• The Journal of the Acoustical Society of Korea
• /
• v.40 no.2
• /
• pp.130-138
• /
• 2021

This paper presents an effective structure by applying various normalization to Convolutional Neural Networks (CNN) for seismic event classification. Normalization techniques can not only improve the learning speed of neural networks, but also show robustness to noise. In this paper, we analyze the effect of input data normalization and hidden layer normalization on the deep learning model for seismic event classification. In addition an effective model is derived through various experiments according to the structure of the applied hidden layer. As a result of various experiments, the model that applied input data normalization and weight normalization to the first hidden layer showed the most stable performance improvement.

• Steel and Composite Structures
• /
• v.44 no.2
• /
• pp.241-254
• /
• 2022

The cables in a cable-stayed bridge are critical load-carrying parts. The potential damage to cables should be identified early to prevent disasters. In this study, an efficient deep learning model is proposed for the damage identification of cables using both a multi-layer perceptron (MLP) and a graph neural network (GNN). Datasets are first generated using the practical advanced analysis program (PAAP), which is a robust program for modeling and analyzing bridge structures with low computational costs. The model based on the MLP and GNN can capture complex nonlinear correlations between the vibration characteristics in the input data and the cable system damage in the output data. Multiple hidden layers with an activation function are used in the MLP to expand the original input vector of the limited measurement data to obtain a complete output data vector that preserves sufficient information for constructing the graph in the GNN. Using the gated recurrent unit and set2set model, the GNN maps the formed graph feature to the output cable damage through several updating times and provides the damage results to both the classification and regression outputs. The model is fine-tuned with the original input data using Adam optimization for the final objective function. A case study of an actual cable-stayed bridge was considered to evaluate the model performance. The results demonstrate that the proposed model provides high accuracy (over 90%) in classification and satisfactory correlation coefficients (over 0.98) in regression and is a robust approach to obtain effective identification results with a limited quantity of input data.

• Journal of Welding and Joining
• /
• v.32 no.4
• /
• pp.26-33
• /
• 2014

The metallurgical and mechanical characteristics, toughness and corrosion resistance of dissimilar welds between super duplex stainless steel UNS S32750 and carbon steel ASTM A516Gr.70 have been evaluated. Three heat inputs of 21.12, 24.00, 26.88kJ/cm were employed to make joints of dissimilar metals with flux cored arc welding(FCAW). Based on microstructural examination, vermicular ferrite was formed in the first layer of weld at low heat input(21.12kJ/cm) and $Cr_{eq}/Ni_{eq}$ of 1.61 while acicular ferrite was formed in last layer of weld at high heat input(26.88kJ/cm) and $Cr_{eq}/Ni_{eq}$ of 1.72. Ferrite percentage in dissimilar welds was lowest in the first layer of weld regardless of heat inputs and it gradually increased in the second and third layers of weld. Heat affected zone showed higher hardness than the weld metal although reheated zone showed lower hardness than weld metal due to the formation of secondary austenite. Tensile strengths of dissimilar welds increased with heat input and there was 100MPa difference. The corrosion test by ferric chloride solution showed that carbon steel had poor corrosion resistance and pitting corrosion occurred in the first layer(root pass) of weld due to the presence of reheated zone where secondary austenite was formed. The salt spray test of carbon steel showed that the surface only corroded but the amount of weight loss was extremely low.

• Journal of KIISE:Software and Applications
• /
• v.30 no.7_8
• /
• pp.649-658
• /
• 2003

We propose a hierarchical architecture of ART2 Network for performance improvement and fast pattern classification model using fitness selection. This hierarchical network creates coarse clusters as first ART2 network layer by unsupervised learning, then creates fine clusters of the each first layer as second network layer by supervised learning. First, it compares input pattern with each clusters of first layer and select candidate clusters by fitness measure. We design a optimized fitness function for pruning clusters by measuring relative distance ratio between a input pattern and clusters. This makes it possible to improve speed and accuracy. Next, it compares input pattern with each clusters connected with selected clusters and finds winner cluster. Finally it classifies the pattern by a label of the winner cluster. Results of our experiments show that the proposed method is more accurate and fast than other approaches.

• International Journal of Control, Automation, and Systems
• /
• v.2 no.4
• /
• pp.423-434
• /
• 2004

In this paper, we introduce a new topology of Self-Organizing Polynomial Neural Networks (SOPNN) based on genetically optimized Multi-Layer Perceptron (MLP) and discuss its comprehensive design methodology involving mechanisms of genetic optimization. Let us recall that the design of the 'conventional' SOPNN uses the extended Group Method of Data Handling (GMDH) technique to exploit polynomials as well as to consider a fixed number of input nodes at polynomial neurons (or nodes) located in each layer. However, this design process does not guarantee that the conventional SOPNN generated through learning results in optimal network architecture. The design procedure applied in the construction of each layer of the SOPNN deals with its structural optimization involving the selection of preferred nodes (or PNs) with specific local characteristics (such as the number of input variables, the order of the polynomials, and input variables) and addresses specific aspects of parametric optimization. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between the approximation and generalization (predictive) abilities of the model. To evaluate the performance of the GA-based SOPNN, the model is experimented using pH neutralization process data as well as sewage treatment process data. A comparative analysis indicates that the proposed SOPNN is the model having higher accuracy as well as more superb predictive capability than other intelligent models presented previously.reviously.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.4
• /
• pp.819-824
• /
• 2020

In this paper, we propose a new multiplexer using quantum dot cellular automata (QCA), a next-generation digital circuit design technology. A multiplexer among digital circuits is a circuit that selects one of the input signals and transfers the selected input to one line. Since it is used in many circuits such as D-flip-flops, resistors, and RAM cells, research has been conducted in various ways to date. However, the previously proposed planar structure multiplexer does not consider connectivity, and therefore, when designing a large circuit, it uses an area inefficiently. There was also a multiplexer proposed as a multi-layer structure, but it does not improve the area due to not considering the interaction between cells. Therefore, in this paper, we propose a new multiplexer that improves 38% area reduction, 17% cost reduction, and connectivity using a cell-to-cell interaction and multi-layer structure.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.9
• /
• pp.94-105
• /
• 1993

In this paper propose a Koaren character recognition system using a neural network is proposed. This system is a multilayer neural network based on the masking field model which consists of a input layer, four feature extraction layers which extracts type, direction, stroke, and connection features, and an output layer which gives us recognized character codes. First, 4x4 subpatterns of an NxN character pattern stored in the input buffer are applied into the feature extraction layers sequentially. Then, each of feature extraction layers extracts sequentially features such as type, direction, stroke, and connection, respectively. Type features for direction and connection are extracted by the type feature extraction layer, direction features for stroke by the direction feature extraction layer and stroke and connection features for stroke by the direction feature extraction layer and stroke and connection features for the recongnition of character by the stroke and the connection feature extractions layers, respectively. The stroke and connection features are saved in the sequential buffer layer sequentially and using these features the characters are recognized in the output layer. The recognition results of this system by tests with 8 single consonants and 6 single vowels are promising.

• Journal of KIISE:Computer Systems and Theory
• /
• v.32 no.11_12
• /
• pp.629-638
• /
• 2005

In the System on a Chip design, the on chip bus is one of the critical factors that decides the overall system performance. Especially, in the case or reusing the IPs such as processors, DSPs and multimedia IPs that requires higher bandwidth, the bandwidth problems of on chip bus are getting more serious. Recently ARM proposes the Multi-Layer AHB BusMatrix that is a highly efficient on chip bus to solve the bandwidth problems. The Multi-Layer AHB BusMatrix allows parallel access paths between multiple masters and slaves in a system. This is achieved by using a more complex interconnection matrix and gives the benefit of increased overall bus bandwidth, and a more flexible system architecture. However, there is one clock cycle delay for each master in existing Multi-Layer AHB BusMatrix whenever the master starts new transactions or changes the slave layers because of the Input Stage and arbitration logic realized with Moore type. In this paper, we improved the existing Multi-Layer AHB BusMatrix architecture to solve the one clock cycle delay problems and to reduce the area overhead of the Input Stage. With the elimination of the Input Stage and some restrictions on the arbitration scheme, we tan take away the one clock cycle delay and reduce the area overhead. Experimental results show that the end time of total bus transaction and the average latency time of improved Multi-Layer AHB BusMatrix are improved by $20\%\;and\;24\%$ respectively. in ease of executing a number of transactions by 4-beat incrementing burst type. Besides the total area and the clock period are reduced by $22\%\;and\;29\%$ respectively, compared with existing Multi-layer AHB BusMatrix.

• Journal of information and communication convergence engineering
• /
• v.18 no.2
• /
• pp.82-87
• /
• 2020

This paper discusses how to design a game server that is scalable, adaptable, and re-buildable with components. Furthermore, it explains how various implementation issues were resolved. To support adaptability, the server comprises three layers: network, user, and database. To ensure independence between the layers, each layer was designed to communicate with each other only via message queues. In this architecture, each layer can have an arbitrary number of threads; thus, scalability is guaranteed for each layer. The network layer uses input/output completion ports(IOCP), which shows the best performance on the Windows platform, it can handle up to 5,000 simultaneous connections on a typical entry-level computer, despite being built with a single-threaded user layer. To completely separate the database from the game server, the SQL code was not directly embedded in the database layer.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.11 no.3
• /
• pp.169-175
• /
• 2008

A fine carbon fibers dispersion model is implemented to calculate the scattering range and ground level concentration of carbon fibers emitted at certain altitudes of atmospheric boundary layer. This carbon fibers dispersion model was composed by coupling a commonly used atmospheric dispersion model and an atmospheric boundary layer model. The atmospheric boundary layer model, applying the Monin-Obukov Similarity Rule obtained from measurement input data at ground level, was used to create the atmospheric boundary layer structure. In the atmospheric dispersion model, the Lagrangian Particle Model and the Markov Process were applied to calculate the trajectory of scattered carbon fibers relative to gravity and aerodynamic force, as well as carbon fibers specification.