RESUMO
OBJECTIVES: Anaphora recognition is a process to identify exactly which noun has been used previously and relates to a pronoun that is included in a specific sentence later. Therefore, anaphora recognition is an essential element of a dialogue agent system. In the current study, all the merits of rule-based, machine learning-based, semantic-based anaphora recognition systems were combined to design and realize a new hybrid-type anaphora recognition system with an optimum capacity. METHODS: Anaphora recognition rules were encoded on the basis of the internal traits of referred expressions and adjacent contexts to realize a rule-based system and to serve as a baseline. A semantic database, related to predicate instances of sentences including referred expressions, was constructed to identify semantic co-relationships between the referent candidates (to which semantic tags were attached) and the semantic information of predicates. This approach would upgrade the anaphora recognition system by reducing the number of referent candidates. Additionally, to realize a machine learning-based system, an anaphora recognition model was developed on the basis of training data, which indicated referred expressions and referents. The three methods were further combined to develop a new single hybrid-based anaphora recognition system. RESULTS: The precision rate of the rule-based systems was 54.9%. However, the precision rate of the hybrid-based system was 63.7%, proving it to be the most efficient method. CONCLUSIONS: The hybrid-based method, developed by the combination of rule-based and machine learning-based methods, represents a new system with enhanced functional capabilities as compared to other pre-existing individual methods.
RESUMO
This paper proposes new combined methods to classify normal and epileptic seizure EEG signals using wavelet transform (WT), phase-space reconstruction (PSR), and Euclidean distance (ED) based on a neural network with weighted fuzzy membership functions (NEWFM). WT, PSR, ED, and statistical methods that include frequency distributions and variation, were implemented to extract 24 initial features to use as inputs. Of the 24 initial features, 4 minimum features with the highest accuracy were selected using a non-overlap area distribution measurement method supported by the NEWFM. These 4 minimum features were used as inputs for the NEWFM and this resulted in performance sensitivity, specificity, and accuracy of 96.33%, 100%, and 98.17%, respectively. In addition, the area under Receiver Operating Characteristic (ROC) curve was used to measure the performances of NEWFM both without and with feature selections.
Assuntos
Encéfalo/fisiopatologia , Diagnóstico por Computador/métodos , Eletroencefalografia/métodos , Epilepsia/diagnóstico , Epilepsia/fisiopatologia , Reconhecimento Automatizado de Padrão/métodos , Análise de Ondaletas , Algoritmos , Mapeamento Encefálico/métodos , Epilepsia/classificação , Redes Neurais de Computação , Reprodutibilidade dos Testes , Sensibilidade e EspecificidadeRESUMO
OBJECTIVES: A healthcare decision-making support model and rule management system is proposed based on a personalized rule-based intelligent concept, to effectively manage chronic diseases. METHODS: A Web service was built using a standard message transfer protocol for interoperability of personal health records among healthcare institutions. An intelligent decision service is provided that analyzes data using a service-oriented healthcare rule inference function and machine-learning platform; the rules are extensively compiled by physicians through a developmental user interface that enables knowledge base construction, modification, and integration. Further, screening results are visualized for the self-intuitive understanding of personal health status by patients. RESULTS: A recommendation message is output through the Web service by receiving patient information from the hospital information recording system and object attribute values as input factors. The proposed system can verify patient behavior by acting as an intellectualized backbone of chronic diseases management; further, it supports self-management and scheduling of screening. CONCLUSIONS: Chronic patients can continuously receive active recommendations related to their healthcare through the rule management system, and they can model the system by acting as decision makers in diseases management; secondary diseases can be prevented and health management can be performed by reference to patient-specific lifestyle guidelines.