• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1794-1799
• /
• 2022

Recently, the increasing number of overloaded vehicles on the road poses a risk to traffic safety, such as falling objects, road damage, and chain collisions due to the abnormal weight distribution, and can cause great damage once an accident occurs. therefore we propose to build an object detection-based AI model to identify overloaded vehicles that cause such social problems. In addition, we present a simple yet effective method to construct an object detection model for the large-scale vehicle images. In particular, we utilize the large-scale of vehicle image sets provided by open AI-Hub, which include the overloaded vehicles. We inspected the specific features of sizes of vehicles and types of image sources, and pre-processed these images to train a deep learning-based object detection model. Also, we propose an integrated system for tracking the detected vehicles. Finally, we demonstrated that the detection performance of the overloaded vehicle was improved by about 23% compared to the one using raw data.

• Journal of Agricultural Extension & Community Development
• /
• v.19 no.2
• /
• pp.241-271
• /
• 2012

The objectives of this study were to explore the duties and tasks of educational program operation, to develop the performance model including the duties and tasks, and to construct the action manual of the tasks and duties in related with implementing effectively the educational program. The findings of this study were as follows. First, The identifying duties and tasks was 1,942 related with implementing educational program operation based on theoretical job model through activity analysis and experience sampling techniques. Second, the finding duties and tasks was reconstructed through classifying with 9 duties and 88 tasks, and then it was developed as educational program operation model of Korean Rural HRD Center. Finally Third, the implementing manual was constructed including the contents and task-elements.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.1
• /
• pp.45-54
• /
• 2020

One of the typical characteristics of smart media is that it is interactive, which shows a different form and property from the existing mass media, and also changes the way users use it. This change requires a different system from the existing method in the advertising process strategic model for effective interactive advertising in smart media. We attempted to derive an effective smart media interactive advertising process strategic model by understanding the interactive advertising processin smart media that is expected to continue to grow asthe main market of the advertising market and identifying the constituent factors. To this end, We analyzed the preminiary research results of interactive advertising and organized expert panels for the Delphi method and reflected their opinions and evaluations. The components and factors of interactive advertising were found and the effective interactive advertising process strategy model in smart media was derived from this study.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.2
• /
• pp.680-699
• /
• 2015

The use of web service has been increased rapidly, with an increase in the number of available services, finding the exact service is the challenging task. Service discovery is the most significant job to complete the service discoverers needs. In order to achieve the efficient service discovery, we focus on designing a cluster based service discovery model for service registering and service provisioning among all mobile nodes in a mobile ad hoc network (MANETs). A dynamic backbone of nodes (i.e. cluster heads) that forms a service repository to which MANET nodes can publish their services and/or send their service queries. The designed model is based on storing services with their service description on cluster head nodes that are found in accordance with the proposed cluster head election model. In addition to identifying and analyzing the system parameters for finding the effectiveness of our model, this paper studies the stability analysis of the network, overhead of the cluster, and bandwidth utilization and network traffic is evaluated using analytic derivations and experimental evaluation has been done.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.2
• /
• pp.407-411
• /
• 2009

This study presents the analysis of the identifications and determinations of the material parameters in the developed model in the former paper and their effects on the stress paths. It was shown that the influences of the parameters, specially involved in the strain rate and the viscous nucleus, were in generally acceptable range. From this point, the model was modified by identifying the plastic yield surface and the viscous yield surface in the same mathematical form. The modified model was successful in simulating stress path.

• Journal of Information Technology Services
• /
• v.10 no.2
• /
• pp.235-245
• /
• 2011

Early criticality prediction models that determine whether a design entity is fault-prone or not are becoming more and more important as software development projects are getting larger. Effective predictions can reduce the system development cost and improve software quality by identifying trouble-spots at early phases and proper allocation of effort and resources. Many prediction models have been proposed using statistical and machine learning methods. This paper builds a prediction model using Support Vector Machine(SVM) which is one of the most popular modern classification methods and compares its prediction performance with a well-known prediction model, BackPropagation neural network Model(BPM). SVM is known to generalize well even in high dimensional spaces under small training data conditions. In prediction performance evaluation experiments, dimensionality reduction techniques for data set are not used because the dimension of input data is too small. Experimental results show that the prediction performance of SVM model is slightly better than that of BPM and polynomial kernel function achieves better performance than other SVM kernel functions.

• The Research Journal of the Costume Culture
• /
• v.16 no.4
• /
• pp.595-608
• /
• 2008

Although Korean apparel companies have transformed dramatically from contractors to sourcing companies thanks to the rapid growth of local market, relatively little work has been done identifying the determinants and the patterns of global sourcing activities of Korean companies. The purpose of this study was to outline a conceptual model that may be used to organize and guide global sourcing activities of Korean apparel manufacturers and retailers. The conceptual model identified four important factors, cost factor, strategic non-cost factor, firm's internal factor, and global factor, which affect global sourcing strategies and help predict how companies conduct various sourcing activities. The model also identified two sourcing patterns, outsourcing and intra-firm sourcing. In developing the model, literature review on how manufacturers and retailers in diverse areas including global apparel sourcing was conducted. Managerial implications and directions far future study were offered as well.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.70.1-70
• /
• 2002

In the fuzzy applications and theories, it is very important to consider how to design the optimal fuzzy model from short training data, in order to construct the reasonable fuzzy model for identifying the practical process. There are several concerns to be confirmed for efficient fuzzy model design. One of concern is the optimization problem of the fuzzy model. In various applications, the genetic algorithm is widely applied to obtain optimal fuzzy model and other cases that adopt evolutionary mechanism of the nature. If we use natural selection and multiplication operation of the genetic algorithm, early convergence to local minimum can be occurred. In other word, we can find only optimum...

• Journal of Institute of Control, Robotics and Systems
• /
• v.4 no.6
• /
• pp.722-728
• /
• 1998

In this paper real-time estimation methods for identifying the tire-road friction coefficient are presented. Taking advantage of the Magic Formula Tire Model, the similarity technique and the specific model for the vehicle dynamics, a reduced order observer/filtered-regressor-based method is proposed. The Proposed method is evaluated on simulations of a full-vehicle model with an eight state nonlinear vehicle/transmission model and nonlinear suspension model. It has been shown through simulations that it is possible to estimate the tire-road friction from measurements of engine rpm, transmission output speed and wheel speeds using the proposed identification method. The proposed method can be used as a useful option as a part of vehicle collision warning/avoidance systems and will be useful in the implementation of a warning algorithm since the tire-road friction can be estimated only using RPM sensors.

• Proceedings of the KIEE Conference
• /
• 2007.04a
• /
• pp.83-85
• /
• 2007

A new approach on identifying a first-order plus time-delay (FOPTD) model using finite--duration pulse inputs has been presented recently [1]. The identification methods are very simple because it is enough to observe only two extremes and the time when they occur in the transient response to pulse input. However, when there is mismatch between actual system and FOPTD model. how sensitive the methods are has not been studied. In this paper, we investigate robustness issue of those identification algorithms in the presence of the model structure mismatch and uncertainties. Through an example we will demonstrate it.