The paper describe the teaching of object-oriented ideas within all four years of a Bachelor of computer System engineering and the BSc in computerscience Degree at La Trobe University. This is taught together with a...
详细信息
The paper describe the teaching of object-oriented ideas within all four years of a Bachelor of computer System engineering and the BSc in computerscience Degree at La Trobe University. This is taught together with a variety of other traditional approaches. A key element in the teaching of OO is the softwareengineering Project, which is explained in some detail. The teaching is also complicated by a number of different target student populations. This also provides us with an opportunity to study the effect of different factors on the learning of OO by the students. The experience indicates that OO is a significant softwareengineering paradigm, well accepted by the students.< >
In this paper we describe the problem-solving constructs, namely information processing constructs, learning constructs, knowledge representation constructs and computational constructs for building complex symbolic-c...
详细信息
In this paper we describe the problem-solving constructs, namely information processing constructs, learning constructs, knowledge representation constructs and computational constructs for building complex symbolic-connectionist systems. These constructs are applicable in particular to complex diagnostic domains and in general to complex data intensive domains.< >
A modular recurrent connectionist architecture is proposed to classify binary and continuous patterns. This system consists of three networks: one feedforward backpropagation (BP) network and two self-organization map...
详细信息
A modular recurrent connectionist architecture is proposed to classify binary and continuous patterns. This system consists of three networks: one feedforward backpropagation (BP) network and two self-organization map (SOM) networks. The feedforward (basic) network is trained until a saturation error level occurs. Simultaneously, the first SOM (input control) network and the last SOM (output control) define the mapping features for the given input/output patterns. The resultant features are used by a Gaussian potential function to adjust the weights of the basic network and to classify the given patterns.< >
This paper outlines some preliminary work on the stability analysis of switched and hybrid systems. The hybrid systems considered are those that combine continuous dynamics, represented by differential or difference e...
详细信息
This paper outlines some preliminary work on the stability analysis of switched and hybrid systems. The hybrid systems considered are those that combine continuous dynamics, represented by differential or difference equations, with finite dynamics usually thought of as being a finite automaton. Here, we concentrate on the continuous dynamics and model the finite dynamics as switching among finitely many continuous systems. We introduce multiple Lyapunov functions as a tool for analyzing Lyapunov stability of such "switched systems". We use iterated function systems theory as a tool for Lagrange stability. We also discuss the case where the switched systems are indexed by an arbitrary compact set.< >
Data fusion is an important function of all intelligent vehicle highway systems (IVHS) components. Raw data on traffic conditions are received from various sources, in several formats, and at different time intervals....
详细信息
Data fusion is an important function of all intelligent vehicle highway systems (IVHS) components. Raw data on traffic conditions are received from various sources, in several formats, and at different time intervals. The goal of data fusion is to combine such data into meaningful inferences about traffic conditions. But it is quite common for these input data to have inconsistencies, uncertainties, and a lack of completeness. Applying binary logic and Bayes decision theory is inappropriate because some contradictions and only partial information are typically present in the input data. This paper presents an alternative approach to data fusion using a fuzzy-valued logic generalized from Belnap's four valued logic.
We outline the features of a cognitively compatible symbolic-connectionist architecture for complex data intensive time-critical domains especially in the diagnostic area. We examine how a symbolic-connectionist archi...
详细信息
We outline the features of a cognitively compatible symbolic-connectionist architecture for complex data intensive time-critical domains especially in the diagnostic area. We examine how a symbolic-connectionist architecture copes with the time-critical and size complexity aspects of a real time alarm processing system developed for a regional power system control centre.< >
This paper presents a method for automatic tuning of a fuzzy logic controller based on a control scheme which consists of a fuzzy logic controller and a conventional derivative controller. For this purpose, a neural n...
详细信息
This paper presents a method for automatic tuning of a fuzzy logic controller based on a control scheme which consists of a fuzzy logic controller and a conventional derivative controller. For this purpose, a neural network is first used to represent fuzzy logic inference. Membership functions regarding change-in-error e/spl dot/, which represent the feedback of velocity, are then defined by the functions of cubic splines. A desired control performance of a system is achieved by the adaptation of the defined membership functions using neural network in the self-organizing process. To demonstrate the effectiveness and robustness of the proposed fuzzy neural network control we report a number of simulation results involving both stepping and tracking controls of a nonlinear plant.< >
The properties of Artificial Neural Networks(ANNs) like massive parallelism, generalization make them amenable for application in various diagnostic/time-critical problem domains including alarm processing in power sy...
详细信息
A modular neural network architecture is proposed to classify binary and continuous patterns. This system consists of a supervised feedforward backpropagation network and an unsupervised self-organization map network....
详细信息
A primary function of most advanced traveler information systems involves the ability to plan optimal routes. Although the route planning ability of ATIS systems could be facilitated using centralized computing resour...
详细信息
暂无评论