Search

The fight against crime is often an arduous task overall when huge amounts of data have to be inspected, as is currently the case when it comes for example in the detection of criminal activity on the dark web. This work presents and describes an artificial intelligence (AI) based system that combines various tools to assist police or law enforcement agencies during their investigations, or at least mitigate the hard process of data collection, processing and analysis. The system is an early warning/early action system for crime investigation that supports law enforcement with different processes to collect and process data as well as having knowledge extraction tools. It helps to extract information during the investigation of a criminal case or even to detect possible criminal hotspots that may lead to further investigation or analysis of a criminal case Abu Al‐Haija et al. (2022, Electronics, 11, 556). The functionality of the proposed system is illustrated through several examples using data collected from the dark web, which includes advertisements offering firearms‐related products. [ABSTRACT FROM AUTHOR]

Fault analysis (FA) is the process of collecting and analyzing data to determine the cause of a failure. It plays an important role in ensuring the quality in manufacturing process. Traditional FA techniques are time-consuming and labor-intensive, relying heavily on human expertise and the availability of failure inspection equipment. In semiconductor industry, a large amount of FA reports are generated by experts to record the fault descriptions, fault analysis path and fault root causes. With the development of Artificial Intelligence, it is possible to automate the industrial FA process while extracting expert knowledge from the vast FA report data. The goal of this research is to develop a complete expert knowledge extraction pipeline for FA in semiconductor industry based on advanced Natural Language Processing and Machine Learning. Our research aims at automatically predicting the fault root cause based on the fault descriptions. First, the text data from the FA reports are transformed into numerical data using Sentence Transformer embedding. The numerical data are converted into latent spaces using Generalized-Controllable Variational AutoEncoder. Then, the latent spaces are classified by Gaussian Mixture Model. Finally, Association Rules are applied to establish the relationship between the labels in the latent space of the fault descriptions and that of the fault root cause. The proposed algorithm has been evaluated with real data of semiconductor industry collected over three years. The average correctness of the predicted label achieves 97.8%. The method can effectively reduce the time of failure identification and the cost during the inspection stage. [ABSTRACT FROM AUTHOR]

Objective To explore the comorbidity patterns and influencing factors of chronic diseases in middle - aged and elderly people in China, so as to provide new ideas for the development of corresponding chronic disease prevention and control strategies and measures. Methods Using data from the China Health and Retirement Longitudinal Study ( CHARLS) 2018, after excluding samples with missing variables for 14 chronic diseases, a final sample of 19,390 individuals aged 45 and older was included. The Apriori algorithm from association rule analysis was utilized to explore the comorbidity patterns among middle - aged and elderly individuals in China. The occurrence of chronic comorbidity (two or more chronic diseases or three or more chronic diseases) was taken as the dependent variable, and the independent variable was determined according to the five dimensions of social determinants of health. 5 696 samples were included after deletion of the missing values, and the influential factors of chronic comorbidity were analyzed by univariate test and multifile logistic regression. Results The prevalence of comorbid chronic diseases among middle - aged and elderly individuals in our country was 55. 4%. The most common comorbidity patterns were arthritis or rheumatic diseases and hypertension. Association rule analysis identified 24 strong rule combinations, with the most common binary association being gastrointestinal or digestive system diseases with arthritis or rheumatic diseases, and the most common ternary association being gastrointestinal or digestive system diseases, hypertension, and arthritis or rheumatic diseases. The results of the multivariate analysis showed that both two or more chronic diseases and three or more chronic diseases were significantly associated with increased risk factors, including : age 60 - 80 years (two or more chronic diseases : OR = 1. 479, 95 % CI : 1. 244 -- 1. 759; three or more chronic diseases : OR = 1. 526, 95% CI: 1.267 -- 1. 839), age >80 years ( OR = 1.545, 95% CI: 1. 144 --2.087; OR = 1. 591, 95% CI: 1. 175 --2. 154), depressive symptoms ( OR = 1. 435, 95% CI: 1. 267 -- 1. 626 ; OR = 1. 382, 95% CI: 1. 216 -- 1. 570), having a pension ( OR = 1.350, 95% CI$ 1.141 --1.598; OR = 1.332, 95%CI: 1.118 --1.586), and residence in central ( OR = 1. 268, 95%CI: 1.096 --1.470; OR = 1. 269, 95% CI: 1.088 -- 1.479) or western regions ( OR = 1.217, 95% CI: 1.062 -- 1.395; OR = 1. 198, 95% CI: 1. 038 -- 1. 382). Conversely, factors associated with a reduced risk of chronic multimorbidity included alcohol consumption (two or more chronic diseases $ OR = 0.811, 95% CI : 0. 707 -- 0. 930; three or more chronic diseases : OR = 0. 837, 95% CI: 0. 724 -- 0. 968 ), 6 --8 hours of night sleep ( OR = 0. 806, 95% CI: 0. 702 -- 0. 926; OR = 0. 792, 95% CI: 0.688 --0.912), more than 8 hours of night sleep ( OR = 0. 738, 95% CI: 0.635 --0.858; OR=0.745, 95% CI: 0.637 -- 0.872), self -- rated general health ( OR=0.357, 95%CI: 0.307 --0.414; OR=0.343, 95%CI: 0.299 --0.392), and self -- rated good health ( OR = 0. 136, 95% CI: 0. 114 --0. 163; OR = 0. 117, 95% CI: 0.096 --0. 142 ). Conclusion It is suggested that the prevention and intervention of chronic comorbidity should be multidimensional, and the health care personnel should take into account the comorbidity of patients and the problem of multiple drug use in the formulation of comorbidity treatment plan. [ABSTRACT FROM AUTHOR]

Within the evolving field of sentiment analysis, the integration of topic modeling and association rule mining presents a promising yet underexplored method. This approach currently lacks an organized framework for maximizing insights that aid in drawing robust conclusions concerning customer sentiments. Therefore, this study addresses the need and rationale for having comprehensive sentiment analysis systems by integrating topic modeling and association rule mining to analyze online customer reviews of earphones sold on Amazon. It employs Bidirectional Encoder Representations from Transformers for Topic Modeling (BERTopic), a technique that generates coherent topics by effectively capturing contextual information, and Frequent Pattern Growth (FPGrowth), an efficient association rule mining algorithm used for discovering patterns and relationships in a dataset without candidate generation. This analysis of reviews on ten earphone products identified key customer concerns as follows: sound quality, noise cancellation, durability, and battery life. The results indicate an overall positive sentiment towards sound quality and battery life, mixed reviews on noise cancellation, and significant dissatisfaction with product durability. Using integrated topic modeling and association rule mining offers deeper insights into customer preferences and highlights specific areas for product improvement and guiding targeted marketing strategies. Moreover, we focused on algorithm selection to improve the model's performance and efficiency, ensuring effective compatibility with our sentiment analysis framework. This study demonstrates how combining advanced data mining techniques and structuring insights from written customer feedback enhances the depth and clarity of sentiment analysis, furthering its applicability in e-commerce research. [ABSTRACT FROM AUTHOR]

The research aims to investigate the support suppliers' decision making for Textile and Garment Vietnamese Enterprises based on using association rules mining. In order to increase the competitive advantage over other enterprises, Vietnamese enterprises are gradually shifting their production methods from CMT (Cut-Make-Trim) to FOB (Free On Board), ODM (Original Design Manufacturing), and OBM (Original Brand Manufacturing). One of the important steps for this transformation is to be self-sufficient in sourcing raw materials from selected suppliers with sufficient capabilities, meeting the requirements of price, and CSR (corporate social responsibility) to enable Vietnamese enterprises to enjoy tax incentives. The Vietnamese Enterprises participate in the textile and garment production process through importing raw materials from other countries such as China, Korea, etc. Therefore, the selection supplier issue is very important to them to enhance their business products. This study researches on finding positive ARs and negative ARs in Textile and Garment data domain via three scenarios to define the relationship of alternative criteria for selection suppliers. By using alternative method of ARM (Association Rule Mining), the experimental results show that Textile and Garment enterprises in Vietnam appreciate the CSR factor highly. This is completely in line with the previous survey research on the new factor in the supplier selection criteria of Textile and Garment enterprises in Vietnam. In another word, in this field, the CSR plays as an important role to reflect company's image and it is the first of decision choice. The other criteria are considered after including Cost, Quality, and Delivery respectively. The remain factors of Service, Capability, Relationship, and Sourcing Country are not highly evaluated via the experiments. With different scenarios along with the association rules mined, they reflect different sets of criteria that textile and garment enterprises use to select their suppliers. Furthermore, the rare rules show situations that are very unlikely but have high reliability in reality. Based on the findings, the factors will show the essentials for suppliers to improve themselves to meet the requirements. • Select a suitable logistics supplier using the association rules method. • Criteria evaluated highly: CSR, Cost, Quality, and Delivery. [ABSTRACT FROM AUTHOR]

This research paper focuses on enhancing the frequent pattern growth (FP-growth) algorithm, an advanced version of the Apriori algorithm, by employing a parallelization approach using the Apache Spark framework. Association rule mining, particularly in healthcare data for predicting and diagnosing diabetes, necessitates the handling of large datasets which traditional methods may not process efficiently. Our method improves the FP-growth algorithm's scalability and processing efficiency by leveraging the distributed computing capabilities of apache spark. We conducted a comprehensive analysis of diabetes data, focusing on extracting frequent itemsets and association rules to predict diabetes onset. The results demonstrate that our parallelized FP-growth (PFP-growth) algorithm significantly enhances prediction accuracy and processing speed, offering substantial improvements over traditional methods. These findings provide valuable insights into disease progression and management, suggesting a scalable solution for large-scale data environments in healthcare analytics. [ABSTRACT FROM AUTHOR]

As the basic guarantee for people's production and life, the safe operation of the power system has an important impact on the development and operation of society. To ensure the safe and stable operation of the power grid, predicting potential faults and taking reasonable preventive measures can effectively avoid the occurrence of power accidents. However, due to the difficulty in ensuring the prediction accuracy of traditional methods, there are issues of protection misoperation and rejection. Therefore, in order to achieve accurate prediction of power grid faults and avoid protection misoperation and rejection issues, a distribution network fault classification prediction model using a combination of three-layer data mining model (TLDM) and adaptive moment estimation (Adam) algorithm/random gradient descent algorithm improved backpropagation neural network (BPNN) is proposed. The implementation results showed that the classification accuracy of artificial fish school a priori, k -means clustering convolutional neural network model and TLDM for single-phase grounding faults was 93.2%, 91.5% and 96.6%, respectively. The classification accuracy for two-phase faults was 92.8%, 92.4% and 95.7%, respectively. The classification accuracy for two-phase grounding faults was 93.7%, 91.2% and 96.9%, respectively. The classification accuracy for three-phase faults was 93.3%, 92.1% and 97.1%, respectively. The TLDM had the highest classification accuracy. The average accuracy, average accuracy and average recall of the BPNN improved by the combination of the ADAM algorithm and random gradient descent algorithm were 94.1%, 90.9% and 88%, respectively, which were higher than the BPNN improved by the combination of ADAM algorithm and random gradient descent algorithm. The above results indicate that the proposed distribution network fault classification and prediction model has good performance and can achieve accurate prediction of distribution network faults. [ABSTRACT FROM AUTHOR]

Data-driven production scheduling and control systems are essential for manufacturing organisations to quickly adjust to the demand for a wide range of bespoke products, often within short lead times. This paper presents a self-learning framework that combines association rules and optimization techniques to create data-driven production scheduling. A new approach to predicting interruptions in the production process through association rules was implemented, using a mathematical model to sequence production activities in real or near real-time. The framework was tested in a case study of a ceramics manufacturer, updating confidence values by comparing planned values to actual values recorded during production control. It also sets a production corrective factor based on confidence value and success rate to avoid product shortages. The results were generated in just 1.25 seconds, resulting in a makespan reduction of 9% and 6% compared to two heuristics based on First-In-First-Out and Short Processing Time strategies. [ABSTRACT FROM AUTHOR]

Distracted driving is a significant factor influencing traffic accidents. Current research primarily focuses on identifying distracted behaviors among drivers, while the investigation into accident mechanisms remains limited. To improve highway driving safety, the coupling relationships among drivers, vehicles, roads, and environments were explored, based on traffic accident data in a specific region. Utilizing association rule algorithms, seasonal variations in accident occurrences were analyzed, and potential patterns of distracted driving accidents were explored from multiple perspectives. The results show that accidents caused by driver distraction exhibit certain temporal and spatial patterns, with a higher frequency during weekday commuting peak hours and identifiable accident-prone locations. Regardless of season, distracted driving accidents tend to occur more frequently on straight road segments under favorable weather conditions. The severity of accidents predominantly involves property damage or injuries, with a low proportion of fatalities. Differences in accident causation and occurrence patterns are observed between summer and winter distracted driving accidents. These findings provide valuable insights for traffic managers to develop innovative policies and enhance road safety. [ABSTRACT FROM AUTHOR]

OBJECTIVE: To study the medication rules of traditional Chinese medicine in the treatment of membranous nephropathy, so as to provide references for the clinical treatment of membranous nephropathy. METHODS: CNKI, Wanfang Data and PubMed were retrieved to collect clinical studies of traditional Chinese medicine in the treatment of membranous nephropathy, and the data files were established. Excel 2019, Clementine 12. 0 and SPSS 21. 0 software were used to perform frequency statistics of syndrome types, usage frequency, classification, dosage, properties, tastes, and meridian tropism of drugs, association rule analysis, factor analysis and cluster analysis. RESULTS: A total of 179 traditional Chinese medicine compounds and 18 high-frequency drugs were included. Among them, Hedysarum Multijugum Maxim, Poria Cocos, Atractylodes Macrocephala Koidz, and Codonopsis Radix were the most frequently used, the most common efficacy classification was tonic drugs, the main properties was warm, and the main tastes was sweet, which was mostly attributed to the spleen meridians. Totally 16 drug combinations with high association strength were obtained by association rule analysis. Six common factors were extracted by factor analysis. Drugs could be divided into 4 groups by cluster analysis. CONCLUSIONS: The treatment of membranous nephropathy with traditional Chinese medicine mainly focuses on supplementing Qi, strengthening spleen, and tonifying kidney, replenish deficiency with sweet and warm, and the use of syndrome differentiation and combination of promoting blood circulation and resolving blood stasis, and promoting urination and draining dampness. [ABSTRACT FROM AUTHOR]

Within the evolving field of sentiment analysis, the integration of topic modeling and association rule mining presents a promising yet underexplored method. This approach currently lacks an organized framework for maximizing insights that aid in drawing robust conclusions concerning customer sentiments. Therefore, this study addresses the need and rationale for having comprehensive sentiment analysis systems by integrating topic modeling and association rule mining to analyze online customer reviews of earphones sold on Amazon. It employs Bidirectional Encoder Representations from Transformers for Topic Modeling (BERTopic), a technique that generates coherent topics by effectively capturing contextual information, and Frequent Pattern Growth (FPGrowth), an efficient association rule mining algorithm used for discovering patterns and relationships in a dataset without candidate generation. This analysis of reviews on ten earphone products identified key customer concerns as follows: sound quality, noise cancellation, durability, and battery life. The results indicate an overall positive sentiment towards sound quality and battery life, mixed reviews on noise cancellation, and significant dissatisfaction with product durability. Using integrated topic modeling and association rule mining offers deeper insights into customer preferences and highlights specific areas for product improvement and guiding targeted marketing strategies. Moreover, we focused on algorithm selection to improve the model’s performance and efficiency, ensuring effective compatibility with our sentiment analysis framework. This study demonstrates how combining advanced data mining techniques and structuring insights from written customer feedback enhances the depth and clarity of sentiment analysis, furthering its applicability in e-commerce research.

The research aims to investigate the support suppliers’ decision making for Textile and Garment Vietnamese Enterprises based on using association rules mining. In order to increase the competitive advantage over other enterprises, Vietnamese enterprises are gradually shifting their production methods from CMT (Cut-Make-Trim) to FOB (Free On Board), ODM (Original Design Manufacturing), and OBM (Original Brand Manufacturing). One of the important steps for this transformation is to be self-sufficient in sourcing raw materials from selected suppliers with sufficient capabilities, meeting the requirements of price, and CSR (corporate social responsibility) to enable Vietnamese enterprises to enjoy tax incentives. The Vietnamese Enterprises participate in the textile and garment production process through importing raw materials from other countries such as China, Korea, etc. Therefore, the selection supplier issue is very important to them to enhance their business products. This study researches on finding positive ARs and negative ARs in Textile and Garment data domain via three scenarios to define the relationship of alternative criteria for selection suppliers. By using alternative method of ARM (Association Rule Mining), the experimental results show that Textile and Garment enterprises in Vietnam appreciate the CSR factor highly. This is completely in line with the previous survey research on the new factor in the supplier selection criteria of Textile and Garment enterprises in Vietnam. In another word, in this field, the CSR plays as an important role to reflect company’s image and it is the first of decision choice. The other criteria are considered after including Cost, Quality, and Delivery respectively. The remain factors of Service, Capability, Relationship, and Sourcing Country are not highly evaluated via the experiments. With different scenarios along with the association rules mined, they reflect different sets of criteria that textile and garment enterprises use to select their suppliers. Furthermore, the rare rules show situations that are very unlikely but have high reliability in reality. Based on the findings, the factors will show the essentials for suppliers to improve themselves to meet the requirements.

A coal mine dual prevention construction evaluation model based on association rule mining and combined weighting cloud model is proposed. Firstly, based on association rule mining, the evaluation indicators for the effectiveness evaluation system of the dual prevention mechanism construction in coal mines are determined. Secondly, the analytic hierarchy process and anti entropy weight method are used to obtain the subjective and objective weights of the indicators. Then, the composite normalization method is used to obtain the combined weights of the indicators, and a cloud theory model is introduced to construct an evaluation model for coal mine dual prevention construction based on the cloud model. Finally, by analyzing a coal mine as a sample, the evaluation results of the model are compared with those of the analytic hierarchy process cloud model and the anti entropy weight method cloud model. The results indicate that the evaluation model is more scientific and accurate in the evaluation of dual prevention construction in coal mines, which helps to assist coal mines in establishing a scientific and reasonable “dual prevention” mechanism.

In order to prevent the occurrence of coal mine roof accidents more scientifically, it is crucial to identify the causal factors of coal mine roof accidents and their association rules. First, 56 causal factors affecting the occurrence of roof accidents were identified through text mining and combined with the SIF accident causal model. Second, we constructed a roof accident database and utilized the Apriori algorithm to mine the association rules of roof accidents. Finally, the complex network diagram of the causal factors of roof accidents was drawn, and the core causal factors of roof accidents and the correlation rules between the causal factors were comprehensively analyzed. The results show that there is a high degree of correlation and enhancement between safety training and education, safety supervision and management, low safety awareness and violation of work procedures by operators, inadequate management of the on-duty management and other causes of accidents, and these factors are the core factors causing roof accidents in coal mines.

Abstract The symptoms of diseases can vary among individuals and may remain undetected in the early stages. Detecting these symptoms is crucial in the initial stage to effectively manage and treat cases of varying severity. Machine learning has made major advances in recent years, proving its effectiveness in various healthcare applications. This study aims to identify patterns of symptoms and general rules regarding symptoms among patients using supervised and unsupervised machine learning. The integration of a rule-based machine learning technique and classification methods is utilized to extend a prediction model. This study analyzes patient data that was available online through the Kaggle repository. After preprocessing the data and exploring descriptive statistics, the Apriori algorithm was applied to identify frequent symptoms and patterns in the discovered rules. Additionally, the study applied several machine learning models for predicting diseases, including stepwise regression, support vector machine, bootstrap forest, boosted trees, and neural-boosted methods. Several predictive machine learning models were applied to the dataset to predict diseases. It was discovered that the stepwise method for fitting outperformed all competitors in this study, as determined through cross-validation conducted for each model based on established criteria. Moreover, numerous significant decision rules were extracted in the study, which can streamline clinical applications without the need for additional expertise. These rules enable the prediction of relationships between symptoms and diseases, as well as between different diseases. Therefore, the results obtained in this study have the potential to improve the performance of prediction models. We can discover diseases symptoms and general rules using supervised and unsupervised machine learning for the dataset. Overall, the proposed algorithm can support not only healthcare professionals but also patients who face cost and time constraints in diagnosing and treating these diseases.

ObjectivesMethodsResultsConclusionCoal mine accidents seriously affect China’s coal safety production and sustainable development. The present study aimed to reveal the risk factors in coal mine accidents and explore the causal relationship among risk factors.This study utilized text mining to analyse 450 coal mine accident reports, identifying 50 risk factors and efficiently mapping them into the 24Model. The association rule algorithm was then used to mine the strong association rules among the risk factors within the 24Model, establishing the interaction mechanism among them. Based on the strong association rules, related hypotheses were proposed. Finally, the hierarchical and logical relationships of risk factors within the 24Model were analysed, and the causal and mediating effects were tested by path analysis.The safety management system has a direct effect on unsafe acts, unsafe conditions, habitual behaviour and organizational safety culture. Moreover, external influence has an effect on unsafe acts, organizational safety culture and habitual behaviour through the mediating effect of the safety management system.Based on the results obtained, this study proposes a series of specific measures to prevent risks in coal mines, providing a new perspective for the analysis and prevention of accidents. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Railway Science & Engineering is the property of Journal of Railway Science & Engineering Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

With the rapid development of big data technology, electronic documents are more and more widely used. Aiming at the characteristics of large amount of data, complex format and non-standard information data of electronic documents, this paper uses data mining technology to realize the correlation construction between documents. Firstly, on the basis of dynamic incremental association rules, according to the characteristics of electronic document business, the association rules are improved. Secondly, the advantages of Boolean matrix operation, original data association rules and frequent 2-item set are used to improve the acquisition ability of the system for frequent items of document features. The experimental results show: that algorithm in this paper has higher computational efficiency in the process of file increment change and deletion change, and is suitable for electronic file processing in the case of big data. [ABSTRACT FROM AUTHOR]

In retail, a major challenge is quickly selling perishable food items like cakes or pastries within a limited time. If unsold, these products lead to losses, even with discount promotions. Retailers must forecast stock accurately and develop more effective strategies to meet consumer demand within the required timeframe. One suggested strategy is bundling, where high-demand products are combined with less popular ones. However, when done manually, this approach often fails to align with consumer preferences. This study aims to develop an automated bundling system using data mining techniques. Market Basket Analysis is used to understand consumer purchasing patterns, while Association Rules with the Apriori Algorithm help identify relationships between different products. These methods reveal which items are frequently bought together, making bundling strategies more effective. The system will be designed with usability and ergonomic principles, ensuring it is user-friendly. The implications of this system include improved stock management, more accurate bundling, and better alignment with customer preferences, ultimately increasing satisfaction. Additionally, automation reduces errors and inconsistencies that occur with manual bundling. The expected outcome is a more efficient, effective, and comfortable system for food retailers, leading to higher sales, reduced losses, and greater overall customer satisfaction.. [ABSTRACT FROM AUTHOR]

Cardiovascular diseases (CVDs)continue to be the primary cause of mortality, accounting for approximately one-third of all fatalities globally. This spawned the proposal of models in several studies. Accordingly, this study contributed to diagnosing heart disease through suggesting soft diagnosis paradigm. Various techniques have been volunteered for serving the suggested paradigm toward achieving its objective. Additionally, this study provided set of contributions. For instance, Tree Soft Technique (TrST) is applied for the first time for forming attributes and sub attributes of patients into nodes and sub-nodes of Tree to obtain relations between it. Even, the study support stakeholders to making accurate decision in mysterious circumstances and in problems with incomplete information through Collaborating the utilized techniques of entropy and Technique for order of preference by similarity to ideal solution (TOPSIS) in this study with Single Value Neutrosophic Sets (SVNSs) forked from neutrosophic uncertainty theory. As well, the relationship between sub-attributes which consider antecedent for obtaining consequent of detecting and diagnosing through collaborating TrST with association rules. Accordingly, we applied four transactions (cases) for obtaining findings of the relations in transactions as listed in Table 13 and Table14. [ABSTRACT FROM AUTHOR]

To address the lack of reliable measurement methods for identifying wear mechanisms and predicting the state of mechanical seal tribo-parts, this study proposes a method for characterizing tribological behavior based on measuring face vibration acceleration. It aims to uncover the source mechanism of mechanical seal face vibration acceleration influenced by tribology and dynamic behavior. This research delves into the dynamic behavior characteristics and vibration acceleration of the mechanical seal stationary ring. We explored the variation pattern of face vibration acceleration root mean square (RMS) with rotation speed, sealing medium pressure, and face surface roughness. The results indicate that under constant medium pressure, an increase in rotation speed leads to a decrease in acceleration RMS and an increase in face temperature. Similarly, under constant rotation speed, an increase in medium pressure results in nonlinear changes in acceleration RMS, forming an "M" shape, along with an increase in face temperature. Furthermore, under conditions of constant medium pressure and rotation speed, an increase in the surface roughness of the rotating ring face corresponds to an increase in acceleration RMS and face temperature. Upon starting the mechanical seal, both acceleration RMS and temperature initially increase before decreasing, a trend consistent with the Stribeck curve. [ABSTRACT FROM AUTHOR]

In response to the demand for scientific training of sports athletes, the author combined data mining technology to study an improved sports training mode decision support evaluation system. In this regard, the author analyzed the characteristics of association rule algorithms and elaborated on their functions in data preprocessing, data mining, and pattern evaluation. Based on the software design of decision support systems, the characteristics of system operation were analyzed. At the same time, the author focused on explaining the data fusion processing of association rules in sports evaluation decision support systems, and proposed an improved Apriori algorithm output mode to improve the effectiveness of system evaluation. Compared with other algorithms such as Apriori, DC Apriori and Apriori, this algorithm has higher reliability. When the minimum confidence is increased, the advantage of prior information will gradually disappear, and the final result will be obtained. Experimental results show that this method can effectively provide support for sports training decision-making. [ABSTRACT FROM AUTHOR]

With the development of network technology, online shopping is becoming more and more convenient. But the increasing number of products also makes it difficult for consumers to make the right decision. When there is no apparent market demand, how to recommend products with commercial potential to customers has become an urgent problem for businesses to solve. This paper proposes e-commerce product recommendation based on user preference and association rule algorithm aiming at the problems existing in e-commerce product recommendation. Firstly, this paper constructs a user interest modeling method. Through analyzing users' interests and preferences, to provide users with timely and accurate personalized services. Then, the FP_Growth algorithm is optimized and improved. A more effective CTE-MARM algorithm is designed, and an association rules database based on user benefit items is constructed and analyzed jointly. Analyze products with strong correlations. According to consumers' interest levels, TOP-N is the best product choice. Experiments show that the algorithm has higher prediction accuracy. The research results of this project can not only improve enterprises' ability to analyse data and provide data support for enterprises to carry out effective marketing management. [ABSTRACT FROM AUTHOR]

In complex environments such as computers, networks, and big data, the integrity and security issues of accounting information have become increasingly prominent. This study analyzes existing vulnerabilities in financial systems to identify specific security and cyber threats that challenge data integrity in the financial industry. In response to the above problems, this paper applies a new network security monitoring technology based on association rules. With the advantages of big data analysis, this traditional monitoring method has been further strengthened, allowing it to better realize real-time monitoring of financial data. Through early detection of security incidents, potential risks are reduced and the normal operation of the accounting system is ensured. Experiments have proven that the enhanced monitoring system has made great improvements in the identification and statistics of network security incidents. There is an average accuracy rate of 95%, which shows that the system is reliable and has the ability to enhance safety measurements. Organically integrate big data technology and traditional network security monitoring methods to form a robust network security protection mechanism. [ABSTRACT FROM AUTHOR]

The learning effect of students is crucial for assessing teaching quality, thus playing a significant role in teaching management. Predicting student achievement is a major challenge in understanding the learning effect of students. Currently, many studies have utilized machine learning methods such as the decision tree algorithms C4.5, ID3, CART, J48, random forest, and others. However, few studies have explored the use of the Bagging algorithm in this field. Therefore, this study proposes a classification prediction method for student achievement based on the Bagging‐CART algorithm. Initially, the student achievement data is preprocessed, and the Apriori method is applied to mine the strongly associated dataset. The optimal hyper‐parameters are determined through grid search to train and predict the Bagging‐CART algorithm. Furthermore, the CART, J48, and Bagging‐CART algorithms are trained, and their evaluation indicators are compared using a confusion matrix. The results indicate that the Bagging‐CART model achieves an accuracy of 98.16%, a recall rate of 91.80%, a precision of 90.83%, and an F1 score of 94.87%. In comparison, the accuracy, precision, and F1 scores are higher than those obtained with CART and J48. Although the recall rate is slightly lower than that of CART by 0.26%, it is 0.52% higher than that of J48. Consequently, this method demonstrates strong predictive capabilities and introduces a new reference method for evaluating students' learning effect. [ABSTRACT FROM AUTHOR]

Aimed at mitigating the limitations of the existing document entity relation extraction methods, especially the complex information interaction between different entities in the document and the poor effect of entity relation classification, according to the semi-structured characteristics of patent document data, a patent document ontology model construction method based on hierarchical clustering and association rules was proposed to describe the entities and their relations in the patent document, dubbed as MPreA. Combined with statistical learning and deep learning algorithms, the pre-trained model of the attention mechanism was fused to realize the effective extraction of entity relations. The results of the numerical simulation show that, compared with the traditional methods, our proposed method has achieved significant improvement in solving the problem of insufficient contextual information, and provides a more effective solution for patent document entity relation extraction. [ABSTRACT FROM AUTHOR]

Presently, there are few teaching evaluation systems with students as the main body, and there is a gap between the evaluation systems of professional course groups. In order to make a targeted teaching quality evaluation for marketing majors with strong practicality, the author designed a correlation analysis method based on association rule (AR) algorithm. Naive Bayes algorithm is used to classify the obtained strong rule results, and finally a teaching quality evaluation system for marketing majors was constructed by combining AR algorithm and SERVQUAL model. The results show that the method has excellent performance and the constructed evaluation system has good applicability. [ABSTRACT FROM AUTHOR]

The symptoms of diseases can vary among individuals and may remain undetected in the early stages. Detecting these symptoms is crucial in the initial stage to effectively manage and treat cases of varying severity. Machine learning has made major advances in recent years, proving its effectiveness in various healthcare applications. This study aims to identify patterns of symptoms and general rules regarding symptoms among patients using supervised and unsupervised machine learning. The integration of a rule-based machine learning technique and classification methods is utilized to extend a prediction model. This study analyzes patient data that was available online through the Kaggle repository. After preprocessing the data and exploring descriptive statistics, the Apriori algorithm was applied to identify frequent symptoms and patterns in the discovered rules. Additionally, the study applied several machine learning models for predicting diseases, including stepwise regression, support vector machine, bootstrap forest, boosted trees, and neural-boosted methods. Several predictive machine learning models were applied to the dataset to predict diseases. It was discovered that the stepwise method for fitting outperformed all competitors in this study, as determined through cross-validation conducted for each model based on established criteria. Moreover, numerous significant decision rules were extracted in the study, which can streamline clinical applications without the need for additional expertise. These rules enable the prediction of relationships between symptoms and diseases, as well as between different diseases. Therefore, the results obtained in this study have the potential to improve the performance of prediction models. We can discover diseases symptoms and general rules using supervised and unsupervised machine learning for the dataset. Overall, the proposed algorithm can support not only healthcare professionals but also patients who face cost and time constraints in diagnosing and treating these diseases. [ABSTRACT FROM AUTHOR]

Copyright of Xinjiang Agricultural Sciences is the property of Xinjiang Agricultural Sciences Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In this paper, an innovative two-layer network model was established to analyze safety risk factors for hazardous chemical accidents(SRFHCA). Firstly, potential safety risk factors were identified through the dataset from human, equipment, management, and environmental dimensions. Then, association rules learning was introduced to learn the associations between different factors. Finally, a two-layer complex network model was constructed to identify the critical factors. Our proposed methods and the corresponding results provide decision support to reduce the risk of hazardous chemical accidents. [ABSTRACT FROM AUTHOR]

IntroductionFalls are the primary cause of unintentional fatalities among individuals aged 65 and older. Enhancing research on fall prevention among older adults is an urgent priority. Consequently, this study aims to investigate the prevalence and influencing factors of falls among community-dwelling older adults in Guangzhou, China, with a particular emphasis on the impact of family functioning.MethodsWe used a multi-stage stratified cluster random sampling technique to successfully survey 2,399 individuals aged 65 and above across 11 districts in Guangzhou City. Data on sociodemographic characteristics, health and lifestyle factors, and fall incidents were collected through telephone interviews. Chi-square tests, Lasso regression, and logistic regression were utilized to pinpoint fall risk factors. Association rule mining uncovered the relationships between falls and associated variables.ResultsA total of 390 participants reported experiencing falls, the prevalence of falls among older adults was 16.3% (95%CI: 14.82% ~ 17.78%). Logistic regression analysis identified several risk factors for falls among older adults: female [OR = 1.511, 95%CI (1.188–1.922)], age 85 years and older [OR = 2.332, 95%CI (1.447–3.758)], stroke [OR = 1.821, 95%CI (1.038–3.192)], hypoglycemia [OR = 1.639, 95%CI (1.228–2.186)], visual impairment [OR = 1.418, 95%CI (1.097–1.833)], need to be cared for [OR = 1.722, 95%CI (1.339–2.215)], chronic pain [OR = 1.663, 95%CI (1.302–2.124)], and anxiety [OR = 1.725, 95%CI (1.243–2.395)]. In addition, it was shown that a well-functioning family was a protective factor against falls [OR = 0.589, 95%CI (0.44–0.789)].ConclusionThe prevalence of falls among community-dwelling older adults in Guangzhou City was high, and the influencing factors were complex. It is recommended to develop and implement comprehensive intervention measures for high-risk groups, including those who are females, older adults, and suffer from chronic diseases while paying special attention to the care of family members for older adults.

Data-driven production scheduling and control systems are essential for manufacturing organisations to quickly adjust to the demand for a wide range of bespoke products, often within short lead times. This paper presents a self-learning framework that combines association rules and optimization techniques to create data-driven production scheduling. A new approach to predicting interruptions in the production process through association rules was implemented, using a mathematical model to sequence production activities in real or near real-time. The framework was tested in a case study of a ceramics manufacturer, updating confidence values by comparing planned values to actual values recorded during production control. It also sets a production corrective factor based on confidence value and success rate to avoid product shortages. The results were generated in just 1.25 seconds, resulting in a makespan reduction of 9% and 6% compared to two heuristics based on First-In-First-Out and Short Processing Time strategies.

ObjectiveTo understand the multiple health service needs of rural residents in China and explore the co-occurrence patterns of these needs throughout the entire life course, providing a basis for the formulation and optimization of health service packaging policies.MethodsThis study utilized a stratified random sampling method, resulting in a final sample size of 15,125 individuals. The R statistical software was employed to apply the Apriori algorithm to mine the co-occurrence relationships among multiple health service needs across the life course and to explore the packaging model of these services.ResultsThe health service needs rate among rural residents in China is 86.76%, with a multiple health service needs rate of 78.72%. The most needed services are health exercise guidance (17.10%), Traditional Chinese Medicine health care (15.53%), and internet health information services (14.40%). The highest combined health service need is for “exercise guidance need + internet health information need + Traditional Chinese Medicine health care need,” followed by “exercise guidance need + internet information need.” There are significant differences in the content and strength of associations in the co-occurrence structure of multiple health service needs across different age groups. During the life preparation stage, the need for multiple health services is high, with modern medical care and child management having the highest support. In the life protection stage, the focus shifts to preventive health needs, with strong associations among co-occurring needs (the highest support rule being Traditional Chinese Medicine health care + exercise guidance, support = 21.12%). The co-occurrence of medical and preventive health service needs among the older adult is diverse, with the strongest association being between chronic disease management services and rehabilitation services (support = 31.24%).ConclusionThe multiple health service needs rate among rural residents in China is high, with the greatest needs being for exercise guidance, Traditional Chinese Medicine health care, and internet health information services. There are significant differences in health service needs across different life stages. It is essential to enhance the integration and packaging of health service resources to promote diversity in health services and meet the multiple health service needs of residents throughout their life courses.

This study examines the access and usage of Information Communication Technologies (ICTs) outside the school environment among upper secondary students in Italy, based on data from the 2021-2022 INVALSI Field Trial. The study investigates the availability of digital devices such as desktops, laptops, and smartphones, and explores usage patterns through a questionnaire addressing the first and second digital divides, socio-demographics, and other relevant factors. The findings provide food for thought for those who need to manage technology and enhance learning. Notably, 96% of students reported having access to a computer at home for both learning and non-learning activities, and 88% had internet connectivity at home. While initial results suggest a reduction in the digital access gap, logistic regression models indicate that the first-level digital divide remains challenging for certain socio-economic groups. Using association rules data mining techniques, therefore, specific activities were identified as the most influential among students. Most of the grade 13 students possessed ICT tools and used them primarily for leisure activities such as social media, online communication platforms, entertainment videos and music, and web browsing.

The advent of the big data era has provided many types of transportation datasets, such as metro smart card data, for studying residents' mobility and understanding how their mobility has been shaped and is shaping the urban space. In this paper, we use metro smart card data from two Chinese metropolises, Shanghai and Shenzhen. Five metro mobility indicators are introduced, and association rules are established to explore the mobility patterns. The proportion of people entering and exiting the station is used to measure the jobs-housing balance. It is found that the average travel distance and duration of Shanghai passengers are higher than those of Shenzhen, and the proportion of metro commuters in Shanghai is higher than that of Shenzhen. The jobs-housing spatial relationship in Shenzhen based on metro travel is more balanced than that in Shanghai. The fundamental reason for the differences between the two cities is the difference in urban morphology. Compared with the monocentric structure of Shanghai, the polycentric structure of Shenzhen results in more scattered travel hotspots and more diverse travel routes, which helps Shenzhen to have a better jobs-housing balance. This paper fills a gap in comparative research among Chinese cities based on transportation big data analysis. The results provide support for planning metro routes, adjusting urban structure and land use to form a more reasonable metro network, and balancing the jobs-housing spatial relationship.

The research entails an evaluation of the efficacy of employing decision trees to augment students’ analytical capacities, encompassing the determination of self-efficacy levels and cognitive loads among students. The sample included 160 students divided into two groups. The present research collected the data using a questionnaire to analyse self-efficacy and cognitive load among students: the research revealed no significant differences in self-efficacy between the two groups of participants (F = 0.01, p > 0.05). The mean cognitive workload and cognitive effort values in the experimental group are 3.01 and 3.46 respectively, while in the control group, they are 2.94 and 3.42. These findings indicate that students in the experimental group exhibit slightly higher levels of the measured indicators compared to the control group; however, these differences are not statistically significant. The practical significance of this work lies in the absence of detected differences between the groups, which may indicate that both methods could be equivalent in terms of enhancing students’ analytical skills. This finding could influence the development of educational programs and enhance their effectiveness. [ABSTRACT FROM AUTHOR]

The Sustainable Development Goals (SDGs) in Indonesia are organized into four main pillars, each addressing specific dimensions of development, namely the pillar of social, economic, environmental, and law and governance development, which include 17 goals with 289 indicators to measure achievement. The achievement of one SDG indicator will have an impact on the achievement of other SDG indicators, both within each pillar and with other pillars. Therefore, it is important to understand the relationships among the SDG indicators of the social development pillar and the relationships between the indicators of the social development pillar and the indicators of the other pillars. In this study, the SDG indicators for 2016–2021 were used, which were obtained from BPS-Statistics and several related agencies. The data are then analyzed using fuzzy membership functions and association rules with the Apriori algorithm method. The results show that there is an association among SDG indicators of the social pillar, which are formed from nine indicators. In addition, this study also found that there's an association between the indicators in the pillars of social, economic, environmental, and law and governance development, which are formed from 12 indicators. Of the 12 indicators, there are two indicators of the social development pillar that are related to other indicators of the remaining pillars, which are the extreme poverty level and the number of regencies/cities that have achieved malaria elimination. [ABSTRACT FROM AUTHOR]

Association Rules Mining is the technique of Data Mining. Association Rule Mining finds interesting relationships among large set of data items. Market Basket Analysis is one of the method of ARM. User can use the variables say Dependent Variable and Independent Variable. Here, Association Rules define as Dependent Variable and Support and Confidence are define as Independent Variable. To verify the relationship between Rules, Support and Confidence, apply the Regression Statistics, Regression Coefficients, Multiple Correlation Coefficient and Multi-collinearity. To evaluates the Regression line, to estimate and predict the Rules and other calculation, R-Studio is applying for to evaluate the Regression Statistics. The R-packages arules and arulesviz is apply for the Association Rules and Visulizations. [ABSTRACT FROM AUTHOR]

K-nearest neighbors (kNN) is a popular machine learning algorithm because of its clarity, simplicity, and efficacy. kNN has numerous drawbacks, including ignoring issues like class distribution, feature relevance, neighbor contribution, and the number of individuals for each class. In particular, some features could be more important than others for classifying a data point, and increasing their weight in the distance computation can make the kNN algorithm more accurate. Researchers propose different feature weightings, such as correlation-based feature selection, mutual information, and chi-square feature selection. This paper presents a new feature weighting technique based on association rules and information gain. The proposed approach gives a good performance compared to other similar methods. [ABSTRACT FROM AUTHOR]

Accurately predicting the chiller coefficient of performance (COP) is essential for improving the energy efficiency of heating, ventilation, and air conditioning (HVAC) systems, significantly contributing to energy conservation in buildings. Traditional performance prediction methods often overlook the dynamic interaction among sensor variables and face challenges in using extensive historical data efficiently, which impedes accurate predictions. To overcome these challenges, this paper proposes an innovative on-site chiller performance prediction method employing a dynamic graph convolutional network (GCN) enhanced by association rules. The distinctive feature of this method is constructing an association graph bank containing static graphs in each operating mode by mining the association rules between various sensor variables in historical operating data. A real-time graph is created by analyzing the correlation between various sensor variables in the current operating data. This graph is fused online with the static graph in the current operating mode to obtain a dynamic graph used for feature extraction and training of GCN. The effectiveness of this method has been empirically confirmed through the operational data of an actual building chiller system. Comparative analysis with state-of-the-art methods highlights the superior performance of the proposed method. [ABSTRACT FROM AUTHOR]

In this paper, a data-driven framework aimed at investigating how weather factors affect the spatio-temporal patterns of air traffic flow in the terminal maneuvering area (TMA) is presented. The framework mainly consists of three core modules, namely, trajectory structure characterization, flow pattern recognition, and association rule mining. To fully characterize trajectory structure, abnormal trajectories and typical operations are sequentially extracted based on a deep autoencoder network with two specially designed loss functions. Then, using these extracted elements as basic components to further construct and cluster per-hour-level descriptions of airspace structure, the spatio-temporal patterns of air traffic flow can be recognized. Finally, the association rule mining technique is applied to find sets of weather factors that often appear together with each flow pattern. Experimental analysis is demonstrated on two months of arrival flight trajectories at Hong Kong International Airport (HKIA). The results clearly show that the proposed framework effectively captures spatial anomalies, fine-grained trajectory structures, and representative flow patterns. More importantly, it also reveals that those flow patterns with non-conforming behaviors result from complex interactions of various weather factors. The findings provide valuable insights into the causal relationships between weather factors and changes in flow patterns, greatly enhancing the situational awareness of TMA. [ABSTRACT FROM AUTHOR]