Search

A new improved ANN control based aircraft shunt filter has been proposed in this paper. The shunt active power filter model has been improved using Genetic Algorithm and fuzzy logic. Genetic Algorithm has been used to find the optimum value of filter inductor; whereas fuzzy logic controller has been used in voltage control loop of the filter. The improvement in the control scheme using ANN control makes APF versatile for compensation of reactive power, harmonic currents, and unbalance in source currents. Proposed aircraft shunt filter also provide proper solution to the neural current in the system. The simulated results using MATLAB model are presented and they clearly prove the effectiveness of the proposed control method of aircraft shunt APF. [ABSTRACT FROM AUTHOR]

In this study, we investigated an alternative technique to automatically classify road traffic congestion with high accuracy aligning with travelers' opinions. The method utilized an intelligent traffic camera system orchestrated with a web survey system to collect the traffic conditions and travelers' opinions. A large number of human perceptions were used to train the artificial neural network (ANN) model that classify velocity and traffic flow into three congestion levels: light, heavy, and jam. The learning parameters were heuristically optimized to gain highest prediction accuracy. The outcomes were a practical method and the model achieving as high as 94.99% accuracy. The model was then compared to the Occupancy Ratio (OR) technique, currently in service in the Bangkok Metropolitan Area. The comparison indicated that our model could determine the traffic congestion levels 12.15% more accurately than the existing system. The analysis revealed that the derived model classified congestion levels based mainly on the vehicle velocity, suggesting that the model could be modified and broadly used with various types of traffic sensors. The methodology, though conceived for use in Bangkok, is a general Intelligent Transportation System (ITS) practice that can be applied to any part of the world. [ABSTRACT FROM AUTHOR]

The geo-mechanical classification - rock mass rating (RMR) - is used for categorizing rock mass. Assessing RMR is an important factor for successful accomplishment of a tunneling project. In the rock mechanics and mining literatures, some empirical methods exist between rock mass and other rock properties, such as using characteristic of the rock, geological structure etc. However, those means have some limitations by special rock types. After analyzed the information to identify RMR, a new parameter as one of the input neurons was used to develop predictive relations. There are eight parameters as the input parameters are presented based on artificial neural networks (ANN). The situ-test data of the tunnel face were measured and the experimental results indicate the proposed method was effective. [ABSTRACT FROM AUTHOR]

In this paper, a neuro-fuzzy technique known as the Adaptive-Neuro Fuzzy Inference System (ANFIS) has been used to highlight the application of ANFIS to perform human posture classification task using the new simplified shock graph (SSG) representation. Basically, a shock graph is a shape abstraction that decomposed a shape into a set of hierarchically organized primitive parts. The shock graph that represents the silhouette of an object in terms of a set of qualitatively defined parts and organized in a hierarchical, directed acyclic graph is used as a powerful representation of human shape in our work. The SSG feature provides a compact, unique and simple way of representing human shape and has been tested with several classifiers. As such, in this paper we intend to test its efficacy with another classifier, that is, the ANFIS classifier system. The result showed that the proposed ANFIS model can be used in classifying various human postures. [ABSTRACT FROM AUTHOR]

For traditional human face based biometrics, usually one task (face recognition) is learned at one time. This single task learning (STL) approach may neglect potential rich information resources hidden in other related tasks, while multitask learning (MTL) can make full use of the latent information. MTL is an inductive transfer method which improves generalization by using the domain information contained in the training signals of related tasks as an inductive bias. In this paper, backpropagation (BP) network based MTL approach is proposed for face recognition. The feasibility of this approach is demonstrated through two different face recognition experiments, which show that MTL based on BP neural networks is more effective than the traditional STL approach, and that MTL is also a practical approach for face recognition. [ABSTRACT FROM AUTHOR]

Multimodal movements are those in which two or more different transportation modes are linked end-to-end in order to move freight and/or people from point of origin to point of destination. Computational efficiency required to select the path will be drastically deteriorated by increasing the number of traffic modes and terminals. With different goals, the minimization of cost, time, risk and unreliability, it is usually assumed that the route selection of multimodal transportation is a multicriteria decision making (MCDM) problem. On the basis of the Fuzzy Analytic Hierarchy Process (AHP) and artificial neural network (ANN) theory, we set up a hybrid MCDM model. The proposed method makes the route selection system in multimodal transportation more comprehensive, scientific, fair and accurate. [ABSTRACT FROM AUTHOR]