Mohammad Reza Yousefi

Face Detection Using Mixture of MLP Experts

This paper presents a face detection method which makes use of a modified mixture of experts. In order to improve the face detection accuracy, a novel structure is introduced which uses the multilayer perceptrons (MLPs), as expert and gating networks, and employs a new learning algorithm to adapt with the MLPs. We call this model Mixture of MLP Experts (MMLPE). Experiments using images from the CMU-130 test set demonstrate the robustness of our method in detecting faces with wide variations in pose, facial expression, illumination, and complex backgrounds. The MMLPE produces promising high detection rate of 98.8% with ten false positives.

Letters: View-independent face recognition with Mixture of Experts

A model for view-independent face recognition, based on Mixture of Experts, ME, is presented. Instead of allowing ME to partition the face space automatically, it is directed to adapt to a particular partitioning corresponding to predetermined views. Experimental results show that this model performs well in recognizing faces of intermediate unseen views. There are neurophysiological evidences that underpin the proposed model, reporting similar mechanisms of pooling the outputs of several view-specific modules to perform view-independent face recognition.

A novel approach in automatic control based on the genetic algorithm in STATCOM for improvement power system transient stability

Static synchronous compensator (STATCOM) is a shunt-connected converter, which can affect rapid control of reactive flow in the transmission line by controlling the generated AC voltage. This article presents a new STATCOM voltage controller design for power system damping. The method of multiplicative uncertainty has been employed to model the variations of the operating points. The controller was tested for a number the step increase in torque reference. Voltage of capacitor STATCOM can be controlled by method of linear quadratic regulator (LQR). In this article, matrixes coefficients and dominant poles of closed loop transfer function are selected based on genetic algorithm method. The results show an improvement in voltage control response in a short response time.

Teacher-directed learning in view-independent face recognition with mixture of experts using single-view eigenspaces

Abstract We propose a new model for view-independent face recognition by multiview approach. We use the so-called “mixture of experts”, ME, in which, the problem space is divided into several subspaces for the experts, and the outputs of experts are combined by a gating network. In our model, instead of leaving the ME to partition the face space automatically, the ME is directed to adapt to a particular partitioning corresponding to predetermined views. To force an expert towards a specific view of face, in the representation layer, we provide each expert with its own eigenspace computed from the faces in the corresponding view. Furthermore, we use teacher-directed learning, TDL, in a way that according to the pose of the input training sample, only the weights of the corresponding expert are updated. The experimental results support our claim that directing the experts to a predetermined partitioning of face space improves the performance of the conventional ME for view-independent face recognition. In particular, for 1200 images of unseen intermediate views of faces from 20 subjects, the ME with single-view eigenspaces yields the average recognition rate of 80.51% in 10 trials, which is noticeably increased to 90.29% by applying the TDL method.

Teacher-directed learning in view-independent face recognition with mixture of experts using overlapping eigenspaces

A model for view-independent face recognition, based on Mixture of Experts, ME, is presented. In the basic form of ME the problem space is automatically divided into several subspaces for the experts, and the outputs of experts are combined by a gating network. In our proposed model, the ME is directed to adapt to a particular partitioning corresponding to predetermined views. To force an expert towards a particular partitioning corresponding to predetermined views, a new representation scheme, overlapping eigenspaces, is introduced, that provides each expert with an eigenspace computed from the faces in the corresponding neighboring views. Furthermore, we use teacher-directed learning, TDL, in a way that according to the pose of the input training sample, only the weights of the corresponding experts are updated. The experimental results support our claim that directing the experts to a predetermined partitioning of the face space improves the performance of the conventional ME for view-independent face recognition. Comparison with some of the most related methods indicates that the proposed model yields excellent recognition rate in view-independent face recognition.

Improving mixture of experts for view-independent face recognition using teacher-directed learning

In this paper we develop a new learning method, called teacher-directed learning (TDL), for mixture of experts (ME) to perform view-independent face recognition. In the basic form of ME the problem space is automatically divided into several subspaces for the experts, and the outputs of experts are combined by a gating network. In our proposed method, the ME is directed to adapt to a particular partitioning corresponding to predetermined views. To do this, we apply a new learning method to ME, called TDL, in a way that according to the pose of the input training sample, only the weights of the corresponding experts are updated. We apply TDL to MEs, composed of MLP experts and a radial basis function gating network, with different representation schemes: global, single-view and overlapping eigenspace. We test them with previously intermediate unseen views of faces. The experimental results support our claim that directing the experts to a predetermined partitioning of the face space improves the performance of the conventional ME for view-independent face recognition. Comparison with some of the most related methods indicates that the proposed model yields excellent recognition rate in view-independent face recognition.

A Mixture of Multilayer Perceptron Experts Network for Modeling Face/Nonface Recognition in Cortical Face Processing Regions

Abstract Recent studies in neurobiology and especially in neuroimaging report that a gating mechanism prior to face processing levels of human visual system, facilitates the face/nonface recognition task. In accordance to these biological evidences, we propose aface/nonface recognition model which makes use of mixture of experts network. In order to improve the face/nonface recognition accuracy, the outputs of the expert networks aze combined using a gating network. A novel structure, which is the use of multilayer perceptrons (MLPs) in forming the expert networks, is introduced. The learning algorithm is modified to be adapted with the MLP networks. The results reveal that using a mixture of simple MLPs is much more beneficial, in many respects, as it shows more certainty at its output and is also easier to train than a single, but complex, MLP.

Simulation of speed sensor less control of PMSM based on DTC method with MRAS

Permanent magnet synchronous motors (PMSM) are appropriate for applications with load-independent speeds or synchronous operation with high accuracy under defined speed. In this paper analysis the structure and equations of the PMSM, direct torque control (DTC) and voltage space vector process then study model reference adaptive system (MRAS) estimators. The PI controller uses from estimate speed feedback and do the speed sensorless control of PMSM based on DTC method with MRAS. The simulation results show that the speed of rotor estimates with high precision and torque response is considerably fast.

Particle swarm optimization and genetic algorithm to optimizing the pole placement controller on Cuk converter

In this paper a novel method to the design of pole placement controller for Cuk converters is presented.This optimized method can control the voltage of DC-DC converter. In this method, average model of converter is employed and it is possible to approximate the system by a linear system and then linear control methods can be used. Pole placement as one of these methods is designed by a systematic methodology based on genetic algorithm (GA) and particle swarm optimization (PSO). The proposed controllers were simultaneously designed and they have provided a coordinated control action and a satisfactory performance for the Cuk converter, as shown in the results.

Operation, modeling, control and applications of static synchronous compensator: A review

Flexible ac transmission systems (FACTS) controller can provide better control than conventional control and achieve fast control response time. Static synchronous compensator (STATCOM) is one of the key flexible ac transmission systems (FACTS) devices based on voltage source converter (VSC) technology. The controller can provide both capacitive and inductive compensation and is able to control output current over the rated maximum capacitive or inductive range independent of the ac system voltage. This paper presents a study of modeling, operation and control fundamentals of the STATCOM.