Data Mining Practical Machine Learning Tools and Techniques

COVID-19 is the disease evoked by a new breed of coronavirus called the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Recently, COVID-19 has become a pandemic by infecting more than 152 million people in over 216 countries and territories. The exponential increase in the number of infections has rendered traditional diagnosis techniques inefficient. Therefore, many researchers have developed several intelligent techniques, such as deep learning (DL) and machine learning (ML), which can assist the healthcare sector in providing quick and precise COVID-19 diagnosis. Therefore, this paper provides a comprehensive review of the most recent DL and ML techniques for COVID-19 diagnosis. The studies are published from December 2019 until April 2021. In general, this paper includes more than 200 studies that have been carefully selected from several publishers, such as IEEE, Springer and Elsevier. We classify the research tracks into two categories: DL and ML and present COVID-19 public datasets established and extracted from different countries. The measures used to evaluate diagnosis methods are comparatively analysed and proper discussion is provided. In conclusion, for COVID-19 diagnosing and outbreak prediction, SVM is the most widely used machine learning mechanism, and CNN is the most widely used deep learning mechanism. Accuracy, sensitivity, and specificity are the most widely used measurements in previous studies. Finally, this review paper will guide the research community on the upcoming development of machine learning for COVID-19 and inspire their works for future development. This review paper will guide the research community on the upcoming development of ML and DL for COVID-19 and inspire their works for future development.

https://onlinelibrary.wiley.com/doi/pdf/10.1111/exsy.12759

Review on COVID-19 diagnosis models based on machine learning and deep learning approaches.

Data mining algorithms play an important role in the prediction of early-stage breast cancer. In this paper, we propose an approach that improves the accuracy and enhances the performance of three different classifiers: Decision Tree (J48), Naive Bayes (NB), and Sequential Minimal Optimization (SMO). We also validate and compare the classifiers on two benchmark datasets: Wisconsin Breast Cancer (WBC) and Breast Cancer dataset. Data with imbalanced classes are a big problem in the classification phase since the probability of instances belonging to the majority class is significantly high, the algorithms are much more likely to classify new observations to the majority class. We address such problem in this work. We use the data level approach which consists of resampling the data in order to mitigate the effect caused by class imbalance. For evaluation, 10 fold cross-validation is performed. The efficiency of each classifier is assessed in terms of true positive, false positive, Roc curve, standard deviation (Std), and accuracy (AC). Experiments show that using a resample filter enhances the classifier’s performance where SMO outperforms others in the WBC dataset and J48 is superior to others in the Breast Cancer dataset.

/pdf/analysis-of-breast-cancer-detection-using-different-machine-316yii3jxg.pdf

Analysis of Breast Cancer Detection Using Different Machine Learning Techniques

Evaluation of the reverse logistics performance in civil construction

Diabetes Diagnostic Prediction Using Vector Support Machines

The internationalization and positioning of universities offers relative comparisons, studied according to different teaching and research criteria. Among the recognized rankings are the Academic Ranking of World Universities (ARWU) or Ranking of Shanghai, QS World University Ranking, SCimago Institutions Rankings SIR and the Web Ranking of Universities-Webometrics. Comparatively, characteristics of each one are presented in terms of scope, volume of universities positioned and evaluation criteria. The indicators associated with research and institutional capacity stand out as common criteria in the revised evaluation methodologies. Regarding Latin America, Brazil leads with its presence in the four rankings. There is a greater number of Latin American universities in QS (40%) and Webometrics (31%), in the other two rankings it does not exceed 8%.

/pdf/analysis-of-patterns-in-the-university-world-rankings-2rybgnu8hm.pdf

Analysis of patterns in the university world rankings webometrics, Shanghai, QS and SIR-SCimago: Case Latin America

Due to the processes of internationalization, competitiveness and other related factors, universities have implemented policies and management systems that allow them to monitor and measure their world ranking position. The present work analyzes a group of manageable visibility factors corresponding to universities present in the Top100 of Latin American Webometrics database published in January 2017 for the identification of profiles. For this purpose, information was collected about: the academic offer and scientific journals published on each university website, figures on documents and profiles found in Google Scholar, activity on social networks, and the institutional score reported by ResearchGate as a scientific network. Clusters were formed by quartiles to characterize the visibility profiles of Latin American universities considering the variables studied. The high offer of postgraduate degrees and presence in scientific networks and Google Scholar characterize the best positioned universities.

/pdf/web-visibility-profiles-of-top100-latin-american-3roifwi5z6.pdf

Web Visibility Profiles of Top100 Latin American Universities

Wireless sensor network for forest fire detection

The study analyzes the factors that contribute to the technical efficiency of the visibility of the universities included in the Top100 of the Latin American Universities Ranking Web published by Webometrics database in January, 2017. Data Envelopment Analysis (DEA) was used to calculate the contributions of input variables to efficiency. As data sources for inputs, the study considers the academic data published on the web of each university, the content and profiles displayed from Google Scholar (GS), data by university published in ResearchGate as a scientific network, and finally, data from social networks as Twitter and Facebook accounts of the respective institutions. The postgraduate offer, visibility in GS, and the use of scientific and social networks contribute favorably to the web positioning of Latin American universities.

/pdf/efficiency-analysis-of-the-visibility-of-latin-american-2mgnvw6jch.pdf

Efficiency analysis of the visibility of Latin American universities and their impact on the ranking web

The purpose of this paper is to present the results of the application of exploratory factor analysis to demonstrate that factors external to the organization influence the outcome of the Evaluation of the level of psychosocial risks. The variables corresponding to external factors are obtained from the Social Determinants of Health Model of the World Health Organization (WHO). These measurement tools are used for companies with a high number of workers, so a large amount of data is generated. The elements included in the construct validation are: the Kaiser-Meyer-Olkin (KMO) sample adequacy measure, Barlett’s sphericity test, the communalities, the explained variance percentages, the matrix of factor structure components, the graph of sedimentation and the matrix of rotated components. As a result, we obtain that external factors have a significant impact on the assessment of the level of psychosocial risks. The external variables found are: education, health care services, housing conditions, means of transport, living conditions.

/pdf/factor-analysis-of-the-psychosocial-risk-assessment-1ykjqhv07j.pdf

Noel Varela

Papers

Analysis of patterns in the university world rankings webometrics, Shanghai, QS and SIR-SCimago: Case Latin America

Web Visibility Profiles of Top100 Latin American Universities

Wireless sensor network for forest fire detection

Efficiency analysis of the visibility of Latin American universities and their impact on the ranking web

Factor Analysis of the Psychosocial Risk Assessment Instrument