| 1. | In chapter 3 , using dynamic programming and the theory of optimal stopping , we determine a hjb equation that the value function satisfy , while we prove a general existence result about the optimal strategy
第三章，利用动态规划方法及最优停时理论，建立值函数所满足的hjb方程，并证明了最优策略的一般存在性结果。 |
| 2. | The paper presents text - independent classifiers : gmm classifier and vq classifier and proposes the dynamic recognition length choose algorithm ( drlca ) based on optimal stopping rules in detail
本文介绍了分类器，特别是文本无关分类器在说话人识别中的应用。基于最优停止理论提出了识别长度自适应算法来解决识别长度的选取问题。 |
| 3. | The results show that the optimal stopping rule for our proposed sequential sampling plan can effectively reduce the average sample number and thus achieve a minimum total loss under the reasonable type and errors
研究结果显示在合理的型误差及型误差下，本研究所提出的抽样计画停止法则可有效降低平均抽样数使抽样总成本达到最低。 |
| 4. | The analysis involves martingale theory , optimal stopping , stochastic control problem and convex analysis . as for the general incomplete financial market , the upper - and lower - hedging prices of arbitrage - free interval are obtained . the quisimartingales decomposition has been proved
借助于鞅论，最优停时，随机控制和凸分析等理论与方法，就一般的非完备金融市场，未定权益的估值得以研究，并且我们求出了上、下保值价格。 |
| 5. | Under the assumption of rational government , the paper builds a optimal stopping currency crises model , which applies optimal stopping theory to explaining of the condition that make government abandon fixed exchange - rate regime , and currency crises contagion is explained by the model
文章还在理性政府的假设下，用最优停止理论解释了政府在什么情况下会放弃固定汇率，构造了货币危机的最优停止模型，并用这个模型解释了理性政府假设下的货币危机传染现象。 |
| 6. | My main work is as following : 1 ) applying feature mapping , sub - band structure classifier and multi - classifier cooperation to enhance the robust of system ; 2 ) giving out close - set fusion and open - set fusion functions to solve the problems of speaker identification and verification respectively ; 3 ) building the dynamic recognition length algorithm based on optimal stopping rules ; 4 ) developing a applied system based on the techniques above
主要工作是： 1 、提出参数映射、子带结构分类器和多分类器系统以提高系统的鲁棒性能； 2 、给出证据融合的闭集公式和开集公式，它们分别适用说话人辨认和确认问题的； 3 、通过最优停止理论建立识别长度自适应算法； 4 、开发了一个实用的说话人识别系统。 |
| 7. | The problem of bayes sequential decision rules to hypothesis testing is often reduced to the problem of optimal stopping . in continuous time situation , the existence of bayes solution is proved by using the general stochastic process theory . in distinguishing among two exponential distributions , the bayes solutions are found out in different situations as an example , which also shows that the uniqueness of solution does not hold in general
假设检验的bayes序贯决策问题往往可用最优停止理论解决.利用随机过程的一般理论证明了连续时间情形下上问题bayes解的存在性。作为一个实例，找出了区分两个指数分布的bayes解的具体形式，并说明解的唯一性在最一般的条件下不成立。 |
