The questionnaire survey method is adopted in this article to analyze the psychological factors influencing college students' consumption of mobile phone in west China, and the relationship between the college students' individual characteristic and the factors what they consider when they choose the mobile phone. Through the exploration, the influencing factors include the social attribute, the coherence, the novelty, and the reliability. Relative data are used to establish the NN model. By this model, the psychological prices of different types of mobile phone in college students could be distinguished, so manufactures could improve the products and implement the drumbeating based on that.
Submerged plant growth is limited by the reduction of underwater photosynthesis attributed to low CO2 availability, as well as light limitation associated with underwater conditions. Heterotrophic bacteria and fungi play an important role in local aqueous dissolved inorganic carbon (DIC) content surrounding submerged plants. In order to investigate the effects of carbon conversion in plant–microbe interactions on plant growth, in the present study we inoculated the plant medium of Vallisneria natans with Pseudomonas putida KT2440 and measured carbon conversion in the system, as well as several indices of plant growth. The quantity of P. putida KT2440 increased twofold because of the availability of organic matter produced by V. natans. Similarly, P. putida KT2440 supplied DIC for V. natans, improving its photosynthetic rate. Moreover, the significantly higher leaf area, specific leaf area and fresh biomass of V. natans attributed to the presence of P. putida KT2440 demonstrated that the interaction between V. natans and P. putida enhanced the efficiency of nutrient and CO2 uptake by V. natans, promoting V. natans growth. Therefore, we suggest that the carbon and oxygen microcycle based on the protocooperation of V. natans and P. putida KT2440 may accelerate the transformation of carbon to increase carbon availability to promote the growth of both plant and microbe.
In recent years, the development trend of artificial intelligence is getting better and better. It has been widely used not only in the fields of big data analysis, automobile automatic driving, intelligent robot and face recognition, but also in various fields of oil and gas industry. Oil and gas production prediction is an important part of reservoir engineering, which is very important for the future production and development of strata, and can give developers some development suggestions. At present, the methods used in oil and gas production prediction are mainly traditional means such as numerical simulation and history matching. With the application of artificial intelligence in various fields of oil and gas industry, the use of machine learning models for oil and gas production prediction has become the direction of development and research. This paper summarizes the basic process and main technical means of applying machine learning model to predict oil and gas production by investigating the research of domestic and foreign scholars on artificial intelligence in oil and gas production prediction in recent years. It provides ideas and lays a foundation for future researchers to study this aspect, and also contributes to the development of smart oil fields in the future.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.