Developing a new approach for design support of subsurface constructed wetland using machine learning algorithms

Drug reviews are commonly used in pharmaceutical industry to improve the medications given to patients. Generally, drug review contains details of drug name, usage, ratings and comments by the patients. However, these reviews are not clean, and there is a need to improve the cleanness of the review so that they can be benefited for both pharmacists and patients. To do this, we propose a new approach that includes different steps. First, we add extra parameters in the review data by applying VADER sentimental analysis to clean the review data. Then, we apply different machine learning algorithms, namely linear SVC, logistic regression, SVM, random forest, and Naive Bayes on the drug review specify dataset names. However, we found that the accuracy of these algorithms for these datasets is limited. To improve this, we apply stratified K-fold algorithm in combination with Logistic regression. With this approach, the accuracy is increased to 96%.

Download Full-text

Management and monitoring of the displaced commercial risk: a prescriptive approach

International Journal of Emerging Markets ◽

10.1108/ijoem-07-2018-0407 ◽

2020 ◽

Vol ahead-of-print (ahead-of-print) ◽

Author(s):

Othmane Touri ◽

Rida Ahroum ◽

Boujemâa Achchab

Keyword(s):

Machine Learning ◽

Design Methodology ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Management Tool ◽

Islamic Finance ◽

Investment Risk ◽

New Approach ◽

Content Type ◽

Several Variables

Purpose The displaced commercial risk is one of the specific risks in the Islamic finance that creates a serious debate among practitioners and researchers about its management. The purpose of this paper is to assess a new approach to manage this risk using machine learning algorithms. Design/methodology/approach To attempt this purpose, the authors use several machine learning algorithms applied to a set of financial data related to banks from different regions and consider the deposit variation intensity as an indicator. Findings Results show acceptable prediction accuracy. The model could be used to optimize the prudential reserves for banks and the incomes distributed to depositors. Research limitations/implications However, the model uses several variables as proxies since data are not available for some specific indicators, such as the profit equalization reserves and the investment risk reserves. Originality/value Previous studies have analyzed the origin and impact of DCR. To the best of authors’ knowledge, none of them has provided an ex ante management tool for this risk. Furthermore, the authors suggest the use of a new approach based on machine learning algorithms.

Download Full-text

One model to rule them all? Using machine learning algorithms to determine the number of factors in exploratory factor analysis.

10.31234/osf.io/u8eca ◽

2020 ◽

Author(s):

David Goretzko ◽

Markus Bühner

Keyword(s):

Machine Learning ◽

Factor Analysis ◽

Exploratory Factor Analysis ◽

Learning Algorithms ◽

Common Factor ◽

Machine Learning Algorithms ◽

Gradient Boosting ◽

New Approach ◽

Correct Number ◽

Number Of Factors

Determining the number of factors is one of the most crucial decisions a researcher has to face when conducting an exploratory factor analysis. As no common factor retention criterion can be seen as generally superior, a new approach is proposed - combining extensive data simulation with state-of-the-art machine learning algorithms. First, data was simulated under a broad range of realistic conditions and three algorithms were trained using specially designed features based on the correlation matrices of the simulated data sets. Subsequently, the new approach was compared to four common factor retention criteria with regard to its accuracy in determining the correct number of factors in a large-scale simulation experiment. Sample size, variables per factor, correlations between factors, primary and cross-loadings as well as the correct number of factors were varied to gain comprehensive knowledge of the efficiency of our new method. A gradient boosting model outperformed all other criteria, so in a second step, we improved this model by tuning several hyperparameters of the algorithm and using common retention criteria as additional features. This model reached an out-of-sample accuracy of 99.3% (the pre-trained model can be obtained from https://osf.io/mvrau/). A great advantage of this approach is the possibility to continuously extend the data basis (e.g. using ordinal data) as well as the set of features to improve the predictive performance and to increase generalizability.

Download Full-text

Potential of machine learning methods to identify patients with nonvalvular atrial fibrillation

Future Cardiology ◽

10.2217/fca-2019-0056 ◽

2020 ◽

Vol 16 (1) ◽

pp. 43-52

Author(s):

Ryoko Suzuki ◽

Jun Katada ◽

Sreeram Ramagopalan ◽

Laura McDonald

Keyword(s):

Machine Learning ◽

Atrial Fibrillation ◽

Learning Algorithms ◽

Area Under The Curve ◽

Machine Learning Algorithms ◽

Nonvalvular Atrial Fibrillation ◽

New Approach ◽

Increased Risk ◽

Sensitivity Specificity ◽

Retrospective Database

Aim: Nonvalvular atrial fibrillation (NVAF) is associated with an increased risk of stroke however many patients are diagnosed after onset. This study assessed the potential of machine-learning algorithms to detect NVAF. Materials & methods: A retrospective database study using a Japanese claims database. Patients with and without NVAF were selected. 41 variables were included in different classification algorithms. Results: Machine learning algorithms identified NVAF with an area under the curve of >0.86; corresponding sensitivity/specificity was also high. The stacking model which combined multiple algorithms outperformed single-model approaches (area under the curve ≥0.90, sensitivity/specificity ≥0.80/0.82), although differences were small. Conclusion: Machine-learning based algorithms can detect atrial fibrillation with accuracy. Although additional validation is needed, this methodology could encourage a new approach to detect NVAF.

Download Full-text

Online Discretization of Continuous-Valued Attributes in Rule Induction

Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science ◽

10.1243/095440605x31571 ◽

2005 ◽

Vol 219 (8) ◽

pp. 829-842 ◽

Cited By ~ 6

Author(s):

D. T. Pham ◽

A. A. Afify

Keyword(s):

Machine Learning ◽

Learning Process ◽

Learning Algorithms ◽

Rule Induction ◽

Machine Learning Algorithms ◽

Learning System ◽

Engineering Applications ◽

New Approach ◽

Numerical Attributes

Machine learning algorithms designed for engineering applications must be able to handle numerical attributes, particularly attributes with real (or continuous) values. Many algorithms deal with continuous-valued attributes by discretizing them before starting the learning process. This paper describes a new approach for discretization of continuous-valued attributes during the learning process. Incorporating discretization within the learning process has the advantage of taking into account the bias inherent in the learning system as well as the interactions between the different attributes. Experiments have demonstrated that the proposed method, when used in conjunction with the SRI rule induction algorithm developed by the authors, improves the accuracy of the induced model.

Download Full-text

A Novel System Design for Prognosis on Breast Cancer using Machine Learning Algorithms

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.d1622.029420 ◽

2020 ◽

Vol 9 (4) ◽

pp. 1484-1490

Keyword(s):

Breast Cancer ◽

Machine Learning ◽

Learning Algorithm ◽

Early Stage ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

New Approach ◽

Cancer Breast ◽

Abnormal Cells ◽

Deadly Disease

Cancer is the term used to describe a class of disease in which abnormal cells divide uncontrolledly and invade body tis sues. There are more than 100 unique types of cancer. Breast cancer is one of the women's deadly disease. The prediction is done at the earlier stage and the results are accurate, the number of death per year can be reduced. So ultimately a new approach is needed to predict the level of cancer at the early stage which shows accurate results on prediction level. Hence Machine learning algorithms are used to predict the level of accuracy. Henceforth this paper analyze the different machine learning algorithm to predict the best levels of cancer and comparative statement was made about accuracy and the results showing SVM is more accurate.

Download Full-text