• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.44 no.6
• /
• pp.124-136
• /
• 2002

A freshwater lake water quality management system(FLAQUM) was developed to help regional manager for the water quality of a rural basin. The integrated user interface system FLAQUM written in Visual Basic, includes three subsystems such as a database management system, basin pollutant loads simulation model using SWMM model and freshwater lake water quality simulation model using WASP5 model. Pollutant load simulation model was applied to simulate the discharge and pollutant loading from the watershed, and freshwater lake water quality model was applied to analyze the changes in water quality with respect to watershed pollutant loads, and this model could be used in planning to control watershed pollutant source for water quality management. Database management system was constructed fur all input and output data processing, and it can be used to analyze statistical characteristics using constructed data. Results are displayed both graph and text for convenience of user. The results of FLAQUM application to Boryeong freshwater lake showed that the lake was in eutrophic condition. The major contribution of pollution comes from tributary No.1 and No.4, which have a large number of livestock farms. Therefore, water quality management must be focused on appropriate management of the livestock farming in the two breanchs.

• Korean System Dynamics Review
• /
• v.9 no.1
• /
• pp.57-71
• /
• 2008

This research paper describes a complex and vague settings in which organization makes a decision and explains a role of decision maker's learning process. The original paper, written by Cohen, March, Olsen in 1972, said that all members of organization depended on the technology taken through trials and errors, which is the 'learning' process literally. But they intended to exclude the learning process in their simulation model because their PORTRAN model couldn't replicate the learning concept. As a result, they couldn't explain how all agents of garbage can simulation model resolve the problem dynamically. To overcome this original paper's limitations, we try to rebuild a learning process simulation model using by system dynamics approach that can capture the linkage between organization leanings and agents-based decision-makings. Our learning simulation results reveal two points. First, decision maker's leanings process improves the efficiency of decision making in complex situation. Second, group learning shows a superior efficiency to an individual learning because group members share organizational memory and energy.

• The Korean Journal of Applied Statistics
• /
• v.22 no.4
• /
• pp.745-758
• /
• 2009

Cluster analysis is the automated search for groups of related observations in a data set. To group the observations into clusters many techniques has been proposed, and a variety measures aimed at validating the results of a cluster analysis have been suggested. In this paper, we compare complete linkage, Ward's method, K-means and model-based clustering and compute validity measures such as connectivity, Dunn Index and silhouette with simulated data from multivariate distributions. We also select a clustering algorithm and determine the number of clusters of Korean consumers based on Korean consumers' palatability scores for Hanwoo bull in BBQ cooking method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.4
• /
• pp.721-727
• /
• 2016

In this paper, in order to resolve the problem of reduction for D2D (device to device) advertisement dissemination efficiency of conventional dissemination algorithms, we here propose several clustering algorithms (modified single linkage algorithm (MSL), K-means algorithm, and expectation maximization algorithm with Gaussian mixture model (EM)) based advertisement dissemination algorithms to improve advertisement dissemination efficiency in D2D communication networks. Target areas are clustered in several target groups by the proposed clustering algorithms. Then, D2D advertisements are consecutively distributed by using a routing algorithm based on the geographical distribution of the target areas and a relay selection algorithm based on the distance between D2D sender and D2D receiver. Via intensive MATLAB simulations, we analyze the performance excellency of the proposed algorithms with respect to maximum number of relay transmissions and D2D user density ratio in a target area and a non-target area.

• Journal of Advanced Navigation Technology
• /
• v.17 no.3
• /
• pp.332-345
• /
• 2013

In this paper, recently, it is described to the piezoelectric transformer technology develops, because it was have to favorable characteristics such as electromagnetic-noise free, compact size, higher efficiency, and superior power density, flux linkage, noiseless, etc. its resonance frequency was used to output waveform of a sine wave. A rotor speed identification method of induction motor based on the theory of flux model reference adaptive system(FMRAS). The estimator execute the rotor speed identification so that the vector control of the induction motor may be achieved. The improved auxiliary variable of the model are introduced to perform accurate rotor speed estimation. The control system is composed of the PI controller for speed control and the current controller using space voltage vector PWM techniuqe and DC-DC converter. High speed calculation and processing for vector control is carried out by digital signal one chip microprocessor. Validity of the proposed control method is verified through simulation and experimental results.

• The Plant Pathology Journal
• /
• v.35 no.3
• /
• pp.189-199
• /
• 2019

In this research, the relationships among the 31 microsatellite markers with charcoal rot disease resistance related indices in 130 different soybean cultivars and lines were evaluated using association analysis based on the general linear model (GLM) and the mixed linear model (MLM) by the Structure and Tassel software. The results of microsatellite markers showed that the genetic structure of the studied population has three subpopulations (K=3) which the results of bar plat also confirmed it. In association analysis based on GLM and MLM models, 31 and 35 loci showed significant relationships with the evaluated traits, respectively, and confirmed considerable variation of the studied traits. The identified markers related to some of the studied traits were the same which can probably be due to pleiotropic effects or tight linkage among the genomic regions controlling these traits. Some of these relationships were including, the relationship between Sat_252 marker with amount of charcoal rot disease, Satt359, Satt190 and Sat_169 markers with number of microsclerota in stem, amount of charcoal rot disease and severity of charcoal rot disease, Sat_416 marker with number of microsclerota in stem and amount of charcoal rot disease and the Satt460 marker with number of microsclerota in stem and severity of charcoal rot disease. The results of this research and the linked microsatellite markers with the charcoal rot disease-related characteristics can be used to identify the suitable parents and to improve the soybean population in future breeding programs.

• Journal of Practical Engineering Education
• /
• v.14 no.1
• /
• pp.137-147
• /
• 2022

Universities should provide experiential learning in subject and non-course subjects so that students can graduate with job competency related to their major and the experiential learning includes capstone design implemented on campus and field training conducted by companies. In particular, the decrease in industry participation in short-term (4 weeks) and mid-term field training (8 weeks) due to the implementation of standard field training introduced from the second half of 2021 is making it more difficult for students to gain practical experience. To solve this problem, in this paper, we propose an industry-participatory capstone design & field practice linkage model that combines capstone design and professional practice to solve the technical difficulties of companies. Participating students find solutions to corporate difficulties in the capstone design process and produce prototypes for solutions during the field practice period, focusing on the case of the department of electronic engineering at Gyeongbuk Y University. We believe that it is one of the good models of industry-university cooperation education in which universities and industries win-win.

• Communications of Mathematical Education
• /
• v.36 no.2
• /
• pp.253-286
• /
• 2022

This study is a study in which four teachers from the same school who participated in a teacher learning community program at the school field developed interdisciplinary linkage and convergence data using Plato as a collaborative circle in ethics and mathematics subjects. In particular, this study aimed to develop practical and shareable lesson materials. The data development procedure was developed according to the following four procedures. 'Development of data development plan, data development, verification of development data, and development of final data that reflects the verification opinions' At this time, in the data development stage, a theme-based design model was applied and developed. In addition, the development data were verified by conducting CVR verification for field teachers to focus on the validity and class applicability, and the final data were presented after the development data being revised to reflect the verification results. This study not only introduced the developed data, but also described the procedure of the data development process and the trial and error and concerns of the developers in the process to provide information on the nature of basic research to other field researchers who attempt data development.

• The Korean Journal of Applied Statistics
• /
• v.35 no.4
• /
• pp.553-568
• /
• 2022

The Household Income and Expenditure Survey is a representative survey of Statistics Korea, which aims to measure and analyze national income and consumption levels and their changes by understanding the current state of household balances. Recently, the disconnection problem in these time series caused by the large-scale reorganization of the survey methods in 2017 and 2019 has become an issue. In this study, we model the characteristics of the time series in the Household Income and Expenditure Survey up to 2016, and use the modeling to compute forecasts for linking the expenditures in 2017 and 2018. In order to evenly reflect the characteristics across all expenditure item series and to reduce the impact of a specific forecast model, we synthesize a total of 8 models such as regression models, time series models, and machine learning techniques. In particular, the noteworthy aspect of this study is that it improves the forecast by using the optimal combination technique that can exactly reflect the hierarchical structure of the Household Income and Expenditure Survey without loss of information as in the top-down or bottom-up methods. As a result of applying the proposed method to forecast expenditure series from 2017 to 2019, it contributed to the recovery of time series linkage and improved the forecast. In addition, it was confirmed that the hierarchical time series forecasts by the optimal combination method make linkage results closer to the actual survey series.