Intelligent information retrieval for reducing missed cancer and improving the healthcare system

This study presents an intelligent information retrieval system that will effectively extract useful information from breast cancer datasets and utilized that information to build a classification model. The proposed model will reduce the missed cancer rate by providing a comprehensive decision support to the radiologist. The model is built on two datasets, Wisconsin Breast Cancer Dataset (WBCD) and 365 free text mammography reports from a hospital. Effective pre-processing techniques including filling missing values with regression, an effective Natural Language Processing (NLP) Parser is developed to handle free text mammography reports, balancing the dataset with Synthetic Minority Oversampling (SMOTE) was applied to prepare the dataset for learning. Most relevant features were selected with the help of filter method and tf-idf scores. K-NN and SGD classifiers are optimized with optimum value of k for K-NN and hyper tuning the SGD parameters with grid search technique.

RESEARCH OF APPROACHES TO THE RECOGNITION OF SEMANTIC IMAGES OF SCIENTIFIC PUBLICATIONS BASED ON NEURAL NETWORKS

The paper is devoted to the problems of orientation and navigation in the world of verbal presentation of scientific knowledge. The solution of these problems is currently hampered by the lack of intelligent information retrieval systems that allow comparing descriptions of various scientific works at the level of coincidence of semantic situations, rather than keywords. The article discusses methods for the formation and recognition of semantic images of scientific publications belonging to specific subject areas. The method for constructing a semantic image of a scientific text developed by Iuliia Bruttan allows to form an image of the text of a scientific publication, which can be used as input data for a neural network. Training of this neural network will automate the processes of pattern recognition and classification of scientific publications according to specified criteria. The approaches to the recognition of semantic images of scientific publications based on neural networks considered in the paper can be used to organize the semantic search for scientific publications, as well as in the design of intelligent information retrieval systems.

System Development for Intelligent Search in Industrial Standards

The article is devoted to the description of intelligent information retrieval system development according to industry standards based on the Stanford CoreNLP tool. The description of the subject area, design, and main stages of system development are presented: development of extracting information module from industrial standards, implementation of a web service using the Flask framework, and a client web application on React JS. The use of the developed system by engineers and software developers will make it possible to effectively manage the definition base of industrial standards, understand them correctly and observe them in accordance with the chosen field of knowledge.

Application of Fuzzy C-Means Clustering and Semantic Ontology in Web Query Session Mining for Intelligent Information Retrieval

Information retrieval based on keywords search retrieves irrelevant documents because of vocabulary gap between document content and search queries. The keyword vector representation of web documents is very high dimensional, and keyword terms are unable to capture the semantic of document content. Ontology has been built in various domains for representing the semantics of documents based on concepts relevant to document subject. The web documents often contain multiple topics; therefore, fuzzy c-means document clustering has been used for discovering clusters with overlapping boundaries. In this paper, the method is proposed for intelligent information retrieval using hybrid of fuzzy c-means clustering and ontology in query session mining. Thus, use of fuzzy clusters of web query session concept vector improve quality of clusters for effective web search. The proposed method was evaluated experimentally, and results show the improvement in precision of search results.