• 한국멀티미디어학회논문지
• /
• 제23권12호
• /
• pp.1540-1551
• /
• 2020

Aiming at the problem that the existing human behavior recognition algorithm cannot fully utilize the multi-level spatio-temporal information of the network, a human behavior recognition algorithm based on a dense three-dimensional residual network is proposed. First, the proposed algorithm uses a dense block of three-dimensional residuals as the basic module of the network. The module extracts the hierarchical features of human behavior through densely connected convolutional layers; Secondly, the local feature aggregation adaptive method is used to learn the local dense features of human behavior; Then, the residual connection module is applied to promote the flow of feature information and reduced the difficulty of training; Finally, the multi-layer local feature extraction of the network is realized by cascading multiple three-dimensional residual dense blocks, and use the global feature aggregation adaptive method to learn the features of all network layers to realize human behavior recognition. A large number of experimental results on benchmark datasets KTH show that the recognition rate (top-l accuracy) of the proposed algorithm reaches 93.52%. Compared with the three-dimensional convolutional neural network (C3D) algorithm, it has improved by 3.93 percentage points. The proposed algorithm framework has good robustness and transfer learning ability, and can effectively handle a variety of video behavior recognition tasks.

• 한국지형학회지
• /
• 제28권2호
• /
• pp.59-70
• /
• 2021

This study aims to determine the sunlight exposure according to depositional environment to improve the accuracy of optically simulated luminescence (OSL) dating. Sufficient sunlight exposure during transportation of sediment is a basic assumption of the OSL dating, and if the process does not occur enough, the results may be overestimated compared to the actual depositional age. Therefore, the main purpose of this study is to establish a correction method by determining residual or unbleachable dose after sunlight exposure in the actual deposition process, not in the laboratory measurement. Four samples from two sites were collected according to the depositional environment from rivers and coasts, and various OSL signals, including the size of residual dose, degree of dispersion between grains, and OSL signal sensitivity, were measured. As a result, it was confirmed that sediments formed under temporarily high energy environments, such as floods and surges, had relatively high residual dose or large dispersion of residual dose between particles. In further studies, the OSL signal characteristics of river sediments by flow velocity will be identified and the relationship between energy and OSL signal characteristics will be identified in more detail. Moreover, a method of reconstructing the paleo-environment at the time of deposition for existing sediments will be devised. It is expected to provide important information for the frequency of disaster recurrence and prediction of future climate change.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2007년도 추계학술대회 논문집
• /
• pp.401-402
• /
• 2007

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2005년도 학술발표회(1)
• /
• pp.596-597
• /
• 2005

• 대한용접접합학회:학술대회논문집
• /
• 대한용접접합학회 2000년도 특별강연 및 추계학술발표대회 개요집
• /
• pp.87-89
• /
• 2000

• 한국원자력학회:학술대회논문집
• /
• 한국원자력학회 2005년도 추계학술발표회
• /
• pp.492-493
• /
• 2005

• 상하수도학회지
• /
• 제21권5호
• /
• pp.601-607
• /
• 2007

In order to maintain constant residual chlorine in sedimentation basin, It is necessary to develop real time prediction model of residual chlorine considering water treatment plant data such as water qualities, weather, and plant operation conditions. Based on the operation data acquired from K water treatment plant, prediction models of residual chlorine in sediment basin were accomplished. The input parameters applied in the models were water temperature, turbidity, pH, conductivity, flow rate, alkalinity and pre-chlorination dosage. The multiple regression models were established with linear and non-linear model with 5,448 data set. The corelation coefficient (R) for the linear and non-linear model were 0.39 and 0.374, respectively. It shows low correlation coefficient, that is, these multiple regression models can not represent the residual chlorine with the input parameters which varies independently with time changes related to weather condition. Artificial neural network models are applied with three different conditions. Input parameters are consisted of water quality data observed in water treatment process based on the structure of auto-regressive model type, considering a time lag. The artificial neural network models have better ability to predict residual chlorine at sediment basin than conventional linear and nonlinear multi-regression models. The determination coefficients of each model in verification process were shown as 0.742, 0.754, and 0.869, respectively. Consequently, comparing the results of each model, neural network can simulate the residual chlorine in sedimentation basin better than mathematical regression models in terms of prediction performance. This results are expected to contribute into automation control of water treatment processes.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 1996년도 자동차부품 제작기술의 진보
• /
• pp.35-46
• /
• 1996

The powder forging process offers beneficial material utilization as well as the minimization of finishing operations over that of conventionally forged rods. In the present work, the sintering behavior of Fe-2Cu-0.6C-0.35MnS, optimum preform design and forgeability of various forging conditions were investigated. This data were generated using a newly proposed sub-scaled con-rod specimen developed specifically to simulate the powder forging process. The results of present work, powder perform is so difficult to flow material into die cavity and mass flow has no effect on improving the strength. And, applied force to increase density of the specimen flowed material is greater than that of all repessing mode. On the contrary, the specimen flowed material became increased hardness of inside in contrast with all repressing mode, but the tensile strength were decreased with residual porosity in surface. Due to material flow characteristic of powder preform, the section of lower density in powder preform became also lower density in forged con-rod. So, preform design is very important in manufacturing powder forged connecting rod.

• International Journal of Vascular Biomedical Engineering
• /
• 제2권1호
• /
• pp.25-30
• /
• 2004

Catheters are used to measure translesional pressure gradients in the stenosed coronary arteries. Uses of catheters during coronary angioplasty cause flow obstructions. A narrowed flow cross section with catheter effectively introduced a tighter stenosis than the enlarged residual stenoses after balloon angiplasty. Catheters in blood vessels cause pressure gradient rise and blood flow drop during the measurements. In this study, three dimensional computer simulations are conducted to investigate the flow blockage effects due to the catheter obstructions during the coronary angioplasty. The computer simulation models are generated by the data, which are measured by coronary angiogram, and the blood is treated as non-Newtonian fluid. The velocity, pressure, and wall shear stress variations are observed for the estimate of damages of blood vessel. This study is also extended to investigate the effects of stenotic vessel size, and shape and catheter size and location.

• 한국해양공학회지
• /
• 제11권4호
• /
• pp.141-151
• /
• 1997

This paper deals with a numerical study of flow-guider applied to controlling current in a bay. Two dimensional numerical model for tidal currents based on the depth averaged equation is developed and standard k-.epsilon. model is adopted to determine the turbulence diffusion. Equations are described in a generalized coordinate system to be implemented by non-staggered grid system and discretized by using finite volume method. Unsteady flow is simulated by fully implicit scheme. Hybrid scheme and central differencing are used to compute the convective terms and source terms, respectively. The tidal current in a rectangular bay is simulated and it gives satisfactory results. The realistic and distinct models of a large structure placed in bay are also exemplified with or without flow-guiders. The simulation results show that the flow-guider gives the residual tidal current in the bay by the different flux with respect to the direction of tidal current.