• Smart Structures and Systems
• /
• v.32 no.2
• /
• pp.83-99
• /
• 2023

The temperature prediction approaches of three important locations in an operational longitudinal slab track-bridge structure by using three typical neural network methods based on the field measuring platform of four meteorological factors and internal temperature. The measurement experiment of four meteorological factors (e.g., ambient temperature, solar radiation, wind speed, and humidity) temperature in the three locations of the longitudinal slab and base plate of three important locations (e.g., mid-span, beam end, and Wide-Narrow Joint) were conducted, and then their characteristics were analyzed, respectively. Furthermore, temperature prediction effects of three locations under five various meteorological conditions are tested by using three neural network methods, respectively, including the Artificial Neural Network (ANN), the Long Short-Term Memory (LSTM), and the Convolutional Neural Network (CNN). More importantly, the predicted effects of solar radiation in four meteorological factors could be identified with three indicators (e.g., Root Means Square Error, Mean Absolute Error, Correlation Coefficient of R2). In addition, the LSTM method shows the best performance, while the CNN method has the best prediction effect by only considering a single meteorological factor.

• Korean Journal of Agricultural Science
• /
• v.47 no.4
• /
• pp.1029-1037
• /
• 2020

The machine learning algorithm has been widely used in water-related fields such as water resources, water management, hydrology, atmospheric science, water quality, water level prediction, weather forecasting, water discharge prediction, water quality forecasting, etc. However, water quality prediction studies based on the machine learning algorithm are limited compared to other water-related applications because of the limited water quality data. Most of the previous water quality prediction studies have predicted monthly water quality, which is useful information but not enough from a practical aspect. In this study, we predicted the dissolved oxygen (DO) using recurrent neural network with long short-term memory model recurrent neural network long-short term memory (RNN-LSTM) algorithms with hourly- and daily-datasets. Bugok Bridge in Oncheoncheon, located in Busan, where the data was collected in real time, was selected as the target for the DO prediction. The 10-month (temperature, wind speed, and relative humidity) data were used as time prediction inputs, and the 5-year (temperature, wind speed, relative humidity, and rainfall) data were used as the daily forecast inputs. Missing data were filled by linear interpolation. The prediction model was coded based on TensorFlow, an open-source library developed by Google. The performance of the RNN-LSTM algorithm for the hourly- or daily-based water quality prediction was tested and analyzed. Research results showed that the hourly data for the water quality is useful for machine learning, and the RNN-LSTM algorithm has potential to be used for hourly- or daily-based water quality forecasting.

• Architectural research
• /
• v.14 no.4
• /
• pp.153-161
• /
• 2012

This paper presents an integrated procedure to predict the temperature and moisture distributions in hardening concrete considering the effects of temperature and aging. The degree of hydration is employed as a fundamental parameter to evaluate hydro-thermal-mechanical properties of hardening concrete. The temperature history and temperature distribution in hardening concrete is evaluated by combining cement hydration model with three-dimensional finite element thermal analysis. On the other hand, the influences of both self-desiccation and moisture diffusion on variation of relative humidity are considered. The self-desiccation is evaluated by using a semi-empirical expression with desorption isotherm and degree of hydration. The moisture diffusivity is expressed as a function of degree of hydration and current relative humidity. The proposed procedure is verified with experimental results and can be used to evaluate the early-age crack of hardening concrete.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.133-152
• /
• 2022

Rice is a fundamental staple food commodity all around the world. Globally, it is grown over 167 million hectares and occupies almost 1/5^th of total cultivated land under cereals. With a total production of 782 million metric tons in 2018. In Pakistan, it is the 2^nd largest crop being produced and 3^rd largest food commodity after sugarcane and rice. The stem borers a type of pest in rice and other crops, Scirpophaga incertulas or the yellow stem borer is very serious pest and a major cause of yield loss, more than 90% damage is recorded in Pakistan on rice crop. Yellow stem borer population of rice could be stimulated with various environmental factors which includes relative humidity, light, and environmental temperature. Focus of this study is to find the environmental factors changes i.e., temperature, relative humidity and rainfall that can lead to cause outbreaks of yellow stem borers. this study helps to find out the hot spots of insect pest in rice field with a control of farmer's palm. Proposed system uses temperature, relative humidity, and rain sensor along with artificial neural network to predict yellow stem borer attack and generate warning to take necessary precautions. result shows 85.6% accuracy and accuracy gradually increased after repeating several training rounds. This system can be good IoT based solution for pest attack prediction which is cost effective and accurate.

• Journal of Environmental Health Sciences
• /
• v.47 no.6
• /
• pp.548-557
• /
• 2021

Background: Due to the emergence of new diseases such as COVID-19, an increasing number of people are struggling with stress and depression. Interest is growing in forest-based recreation for physical and mental relief. Objectives: A prediction model equation using meteorological factors and data was developed to predict the quantities of medicinal substances generated in forests (monoterpenes) in real-time. Methods: The concentration of phytoncide and meteorological factors in the forests near Chuncheon in South Korea were measured for nearly two years. Meteorological factors affecting the observation data were acquired through a multiple regression analysis. A model equation was developed by applying a linear regression equation with the main factors. Results: The linear regression analysis revealed a high explanatory power for the coefficients of determination of temperature and humidity in the coniferous forest (R²=0.7028 and R²=0.5859). With a temperature increase of 1℃, the phytoncide concentration increased by 31.7 ng/Sm³. A humidity increase of 1% led to an increase in the coniferous forest by 21.9 ng/Sm³. In the deciduous forest, the coefficients of determination of temperature and humidity had approximately 60% explanatory power (R²=0.6611 and R²=0.5893). A temperature increase of 1℃ led to an increase of approximately 9.6 ng/Sm³, and 1% humidity resulted in a change of approximately 6.9 ng/Sm³. A prediction model equation was suggested based on such meteorological factors and related equations that showed a 30% error with statistical verification. Conclusions: Follow-up research is required to reduce the prediction error. In addition, phytoncide data for each region can be acquired by applying actual regional phytoncide data and the prediction technique proposed in this study.

• Food Engineering Progress
• /
• v.21 no.4
• /
• pp.312-317
• /
• 2017

Weight loss that influences quality and farmer incomes is affected by the storage environment of agricultural products. The interior of storage should be maintained at high humidity to prevent the weight loss of products which contain a lot of moisture. The research had constantly proceeded with change in the heat exchanger surface areas, humidity systems, and weight loss forecast to maintain high humidity within storage. Relative humidity that exerts an effect weight loss of crop is influenced by storage temperature, leak state, and volume of product. When weight loss is predicted, different conditions of these factors are derived. In case of CA storage, ways of forecasting the weight loss become easier compared to cold storage due to sealed storage with external environment during storage period. In this study, apples were stored in purge-type CA storage and weight loss has been predicted by using operating characteristics and environmental conditions. As a result, humidity variation in the storage fluctuates with the operation of the unit-cooler. Furthermore, unit-cooler operation factor is influenced by outside temperature and respiration heat. Prediction value of weight loss according to temperature and humidity has been most accurately predicted. Prediction value through defrosting water measured shows unit-cooler work quality. K-value needs verification to calculate the VPD method.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.13 no.3
• /
• pp.167-173
• /
• 2001

This paper represents the numerical analysis for microenvironments various temperature and humidity in bed mattress. He purpose of this study is for healthful bed mattress by controling a bacteria with a prediction of the vapor and temperature distributions in the bed mattress. The numerical model is one dimensional unsteady state and the governing equations were discretized by fully implicit scheme. The numerical results were compared with experimental data, and showed a good agreement with them. Specially, the excess-relative humidity shows a lower distribution near the surface of mattress, meaning that the optimum living condition for bacteria will be caused.

• Proceedings of the Korea Concrete Institute Conference
• /
• 1999.10a
• /
• pp.767-770
• /
• 1999

The carbonation process is affected both by the concrete material properties such as W/C ratio, types of cement and aggregated, admixture characteristics and the environmental factors such as CO2 concentration, temperature, humidity. Based on results of preliminary research on carbonation, this study is to propose a carbonation prediction model by taking into account of prediction model by taking into account of CO2 concentration and W/C ratio among major factors affecting the carbonation process.

• Korean Journal of Food Science and Technology
• /
• v.19 no.2
• /
• pp.176-180
• /
• 1987

The sorption characteristics of dried garlic flakes stored at various relative humidity and storage temperature were studied. At low relative humidity below RH 51%, the sorption equilibrium was easily attained, whereas at higher relative humidity above RH 67%, the flakes were browned by higher equilibrium moisture content. The flakes were browned at relative humidity above 67% at $20^{\circ}C$ and $35^{\circ}C$, above 84% at $5^{\circ}C$, respectively. The moisture contents of monolayer value for the flakes were ranging from 5.80% to 6.20% (DB) with varying temperatures. And the necessity of moisture-proof packaging material suggested for the long term storage of the flakes because the lower moisture content and storage temperature, the higher driving force of wetting. Regression equation for browning rate prediction with relative humidity and storage temperature of the flakes was determined.

• Composites Research
• /
• v.32 no.6
• /
• pp.382-387
• /
• 2019

A single frequency strain mode test, a stress relaxation mode test, and a creep test using RH-DMA were performed to investigate the effects of relative humidity and temperature on the viscous properties of PET film. The relative humidity was 10%, 30%, 50%, 70%, and 90%. The temperature was considered to be 30~95℃ for single frequency strain mode tests, 30℃ and 70℃ for stress relaxation mode test, and 5~95℃ for creep test. According to the results, higher relative humidity results in lower storage modulus and loss modulus, but the maximum value of the loss modulus is not significantly affected by changes in relative humidity and is almost constant. Relaxation modulus decreases rapidly at the beginning and becomes constant, and as the temperature increases, it is susceptible to changes in relative humidity. Strain recovery also increases rapidly at the beginning and is susceptible to changes in relative humidity as the temperature increases. In addition, as the temperature increases, the degree of increase in creep compliance increases, and as the temperature rises above the glass transfer temperature, the degree of increase becomes very large. The master curve determined by the time-temperature superposition provides the information to predict the long-term performance under operating conditions such as relative humidity and temperature.