• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.35 no.1
• /
• pp.9-14
• /
• 2022

In this study, a smart jack-up system was developed to prevent safety accidents by performing risk analysis when a structure is lifted for maintenance. A quantitative risk analysis program that can analyze the risk using the pairwise comparison matrix analysis method was developed. The risk was analyzed in real-time for the lifting structure by connecting the program with an automatic jack-up system. Displacements were measured by the IR sensor among the components of the automatic jack-up system, and the displacements were provided to the quantitative risk analysis program. To confirm the performance of the smart automatic jack-up system, experiments were conducted on bridge and risk analysis was performed when a superstructure was lifted. A linear variable differential transformer (LVDT) was also installed on the bridge to verify the performance of the smart automatic jack-up system. The maximum displacements were measured using the devices, and the declinations were compared. The performance of the simultaneous operation of the jack-up device was verified by the analysis of variance (ANOVA).

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.10
• /
• pp.29-41
• /
• 2022

Recently, with the development of deep learning technology, a variety of huge models with excellent performance have been devised by pre-training massive amounts of text data. However, in order for such a model to be applied to real-life services, the inference speed must be fast and the amount of computation must be low, so the technology for model compression is attracting attention. Knowledge distillation, a representative model compression, is attracting attention as it can be used in a variety of ways as a method of transferring the knowledge already learned by the teacher model to a relatively small-sized student model. However, knowledge distillation has a limitation in that it is difficult to solve problems with low similarity to previously learned data because only knowledge necessary for solving a given problem is learned in a teacher model and knowledge distillation to a student model is performed from the same point of view. Therefore, we propose a heterogeneous knowledge distillation method in which the teacher model learns a higher-level concept rather than the knowledge required for the task that the student model needs to solve, and the teacher model distills this knowledge to the student model. In addition, through classification experiments on about 18,000 documents, we confirmed that the heterogeneous knowledge distillation method showed superior performance in all aspects of learning efficiency and accuracy compared to the traditional knowledge distillation.

• International Journal of Computer Science & Network Security
• /
• v.22 no.8
• /
• pp.97-104
• /
• 2022

European integration processes have acted as a catalyst for the emergence of a new type of educational environment, which is characterized by competent flexibility of specialists. Therefore, the article focuses on professional training of teachers in the context of European integration processes using information technology and the search for innovative methods of training specialists. One of the educational priorities in Europe is to create a new model of a teacher who has an academic education, knows innovative methods, is able to perform functions and tasks efficiently and professionally, adequately, quickly and correctly respond to changes and innovations. The tasks facing education in the European dimension are formulated. The main trends in the education of teachers in modern Europe are described: the need to deepen and expand subject training programs in pedagogical institutions of Higher Education, which will allow autonomy of activity, awareness of responsibility for independent creative decisions, create favorable conditions for the development of professionalism through the use of Information Technology and the search for innovative methods of training specialists. At the present stage, various models of teacher training are being developed based on the University and practical concept using information technology and searching for innovative methods of training specialists. On this basis, two different theories of perception of teacher education were formed: as preparation of teachers for work throughout their professional career; as preparation for the first years of professional work, which is periodically repeated in the process of continuous professional training and improvement. Among the advantages that the use of Information Technology and the search for innovative methods of training specialists to implement the learning process, it is worth mentioning the following: simultaneous use of several channels of perception of the student or student in the learning process, thanks to which the integration of information processed by different sensory organs is achieved; the ability to simulate complex real experiments; visualization of abstract information by dynamic representation of processes, etc.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.5
• /
• pp.274-286
• /
• 2022

Multi-object tracking has been studied for a long time under computer vision and plays a critical role in applications such as autonomous driving and driving assistance. Multi-object tracking techniques generally consist of a detector that detects objects and a tracker that tracks the detected objects. Various publicly available datasets allow us to train a detector model without much effort. However, there are relatively few publicly available datasets for training a tracker model, and configuring own tracker datasets takes a long time compared to configuring detector datasets. Hence, the detector is often developed separately with a tracker module. However, the separated tracker should be adjusted whenever the former detector model is changed. This study proposes a system that can train a model that performs detection and tracking simultaneously using only the detector training datasets. In particular, a Siam network with augmentation is used to compose the detector and tracker. Experiments are conducted on public datasets to verify that the proposed algorithm can formulate a real-time multi-object tracker comparable to the state-of-the-art tracker models.

• Journal of the Society of Disaster Information
• /
• v.19 no.1
• /
• pp.117-127
• /
• 2023

Purpose: The number of Cold Storages at home and abroad is on the rise, fires in large Cold Storages have recently occurred. As fires continue to occur and property damage is on the rise every year, the importance of preventing fires in large Cold Storage is growing. Method: Real Cold Storages were investigated on-site and fire cases were analyzed to derive and analyze fire risk, and the ORS, which is emerging as an adaptive fire prevention technology of Cold Storage, was investigated through FDS. Result: oxygen concentration 21, 15.7% and 17.7, 16.7% were analyzed through FDS, and flashover was reached within 3~4 minutes from 21, 17.7, 16.7%, but if oxygen concentration was lowered to 15.7%, it didn't ignite for 13 minutes. Conclusion: This study understood the concept and general part of the ORS, modeled the freezer through FDS, and analyzed the oxygen concentration to analyze the fire protection adaptability of the ORS. In the future, it is expected that large-scale empirical experiments and related regulations will be prepared to provide solutions for fire prevention in Cold Storages in blind spots of fire.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.4
• /
• pp.194-210
• /
• 2023

LiDAR plays a key role in autonomous vehicles, where it is used to detect the environment in place of the driver's eyes, and its role is expanding. In recent years, there has been a growing need to test the performance of LiDARs installed in autonomous vehicles. Many LiDAR performance tests have been conducted in simulated and indoor(lab) environments, but the number of tests in outdoor(field) and real-world road environments has been minimal. In this study, we compared LiDAR performance under the same conditions lab and field to determine the relationship between lab and field tests and to establish the characteristics and roles of each test environment. The experimental results showed that LiDAR detection performance varies depending on the lighting environment (direct sunlight, led) and the detected object. In particular, the effect of decreasing intensity due to increasing distance and rainfall is greater outdoors, suggesting that both lab and field experiments are necessary when testing LiDAR detection performance on objects. The results of this study are expected to be useful for organizations conducting research on the use of LiDAR sensors and facilities for LiDAR sensors.

• Journal of IKEEE
• /
• v.27 no.3
• /
• pp.345-349
• /
• 2023

In this paper, we propose a study on the development of deep learning structure for defective pixel detection of next-generation smart LED display board using imaging device. In this research, a technique utilizing imaging devices and deep learning is introduced to automatically detect defects in outdoor LED billboards. Through this approach, the effective management of LED billboards and the resolution of various errors and issues are aimed. The research process consists of three stages. Firstly, the planarized image data of the billboard is processed through calibration to completely remove the background and undergo necessary preprocessing to generate a training dataset. Secondly, the generated dataset is employed to train an object recognition network. This network is composed of a Backbone and a Head. The Backbone employs CSP-Darknet to extract feature maps, while the Head utilizes extracted feature maps as the basis for object detection. Throughout this process, the network is adjusted to align the Confidence score and Intersection over Union (IoU) error, sustaining continuous learning. In the third stage, the created model is employed to automatically detect defective pixels on actual outdoor LED billboards. The proposed method, applied in this paper, yielded results from accredited measurement experiments that achieved 100% detection of defective pixels on real LED billboards. This confirms the improved efficiency in managing and maintaining LED billboards. Such research findings are anticipated to bring about a revolutionary advancement in the management of LED billboards.

• Journal of the Korea Society for Simulation
• /
• v.18 no.4
• /
• pp.137-148
• /
• 2009

The purpose of this study is to implement variable selection algorithm which helps construct a reliable linear regression model. If we use all candidate variables to construct a linear regression model, the significance of the model will be decreased and it will cause 'Curse of Dimensionality'. And if the number of data is less than the number of variables (dimension), we cannot construct the regression model. Due to these problems, we consider the variable selection problem as a combinatorial optimization problem, and apply GA (Genetic Algorithm) to the problem. Typical measures of estimating statistical significance are $R^2$, F-value of regression model, t-value of regression coefficients, and standard error of estimates. We design GA to solve multi-objective functions, because statistical significance of model is not to be estimated by a single measure. We perform experiments using simulation data, designed to consider various kinds of situations. As a result, it shows better performance than LARS (Least Angle Regression) which is an algorithm to solve variable selection problems. We modify algorithm to solve portfolio selection problem which construct portfolio by selecting stocks. We conclude that the algorithm is able to solve real problems.

• Journal of the Korea Society for Simulation
• /
• v.18 no.3
• /
• pp.35-45
• /
• 2009

Emergency medical center(EMC) is the place for patients who need medical treatment immediately due to a disease, childbirth, or all sorts of accidents. Currently, most of EMCs use temporary beds because regular EMC beds cannot afford to serve all incoming patients. However, since it decreases the quality of service(QoS) of EMC patients and their guardians and efficiency of the EMC, some improvements are highly required to diminish the usage of temporary beds. The system duration time is one of the typical QoSs. This thesis proposes the information which is critical to make a better decision for cut down the number of temporary beds without sacrificing QoS of patients. The key point is to control the duration time of medical treatments for the consultation and hospitalization process, since it is the major reason of overcrowding in EMC and the usage of temporary beds. In this paper, we proposed an Arena simulation model reflecting real world substantially. Arena is one of the most widely accepted simulation softwares in the world. Using the developed model, we can obtain the optimal EMC operation parameters through simulation experiments. Optquest, included in the Arena, is used to make the developed simulation model collaborate with an optimization model. The results showed one can determine the set of optimal operation parameters decreasing the required number of temporary beds without deteriorating EMC patient's QoS.

• Journal of The Korean Association For Science Education
• /
• v.43 no.4
• /
• pp.403-414
• /
• 2023

In this study, we examined the adaptive practices of science teachers in their classrooms and their perspectives on the distinguishing features of these practices within science subjects. Our analysis comprised 339 cases from 128 middle and high school science teachers nationwide, and 199 cases on the characteristics of adaptive practices in science disciplines. The primary findings were as follows: First, the most significant characteristic of adaptive practice in science disciplines pertained to experimental procedures. Within the 'suggestion of additional materials/activities' category, the most frequently cited adaptive practice, teachers incorporated demonstrations to either facilitate student comprehension or enhance motivation. Additionally, 'experimental equipment manipulation or presentation of inquiry skills' emerged as the second most common adaptive practice related to experiments. Notably, over 50% of teacher responses regarding the characteristics of adaptive practices in science pertained to experiment guidance. Second, many adaptive practices involving difficulties experienced by students in learning situations were presented, particularly in areas such as numeracy and literacy. Many cases were related to the basic ability of mathematics used as a tool in science learning and understanding scientific terms in Chinese characters. Third, beyond 'experiment guidance', the characteristic adaptive practices of science subjects were related to 'connections between scientific theory and the real world', 'misconception guidance in science', 'cultivation of scientific thinking', and 'convergence approaches'. Fourth, the cases of adaptive practice presented by the science teachers differed by school level and major; therefore, it is necessary to consider school level or major in future research related to adaptive practice. Fifth, most of the adaptive action items with a small number of cases were adaptive actions executed from a macroscopic perspective, so it is necessary to pay attention to related professionalism. Finally, based on the results of this study, the implications for science education were discussed.