Search

The complex interaction between emissions, meteorology, and atmospheric chemistry makes accurate predictions of particulate pollution difficult. Advanced data mining techniques can reveal potential laws, providing new possibilities for understanding the evolution and causes of air pollution. Based on the Granger method and block modeling analysis, this paper explored the intercity spillover effects of hourly PM2.5 in Hubei Province, China, to determine the specific role (i.e., overflow, limited overflow, bilateral, inflow, and limited inflow) of each city on regional pollution formation. Furthermore, a dynamic Apriori algorithm considering time-lag effects was used to mine the spatio-temporal associations of extreme PM2.5 pollution events among different cities. Results suggest that the northern and central cities with high-level PM2.5 concentration in Hubei have a significant spillover effect, whereas the eastern and southern cities generally play a role as the sink of pollutants. Based on the association rules of extreme PM2.5 pollution, four main pollutant transport channels were excavated and well matched with the trajectories extracted by the atmospheric model. This paper provides new insights for exploring the interaction of intercity particulate pollution, which is a supplement and cross-validation of the model results. [ABSTRACT FROM AUTHOR]

In order to improve the identification accuracy and shorten the analysis time of poor households in poverty alleviation, this paper studies a logistic regression analysis algorithm of targeted poverty alleviation based on mobile big data. Based on the theories related to big poverty alleviation data, Apriori algorithm is used to mine the basic information of households collected through mobile network based on Maslow's hierarchy of needs theory. A multi-dimensional item data of poverty detection is obtained by analyzing the frequent itemsets of association rules in poor areas, and the poverty characteristics of poor areas from different dimensions are analyzed. Taking the big data platform of targeted poverty alleviation in Jiangxi Province, China, as an example, the economic assistance data is selected and sent into the k-means algorithm to cluster by taking the village as the unit. Then, combined with the correlation of poverty characteristics, the abnormal phenomena in poverty alleviation are found, and the effectiveness of the targeted assistance to poverty alleviation target areas is analyzed. Based on nonlinear logistic regression, the identification model of poor households is built, and the Spark frame is used to extract, transform and read the characteristics of samples respectively. Finally, the poor households are identified with the logistic regression algorithm. Experimental results show that the average recognition accuracy of poor households reaches 92%, and the mining time of poverty feature analysis is only 18 s, which improves the efficiency of data analysis than current algorithms. [ABSTRACT FROM AUTHOR]

In recent years, the rapid development of the Internet has promoted the continuous expansion of the scale of China's tourism industry, and the amount of tourism data has surged. However, tourists need help bringing personal interest and high-value data from the plethora of tourism information. The rise of artificial intelligence has transformed traditional tourism into an intelligent, data-driven industry. This shift has generated vast tourism data, offering both opportunities and challenges. The paper discusses an AI and IoT-based Intelligent Tourism Recommendation System (ITRS) that offers travelers predefined itineraries, personalized suggestions, and tourism insights. This system simplifies attraction discovery, unveiling hidden value within tourism data at the intersection of AI and IoT. The present study thoroughly investigates AI-based recommendation algorithms before delving into the system's architecture. It categorizes user-based, project-based, and article-based collaborative filtering methodologies tailored to specific goals. First, thoroughly examine AI-based recommendation algorithms before delving into the system architecture. Second, categorize collaborative filtering methods as user-based, project-based, and article-based, each tailored to specific objectives. Third, delve into the Apriori algorithm's complexity within the context of weighted association rules and introduce an enhanced iteration for improved efficiency. The proposed scheme encompasses an elaborate ITRS plan featuring a user interest model and a client module, crucial for the computation and analysis of users' long-term and short-term interests. Rigorous performance testing confirms the ITRS's superiority across varying support levels, with experimental results demonstrating the Apriori algorithm's exceptional accuracy, achieving a 94.3% improvement over other methods. The Apriori algorithm is better than traditional recommendation algorithms such as Linear Regression, Logistic Regression, Decision Trees, Random Forest, Support Vector Machines, K-nearest neighbor, Naive Bayes, and XGBoost. [ABSTRACT FROM AUTHOR]

Identifying the environmental factors and analyzing the causal mechanism of flash floods help to manage the risk. Maximum 24-h precipitation (MP), digital elevation (DE), slope degree (SD), soil type (ST), drainage density (DD), and vegetation cover (VC) are selected as the risk factors of flash floods in this study. Precipitation is the important meteorological components in flash floods; thus spatial characteristics of precipitation trend have been analyzed by using Mann-Kendall tests, and a positive trend of precipitation in Upper Hanjiang River is detected. Then, association rule mining approach is proposed to investigate the multiple environmental factors of flash floods, in which both single and multiple dimension data mining have been conducted by Apriori algorithm. Considering the high rate of 5-year return period floods in the flash flood inventory, further association rule mining after sampling has been conducted in order to deeply mine the causal patterns of flash floods in different risk magnitudes. Results show that soil type, slope degree, and digital elevation are the dominant environmental factors of flash floods in the study area, and precipitation is one of the important causal factors in severe flash flood hazards. It is also highlighted that flash floods might easily occur even with a slight rainfall present due to the instability of sand clay and saturated soil moisture. The proposed novel use of field data and data mining has the potential for providing procedures and solutions for an effective interpretation of flash flood mechanism. The results are expected to be applicable for decision-making and sustainable management in flooding risk. [ABSTRACT FROM AUTHOR]

Several extensive landslides have occurred in the vicinity of the Three Gorges Reservoir since its initial impoundment in June 2003. A reduction of the landslide risk is essential for the safety and security of lives and property in the region. This study analyses the deformation states of two typical colluvial landslides (the Baijiabao and Laoshewo landslides) using 6 years of monitoring data, a two-step cluster analysis, and the Apriori algorithm. The landslide displacement versus time curves exhibit step-like patterns, and the landslide deformation is highly correlated with fluctuations in the reservoir level and seasonal precipitation. To determine different types of landslide deformation, the monthly displacement curves of the colluvial landslides are classified into three types using a two-step cluster analysis: initial deformation, constant deformation, and rapid deformation. Five driving factors were selected as the antecedents for the Apriori algorithm to obtain rules that describe the relationships between the landslide deformation and the influential parameters. These factors include the cumulative precipitation over the previous month, the maximum daily precipitation during the current month, changes in the reservoir level over the previous month, cumulative increases in the reservoir level and the average reservoir level during the current month. The analytical results were validated by comparing them with observed landslide deformation characteristics using three measurement standards: support, confidence and lift. The results show that the combined method of a two-step cluster analysis with the Apriori algorithm can effectively model the landslide deformation states that are associated with the Baijiabao and Laoshewo landslides. Moreover, this method may serve as a potential reference for deformation analyses of colluvial landslides in the Three Gorges. [ABSTRACT FROM AUTHOR]