In this paper, we assess the performance of DSMIO cachecoherence algorithm implemented in a parallel object-based database management system (ODBMS). The distinguishing feature of DSMIO is its use of the lazy release ...
详细信息
The paper presents a comparison between two unsupervised neural network models: (i) the well-known fuzzy ART, and (ii) AUTOWISARD, a new unsupervised version of the classic WISARD weightless neural network model. It i...
详细信息
The paper presents a comparison between two unsupervised neural network models: (i) the well-known fuzzy ART, and (ii) AUTOWISARD, a new unsupervised version of the classic WISARD weightless neural network model. It is shown that AUTOWISARD is simple, fast and stable, whilst keeping compatibility with the original WISARD architecture. Experimental test results over binary patterns benchmarks have shown that, although both unsupervised learning models are remarkably simple, AUTOWISARD consistently exhibits better classification skills than fuzzy ART. It is also shown that such superiority happens thanks to AU-TOWISARD's richer internal representation of the trained patterns and the training methods employed by the algorithm, such as the learning window and partial training strategies.
We present the fuzzy Markov predictor (FMP), a hybrid system that is applied to the task of monthly electric load forecasting. The FMP is a modification we introduce in the hidden Markov model in order to enable it to...
详细信息
We present the fuzzy Markov predictor (FMP), a hybrid system that is applied to the task of monthly electric load forecasting. The FMP is a modification we introduce in the hidden Markov model in order to enable it to predict numerical values. The FMP can be seen as an extension of the fuzzy Bayes predictor (FBP) that was modified from the naive Bayes classifier. For verifying the efficiency of the FMP's prediction, we compare it with the FBP, one fuzzy system and two traditional forecasting methods, Box-Jenkins and Winters exponential smoothing.
We present two new versions of the fuzzy Markov predictor (FMP) with different dependences among the inputs: first-order and second-order dependences. The FMP is a modification of the hidden Markov model in order to e...
详细信息
We present two new versions of the fuzzy Markov predictor (FMP) with different dependences among the inputs: first-order and second-order dependences. The FMP is a modification of the hidden Markov model in order to enable it to predict numerical values. The FMP can be seen as an extension of the fuzzy Bayes predictor. These hybrid systems are applied to the task of monthly electric load forecasting and successfully compared with one fuzzy system, and two traditional forecasting methods: Box-Jenkins and Winters exponential smoothing.
In this paper we present a new, adaptive spatial-derivative circuit for CMOS image sensors. The circuit removes its offset as a natural part of its operation using a combination of electron tunneling and hot-electron ...
详细信息
In this paper we present a new, adaptive spatial-derivative circuit for CMOS image sensors. The circuit removes its offset as a natural part of its operation using a combination of electron tunneling and hot-electron injection to add or remove charge on a floating-gate of an auto-zeroing amplifier. We designed, fabricated and successfully tested a chip with the circuit. Test results show that the circuit reduces the offsets by more than an order of magnitude.
The design of wholesale electricity markets through deregulation has focused almost exclusively on the development of competitive supply (generation). The demand side of the market has been virtually ignored. Mostly, ...
详细信息
ISBN:
(纸本)0780373227
The design of wholesale electricity markets through deregulation has focused almost exclusively on the development of competitive supply (generation). The demand side of the market has been virtually ignored. Mostly, this is due to the assumption that electricity demand is almost completely inelastic. As a result, deregulated wholesale markets universally fail to pass price signals down to the end-users. This paper challenges the assumption of inelastic demand by exploring the potential benefits of implementing a simple load control scheme. This load control scheme allows consumers to shift demand from high priced hours to low priced hours during the day. The benefits to the individual consumer are explored through an example applied to residential air conditioning using price and demand data from California. This example shows that "smart" use of air conditioning can lead to great savings for residential consumers, without sacrificing comfort. The potential for multiple consumers implementing load control to reduce wholesale prices is also examined.
A soft expert system is defined to be one that is qualitatively fuzzy. In this paper, we present such a system known as "KASER" which stands for 'Knowledge Amplification by Structural Expert Randomizatio...
详细信息
A soft expert system is defined to be one that is qualitatively fuzzy. In this paper, we present such a system known as "KASER" which stands for 'Knowledge Amplification by Structural Expert Randomization". KASER facilitates reasoning using domain specific expert and commonsense knowledge. It accomplishes this through object-classed predicates and an associated novel inference engine. It addresses the high cost associated with the knowledge acquisition bottleneck. It also enables the entry of a basis of rules and provides for the automatic extension of that basis through domain symmetries. We demonstrate an application for KASER in the design of an intelligent tutoring system that teaches the basic science of crystal-laser design. It enables the student to experiment with various design concepts and receive feedback on the functionality of the proposed design. This is possible without a need to preprogram all possible scenarios.
Adaptive critics have shown much promise for designing optimal nonlinear controllers in an off-line context. Still, their greatest potential exists in the context Of reconfigurable control, that is, real time controll...
详细信息
Adaptive critics have shown much promise for designing optimal nonlinear controllers in an off-line context. Still, their greatest potential exists in the context Of reconfigurable control, that is, real time controller redesign in response to (substantial) changes in plant dynamics. To accomplish this, a framework is proposed for the application of adaptive critics in real-time control (for those critic methods requiring a model of the plant). The framework is presented in the context of work being done in reconfigurable flight control by the NW Computational Intelligence Lab (NWCIL) at Portland State University. The proposal incorporates recent work (by others) in fast and efficient on-line plant identification, considerations for bounding the computational costs of converging neural networks, and a novel approach (by us) toward the task of assuring system stability during the adaptation process. The potential and limitations of the proposed framework are discussed. It is suggested that with the recent rapid reduction in computational barriers, only certain theoretical issues remain as the central barriers to successful on-line application of the methods.
Intelligence Preparation of the Battlespace (IPB) is a predominantly "gray matter-based" fusion and information synthesis process conducted to predict possible future adversary courses of action. The purpose...
详细信息
We propose an efficient heuristic algorithm that sets up and releases lightpaths for connection requests dynamically. We partition the routing and wavelength assignment (commonly known as RWA) problem into two subprob...
详细信息
ISBN:
(纸本)0780374002
We propose an efficient heuristic algorithm that sets up and releases lightpaths for connection requests dynamically. We partition the routing and wavelength assignment (commonly known as RWA) problem into two subproblems and solves both of them using a well-known shortest path routing algorithm. For solving the routing subproblem, an auxiliary graph is created whereby the nodes and links in the original network are transformed to the edges and vertices, respectively, and the availability of each wavelength on the input and output links of a node as well as the number of available wavelength converters are taken into account in determining the weights of edges. Furthermore, for solving the wavelength assignment subproblem, an auxiliary graph is also utilized and the cost for wavelength conversion is taken into consideration in the edge weight function. A distinguished feature of our algorithm is that it employs more accurate network information on the availability of both the wavelengths and the wavelength converters than the existing algorithms in deciding the routing and the wavelength assignment. Simulation results show that our algorithm performs much better than previously proposed algorithms with comparable computation time, especially when the number of wavelengths is large while the number of converters at each node is limited.
暂无评论