Evaluation and Construction of College Students’ Growth and Development Index System Based on Data Association Mining and Deep Learning Model

The rise of big data in the field of education provides an opportunity to solve college students’ growth and development. The establishment of a personalized student management mode based on big data in universities will promote the change of personalized student management from the empirical mode to the scientific mode, from passive response to active warning, from reliance on point data to holistic data, and thus improve the efficiency and quality of personalized student management. In this paper, using the latest ideas and techniques in deep learning such as self-supervised learning and multitask learning, we propose an open-source educational big data pretrained language model F-BERT based on the BERT model architecture. Based on the BERT architecture, F-BERT can effectively and automatically extract knowledge from educational big data and memorize it in the model without modifying the model structure specific to educational big data tasks so that it can be directly applied to various educational big data domain tasks downstream. The experiment demonstrates that Vanilla F-BERT outperformed the two Vanilla BERT-based models, Vanilla BERT and BERT tasks, by 0.0.6 and 0.03 percent, respectively, in terms of accuracy.

Analyzing a Decade of Wind Turbine Accident News with Topic Modeling

Despite the significance and growth of wind energy as a major source of renewable energy, research on the risks of wind turbines in the form of accidents and failures has attracted limited attention. Research that applies data analytics methodologically in this context is scarce. The research presented here, upon construction of a text corpus of 721 selected wind turbine accident and failure news reports, develops and applies a custom-developed data analytics framework that integrates tabular analysis, visualization, text mining, and machine learning. Topic modeling was applied for the first time to identify and classify recurring themes in wind turbine accident news, and association mining was applied to identify contextual terms associated with death and injury. The tabular and visual analyses relate accidents to location (offshore vs. onshore), wind turbine life cycle phases (transportation, construction, operation, and maintenance), and the incidence of death and injury. As one of the insights, more incidents were found to occur during operation and transportation. Through topic modeling, topics associated most with deaths and injuries were revealed. The results could benefit wind turbine manufacturers, service providers, energy companies, insurance companies, government bodies, non-profit organizations, researchers, and other stakeholders in the wind energy sector.

The butterfly effect in the price of agricultural products: A multidimensional spatial-temporal association mining

With the advent of the era of big data, data mining methods show their powerful information mining ability in various fields, seeking the association information hidden in the data, which is convenient for people to make scientific decisions. This paper analyses the butterfly effect in the agricultural product industry chain from the perspective of producer and consumer by using multidimensional time and space theory and proposes a new price forecasting method. We consider that the price change of agricultural products is not only affected by the balance of market supply and demand but also by the factors of time and space. Taking the pig industry chain of Sichuan Province as an example, this paper explores and excavates the data from 2010 to 2020 in the time dimension. Interestingly, we found that the price changes in pork in the market are generally highly correlated with the prices of slaughtered pigs, piglets a few weeks ago and the prices of multiple feed a few months ago. Based on the precise time-space factors, we improved the price forecasting model, greatly improved the accuracy of price prediction, and proved the effectiveness of multidimensional spatiotemporal association mining. The research in this paper is helpful to establish a brand-new agricultural product price prediction theory, which is of great significance to the development of the agricultural economy and global poverty alleviation.

Review of Association Mining Methods for the Extraction of Rules Based on the Frequency and Utility Factors

Association rule defines the relationship among the items and discovers the frequent items using a support-confidence framework. This framework establishes user-interested or strong association rules with two thresholds (i.e., minimum support and minimum confidence). Traditional association rule mining methods (i.e., apriori and frequent pattern growth [FP-growth]) are widely used for discovering of frequent itemsets, and limitation of these methods is that they are not considering the key factors of the items such as profit, quantity, or cost of items during the mining process. Applications like e-commerce, marketing, healthcare, and web recommendations, etc. consist of items with their utility or profit. Such cases, utility-based itemsets mining methods, are playing a vital role in the generation of effective association rules and are also useful in the mining of high utility itemsets. This paper presents the survey on high-utility itemsets mining methods and discusses the observation study of existing methods with their experimental study using benchmarked datasets.

Association mining based approach to analyze COVID-19 response and case growth in the United States

Containing the COVID-19 pandemic while balancing the economy has proven to be quite a challenge for the world. We still have limited understanding of which combination of policies have been most effective in flattening the curve; given the challenges of the dynamic and evolving nature of the pandemic, lack of quality data etc. This paper introduces a novel data mining-based approach to understand the effects of different non-pharmaceutical interventions in containing the COVID-19 infection rate. We used the association rule mining approach to perform descriptive data mining on publicly available data for 50 states in the United States to understand the similarity and differences among various policies and underlying conditions that led to transitions between different infection growth curve phases. We used a multi-peak logistic growth model to label the different phases of infection growth curve. The common trends in the data were analyzed with respect to lockdowns, face mask mandates, mobility, and infection growth. We observed that face mask mandates combined with mobility reduction through moderate stay-at-home orders were most effective in reducing the number of COVID-19 cases across various states.

An Enhanced Apriori with Interestingness of Patterns using cSupport and rSupport

Data mining is wide spreading its applications in several areas. There are different tasks in mining which provides solutions for wide variety of problems in order to discover knowledge. Among those tasks association mining plays a pivotal role for identifying frequent patterns. Among the available association mining algorithms Apriori algorithm is one of the most prevalent and dominant algorithm which is used to discover frequent patterns. An enhancement to Apriori algorithm is done i.e. Apriori2 which minimized the number of scans. In this research Apriori2 is modified by including rSupport or cSupport. Also includes the comparison of these variants of APRIORI along with the proposed.