In this paper we propose X-MAQoS, a novel XML-based multi-agent system for the QoS management in telecommunications networks. This system is characterized by the following features: (i) it handles a user profile and exploits it jointly with suitable network resource management techniques to maximize user satisfaction; (ii) it is capable of operating in a large variety of telecommunications networks; (iii) it is semi-automatic; (iv) it exploits XML for guaranteeing a light, versatile and standard mechanism for information representation, storing and exchange. In this paper the basic features of the system are discussed in details. Furthermore, the main results of a performance evaluation study in UMTS environment, aiming at comparing X-MAQoS with alternative agent-based approaches for handling user access to telecommunications networks, are reported.

Automobile companies that spend billions of dollars annually towards warranty cost, give high priority to warranty reduction programs. Forecasting of automobile warranty performance plays an important role towards these efforts. The forecasting process involves prediction of not only the specific months-in-service (MIS) warranty performance at certain future time, but also at future MIS values. However, ‘maturing data’ (also called warranty growth) phenomena that causes warranty performance at specific MIS values to change with time, makes such a forecasting task challenging. Although warranty forecasting methods such as log-log plots and dynamic linear models appear in literature, there is a need for applications addressing the well recognized issue of ‘maturing data’. In this paper we use an artificial neural network for the forecasting of warranty performance in presence of ‘maturing data’ phenomena. The network parameters are optimized by minimizing the training and testing errors using response surface methodology. This application shows the effectiveness of neural networks in the forecasting of automobile warranty performance in the presence of the ‘maturing data’ phenomena.

In this paper, the partial stabilization problem for a class of nonlinear continuous control systems with separated variables is investigated. Several stabilizing controllers are constructed based on the partial stability theory of Lyapunov and the property of M-matrix, and some of these stabilizing controllers are only related to partial state variables. The controllers constructed here are shown to guarantee partial asymptotic stability of the closed-loop systems and these sufficient conditions may give some instructions to actual engineering application. A example is also given to illustrate the design method.

In this paper, a constrained genetic algorithm (CGA) is proposed to solve the single machine total weighted tardiness problem. The proposed CGA incorporates dominance rules for the problem under consideration into the GA operators. This incorporation should enable the proposed CGA to obtain close to optimal solutions with much less deviation and much less computational effort than the conventional GA (UGA). Several experiments were performed to compare the quality of solutions obtained by the three versions of both the CGA and the UGA with the results obtained by a dynamic programming approach. The computational results showed that the CGA was better than the UGA in both quality of solutions obtained and the CPU time needed to obtain the close to optimal solutions. The three versions of the CGA reduced the percentage deviation by 15.6%, 61.95%, and 25% respectively and obtained close to optimal solutions with 59% lower CPU time than what the three versions of the UGA demanded. The CGA performed better than the UGA in terms of quality of solutions and computational effort when the population size and the number of generations are smaller.

The slow convergence rate of reinforcement learning algorithms limits their wider application. In engineering domains, hierarchical reinforcement learning is developed to perform actions temporally according to prior knowledge. This system can converge fast due to reduced state space. There is a test of elevator group control to show the power of the new system. Two conventional group control algorithms are adopted as prior knowledge. Performance indicates that hierarchical reinforcement learning can reduce the learning time dramatically.

It is not unusual for the level of a monthly economic time series, such as industrial production, retail and wholesale sales, monetary aggregates, telephone calls or road accidents, to be influenced by calendar effects. Such effects arise when changes occur in the level of activity resulting from differences in the composition of calendar between years. The two main sources of calendar effects are trading day variations and moving festivals. Ignoring such calendar effects will lead to substantial distortions in the identification stage of time series modeling. Therefore, it is mandatory to introduce calendar effects, when they are present in a time series, as the component of the model which one wants to estimate.

It is a new research topic to create a rational judgment matrix using the cognition theory because of the construction of judgment matrix in AHP involving the decision-maker’s cognitive activities. Owing to the presence of uncertain information in the decision procedure, the improper use of the uncertain information will doubtless cause weight changes. In this paper, we add a feedforward process prior to constructing the judgment matrix so that the decision maker can use both the certain and uncertain information to get the initial uncertain rough judgment matrix, and then convert it into a fuzzy matrix. Consequently, it will be better for decision maker to obtain the rough set of order equivalent classes through the decision graph. According to the qualitative analysis, the decision maker can easily construct the final judgment matrix instructed by the rough set created earlier.

This paper deals with on-line state and parameter estimation of a reasonably large class of nonlinear continuous-time systems using a step-by-step sliding mode observer approach. The method proposed can also be used for adaptation to parameters that vary with time. The other interesting feature of the method is that it is easily implementable in real-time. The efficiency of this technique is demonstrated via the on-line estimation of the electrical parameters and rotor flux of an induction motor. This application is based on the standard model of the induction motor expressed in rotor coordinates with the stator current and voltage as well as the rotor speed assumed to be measurable. Real-time implementation results are then reported and the ability of the algorithm to rapidly estimate the motor parameters is demonstrated. These results show the robustness of this approach with respect to measurement noise, discretization effects, parameter uncertainties and modeling inaccuracies. Comparisons between the results obtained and those of the classical recursive least square algorithm are also presented. The real-time implementation results show that the proposed algorithm gives better performance than the recursive least square method in terms of the convergence rate and the robustness with respect to measurement noise.