• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.23-34
• /
• 2023

Wearable technology for military applications has received considerable attention as a means of personal status check and monitoring. Among many, an implementation to recognize specific motion states of a human is promising in that allows active management of troops by immediately collecting the operational status and movement status of individual soldiers. In this study, as an extension of military wearable application research, a new ankle wearable device is proposed that can glean the information of a soldier on the battlefield on which action he/she takes in which environment. Presuming a virtual situation, the soldier's upper limbs are easily exposed to uncertainties about circumstances. Therefore, a sensing module is attached to the ankle of the soldier that may always interact with the ground. The obtained data comprises 3-axis accelerations and 3-axis rotational velocities, which cannot be interpreted by hand-made algorithms. In this study, to discern the behavioral characteristics of a human using these dynamic data, a data-driven model is introduced; four features extracted from sliced data (minimum, maximum, mean, and standard deviation) are utilized as an input of the model to learn and classify eight primary military movements (Sitting, Standing, Walking, Running, Ascending, Descending, Low Crawl, and High Crawl). As a result, the proposed device could recognize a movement status of a solider with 95.16% accuracy in an arbitrary test situation. This research is meaningful since an effective way of motion recognition has been introduced that can be furtherly extended to various military applications by incorporating wearable technology and artificial intelligence.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.2B
• /
• pp.225-231
• /
• 2006

The nonpoint source control is based on TPLMS (Total Pollution Load Management System) program. Recently, the Ministry of Environment in Korea has programed TPLMS for 4 major large rivers to improve the water quality in rivers by controling the total pollutant loadings from the watershed area. Usually the urbanization is the main pollutant sources, particularly for nonpoint pollutants, because of high imperviousness and high pollutant mass emissions. The stormwater runoff from urban areas is containing various pollutants such as sediments, metals and toxic chemicals due to human and vehicle activities. Of the various landuses, the highways are highly polluted landuses because of high pollutant accumulation rate by vehicle activities during dry periods. Therefore, this research is achieved to provide pollutant EMCs (Event Mean Concentrations) and mass loadings washed-off from highways during rainfall periods. Five monitoring locations were equipped with an automatic rainfall gage and an flow meter. The results show that the EMC ranges for 95% confidence intervals in highway land use are 45.52-125.76 mg/L for TSS, 52.04-95.48 mg/L for COD, 1.77-4.48 mg/L for TN, 0.29-0.54 mg/L for TP. The ranges of washed- off mass loading are $712.7-2,418.4mg/m^2$ for TSS and $684.1-1,779.6mg/m^2$ for COD.

• Journal of Korea Water Resources Association
• /
• v.47 no.10
• /
• pp.973-983
• /
• 2014

This study focused on the selection of appropriate plant species of VFS (vegetative fiter strips) and the assessment of VFS effects for reducing NPS (non-point source) pollution from uplands. The experimental field was constructed with 1 control and 6 treated plots in the upland area of $1,500m^2$ with 5% slope which is located in Gunwi-gun, Gyeongbuk province. Six vegetation including Chufa, Common crabgrass, Barnyard grass, Turf grass, Tall fescue, Kenturky bluegrass, were applied to install VFS systems during the study period from June 2011 to Dec. 2012. The results of this study showed that 6.1~77.8% in runoff and 15.6~90.3% in TS, 49.9~96.6% in T-P, and 6.7~91.1% in T-N were reduced from the VFS treated plots. Generally high reduction effects were observed from TS, T-P, T-N, and SS, while BOD, TOC, and $NO_3^-$ showed low reductions. The best vegetation type was Turf grass showing higher reduction effects of NPS pollutions and having relatively easier maintenance efforts compared to other vegetations selected in this study. Based on these results, VFS technique found to be an effective management practice for reducing agricultural NPS pollutions in Korean upland conditions. Further study needs to be performed through various field experiments with long term monitoring in order to develop a design manual of VFS system for practical applications.

• Journal of Life Science
• /
• v.18 no.3
• /
• pp.395-402
• /
• 2008

Level of microbial contamination was examined in four fish farms of Jeju east coast for sanitary indication of bacterial contamination such as heterotrophic bacteria, Escherichia coli O157:H7, Salmonella spp., Vibrio parahaemolyticus, Staphylococcus aureus, Bacillus cereus and total coliforms. The samples were collected and investigated from June to October in 2007. Bacterial species of S. aureus, B. cereus and Salmonella spp. were frequently detected from the seawater of above fish farms. Salmonella spp., S. aureus, B. cereus were detected in the range of $0{\sim}4.3{\times}l0^3,\;0{\sim}2.7{\times}l0^4,\;0{\sim}7.6{\times}l0^3$ CFU/ml, respectively, from the fish feed used in all four selected farms. Additionally, Salmonella spp., S. aureus, B. cereus were detected in oliver flounder (Paralichthys olivaceus) of these farms, however total coliforms and E. coli O157:H7 were not detected during our experimental period. For the production of microbiologically safe and healthy oliver flounder, proper quality control of feed, sanitation programs, and continuous monitoring of microorganism are essential practices, which required to include in the farm management system.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.12
• /
• pp.1959-1970
• /
• 2013

Attempts were made in this paper to compare the practice of protective actions for information of patients' medical treatment between hospital administrators who do not make direct contact with patients and occupational therapists who usually do. The comparison between jobs in charge showed that occupational therapists did not practice much protective actions for information of patients' medical treatment ($3.52{\pm}.809$) compared to hospital administrators ($3.92{\pm}.724$), even though the former had received regular education about protection, management and supervision of patients' medical information more often ($3.17{\pm}1.129$) than the latter ($3.16{\pm}1.037$). In spite of the fact that occupational therapists were exposed frequently to the danger of revealing medical information in the process of their job performance through talks and communications with patients, they displayed relatively little concern for and awareness of keeping information of medical treatment from being leaked by them. It is thus suggested to promote awareness of medical staff to protect medical information by means of flexible educational system for each occupational group, periodical monitoring, continuing public relation, training and quality control for protection of medical information, as well as routine self-examination of such practice.

• Journal of Digital Convergence
• /
• v.15 no.6
• /
• pp.407-414
• /
• 2017

With an increase in urban crimes in various forms, this study is intended to analyze the effectiveness of the service design that presented a new model resolving crime risks through differentiated thinking paradigm and problem approaches. The empirical case addressed in this study is 'the project to create resident-driven safe community in Duryu-dong, Dalseo-gu, Deagu though service design'. This project is evaluated as having prepared a prevention-oriented local safety system through a preemptive and resident-centered process. The project was promoted as a 'natural monitoring capacity building program' for residents to prevent local crimes, a 'social role expansion program' for local safety, and 'crime prevention environment design', which provides comprehensive solutions for residents' safety. Here, designers act as exerts in designing a task-based platform that can be driven by residents rather than a visual environment improver, and reorganizing the local ecosystem by expanding the opportunities for residents to interact. This case identifies the role of service design as binding the solidarity of local residents beyond the improvement of the crime environment and giving them the potential capacity to maintain a safe living space in relation to a safety issues of community.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.9
• /
• pp.134-143
• /
• 2020

This study investigated the status of infectious disease inpatients at long-term care hospitals in Korea. A descriptive study was conducted on patients with 14 infectious diseases at 798 long-term care hospitals during 2016-2017. The number of infected patients, total admission days, and total medical expenses were higher in 2017 than in 2016. The most common infectious diseases were enterocolitis due to Clostridium difficile, influenza, and scabies. The number of hospitals with patients who had enterocolitis due to C. difficile and resistance to carbapenem was higher in 2017 than in 2016. Hospitals with 150-299 beds had higher numbers of infectious disease patients than those with under 150 or over 300 beds. Therefore, intensive efforts are needed to control the most common diseases at long-term care hospitals, such as enterocolitis due to C. difficile, influenza, and scabies. It is recommended to apply relevant guidelines related to infection control management as well as implement educational programs. It will also be necessary to develop applicable infection monitoring standards and support the facilities and health workforce of long-term care hospitals under 300 beds through an effective infection surveillance system.

• Journal of the Society of Cosmetic Scientists of Korea
• /
• v.35 no.1
• /
• pp.27-32
• /
• 2009

Human hair is an excretory system for trace metals and thus metal content in human hair can reflect the body status. The investigation of trace elements in human hair has been correlated with the diagnosis of various diseases as well as the monitoring of deficiency statues in nutrition. Many chronic diseases may be related to mineral status, some may be related to toxic mineral. Hair samples were collected from 120 inhabitants of the city of Seoul, Korea. In this study the concentrations of 10 elements (Hg, Pb, Cd, Al, As, U, Bi, Sb, Ba, Be) in hair were determined by inductively coupled plasma mass spectroscopy (ICP-MS). The conclusions showed that people in Seoul, Korea were affected by some kinds of toxic minerals. The Hg concentrations of male are higher than those of female and reference range. The mean concentration of Sb was higher in the female than male and reference range. In age distribution, the mean concentration of Hg was in 40's are higher than 20's and 30's and reference range. The concentrations of Al were the highest in the 20's. After analyzing, we concluded that a compounded treatment should be conducted, which considers the variety of factors related to detoxification.

• Journal of Food Hygiene and Safety
• /
• v.36 no.3
• /
• pp.239-247
• /
• 2021

In order to confirm the impact of the Positive List System (PLS) being applied to all agricultural products from January 1, 2019, we analyzed 28,693 points of inspection-related data on agricultural products distributed in Gyeonggi-do from 2018 to 2020. The ratio of cases exceeding the standard for the total inspection performance was 1.0% in 2018, 1.2% in 2019, and 1.2% in 2020. Out of the 114 cases exceeding the standard in 2019, 55 were applied on a Maximum Residue Limit (MRL) of 0.01 mg/kg, and out of the 115 cases exceeding the standard in 2020, 66 were applied on a MRL of 0.01 mg/kg. To improve this, it seems necessary to manage unintentional pollution, conventional use for unregistered crops, and illegal pesticides. Fluquinconazole detection resulted from unintentional contamination, and diazinon, chlorothalonil, and methabenzthiazuron detection resulted from conventional use in unregistered crops. Chinomethionat is a pesticide component that was discarded in the past and its current use has been attributed to the smuggling of pesticides. This study and future monitoring data can be used as reference data for system supplementation and on-site management reinforcement.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.57-73
• /
• 2021

Maintenance and prevention of failure through anomaly detection of ICT infrastructure is becoming important. System monitoring data is multidimensional time series data. When we deal with multidimensional time series data, we have difficulty in considering both characteristics of multidimensional data and characteristics of time series data. When dealing with multidimensional data, correlation between variables should be considered. Existing methods such as probability and linear base, distance base, etc. are degraded due to limitations called the curse of dimensions. In addition, time series data is preprocessed by applying sliding window technique and time series decomposition for self-correlation analysis. These techniques are the cause of increasing the dimension of data, so it is necessary to supplement them. The anomaly detection field is an old research field, and statistical methods and regression analysis were used in the early days. Currently, there are active studies to apply machine learning and artificial neural network technology to this field. Statistically based methods are difficult to apply when data is non-homogeneous, and do not detect local outliers well. The regression analysis method compares the predictive value and the actual value after learning the regression formula based on the parametric statistics and it detects abnormality. Anomaly detection using regression analysis has the disadvantage that the performance is lowered when the model is not solid and the noise or outliers of the data are included. There is a restriction that learning data with noise or outliers should be used. The autoencoder using artificial neural networks is learned to output as similar as possible to input data. It has many advantages compared to existing probability and linear model, cluster analysis, and map learning. It can be applied to data that does not satisfy probability distribution or linear assumption. In addition, it is possible to learn non-mapping without label data for teaching. However, there is a limitation of local outlier identification of multidimensional data in anomaly detection, and there is a problem that the dimension of data is greatly increased due to the characteristics of time series data. In this study, we propose a CMAE (Conditional Multimodal Autoencoder) that enhances the performance of anomaly detection by considering local outliers and time series characteristics. First, we applied Multimodal Autoencoder (MAE) to improve the limitations of local outlier identification of multidimensional data. Multimodals are commonly used to learn different types of inputs, such as voice and image. The different modal shares the bottleneck effect of Autoencoder and it learns correlation. In addition, CAE (Conditional Autoencoder) was used to learn the characteristics of time series data effectively without increasing the dimension of data. In general, conditional input mainly uses category variables, but in this study, time was used as a condition to learn periodicity. The CMAE model proposed in this paper was verified by comparing with the Unimodal Autoencoder (UAE) and Multi-modal Autoencoder (MAE). The restoration performance of Autoencoder for 41 variables was confirmed in the proposed model and the comparison model. The restoration performance is different by variables, and the restoration is normally well operated because the loss value is small for Memory, Disk, and Network modals in all three Autoencoder models. The process modal did not show a significant difference in all three models, and the CPU modal showed excellent performance in CMAE. ROC curve was prepared for the evaluation of anomaly detection performance in the proposed model and the comparison model, and AUC, accuracy, precision, recall, and F1-score were compared. In all indicators, the performance was shown in the order of CMAE, MAE, and AE. Especially, the reproduction rate was 0.9828 for CMAE, which can be confirmed to detect almost most of the abnormalities. The accuracy of the model was also improved and 87.12%, and the F1-score was 0.8883, which is considered to be suitable for anomaly detection. In practical aspect, the proposed model has an additional advantage in addition to performance improvement. The use of techniques such as time series decomposition and sliding windows has the disadvantage of managing unnecessary procedures; and their dimensional increase can cause a decrease in the computational speed in inference.The proposed model has characteristics that are easy to apply to practical tasks such as inference speed and model management.