ASSOCIATION RULE MINING FOR PREDICTION OF COVID-19

COVID-19 is a raging pandemic that has created havoc with its impact ranging from loss of millions of human lives to social and economic disruptions of the entire world. Therefore, error-free prediction, quick diagnosis, disease identification, isolation and treatment of a COVID patient have become extremely important. Nowadays, mining knowledge and providing scientific decision making for diagnosis of diseases from clinical datasets has found wide-ranging applications in healthcare sector. In this direction, among different data mining tools, association rule mining has already emerged out as a popular technique to extract invaluable information and develop important knowledge-base to help in intelligent diagnosis of distinct diseases quickly and automatically. In this paper, based on 5434 records of COVID cases collected from a popular data science community and using Rapid Miner Studio software, an attempt is put forward to develop a predictive model based on frequent pattern growth algorithm of association rule mining to determine the likelihood of COVID-19 in a patient. It identifies breathing problem, fever, dry cough, sore throat, abroad travel and attended large gathering as the main indicators of COVID-19. Employing the same clinical dataset, a linear regression model is also proposed having a moderately high coefficient of determination of 0.739 in accurately predicting the occurrence of COVID-19. A decision support system can also be developed using the association rules to ease out and automate early detection of other diseases. © 2023 by the authors.

Mining association rules for classification using frequent generator itemsets in arules package

Mining frequent itemsets is an attractive research activity in data mining whose main aim is to provide useful relationships among data. Consequently, several open-source development platforms are continuously developed to facilitate the users' exploitation of new data mining tasks. Among these platforms, the R language is one of the most popular tools. In this paper, we propose an extension of arules package by adding the option of mining frequent generator itemsets. We discuss in detail how generators can be used for a classification task through an application example in relation with COVID-19.

Discovering COVID-19 Death Patterns from Deceased Patients: A Case Study in Saudi Arabia

COVID-19 is a serious infection that cause severe injuries and deaths worldwide. The COVID-19 virus can infect people of all ages, especially the elderly. Furthermore, elderly who have co-morbid conditions (e.g., chronic conditions) are at an increased risk of death. At the present time, no approach exists that can facilitate the characterization of patterns of COVID-19 death. In this study, an approach to identify patterns of COVID-19 death efficiently and systematically is applied by adapting the Apriori algorithm. Validation and evaluation of the proposed approach are based on a robust and reliable dataset collected from Health Affairs in the Makkah region of Saudi Arabia. The study results show that there are strong associations between hypertension, diabetes, cardiovascular disease, and kidney disease and death among COVID-19 deceased patients © 2023, International Journal of Advanced Computer Science and Applications.All Rights Reserved.

Extracting Temporal Relationships in EHR: Application to COVID-19 Patients.

Association rules are one of the most used data mining techniques. The first proposals have considered relations over time in different ways, resulting in the so-called Temporal Association Rules (TAR). Although there are some proposals to extract association rules in OLAP systems, to the best of our knowledge, there is no method proposed to extract temporal association rules over multidimensional models in these kinds of systems. In this paper we study the adaptation of TAR to multidimensional structures, identifying the dimension that establishes the number of transactions and how to find time relative correlations between the other dimensions. A new method called COGtARE is presented as an extension of a previous approach proposed to reduce the complexity of the resulting set of association rules. The method is tested in application to COVID-19 patients data.

Application of Data Mining to Support Facilities Management in Smart Buildings

Concerns about the effects of global warming and predicted rising sea levels are radically changing government policies to lower carbon emissions using sustainable green technologies. The United Kingdom aims to reduce its carbon emissions by 78% by 2035 and achieve net zero by 2050. This is a major driver for energy management and is influencing development of buildings which use autonomous smart technologies to assist in lowering carbon footprints. These Smart Buildings use digital technologies by connecting sensor data with intelligent systems which can be monitored remotely to provide more efficient facilities management. The data harvested and transmitted from the IoT sensors provides a key component for Big Data Analytics using techniques such as Association rule mining for intelligent interpretation which can assist facilities management becoming more agile regarding office space utilization. The shift toward hybrid working particularly instigated by the COVID-19 pandemic and recent energy supply concerns caused by the Ukraine crisis presents facilities management with opportunities to optimize their space, reduce energy consumption, and allow them to identify commercial opportunities for the unused space throughout the building. This chapter discusses the use of association rules for data mining derived from a simulated dataset for an investigative analysis of office workflow patterns for facilities management operations, resource conservation, and sustainability. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Execution of Market Basket Analysis and Recommendation Systems in Physical Retail Stores to Advance Sales Revenues

In the early months of 2020, pandemic covid-19 hit many parts of the world. Especially developing countries like India observed a negative growth rate in few quarters of last financial year. Retailing is one of the key sectors that contribute to Indian GDP with a share of nearly 10 percent. Hence there is a need for the retail sector to bounce back which is possible with the efficient use of new digital technologies. Market basket analysis is used here to extract the association rules which can be directly used for formulating discount and combo offers. Along with that, these rules can be used to decide the product positioning in the retail store. Items which are bought together can be placed next to each other to increase sales. Recommendation systems are most commonly used in ecommerce websites like Amazon, Flipkart, etc, and streaming platforms like Netflix to recommend the items that are to be purchased by users. Although recommendation engines are implemented in multiple web and mobile applications, these are not in the implementation stage in offline retail stores due to many implications associated with them like infrastructure, cost, etc. In this project, we have used market basket analysis and recommendation systems to propose a model to implement in retail stores to increase sales revenues and enhance customer experience. © 2022 IEEE.

Ontology-based semantic data interestingness using BERT models

The COVID-19 pandemic has generated massive data in the healthcare sector in recent years, encouraging researchers and scientists to uncover the underlying facts. Mining interesting patterns in the large COVID-19 corpora is very important and useful for the decision makers. This paper presents a novel approach for uncovering interesting insights in large datasets using ontologies and BERT models. The research proposes a framework for extracting semantically rich facts from data by incorporating domain knowledge into the data mining process through the use of ontologies. An improved Apriori algorithm is employed for mining semantic association rules, while the interestingness of the rules is evaluated using BERT models for semantic richness. The results of the proposed framework are compared with state-of-the-art methods and evaluated using a combination of domain expert evaluation and statistical significance testing. The study offers a promising solution for finding meaningful relationships and facts in large datasets, particularly in the healthcare sector. © 2023 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

COVID-19 patient diagnosis and treatment data mining algorithm based on association rules.

Association rules are used in different data mining applications, including Web mining, intrusion detection, and bioinformatics. This study mainly discusses the COVID-19 patient diagnosis and treatment data mining algorithm based on association rules. General data The key time interval during the main diagnosis and treatment process (including onset to dyspnea, first diagnosis, admission, mechanical ventilation, death, and the time from first diagnosis to admission, etc.), the cause of death by laboratory examination, and so forth. The frequency of drug use was counted and association rule algorithm was used to analyse and study the effect of drug treatment. The results could provide reference for rational drug use in COVID-19 patients. In this study, in order to improve the efficiency of data mining in data processing, it is necessary to pre-process these data. Secondly, in the application of this data mining, the main objective is to extract association rules of COVID-19 complications. So its properties for mining should be various diseases. Therefore, it is necessary to classify individual disease types. During the construction of association rules database, the data in the data warehouse is analysed online and the association rules data mining is analysed. The results are stored in the knowledge base for decision support. For example, the prediction results of the decision tree can be displayed at this level. After the construction of the mining model, the display interface can be mined, and the decision-maker can input the corresponding attribute value and then predict it. 0.76% of people had both COVID-19, CHD and hypertension, while 46.5% of people with COVID-19 and CHD were likely to have hypertension. This study is helpful to analyse the imaging factors of COVID-19 disease.

Diagnosis of COVID-19 Infection via Association Rules of Cough Encoding

COVID-19 has roused the scientific community, prompting calls for immediate solutions to avoid the infection or at least reduce the virus's spread. Despite the availability of several licensed vaccinations to boost human immunity against the disease, various mutated strains of the virus continue to emerge, posing a danger to the vaccine's efficacy against new mutations. As a result, the importance of the early detection of COVID-19 infection becomes evident. Cough is a prevalent symptom in all COVID-19 mutations. Unfortunately, coughing can be a symptom of various of diseases, including pneumonia and infiuenza. Thus, identifying the coughing behavior might help clinicians diagnose the COVID-19 infection earlier and distinguish coronavirus-induced from non-coronavirus-induced coughs. From this perspective, this research proposes a novel approach for diagnosing COVID-19 infection based on cough sound. The main contributions of this study are the encoding of cough behavior, the investigation of its unique characteristics, and the representation of these traits as association rules. These rules are generated and distinguished with the help of data mining and machine learning techniques. Experiments on the Virufy COVID-19 open cough dataset reveal that cough encoding can provide the desired accuracy (100%). © 2023, ECTI Association. All rights reserved.

Execution of market basket analysis and recommendation systems in physical retail stores to advance sales revenues

Pandemic COVID-19 struck numerous regions of the planet in the first few months of 2020. India and other emerging nations in particular saw negative growth over a few quarters of the previous fiscal year. With a contribution of over 10%, retailing is one of the major industries that contribute to India's GDP. As a result, the retail industry must recover, which may be done with the effective application of new digital technology. Here, association rules that may be utilised to create discounts and package deals are extracted using market basket analysis. Additionally, similar guidelines may be applied to determine where to arrange a product in a retail setting. Items purchased in bulk can be arranged adjacent to one another to improve sales. To suggest the products that consumers should buy, recommendation algorithms are most frequently employed in e-commerce websites like Amazon, Flipkart, etc. and streaming platforms like Netflix. Although there are numerous online and mobile apps that use recommendation engines, physical retail businesses have not yet adopted them owing to the various consequences they have, such as infrastructure, cost, etc. In this project, we've used market basket research and recommendation algorithms to develop a model that can be used in retail establishments to boost sales and improve customer satisfaction. © 2022 IEEE.

Implementation of Association Rules with Apriori Algorithm in Determining Customer Purchase Patterns

Micro, Small, and Medium Enterprises in Indonesia Usaha Mikro, Kecil, Menengah (UMKM) have been affected by the COVID-19 pandemic. The barcode scanning system currently only helps support the buying and selling process and cannot determine the provision of stock or the creation of promotional packages. Website application development using the Association Rule Method with the Apriori Algorithm is the solution offered to produce a pattern of relationships between products that buy by customers. The goods relationship is the basis for making decisions by shop owners to determine the stock of interconnected goods or making promotional packages with the association method by calculating the value of support and confidence. The system was built using the PHP programming language and 4820 transaction data. The results of data analysis through the website using the Antoni store dataset show the results of association rules. Based on 50 experiments conducted by researchers, if the Antoni shop wants to produce two directions, it is better to use minimum confidence of 10% or 12% with minimum support of 2% or 4%. However, if you want to produce 1 rule, you should use minimum confidence of 14%, 16%, or 18% with minimum support of 2%, 4%, or 6%. The lift ratio value of each minimum belief and the recommended support are more significant than 1. Therefore, the combination of association rules results is solid and valid. It can be used that this algorithm is suitable for a collection of related items, so it is appropriate to be used in analyzing product sales patterns at Antoni Stores. © 2022 IEEE.

Machine Learning Approach: Consumer Buying Behavior Analysis

The rise of multiple company competitors during the COVID-19 outbreak resulted in fierce competition among competing firms for new clients and the retention of current ones. As a result of the foregoing, exceptional customer service is required, regardless of the size of the organization. Furthermore, any company's ability to know each of its customers' desires will provide it an advantage when it comes to providing specialized customer care and establishing customized marketing plans for them. The term 'Consumer Buying Behavior Analysis' refers to a comprehensive assessment of the company's ideal clients/customers. In this project, we're utilizing the K-Means Algorithm to divide clients into two groups: 'Highly Active Customers' and 'Least Active Customers.' Then, utilizing the Apriori Algorithm, we use Association Rule Mining to recommend the best goods to clients based on their purchasing history and associations. We take one step further and use Logistic Regression to validate our Clustering operation by doing Binary Classification with our clusters as the label, resulting in accuracy and an F1 score of 91%. © 2022 IEEE.

Ontology-Based Method for Semantic Association Rules

Finding interesting association rules is a popular and current topic in data mining. The Apriori family of algorithms is built around two rule extraction measures: support and confidence. Even though these two measures are easy to compute, they yield many rules, the majority of which are redundant and may not be of interest to the user. Also, by themselves, support and confidence do not generate strong rules. Additional measures are required to mine interesting facts from data. Ontologies have become the fundamental building blocks for structuring and formalizing data. With the semantic structuring of information, the implicit relationship between data elements makes the analyst get important facts from the data. Our study proposes a novel framework for interestingness in data by combining domain ontology with semantic interestingness measures. The ontology-based method infers rules that are semantically enriched and strong. We analyze the quality of the rule considering the factors defined by the domain experts. It is observed that our methodology generates semantically enriched rules that are more acceptable to domain experts. © 2022 IEEE.

CauRuler: Causal irredundant association rule miner for complex patient trajectory modelling.

BACKGROUND AND OBJECTIVES: Discovering causal associations between variables is one of the main goals of clinical trials, with the ultimate aim of identifying the causes of specific health status. Prior knowledge of causal paths could help ensure patients do not develop the resultant conditions. In recent years, thanks to the enormous amount of health data stored with the support of digital tools, attempts have been made to employ Machine Learning to infer causality. Those methodologies suffer from some deficiencies in controlling cofounders when analysing causality, as well as providing causal rules general enough to be useful in healthcare practice. Conversely, this work presents and evaluates CauRuler, a new approach to deal with causality from association rules. The proposed approach uses a pruning strategy to reduce the association rule set, which does not compromise the causality learning capability of the algorithm. This behaviour makes the algorithm suitable for exploiting large health databases with thousands of patients and medical instances. CauRuler can control a larger number of confounders than other proposals, bringing robustness to causal analysis and avoiding the identification of spurious associations. Additionally, the method generalizes causality using anti-monotone properties to obtain complex and general causal paths. The method can target correct causal associations in complex medical databases with retrospective data. METHOD: CauRuler extends association rule mining with an irredundancy property so that the set of rules learnt is reduced in size and generalized. General association rules, conformed by fewer items, enable controlling more confounding variables to verify, with more statistical evidence on available data, if they represent causal paths in patient disease trajectories. RESULTS: CauRuler has been tested on a complex real medical database (3,5 M visits to the primary care services between 2019 and 2020, and controlling over 15.000 different variables including diagnoses and demographic and other clinical patient data). The reduction of the rule set achieved by the pruning strategy goes from 7.732 to 2.240 rules, from which 46 have been found to have causality relationships in the patient trajectories, and generalized to 14 rules tested as true causal relationships thanks to the confounding analysis. These rules have been validated by clinicians with the support of a graphical map. The obtained causal paths control in average of 906 confounder variables, retrieving robust results. CONCLUSIONS: Causal relationships enable predicting causal paths between health conditions according to patient trajectories. Knowing these causal paths is crucial for understanding and preventing the appearance or worsening of diseases in patients. CauRuler, with high demanding thresholds, has proven its efficiency and effectiveness in targeting previously known causal associations between diagnoses, reaching consensus in the medical community. Softening these thresholds should help target interesting general causal paths.

D-Learning and COVID-19 Crisis: Appraisal of Reactions and Means of Perpetuity.

Distance Learning (D-learning), as an alternative educational solution for students who cannot attend in-person classes, has been deployed during the COVID-19 pandemic to deliver the promises promoted long ago by technology and education experts. For many professors and students, the shift was a first as they had to resume their classes fully online despite not being academically competent to do so. This research paper examines the D-learning scenario introduced by Moulay Ismail University (MIU). It is based on the intelligent Association Rules method to identify relations between different variables. The significance of the method lies in its ability to assist in drawing relevant and accurate conclusions for decision-makers on how to rectify and adjust the adopted D-learning model in Morocco and elsewhere. The method also tracks the most probable future rules that govern the behavior of the population under study vis-à-vis D-learning; once these rules are outlined, the training quality can be dramatically improved by adopting better-informed strategies. The study concludes that most recurrent D-learning issues reported by students systematically interrelate with ownership of gadgets and that once specific procedures are implemented, reports concerning the D-learning experience at MIU are likely to be more comforting.

Data-driven assisted model specification for complex choice experiments data: Association rules learning and random forests for Participatory Value Evaluation experiments

We propose three procedures based on association rules (AR) learning and random forests (RF) to support the specification of a portfolio choice model applied in data from complex choice experiment data, specifically a Participatory Value Evaluation (PVE) choice experiment. In a PVE choice experiment, respondents choose a combination of alternatives, subject to a resource constraint. We combine a methodological-iterative (MI) procedure with AR learning and RF models to support the specification of parameters of a portfolio choice model. Additionally, we use RF model predictions to contrast the validity of the behavioural assumptions of different specifications of the portfolio choice model. We use data of a PVE choice experiment conducted to elicit the preferences of Dutch citizens for lifting COVID-19 measures. Our results show model fit and interpretation improvements in the portfolio choice model, compared with conventional model specifications. Additionally, we provide guidelines on the use of outcomes from AR learning and RF models from a choice modelling perspective. © 2022 The Author(s)

A new QoE-based prediction model for evaluating virtual education systems with COVID-19 side effects using data mining.

Today, emerging technologies such as 5G Internet of things (IoT), virtual reality and cloud-edge computing have enhanced and upgraded higher education environments in universities, colleagues and research centers. Computer-assisted learning systems with aggregating IoT applications and smart devices have improved the e-learning systems by enabling remote monitoring and screening of the behavioral aspects of teaching and education scores of students. On the other side, educational data mining has improved the higher education systems by predicting and analyzing the behavioral aspects of teaching and education scores of students. Due to an unexpected and huge increase in the number of patients during coronavirus (COVID-19) pandemic, all universities, campuses, schools, research centers, many scientific collaborations and meetings have closed and forced to initiate online teaching, e-learning and virtual meeting. Due to importance of behavioral aspects of teaching and education between lecturers and students, prediction of quality of experience (QoE) in virtual education systems is a critical issue. This paper presents a new prediction model to detect technical aspects of teaching and e-learning in virtual education systems using data mining. Association rules mining and supervised techniques are applied to detect efficient QoE factors on virtual education systems. The experimental results described that the suggested prediction model meets the proper accuracy, precision and recall factors for predicting the behavioral aspects of teaching and e-learning for students in virtual education systems.

Association Rules Extraction From the Coronavirus Disease 2019: Attributes on Morbidity and Mortality

This research was aimed to extract association rules on the morbidity and mortality of corona virus disease 2019 (COVID-19). The dataset has four attributes that determine morbidity and mortality;including Confirmed Cases, New Cases, Deaths, and New Deaths. The dataset was obtained as of 2nd April, 2020 from the WHO website and converted to transaction format. The Apriori algorithm was then deployed to extract association rules on these attributes. Six rules were extracted: Rule 1. {Deaths, NewDeaths}=>{NewCases}, Rule 2. {ConfCases, NewDeaths}=>{NewCases}, Rule 3. {ConfCases, Deaths}=>{NewCases}, Rule 4. {Deaths, NewCases}=>{NewDeaths}, Rule 5. {ConfCases, Deaths}=>{NewDeaths}, Rule 6. {ConfCases, NewCases}=>{NewDeaths}, with confidence 0.96, 0.96, 0.86, 0.66, 0.59, 0.51 respectively. These rules provide useful information that is vital on how to curtail further spread and deaths from the virus, both in areas where the pandemic is already ravaging and in areas yet to experience the outbreak.

Applying Clustering and Association Rules on attracting tourists to the South Central Area post Covid-19 pandemic in Vietnam

Covid-19 has caused a plummet in the number of tourists visiting to the South Central of Vietnam and driven changes in their traveling behaviors. This has formed challenging barriers over the operations of entities in the tourism industry. The purpose of this paper is supporting the tourism organizations to attract domestic and foreign visitors to the South Central of Vietnam post the pandemic. The research uses the secondary data collected by Vitours company - a leading travel agency in South Central - to demonstrate tourists' demands when visiting destinations in the area between September 2020 and April 2021. Data mining, clustering and association rules techniques are also applied to classify traveler's segmentations and analyze the connections among these groups. The findings of this research indicates 4 clusters of tourists and 6 association rules, which contributes to the stimulus of the tourism industry in South Central after Covid-19. © 2022 ACM.

Mining Association Rules in Commuter Feedback Comments from Facebook of Swiss National Railways (SBB) Using Apriori Algorithm

Nowadays, all kinds of service-based organizations open online feedback possibilities for customers to share their opinion. Swiss National Railways (SBB) uses Facebook to collect commuters' feedback and opinions. These customer feedbacks are highly valuable to make public transportation option more robust and gain trust of the customer. The objective of this study was to find interesting association rules about SBB's commuters pain points. We extracted the publicly available FB visitor comments and applied manual text mining by building categories and subcategories on the extracted data. We then applied Apriori algorithm and built multiple frequent item sets satisfying the minsup criteria. Interesting association rules were found. These rules have shown that late trains during rush hours, deleted but not replaced connections on the timetable due to SBB's timetable optimization, inflexibility of fines due to unsuccessful ticket purchase, led to highly customer discontent. Additionally, a considerable amount of dissatisfaction was related to the policy of SBB during the initial lockdown of the Covid-19 pandemic. Commuters were often complaining about lack of efficient and effective measurements from SBB when other passengers were not following Covid-19 rules like public distancing and were not wearing protective masks. Such rules are extremely useful for SBB to better adjust its service and to be better prepared by future pandemics. © 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.