Online archive of Computer Science and Mathematical Modelling
M. Cebula, P. Murawski - Design and implementation of an information system to study the repeatability of the orientation in space for medical applicationsPages: 5 - 16
Abstract: The aim of the study was to study the repeatability of the object’s orientation in space. During the study, a self-constructed system of 4 gyroscope and an available robot of the kuka type were used. An application allowing for comparison of research results was written and presented. The article contains individual stages of work (analytical and implementation), research results, conclusions and discussion.
Keywords orientation in space, gyroscope, medical applications
Full article: 5_16_mcebula_pmurawski_design_csmm_10.pdf
M. Romaldowski - The method of automatic assignment ICD codes based on semantic informationPages: 17 - 23
Abstract: The paper presents the method of automatic assignment of ICD codes based on semantic information contained in clinical reports of the MIMIC-III database. It is showing the possibility of using multi-criteria optimization methods for simple classifiers fusion in a more precise classifiers complex. ICD code assignment is important in the modern hospital, more accurate automation of assigning codes will make the clinical process more efficient and can help clinicians carry out better diagnostics and effectively improve medical care systems.
Keywords MIMIC III, ICD, TFIDF, word2vec, classification, machine learning, natural language processing, classifiers synthesis, Pareto filter
Full article: 17_23_mromaldowski_themethod_csmm_10.pdf
C. Tran, A. Ameljańczyk - Clustering Web search results using Wikipedia resourcePages: 25 - 29
Abstract: The paper presents a proposal of a new method for clustering search results. The method uses an external knowledge resource, which can be, for example, Wikipedia. Wikipedia – the largest encyclopedia, is a free and popular knowledge resource which is used to extract topics from short texts. Similarities between documents are calculated based on the similarities between these topics. After that, affinity propagation clustering algorithm is employed to cluster web search results. Proposed method is tested by AMBIENT dataset and evaluated within the experimental framework provided by a SemEval-2013 task. The paper also suggests new method to compare global performance of algorithms using multi – criteria analysis.
Keywords affinity propagation, similarity of documents, multi-criteria assessment, Web search results, Wikipedia.
Full article: 25_29_ctran_aameljanczyk_clustering_csmm_10.pdf
B. Szafrański, R. Bałazy - Data protection in transactional and statistical applications of databasesPages: 31 - 39
Abstract: The article describes a discussion on the issue of data protection in databases. The discussion attempts to answer the question about the possibility of using a transactional database system as a system capable of data protection in a statistical database. The discussion is preceded by a reminder of the basic issues related to data protection in databases, including reminder of flow control models, access control models and the inference. The key element of the article is the analysis, based on the example of the Oracle database management system, whether data protection mechanisms in transactional databases can be effective in case of data protection in statistical databases.
Keywords database, database system, data protection in database, flow control, inference control, statistical database, Oracle
Full article: 31_39_bszafranski_rbalazy_dataprotecton_csmm_10.pdf