Hierarchical ensemble learning method in diversified dataset analysis

The remarkable advances in ensemble machine learning methods have led to a significant analysis in large data, such as random forest algorithms. However, the algorithms only use the current features during the process of learning, which caused the initial upper accuracy’s limit no matter how well the algorithms are. Moreover, the low classification accuracy happened especially when one type of observation’s proportion is much lower than the other types in training datasets. The aim of the present study is to design a hierarchical classifier which try to extract new features by ensemble machine learning regressors and statistical methods inside the whole machine learning process. In stage 1, all the categorical variables will be characterized by random forest algorithm to create a new variable through regression analysis while the numerical variables left will serve as the sample of factor analysis (FA) process to calculate the factors value of each observation. Then, all the features will be learned by random forest classifier in stage 2. Diversified datasets consist of categorical and numerical variables will be used in the method. The experiment results show that the classification accuracy increased by 8.61%. Meanwhile, it also improves the classification accuracy of observations with low proportion in the training dataset significantly.

MANAGEMENT ORGANIZATION ACCESS TO MEDICAL INFORMATION SYSTEMS USING THE METHODS SEMANTIC PROXIMITY

На основе анализа применения моделей управления доступом с использованием тематических иерархических классификаторов в медицинских информационных системах с применением мобильных систем в качестве элементов предложены методы формирования доверительных прав на доступ к объектам. При использовании традиционных тематически иерархических моделей управления доступа логическая информационная архитектура ресурсов медицинских информационных систем формирует собой тематический иерархический классификатор (рубрикатор). Диаграмма Хассе вводит отношения порядка в тематическом классификаторе на решетке безопасности для формирования доверительно - тематических полномочий пользователей медицинских информационных систем. Построение диаграмм Хассе на решетке безопасности включающей несколько уровней безопасности достаточно сложная алгоритмическая задача. При построении доверительно - тематических полномочий пользователей для избегания неопределенности при неполноте построенной диаграммы Хассе и завышения предоставленных полномочий при формировании прав доступа предлагается использовать семантическую близость запроса на доступ пользователя и тематической рубрики иерархического классификатора. Анализ существующих подходов к формированию метрик семантической близости показал, что в качестве наилучшей метрики для задания доверительных полномочий пользователя может использоваться меры близости, основанные на иерархии понятий Based on the analysis of the application of access control models using thematically hierarchical classifiers in medical information systems using mobile technologies (MS), methods of forming access rights to objects are proposed. When using traditional thematically hierarchical access control models, the logical information architecture of the medical information systems resources forms a thematic hierarchical classifier (rubricator). The Hasse diagram introduces order relations into the thematic classifier on the security grid to form the trust-thematic powers of the medical information systems users. The construction of Hasse diagrams on a security grid that includes several security levels is a rather complex algorithmic task. When constructing trust-thematic user powers to avoid ambiguity in the case of incompleteness of the constructed Hasse diagram and overestimation of the granted powers when forming access rights, it is proposed to use the semantic proximity of the user's access request and the thematic heading of the hierarchical classifier. An analysis of existing approaches to the formation of semantic proximity metrics showed that proximity measures based on a hierarchy of concepts can be used as the best metric for setting the user's trust authority

Using Transfer Learning and Hierarchical Classifier to Diagnose Melanoma From Dermoscopic Images

The deadliest form of skin cancer is melanoma, and if detected in time, it is curable. Detection of melanoma using biopsy is a painful and time-consuming task. Alternate means are being used by medical experts to diagnose melanoma by extracting features from skin lesion images. Medical image diagnosis requires intelligent systems. Many intelligent systems based on image processing and machine learning have been proposed by researchers in the past to detect different kinds of diseases that are successfully used by healthcare organisations worldwide. Intelligent systems to detect melanoma from skin lesion images are also evolving with the aim of improving the accuracy of melanoma detection. Feature extraction plays a critical role. In this paper, a model is proposed in which features are extracted using convolutional neural network (CNN) with transfer learning and a hierarchical classifier consisting of random forest (RF), k-nearest neighbor (KNN), and adaboost is used to detect melanoma using the extracted features. Experimental results show the effectiveness of the proposed model.

Learn class hierarchy using convolutional neural networks

A large amount of research on Convolutional Neural Networks (CNN) has focused on flat Classification in the multi-class domain. In the real world, many problems are naturally expressed as hierarchical classification problems, in which the classes to be predicted are organized in a hierarchy of classes. In this paper, we propose a new architecture for hierarchical classification, introducing a stack of deep linear layers using cross-entropy loss functions combined to a center loss function. The proposed architecture can extend any neural network model and simultaneously optimizes loss functions to discover local hierarchical class relationships and a loss function to discover global information from the whole class hierarchy while penalizing class hierarchy violations. We experimentally show that our hierarchical classifier presents advantages to the traditional classification approaches finding application in computer vision tasks. The same approach can also be applied to some CNN for text classification.

The Hierarchical Classifier for COVID-19 Resistance Evaluation

Finding dependencies in the data requires the analysis of relations between dozens of parameters of the studied process and hundreds of possible sources of influence on this process. Dependencies are nondeterministic and therefore modeling requires the use of statistical methods for analyzing random processes. Part of the information is often hidden from observation or not monitored. That is why many difficulties have arisen in the process of analyzing the collected information. The paper aims to find frequent patterns and parameters affected by COVID-19. The novelty of the paper is hierarchical architecture comprises supervised and unsupervised methods. It allows the development of an ensemble of the methods based on k-means clustering and classification. The best classifiers from the ensemble are random forest with 500 trees and XGBoost. Classification for separated clusters gives us higher accuracy on 4% in comparison with dataset analysis. The proposed approach can be used also for personalized medicine decision support in other domains. The features selection allows us to analyze the following features with the highest impact on COVID-19: age, sex, blood group, had influenza.

Scalable classification of organisms into a taxonomy using hierarchical supervised learners

Accurately identifying organisms based on their partially available genetic material is an important task to explore the phylogenetic diversity in an environment. Specific fragments in the DNA sequence of a living organism have been defined as DNA barcodes and can be used as markers to identify species efficiently and effectively. The existing DNA barcode-based classification approaches suffer from three major issues: (i) most of them assume that the classification is done within a given taxonomic class and/or input sequences are pre-aligned, (ii) highly performing classifiers, such as SVM, cannot scale to large taxonomies due to high memory requirements, (iii) mutations and noise in input DNA sequences greatly reduce the taxonomic classification score. In order to address these issues, we propose a multi-level hierarchical classifier framework to automatically assign taxonomy labels to DNA sequences. We utilize an alignment-free approach called spectrum kernel method for feature extraction. We build a proof-of-concept hierarchical classifier with two levels, and evaluated it on real DNA sequence data from barcode of life data systems. We demonstrate that the proposed framework provides higher f1-score than regular classifiers. Besides, hierarchical framework scales better to large datasets enabling researchers to employ classifiers with high classification performance and high memory requirement on large datasets. Furthermore, we show that the proposed framework is more robust to mutations and noise in sequence data than the non-hierarchical classifiers.