• Ecology and Resilient Infrastructure
• /
• v.8 no.4
• /
• pp.223-232
• /
• 2021

In general, stormwater flows to the road surface, especially in urban areas, and it is discharged through the drainage grate inlets on roads. The appropriate evaluation of the road drainage capacity is essential not only in the design of roads and inlets but also in the design of sewer systems. However, the method of road surface flow analysis that reflects the topographical and hydraulic conditions might not be fully developed. Therefore, the enhanced method of road surface flow analysis should be presented by investigating the existing analysis method such as the flow analysis module (uniform; varied) and the flow travel time (critical; fixed). In this study, the algorithm based on varied and uniform flow analysis was developed to analyze the flow pattern of road surface. The numerical analysis applied the uniform and varied flow analysis module and travel time as parameters were conducted to estimate the characteristics of rainfall-runoff in various road conditions using the developed algorithm. The width of the road (two-lane (6 m)) and the slope of the road (longitudinal slope of road 1 - 10%, transverse slope of road 2%, and transverse slope of gutter 2 - 10%) was considered. In addition, the flow of the road surface is collected from the gutter along the road slope and drained through the gutter in the downstream part, and the width of the gutter was selected to be 0.5 m. The simulation results were revealed that the runoff characteristics were affected by the road slope conditions, and it was found that the varied flow analysis module adequately reflected the gutter flow which is changed along the downstream caused by collecting of road surface flow at the gutter. The varied flow analysis module simulated 11.80% longer flow travel time on average (max. 23.66%) and 4.73% larger total road surface discharge on average (max. 9.50%) than the uniform flow analysis module. In order to accurately estimate the amount of runoff from the road, it was appropriate to perform flow analysis by applying the critical duration and the varied flow analysis module. The developed algorithm was expected to be able to be used in the design of road drainage because it was accurately simulated the runoff characteristics on the road surface.

• Food Engineering Progress
• /
• v.14 no.4
• /
• pp.307-315
• /
• 2010

The safety and security of food supply should be one of the primary responsibilities of any government. Estimation of nation's food commodity intakes is important to control the potential risks in food systems since food hazards are often associated with quality and safety of food commodities. The food intake databases provided by Korea National Health and Nutrition Examination Survey (KNHANES) are good resources to estimate the demographic data of intakes of various food commodities. A limitation of the KNHANES databases, however, is that the food intakes surveyed are not based on commodities but ingredients and their mixtures. In this study, reasonable calculation strategies were applied to convert the food intakes of the ingredients mixtures from the KNHANES into food commodity intakes. For example, Perilla leaf consumed with meat, raw fish, and etc. in Korean diets was used to estimate its Korean intakes and develop algorithms for demographic analysis. Koreans have consumed raw, blanched, steamed, and canned perilla leaf products. The average daily intakes of the perilla leaf were analyzed demographically, for examples, the intakes by gender, age, and etc. The average daily intakes of total perilla leaf were 2.03${\pm}$0.27 g in 1998, 2.11${\pm}$0.26 g in 2001, 2.29${\pm}$0.27 g in 2005, 2.75${\pm}$0.35 g in 2007, and 2.27${\pm}$0.20 g in 2008. Generally, people equal to or over 20 years of age have shown higher perilla leaf intakes than people below 20. This study would be contributed to the estimation of intakes of possible chemical contaminants such as residual pesticides and subsequent analysis for their potential risk.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.43-62
• /
• 2019

At one time, the anomaly detection sector dominated the method of determining whether there was an abnormality based on the statistics derived from specific data. This methodology was possible because the dimension of the data was simple in the past, so the classical statistical method could work effectively. However, as the characteristics of data have changed complexly in the era of big data, it has become more difficult to accurately analyze and predict the data that occurs throughout the industry in the conventional way. Therefore, SVM and Decision Tree based supervised learning algorithms were used. However, there is peculiarity that supervised learning based model can only accurately predict the test data, when the number of classes is equal to the number of normal classes and most of the data generated in the industry has unbalanced data class. Therefore, the predicted results are not always valid when supervised learning model is applied. In order to overcome these drawbacks, many studies now use the unsupervised learning-based model that is not influenced by class distribution, such as autoencoder or generative adversarial networks. In this paper, we propose a method to detect anomalies using generative adversarial networks. AnoGAN, introduced in the study of Thomas et al (2017), is a classification model that performs abnormal detection of medical images. It was composed of a Convolution Neural Net and was used in the field of detection. On the other hand, sequencing data abnormality detection using generative adversarial network is a lack of research papers compared to image data. Of course, in Li et al (2018), a study by Li et al (LSTM), a type of recurrent neural network, has proposed a model to classify the abnormities of numerical sequence data, but it has not been used for categorical sequence data, as well as feature matching method applied by salans et al.(2016). So it suggests that there are a number of studies to be tried on in the ideal classification of sequence data through a generative adversarial Network. In order to learn the sequence data, the structure of the generative adversarial networks is composed of LSTM, and the 2 stacked-LSTM of the generator is composed of 32-dim hidden unit layers and 64-dim hidden unit layers. The LSTM of the discriminator consists of 64-dim hidden unit layer were used. In the process of deriving abnormal scores from existing paper of Anomaly Detection for Sequence data, entropy values of probability of actual data are used in the process of deriving abnormal scores. but in this paper, as mentioned earlier, abnormal scores have been derived by using feature matching techniques. In addition, the process of optimizing latent variables was designed with LSTM to improve model performance. The modified form of generative adversarial model was more accurate in all experiments than the autoencoder in terms of precision and was approximately 7% higher in accuracy. In terms of Robustness, Generative adversarial networks also performed better than autoencoder. Because generative adversarial networks can learn data distribution from real categorical sequence data, Unaffected by a single normal data. But autoencoder is not. Result of Robustness test showed that he accuracy of the autocoder was 92%, the accuracy of the hostile neural network was 96%, and in terms of sensitivity, the autocoder was 40% and the hostile neural network was 51%. In this paper, experiments have also been conducted to show how much performance changes due to differences in the optimization structure of potential variables. As a result, the level of 1% was improved in terms of sensitivity. These results suggest that it presented a new perspective on optimizing latent variable that were relatively insignificant.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.10
• /
• pp.261-268
• /
• 2021

Cloud computing is a computing paradigm in which users can utilize computing resources in a pay-as-you-go manner. In a cloud system, resources can be dynamically scaled up and down to the user's on-demand so that the total cost of ownership can be reduced. The Modeling and Simulation (M&S) technology is a renowned simulation-based method to obtain engineering analysis and results through CAE software without actual experimental action. In general, M&S technology is utilized in Finite Element Analysis (FEA), Computational Fluid Dynamics (CFD), Multibody dynamics (MBD), and optimization fields. The work procedure through M&S is divided into pre-processing, analysis, and post-processing steps. The pre/post-processing are GPU-intensive job that consists of 3D modeling jobs via CAE software, whereas analysis is CPU or GPU intensive. Because a general-purpose desktop needs plenty of time to analyze complicated 3D models, CAE software requires a high-end CPU and GPU-based workstation that can work fluently. In other words, for executing M&S, it is absolutely required to utilize high-performance computing resources. To mitigate the cost issue from equipping such tremendous computing resources, we propose HEMOS-Cloud service, an integrated cloud and cluster computing environment. The HEMOS-Cloud service provides CAE software and computing resources to users who want to experience M&S in business sectors or academics. In this paper, the economic ripple effect of HEMOS-Cloud service was analyzed by using industry-related analysis. The estimated results of using the experts-guided coefficients are the production inducement effect of KRW 7.4 billion, the value-added effect of KRW 4.1 billion, and the employment-inducing effect of 50 persons per KRW 1 billion.

• Journal of the Society of Disaster Information
• /
• v.17 no.1
• /
• pp.97-111
• /
• 2021

Purpose: It is expected that various infrastructures diagnosis equipment will be needed as infrastructures management is strengthened to implement the Framework Act on Sustainable Infrastructure Management. It is necessary for a certification system to supply certified products of a reasonable level in accordance with market requirements for various convergence equipment. This paper deals with the introduction of certification system of inspection and diagnosis equipment for infrastructure using advanced technologies. Method: The basic elements, systems and procedures of certification system were reviewed through analyzing and comparing the existing similar certification system in Korea. In addition, a survey was conducted on a catalog method and the minimum performance criterion (sampling survey and complete enumeration survey) to equipment developers (manufacturers), clients and equipment users. Result: This survey showed that clients preferred complete enumeration method on the basis of minimum performance, and equipment users also preferred complete enumeration survey and sample survey, for minimum performance, at a similar rate. On the other hand, equipment developers preferred the catalog method. Conclusion: Clients and users who are the users of the diagnostic equipment preferred the minimum performance criterion because their trust in quality is important. On the other hand, developers(manufacturers) preferred the catalog method which adopts self certification because it is regulated in developing various products. There is no specific plan for the minimum performance standards required for the introduction of the method which users demand, at present. In addition, it is not desirable to force to introduce a certification system because it requires a considerable period of study to prepare the specific standards. Therefore, it is appropriate to operate the system for a certain period of time centering around the catalog method for the stable and continuous development of the infrastructure diagnosis and test equipment market in Korea. Also, it is effective to expand and develop the certification system to the extent that it minimizes the impact on the market when specific plans for the standards are prepared in the future.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.75-94
• /
• 2021

The low birth rate and shortened military service period are causing concerns about selecting excellent military officers. The Republic of Korea entered a low birth rate society in 1984 and an aged society in 2018 respectively, and is expected to be in a super-aged society in 2025. In addition, the troop-oriented military is changed as a state-of-the-art weapons-oriented military, and the reduction of the military service period was implemented in 2018 to ease the burden of military service for young people and play a role in the society early. Some observe that the application rate for military officers is falling due to a decrease of manpower resources and a preference for shortened mandatory military service over military officers. This requires further consideration of the policy of securing excellent military officers. Most of the related studies have used social scientists' methodologies, but this study applies the methodology of text mining suitable for large-scale documents analysis. This study extracts words of discriminative characteristics from the Republic of Korea Air Force Non-Commissioned Officer Applicant cover letters and analyzes the polarity of pass and fail. It consists of three steps in total. First, the application is divided into general and technical fields, and the words characterized in the cover letter are ordered according to the difference in the frequency ratio of each field. The greater the difference in the proportion of each application field, the field character is defined as 'more discriminative'. Based on this, we extract the top 50 words representing discriminative characteristics in general fields and the top 50 words representing discriminative characteristics in technology fields. Second, the number of appropriate topics in the overall cover letter is calculated through the LDA. It uses perplexity score and coherence score. Based on the appropriate number of topics, we then use LDA to generate topic and probability, and estimate which topic words of discriminative characteristic belong to. Subsequently, the keyword indicators of questions used to set the labeling candidate index, and the most appropriate index indicator is set as the label for the topic when considering the topic-specific word distribution. Third, using L-LDA, which sets the cover letter and label as pass and fail, we generate topics and probabilities for each field of pass and fail labels. Furthermore, we extract only words of discriminative characteristics that give labeled topics among generated topics and probabilities by pass and fail labels. Next, we extract the difference between the probability on the pass label and the probability on the fail label by word of the labeled discriminative characteristic. A positive figure can be seen as having the polarity of pass, and a negative figure can be seen as having the polarity of fail. This study is the first research to reflect the characteristics of cover letters of Republic of Korea Air Force non-commissioned officer applicants, not in the private sector. Moreover, these methodologies can apply text mining techniques for multiple documents, rather survey or interview methods, to reduce analysis time and increase reliability for the entire population. For this reason, the methodology proposed in the study is also applicable to other forms of multiple documents in the field of military personnel. This study shows that L-LDA is more suitable than LDA to extract discriminative characteristics of Republic of Korea Air Force Noncommissioned cover letters. Furthermore, this study proposes a methodology that uses a combination of LDA and L-LDA. Therefore, through the analysis of the results of the acquisition of non-commissioned Republic of Korea Air Force officers, we would like to provide information available for acquisition and promotional policies and propose a methodology available for research in the field of military manpower acquisition.

• Applied Chemistry for Engineering
• /
• v.22 no.2
• /
• pp.178-184
• /
• 2011

In this study, the antibacterial, antioxidative and inhibitory effects of Allium cepa peel extracts on tyrosinase and elastase were investigated. MIC values of the ethyl acetate fraction of Allium cepa peel on especially, S. aureus among the skin resident flora (Staphylococcus aureus, S. aureus; Propionibacterium acnes, P. acnes; Pityrosporum ovale, P. ovale; Escherichia coli, E. coli) were 0.06%. The aglycone fraction showed more excellent free radical (1,1-diphenyl-2-picrylhydrazyl radical, DPPH) scavenging activity ($FSC_{50}=5.05{\mu}g/mL$). Reactive oxygen species (ROS) scavenging activities ($OSC_{50}$) of the ethyl acetate fraction and aglycone fraction in the luminol-dependent $Fe^{3+}-EDTA/H_2O_2$ system were 0.05 and $0.03{\mu}g/mL$, respectively. The cellular protective effect of the aglycone fraction on the rose-bengal sensitized photohemolysis of human erythrocytes exhibited more prominent (${\tau}_{50}$, 480 min at $25{\mu}g/mL$). The inhibitory effects ($IC_{50}$) of the ethyl acetate fraction and aglycone fraction on tyrosinase were 9.16 and $8.68{\mu}g/mL$, the inhibitory effect ($IC_{50}$) of the aglycone fraction on elastase was $14.12{\mu}g/mL$ The transepidermal water loss of the cream containing 0.1% ethyl acetate fraction was decreased from $8.3g/m^2h$ in control to $6.8g/m^2h$ in the subjects applied with cream containing the ethyl acetate fraction. These results indicate that extract/fractions of Allium cepa peel can function as antioxidant in biological systems, particularly skin exposed to UV radiation by scavenging $^1O_2$ and other ROS, and protect cellular membranes against ROS, and possibly as antiaging agents. Allium cepa peel extract could be used as a new cosmeceutical for whitening and anti-wrinkle products.

• Journal of Korea Water Resources Association
• /
• v.54 no.8
• /
• pp.577-587
• /
• 2021

Drought is generally considered to be a natural disaster caused by accumulated water shortages over a long period of time, taking months or years and slowly occurring. However, climate change has led to rapid changes in weather and environmental factors that directly affect agriculture, and extreme weather conditions have led to an increase in the frequency of rapidly developing droughts within weeks to months. This phenomenon is defined as 'Flash Drought', which is caused by an increase in surface temperature over a relatively short period of time and abnormally low and rapidly decreasing soil moisture. The detection and analysis of flash drought is essential because it has a significant impact on agriculture and natural ecosystems, and its impacts are associated with agricultural drought impacts. In South Korea, there is no clear definition of flash drought, so the purpose of this study is to identify and analyze its characteristics. In this study, flash drought detection condition was presented based on the satellite-derived drought index Evaporative Stress Index (ESI) from 2014 to 2018. ESI is used as an early warning indicator for rapidly-occurring flash drought a short period of time due to its similar relationship with reduced soil moisture content, lack of precipitation, increased evaporative demand due to low humidity, high temperature, and strong winds. The flash droughts were analyzed using hydrometeorological characteristics by comparing Standardized Precipitation Index (SPI), soil moisture, maximum temperature, relative humidity, wind speed, and precipitation. The correlation was analyzed based on the 8 weeks prior to the occurrence of the flash drought, and in most cases, a high correlation of 0.8(-0.8) or higher(lower) was expressed for ESI and SPI, soil moisture, and maximum temperature.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.3
• /
• pp.247-262
• /
• 2022

In domestic tunnels, it is mandatory to install CCTVs in tunnels longer than 200 m which are also recommended by installation of a CCTV-based automatic accident detection system. In general, the CCTVs in the tunnel are installed at a low height as well as near by the moving vehicles due to the spatial limitation of tunnel structure, so a severe perspective effect takes place in the distance of installed CCTV and moving vehicles. Because of this effect, conventional CCTV-based accident detection systems in tunnel are known in general to be very hard to achieve the performance in detection of unexpected accidents such as stop or reversely moving vehicles, person on the road and fires, especially far from 100 m. Therefore, in this study, the region of interest is set up and a new concept of inverse perspective transformation technique is introduced. Since moving vehicles in the transformed image is enlarged proportionally to the distance from CCTV, it is possible to achieve consistency in object detection and identification of actual speed of moving vehicles in distance. To show this aspect, two datasets in the same conditions are composed with the original and the transformed images of CCTV in tunnel, respectively. A comparison of variation of appearance speed and size of moving vehicles in distance are made. Then, the performances of the object detection in distance are compared with respect to the both trained deep-learning models. As a result, the model case with the transformed images are able to achieve consistent performance in object and accident detections in distance even by 200 m.

• 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.