ID 原文 译文
24895 然而由于事件驱动的数据是异步的且缺少一种统一的表示形式，在复杂的交通场景下，以车道检测为代表的基于事件驱动数据的交通场景分割任务难以应用传统的语义分割算法。 However, event-driven data is asynchronous and lacks a unified representation. At the same time, in the complex traffic scenario, the traditional semantic segmentation model is difficult to be applied to the event-driven data-based traffic scene segmentation task, for instance, the lane detection task.
24896 针对以上问题，本文提出了一种三通道的事件数据编码方式，综合考虑事件数据的时空特征，将其作为卷积神经网络的输入； In view of the above problems, our study proposes a three-channel encoding method for event data, which is successfully used as the input of convolution neural network by considering the spatio-temporal characteristics of event data comprehensively.
24897 提出了一种基于编解码模型的事件数据车道检测算法，在基于事件驱动的车道线检测数据集DET上，本文方法的mIoU（mean Intersection over Union）达到了58.76%，比基准方法提高了4.4%。 This paper also proposes a lane segmentation algorithm based on encoding-decoding model, which is superior to the traditional event-based lane line segmentation. On the DET data set, with mIoU (mean Intersection over Union) as the evaluation index, this paper reaches 58.76%, which is 4.4% higher than the benchmark.
24898 针对已有的异常检测模型在高维、样本多样(类内多样)的数据背景下无法获得合理的潜在表示分布，不平衡数据较多(正常数据远大于异常数据)时特征提取准确性低，以及分类器超参数敏感等问题，本文提出一种基于深度对抗学习潜在表示分布的异常检测模型。 To solve the problems of the existing anomaly detection models, such as incoherent latent representation distribution under in high-dimensional and diverse (within each class) data background, the low accuracy of feature extraction when unbalanced data (normal data far outweighs abnormal data) is large, and the sensitivity of classifier' s hyperparameter, a deep adversarial learning latent representation distribution model for anomaly detection is proposed.
24899 基于正则化约束改进自编码器，将数据的原始特征空间映射到潜在特征空间形成低维的潜在表示，使其保持合理的空间分布； Based on the regularization constraint, an improved autoencoder can map the original data feature space to a low-dimensional the latent feature space to get the reasonable latent representation distribution.
24900 配以基于多判别器的生成对抗网络，在有效避免重构特征循环不一致和训练不稳定的基础上，来精确估计潜在表示的概率分布；以获得的潜在表示概率分布为单类分类器的输入，解决单类分类器超参数敏感问题，从而有效提高异常检测的整体性能。 On the premise of avoiding the problems of circulation inconsistent of reconstruction feature and unstable training, the multi-discriminator-based generative adversarial network can evaluate the latent representation probability distribution accurately, and to solve the hyperparameter sensitivity of one class classifier, so as to improve the overall performances of anomaly detection.
24901 实验结果表明，相比于最新的基于机器学习和深度学习的异常检测模型，本文模型可在高维、样本多样、不平衡数据较多的应用背景下获得更合理的潜在表示空间分布并有效估计其概率分布，对单类分类器的超参数不敏感，并有效提高模型的检测性能。 Experimental results show that, compared with the up-to-date anomaly detection models based on machine learning and deep learning, the proposed model can obtain more coherent space distribution and ideal probability distribution of latent representation, is not sensitive to the hyperparameters of the single-classclassifier, and effectively improve the detection performances under the application background with high-dimensional, diverse, unbalanced data.
24902 针对智慧照明可靠性要求高、通信数据量小的特点,本设计提出一种基于导通角调制的电力线通信技术。 Aiming at the characteristics of high reliability of the intelligent lighting technique with limited communication data, a power line communication technology based on the conduction angle modulation is proposed.
24903 利用斩波技术调制工频波形的导通角,并将调制后的工频波形在电力线上传输。 The chopper technology is used to modulate the conduction angle of the power waveform and transmit the modulated power waveform on the power line.
24904 本设计的编码方式是将完整工频波形设为信号“0”,斩波波形设为信号“1”,一帧数据包含 24位信号。 The principle of the coding in the design is simple and distinctive, in which a complete power waveform corresponding to signal "0", while the chopped waveform relating to signal "1". One frame data contains 24 bit signal.