• 융합정보논문지
• /
• 제12권4호
• /
• pp.260-269
• /
• 2022

본 논문에서는 기존에 전문가에 의해서 이루어지던 국가 대기오염 측정망 데이터들의 이상 탐지 작업을 인공지능을 통해 자동화하고자 심층 신경망을 이용한 이상 탐지 모델을 제안하였다. 환경과학원에서 제공받은 기상자료 데이터의 결측치 및 이상치를 분석하여 학습데이터를 생성하였으며 비지도 학습 방식의 BeatGAN 모델에 기반하여 커널 구조 변경과 합성곱 필터층 및 전치 합성곱 필터층의 추가를 통해 새로운 모델을 제안하여 이상 탐지 성능을 높이고자 하였다. 또한 제안하는 모델의 생성적 특징을 활용하여 새로운 데이터를 생성하고 이를 학습에 사용하는 재학습 알고리즘을 구현 및 적용하여 기존 BeatGAN 모델뿐 아니라 다른 비지도 학습 모델인 Iforest, One Class SVM과 비교하였을 때 제안모델의 성능이 가장 높았음을 확인할 수 있었다. 본 연구를 통해 실제 산업현장에서 센서의 이상, 점검 등의 여러 요인으로 인해 학습 데이터가 부족한 상황에서 추가적인 비용없이 과적합을 피하며 제안하는 모델의 이상탐지 성능을 올릴 수 있는 방법을 제시할 수 있었다.

• 센서학회지
• /
• 제27권3호
• /
• pp.143-149
• /
• 2018

In this paper, we introduce an edge-spike modulation method for visible light communication (VLC). This method is effective in preventing LED flicker and 120 Hz noise interference in base-band VLC. In the VLC transmitter, edge-spikes are generated by passing the digital data through a simple RC-high pass filter (HPF). The LED modulation of the edge-spikes does not change the average power of the LED light; thus it prevents LED flicker. In the VLC receiver, the 120 Hz noise from other lighting lamps is easily eliminated by RC-HPF, while the edge-spike signal is detected normally. In our experiment, the message of an air-quality sensor was successfully transmitted using edge-spike modulation. This structure is useful in constructing, e.g., wireless gas monitoring sensor systems to warn and prevent harmful gas leakage accidents in buildings using LED light.

• 센서학회지
• /
• 제17권2호
• /
• pp.151-155
• /
• 2008

In this paper, it was investigated that the pattern recognition of multiplication environment of lactic acid bacteria in the process of curd yogurt preparation using household fermentation system, which was manufactured by combining incubator with sensor module, data processing circuit and computer. It will be sufficiently applicable to determine the maximum ratio of the amount of air to mixed milk for preparation of high quality yogurt.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2021년도 봄 학술논문 발표대회
• /
• pp.17-18
• /
• 2021

The unit-water content of concrete is one of the important factors in determining the quality of concrete and is directly related to the durability of the construction structure, and the current method of measuring the unit-water content of concrete is applied by the Air Meta Act and the Electrostatic Capacity Act. However, there are complex and time-consuming problems with measurement methods. Therefore, high frequency moisture sensor was used for quick and high measurement, and unit-water content of mortar was evaluated through machine running and deep running based on measurement big data.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2020년도 가을 학술논문 발표대회
• /
• pp.6-7
• /
• 2020

The unit-water content of concrete is one of the important factors in determining the quality of concrete and is directly related to the durability of the construction structure, and the current method of measuring the unit-water content of concrete is applied by the Air Meta Act and the Electrostatic Capacity Act. However, there are complex and time-consuming problems with measurement methods. Therefore, high frequency moisture sensor was used for quick and high measurement, and unit-water content of mortar was evaluated through machine running and deep running based on measurement big data.

• 산업경영시스템학회지
• /
• 제46권3호
• /
• pp.186-197
• /
• 2023

In this study, we focus on the improvement of data quality transmitted from a weather buoy that guides a route of ships. The buoy has an Internet-of-Thing (IoT) including sensors to collect meteorological data and the buoy's status, and it also has a wireless communication device to send them to the central database in a ground control center and ships nearby. The time interval of data collected by the sensor is irregular, and fault data is often detected. Therefore, this study provides a framework to improve data quality using machine learning models. The normal data pattern is trained by machine learning models, and the trained models detect the fault data from the collected data set of the sensor and adjust them. For determining fault data, interquartile range (IQR) removes the value outside the outlier, and an NGBoost algorithm removes the data above the upper bound and below the lower bound. The removed data is interpolated using NGBoost or long-short term memory (LSTM) algorithm. The performance of the suggested process is evaluated by actual weather buoy data from Korea to improve the quality of 'AIR_TEMPERATURE' data by using other data from the same buoy. The performance of our proposed framework has been validated through computational experiments based on real-world data, confirming its suitability for practical applications in real-world scenarios.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2010년도 추계학술대회
• /
• pp.389-392
• /
• 2010

특수한 작업장이외의 주택실내나 일반 사무실 등에서의 공기오염 문제는 인간이 주거시설에 거주한 이례로 계속되어온 문제로서 그 대책이 시급하다. 쉽게 외부의 신선한 공기와 충분한 양의 환기로서 해결이 가능하나 사람이 계속해서 관리해 주기에는 불편한 상황이다. 네트워크상에서 센서 네트워크를 이용한다면 쉽게 관리 및 제어가 가능하다. 유비쿼터스 센서 네트워크는 부착된 태그와 센서로부터 사물 및 환경 정보를 감지, 저장, 가공, 전달하여 인간 생활에 폭넓게 활용되며, 환경오염에 대해서도 사람이 직접 측정 및 모니터링 하기 힘든 지역에 설치되어 활용되고 있다. 다른 네트워크에 비해 초소형, 저전력, 저비용으로 쉽게 구성 가능하기 때문에 꾸준히 연구되어지고 있으며 환경과 IT의 전략적 융합을 통한 그린 IT의 네트워크 접목 또한 중요한 연구분야로 조명되고 있다. 본 논문에서는 네트워크 기반하에 실내 공기질 관리를 구성하고 관리 및 제어하여 활용 방안에 대하여 제시한다.

• 센서학회지
• /
• 제27권4호
• /
• pp.227-231
• /
• 2018

Indoor air pollution has become a serious issue, affecting the health and comfort of building occupants. Volatile organic compounds (VOCs) are among the most common indoor contaminants, and are released from numerous indoor emission sources. Among the VOCs, formaldehyde and toluene are toxic chemicals at low levels and are frequently detected indoors. Exposure to formaldehyde and toluene can irritate sensitive tissue and may increase the risk of cancer. Therefore, monitoring formaldehyde and toluene is critical for the health and comfort of residents. In addition, as human indoor activities can generate VOC gases, analysis of their influence on VOCs is needed. In this study, we compared electronic nose (E-Nose) data for formaldehyde and toluene with E-Nose data for indoor mixture gas with consideration for human indoor activities.

• 한국환경보건학회지
• /
• 제46권4호
• /
• pp.444-456
• /
• 2020

Objectives: This study developed an index for the indoor air quality management of city buses to allow the provision of indoor air quality information to city bus users. Methods: Nine city buses in Seoul were measured for PM₁₀, PM_2.5, CO₂, temperature, and relative humidity through IoT sensors. Big data collected through the sensors was analyzed to identify indoor air quality on city buses and graded through the index. Results: As a result of dividing the measured city bus data into five grades through the IAQ index, PM₁₀ was rated "good" for 30.4% of the total measured values, and 9.2% were rated "risky". For PM_2.5, 67.7 percent were rated "good" and 0.4 percent were rated "risky". For CO₂, 0.9% were 'good' and 1.1% were 'risky'. The results of the classification through the IAQ index for city buses showed that the impact of good, normal, sensitive, bad, and dangerous were 2.7, 38.8, 46.0, 12.4, and 0.1%, respectively. According to the analysis by measurement area, Seocho-gu, Gangnam-gu, Seongdong-gu, Gwangjin-gu, and Dobong-gu are "normal" and other areas (Seodaemoon-gu, Jongno-gu, Yongsan-gu, Jung-gu, Seongbuk-gu, Dongdaemun-gu, Junggye-gu, Gangbuk-gu, and Nowon-gu) are all rated "sensitive". Conclusions: When analyzing cases where PM₁₀ and CO₂ indices are in the "bad" zone, the concentration is generally found to increase during rush hour, during which there are a large number of passengers. It is expected that indoor air quality management in vehicles will be necessary during rush hour.

• 한국식품과학회지
• /
• 제34권6호
• /
• pp.947-953
• /
• 2002

시중에서 판매되는 김을 구입하여 습도가 32%, 43%, 75%, 온도는 $5^{\circ}C,\;15^{\circ}C,\;30^{\circ}C$에서 각각 김을 보관 한 후 저장 기간에 따른 김의 품질변화를 metal oxide 센서로 구성된 전자코와 SAW 센서를 바탕으로한 GC(z-Nose)를 이용하여 측정하였다. PCA 분석결과, $5^{\circ}C$, 32%에서 보관한 김의 경우는 저장기간이 지나도 김의 품질변화가 거의 없었다. 이것은 온도와 습도가 모두 낮아 김의 품질변화에는 영향을 미치지 않았으며, RH 43%, RH 75%에서 보관한 김의 경우는 저장기간이 지날수록 제 1 주성분 값이 양의 값$(+0.2{\sim}0.4})$에서 음의 값$(-0.4{\sim}\;-0.2)$으로 변화하는 경향으로 나타났다. RH 43% 보다 75%의 경우가 더 뚜렷한 감소를 보였으며 높은 상대습도 조건에서는 $15^{\circ}C$와 $30^{\circ}C$에서 유사한 경향을 나타내었다. z-Nose로 얻은 데이터를 패턴 분석한 결과 저장 기간이 지나면서 저장 온도와 습도에 따라 변질된 향시성분의 차이를 보여주었다. 이것은 미생물 수를 측정할 때와 마찬가지의 결과$(r^2=0.87)$를 보였으며 색도와는 크게 영향이 없음을 알 수 있었다. 이것으로 보면 전자코를 이용하여 조건을 달리하여 보관한 김의 품질관리를 효과적임을 알 수 있었다.