Heterogeneous Unstructured Data Research Articles

Algorithm for early diagnosis of hepatocellular carcinoma based on gene pair similarity

The article proposes an algorithm based on intelligent methods for the early diagnosis of hepatocellular carcinoma (HCC), known as liver cancer, which is rated third cause of cancer deaths in the world. Initial diagnosis of HСC is based on laboratory studies, computer tomography and X-ray examination. However, in some cases, identifying cancerous tissues as similar non-cancerous tissues (cirrhotic tissues and normal tissues) made it necessary to perform gene analysis for the diagnosis. To predict HCC based on such numerous, diverse and heterogeneous unstructured data, preference is given to the method of artificial intelligence, i.e., machine learning. It shows the possibility of applying machine learning methods to solve the problem of accurate identification of HCC due to the compatibility of HCC tissues with identical CwoHCC non-cancerous tissues. The technology of gene pair profiling using relevant peer databases is described and the Within-Sample Relative Expression Orderings (REO) technique is used to determine the gene pair’s similarity. The article also presents a new approach based on The Within-Sample Relative Expression Orderings technique for determining the gene pair’s similarity, Incremental feature selection method for feature selection, and Support Vector Machine methods for gene pair classification. The proposed approach constitutes the methodological basis of a decision support system for the early diagnosis of HCC, and the development of such a system may be beneficial for physician decision support in the relevant field

Ontology population with deep learning-based NLP: a case study on the Biomolecular Network Ontology

As a scientific discipline, systems biology aims to build models of biological systems and processes through the computer analysis of a large amount of experimental data describing the behaviour of whole cells. It is within this context that we already developed the Biomolecular Network Ontology especially for the semantic understanding of the behaviour of complex biomolecular networks and their transittability. However, the challenge now is how to automatically populate it from a variety of biological documents. To this end, the target of this paper is to propose a new approach to automatically populate the Biomolecular Network Ontology and take advantage of the vast amount of biological knowledge expressed in heterogeneous unstructured data about complex biomolecular networks. Indeed, we have recently observed the emergence of deep learning techniques that provide significant and rapid progress in several domains, particularly in the process of deriving high-quality information from text. Despite its significant progress in recent years, deep learning is still not commonly used to populate ontologies. In this paper, we present a deep learning-based NLP ontology population system to populate the Biomolecular Network Ontology. Its originality is to jointly exploit deep learning and natural language processing techniques to identify, extract and classify new instances referring to the BNO ontology’s concepts from textual data. The preliminary results highlight the efficiency of our proposal for ontology population.

Design and Application of a Containerized Hybrid Transaction Processing and Data Analysis Framework

This article describes how rapidly growing data volumes require systems that have the ability to handle massive heterogeneous unstructured data sets. However, most existing mature transaction processing systems are built upon relational databases with structured data. In this article, the authors design a hybrid development framework, to offer greater scalability and flexibility of data analysis and reporting, while keeping maximum compatibility and links to the legacy platforms on which transaction business logics run. Data, service and user interfaces are implemented as a toolset stack, for developing applications with functionalities of information retrieval, data processing, analyzing and visualizing. A use case of healthcare data integration is presented as an example, where information is collected and aggregated from diverse sources. The workflow and simulation of data processing and visualization are also discussed, to validate the effectiveness of the proposed framework.

ENFORCING CRIME FACTOR ANALYSIS THROUGH OPTIMIZED MULTI CLASS SVM CLASSIFICATION

In recent world, the crime factors are increasing day by day. Some of the preventive measures are taken to identify and avoid the crimes by their concern departments. There are huge amount of heterogeneous unstructured data are collected about the crime factors and the criminals. That the gathered unstructured data should be gathered, elicited and classified for analyzing the crime factors and find out the predictive measures for the prevention of crime activities. Many classification techniques are used in the analysis of crime factors and make predictive analysis through it. However the effective techniques are used for the analysis of the crime factors, this is potentially strong based on the dataset taken as an input or in training phase. In existing, for gathering the relevant data for the analysis is obtained through the Hierarchal Clustering. It is most efficient clustering technique but it works well in the structured text data. To obtain the effective data clustering in heterogeneous unstructured data, the K Means Clustering has been proposed. Next to clustering, the classification technique is required to classify the properties of the crime factors through the parameters in unstructured data using Cluster Based Support Vector Machine Classification. The main contribution of this proposed work is to create a novel mechanism for obtain the predictive analysis for prevention of crime factors from the various crime classes. The predictive analysis can be obtained through the continuous process of K means clustering and Multi Class SVM Classification. To prove the effectiveness of the proposed mechanism capable of deals with multiple domains, SVM Classification algorithm can be optimized through this algorithm. The experiments have been illustrating the efficiency of the mechanism with the dataset from UCI repository and data from government of India.

Spatial Information Extraction from Short Messages

Texts in addition to maps and satellite images, have become an important spatial data resource in recent years. Electronic written texts used in mediated interactions, especially short messages, have triggered the emergence of new ways of writing. Extracting information from such short messages, which represent a rich source of information, is highly important in order to discover domain-relevant information in the text and facilitate information retrieval. However, short messages are hard to analyse because of their brief, unstructured and informal nature. This paper focuses on the kinds of special or unique spatial entities and relations are contained in short messages. A new entity extraction method specifically dedicated to French short messages (SMS and tweets) is outlined to address this issue. The method is then tested on more traditional sources, like newspaper texts. This work is crucial in order to take advantage of the vast amount of geographical knowledge expressed in heterogeneous unstructured data. Firstly, we propose a process in which new spatial entities are extracted (e.g. motpellier, montpelier, Montpel are associated with Montpellier). Secondly, we identify new spatial relations that precede spatial entities (e.g. sur, par). Finally, we propose general patterns for the extraction of spatial relations. The task is very challenging and complex due to the specificity of short message language, which is based on weakly standardized modes of writing. The experiments were carried out on the three French corpora (i.e. 88milSMS, tweets, and Midi Libre) and highlight the efficiency of our proposal for identifying new kinds of spatial entities and relations.