• Journal of Korean Society of Transportation
• /
• v.27 no.6
• /
• pp.129-137
• /
• 2009

Operation of intelligent transport systems technologies in transportation networks and more detailed analysis give rise to necessity of dynamic traffic analysis model. Existing static models describe network state in average. on the contrary, dynamic traffic analysis model can describe the time-dependent network state. In this study, a dynamic traffic model for the expressway system using FTMS data is developed. Time-dependent origin-destination trip tables for nationwide expressway network are constructed using TCS data. Computation complexity is critical issue in modeling nationwide network for dynamic simulation. A subarea analysis model is developed which converts the nationwide O-D trip tables into subarea O-D trip tables. The applicability of the proposed model is tested under various scenario. This study can be viewed as a starting point of developing deployable dynamic traffic analysis model. The proposed model needs to be expanded to include arterial as well without critical computation burden.

• Journal of Information Technology Services
• /
• v.22 no.5
• /
• pp.87-98
• /
• 2023

Traditionally, tooth restoration has been carried out by replicating teeth using plaster-based materials. However, recent technological advances have simplified the production process through the introduction of computer-aided design(CAD) systems. Nevertheless, dental restoration varies among individuals, and the skill level of dental technicians significantly influences the accuracy of the manufacturing process. To address this challenge, this paper proposes an approach to designing personalized tooth restorations using Generative Adversarial Network(GAN), a widely adopted technique in computer vision. The primary objective of this model is to create customized dental prosthesis for each patient by utilizing 3D data of the specific teeth to be treated and their corresponding opposite tooth. To achieve this, the 3D dental data is converted into a depth map format and used as input data for the GAN model. The proposed model leverages the network architecture of Pixel2Style2Pixel, which has demonstrated superior performance compared to existing models for image conversion and dental prosthesis generation. Furthermore, this approach holds promising potential for future advancements in dental and implant production.

• International Journal of Concrete Structures and Materials
• /
• v.6 no.3
• /
• pp.177-186
• /
• 2012

The temperature distributions of concrete structures strongly depend on the value of thermal conductivity of concrete. However, the thermal conductivity of concrete varies according to the composition of the constituents and the temperature and moisture conditions of concrete, which cause difficulty in accurately predicting the thermal conductivity value in concrete. For this reason, in this study, back-propagation neural network models on the basis of experimental values carried out by previous researchers have been utilized to effectively account for the influence of these variables. The neural networks were trained by 124 data sets with eleven parameters: nine concrete composition parameters (the ratio of water-cement, the percentage of fine and coarse aggregate, and the unit weight of water, cement, fine aggregate, coarse aggregate, fly ash and silica fume) and two concrete state parameters (the temperature and water content of concrete). Finally, the trained neural network models were evaluated by applying to other 28 measured values not included in the training of the neural networks. The result indicated that the proposed method using a back-propagation neural algorithm was effective at predicting the thermal conductivity of concrete.

• Journal of Microbiology and Biotechnology
• /
• v.15 no.3
• /
• pp.551-559
• /
• 2005

The recent rapid increase in genomic data related to many microorganisms and the development of computational tools to accurately analyze large amounts of data have enabled us to design several kinds of simulation approaches for the complex behaviors of cells. Among these approaches, dFBA (dynamic flux balance analysis), which utilizes FBA, differential equations, and regulatory events, has correctly predicted cellular behaviors under given environmental conditions. However, until now, dFBA has centered on substrate concentration, cell growth, and gene on/off, but a detailed hierarchical structure of a regulatory network has not been taken into account. The use of Boolean rules for regulatory events in dFBA has limited the representation of interactions between specific regulatory proteins and genes and the whole transcriptional regulation mechanism with environmental change. In this paper, we adopted the operon as the basic structure, constructed a hierarchical structure for a regulatory network with defined fundamental symbols, and introduced a weight between symbols in order to solve the above problems. Finally, the total control mechanism of regulatory elements (operons, genes, effectors, etc.) with time was simulated through the linkage of dFBA with regulatory network modeling. The lac operon, trp operon, and tna operon in the central metabolic network of E. coli were chosen as the basic models for control patterns. The suggested modeling method in this study can be adopted as a basic framework to describe other transcriptional regulations, and provide biologists and engineers with useful information on transcriptional regulation mechanisms under extracellular environmental change.

• Spatial Information Research
• /
• v.19 no.1
• /
• pp.93-105
• /
• 2011

In recent years, large and complex three-dimensional building has been constructed by the development of building technology and advanced IT skills, and people have lived there and spent a considerable time so far. Accordingly. in this sophisticatcd three-dimensional space, emergencies services or convenient information services have been in demand. In order to provide these services efficiently, understanding of topological relationships among the complex space should be supported naturally. Not on1y each method of understanding the topological relationships but also its efficiency can be different depending on different topological data models. B-rep based data model is the most widely used for storaging and representing of topological relationships. And from early 2000s, many researches on a network based topological data model have been conducted. The purpose of this study is to verify the efficiency of performance on spatial queries. As a result, Network-based topological data model is more efficient than B-rep based data model for determining the spatial relationship.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.270-273
• /
• 2015

In shipbuilding and marine industry, engineering and design software solutions have upgraded from the original 2D schematic data based CAD system to a modern 3D drawing-based system. Due to the fact that the massive amount of data usage in real time and data volumes of various engineering models including graphic data have increased, several problems such as lack of server resources and improper handling of 3D drawings have been raised. Besides, increasing the number of session connections per server can cause deterioration of server performance. Recently, increasing the yard's sophisticated design capabilities highlighted the need to develop engineering and design system which would not only overcome the network performance issues, but would provide efficient collaborative design environment. This paper presents an overview of the framework for collaborative engineering design system based on the virtual application (Citrix XenApp 6.5)and acceleration hardware technology of 3D graphics (NVIDIA GRID K2 solution).

• Journal of Korean Society of Transportation
• /
• v.18 no.5
• /
• pp.83-97
• /
• 2000

The traffic management schemes through traffic signal control and information provision could be effective when the link-level data and trip-level data were used simultaneously in analysis Procedures. But, because the trip-level data. such as origin, destination and departure time, can not be obtained through the existing surveillance systems directly. It is needed to estimate it using the link-level data which can be obtained easily. Therefore the objective of this study is to develop the model to estimate O-D demand using only the link flows in highway network as a real time. The methodological approaches in this study are kalman filer, least-square method and normalized least-square method. The kalman filter is developed in the basis of the bayesian update. The normalized least-square method is developed in the basis of the least-square method and the natural constraint equation. These three models were experimented using two kinds of simulated data. The one has two abrupt changing Patterns in traffic flow rates The other is a 24 hours data that has three Peak times in a day Among these models, kalman filer has Produced more accurate and adaptive results than others. Therefore it is seemed that this model could be used in traffic demand management. control, travel time forecasting and dynamic assignment, and so forth.

• International Journal of Computer Science & Network Security
• /
• v.21 no.3
• /
• pp.41-47
• /
• 2021

Detection of protein-protein interactions (PPIs) remains essential for the development of therapies against diseases. Experimental studies to detect PPI are longer and more expensive. Today, with the availability of PPI data, several computer models for predicting PPIs have been proposed. One of the big challenges in this task is feature extraction. The relevance of the information extracted by some extraction techniques remains limited. In this work, we first propose an extraction method based on correlation relationships between the physicochemical properties of amino acids. The proposed method uses a correlation matrix obtained from the hydrophobicity and hydrophilicity properties that it then integrates in the calculation of the bigram. Then, we use the SVM algorithm to detect the presence of an interaction between 2 given proteins. Experimental results show that the proposed method obtains better performances compared to the approaches in the literature. It obtains performances of 94.75% in accuracy, 95.12% in precision and 96% in sensitivity on human HPRD protein data.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.10 no.3
• /
• pp.419-429
• /
• 1999

Identifying the boundary of the effective receiving power of waves is one of the most important factors for cell optimization. In this paper, we introduce a propagation loss prediction model which yields highly accurate prediction in very complex areas as Seoul where a mixture of many large buildings, small buildings, broad streets, narrow alleys, rivers and forests co-exist in an irregular arrangement. This prediction model is based on neural networks trained on field measurement data collected in the past. Using these data along with 3-D digital elevation maps and vector data for building structures, we extract the parameter values which mainly affect the amount of propagation loss. These parameter values are then used as the inputs to the neural network. Trained neural network becomes the approximated function of the propagation loss model which generalizes very well and can predict accurately in the regions not included in training the neural network. The experimental results show a superior performance over the other models in the cells operating in the city of Seoul.

• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.175-182
• /
• 2022

In our daily life, we come across different types of information, for example in the format of multimedia and text. We all need different types of information for our common routines as watching/reading the news, listening to the radio, and watching different types of videos. However, sometimes we could run into problems when a certain type of information is required. For example, someone is listening to the radio and wants to listen to jazz, and unfortunately, all the radio channels play pop music mixed with advertisements. The listener gets stuck with pop music and gives up searching for jazz. So, the above example can be solved with an automatic audio classification system. Deep Learning (DL) models could make human life easy by using audio classifications, but it is expensive and difficult to deploy such models at edge devices like nano BLE sense raspberry pi, because these models require huge computational power like graphics processing unit (G.P.U), to solve the problem, we proposed DL model. In our proposed work, we had gone for a low complexity model for Audio Event Detection (AED), we extracted Mel-spectrograms of dimension 128×431×1 from audio signals and applied normalization. A total of 3 data augmentation methods were applied as follows: frequency masking, time masking, and mixup. In addition, we designed Convolutional Neural Network (CNN) with spatial dropout, batch normalization, and separable 2D inspired by VGGnet [1]. In addition, we reduced the model size by using model quantization of float16 to the trained model. Experiments were conducted on the updated dataset provided by the Detection and Classification of Acoustic Events and Scenes (DCASE) 2020 challenge. We confirm that our model achieved a val_loss of 0.33 and an accuracy of 90.34% within the 132.50KB model size.