利用大流量液压支架控制顶板事故的发生

通过对工作面端面冒顶原因及支护系统的分析得出，加大液压支架的流量可以加快移架速度，降低冒顶事故率，提高生产效率。     

Two-tier architecture for unconstrained handwritten character recognition

In this paper, we propose an approach that combines the unsupervised and supervised learning techniques for unconstrained handwritten numeral recognition. This approach uses the Kohonen self-organizing neural network for data classification in the first stage and the learning vector quantization (LVQ) model in the second stage to improve classification accuracy. The combined architecture performs better than the Kohonen self-organizing map alone. In the proposed approach, the collection of centroids at different phases of training plays a vital role in the performance of the recognition system. Four experiments have been conducted and experimental results show that the collection of centroids in the middle of the training gives high performance in terms of speed and accuracy. The systems developed also resolve the confusion between handwritten numerals.     

两江水利枢纽泄洪洞出口右侧高边坡锚喷支护施工技术

锚喷支护作为地质灾害治理中山体过坡支护的一杆方法．具有安全、优质、高效、灵活等特点，本文以吉林省安图县两江水利枢纽泄洪洞出口右侧高边坡治理工程为例．对锚喷支护施工技术作一简单介绍。     

F150交换机告警关联规则的研究

为了提高电信网络运营效率，降低维护成本，电信运营企业在网络告警管理系统中需要引入数据挖掘技术。本文主要研究利用数据挖掘技术来进行故障的管理，即对告警进行关联性分析，详细分析了告警序列数据的关联规则挖掘算法，并在南昌本地网F150交换机的告警数据库中予以实现，同时对实际挖掘结果进行分析和整理，推导出一些实用的关联规则。     

回归分析法简化钻爆设计

以某工程钻爆参数为例,阐述了在地下工程掘进施工中,应用回归分析法建立钻爆参数的相关模型,并利用此模型帮助建立某断面钻爆方案.     

用于一维图像识别的支撑矢量机方法

研究了支撑矢量机的分类机理,并利用支撑矢量机对雷达目标一维像进行了识别.识别的结果表明了该方法的优越性,并显示它可以对残缺不全的样本进行识别.     

Modelling the rate of secondary succession after farmland abandonment in a Mediterranean mountain area

Secondary succession after farmland abandonment has become a common process in north Mediterranean countries, especially in mountain areas. In this paper, a methodology is tested which combines Markov chains and logistic multivariate regression to model secondary succession after farmland abandonment in environments where abiotic constraints play a major role, like mountain areas. In such landscapes, a decay in the succession rate with time is usually found, as the best locations are progressively occupied. This is frequently addressed using non-stationary Markov chains. Here, we test if the combination of logistic multivariate regression with Markov chains, however, allows for spatially distributed transitions probabilities based on abiotic factors and therefore, it is able to reproduce the preferential colonization of the most favourable locations. The model is tested in the Ijuez Valley in the Spanish Pyrenees, which underwent generalized land abandonment during the 1950s. Results confirm a substantial improvement in the prediction success of the Markov-logistic model when compared to the standard Markov chain approach. As a result, the decay in the succession rate can be successfully modelled. The specific results for our study area are discussed further in an ecological context. The methodology proposed is applicable to any landscape where vegetation dynamics are constrained by environmental factors. However, the inclusion of land use as an explanatory factor would be necessary in human-managed landscapes.     

基于支持向量机的岩爆识别模型

岩爆的发生受多种因素的影响,这些因素关系错综复杂,以不同的特征和组合对岩爆产生综合影响,为科学、充分地利用现有的有限工程资料,本文从地下洞室围岩最大切向应力、岩石的单轴抗压强度和抗拉强度以及岩石冲击倾向指数四个主要因素出发,提出了基于支持向量机的岩爆识别模型,较好地解决小样本、非线性、高维数、局部极小点等的实际问题。     

激光相变硬化性能与工艺参数关系的数学模型

用回归正文分析的方法．建立了中碳结构钢、碳素工具钢和合金结构钢的激光相变硬化性能与工艺参数间关系的数学模型。分析了回归力程的显著性并预测了各硬化指标的精度。