Effective enhancement of classification of respiratory states using feed forward back propagation neural networks

In biomedical signal analysis, Artificial Neural Networks are frequently used for classification, owing to their capability to resolve nonlinearly separable problems and the flexibility to implement them on-chip processor, competently. Artificial Neural Network for a classification task attempts to hand design a network topology and to find a set of network parameters using a back propagation training algorithm. This work presents an intelligent diagnosis system using artificial neural network. Features were extracted from respiratory effort signal based on the threshold-based scheme and the respiratory states were classified into normal, sleep apnea and motion artifacts. The introduced neural classifier was then trained with different back propagation training algorithms and the classified output was compared with the hand designed results. Five different back propagation training algorithms were used for training, such as Levenberg–Marquardt, scaled conjugate gradient, BFGS algorithm, one step secant and Powell–Beale restarts. Our results revealed that the system could correctly classify at an average of 98.7%, when the LM training method was used. Receiver Operating Characteristic (ROC) analysis and confusion matrix showed that the LM method conferred a more balanced and an apt classification of sleep apnea and normal states.     

Generating queries and replies during information-seeking interactions

Analysis of naturally occurring information-seeking dialogues indicates that they usually consist of a number of distinct discourse segments, such as a greeting segment, a request issued by a user, an optional clarification segment, a transfer of information segment and a final closing segment. The clarification interaction is often initiated by the information provider and it may be due to one of the following reasons: (1) there is confusion regarding the user's intentions, (2) there is insufficient information to formulate a plan to satisfy a recognized intention, or (3) there is difficulty in formulating a plan that satisfies a recognized intention. Once the information provider determines the user's intention and formulates a plan to achieve this intention, the information transfer phase is initiated to inform the user about the proposed plan.In this paper, we present a mechanism for generating queries during the clarification stage and answers during the information transfer stage. Given a hierarchical representation of the alternatives possibly intended by a user and the probabilities of these alternatives, our mechanism determines the hierarchy level at which a query must be directed and the query to be posed in order to determine the alternative intended by the user. Once the user's intentions are ascertained, the mechanism determines whether additional information is required and the manner in which queries may be posed to acquire this information. When a user's intentions cannot be satisfied by means of a single plan, our mechanism enters into a negotiation process to alter the user's specifications until a valid plan is formulated. In the final stages of the interaction, the mechanism determines the information to be transferred and generates an answer to effect the transfer. The mechanisms for negotiation and for the generation of queries and answers described in this paper have been implemented in a system called , a computerized information providing system that functions as a travel agent.