Adaptive Human Machine Interaction Approach for Feature Selection-Extraction Task in Medical Data Mining

Perova, Iryna; Bodyanskiy, Yevgeniy

doi:10.47839/ijc.17.2.997

Cited by 13 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Among other problems of classification of short sets of biomedical data using machine learning methods, the problem of automatic selection/extraction of important features for classification should be highlighted, taking into account the multidimensionality of such data [7]. Additionally, models trained on short datasets can be more vulnerable to outliers, noise, and anomalies in the input data.…”

Section: Introductionmentioning

confidence: 99%

An Unsupervised-Supervised Ensemble Technology With Non-Iterative Training Algorithm for Small Biomedical Data Analysis

IZONIN

2023

CSIT

View full text Add to dashboard Cite

Improving the accuracy of intelligent data analysis is an important task in various application areas. Existing machine learning methods do not always provide a sufficient level of classification accuracy for their use in practice. That is why, in recent years, hybrid ensemble methods of intellectual data analysis have begun to develop. They are based on the combined use of clustering and classification procedures. This approach provides an increase in the accuracy of the classifier based on machine learning due to the expansion of the space of the input data of the task by the results of the clustering. In this paper, the tasks of modification and improvement of such technology for small data analysis are considered. The basis of the modification is the use of clustering with output at the first step of the method to increase the accuracy of the entire technology. Despite the high accuracy of the work, this approach requires a significant expansion of the inputs of the final linear classifier (labels of the obtained clusters are added to the initial inputs). To avoid this shortcoming, the paper proposes an improvement based on the introduction of a new classification procedure at the first step of the method and replaces all the initial inputs of the task with the results of its work. In parallel with it, clustering is performed taking into account the original attribute, the results of which are added to the output of the classifier of the first step. In this way, the formation of an expanded set of data of significantly lower dimensionality in comparison with the existing method takes place (here there is no longer a large number of initial features, which is characteristic of biomedical engineering tasks). This reduces the training time of the method and increases its generalization properties. Modeling of the method was based on the use of a short dataset contained in an open repository. After the preprocessing procedures, the dataset has only 294 vectors, each of which was characterized by 18 attributes. Data classification was done using an SGTM-based neural-like structure classifier. This linear classifier provides high accuracy of work. In addition, it does not provide for the implementation of an iterative training procedure and additional adjustment of work parameters. Data clustering was performed using the k-means method. This choice is due to both the simplicity and speed of its work. The search for the optimal number of k-means clusters was carried out using 4 different methods. They all showed different results. That is why, some experiments were conducted to assess the influence of different numbers of clusters (from 3 to 7) on the accuracy of all 4 algorithms of the developed technology. The accuracy of the proposed technology has been established experimentally in comparison with the linear classifier and the existing hybrid method. In addition, by reducing the inputs of the final classifier, the developed technology reduces the duration of the training procedure compared to the basic method. All this ensures the possibility of using the proposed technology when solving various applied problems of medical diagnostics, in particular, based on the analysis of small data. Keywords: small data approach, non-iterative training, ensemble learning, unsupervised-supervised technology, biomedical engineering.

show abstract

Section: Introductionmentioning

confidence: 99%

An Unsupervised-Supervised Ensemble Technology With Non-Iterative Training Algorithm for Small Biomedical Data Analysis

IZONIN

2023

CSIT

View full text Add to dashboard Cite

show abstract

“…Introduction. Intelligent analysis of biomedical datasets by machine learning tools is a difficult task due to many features of such data, in particular [1,2]:  the multiparametric nature of such datasets;  the need to take into account medical, biological, engineering, and technical features of biomedical datasets;  complex non-linear interconnections inside of the tabular dataset;  the presence of both numerical and categorical features;  the presence of a large number of omissions, anomalies and outliers that occur during data collection;  etc. All this significantly affects the accuracy and generalization properties of machine learning (ML) tools.…”

mentioning

confidence: 99%

“…Having meaning pred i y from (4) and pred i z from (8) we can perform the first adjustment of the sought initial value (1) i y (5) using the following expression [10]:…”

mentioning

confidence: 99%

An Ensemble Method for the Regression Model Parameter Adjustments: Direct Approach

Izonin

2023

mcm-tech

View full text Add to dashboard Cite

Intelligence analysis of tabular datasets in the field of biomedical engineering is a complex task. This is explained both by the multidimensional datasets and the complex relationships between the components of the set, and by the high price of the error in the prediction. The task becomes more difficult in the case of limited data for training, which often occurs in this field. This is due to the enormous time, material, or human resources required to collect enough data to implement training procedures with classical machine learning tools. This paper presents a new approach to solving this task. The author has developed a new ensemble method for the regression model parameters adjustments (direct approach) with the possibility of cyclically increasing the accuracy of intellectual analysis of short datasets. The basis of the method is the use of the rational fraction and two machine learning algorithms for its parametric identification. Modeling of the method's efficiency on a real-world short set of data from the field of biomedical engineering demonstrated the high accuracy of the developed method's operation. In particular, the prediction accuracy of the General Regression Neural Network was increased by more than 14% (based on the coefficient of determination. That is why the developed method can be used to solve various applied biomedical engineering tasks in the case of the need to analyze small amounts of data

show abstract

“…Використання методу кластерного аналізу (Fuzzy-c-means) при встановленні частки внеску кожного з чинників у загальний біологічний ефект сполученої дії є ефективним методичним підходом з максимальною об'єктивізацією даних за рахунок визначення відстані між центрами кластерів кожної з груп на кожному із днів експерименту [11]. Для візуалізації даних методом головних компонент та отримання при цьому лінійно роздільних кластерів був використаний метод Feature Selection-Extraction [12], що дозволило встановити провідні за внеском фактори і далі виявити фізіологічні механізми, в основі яких лежать відповідні реакції організму на вплив саме зниженої температури. Знижена температура є сильним стресором, який викликає суттєві фізіологічні зрушення в організмі в сторону підтримки термогенезу, що може обтяжувати відповідь на інші фактори, що впливають [13].…”

unclassified

Peculiarities of Evaluation of Biological Effects of the Influence of Electromagnetic Radiation in Conditions of Reduced Temperature (Experiment)

Літовченко¹,

Perova²

2021

Ukr. ž. med. bìol. sportu

View full text Add to dashboard Cite

In modern conditions there is a high need to improve methods for establishing the nature of the combined influence of factors using modern approaches for further development of prevention measures against the negative impact of factors on the body. The purpose of the study was to investigate the combined effect of electromagnetic radiation and low temperatures with subsequent determination of the level of contribution of each factor in the formation of biological effects within the experiment by mathematical analysis of data using the method of artificial intelligence. Materials and methods. The subchronic experiment (30 days) was performed on male rats. The animals were divided into groups: combined exposure to electromagnetic radiation (70 kHz, 600 V/m) and reduced temperature (40C), isolated exposure to reduced temperature, isolated exposure to electromagnetic radiation and a control group. The establishment of biological effects was performed at stages 5, 15 and 30 days of the experiment. Changes in the body were assessed by physiological, biochemical and immunological parameters of the blood (30 indicators). Data processing was performed using computational intelligence methods (Neuro-fuzzy system). Results and discussion. The combined effect of the factors was manifested by the following biological effects: intensification of peroxidation processes with simultaneous moderate suppression of antioxidant protection, intensification of lipid metabolism was characterized by dyslipoproteinemia, manifesting in: increase in triglycerides, cholesterol and its fractions. Changes of the immune system were decrease in the ability of neutrophils to phagocytosis at different stages of the experiment, imbalance of the activation of the system of reducing the concentration of C4 at the background of increased intensity of IgM and IgG synthesis. The method of determining the intensity of the factors, developed on the basis of factor and cluster analysis, allowed to determine that during the experiment the ratios between the factors changed, but the greatest contribution was made by reduced temperature by both biochemical parameters (63%) and immunological (53%) at the same time, the level of electromagnetic radiation contribution was 37% and 47%, respectively. Thus, the reduced temperature was the leading factor in the combined effect, which added 60% to the overall biological effect throughout the study, against the effect of electromagnetic radiation for which the level of contribution was only 40%. By means of the factor analysis informative indicators, making it possible to establish the characteristics of biological effects, and therefore leading indicators in formation of biological effects were the increase in concentration of DC with simultaneous decrease in concentration of SH-groups, increase in VLDL and suppression of oxygen-dependent metabolism of neutrophil-test. Conclusion. Thus, the tested mathematical approach allowed to determine the leading role of each of the studied factors under the conditions of their combined influence in different systems, which allows to predict probable appropriate reactions of the whole organism and gives a reasonable approach to the development of preventive measures

show abstract

Adaptive Human Machine Interaction Approach for Feature Selection-Extraction Task in Medical Data Mining

Cited by 13 publications

References 18 publications

An Unsupervised-Supervised Ensemble Technology With Non-Iterative Training Algorithm for Small Biomedical Data Analysis

An Unsupervised-Supervised Ensemble Technology With Non-Iterative Training Algorithm for Small Biomedical Data Analysis

An Ensemble Method for the Regression Model Parameter Adjustments: Direct Approach

Peculiarities of Evaluation of Biological Effects of the Influence of Electromagnetic Radiation in Conditions of Reduced Temperature (Experiment)

Contact Info

Product

Resources

About