ID 原文 译文
45916 从基于大数据的智能决策角度研究智能空气指数预测，引入流行的分类算法，挖掘历史数据隐含的信息，实现空气质量预测； The intelligent forecasting of air index was studied from the perspective of big data and intelligent decision making. For the index prediction of air quality, the popular classification algorithm was introduced to realize the intelligent analysis of historical data.
45917 构建了基于物联网的空气质量监测系统，利用分类算法实现实时采集数据的智能处理。 To obtain air quality information in real time, a monitoring system based on Internet of Things was established, and intelligent processing of real-time data collected by the classification algorithm was achieved.
45918 针对空气指数历史数据和实时采集数据规模较大的问题，为提高数据处理速度、增强空气质量预测的实时性，引入云计算技术加速数据处理； Due to the large amount of historical air index data and real-time data collected, the technology of cloud computing and big data was introduced to speed up the data processing and improve the storage of data.
45919 为使用户随时随地了解空气指数，还设计了基于 Android 平台开发空气指数预报客户端。 In addition, the client-based on Android was developed to allow users to query the air quality anytime, anywhere.
45920 通过迁移深度神经网络在图像识别方面的经验，提出了一种基于 Inception 神经网络和循环神经网络结合的深度学习模型（InnoHAR），该模型端对端地输入多通道传感器的波形数据，利用 1×1 卷积对多通道数据的有机组合，不同尺度的卷积提取不同尺度的波形特征，最大池化过滤微小扰动造成的假阳性，结合时间特征提取（GRU）为时序特征建模，充分利用数据特征完成分类任务。 The experience from computer vision was learned, an innovative neural network model called InnoHAR (inception neural network for human activity recognition) based on the inception neural network and recurrent neural net-work was put forward, which started from an end-to-end multi-channel sensor waveform data, followed by the 1×1 convolution for better combination of the multi-channel data, and the various scales of convolution to extract the waveform characteristics of different scales, the max-pooling layer to prevent the disturbance of tiny noise causing false positives,combined with the feature of GRU helped to time-sequential modeling, made full use of the characteristics of data classification task.
45921 相比已知最优的神经网络模型，在识别准确度上有近 3%的提升，达到了 state-of-the-art 的水平，同时可以保证低功耗嵌入式平台的实时预测，且在网络结构组成上更加丰富，具有更大的潜力和挖掘空间。 Compared with the state-of-the-art neural network model, the InnoHAR model has a promotion of 3% in the recognition accuracy, which has reached the state-of-the-art on the dataset we used, at the same time it still can guarantee the real-time prediction of low-power embedded platform, also with more space for future exploration.
45922 提出了一种新的无拓扑结构的社交网信息传播模型，简称 NT-II，并使用表达学习方式，构建了 2 个隐藏的空间： A new non-topological information diffusion model of social network was proposed, called non-topological influency-interest diffusion model (NT-II).
45923 用户影响空间和用户兴趣空间，每个用户和每个传播项都映射成空间中的向量。 Representation learning was exploited to construct two hidden spaces for NT-II，called the user-influence space and the user-interest space, each user and each propagation item was mapped into a vectoring space.
45924 模型在预测用户接收传播项的概率时，既考虑来自其他用户的影响程度，又考虑该用户对传播项的喜爱程度，分别根据 2 个用户向量之间的距离和用户向量和传播项向量之间的距离来推断。 The model predicted the probability of a user receiving a propagated item, considering not only the degree of influence from other users, but also the user's preference for propagated item.
45925 实验结果表明：NT-II 模型能更准确地模拟传播过程和预测传播结果。 The experimental results show that the model can simulate the propagation process and predict the propagation results more accurately.