• 스마트미디어저널
• /
• 제13권1호
• /
• pp.24-35
• /
• 2024

The combination of Artificial Intelligence and the Internet of Things (AIoT) has gained significant popularity. Deep neural networks (DNNs) have demonstrated remarkable success in various applications. However, deploying complex AI models on embedded boards can pose challenges due to computational limitations and model complexity. This paper presents an AIoT-based system for smart parking lots using edge devices. Our approach involves developing a detection model and a decision tree for occupancy status classification. Specifically, we utilize YOLOv5 for car license plate (LP) detection by verifying the position of the license plate within the parking space.

• Journal of Communications and Networks
• /
• 제5권4호
• /
• pp.309-318
• /
• 2003

This paper presents an in-depth study of a UWB indoor radio channel between 1 and 9 GHz, which was used for the subsequent development of a new statistical UWB multipath channel model, focusing on short range indoor scenarios. The channel sounding process was carried out covering different indoor environments, such as laboratories, halls or corridors. A combination of new and traditional parameters has been used to accurately model the channel impulse response in order to perform a precise temporal estimation of the received pulse shape. This model is designed specifically for UWB digital systems, where the received pulse is correlated with an estimated replica of itself. The precision of the model has been verified through the comparison with measured data from equivalent scenarios and cases, and highly satisfactory results were obtained.

• 산업경영시스템학회지
• /
• 제20권44호
• /
• pp.243-255
• /
• 1997

Forecasting the future values of an observed time series is an important problem in many areas, including economics, traffic engineering, production planning, sales forecasting, and stock control. The purpose of this paper is aimed to discover the more efficient forecasting model through the parameter estimation and residual analysis among the quantitative method such as Winters' exponential smoothing model, Box-Jenkins' model, and Kalman filtering model. The mean of the time series is assumed to be a linear combination of known functions. For a parameter estimation and residual analysis, Winters', Box-Jenkins' model use Statgrap and Timeslab software, and Kalman filtering utilizes Fortran language. Therefore, this paper can be used in real fields to obtain the most effective forecasting model.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2009년도 학술발표회 초록집
• /
• pp.107-111
• /
• 2009

The parameters in the Horton's model which has well known as typical infiltration model were determined by the use of the optimization technique. It was assumed the initial infiltration capacity in this model was related to the antecedent precipitation per 10 days with linear combination. And both the parameters of the ultimate infiltration capacity and the decay factor were determined uniquely on a basin. Thus the optimal model's parameters representative to a basin were obtained and the Horton's infiltration equations by rainstorm events were determined. The data of ten rainstorm events for this study were observed at the Jeonjeokbigyo station located at the Selmacheon experimental basin that was $8.5\;km^2$ wide in the Imjin river.

• Communications for Statistical Applications and Methods
• /
• 제13권3호
• /
• pp.701-718
• /
• 2006

In cancer microarray experiments, the experimenter or patient which is nested in each experimenter often shows quite heterogeneous error variability, which should be estimated for identifying a source of variation. Our study describes a Bayesian method which utilizes clinical information for identifying a set of DE genes for the class of subtypes as well as assesses and examines the experimenter effect and patient effect which is nested in each experimenter as a source of variation. We propose a Bayesian multilevel mixed effect model based on analysis of covariance (ANACOVA). The Bayesian multilevel mixed effect model is a combination of the multilevel mixed effect model and the Bayesian hierarchical model, which provides a flexible way of defining a suitable correlation structure among genes.

• 멤브레인
• /
• 제3권3호
• /
• pp.108-116
• /
• 1993

수면전개 혼합적층막의 기체투과계수는 PS의 혼합비율이 증가함에 따라, 분리계수는 PVC의 환합비율이 증가함에 따라 증가하였다. 기체투과기구는 PS의 혼합비율이 감소함에 따라 Poiseuile-Knudsen 모델에서 solution-diffusion모델로 전이하였다. 한편 혼합박막의 구조는 공기면측에 소수성의 PS가, 수면측에는 친수성인 PVC가 배향된 직렬혼합구조였으며, 기체투과거동은 series model을 따랐다.

• Geomechanics and Engineering
• /
• 제23권5호
• /
• pp.493-502
• /
• 2020

The prediction of soil response under repetitive mechanical loadings remains challenging in geotechnical engineering applications. Modeling the cyclic soil response requires a robust model validation with an experimental dataset. This study proposes a unique method adopting linearity of model constant with the number of cycles. The model allows the prediction of the terminal density of sediments when subjected to repetitive changes in pore-fluid pressure based on the two-surface plasticity. Model simulations are analyzed in combination with an experimental dataset of sandy sediments when subjected to repetitive changes in pore fluid pressure under constant deviatoric stress conditions. The results show that the modified plastic moduli in the two-surface plasticity model appear to be critical for determining the terminal density. The methodology introduced in this study is expected to contribute to the prediction of the terminal density and the evolution of shear strain at given repetitive loading conditions.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 1997년도 춘계학술대회논문집
• /
• pp.50-54
• /
• 1997

An expert drawbead model is developed to model a cranky drawbead in the finite element analysis of stamping processes. The expert model calculates the drawbead restraining forces (DBRF's) and bead-exit thinning, which are boundary conditions. DBRF's are calculated by considering bending force, unbending force, and friction force in order. Bead-exit thinning are due to the bending and tension during the deformation. The DBFR's and thinning computed form the mathematical model for the basic beads are compared with measurements and correction factors compensating for the differences are found using the multiple linear regression method. The composition beads are assumed to be a combination of basic beads so that the DBRF's and bead-exit thinning are computed to the sum of those of basic beads.

• 한국멀티미디어학회논문지
• /
• 제17권11호
• /
• pp.1296-1306
• /
• 2014

Recently there are many attempts that IT convergence has been studied together with very different sector like art and music. If it is possible to make a formal model with combination of engineering with strong creative sector like music, there will be some advantages to analyze its contents easily. In this study, the model has been provided to utilize music analysis and compose algorithm through the formal model research of Sonata. To this end, this study has been provided a formal model of Sonata with the Petri net model being widely used and verify the effectiveness of the proposed model on the case of Piano Sonata K. 332.

• KIEAE Journal
• /
• 제2권4호
• /
• pp.65-72
• /
• 2002

In this study, the evaluation of environmental performance of the building energy system of domestic commercial sector was carried out. Based on the theory of linear programming model, we established an evaluation model satisfying object functions and constraint conditions. Employing the model, the evaluation of building energy system was performed under the consideration of cost and environmental constraint conditions. As an evaluation tool, MARKAL (MARKet Allocation) known as a market distribution model was employed. We analyzed scenarios of Case I (Base Scenarios) through Case IX established by the combination of the components of building energy system such as glazing, building skin, core, and heat source system. According to the results of the evaluation, highest contribution on the useful energy demand was obtained from the building energy system combined with solar heat source system, when the total amounts of $CO_2$ exhaust as an environmental constraint condition is assumed to be the level of 1995.