ID 原文 译文
17715 相关实验表明，该译码系统在不同信噪比、不同码速、信号出现频率漂移以及不同发报手法引起的码长偏差等情况下，均能取得较好的识别效果，性能优于传统的自动识别算法。 Related experiments show that the decodingsystem can achieve good recognition results under different signal-to-noise ratio, code rate, frequency drift andcode length deviation caused by different sending manipulation, and the performance is better than thetraditional recognition algorithms.
17716 极限学习机(ELM)具有学习速度快、易实现和泛化能力强等优点，但单个ELM的分类性能不稳定。 Extreme Learning Machine (ELM) has unique advantages such as fast learning speed, simplicity of implementation, and excellent generalization performance. However, the performance of a single ELM is unstable in classification.
17717 集成学习可以有效地提高单个ELM的分类性能，但随着数据规模和基ELM数目的增加，计算复杂度会大幅度增加，消耗大量的计算资源。 Ensemble learning can effectively improve the classification ability of single ELMs,but it may incur the rapid increase in memory space and computational overheads as the increase of the datasize and the number of ELMs.
17718 针对上述问题，该文提出一种基于双错测度的极限学习机选择性集成方法(DFSEE)，同时从理论和实验的角度进行了详细分析。 To address this issue, a Selective Ensemble approach of ELM based on Double-Fault measure (DFSEE) is proposed, and it is evaluated by theoretical and experimental analysissimultaneously.
17719 首先，运用bootstrap 方法重复抽取训练集，获得多个训练子集，在ELM上进行独立训练，得到多个具有较大差异性的基ELM，构成基ELM池； Firstly, multiple training subsets extracted from a training dataset are obtained employing thebootstrap sampling method, and an initial pool of base ELMs is constructed by independently training multipleELMs on different training subsets;
17720 其次，计算出每个基ELM的双错测度，将基ELM按照双错测度的大小进行升序排序； Secondly, the ELMs in pool are sorted in ascending order according to theirdouble-fault measures of those ELMs.
17721 最后，采用多数投票算法，根据顺序将基ELM逐个累加集成，直至集成精度最优，即获得基ELM最优子集成，并分析了其理论基础。 Finally, it starts with one ELM and grows the ensemble by adding newbase ELMs according to the order, the final ensemble of ELMs can be achieved with the best classificationability, and the theoretical basis of DFSEE is analyzed.
17722 在10个UCI数据集上的实验结果表明，较其他方法使用了更小规模的基ELM，获得了更高的集成精度，同时表明了其有效性和显著性。 Experimental results on 10 benchmark classificationtasks show that DFSEE can achieve better results with less number of ELMs by comparing with otherapproaches, and its validity and significance.
17723 大规模多输入多输出技术作为第5代通信系统的关键技术，可有效提高频谱利用率。 As a key technology of the fifth generation communication system, large-scale Multi-Input and Multi-Output(MIMO) technology can effectively improve spectrum utilization.
17724 基站端采用消息传递检测(MPD)算法可以实现良好的检测性能。 The base station side uses the MessagePassing Detection (MPD) algorithm to achieve good detection performance.