A method of establishing a prediction model of the greenhouse temperature based on time-series analysis and the boosting tree model is proposed, aiming at the problem that the temperature of a greenhouse cannot be accurately predicted owing to nonlinear changes in the temperature of the closed ecosystem of a greenhouse featuring modern agricultural technology and various influencing factors. This model comprehensively considers environmental parameters, including humidity inside and outside the greenhouse, air pressure inside and outside the greenhouse, and temperature outside the greenhouse, as well as time-series changes, to make a more accurate prediction of the temperature in the greenhouse. Experiments show that the R2 determination coefficients of different prediction models are improved and the mean square error and mean absolute error are reduced after adding time-series features. Among the models tested, LightGBM performs best, with the mean square error of the prediction results of the model decreasing by 18.61% after adding time-series features. Comparing with the support vector machine, radial basis function neural network, back-propagation neural network, and multiple linear regression model after adding time-series features, the mean square error is 11.70% to 29.12% lower. Furthermore, the fitting degree of LightGBM is the best among the models. The prediction results of LightGBM therefore have important application value in greenhouse temperature control.

Abstract. The limitations of Shannon information theory are pointed out from new perspectives. The limitations mainly exist in the neglects of the information reliability and completeness. The significances of the information reliability to the information measurements are further illustrated through example analysis. It is pointed out that such limitations originate from neglects of multilevel information uncertainties, uncertainty of the model and other objects of information system, and insufficient knowledge on uncertainties of probability values.Keywords: information theory, communication, reliability, model, uncertainty, probability. IntroductionShannon information theory is aimed at the communication issues, and is not quite necessarily applicable to the information issues in the reality [1], and his infor-mation theory is called the special information theory by the later researchers. Aimed at the general information, some researchers have developed comprehensive information theory, generalized information theory, unified information theory etc [2][3][4][5], in which some limitations of the special information theory are identified, but no one of these information theories can eliminate all the limitations of information theories. In this paper, we attempt to analyze the limitations of the special information theory from some new perspectives. Limitations of Shannon Information Theory in the RealityThe currently recognized limitations of Shannon information theory are mainly as follows: Firstly, only the random uncertainty is considered in his information theory, while the uncertainties such as the limitations of sets in information expressions and the information fuzziness etc are not considered. Aimed at this issue, some researchers have developed the theories of fuzzy sets and rough sets. Secondly, neither the semantic nor the pragmatic aspects are considered in Shannon information theory,

The rapid development of mobile technology has brought the change of learning. Mobile learning refers to a new kind of learning for the use of wireless communication technologies and mobile equipments to obtain the educational information, resources, and services. The framework of mobile learning system using wireless communication technology is proposed, a mobile learning support system with multiple wireless terminals is implemented which customs communication protocol to communicate with each other and uses multi-threading technology. The server push learning content to the terminal, learners receive information or to send information to the server through wireless terminal, to feedback information and interaction, and server processes terminal information, data analysis, and then sent to the learner. The system can be applied to a variety of mobile learning occasions, the application shows that the effect of the system effectively reduce the learning environment, and to increase the participation and interest of the learner, improve learning efficiency and learning outcomes.

Traditional collaborative filtering recommendation algorithms only consider the interaction between users and items leading to low recommendation accuracy. Aiming to solve this problem, a graph convolution collaborative filtering recommendation method integrating social relations is proposed. Firstly, a social recommendation model based on graph convolution representation learning and general collaborative filtering (SRGCF) is constructed; then, based on this model, a social relationship recommendation algorithm (SRRA) is proposed; secondly, the algorithm learns the representations of users and items by linear propagation on the user–item bipartite graph; then the user representations are updated by learning the representations with social information through the neighbor aggregation operation in the social network to form the final user representations. Finally, the prediction scores are calculated, and the recommendation list is generated. The comparative experimental results on four real-world datasets show that: the proposed SRRA algorithm performs the best over existing baselines on Recall@10 and NDCG@10; specifically, SRRA improved by an average of 4.40% and 9.62% compared to DICER and GraphRec, respectively, which validates that the proposed SRGCF model and SRRA algorithm are reasonable and effective.

No abstract