AI paradigms

The aim of this paper is comparative analysis of most important AI paradigms. An AI paradigm is defined as the pair composed by a concept of intelligence and a methodology in which intelligent computer systems are developed and operated. Three paradigms, the behaviourist paradigm, the agent paradigm, and the artificial life paradigm are discussed.     

基于人工免疫机制的木马检测系统

将生物体免疫系统的原理、规则和机制运用到计算机木马检测系统中。利用人工免疫系统的分布性、自适应性、记忆性和高效性,降低检测系统的误报率和提高自适应性问题。     

基于人工势场方法的WSN传感覆盖率提高算法

感覆盖率是WSN系统中重要的性能指标之一。Sink节点的移动性能提高系统的传感覆盖率,人工势场能描述普通节点与Sink节点之间的关系。提出了一种利用人工势场方法有效的Sink节点移动控制策略,通过Sink节点的移动能够提高系统的传感覆盖率。普通节点搜集的数据能通过多跳的方式传送给Sink节点。在最初的随机部署之后,由人工势场产生的力迫使移动Sink节点移动到整个环境中的平衡点以获得更高的传感覆盖率。在整个算法执行过程中无需事先了解环境的情况,此方法能在实时的环境中采用。给出了具体的算法步骤,最后利用一个仿真实例对控制效果进行了说明。     

一种空间信息网络缓存决策策略

针对空间信息网络（space information network,SIN）中卫星节点缓存容量有限,且卫星高速移动使得星间链路时变,导致地面用户内容访问延迟增大的问题,提出一种基于人工蜂群算法的空间信息网络缓存决策策略（satellite improved artificial bee colony,SIABC）。首先根据低轨卫星节点链路切换的周期性和可预知性,建立网络分区模型,对空间信息网络的卫星节点进行分区,在此基础上,建立区域节点协作缓存模型,使得整个网络区域内的卫星节点有选择性地缓存不同流行度的内容,同时兼顾区域内节点的协作缓存,从而流行度高的内容缓存在网络边缘。仿真结果表明,与现有缓存机制相比,该缓存策略能够明显提高内容的平均缓存命中率,并显著降低用户的内容访问时延。     

Temporal dynamics and drivers of lake ecosystem metabolism using high resolution observations in a shallow,tropical, eutrophic lake (Laguna Lake,Philippines)

The physical, chemical, and biological dynamics under changing atmospheric conditions of Laguna Lake, Philippines were analyzed from intensive observations. Diel measurements were conducted for 48 continuous hours for both dry and wet tropical seasons in addition to fine resolution long-term monitoring. Results revealed significant vertical and diel variations of lake variables in spite of a shallow water depth (2.5 m) caused by the intense surface heating from solar irradiance (~800 W m^?2) and accentuated by the lake's high turbidity (16–32 ftu). Late afternoon land-lake breeze (~5–7 m s^?1) regularly breaks daytime thermal stratification, and convective cooling at night maintains isothermal condition until dawn of the next day. The stratified condition demonstrated a wind-driven, density-induced 2-layer current pattern with a windward moving epilimnion (~4 folds faster) and a compensating hypolimnetic flow in the general lake circulation direction. Laguna Lake was observed to have a dominating diel cycle but also undergoes significant seasonal limnological variations brought primarily by climate, hydrology, and its interaction with the adjacent sea. Significantly correlated variations of pH, chlorophyll-a and DO in the dry season were indicative of the higher biological activity associated with the intrusion of polluted waters from Metro Manila. The non-occurrence of thermal over-turn was observed to be regularly followed by bottom hypoxic conditions (2–4 mg L^?1), indicative of the eutrophic condition of the lake and the importance of diel wind-induced mixing in the bottom supply of DO. Laguna Lake was found to be predominantly net heterotrophic (GPP:R < 1, NEP < 0).     

洪水预报智能模型在中国半干旱半湿润区的应用对比

为探究不同洪水预报智能模型在我国半干旱半湿润区的应用效果,选用决策树、多层感知器、随机森林和支持向量机4种模型在陕西省3个典型流域进行逐时洪水预报;选择相关系数、纳什效率系数、均方根误差、平均绝对误差和相对误差等评价指标,比较不同预见期下4种模型在半干旱半湿润典型流域洪水预报的适用性。结果表明:在短预见期预报中,4种模型在半湿润区典型流域均可获得较高的预报结果,在半干旱典型流域模拟精度相对偏低,仅支持向量机模型满足预报要求;随着预见期延长,不同模型性能变化差异大,支持向量机模型整体稳定,在小流域实时洪水预报中具有明显优势;随机森林模型与决策树模型精度随预见期延长而缓慢下降,前者适应性更好;多层感知器模型精度随预见期延长而骤减,模型稳定性较差。     

高坝泄洪诱发场地振动响应分析及传播规律

为研究高坝泄洪诱发场地振动的问题,提出一种基于黏弹性人工边界的有限元数值模拟和水力学模型试验相结合的方法计算场地振动响应。以国内某工程为例,计算不同工况下场地振动响应,分析泄洪量和泄洪调度方式对场地振动的影响,揭示不同岩体条件下振动波的传播规律。结果表明:该工程各种泄洪方式都不会对周边居民的生活造成影响;泄洪量越大,下游场地振动响应越大,当3个溢洪洞泄洪条件一致时,采用2号洞泄洪最不利;同等泄洪条件下,采用4洞均分泄洪的振动响应小于按设计开度泄洪的振动响应;模型范围内放大振动波的主因是断层左右岩体性质的差异,断层的存在进一步加大了放大效应。     

印尼某火电厂Ａ２—Ａ４区人工边坡失稳机制研究

以印尼某火电厂涉外项目Ａ２—Ａ４区的问题人工边坡为研究对象,通过现场地勘、实际变形失稳过程、数值模拟等方法综合研究了该地人工边坡失稳机制。在此基础上,探讨了边滑坡加固措施的作用效果及合理性。所得主要结论:Ａ２—Ａ４区人工边坡变形失稳机制主要为软弱地层（煤层）切穿暴露所造成的组合滑移以及坡体沿土岩分界面所造成局部变形,变形破坏模式接近圆弧滑动,人工边坡中的软弱夹层是导致边坡失稳的主控因素;Ａ２、Ａ４区综合考虑桩锚＋坡面锚杆的方式进行加固,煤层和全风化泥岩及上部土层内的组合变形没有发展贯通趋势,边坡整体安全。Ａ３区在加固作用下存在沿二级坡脚＋煤层＋全风化泥岩＋上部土层内越顶组合滑移风险以及基坑开挖造成基坑侧壁坍滑风险,需要引起重视并加强监测。     

Semi-automated user agents in distributed change management

Flexible integration of distributed design and manufacturing activities is one of the key issues in applying just-in-time principles along the logistics chain. The potential of AI based approaches in this field is clear, but the inherent asynchrony, concurrency, and inconsistency of distributed operations has reduced enthusiasm so far.This paper discusses coordination in the context of geographically distributed manufacturing of one-of-a-kind products. Cooperation of partners is based on semi-automated user agents which operate as an integrative layer between more dedicated tools and systems. The management of order changes in elevator manufacture is used as a case example.The work reported here is part of the DIMUN project (DIMUN, 1989) in the RACE program.     

一种基于网络安全风险评估的入侵检测方法

针对传统的入侵检测系统存在报警数量大、误报率高等缺陷,提出了一种基于网络安全风险评估的入侵检测方法,该方法基于入侵检测结果,引入抗体浓度随入侵强度动态变化这一人工免疫理论的最新研究成果进行网络安全风险的计算,然后根据当前网络面临的实时安全风险动态设置报警策略。实验结果表明,该方法能够实时、定量地计算主机和网络所面临的风险,并极大地降低报警数量和误报率。