基于原训练样本集和新增训练样本集在增量训练中地位等同，提出了一种新的SVM增量学习算法。
Based on the equivalence between the original training set and the newly added training set, a new algorithm for SVM-based incremental learning was proposed.
同时新算法结合了原VM8和基于零系数百分比算法的优点，可以获得更加精确的控制效果。
The new algorithm adopts some advantages of VM8 and Zero coefficient percentage algorithms. It can control the bits more accurately.
本文提出了一个基于模式分解树，不需要扫描原数据库的增量挖掘算法。
The paper presents an algorithm for incremental mining which is based on pattern decomposing tree and has no need for scanning old data base.
文中通过对神经网络分界面以及原神经网络算法的分析，提出一种基于球领域模型的改进的神经网络算法。
In this paper a modification approach for neural network is introduced according to the analysis of the neural network separate boundary faces and the original algorithm.
本文提出一个基于性能的LUT结构的FPGA的再设计算法，该算法采用特征函数以及对原布尔网络进行相应的约束实现电路的再设计。
This paper presents a performance based redesign algorithm for LUT type FPGA. The algorithm uses characteristic functions and presents a redesign method based on restriction for an original relation .
实验结果表明：在相同条件下，基于二字词检测位图表的最大匹配分词算法较原算法分词速度更快。
The experimental result shows: under the same condition, the improved maximum match algorithm that based on the two-word bitmap has fastened segmentation speed than original algorithm.
为此，我们面向高频度故障，提出了一个基于原测试流程的局部优化方法，并且还提出了一个以减少诊断所需探针操作次数为目标的启发式故障诊断算法。
In this paper, a local-optimization method oriented to frequently occurring faults is presented. A heuristic fault diagnosis algorithm with fewer probing operations is also discussed.
由于遗传算法的计算速度难以满足实时电压控制的要求，本文进行了基于原-对偶内点法的无功优化算法的研究。
Reactive power optimization based on interior point method is studied in this thesis as that GA's calculation speed can not satisfy the requirement of real time voltage control.
其中抗SPA攻击措施是本文提出的一种基于MOF编码并且能以较小的开销加入到原IP中的新算法。
Emphasis is paid on anti-SPA countermeasure which is based on MOF encoding and can be incorporated into the original IP with very low cost.
为此，提出一种基于分散式服务器的算法，通过对原数据进行分割编码来实现数据块的冗余存储。
This paper proposed decentralized Erasure Code to solve the problem. Redundant storage was achieved by the partition and encoding of the original data.
为此，提出一种基于分散式服务器的算法，通过对原数据进行分割编码来实现数据块的冗余存储。
This paper proposed decentralized Erasure Code to solve the problem. Redundant storage was achieved by the partition and encoding of the original data.
应用推荐