动态模糊神经网络研究

针对静态网络无法处理暂态问题，对具有递归环节的动态模糊神经网络进行了研究。通过在网络第二层中加入内部反馈连接，使其具有动态映射能力，从而对动态系统有更好的响应。网络使用遗传算法与反向传播BP(BackPropagation)算法相结合来训练，避免陷入局部最优解。采用时序预测和动态非线性系统进行了仿真研究，结果表明，动态模糊神经网络较之普通模糊神经网络在收敛速度、预测精度和网络规模等方面都有较大的改善，并具有更好的动态系统处理能力。     

遗传指纹图谱技术对微生物群落的分析

微生物培养技术无法获得自然生境中99％以上的微生物，而可培养的微生物也仅提供极少的形态学线索，鉴定和生理学特性经常是模糊的。分子生物学技术对不可培养微生物的研究，开启了探索微生物多样性和新资源的大门。DNA杂交、rRNA分子标记测序等已经成为研究分子微生物生态学的常规手段，可以鉴定和描述微生物群落的种群，但却不适于探索微生物复杂群落的动力学。遗传指纹图谱技术允许同时进行多样本的分析，可比较不同生境和随时间变化的微生物群落行为，是传统手段的有力补充。     

遗传算法在气体分离装置调优中的应用

提出了一种基于遗传算法和随机复合形法相结合的混合遗传算法，并以某厂气体分馏装置的生产过程的优化问题进行了测试，得出了优化操作条件。     

A dynamic fuzzy clustering method based on genetic algorithm

A dynamic fuzzy clustering method is presented based on the genetic algorithm. By calculating the fuzzy dissimilarity between samples the essential associations among samples are modeled factually. The fuzzy dissimilarity between two samples is mapped into their Euclidean distance, that is, the high dimensional samples are mapped into the two-dimensional plane. The mapping is optimized globally by the genetic algorithm, which adjusts the coordinates of each sample, and thus the Euclidean distance, to approximate to the fuzzy dissimilarity between samples gradually. A key advantage of the proposed method is that the clustering is independent of the space distribution of input samples, which improves the flexibility and visualization. This method possesses characteristics of a faster convergence rate and more exact clustering than some typical clustering algorithms. Simulated experiments show the feasibility and availability of the proposed method.     

生物机制在智能计算中的应用

揭示生物机制在智能计算中的应用。与生物学相关理论相结合 ,论述遗传算法、人工神经网络和DNA计算的生物机制 ,揭示生物学思想在其中的应用 ,说明现在各类学科交叉发展的趋势     

Ratio K: a New Way of Metering and Evaluating the Risk and Return of Stock Investment

Although widely used, both the Markowitz model and VAR (Value at Risk) model have some limitations in evaluating the risk and return of stock investment. By the analysis of the conceptions of risk and return, together with the three hypotheses of technological analysis, a novelty model of metering and evaluating the risk and return of stock investment is established. The major indicator of this model , risk-return ratio K, combines the characteristic indicators of risk and return. Regardless of the form of the risk-return probability density functions, this indicator K can always reflect the risk-return performances of the invested stocks clearly and accurately. How to use the model to make optimum investment and how to make portfolio combined with clustering analysis is also explained.     

Genetic Diversity in Populations of Sepiella maindroni Using 16S rRNA Gene Sequence Analysis

Part of the 16S rRNA gene is amplified with PCR and sequenced for 5 populations of common Chinese cuttlefish Sepiella maindroni:three from the South China Sea,one from East China Sea and one from Japan.The result shows that a total of 5 nucleotide positions are found to have gaps or insertions of base pairs among these individuals,and 13 positions are examined to be variable in all the sequences,which range from 494 to 509 base pairs.All of the individuals are grouped into 7 haplotypes (h1-h7).No marked genetic difference is osberved among those populations.All of the individuals from Nagasaki belong to h1 and the h3 haplotype is found only in the coastal waters of China.A→←G transition in Nucleotide 255 is suggested to be taken as a kind of genetic marker to identify the populations distributed in East-South China Sea and the Nagasaki waters of Japan.     

4种木麻黄亲缘关系的RAPD分析

应用RAPD枝术对普通木麻黄(Casuarina equiseti folia)，粗枝木麻黄(C.gluca)，细枝木麻黄(C．cunninghamaina)和滨海木麻黄(Allocasuarina littoralis)的亲缘关系进行分析，从40个引物中筛选出18个重复性好、稳定性高的有效引物．18个有效引物共扩增出690条DNA带，其中多态性条带318条，占总扩增条带的46．09％．对扩增出来的690条DNA带进行聚类分析，结果表明：木麻黄属(Casuarina)的普通木麻黄、粗枝木麻黄和细枝木麻黄的平均遗传距离为0．30，其中细枝木麻黄和粗枝木麻黄的遗传距离特别小，为0．19；而异果木麻黄属(Allocasuarina)的滨海木麻黄与其他3种木麻黄的平均遗传距离为0．65．RAPD聚类分析结果表明，4种木麻黄之间的亲缘关系与血清学和化学分类学的结果一致，说明RAPD分子标记技术适用于木麻黄植物的遗传多样性研究．     

一种用于多峰函数优化的改进混合遗传算法

针对遗传算法在处理复杂多峰函数优化问题中存在的一些缺陷，提出了一种改进型的混合遗传算法，它在小生境技术的基础上引入单纯搜索算法、最优保存算法和近优淘汰算法，并使之相互结合，经编程实践证明，这种改进的混合遗传算法在处理复杂多峰函数优化问题时，局部搜索能力和克服过早收敛能力方面都显著优于标准遗传算法，并在实际应用中取得了较好的效果。     

对技术项目投资风险的模糊评价

利用模糊评价法,对技术项目的投资风险进行评价,以判断是否具有投资价值.