,在不同电机状态下分别采集振动、电流和电压信号,利用统计学方法获取了高维混合特征集;然后,以互信息为背景,利用mRMR根据特征与状态标签间的相关性和特征间的冗余性,筛选了具备强区分能力的特征,以避免计算冗余和后验诊断性能下降;最后,采用SOM对异步电机健康和轴承故障状态进行了分类识别,验证了SOM对异步电机轴承故障诊断的有效性,以及mRMR对故障诊断结果的影响。研究结果表明:基于mRMR-SOM的异步电机轴承故障诊断方法能够准确地区分健康和故障状态,测试集分类准确率达到89%;使用mRMR特征筛选能够将154维特征降低至17维,缩短23.5%的网络收敛时间,并将分类准确率由89%提升至98%;试验结果验证了基于mRMR-SOM的异步电机轴承故障诊断方法对于异步电机轴承故障诊断问题的有效性,且证实其具备良好的诊断效果。

Path Selection in Disaster Response Management Based on Q-learning

Suitable rescue path selection is very important to rescue lives and reduce the loss of disasters, and has been a key issue in the field of disaster response management. In this paper, we present a path selection algorithm based on Q-learning for disaster response applications. We assume that a rescue team is an agent, which is operating in a dynamic and dangerous environment and needs to find a safe and short path in the least time. We first propose a path selection model for disaster response management, and deduce that path selection based on our model is a Markov decision process. Then, we introduce Q-learning and design strategies for action selection and to avoid cyclic path. Finally, experimental results show that our algorithm can find a safe and short path in the dynamic and dangerous environment, which can provide a specific and significant reference for practical management in disaster response applications.

Walking and Aerobic Capacity in Old Adults after Concentric and Eccentric Endurance Exercise at Self-Selected Intensities

Self-selected exercise intensity can be a useful exercise prescription tool for older adults;however, it is not known if it can elicit improvements in walking and aerobic capacity. In older adults, effects of concentric or eccentric endurance exercise at self-selected walking speed were examined on 1-mile indoor walk performance, predicted maximum oxygen uptake and physiological parameters. Twenty-four older adults (67 ± 4 years) completed 3 × 30 min treadmill walks per week for 12-weeks on level (LTW, n = 11, 0%) or downhill (DTW, n = 13, ﹣10%) treadmill gradient at a self- selected speed, which progressed every 4 weeks. Maximal oxygen uptake was predicted using a 1-mile walk at 4-week intervals with physiological responses recorded using a portable metabolic system. One-mile walking speed increased from baseline following 8- and 12-weeks (12 weeks: LTW: 13% ± 6%, DTW: 14% ± 9%,

Molecular mapping of a novel wheat powdery mildew resistance gene Ml92145E8-9 and its application in wheat breeding by marker-assisted selection

Powdery mildew, caused by Blumeria graminis f. sp. tritici(Bgt), is one of the most devastating diseases of common wheat(Triticum aestivum L.). The wheat line 92145 E8-9 is immune to Bgt isolate E09. Genetic analysis reveals that the powdery mildew resistance in 92145 E8-9 is controlled by a single dominant gene, temporarily designated Ml92145 E8-9. Bulkedsegregant analysis(BSA) with simple sequence repeat(SSR) markers indicates that Ml92145 E8-9 is located on chromosome 2 AL. According to the reactions of 92145 E8-9,VPM1(Pm4 b carrier), and Lankao 906(PmLK906 carrier) to 14 Bgt isolates, the resistance spectrum of 92145 E8-9 differs from those of Pm4 b and PmLK906, both of which were previously localized to 2 AL. To test the allelism among Ml92145 E8-9, Pm4 b and PmLK906, two F2 populations of 92145 E8-9 × VPM1(Pm4 b) and 92145 E8-9 × Lankao 906(PmLK906) were developed in this study. Screening of 784 F2 progeny of 92145 E8-9 × VPM1 and 973 F2 progeny of 92145 E8-9 × Lankao 906 for Bgt isolate E09 identified 37 and 19 susceptible plants, respectively. These findings indicated that Ml92145 E8-9 is non-allelic to either Pm4 b or PmLK906. Thus, Ml92145 E8-9 is likely to be a new powdery mildew resistance gene on2 AL. New polymorphic markers were developed based on the collinearity of genomic regions of Ml92145 E8-9 with the reference sequences of the International Wheat Genome Sequencing Consortium(IWGSC). Ml92145 E8-9 was mapped to a 3.6 c M interval flanked by molecular markers Xsdauk13 and Xsdauk682. This study also developed five powdery mildew-resistant wheat lines(SDAU3561, SDAU3562, SDAU4173, SDAU4174, and SDAU4175)using flanking marker-aided selection. The markers closely linked to Ml92145 E8-9 would be useful in marker-assisted selection for wheat powdery mildew resistance breeding.

Grain selection and growth orientation of prior-β phase for Ti-6-4 during additive manufacturing:insights from a modeling perspective

The microstructure of Ti-6-4 components produced by additive manufacturing suffers from the coarse and elongated prior-β grain,which leads to a decrease of the tensile behavior and the occurrence of anisotropy.To understand and control the grain evolution,a multiscale simulation is applied to investigate the relationship between the grain selection,growth orientation,and the molten pool morphology with the different deposition layer numbers and processing parameters.The accuracy of the simulation is validated by experiments in both qualitative and quantitative ways.Results show that when the grain with unfavorable orientation loses the competitive growth with its neighbors,there will be a great chance that the blocked grain is eliminated in the following layer-and-layer deposition,which leads to the increase of the grain width.The size of the molten pool increases remarkably as the layer number increases,which lays a heavy burden on the stability of the molten pool.The analytical relationship between the molten pool morphology and the grain growth orientation is also deduced.The flat molten pool causes the grains with the <001> direction close to the building direction to have greater survival potential.Besides,decreasing the line power energy shows little effect on the stability of the molten pool and the grain growth orientation,especially when the deposited layer number is large.The revealing mechanisms will help in understanding and further controlling the grain evolution.

基于自编码器的PCA-SOM公共服务资源配置评价与选址优化决策方法

当前城市规划和公共服务资源配置存在分配不均和选址效率低下的问题。将公共服务资源的电力消耗数据与其资源数量、区域人口数量相结合,基于主成分分析(principal component analysis,PCA)评估各区域公共服务资源的配置状况,并以兰州市为案例,运用自组织映射(self-organizingmapping,SOM)算法进行教育资源的优化选址。研究发现,电力数据能有效指示资源配置的不足,并为优化分配提供精确的指导。尤其在兰州市,SOM算法的应用不仅提高了教育资源选址的效率,还促进了资源的公平分配。不仅为甘肃省提供了公共服务资源配置的科学决策依据,也为其他地区在相似领域的研究提供了参考。

Pay-based Screening Mechanism: Personnel Selection in the View of Economics Theory

Based on economic theories,the paper studies the personnel selection at the asymmetric job market using signaling and screening model.The authors hold the opinion that an organization can screen the candidates'signaling based on the self-selection principle by providing an apropriate compensation choice.A pay-based screening mechanism is qualified applicants and retain the excellent applicants.

基于阴性选择原则的Non-self探测器生成算法

基于免疫系统异己检测原理,深入进行了计算机免疫系统探测器生成算法的研究.首先,简要介绍了阴性选择算法,总结了相关的探测器生成算法;然后,基于阴性选择原则提出了两种探测器生成算法,即位变异算法(BMGDGA)和余数生长算法(AGDGA).文中对两种算法在多种不同的数据集上进行了全面的验证和实验,并与穷尽式探测器生成算法进行了全面系统的比较.结果表明,两种探测器生成算法在综合性能上均优于穷尽式探测器生成算法.

基于拉普拉斯小波滤波和SA-DS-CNN的滚动轴承故障诊断

针对基于深度学习模型的滚动轴承故障诊断方法易受环境噪声干扰的问题,提出了一种基于拉普拉斯小波滤波(LWF)和自注意力机制-动态选择-卷积神经网络(SA-DS-CNN)的滚动轴承故障诊断模型。首先,提出一种拉普拉斯小波阻尼参数自适应选取策略,使用拉普拉斯小波对采集的滚动轴承振动信号进行相关滤波并进行功率谱变换;其次,基于卷积神经网络框架,引入自注意力机制和动态选择机制,构造SA-DS-CNN;最后,利用SA-DS-CNN提取功率谱特征,根据轴承的不同故障状态定位相关特征信息,实现故障特征的提取和诊断。对N205EM圆柱滚子轴承的故障诊断试验表明:LWF降噪效果较好,能为SA-DS-CNN模型提供优秀的训练样本;SA-DS-CNN模型能抑制无用通道信息,增强网络特征学习能力;LWF和SA-DS-CNN组合模型的故障诊断准确率达到99.65%,优于其他组合模型。

Biologically inspired self-organizing networks

Information networks are becoming more and more complex to accommodate a continuously increasing amount of traffic and networked devices,as well as having to cope with a growing diversity of operating environments and applications. Therefore,it is foreseeable that future information networks will frequently face unexpected problems,some of which could lead to the complete collapse of a network. To tackle this problem,recent attempts have been made to design novel network architectures which achieve a high level of scalability,adaptability,and robustness by taking inspiration from self-organizing biological systems. The objective of this paper is to discuss biologically inspired networking technologies.

Parameter Self - Learning of Generalized Predictive Control Using BP Neural Network

This paper describes the self—adjustment of some tuning-knobs of the generalized predictive controller(GPC).A three feedforward neural network was utilized to on line learn two key tuning-knobs of GPC,and BP algorithm was used for the training of the linking-weights of the neural network.Hence it gets rid of the difficulty of choosing these tuning-knobs manually and provides easier condition for the wide applications of GPC on industrial plants.Simulation results illustrated the effectiveness of the method.

Self - Crosslinking Behavior of Self - Emulsion Water - Based Polyure-thane Coating Agents

The relation between structures and properties of polyurethane are investigated by modern physical and chemical methods.The results obtained are as follows:the effects of the content of self-crosslinking agent on the properties of polyurethane,i.e.,dispersion stability,dynamical viscoelasticity and mechanical properties are discussed.It is found that the optimum molar ratio of epichlorohydrin and diethylenetriamine is 1:2.A mois-

Culture Self- Consciousness in Transmission of Chinese Philosophy from the Perspective of English Globalization -- Taking the Belt and Road Initiative for Example

The Belt and Road Initiative contains the aspiration of Chinese nation to pursue ideological freedom and desire of strengthening international exchanges and cooperation. This paper takes the Belt and Road Initiative for example,emphasizing the interpretation of the inheritance and development of Chinese culture so as to study the importance of Culture Self-Consciousness in Chinese Philosophy,in the context of English globalization. That is to say,this paper stresses the spirits and the stand of nation 's demonstration on pursuing peace,cooperation and sustainable development in the civilization continuity from traditional China to the contemporary China,with practical philosophic view.

过硫酸铵/PDA-PEI层层自组装法制备选择性阳离子交换膜

针对多巴胺聚合速率较慢的问题,以过硫酸铵为氧化剂,诱导多巴胺快速聚合.以此为基础,采用多巴胺与聚乙烯亚胺层层自组装法制备具有单双价阳离子选择分离功能的离子交换膜.考察了过硫酸铵氧化多巴胺聚合过程影响,以及不同改性层数对阳离子交换膜性能的影响.结果显示,过硫酸铵的加入可较大地加快氧化过程,且对膜选择性无影响;改性层数为5层时,复合膜对Mg^(2+)与Na+具有较高的选择性[p(Na+/Mg^(2+))=6.92].5层改性膜面电阻为3.36Ω·cm^(2).说明改性膜具有较好的实用价值.