Mining Model Research Articles

Educational data mining model using support vector machine for student academic performance evaluation

Educational data mining model using support vector machine for student academic performance evaluation

An Advanced Approach for Geometallurgical Modeling Applied to Bauxite Mines

Geometallurgy is an approach that integrates geology, mining, processing, and environmental areas, aiming to increase knowledge of the deposit and reduce risks in mining projects and/or operations. Growing changes in economic and operational scenarios require the development of robust models for metallurgical responses. Typically, the population of geometallurgical variables is small, and there are restrictions on applying geostatistical techniques, such as Ordinary Kriging, since recoveries are considered non-additive variables. This study used multiple linear regression to develop a geometallurgical model for a bauxite mine. The developed models enabled reconciliation with real results, and this application for bauxite mining represents a novelty in the literature. The model estimated the mass recovery in the coarse fraction with an accuracy greater than 97%. Additionally, the geometallurgical model developed for Mineração Rio do Norte (MRN) allows predictability and mapping potential product quality deviations.

Prediction of ketosis using radial basis function neural network in dairy cattle farming.

The purpose of the paper was to apply an Artificial Neural Networks with Radial Basis Function to develop an application model for diagnosing a subclinical ketosis type I and II in dairy cattle. While building the neural network model, applied methodology was compatible to the procedures used in Data Mining processes.The data set was created based on the composition of milk samples of 1520 Polish Holstein-Friesian cows. The milk samples were collected during test-day milkings and made available by Polish Federation of Cattle Breeders and Milk Producers. The milk composition parameters were used as the input variables for RBF network models. The value of the output variable was determined based on the content of β-hydroxybutyric acid in blood of cows. In the next stage of the work, the qualities of the pre-selected models were compared and the best ones were chosen. The sensitivity and specificity as well as the size of the AUC (Area Under the Curve) under the ROC (Receiver Operating Characteristic) were taken as the main criteria for network models evaluation. The model characterized by sensitivity of 0.86, specificity of 0.71 and AUC of 0.89 was selected for ketosis type I. The optimal for ketosis type II showed the sensitivity and specificity 0.81 and 0.75, respectively, and the size of AUC above 0.85. Chosen models were recorded using the predictive modelling markup language (PMML) for data mining models to be shared and used between the different applications.

The Application of Data Mining Models in Personal Credit Risk Control

This study employs LendingClub data in the field of personal credit risk control as an illustrative case. Various data mining models, and support vector machine, are utilized for training purposes. Additionally, a Stacking model is integrated into the analysis to forecast customer default likelihood. Subsequently, lending decisions are made in accordance with these predictions. The outcomes indicate a reduction in customer default rates compared to scenarios without the application of data mining models, thereby achieving our goal of risk control.

Assessing the nexus of label content and consumer reviews: insights from premium wines on Vivino

Purpose This study aims to explore the relationship between wine label content and consumer reviews on Vivino, focusing on how label information compares to consumer perceptions and purchase decisions. Design/methodology/approach The research uses text mining, image mining and topic modeling techniques to analyze a data set of 444 highly rated Portuguese wines and 993,945 consumer reviews from Vivino. It examines the overlap between topics discussed in consumer reviews and the information provided on wine labels. Findings The findings reveal that wine labels have a limited similarity with consumer reviews. While consumer reviews primarily emphasize sensory characteristics like fruitiness and tannins, wine labels focus more on descriptive and technical information. Originality/value This research provides new insights into the dynamic relationship between wine labeling and consumer behavior. By analyzing the alignment between traditional wine labels and online consumer reviews, the study offers valuable implications for wineries seeking to optimize label design to match consumer preferences, particularly sensory attributes better. This study extends existing research and highlights critical gaps in how wine labels convey essential sensory information to consumers.

Intelligent Personalized Tourism Recommendation Based on Optimized Unsupervised Multi Implicit Semantic Trajectory Mining Model

Intelligent Personalized Tourism Recommendation Based on Optimized Unsupervised Multi Implicit Semantic Trajectory Mining Model

Exploring the General and Educational Use of the Metaverse: Public Perspectives, Sentiments, Attitudes, and Discourses

This study examines and analyzes the public perspectives, attitudes, sentiments, and discourses regarding the metaverse and its general and educational use. The study explores four research questions and involves the analysis of two datasets containing over 8 million tweets from Twitter (currently called X). The analysis involves text mining, sentiment analysis, and topic modeling techniques and to carry it out different tools are used, such as the National Research Council Canada (NRC) Word-Emotion Association Lexicon (EmoLex), Valence Aware Dictionary for Sentiment Reasoning (VADER), TextBlob, Latent Dirichlet Allocation (LDA), etc. Based on the results, the increase in interest of the public in the metaverse is in line with that of the educational and scientific communities. The public expressed mostly positive attitudes and emotions toward the general and educational use of the metaverse while the negative sentiment percentage was really low. The sentiments and emotions were more intense within the tweets of the educational dataset. The versatility and applicability of the metaverse emerged from the topic analysis from which eight topics arose: digital currencies, virtual environments, gaming, education, immersive learning environments, entertainment, online communities, and industry. The increasing interest in the metaverse, its potentials to enrich education, and the positive attitudes of the public toward its use in education were evident. More intense emotions and sentiments were expressed in the educational dataset which indicates that impulsive decisions may occur and should be anticipated in the educational domain and that the educational community is open to new approaches and supports technology-enhanced learning. Social media arose as an effective medium to communicate the integration of new technologies and innovations in education.

Effect of positive emotions on perceiving dating violence as affection

Research has found that when an individual is subject to controlling behavior (dating violence), the victim can sometimes interpret it as an expression of affection. This study clarified the positive emotions that may arise when university students are subjected to controlling behavior from their dating partners and the effects of these emotions on their interpretation of the behavior as an expression of affection. A survey of Japanese university students was conducted and the results were analyzed using text mining and structural equation modeling. Three positive emotions were found to influence the interpretation of controlling behavior as an expression of affection. Moreover, traditional gender roles influenced these pathways. The results offer insights that enable professionals working in the field to better understand victims’ feelings and provide appropriate support.

Research on the realization path of open public health data in China

Purpose/Significance Public health data is an important part of China's public data. It can help improve China's public data open system, realize the value that public health data should have, and achieve the goal of “building a community of shared future for human health” as soon as possible. Method/Process Using the topic mining model, the bibliographic information related to “public health data openness” in the CNKI and WOS is processed to find the influencing factors that affect the realization of public health data openness. Secondly, the mutual influence relationship between these factors is found, and using system dynamics, a causal relationship diagram and a system flow diagram are constructed to simulate and analyze the value realization model of China's public health data openness, and then the value realization path of China's public health data openness is summarized. Result The causal relationship diagram mainly includes four types of circuits, and 43 equation designed models have been determined through multiple simulation simulations. At the 22nd month, the value of “public health data” began to gradually emerge. At the same time, the slope of the line between “data security” and “timely response to data concerns” is also rapidly increasing. In the fourth month, the value of “public health data” remained relatively low and stable. Conclusion The realization path of China's public health data openness can be carried out from three aspects, namely, the “safety standards” on the supply side, the “quality and quantity of citizens” on the demand side, and the improvement of the relevant supervision mechanisms that connect the supply and demand sides, so as to effectively tap the potential value of China's public health data.

Online comments of tourist attractions combining artificial intelligence text mining model and attention mechanism

This paper intends to solve the limitations of the existing methods to deal with the comments of tourist attractions. With the technical support of Artificial Intelligence (AI), an online comment method of tourist attractions based on text mining model and attention mechanism is proposed. In the process of text mining, the attention mechanism is used to calculate the contribution of each topic to text representation on the topic layer of Latent Dirichlet Allocation (LDA). The Bidirectional Recurrent Neural Network (BiGRU) can effectively capture the temporal relationship and semantic dependence in the text through its powerful sequence modeling ability, thus achieving a more accurate classification of emotional tendencies. In order to verify the performance of the proposed ATT-LDA- Bigelow model, online comments about tourist attractions are collected from Ctrip.com, and users’ emotional tendencies towards different scenic spots are analyzed. The results show that this model has the best emotion classification effect in online comments of scenic spots, with the accuracy and F1 value reaching 93.85% and 93.68% respectively, which is superior to other emotion classification models. The proposed method not only improves the accuracy of sentiment analysis, but also provides strong support for the optimization of tourism recommendation system and provides more comprehensive, objective and accurate tourism information for scenic spot managers and tourism enterprises. This achievement is expected to bring new enlightenment and breakthrough to the research and practice in related fields.

Configuration path identification of investment risk in China's overseas energy projects: An exploration based on LDA and fsQCA

AbstractChina's overseas energy investment is subject to various risks and uncertainties. This study uses the latent Dirichlet allocation (LDA) model for text mining to comprehensively identify risk factors for overseas energy project investment. Then, we utilize fuzzy set qualitative comparative analysis (fsQCA) to explore the configuration path of risk based on 25 overseas energy project investment cases. The results show that there are six categories of investment risks in overseas energy projects, namely: political risk, economic risk, resource risk, environmental risk, social risk, and national relations risk. The occurrence of a single risk is insufficient to cause an investment in an overseas energy project to fail. Rather, it is only when multiple risks occur together and act in concert that the project is disadvantaged. The configuration paths of risk can be categorized into four types, which are geopolitical dominance type, socio‐economic dominance type, resource‐environment dominance type, and comprehensive type. From a holistic perspective, this study examines the cumulative impact of multiple risk factors on the investment effect of energy projects, illustrating the inherent complexity of investment risks associated with overseas energy projects. This study provides direction for investors and policymakers to develop effective risk management programs and sound investment strategies.

AI for Good: History, Open Data and Some ESG-based Applications

ABSTRACT This paper investigates the notion of artificial intelligence (AI) for good. As part of that analysis, this paper reviews what is meant by AI for Good, and traces some of the history associated with the term. The paper also briefly reviews open data and the integration of open data, AI for text mining and large language models. That analysis helps to use AI in some applications based on environment, social and governance issues (ESG). As part of that analysis, we drill down on three applications illustrating some approaches to AI for Good, (i) examining development of a carbon pollution dictionary, (ii) building an interface to 311 open data to improving communication with citizens and (iii) using AI to facilitate monitoring of government purchases. In so doing, we also generate some methodological approaches to addressing those issues and stress an important link between organisations’ open data and newly emerging AI capabilities.

Application of Transformer Models for Advanced Process Optimization and Process Mining

Application of Transformer Models for Advanced Process Optimization and Process Mining

Occupational health risk assessment and risk monetization based on xylene exposure.

The risk evaluation of occupational exposure to xylene was conducted to provide a basis for the formulation of policies on the prevention and control of occupational hazards of xylene and to fill the gap in this field. In this study, a number of xylene-related companies in seven industries from 2020 to 2023 were collected as research subjects, and the health risks caused by xylene exposure were evaluated using the EPA model designated by the U.S. Environmental Protection Agency, the Singapore Semi-Quantitative Risk Assessment Model (MOM), and the International Council on Mining and Metals (ICMM) Occupational Health Risk Assessment Model. Subsequently, a risk monetization method was used to convert the health risks of xylene exposure into currency. the results of the study showed that the EPA and MOM models were more reasonable and could accurately identify occupational health risks due to xylene exposure, while the ICMM model overestimated the health risks due to xylene exposure by assessing the risk level of all industries as level 4 or higher. Incorporating the number of people on the job into the risk assessment can differentiate the number of people involved in the health risks caused by xylene exposure, which is more conducive to the adoption of targeted preventive and control measures. The risk monetization model can provide a more intuitive view of the direct economic losses that may be caused by occupational exposure to xylene, which can help the relevant authorities to formulate strategies for the prevention and control of xylene hazards, and also provide a strong support for occupational damage compensation.

Predicting the structure and stability of oxide nanoscrolls from dichalcogenide precursors

Low-dimensional nanostructures such as nanotubes, nanoscrolls, and nanofilms have found applications in a wide variety of fields such as photocatalysis, sensing, and drug delivery. Recently, it was demonstrated that nanoscrolls of Mo and W transition metal oxides, which do not exhibit van der Waals (vdW) layering in their bulk counterparts, can be successfully synthesized using plasma processing of corresponding layered transition metal dichalcogenides. In this work, we employ data mining, first-principles simulations, and physio-mechanical models to theoretically examine the potential of other dichalcogenide precursors to form oxide nanoscrolls. By data mining bulk and two-dimensional materials databases, we first identify dichalcogenides that would be mostly amenable to plasma processing based on their vdW layering and thermodynamic stability. To determine the propensity for forming a nanoscroll, we develop a first-principles simulation-based physio-mechanical model to determine the thermodynamic stability of nanoscrolling as well as the equilibrium structure of the nanoscrolls, that is, their inner radius, outer radius, and interlayer spacing. We validate this model using experimental observations and find excellent agreement for the equilibrium nanoscroll structure. Furthermore, we demonstrate that the model’s energies can be utilized for a generalized quantitative categorization of nanoscroll stability. We apply the model to study oxide nanoscroll formation in MoS2, WS2, MoSe2, WSe2, PdS2, HfS2, and GeS2, paving the way for a systematic study of oxide nanoscroll formation atop other dichalcogenide substrates.

A feature mining model for financial product purchase behaviour data based on consumer behaviour perspective

A feature mining model for financial product purchase behaviour data based on consumer behaviour perspective

A feature mining model for financial product purchase behaviour data based on consumer behaviour perspective

A feature mining model for financial product purchase behaviour data based on consumer behaviour perspective

Similar pipeline experiment and disaster control emergency plan of updraft airflow fire in mine

Based on the engineering example of Linsheng coal mine, this paper uses TF1M3D computer simulation platform to systematically analyze the process of smoke flow spreading and air flow disorder disaster from the perspective of the whole mine network, and puts forward corresponding plans and measures. A small scale similar experiment was carried out to study the updraft flow fire in the mine. Through the analysis of the collected experimental data, the variation law of the air volume of the fire source in the main air path, side branch road and total air path with different air volume and the variation characteristics of the temperature at the monitoring point with time were obtained under different air volume conditions, and the critical air volume was fitted as 1.65 m3·s− 1. The CAD digital stereoscopic model of Linsheng mine was established, and the TF1M3D simulation platform was used to simulate the mine fire under normal ventilation condition. The preset fire source point of the conveyor belt roadway in the first west district of Linsheng coal mine was used to observe the change of air volume during the fire process.The smoke flow reversal phenomenon would occur when the fire occurred in the first west district. The reversed smoke flow will flow to the 503 face and cause contamination. In order to inhibit the reversal of smoke flow, the emergency plan is proposed to increase the number of fan rotation and set fire doors in appropriate places, which can effectively inhibit the diffusion of smoke and improve mine disaster resistance.

Detection of β - Thalassemia Carriers using Data Mining Techniques

Thalassemia, a genetic blood disorder, presents a significant challenge in Sri Lanka due to its high prevalence. Traditional methods of identifying tha-lassemia carriers, such as genetic and blood testing, are both costly and time-consuming, and potentially not available for certain demographic groups. However, there haven’t been many studies done on the efficacy of data mining models for thalassemia carrier detection, therefore the field is still in its in fancy. As such, evaluating their accuracy and utility in clinical practice is crucial. This study aims to develop a time-efficient model to detect the β-thalassemia carriers, which can reduce the time to take a decision and develop the built model as a decision support tool. Eight blood parameters - includ-ing RBC, HGB, HCT, MCV, MCH, MCHC, RDW, and HbA2 were selected based on literature. Two model-fitting approaches were introduced, each un-der different data selection methods: Method 1: Model fitting before handling the class imbalance problem and Method 02: Model fitting with random over-sampling technique. Support Vector Machine (SVM) and Probabilistic Neural Network (PNN) models were utilized for β-thalassemia carrier detection. Method 2 exhibited superior performance, especially with the PNN Model 2, achieving an impressive 98.75% overall classification accuracy. Moreover, the implemented PNN Model 2 could be utilized as an efficient decision-support tool, offering both time and cost savings in identifying β-thalassemia carriers. Nonetheless, for further investigation, consulting a medical expert is recommended.

Integration of artificial intelligence techniques and intrusion detection systems in anomaly detection for data networks

This research investigates the integration of artificial intelligence (AI) and intrusion detection system (IDS) for anomaly detection in data networks, the study aims to evaluate the effectiveness of AI techniques in identifying malicious activities within network traffic. A proprietary dataset is developed instead of other existing ones to have a varied set of threats and mainly due to the architecture used to realize the analysis. The integration of AI with IDS represents a significant advancement in the field of cybersecurity, particularly in the context of increasing cyber threats identification. Through a comprehensive analysis involving the use of open-source software tools and various data mining models, this study demonstrates that AI-enhanced IDS systems can significantly improve the detection of network anomalies, thereby enhancing overall network security. The results highlight the critical need for continuous updates and the adaptation of new AI models to address the evolving cyber threats that frequently occur.