• 한국인공지능학회지
• /
• 제6권1호
• /
• pp.1-10
• /
• 2018

Compressed Air is an important energy source used in most factories nowadays. The automation trend using air compressor has been gradually increasing with the interest of the 4th industry in recent years. With the air compressor system, it is possible to construct the device at low cost and easily achieve automation and energy saving. In addition, With trend of FA, miniaturation and light weight manufacturing trend expand their use in the electronics, medical, and food sectors. Research method is to design the technology for the remote control of the following information as USN base. Development of flexible sensing module from real time observation module for fusion of IT technology in compressed air systems, design and manufacture of flexible sensing module, and realiability assessment. Design of real-time integrated management system for observation data of compressed air system - Ability to process observation data measured in real time into pre-processing and analysis data. This study expects unconventionally decreasing effect of energy cost that takes up 60~70% of air compressor layout and operation and maintenance management cost through USN(Ubiquitous Sensor Network) technology by using optimum operational condition from real time observation module. In addition, by preventing maintenance cost from malfunction of air compressor beforehand, maintenance cost is anticipated to cut back.

• 농촌계획
• /
• 제20권2호
• /
• pp.1-10
• /
• 2014

Smartphones change the picture of data and information sharing and make it possible to share various real-time flooding data and information. The vulnerability indicators of farmland inundation is needed to calculate the risk of farmland flood based on changeable hydro-meteorological data over time with morphologic characteristics of flood-damaged areas. To find related variables show the vulnerability of farmland inundation using the binary-logit model and correlation analysis and to provide vulnerability indicators were estimated by fuzzy set method. The outputs of vulnerability indicators were compared with the results of Monte Carlo simulation (MCS) for verification. From the result vulnerability indicators are applicable to mobile_based information system of farmland inundation.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.375-381
• /
• 2022

Safety accidents are of concern during construction projects, even given the recent innovations in digital technologies. These projects remain focused on overcoming specific and limited applications on construction sites. For this reason, the development of an inclusive safety management system has become crucial. This study aims to build a Big Data platform to inform decisions on how to proactively eliminate worker hazards on construction sites. The platform consists of about 100,000 real records and a real-time monitored database featuring various safety indices, such as workers' altitudes, heart rates, and fatigability during construction, which are determined through various wearable devices. The data types are customized and integrated by a research team in accordance with the characteristics of a specific project using hypertext transfer protocol (HTTP). The results can be helpful as efficient tools to ensure successful safety management in complex construction situations. This study is expected to provide three significant contributions to the field, including real-time fatigability analysis and tracking of workers on-site; providing early GPS-based warnings to workers who might be accessing dangerous spaces or places; and monitoring the workers' health indices, based on details from 100,000 cases.

• International Journal of Advanced Culture Technology
• /
• 제11권4호
• /
• pp.464-469
• /
• 2023

As modern society develops, the number of diseases caused by bad smells is increasing. As it can harm people's health, it is important to predict in advance the extent to which bad smells may occur, inform the public about this, and take preventive measures. In this paper, we propose a hybrid neural network structure of CNN and LSTM that can be used to detect or predict the occurrence of odors, which are most required in manufacturing or real life, using odor complex sensors. In addition, the proposed learning model uses a complex odor sensor to receive four types of data, including hydrogen sulfide, ammonia, benzene, and toluene, in real time, and applies this data to the inference model to detect and predict the odor state. The proposed model evaluated the prediction accuracy of the training model through performance indicators based on accuracy, and the evaluation results showed an average performance of more than 94%.

• 환경영향평가
• /
• 제20권4호
• /
• pp.575-583
• /
• 2011

In this study, the plausible grid size was estimated to increase for efficiency of reservoir management using 3 dimensional water quality model. To validate utilization of a real time water quality management tool, ELCOM-CAEDYM model was applied to Soyang reservoir in korea. 100m grid size can represent the real topography and take out exact analysis results. $400{\times}400m$ grid can be easily used to analysis because of data capacity. Consequently, the grid size of 200m or 300m was recommended to establish 3D model considering the required simulation time and the irrelevance between horizontal grid size and vertical distribution for temperature and turbidity analysis.

• 기술혁신연구
• /
• 제7권1호
• /
• pp.176-186
• /
• 1999

This paper starts out by reviewing the literature that in different ways utilizes patent data as an output of Research ＆ Development (R&D) investment. The main focus, however, is an analysis of time-lag between industrial R&D input and its output. To achieve this research's purpose, the basic data associated with the industrial R&D input (expenditure, researchers) and output (applied patent and utilities) for the past 15 years, from 1980 to 1994, in the areas of electrical-electronic, mechanical and chemical industries have been collected. And the raw input data were altered into real flow data (but stock data) using Laspeyres approach and analyzed using multiple regression analysis, especially stepwise regression analysis. The result of this study can be summarized as follows: a) The time-lag; between industrial R&D input and its output is within 1 to 3 years. b) The time-lag: of patents was longer than that of utility models. c) The time-lag: in electrical-electronic, chemical industry was longer than that of the mechanical industry.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 1999년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.194-197
• /
• 1999

In AVL, GIS analyze the information from the vehicles to provide commercial or other value far user. As spatial analysis functions in GIS make a new valuable information using the vehicle's position and geographic object's location, they perform an important roles to improve the management efficiency of vehicles. Most GIS however are used static data for the spatial analysis, so the research area on AVL used dynamic vehicle location has generated unsuitable result. In this study, we use GPS real time tracking data to perform spatial analysis between moving vehicle and static geographic object. The method proposed in this paper considers the driving direction of vehicle and creates the result which is located in forward of vehicle. In this paper, two spatial analysis functions, near and connectivity, are developed.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2008년도 춘계 학술발표회 초청강연 및 논문집
• /
• pp.704-715
• /
• 2008

The Aim of this development is the management of a forecasting analysis program based on a real-time remote sensing data. Using this program it is possible to predict a failure of levee facilities in advance. therefor, it is necessary for making plans of a safety countermove. In this development we have researched the analysis method which could operate effectively the levee facilities using real-time monitoring data from a remote sensing system and the safety managerial program using the algorism from the analysis method developed.

• 한국도로학회논문집
• /
• 제10권1호
• /
• pp.155-164
• /
• 2008

최근 들어 널리 확대되는 ITS시설과 장비의 효율적인 활용을 위해서는 실시간 통행시간예측과 같은 핵심기술의 개발이 매우 중요하다. 실시간 통행시간 예측기술을 통해 도로 이용자에게 통행시간 정보를 제공해줌으로써 운전자가 정보에 기반을 둔 선택을 할 수 있게 되며, 이에 따라 도로이용자의 통행 효용 및 도로시설 이용효율을 극대화할 수 있다. 본 연구에서는 자료 성질이 다른 VDS정보와 AVI정보를 하나의 틀 안에서 융합하는 모형을 제시하였으며, 이를 통해 VDS정보의 실시간성과 AVI 정보의 현실반영 특성을 반영한 통행시간추정이 가능하게 되었다. 또한 실시간 교통정보 제공을 위해 알고리즘의 수치연산 처리량이 실시간 현장 적용이 가능한 수준이 되도록 모형을 개발하였다. 본 연구에서 제시된 통행시간 추정 모형의 적용가능성과 신뢰성은 실제 국도 교통량자료를 이용하여 검증하였다. 실험결과에 따르면 본 모형은 연산처리 효율성이 매우 우수하여 실시간 운영 이 가능할 뿐만 아니라 실시간으로 수집되는 검지정 보를 사용함으로써 예측의 정확도를 향상시켰다. 특히 본 연구에서 제시한 이질적 자료의 융합방법은 향후 새로운 형태의 검지자료를 활용하는데 있어서 매우 유용하게 사용될 수 있을 것으로 기대된다.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2007년도 추계학술대회 논문집
• /
• pp.411-418
• /
• 2007

To analyze dynamic and long-term behavior of high speed rail system, and seismic measurements been installed at the various locations in the high speed rail system. Among these, 76 measurements were installed Chunan and Deajeon, and 80 measurements between Kwangmyung and Chunan. From these 156 measurements, real time data are continuously corrected and be sent to the main monitoring system to be used further analysis. These two systems were installed by different institution, and so there are not only basic differences in the system itself, but system running methods and data collecting/transferring methodology. There has been systematic difficulties due to these differences. This study shows the whole steps of high speed rail data monitoring systems include measurement equipment itself and data collecting/transferring system. study will proposed a more effective methods for collecting. This study also discuss the real time analysis method which can be used for future high speed rail monitoring system.