Servicio de comunicación causal bidirecciional sin contención.

Las arquitecturas jerárquicas de comunicación causal se presentan como una alternativa habitual para reducir el elevado tamaño de la información de control causal a enviar en cada mensaje, cuando la comunicación se realiza entre un subconjunto de procesos que pertenecen a un grupo muy numeroso. Sin embargo, en estas arquitecturas, los nodos intermedios de la jerarquía padecen un efecto indeseable denominado efecto convoy. Estos nodos intermedios tienden a generar ráfagas de envíos que sobrecargan tanto a los nodos de los niveles inferiores de la jerarquía como a la red, provocando pérdidas de mensajes y periodos entre ráfagas de infrautilización de la red. Este artículo presenta un servicio causal bidireccional sin contención que, aplicado a los nodos intermedios de la jerarquía, soluciona el efecto convoy. Este servicio causal sin contención entrega a la capa de aplicación y envía al sistema un mensaje sin esperar la entrega o el envío previo de mensajes que constituyen la historia causal del primero, por lo que evita las ráfagas de entrega y de envío de mensajes. La entrega de un mensaje va acompañada de un identificador causal, que es un número natural que indica el número de orden de ese mensaje en la secuencia causal total. El envío de un mensaje supone construir un vector causal válido a partir de un identiificador causal, que permita ordenar dicho mensaje en orden causal en el proceso receptor.

Using a causal smoothing to improve the performance of an on-line neural network glucose prediction algorithm

This work evaluates a spline-based smoothing method applied to the output of a glucose predictor. Methods:Our on-line prediction algorithm is based on a neural network model (NNM). We trained/validated the NNM with a prediction horizon of 30 minutes using 39/54 profiles of patients monitored with the Guardian® Real-Time continuous glucose monitoring system The NNM output is smoothed by fitting a causal cubic spline. The assessment parameters are the error (RMSE), mean delay (MD) and the high-frequency noise (HFCrms). The HFCrms is the root-mean-square values of the high-frequency components isolated with a zero-delay non-causal filter. HFCrms is 2.90±1.37 (mg/dl) for the original profiles.

B2DI a bayesian BDI agent model with causal belief updating based on MSBN

In this paper, we introduce B2DI model that extends BDI model to perform Bayesian inference under uncertainty. For scalability and flexibility purposes, Multiply Sectioned Bayesian Network (MSBN) technology has been selected and adapted to BDI agent reasoning. A belief update mechanism has been defined for agents, whose belief models are connected by public shared beliefs, and the certainty of these beliefs is updated based on MSBN. The classical BDI agent architecture has been extended in order to manage uncertainty using Bayesian reasoning. The resulting extended model, so-called B2DI, proposes a new control loop. The proposed B2DI model has been evaluated in a network fault diagnosis scenario. The evaluation has compared this model with two previously developed agent models. The evaluation has been carried out with a real testbed diagnosis scenario using JADEX. As a result, the proposed model exhibits significant improvements in the cost and time required to carry out a reliable diagnosis.

Explanation of changes in real estate stock market

The aim of this study is to explain the changes in the real estate prices as well as in the real estate stock market prices, using some macro-economic explanatory variables, such as the gross domestic product (GDP), the real interest rate and the unemployment rate. Several regressions have been carried out in order to express some types of incremental and absolute deflated real estate lock market indexes in terms of the macro-economic variables. The analyses are applied to the Swedish economy. The period under study is 1984-1994. Time series on monthly data are used. i.e. the number of data-points is 132. If time leads/lags are introduced in the e regressions, significant improvements in the already high correlations are achieved. The signs of the coefficients for IR, UE and GDP are all what one would expect to see from an economic point of view: those for GDP are all positive, those for both IR and UE are negative. All the regressions have high R2 values. Both markets anticipate change in the unemployment rate by 6 to 9 months, which seems reasonable because such change can be forecast quite reliably. But, on the contrary, there is no reason why they should anticipate by 3-6 months changes in the interest rate that can hardly be reliably forecast so far in advance.