ID 原文 译文
58088 针对异常声音识别率低和算法复杂度高等技术难题，提出了一种基于粒子群优化粒子滤波( PSO-PF) 算法优化支持向量机( SVM) 的识别方法. In order to solve the problems of low recognition accuracy and high computation complexity inabnormal sound signals，a particle filter based on particle swarm optimization ( PSO-PF) algorithm is proposed to optimize the parameters of support vector machine ( SVM) .
58089 将 PSO 算法引入粒子滤波中，通过不断更新粒子速度和位置，使粒子群向高似然后验概率区域移动，提高粒子滤波的参数估计精度. To improve the estimation precisionof particle filter，the particle swarm optimization is applied to drive all the particles to the regions inwhich their likelihoods are high，by updating the velocity and position of particles constantly.
58090 将 PSO-PF 算法应用于 SVM 参数优化中，可解决现有 SVM参数优化算法易陷入局部最优值等问题. And the algorithm can avoid falling into local optimum in SVM parameter optimization.
58091 实验结果表明，将所提方法应用于多类异常声音识别，能够有效提高识别率，降低算法复杂度. The experimental resultsshow that the new algorithm can achieve higher recognition accuracy and lower computation complexity forabnormal sounds recognition.
58092 针对车联网中车辆间相遇机会间隔的统计分布模型及其参数估计问题，基于北京市出租车轨迹大数据，提出了基于栅格划分和地理哈希值索引的过滤查找方法和轨迹内插方法以高效提取车辆间的相遇机会时刻，进而对机会间隔进行统计建模、参数估计和假设检验. As a kind of opportunistic networks，the vehicle network，in which vehicles communicate instantaneously with each other only when they meet opportunely，attracts more and more attentions. Theinter-contact times of communication opportunities depend on the factors such as the vehicle moving model and the vehicle density. Based on the data of the taxi traces in Beijing city，an efficient method whichcombines the GeoHash-based filter and the trace interpolation is proposed to extract all the instants of thecommunication opportunities to model the statistical distribution.
58093 模型呈现分段分布，在小尺度时间间隔上呈指数分布，在大尺度间隔上呈对数正态分布，并具有重尾特征. It is concluded that the inter-contacttimes obey an exponential distribution if the interval is small while a log-normal one if the interval islarge. Such a piecewise heavy-tailed distribution will affect the design of the vehicle networks to some extent.
58094 提出了一种基于胶囊的英文文本蕴含识别方法. An English textual entailment recognition method using capsules is presented.
58095 分别为每一种蕴含关系构建一个胶囊，用于模拟此蕴含关系的识别，并将其指定为该胶囊的属性. This methodbuilds a capsule for each relationship to model the recognition of this relationship and assigns it as the attribute of the capsule.
58096 给定两段文本，经过 highway 编码层和序列编码层获取语义表示，分别输入胶囊中，依次通过其内部的交互模块、比较模块和聚合模块. Given two texts，they are first encoded by highway encoding layer and sequenceencoding layer to obtain the semantic representations，and then fed into each capsule，passing through itsinternal interaction module，comparison module and aggregation module in turn.
58097 交互模块利用交互注意力机制提取文本间的局部交互特征，比较模块和聚合模块使用前馈神经网络进行语义信息比较和聚合. The interaction moduleuses the inter-attention mechanism to extract local interactive features between texts. The comparisonmodule and the aggregation module use the feedforward network to compare and aggregate the semanticinformation.