• 한국멀티미디어학회논문지
• /
• 제24권10호
• /
• pp.1414-1424
• /
• 2021

In this paper, the importance of input factors of a DNN (Deep Neural Network) PM_2.5 forecasting model using LRP(Layer-wise Relevance Propagation) is analyzed, and forecasting performance is improved. Input factor importance analysis is performed by dividing the learning data into time and PM_2.5 concentration. As a result, in the low concentration patterns, the importance of weather factors such as temperature, atmospheric pressure, and solar radiation is high, and in the high concentration patterns, the importance of air quality factors such as PM_2.5, CO, and NO₂ is high. As a result of analysis by time, the importance of the measurement factors is high in the case of the forecast for the day, and the importance of the forecast factors increases in the forecast for tomorrow and the day after tomorrow. In addition, date, temperature, humidity, and atmospheric pressure all show high importance regardless of time and concentration. Based on the importance of these factors, the LRP_DNN prediction model is developed. As a result, the ACC(accuracy) and POD(probability of detection) are improved by up to 5%, and the FAR(false alarm rate) is improved by up to 9% compared to the previous DNN model.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2020년도 가을 학술논문 발표대회
• /
• pp.188-189
• /
• 2020

In the field of architecture, concrete and steel bars are the most common and popular combinations. The relationship between the two in a structure is a complementary good that increases in utility when consuming both materials at the same time. However, the combination of the two, which has been perceived as semi-permanent, often faces repairs or reconstruction without its lifespan reaching decades. There are a number of deterioration factors at work for the reason for this phenomenon. Among them, the neutralization of concrete in particular refers to the process in which calcium hydroxide inside concrete reacts with carbon dioxide and loses alkalinity, which creates a corrosive environment for rebars inside concrete, causing serious damage to concrete. In this study, we intend to use a multi-physical analysis program using finite element analysis method to analyze the degree of carbonation according to the internal temperature and concentration of carbon dioxide in concrete, thereby contributing to the prediction of long-term neutralization of concrete and the research related to measures for neutralization of concrete.

• 한국환경과학회지
• /
• 제28권8호
• /
• pp.701-707
• /
• 2019

Highland farming is agriculture that takes place 400 m above sea level and typically involves both low temperatures and long sunshine hours. Most highland Chinese cabbages are harvested in the Gangwon province. The Ubiquitous Sensor Network (USN) has been deployed to observe Chinese cabbages growth because of the lack of installed weather stations in the highlands. Five representative Chinese cabbage cultivation spots were selected for USN and meteorological data collection between 2015 and 2017. The purpose of this study is to develop a weight prediction model for Chinese cabbages using the meteorological and growth data that were collected one week prior. Both a regression and random forest model were considered for this study, with the regression assumptions being satisfied. The Root Mean Square Error (RMSE) was used to evaluate the predictive performance of the models. The variables influencing the weight of cabbage were the number of cabbage leaves, wind speed, precipitation and soil electrical conductivity in the regression model. In the random forest model, cabbage width, the number of cabbage leaves, soil temperature, precipitation, temperature, soil moisture at a depth of 30 cm, cabbage leaf width, soil electrical conductivity, humidity, and cabbage leaf length were screened. The RMSE of the random forest model was 265.478, a value that was relatively lower than that of the regression model (404.493); this is because the random forest model could explain nonlinearity.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.2060-2077
• /
• 2019

Recently, mobile healthcare services have attracted significant attention because of the emerging development and supply of diverse wearable devices. Smartwatches and health bands are the most common type of mobile-based wearable devices and their market size is increasing considerably. However, simple value comparisons based on accumulated data have revealed certain problems, such as the standardized nature of health management and the lack of personalized health management service models. The convergence of information technology (IT) and biotechnology (BT) has shifted the medical paradigm from continuous health management and disease prevention to the development of a system that can be used to provide ground-based medical services regardless of the user's location. Moreover, the IT-BT convergence has necessitated the development of lifestyle improvement models and services that utilize big data analysis and machine learning to provide mobile healthcare-based personal health management and disease prevention information. Users' health data, which are specific as they change over time, are collected by different means according to the users' lifestyle and surrounding circumstances. In this paper, we propose a prediction model of user physical activity that uses data characteristics-based long short-term memory (DC-LSTM) recurrent neural networks (RNNs). To provide personalized services, the characteristics and surrounding circumstances of data collectable from mobile host devices were considered in the selection of variables for the model. The data characteristics considered were ease of collection, which represents whether or not variables are collectable, and frequency of occurrence, which represents whether or not changes made to input values constitute significant variables in terms of activity. The variables selected for providing personalized services were activity, weather, temperature, mean daily temperature, humidity, UV, fine dust, asthma and lung disease probability index, skin disease probability index, cadence, travel distance, mean heart rate, and sleep hours. The selected variables were classified according to the data characteristics. To predict activity, an LSTM RNN was built that uses the classified variables as input data and learns the dynamic characteristics of time series data. LSTM RNNs resolve the vanishing gradient problem that occurs in existing RNNs. They are classified into three different types according to data characteristics and constructed through connections among the LSTMs. The constructed neural network learns training data and predicts user activity. To evaluate the proposed model, the root mean square error (RMSE) was used in the performance evaluation of the user physical activity prediction method for which an autoregressive integrated moving average (ARIMA) model, a convolutional neural network (CNN), and an RNN were used. The results show that the proposed DC-LSTM RNN method yields an excellent mean RMSE value of 0.616. The proposed method is used for predicting significant activity considering the surrounding circumstances and user status utilizing the existing standardized activity prediction services. It can also be used to predict user physical activity and provide personalized healthcare based on the data collectable from mobile host devices.

• 한국컴퓨터정보학회논문지
• /
• 제16권8호
• /
• pp.137-146
• /
• 2011

에너지 소모에 대한 증가되는 소비자의 관심을 지원하기 위하여 가전기기의 에너지 모니터링과 예측 방식을 제안한다. 제안한 시스템은 0.5초마다 전류 센서를 지나가는 전류량을 측정하는 스마트 플러그라는 일반 전기 콘센트로 설계하고, 신경회로망의 훈련과 시험 데이터를 얻기 위해 평균기온, 최저기온, 초고기온, 습도, 일조시간의 날씨 정보를 입력 데이터로 사용하고, 스마트 플러그를 통한 전기 사용량을 목표값으로 사용하였다. 훈련을 위한 실험데이터를 사용하여 역전파 알고리즘을 기반으로 한 신경회로망을 구성하였다. 입력과 출력 데이터의 비선형 매핑을 위해 다층신경회로망을 사용하였다. 제안한 신경회로망 모델은 상관관계 계수가 0.9965로 우수하게 전기 사용량을 예측할 수 있는 것을 확인하였으며, 예측의 평균 제곱 오차는 0.02033이다.

• 한국의류학회지
• /
• 제17권2호
• /
• pp.291-299
• /
• 1993

In this study, bedclimate was investigated depending on three bedquilts used on ondol in winter. The environmental room condition and the ondol surface temperature were maintained $20{\pm}1^{\circ}C$, $50{\pm}3%R$. H and $30{\pm}1^{\circ}C$, respectively. The materials of the experimental quilts were not different from each other. But the weights of cotton filler were 1.5, 3.0, and 4.5kg for the bedquilts. Two healthy young women were subjected for seven hour's sleep with two replications for this study. The results are as follows. 1) The range of temperature under the mattress was higher($38.5{\sim}43.2^{\circ}C$) than that of the temperature on the mattress($32.4{\sim}37.0^{\circ}C$) or that of the temperature inside the bedquilts($30.2{\sim}34.5^{\circ}C$). The humidity inside the bedquilts was 40~73%R.H. 2) The range of bedclimate which subjects feel comfortable were $33.6{\sim}37.1^{\circ}C$ on the mattress, $30.2{\sim}33.6^{\circ}C$, 42~67%R.H. inside the bedquilts. At this range, the mean skin temperature of the subjects was was $34.7{\sim}35.6^{\circ}C$. 3) When there was heating, the weight of mattress increased due to evaporation by heat from below, while wehght of other bedding increased. 4) The lower limbs are noted to be a good representative for the prediction of the skin temperature during sleep. 5) The thicker the bedquilt, the warmer and more humid the bedquilt, which induce frequent body movement during sleep, hence inferior comfort properties of bedquilts.

• 터널과지하공간
• /
• 제30권5호
• /
• pp.446-461
• /
• 2020

MX80 벤토나이트 펠렛에서의 열-수리-역학적 복합거동 특성을 파악하고자 TOUGH2-FLAC3D 시뮬레이터를 이용하여 스페인 CIEMAT에서 수행된 컬럼 시험에 대한 수치해석을 수행하였다. 수치해석에서는 실험실에서 사용된 것과 동일한 히터 파워와 물 주입압을 경계조건으로 설정하고 해석을 수행하였다. 사용된 열-수리 모델이 벤토나이트 펠렛의 복합거동 예측에 적용하기 적합한지 판단하기 위해 가열과 물 주입에 의한 벤토나이트 펠렛에서의 온도와 상대습도 변화를 시간 경과에 따라 잘 예측할 수 있는 지를 살펴보았다. 계산된 결과가 계측된 온도와 상대습도 변화 경향을 적절하게 재현 할 수 있었기 때문에 사용된 열-수리 모델은 벤토나이트 펠렛의 열-수리 복합거동을 예측하고 재현하기에 적절한 것으로 판단된다. 하지만, 물 주입 이후의 계산된 응력변화가 상대적으로 작고 느리게 변화되는 것으로 보아 사용된 탄성모델과 스웰링 모델에 한계점이 존재하는 것으로 보이며, 사용된 두 역학 모델로 완충재의 복잡한 열-수리-역학적 복합거동을 현실적으로 재현하기에 부족한 것으로 판단된다.

• 대한토목학회논문집
• /
• 제30권5B호
• /
• pp.437-444
• /
• 2010

토양수분은 물 에너지 순환에서 지표면과 대기 사이의 복잡한 관계를 이해하기 위한 중요한 수문인자 중 하나이다. 일반적으로, 토양수분은 온도, 바람, 토성에 의한 증발과 식생에 의한 증산에 의하여 결정이 되는 것으로 알려져 있다. 하지만, 각 인자와 토양수분과의 관계에 대한 심도 있는 연구는 아직 부족한 실정이다. 본 연구에서는 Flux tower(설마천 타워)에서 생성되는 측정인자인 대기온도, 비습, 풍속을 고려하여 토양수분 예측치를 산정하였으며 이를 실측치와 비교하고 상관분석을 실시하였다. 토양수분은 특히 겨울에는 지중온도와 매우 강한 양의 상관계수를 가졌으나 이외의 항인 대기온도, 비습, 풍속과는 상관성이 낮게 산정되었다. 봄부터 가을까지의 자료에서는 지중온도가 토양수분과 매우 강한 음의 상관계수를 가지며 대기온도와 비습의 경우 상당한 음의 상관계수를 가지며 풍속은 식생의 영향으로 상관성이 매우 낮은 것으로 판단되었다. 중회귀분석을 통하여 계절별 토양수분을 추정하여 이를 측정값과 비교하였으며 결정계수($R^2$)는 봄의 경우 0.82, 여름의 경우 0.81, 가을의 경우 0.82, 겨울의 경우 0.96로 대체로 양호한 결과를 나타내었다. 본 연구에서 토양수분에 대한 지표상의 수문기상인자들과의 밀접한 상관관계는 공간해상도가 비교적 큰 원격탐사 토양수분의 downscaling에 유용한 정보를 제공할 수 있으며, 지표상의 물 에너지 순환에 대한 보다 나은 이해를 줄 것으로 사료된다.

• KIEAE Journal
• /
• 제3권1호
• /
• pp.13-20
• /
• 2003

It is highly recognized that there is need for protection against indoor air pollution, as we realize environmental pollution is growing, For example, in an indoor environment, a person spends more than 80 percent of their time inside the building. Thus, concern about indoor decoration materials is growing, since they cause pollution in the rooms of an apartment, as well as in offices. As the indoor decoration materials become more diverse and lusurious, so the effect of VOCs(Volatile Organic Compounds) and HCHO(Formaldehy) is growing. The indoor decoration materials cause the Sick Building Syndrome, such as headaches, dizziness, or lack of concentraion, and they in turn cause serious deterioration in people's health. In this study, I probed the status of the indoor air pollution and carried on an investigation and analysis about the prevention technique. In doing so, I performed experimental tests and an assessment of the indoor decoration materials of an apartment. I also examined elements of the emitted and the emission. Finally, I examined the character of emissions, by changing environmental conditions, such as the temperature, humidity, and ventilation. With respect to VOCs tests, I applied the method of solid state adsorption using the adsorptive tube, based on the measurement of the American EPA TO-17, ASTM 5116-97, and the measurement of the Japanese Wall Decoration Industrial Association. The tested sample was analyzed by High Performance Liquid Chromatography, after going through the process of dissolvent extraction. As subjects of the test, Paint were selected. The process of this test is as follows; first, I figured out the character of the emission, by measuring the emitted concentration of VOCs and HOHC from the indoor decoration materials of an apartment. Second, I made a small-scale chamber and the test was processed in the chamber in order to suggest an environment-friendly prediction modlel development.

• 대기
• /
• 제34권2호
• /
• pp.177-185
• /
• 2024

As increasing global interest in renewable energy due to the ongoing climate crisis, there is a growing need for efficient technologies to manage such resources. This study focuses on the predictive skill of daily solar power generation using weather observation and forecast data. Meteorological data from the Korea Meteorological Administration and solar power generation data from the Korea Power Exchange were utilized for the period from January 2017 to May 2023, considering both inland (Daejeon) and coastal (Busan) regions. Temperature, wind speed, relative humidity, and precipitation were selected as relevant meteorological variables for solar power prediction. All data was preprocessed by removing their systematic components to use only their residuals and the residual of solar data were further processed with weighted adjustments for homoscedasticity. Four models, MLR (Multiple Linear Regression), RF (Random Forest), DNN (Deep Neural Network), and RNN (Recurrent Neural Network), were employed for solar power prediction and their performances were evaluated based on predicted values utilizing observed meteorological data (used as a reference), 1-day-ahead forecast data (referred to as fore1), and 2-day-ahead forecast data (fore2). DNN-based prediction model exhibits superior performance in both regions, with RNN performing the least effectively. However, MLR and RF demonstrate competitive performance comparable to DNN. The disparities in the performance of the four different models are less pronounced than anticipated, underscoring the pivotal role of fitting models using residuals. This emphasizes that the utilized preprocessing approach, specifically leveraging residuals, is poised to play a crucial role in the future of solar power generation forecasting.