• Journal of information and communication convergence engineering
• /
• v.13 no.2
• /
• pp.123-131
• /
• 2015

Training neural networks is a complex task with great importance in the field of supervised learning. In the training process, a set of input-output patterns is repeated to an artificial neural network (ANN). From those patterns weights of all the interconnections between neurons are adjusted until the specified input yields the desired output. In this paper, a new hybrid algorithm is proposed for global optimization of connection weights in an ANN. Dynamic swarms are shown to converge rapidly during the initial stages of a global search, but around the global optimum, the search process becomes very slow. In contrast, the gradient descent method can achieve faster convergence speed around the global optimum, and at the same time, the convergence accuracy can be relatively high. Therefore, the proposed hybrid algorithm combines the dynamic particle swarm optimization (DPSO) algorithm with the backpropagation (BP) algorithm, also referred to as the DPSO-BP algorithm, to train the weights of an ANN. In this paper, we intend to show the superiority (time performance and quality of solution) of the proposed hybrid algorithm (DPSO-BP) over other more standard algorithms in neural network training. The algorithms are compared using two different datasets, and the results are simulated.

• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.1097-1112
• /
• 1989

An iterative learning control scheme is incorporated to the computed torque method as a means to enhance the accuracy and the flexibility. A learning rule is constructed by utilizing a gradient descent algorithm and data compressing techniques are illustrated. Computer simulation results show a good performance of the scheme under a relatively high speed and a heavy payload condition.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.37 no.12
• /
• pp.1445-1452
• /
• 2013

In this paper, we propose a real-time algorithm for estimating the relative position of a person with respect to a robot (camera) using a monocular camera. The algorithm detects the head and shoulder regions of a person using HOG (Histogram of Oriented Gradient) feature vectors and an SVM (Support Vector Machine) classifier. The size and location of the detected area are used for calculating the relative distance and angle between the person and the camera on a robot. To increase the speed of the algorithm, we use a GPU and NVIDIA's CUDA library; the resulting algorithm speed is ~ 15 Hz. The accuracy of the algorithm is compared with the output of a SICK laser scanner.

• ETRI Journal
• /
• v.35 no.2
• /
• pp.193-199
• /
• 2013

This paper addresses nonnegative independent component analysis (NICA), with the aim to realize the blind separation of nonnegative well-grounded independent source signals, which arises in many practical applications but is hardly ever explored. Recently, Bertrand and Moonen presented a multiplicative NICA (M-NICA) algorithm using multiplicative update and subspace projection. Based on the principle of the mutual correlation minimization, we propose another novel cost function to evaluate the diagonalization level of the correlation matrix, and apply the multiplicative exponentiated gradient (EG) descent update to it to maintain nonnegativity. An efficient approach referred to as the EG-NICA algorithm is derived and its validity is confirmed by numerous simulations conducted on different types of source signals. Results show that the separation performance of the proposed EG-NICA algorithm is superior to that of the previous M-NICA algorithm, with a better unmixing accuracy. In addition, its convergence speed is adjustable by an appropriate user-defined learning rate.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.12
• /
• pp.2418-2425
• /
• 1994

Although the error backpropagation(EBP) algorithm based on the gradient descent method is a widely-used learning algorithm of neural networks, learning sometimes takes a long time to acquire accuracy. This paper develops a novel learning method to alleviate the problems of EBP algorithm such as local minima, slow speed, and size of structure and thus to improve performance by adopting other new networks. Gaussian Potential Function networks(GPFN), in parallel with multilayer neural networks. Empirical simulations show the efficacy of the proposed algorithm in function approximation, which enables us to train networks faster with the better generalization capabilities.

• Journal of the Semiconductor & Display Technology
• /
• v.13 no.1
• /
• pp.57-62
• /
• 2014

This paper proposes a new optical recognition method of credit card numbers. Firstly, the proposed method segments numbers from the input image of a credit card. It uses the significant differences of standard deviations between the foreground numbers and the background. Secondly, the method extracts gradient features from the segmented numbers. The gradient features are defined as four directions of grayscale pixels for 16 regions of an input number. Finally, it utilizes an artificial neural network classifier that uses an error back-propagation algorithm. The proposed method is implemented using C language in an embedded Linux system for a high-speed real-time image processing. Experiments were conducted by using real credit card images. The results show that the proposed algorithm is quite successful for most credit cards. However, the method fails in some credit cards with strong background patterns.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.12a
• /
• pp.113-117
• /
• 2002

PID controllers, which have been widely used in industry, have a simple structure and robustness to modeling error. But it is difficult to have uniformly good control performance in system parameters variation or different velocity command. In this paper, we propose a nonlinear adaptive PR controller based on an Immune feedback mechanism and a gradient descent teaming. This algorithm has a simple structure and robustness to system parameters variation. To verify performances of the proposed nonlinear adaptive PID controller, the speed control of nonlinear DC motor Is peformed. The simulation results show that the proposed control systems are effective in tracking a command velocity under system parameters variation

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.385-398
• /
• 2021

The complexity of deep learning models affects the real-time performance of gesture recognition, thereby limiting the application of gesture recognition algorithms in actual scenarios. Hence, a residual learning neural network based on a deep convolutional neural network is proposed. First, small convolution kernels are used to extract the local details of gesture images. Subsequently, a shallow residual structure is built to share weights, thereby avoiding gradient disappearance or gradient explosion as the network layer deepens; consequently, the difficulty of model optimisation is simplified. Additional convolutional neural networks are used to accelerate the refinement of deep abstract features based on the spatial importance of the gesture feature distribution. Finally, a fully connected cascade softmax classifier is used to complete the gesture recognition. Compared with the dense connection multiplexing feature information network, the proposed algorithm is optimised in feature multiplexing to avoid performance fluctuations caused by feature redundancy. Experimental results from the ISOGD gesture dataset and Gesture dataset prove that the proposed algorithm affords a fast convergence speed and high accuracy.

• Transactions on Control, Automation and Systems Engineering
• /
• v.1 no.1
• /
• pp.69-74
• /
• 1999

Adaptive algorithms based on gradient adaptation have been extensively investigated and successfully joined with active noise/vibration control applications. The Filtered-X LMS algorithm became one of the basic feedforward algorithms in such applications, but is not fully understood yet. Effects of cancellation path model on the Filtered-X LMS algorithm have investigated and some useful properties related to stability were discovered. Most of the results stated that the error in the cancellation path model is undesirable to the Filtered X LMS. However, we started convergence analysis of Filtered-X LMS based on the assumption that erroneous model does not always degrade its performance. In this paper, we present a way of optimizing the cancellation path modern in order to enhance the convergence speed by introducing intentional phase error. Carefully designed intentional phase error enhances the convergence speed of the Filtered X LMS algorithm for pure tone noise suppression application without any performance loss at steady state.

• 제어로봇시스템학회:학술대회논문집
• /
• 1999.10a
• /
• pp.309-312
• /
• 1999

This paper proposed a novel method for pseudo-on-line scheme using look-up table based on the genetic algorithm The technique is an pseudo-on-line method that optimally estimate the parameters of FPID controller for systems with non-linearity using the genetic algorithm which does not use the gradient and finds the global optimum of an unconstraint optimization problem. The proposed controller is applied to speed control of 3-phase induction motor and its computer simulation is carried out. Simulation results show that the proposed method is more excellent then conventional FPID and PID controllers.