从文献计量学指标看《自动化学报》和自动化研究领域

汇集不同数据源中,《自动化学报》的各项文献计量指标,如影响因子、影响因子排名、总被引频次和海外论文比等,以图表的形式清晰直观地展示出这些指标近五年的年度变化趋势.同时也分析了国际自动化、控制系统和模式识别领域研究的进展、主题、文献类型、主要机构和国家（地区）、研究热点等,向读者展示《自动化学报》和自动化研究领域近五年的发展图景.     

域自适应学习研究进展

传统的机器学习假设测试样本和训练样本来自同一概率分布. 但当前很多学习场景下训练样本和测试样本可能来自不同的概率分布. 域自 适应学习能够有效地解决训练样本和测试样本概率分布不一致的学习问题,作为 机器学习新出现的研究领域在近几年受到了广泛的关注. 鉴于域自适应学习技术 的重要性,综述了域自适应学习的研究进展. 首先概述了域自适应学习的基本问 题,并总结了近几年出现的重要的域自适应学习方法. 接着介绍了近几年提出的 较为经典的域自适应学习理论和当下域自适应学习的热门研究方向,包括样例加 权域自适应学习、特征表示域自适应学习、参数和特征分解域自适应学习和多 源域自适应学习. 然后对域自适应学习进行了相关的理论分析,讨论了高效的度 量判据,并给出了相应的误差界. 接着对当前域自适应学习在算法、模型结构和 实际应用这三个方面的研究新进展进行了综述. 最后分别探讨了域自适应学习在 特征变换和假设、训练优化、模型和数据表示、NLP 研究中存在的问题这四个方面 的有待进一步解决的问题.     

Dynamics of fluid circulation in coupled free and heterogeneous porous domains

Fluid flow in coupled free and porous domain, particularly when the porous medium is heterogeneous, is encountered in many hydro-environmental conditions, e.g., leakage from underground pipe, combined groundwater lake-subsurface interactions. One of the most difficult problems in the study of coupled flow behaviour has been the development of a universally applicable modelling scheme for combining the flow regimes. This is because the free/porous interfacial properties (e.g., shear-stress; velocity slip) that govern the coupled flow behaviour are difficult to determine experimentally under hydro-environmental conditions. On the other hand, the implications of various forms of heterogeneity in the porous media properties can be very different on the fluid-flow behaviour. Difficulties may also arise in direct coupling of the model equations that govern the fluid flow in the individual regions (e.g., Navier-Stokes for free-flow region and the Darcy's equation for the porous flow region). Consequently, models of coupled free and porous flow for hydro-environmental conditions are not very well developed at the moment. While there are some indications that fluids in coupled free and porous domains may circulate (i.e., development of flow cells), there is a lack of appropriate 3D analysis on how heterogeneities in porous media may affect such flow patterns. In this paper, we aim to analyse how porous media heterogeneity affects the dynamics of flow circulation in the porous side of a coupled free and porous domain. For this purpose, we analyse flow patterns in several model domains made up of two porous layers with differing permeabilities. The governing model equations are discretised and solved using the standard finite volume method on a staggered cell-centred mesh. The temporal discretisation is done using the explicit method. An in-house graphical user interface (GUI) has been created specifically to aid in the visualisation of otherwise complex flow patterns. The GUI contains many post-processing options and provides a comprehensive tool for the analysis of hydrodynamics and contaminant motion (not discussed in this paper) in coupled free and porous flow domains. This GUI is described in this paper briefly. The effects of altering the aspect ratio (i.e., multi-scale) of the domain on the coupled flow pattern have also been discussed.     

改进的蚁群算法在溶质运移参数识别问题中的应用

非饱和土壤水分和溶质运移参数(扩散率、导水率和水动力弥散系数)取值范围较大,往往跨越几个数量级。采用传统离散化蚁群算法求解此类问题,所需节点较多,这会造成算法收敛时间较长。该文在传统蚁群算法基础上,对蚂蚁搜索路径进行改进,改进后的蚁群算法寻优路径由参数精度位数(整数位和小数位)、参数个数以及0–9十个数字构成,并将路径解码公式修改为具有判别参数正负功能的解码公式。采用改进的连续蚁群算法对非饱和溶质运移参数识别优化模型进行求解。数值模拟表明相同迭代次数下改进的蚁群算法比传统蚁群算法耗时少,算法计算时间与迭代次数满足线性关系,含水率和溶质浓度实测值与计算值吻合较好、相关性较高。     

Sequence and structure of VH domain from naturally occurring camel heavy chain immunoglobulins lacking light chains

We cloned 17 different PCR fragments encoding V_H genes of camel(Camelus dromedarius). These clones were derived from the camelheavy chain immunoglobulins lacking the light chain counterpartof normal immunoglobulins. Insight into the camel V_H sequencesand structure may help the development of single domain antibodies.The most remarkable difference in the camel V_H, consistent withthe absence of the V_L interaction, is the substitution of theconserved Leu45 by an Arg or Cys. Another noteworthy substitutionis the Leu11 to Ser. This amino acid normally interacts withthe C_H1 domain, a domain missing in the camel heavy chain immunoglobulins.The nature of these substitutions agrees with the increasedsolubility behavior of an isolated camel V_H domain. The V_H domainsof the camels are also characterized by a long CDR3, possiblycompensating for the absence of the V_L contacts with the antigen.The CDR3 lacks the salt bridge between Arg94 and Asp101. However,the frequent occurrence of additional Cys residues in both theCDR1 and CDR3 might lead to the formation of a second internaldisulfide bridge, thereby stabilizing the CDR structure as inthe DAW antibody. Within CDRs of the camel V_H domains we observea broad size distribution and a different amino acid patterncompared with the mouse or human V_H. Therefore the camel hypervariableregions might adopt structures which differ substantially fromthe known canonical structures, thereby increasing the repertoireof the camel antigen binding sites within a V_H.     

Event-driven,pattern-based methodology for cost-effective development of standardized personal health devices

Experiences applying standards in personal health devices (PHDs) show an inherent trade-off between interoperability and costs (in terms of processing load and development time). Therefore, reducing hardware and software costs as well as time-to-market is crucial for standards adoption. The ISO/IEEE11073 PHD family of standards (also referred to as X73PHD) provides interoperable communication between PHDs and aggregators. Nevertheless, the responsibility of achieving inexpensive implementations of X73PHD in limited resource microcontrollers falls directly on the developer. Hence, the authors previously presented a methodology based on patterns to implement X73-compliant PHDs into devices with low-voltage low-power constraints. That version was based on multitasking, which required additional features and resources. This paper therefore presents an event-driven evolution of the patterns-based methodology for cost-effective development of standardized PHDs. The results of comparing between the two versions showed that the mean values of decrease in memory consumption and cycles of latency are 11.59% and 45.95%, respectively. In addition, several enhancements in terms of cost-effectiveness and development time can be derived from the new version of the methodology. Therefore, the new approach could help in producing cost-effective X73-compliant PHDs, which in turn could foster the adoption of standards.     

A novel image steganography scheme with high embedding capacity and tunable visual image quality based on a genetic algorithm

Steganography is knowledge and art of hiding secret data into information which is largely used in information security systems. Various methods have been proposed in the literature which most of them are not capable of both preventing visual degradation and providing a large embedding capacity. In this paper, we propose a tunable visual image quality and data lossless method in spatial domain based on a genetic algorithm (GA). The main idea of the proposed technique is modeling the steganography problem as a search and optimization problem. Experimental results, in comparison with other currently popular steganography techniques, demonstrate that the proposed algorithm not only achieves high embedding capacity but also enhances the PSNR of the stego image.     

Credit rating with a monotonicity-constrained support vector machine model

Deciding whether borrowers can fulfill their obligations is a major issue for financial institutions, and while various credit rating models have been developed to help achieve this, they cannot reflect the domain knowledge of human experts. This paper proposes a new rating model based on a support vector machine with monotonicity constraints derived from the prior knowledge of financial experts. Experiments conducted on real-world data sets show that the proposed method, not only data driven but also domain knowledge oriented, can help correct the loss of monotonicity in data occurring during the collecting process, and performs better than the conventional counterpart.     

结合相关规则和本体加权图的查询扩展

针对现有信息检索系统查询性能的不足,提出了一种结合相关规则和WordNet本体信息的查询扩展方法.该方法借助相关规则挖掘和WordNet本体信息构建加权词语关系图,并根据加权图的结构和权重信息计算扩展词的重要性.查询时,从这个图中取原查询词的最邻近词作为扩展词来源,选取其中权重最大的p个词返回并进行二次检索.在实现算法的基础上,通过Lucene全文检索器进行实验,将所得的结果值F1与其他算法的结果作比较.比较结果表明,该方法比不作扩展的检索有约16.93％的性能提升.     

一种混合的领域概念分类体系自动构建算法

领域概念分类体系自动构建在人工智能、自然语言处理和信息检索等领域具有重要作用,但现有研究较多关注通用知识,面向特定领域的研究较少,且存在领域概念间关系抽取准确率以及自动构建算法效率较低等问题。为此,提出一种混合的领域概念分类体系自动构建算法,该算法主要包括领域概念间关系抽取模块和分类体系构建模块。领域概念间关系抽取模块设计考虑中文自身的特点,采取句法树和基于规则相结合的方法,以提高抽取领域概念间关系的查准率和查全率;分类体系构建模块设计采取改进的BRT算法,从而在降低算法复杂度的同时,提高领域分类体系构建的查准率。在通信、金融和计算机领域的实验结果均表明,与BRT算法相比,该算法的构建效果较好,查准率最高可达到89.3%。