A cluster-based intelligence ensemble learning method for classification problems

Analysis of risk factors in diabetics resulted from polycystic ovary syndrome in women by EDA analysis and machine learning techniques

This study discusses the relationship between Polycystic Ovary Syndrome (PCOS) and diabetes in women, which has become increasingly prevalent due to changing lifestyles and environmental factors. The characteristic that distinguishes women with PCOS is hyperandrogenism which results from abnormal ovarian or adrenal function, which leads to the overproduction of androgens. Excessive androgens in women increase the risk of Type 2 diabetes (T2D) and insulin resistance (IR). Nowadays, diabetes affects people of all ages and is linked to factors such as lifestyle, genetics, stress, and aging. Diabetes, the uncontrolled high blood sugar level can potentially harm kidneys, nerves, eyes, and other organs and there is no cure, making it a concerning disease in developing nations. This research tried to submit the evidence through feature-wise correlation analyses between PCOS and diabetes. Hence, this model utilized the Exploratory Data Analysis (EDA) and the Elbow clustering algorithms for the experimental purpose in which the EDA deeply analyzed the features of PCOS and diabetes and recorded a positive correlation of 95%. The Elbow clustering technique is employed for verifying the correlations identified through EDA. Although limited research exists on this specific disease, this work provides potential evidence for the research community by evaluating the clustering results using Silhouette Score, Calinski-Harabasz Index, and Davies-Bouldin Index.

Cluster-based deep ensemble learning for emotion classification in Internet memes

Memes have gained popularity as a means to share visual ideas through the Internet and social media by mixing text, images and videos, often for humorous purposes. Research enabling automated analysis of memes has gained attention in recent years, including among others the task of classifying the emotion expressed in memes. In this article, we propose a novel model, cluster-based deep ensemble learning (CDEL), for emotion classification in memes. CDEL is a hybrid model that leverages the benefits of a deep learning model in combination with a clustering algorithm, which enhances the model with additional information after clustering memes with similar facial features. We evaluate the performance of CDEL on a benchmark data set for emotion classification, proving its effectiveness by outperforming a wide range of baseline models and achieving state-of-the-art performance. Further evaluation through ablated models demonstrates the effectiveness of the different components of CDEL.

On the Suitability of Bagging-Based Ensembles with Borderline Label Noise

Real-world classification data usually contain noise, which can affect the accuracy of the models and their complexity. In this context, an interesting approach to reduce the effects of noise is building ensembles of classifiers, which traditionally have been credited with the ability to tackle difficult problems. Among the alternatives to build ensembles with noisy data, bagging has shown some potential in the specialized literature. However, existing works in this field are limited and only focus on the study of noise based on a random mislabeling, which is unlikely to occur in real-world applications. Recent research shows that other types of noise, such as that occurring at class boundaries, are more common and challenging for classification algorithms. This paper delves into the analysis of the usage of bagging techniques in these complex problems, in which noise affects the decision boundaries among classes. In order to investigate whether bagging is able to reduce the impact of borderline noise, an experimental study is carried out considering a large number of datasets with different noise levels, and several noise models and classification algorithms. The results obtained reflect that bagging obtains a better accuracy and robustness than the individual models with this complex type of noise. The highest improvements in average accuracy are around 2–4% and are generally found at medium-high noise levels (from 15–20% onwards). The partial consideration of noisy samples when creating the subsamples from the original training set in bagging can make it so that only some parts of the decision boundaries among classes are impaired when building each model, reducing the impact of noise in the global system.

A two-layer nested heterogeneous ensemble learning predictive method for COVID-19 mortality

The COVID-19 epidemic has had a great adverse impact on the world, having taken a heavy toll, killing hundreds of thousands of people. In order to help the world better combat COVID-19 and reduce its death toll, this study focuses on the COVID-19 mortality. First, using the multiple stepwise regression analysis method, the factors from eight aspects (economy, society, climate etc.) that may affect the mortality rates of COVID-19 in various countries is examined. In addition, a two-layer nested heterogeneous ensemble learning-based prediction method that combines linear regression (LR), support vector machine (SVM), and extreme learning machine (ELM) is developed to predict the development trends of COVID-19 mortality in various countries. Based on data from 79 countries, the experiment proves that age structure (proportion of the population over 70 years old) and medical resources (number of beds) are the main factors affecting the mortality of COVID-19 in each country. In addition, it is found that the number of nucleic acid tests and climatic factors are correlated with COVID-19 mortality. At the same time, when predicting COVID-19 mortality, the proposed heterogeneous ensemble learning-based prediction method shows better prediction ability than state-of-the-art machine learning methods such as LR, SVM, ELM, random forest (RF), long short-term memory (LSTM) etc.