An ensemble of Neural Networks offers several advantages over classical single classifier systems when applied to complex pattern classification problems. However, the performance of the ensemble as a unit depends not...
详细信息
An ensemble of Neural Networks offers several advantages over classical single classifier systems when applied to complex pattern classification problems. However, the performance of the ensemble as a unit depends not only on the effective aggregation of the modules decisions, but also on the accuracy of the individual classification decisions of each module. The accuracy at the modular level is a result of the quality of training received by each module. This paper presents an adaptive training algorithm that can be used to direct the training of the individual modules so as to improve the classification accuracy and training efficiency of the ensemble.
In this paper, we propose a new approach to the high-speed wall following of wheeled mobile robots using hybrid controlsystem. The proposed hybrid system consists of the discrete state system as the high-level proces...
详细信息
ISBN:
(纸本)0780372034
In this paper, we propose a new approach to the high-speed wall following of wheeled mobile robots using hybrid controlsystem. The proposed hybrid system consists of the discrete state system as the high-level process and the continuous state system as the low-level process. In discrete state system, the discrete states are defined by the user-defined constraints and the reference motion commands are specified in the abstracted motions. The reference motion commands are translated into the control inputs for each wheel in the continuous state system. The hybrid controlsystem applied for wheeled mobile robots can combine the motion planning and autonomous navigation with obstacle avoidance in indoor navigation problem. Simulation results show that hybrid system approach is an effective method for the autonomous navigation. In the experiments of the indoor environments, we proved that the performance of the high-speed navigation is excellent.
A new method of applying linear matrix inequalities (LMIs) to multi-objective eigenstructure assignment is put forward. Since there is always a degree of freedom in eigenstructure assignment using state or output feed...
详细信息
A new method of applying linear matrix inequalities (LMIs) to multi-objective eigenstructure assignment is put forward. Since there is always a degree of freedom in eigenstructure assignment using state or output feedback, it is available to use this kind of freedom in designing a system to satisfy some additional specializations. With the help of LMI technology, a controller insensitive to pertubation and good in robust stability is realized. And the result of a practical example shows that the method is very useful in flight controller design.
In this paper, we propose a new approach to the high-speed navigation of the indoor environments for wheeled mobile robots using hybrid dynamic control approach. The proposed hybrid system consists of the discrete sta...
详细信息
In this paper, we propose a new approach to the high-speed navigation of the indoor environments for wheeled mobile robots using hybrid dynamic control approach. The proposed hybrid system consists of the discrete state system as the high-level process and the continuous state system as the low-level process. In discrete state system, the di crete states are defined by the user-defined constraints and the abstracted motions specify the reference motion commands of mobile robots. The experimental results show that hybrid system approach is an effective method for the autonomous navigation and highspeed maneuvering.
Power systems for hybrid electric vehicles, like most autonomous power systems, must fully and effectively utilize internal power resources to ensure the desired performance on one hand and longevity of system compone...
详细信息
Power systems for hybrid electric vehicles, like most autonomous power systems, must fully and effectively utilize internal power resources to ensure the desired performance on one hand and longevity of system components on the other. The optimum solution involves tradeoffs between two often contradictory things. Achieving the optimum depends on the capabilities of design tools used. The Synergetic Approach used in the work described here opens new opportunities to solve this problem more effectively.
This paper is concerned with the argument that the identification of Takagi Sugeno (T-S) fuzzy models from training data should involve an important feature between data fitness and model complexity. One hand a (T-S) ...
详细信息
This paper presents an improved ZVS partial series resonant DC/DC converter (PSRC) with low conduction losses, suitable for high power and high frequency application. The proposed PSRC has advantages of zero-voltage-s...
详细信息
A design approach of the initial state of the repetitive controller is proposed in this paper. The approach makes full use of the feature of the digital controller and optimizes the transient response without perplexi...
详细信息
A design approach of the initial state of the repetitive controller is proposed in this paper. The approach makes full use of the feature of the digital controller and optimizes the transient response without perplexing the controller. A numerical example is presented to illustrate the validity of the approach.
In this paper, a dynamic fuzzy approach is proposed for the selection of an evaluation function for a genetic algorithm (GA). The GA is in turn used to optimise a neural network (NN) architecture. A correctly classifi...
详细信息
In this paper, a dynamic fuzzy approach is proposed for the selection of an evaluation function for a genetic algorithm (GA). The GA is in turn used to optimise a neural network (NN) architecture. A correctly classified pattern in the presence of error is considered for the fitness function. Fuzzy logic is used to dynamically select the chromosome for evolution. It gives a direction of evolution as well as provides more exploration among most desirable ones in the population, by dynamically changing the range of the membership function. To increase the resolution, different heights of the membership function with increasing heights towards more feasible features are considered. Modelling of a flexible manipulator is used to show the performance of the proposed approach. Results show that dynamic fuzzy logic performs better than fuzzy logic with fixed range and height.
This paper discusses speech recognition based on a new statistical phoneme segment model which is trained by phoneme parameters derived from automatically extracted phoneme segments. The proposed system operates as fo...
详细信息
This paper discusses speech recognition based on a new statistical phoneme segment model which is trained by phoneme parameters derived from automatically extracted phoneme segments. The proposed system operates as follows. In preprocessing before recognition, the phoneme boundaries are detected by segmentation. The phonemes are discriminated using a stochastic phoneme segment model, and a phoneme segment lattice with scores is constructed. Next the speech recognition is performed by matching of symbol sequences to dictionary items. The segmentation system that is employed can infer phoneme boundaries with high accuracy. This helps to eliminate unnecessary parameters, leaving the feature parameters which are effective in separating phonemes. In other words, the phoneme recognition problem in continuous speech can be reduced to a discrimination problem and thus a speaker-independent model can be constructed from a relatively small number of training data. The stochastic phoneme segment model is trained with training samples extracted from a phoneme-balanced word set of 4920 words uttered by 10 speakers. In a recognition experiment with 6709 words uttered by 63 nontraining speakers, a recognition rate of 92.6% was obtained as the average for all speakers, using a word dictionary of 212 words.
暂无评论