• Journal of the Korea Institute of Military Science and Technology
• /
• v.14 no.6
• /
• pp.965-973
• /
• 2011

Small unmanned ground vehicles(SUGVs) are typically operational on unstructured environments such as crashed building, mountain area, caves, and so on. On those terrains, driving control can suffer from the unexpected ground disturbances which occasionally lead turnover situation. In this paper, we have proposed an algorithm which sustains driving stability of a SUGV as preventing from turnover. The algorithm exploits potential field method in order to determine the stability of the robot. Then, the flipper and manipulator posture of the SUGV is optimized from local optimization algorithm known as gradient descent method. The proposed algorithm is verified using 3D dynamic simulation, and results showed that the proposed algorithm contributes to driving stability of SUGV.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.1964-1966
• /
• 2001

Active Noise control(ANC) is rapidly becoming the most effective way to reduce noises that can otherwise be very difficult and expensive to control. This research presents ANFIS (Adaptive Network Fuzzy Inference System) controller for adaptively noise cancelling in a duct. ANC system generates secondary control sound pressure with same amplitude and with opposite phase as noise to be eliminated. ANFIS controller is trained to optimize its parameters for adaptively cancelling noise. That is ANFIS train its parameters by gradient descent and LSE method so called hybrid method. This paper present ANFIS in active noise control which provides an improvement convergence speed and limitation of linearity condition. It can model nonlinear functions of arbitrary complexity and ANFIS can construct an input-ouput mapping based on both human knowledge in the form of Takagi and Sugeno's fuzzy if-then rules and stipulated input-output data pairs. This paper also shows that the proposed ANFIS active noise control system successfully cancelled noise.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2184-2186
• /
• 2001

The research presented in this paper focuses on a method for the detection of High Impedance Fault(HIF). The method will use the fast wavelet transform and neural network system. HIF on the multi-grounded three-phase four-wires primary distribution power system cannot be detected effectively by existing over current sensing devices. These paper describes the application of fast wavelet transform to the various HIF data. These data were measured in actual 22.9kV distribution system. Wavelet transform analysis gives the frequency and time-scale information. The neural network system as a fault detector was trained to discriminate HIF from the normal status by a gradient descent method. The proposed method performed very well by proving the right state when it was applied staged fault data and normal load mimics HIF, such as arc-welder.

• Computers and Concrete
• /
• v.20 no.6
• /
• pp.627-634
• /
• 2017

Predicting the compressive strength of concrete is important to assess the load-carrying capacity of a structure. However, the use of blended cements to accrue the technical, economic and environmental benefits has increased the complexity of prediction models. Artificial Neural Networks (ANNs) have been used for predicting the compressive strength of ordinary Portland cement concrete, i.e., concrete produced without the addition of supplementary cementing materials. In this study, models to predict the compressive strength of blended cement concrete prepared with a natural pozzolan were developed using regression models and single- and 2-phase learning ANNs. Back-propagation (BP), Levenberg-Marquardt (LM) and Conjugate Gradient Descent (CGD) methods were used for training the ANNs. A 2-phase learning algorithm is proposed for the first time in this study for predictive modeling of the compressive strength of blended cement concrete. The output of these predictive models indicates that the use of a 2-phase learning algorithm will provide better results than the linear regression model or the traditional single-phase ANN models.

• Computers and Concrete
• /
• v.21 no.6
• /
• pp.697-703
• /
• 2018

Compressive strength is one of the most important engineering properties of concrete, and testing of the compressive strength of concrete specimens is often costly and time consuming. In order to provide the time for concrete form removal, re-shoring to slab, project scheduling and quality control, it is necessary to predict the concrete strength based upon the early strength data. However, concrete compressive strength is affected by many factors, such as quality of raw materials, water cement ratio, ratio of fine aggregate to coarse aggregate, age of concrete, compaction of concrete, temperature, relative humidity and curing of concrete. The concrete compressive strength is a quite nonlinear function that changes depend on the materials used in the concrete and the time. This paper presents an adaptive neuro-fuzzy inference system (ANFIS) for the prediction of concrete compressive strength. The training of fuzzy system was performed by a hybrid method of gradient descent method and least squares algorithm, and the subtractive clustering algorithm (SCA) was utilized for optimizing the number of fuzzy rules. Experimental data on concrete compressive strength in the literature were used to validate and evaluate the performance of the proposed ANFIS model. Further, predictions from three models (the back propagation neural network model, the statistics model, and the ANFIS model) were compared with the experimental data. The results show that the proposed ANFIS model is a feasible, efficient, and accurate tool for predicting the concrete compressive strength.

• Current Optics and Photonics
• /
• v.2 no.6
• /
• pp.612-622
• /
• 2018

In wave-front-sensor-less adaptive optics (WFS-less AO) systems, the Jacopo Antonello (JA) method belongs to the model-based class and requires few iterations to achieve acceptable distortion correction. However, this method needs a lot of measurements, especially when it deals with moderate or severe aberration, which is undesired in free-space optical communication (FSOC). On the contrary, the stochastic parallel gradient descent (SPGD) algorithm only requires three time measurements in each iteration, and is widely applied in WFS-less AO systems, even though plenty of iterations are necessary. For better and faster compensation, we propose a WFS-less hybrid approach, borrowing from the JA method to compensate for low-order wave front and from the SPGD algorithm to compensate for residual low-order wave front and high-order wave front. The correction results for this proposed method are provided by simulations to show its superior performance, through comparison of both the Strehl ratio and the convergence speed of the WFS-less hybrid approach to those of the JA method and SPGD algorithm.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.1
• /
• pp.136-141
• /
• 2022

A very complex task in deep learning such as image classification must be solved with the help of neural networks and activation functions. The backpropagation algorithm advances backward from the output layer towards the input layer, the gradients often get smaller and smaller and approach zero which eventually leaves the weights of the initial or lower layers nearly unchanged, as a result, the gradient descent never converges to the optimum. We propose a two-factor non-saturating activation functions known as Bea-Mish for machine learning applications in deep neural networks. Our method uses two factors, beta (𝛽) and alpha (𝛼), to normalize the area below the boundary in the Mish activation function and we regard these elements as Bea. Bea-Mish provide a clear understanding of the behaviors and conditions governing this regularization term can lead to a more principled approach for constructing better performing activation functions. We evaluate Bea-Mish results against Mish and Swish activation functions in various models and data sets. Empirical results show that our approach (Bea-Mish) outperforms native Mish using SqueezeNet backbone with an average precision (AP50val) of 2.51% in CIFAR-10 and top-1accuracy in ResNet-50 on ImageNet-1k. shows an improvement of 1.20%.

• Journal of Auto-vehicle Safety Association
• /
• v.14 no.2
• /
• pp.26-38
• /
• 2022

This paper proposes multiple RLS and actuator performance index-based adaptive actuator fault-tolerant control and detection algorithms for longitudinal autonomous driving. The proposed algorithm computes the desired acceleration using feedback law for longitudinal autonomous driving. When actuator fault or performance degradation exists, it is designed that the desired acceleration is adjusted with the calculated feedback gains based on multiple RLS and gradient descent method for fault-tolerant control. In order to define the performance index, the error between the desired and actual accelerations is used. The window-based weighted error standard deviation is computed with the design parameters. Fault level decision algorithm that can represent three fault levels such as normal, warning, emergency levels is proposed in this study. Performance evaluation under various driving scenarios with actuator fault was conducted based on co-simulation of Matlab/Simulink and commercial software (CarMaker).

• 제어로봇시스템학회:학술대회논문집
• /
• 1994.10a
• /
• pp.263-266
• /
• 1994

Recently, complicated and dexterous tasks with two or more arms are needed in ninny robot manipulator applications which can not be accomplished with one manipulator. In general, when two arms manipulate an object, tile dynamics of the arms and the object should be considered simultaneously. In order to control the force of tile arms, we can use various control schemes based upon dynamic modeling. But, there are difficulties in solving inverse dynamics equations, and the environment where a manipulator performs various tasks is usually unknown, and we can not describe a model precisely, for instances, the effect of the joint flexibility, and the friction between the arm and the object. Therefore, in this paper, we suggest a new force control method employing fuzzy inference without solving dynamic equations. Fuzzy inference rules and parameters are designed and adjusted with the automatic fuzzy modeling method using the Hough transform and gradient descent method.

• International Journal of Computer Science & Network Security
• /
• v.23 no.10
• /
• pp.115-128
• /
• 2023

Deep learning has been incorporating various optimization techniques motivated by new pragmatic optimizing algorithm advancements and their usage has a central role in Machine learning. In recent past, new avatars of various optimizers are being put into practice and their suitability and applicability has been reported on various domains. The resurgence of novelty starts from Stochastic Gradient Descent to convex and non-convex and derivative-free approaches. In the contemporary of these horizons of optimizers, choosing a best-fit or appropriate optimizer is an important consideration in deep learning theme as these working-horse engines determines the final performance predicted by the model. Moreover with increasing number of deep layers tantamount higher complexity with hyper-parameter tuning and consequently need to delve for a befitting optimizer. We empirically examine most popular and widely used optimizers on various data sets and networks-like MNIST and GAN plus others. The pragmatic comparison focuses on their similarities, differences and possibilities of their suitability for a given application. Additionally, the recent optimizer variants are highlighted with their subtlety. The article emphasizes on their critical role and pinpoints buttress options while choosing among them.