More frequently than ever companies are evaluating third party client/server applications as an alternative to developing applications in-house. Many times the desired application has never been tested or put into pro...
There is a continuing trend in the industry for expedient access to concise, up-to-date information about resource consumption, performance information and planning strategies. Our organization is exploring the use of...
详细信息
The proceedings contain 124 papers. The topics discussed include: a resource occupancy model for evaluating instrumentation system overheads;capacity planning for tape drives: learning to count;DASD subsystems: evalua...
The proceedings contain 124 papers. The topics discussed include: a resource occupancy model for evaluating instrumentation system overheads;capacity planning for tape drives: learning to count;DASD subsystems: evaluating their performance and characteristics through benchmarking;generating representative synthetic workloads: an unsolved problem;introduction to simple network management protocol (SNMP);performance modeling of large transients in computer systems;the structure and evolution of a distributed measurement framework;a federation-oriented capacity management methodology for LAN environments;a performance modeling tool for a client/server backup product;alarm-based vs. historical trending performance management or really large UNIX installation performance management;and capacity planning skills migration from mainframe to client/server.
lnstrumentatiun systems (IS) are used to collect runtime information for state-of-the-art tool environments for parallel and distributed systems. The nondeterministic nature of the events in a concurrent computer syst...
详细信息
An interpretation is discussed with regard to using fuzzy logic systems (FLSs) as system models. The development of FLSs by a pseudo-clustering technique is presented which bypasses the use of conventional clustering ...
详细信息
ISBN:
(纸本)0780325605
An interpretation is discussed with regard to using fuzzy logic systems (FLSs) as system models. The development of FLSs by a pseudo-clustering technique is presented which bypasses the use of conventional clustering algorithms. This method is shown to provide reasonably good responses with very little development overhead. A second modeling technique relies on interpreting the available data itself as the FLS. These methods provide a transition between artificial neural network (ANN) realizations and classical FLSs, in that most of their computations could be performed in parallel.
In this paper a new form of neuro-fuzzy-genetic controller design of rigid-link flexible-joints robot manipulators has been presented. The control algorithm used fuzzy logic with neural membership functions and rule b...
详细信息
ISBN:
(纸本)0780330269;0780330277
In this paper a new form of neuro-fuzzy-genetic controller design of rigid-link flexible-joints robot manipulators has been presented. The control algorithm used fuzzy logic with neural membership functions and rule base without needing the knowledge of the mathematical model or the parameter values of the robot. The Genetic Algorithms are applied for fuzzy rules set optimization. The proposed controller is capable of compensating the elastic oscillations at the joints. The obtained membership functions and fuzzy rules are implemented with backpropagation feedforward neural networks. The membership functions are modified through learning process as a fine tuning. Results of the computer simulation applied to the 4 DOF rigid-link flexible joints SCARA robot manipulators show the validity of the proposed method.
In this study, a computer platform for investigating optimal trajectories of FES-induced motion was developed. Similar to a gait analysis program, this system interprets body segment lengths and joint angle trajectori...
详细信息
ISBN:
(纸本)0780326938
In this study, a computer platform for investigating optimal trajectories of FES-induced motion was developed. Similar to a gait analysis program, this system interprets body segment lengths and joint angle trajectories for a subject undergoing an arbitrary movement, and displays that movement, along with a center of mass and time plot of the moment about the knee joint onscreen. Movements to be optimized in the near term are sit-to-stand transitions, stand-to-sit transitions, shifting weight side-to-side while seated, and single steps over small architectural barriers. These motions will be optimized for stability, efficiency, safety, and stress, as applied to a T-10 paraplegic human subject undergoing FNS of ten motor nerves in each leg. The program was demonstrated to work for sit-to-stand and stand-to-sit motions, and is now used to optimize those transitions.
In this research, a self-organizing fuzzy-nets optimization (FNO) system is developed to generate a knowledge bank that can show the required cutting power to be on-line for a short length of time in an NC verifier. T...
详细信息
In this research, a self-organizing fuzzy-nets optimization (FNO) system is developed to generate a knowledge bank that can show the required cutting power to be on-line for a short length of time in an NC verifier. The FNO system requires a self-learning procedure consisting of five steps. A generic system consisting of a fuzzification module and a defuzzification module is implemented to perform the procedure.
Nonlinear system behavior is not always well characterized by linear or linearized system models, especially if the system is rapidly time-varying and/or is chaotic. Model paradigms that are themselves nonlinear, such...
详细信息
ISBN:
(纸本)0780325605
Nonlinear system behavior is not always well characterized by linear or linearized system models, especially if the system is rapidly time-varying and/or is chaotic. Model paradigms that are themselves nonlinear, such as neural networks, potentially offer more accurate and more robust models for these nonlinear systems. This research studies the use of a neural network structure to model a linear system and two nonlinear systems, a quadratic system and a chaotic system. Several training algorithms are used, including traditional back propagation, an evolutionary programming approach, and a hybrid approach. Net architectures studied here consist of a traditional feed forward topology and a radial basis topology. Modified back propagation training using a feed forward network proved adequate for modeling the linear and quadratic systems, but these were hopelessly inadequate in modeling the chaotic system. The radial basis net fared better, but was still a poor performer for projecting the chaotic system beyond the observed data.
In this paper, we propose a multicriteria decision making (MCDM) method by using a genetic algorithm (GA). The system consists of three phases. In the first phase, a rough set of Pareto optimal solutions is obtained u...
详细信息
ISBN:
(纸本)0780325605
In this paper, we propose a multicriteria decision making (MCDM) method by using a genetic algorithm (GA). The system consists of three phases. In the first phase, a rough set of Pareto optimal solutions is obtained using Kohonen's self organizing map (SOM). In the second phase, the decision maker (DM) selects his preferred solutions among the obtained set, where the mechanism of GA is used with the DM's preference assisted by radial basis function network (RBFN). In the third phase, the DM can explore the solution space further for the final decision.
暂无评论