• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.23 no.11
• /
• pp.831-836
• /
• 2010

In this paper, Plasma Enhanced Chemical Vapor Deposition (PECVD) $SiO_2$ film properties are modeled using statistical analysis and neural networks. For systemic analysis, Box-Behnken's 3 factor design of experiments (DOE) with response surface method are used. For characterization, deposited film thickness and film stress are considered as film properties and three process input factors including plasma RF power, flow rate of $N_2O$ gas, and flow rate of 5% $SiH_4$ gas contained at $N_2$ gas are considered for modeling. For film thickness characterization, regression based model showed only 0.71% of root mean squared (RMS) error. Also, for film stress model case, both regression model and neural prediction model showed acceptable RMS error. For sensitivity analysis, compare to conventional fixed mid point based analysis, proposed sensitivity analysis for entire range of interest support more process information to optimize process recipes to satisfy specific film characteristic requirements.

• Journal of Advanced Marine Engineering and Technology
• /
• v.21 no.4
• /
• pp.414-420
• /
• 1997

An intelligent speed control system for marine diesel engines is presented. The approach adopt¬ed is to use a conventional PID controller for normal operation and a feedforward controller for adaptive control. The feedforward controller is a neural network. The neural network is the inverse dynamics model of the plant, which is being trained on line. The parametric model of the diesel engine is represented in a linear second-order system, with a first-order combustion part and a revolution part each at a normal operating point. The time delay in the control of the com¬bustion part is approximated to the first-order system. The tuned PID parameters are set based on the model for normal operating point. To obtain the inverse dynamics of the diesel engine system, two neural networks are used, one for inverse, the other for forward dynamics. The former is posi¬tioned across the plant to learn its inverse dynamics during operation, and the latter is placed in series with the controlled plant. Simulation results are presented to illustrate the applicability of the proposed scheme to intelligent adaptive control of diesel engines.

• Journal of Information Processing Systems
• /
• v.14 no.1
• /
• pp.176-190
• /
• 2018

This paper presents a novel convolutional neural network based multi-feature fusion learning method for non-rigid 3D model retrieval, which can investigate the useful discriminative information of the heat kernel signature (HKS) descriptor and the wave kernel signature (WKS) descriptor. At first, we compute the 2D shape distributions of the two kinds of descriptors to represent the 3D model and use them as the input to the networks. Then we construct two convolutional neural networks for the HKS distribution and the WKS distribution separately, and use the multi-feature fusion layer to connect them. The fusion layer not only can exploit more discriminative characteristics of the two descriptors, but also can complement the correlated information between the two kinds of descriptors. Furthermore, to further improve the performance of the description ability, the cross-connected layer is built to combine the low-level features with high-level features. Extensive experiments have validated the effectiveness of the designed multi-feature fusion learning method.

• The Journal of Korea Robotics Society
• /
• v.17 no.4
• /
• pp.425-430
• /
• 2022

As robots are considered one of the mainstream digital transformations, robots with machine vision becomes a main area of study providing the ability to check what robots watch and make decisions based on it. However, it is difficult to find a small object in the image mainly due to the flaw of the most of visual recognition networks. Because visual recognition networks are mostly convolution neural network which usually consider local features. So, we make a model considering not only local feature, but also global feature. In this paper, we propose a detection method of a small marker on the object using deep learning and an algorithm that considers global features by combining Transformer's self-attention technique with a convolutional neural network. We suggest a self-attention model with new definition of Query, Key and Value for model to learn global feature and simplified equation by getting rid of position vector and classification token which cause the model to be heavy and slow. Finally, we show that our model achieves higher mAP than state of the art model YOLOr.

• Structural Engineering and Mechanics
• /
• v.75 no.5
• /
• pp.633-642
• /
• 2020

Artificial neural networks (ANNs) are known as intelligent methods for modeling the behavior of physical phenomena because of it is a soft computing technique and takes data samples rather than entire data sets to arrive at solutions, which saves both time and money. ANN is successfully used in the civil engineering applications which are suitable examining the complicated relations between variables. Functionally graded materials (FGMs) are advanced composites that successfully used in various engineering design. The FGMs are nonhomogeneous materials and made of two different type of materials. In the present study, the bending analysis of functionally graded material (FGM) beams presents on theoretical based on combination of mixed-finite element method, Gâteaux differential and Timoshenko beam theory. The main idea in this study is to build a model using ANN with four parameters that are: Young's modulus ratio (E_t/E_b), a shear correction factor (k_s), power-law exponent (n) and length to thickness ratio (L/h). The output data is the maximum displacement (w). In the experiments: 252 different data are used. The proposed ANN model is evaluated by the correlation of the coefficient (R), MAE and MSE statistical methods. The ANN model is very good and the maximum displacement can be predicted in ANN without attempting any experiments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.9
• /
• pp.3204-3220
• /
• 2021

We perform the task of video object segmentation by incorporating a conditional random field (CRF) and convolutional neural networks (CNNs). Most methods employ a CRF to refine a coarse output from fully convolutional networks. Others treat the inference process of the CRF as a recurrent neural network and then combine CNNs and the CRF into an end-to-end model for video object segmentation. In contrast to these methods, we propose a novel higher-order CRF model to solve the problem of video object segmentation. Specifically, we use CNNs to establish a higher-order dependence among pixels, and this dependence can provide critical global information for a segmentation model to enhance the global consistency of segmentation. In general, the optimization of the higher-order energy is extremely difficult. To make the problem tractable, we decompose the higher-order energy into two parts by utilizing auxiliary variables and then solve it by using an iterative process. We conduct quantitative and qualitative analyses on multiple datasets, and the proposed method achieves competitive results.

• International Journal of Control, Automation, and Systems
• /
• v.6 no.1
• /
• pp.24-34
• /
• 2008

A novel neural network model, termed the standard neural network model (SNNM), similar to the nominal model in linear robust control theory, is suggested to facilitate the synthesis of controllers for delayed (or non-delayed) nonlinear systems composed of neural networks. The model is composed of a linear dynamic system and a bounded static delayed (or non-delayed) nonlinear operator. Based on the global asymptotic stability analysis of SNNMs, Static state-feedback controller and dynamic output feedback controller are designed for the SNNMs to stabilize the closed-loop systems, respectively. The control design equations are shown to be a set of linear matrix inequalities (LMIs) which can be easily solved by various convex optimization algorithms to determine the control signals. Most neural-network-based nonlinear systems with time delays or without time delays can be transformed into the SNNMs for controller synthesis in a unified way. Two application examples are given where the SNNMs are employed to synthesize the feedback stabilizing controllers for an SISO nonlinear system modeled by the neural network, and for a chaotic neural network, respectively. Through these examples, it is demonstrated that the SNNM not only makes controller synthesis of neural-network-based systems much easier, but also provides a new approach to the synthesis of the controllers for the other type of nonlinear systems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3416-3435
• /
• 2023

Task offloading in vehicular networks is hot topic in the development of autonomous driving. In these scenarios, due to the role of vehicles and pedestrians, task characteristics are changing constantly. The classical deep learning algorithm always uses a pre-trained neural network to optimize task offloading, which leads to system performance degradation. Therefore, this paper proposes a neural network fine-tuning task offloading algorithm, combining with location prediction for pedestrians and vehicles by the Payne model of fluid dynamics and the car-following model, respectively. After the locations are predicted, characteristics of tasks can be obtained and the neural network will be fine-tuned. Finally, the proposed algorithm continuously predicts task characteristics and fine-tunes a neural network to maintain high system performance and meet low delay requirements. From the simulation results, compared with other algorithms, the proposed algorithm still guarantees a lower task offloading delay, especially when congestion occurs.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.5
• /
• pp.829-835
• /
• 2009

Parameter design is an approach to reducing performance variation of quality characteristic value in products and processes. Taguchi has used the signal-to-noise ratio to achieve the appropriate set of operating conditions where variability around target is low in the Taguchi parameter design. However, there are difficulties in practical application, such as complexity and nonlinear relationships among quality characteristics and control factors (design factors), and interactions occurred among control factors. Neural networks have a learning capability and model free characteristics. There characteristics support neural networks as a competitive tool in processing multivariable input-output implementation. In this paper we propose a substantially simpler optimization procedure for parameter design using neural network. An example is illustrated to compare the difference between the Taguchi method and neural network method.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.301-307
• /
• 2022

Energy consumption has grown alongside dramatic population increases. Statistics show that buildings in particular utilize a significant amount of energy, worldwide. Because of this, building energy prediction is crucial to best optimize utilities' energy plans and also create a predictive model for consumers. To improve energy prediction performance, this paper proposes a ResNet-LSTM model that combines residual networks (ResNets) and long short-term memory (LSTM) for energy consumption prediction. ResNets are utilized to extract complex and rich features, while LSTM has the ability to learn temporal correlation; the dense layer is used as a regression to forecast energy consumption. To make our model more robust, we employed Huber loss during the optimization process. Huber loss obtains high efficiency by handling minor errors quadratically. It also takes the absolute error for large errors to increase robustness. This makes our model less sensitive to outlier data. Our proposed system was trained on historical data to forecast energy consumption for different time series. To evaluate our proposed model, we compared our model's performance with several popular machine learning and deep learning methods such as linear regression, neural networks, decision tree, and convolutional neural networks, etc. The results show that our proposed model predicted energy consumption most accurately.