Industrial Internet of Things (IIoTs) are producing massive data, which are valuable for knowing running status of the underlying equipment. However, these data involve various operation events that span some time, which raise questions on how to model long memory of states, and how to predict the running status based on historical data accurately. This paper aims to develop a method of (1) analyzing equipment working condition based on the sensed data; (2) building a prediction model for working status forecasting, and designing a deep neural network model to predict equipment running data; (3) improving the prediction accuracy by systematic feature engineering and optimal hyperparameter searching. We evaluate our method with real-world monitoring data collected from 33 sensors of a main pump in a power station for 3 months. The model achieves less root mean square error than that of ARIMA. Our method is applicable to general IIoT equipment for analyzing time series data and forecasting operation status.

Real-time intelligent video processing on embedded devices with low power consumption can be useful for applications like drone surveillance, smart cars, and more. However, the limited resources of embedded devices is a challenging issue for effective embedded computing. Most of the existing work on this topic focuses on single device based solutions, without the use of cloud computing mechanisms for parallel processing to boost performance. In this paper, we propose a cloud platform for real-time video processing based on embedded devices. Eight NVIDIA Jetson TX1 and three Jetson TX2 GPUs are used to construct a streaming embedded cloud platform (SECP), on which Apache Storm is deployed as the cloud computing environment for deep learning algorithms (Convolutional Neural Networks - CNNs) to process video streams. Additionally, self-managing services are designed to ensure that this platform can run smoothly and stably, in the form of a metric sensor, a bottleneck detector and a scheduler. This platform is evaluated in terms of processing speed, power consumption, and network throughput by running various deep learning algorithms for object detection. The results show the proposed platform can run deep learning algorithms on embedded devices while meeting the high scalability and fault tolerance required for real-time video processing.

During the novel coronavirus pneumonia, the underlying comments and news of the epidemic had bombed on the Internet media and social networks, reflecting the views and attitudes of the governments, society, and individuals to the epidemic situation. Those comments are closely related to people's lives and blend with each other. Novel coronavirus pneumonia affects people's lives, and they publish comments on social networks and media, and the underlying information from social networks and Internet media in turn affects people's attitude to the epidemic and the measures, and strategies taken to fight coronavirus in life. We collect the comments from various social network platforms and network media such as Weibo, WeChat, Chinanews, Sina News, NetEase News, Sohu News, and analyze the overall situation of public opinion on the novel coronavirus pneumonia. We explore the interaction between online public opinion and real life using a variety of algorithms in different stages of the epidemic. We can obtain public attention and key nodes in the dissemination of public opinion by detecting hot events and calculating user's influence. The analysis of information dissemination path is conducive to the rapid propagation of healthy comments, curbing the spread of bad information. Event-specific details and topics are mined from large amounts of comments by thematic clustering and association relationship detecting, which helps to provide technical support for government response measures. The emotional analysis of Internet users' groups helps to guide the direction of public opinion. The situation analysis shows the deep blending and mutual influence between the online public opinion and the real world.

People can post their comments on public events on the Internet, such as their ideas, emotions, and attitudes that can affect others. Online public opinions may affect the stability or security of the country because of the speed and convenience of information disseminating on the Internet. This article proposes the public opinion cellular automata for situation deduction to predict the possible trending of public events. In the cellular automata, online users are represented by cells, and their eigenvalues are calculated from the user's historical comment data. The cell and their neighbors form a cellular space, whose topology is a directed graph. We set the state of each cell based on its attributes and initialize the cellular automata. The automata can deduce public opinion and predict the trend of public opinion by following the set evolutionary rules in advance. Experiments with the real data from Sina Weibo online users show that the cells in the cellular automata can accurately simulate users' behavior, and the deduction results are close to the trend of real historical events. The cellular automata-based prediction of the number of participants and emotional trending are more accurate than other methods.