• Journal of Sensor Science and Technology
• /
• v.24 no.5
• /
• pp.291-298
• /
• 2015

There are many landslides occurred by typhoons and intense rainfall during the summer seasons in Korea. To predict a landslide triggering it is important to understand mechanisms and potential areas of landslides by the geological approaches. However, recent climate changes make difficult to predict landslide based on only conventional prediction methods. Therefore, the importance of a real-time monitoring of landslide using various sensors is emphasized in recent. Many researchers have studied monitoring techniques of landslides and suggested several monitoring systems which can be applicable to the natural terrain. Most sensors of landslide monitoring measure slope displacement, hydrogeologic properties of soils and rocks, changes of stress in soil and rock fractures, and rainfall amount and intensity. The measured values of each sensor are transmitted to a monitoring server in real-time. The ultimate goal of landslide monitoring is to warn landslide occurrence in advance and to reduce damages induced by landslides. This study introduces the current situation of landslide monitoring techniques in each country.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.6
• /
• pp.439-447
• /
• 2019

In this study, experiments were conducted to establish appropriate measures for slopes with high risk of collapse and to obtain results for minimizing slope collapse damage by detecting the micro-displacement of soil in advance by installing a laser sensor and a vibration sensor in the landslide reduction model experiment. Also, the behavior characteristics of the soil layer due to rainfall and moisture ratio changes such as pore water pressure and moisture were analyzed through a landslide reduction model experiment. The artificial slope was created using granite weathering soil, and the resulting water ratio(water pressure, water) changes were measured at different rainfall conditions of 200mm/hr and 400mm/hr. Laser sensors and vibration sensors were applied to analyze the surface displacement, and the displacement time were compared with each other by video analysis. Experiments have shown that higher rainfall intensity takes shorter time to reach the limit, and increase in the pore water pressure takes shorter time as well. Although the landslide model test does not fully reflect the site conditions, measurements of the time of detection of displacement generation using vibration sensors show that the timing of collapse is faster than the method using laser sensors. If ground displacement measurements using sensors are continuously carried out in preparation for landslides, it is considered highly likely to be utilized as basic data for predicting slope collapse, reducing damage, and activating the measurement industry.

• Journal of Advanced Navigation Technology
• /
• v.23 no.1
• /
• pp.84-89
• /
• 2019

This is a pilot study of machine learning based structural health monitoring system using flight data of composite aircraft. In this study, the most suitable machine learning algorithm for structural health monitoring was selected and dimensionality reduction method for application on the actual flight data was conducted. For these tasks, impact test on the cantilever beam with added mass, which is the simulation of damage in the aircraft wing structure was conducted and classification model for damage states (damage location and level) was trained. Through vibration test of cantilever beam with fiber bragg grating (FBG) sensor, data of normal and 12 damaged states were acquired, and the most suitable algorithm was selected through comparison between algorithms like tree, discriminant, support vector machine (SVM), kNN, ensemble. Besides, through neighborhood component analysis (NCA) feature selection, dimensionality reduction which is necessary to deal with high dimensional flight data was conducted. As a result, quadratic SVMs performed best with 98.7% for without NCA and 95.9% for with NCA. It is also shown that the application of NCA improved prediction speed, training time, and model memory.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.6
• /
• pp.719-729
• /
• 2017

Recently, the field of agriculture has been gaining a new leap with the integration of ICT technology in agriculture. In particular, smart farms, which incorporate the Internet of Things (IoT) technology in agriculture, are in the spotlight. Smart farm technology collects and analyzes information such as temperature and humidity of the environment where crops are cultivated in real time using sensors to automatically control the devices necessary for harvesting crops in the control device, Environment. Although smart farm technology is paying attention as if it can solve everything, most of the research focuses only on increasing crop yields. This paper focuses on the development of a system architecture that can harvest high quality crops at the optimum stage rather than increase crop yields. In this paper, we have developed an architecture using apple trees as a sample and used the color information and weight information to predict the harvest time of apple trees. The simple board that collects color information and weight information and transmits it to the server side uses Arduino and adopts model-driven development (MDD) as development methodology. We have developed an architecture to provide services to PC users in the form of Web and to provide Smart Phone users with services in the form of hybrid apps. We also developed an architecture that uses beacon technology to provide orchestration information to users in real time.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.301-307
• /
• 2023

Deep learning requires building a deep neural network, collecting a large amount of training data, and then training the built neural network for a long time. If training does not proceed properly or overfitting occurs, training will fail. When using deep learning tools that have been developed so far, it takes a lot of time to collect training data and learn. However, due to the rapid advent of the mobile environment and the increase in sensor data, the demand for real-time deep learning technology that can dramatically reduce the time required for neural network learning is rapidly increasing. In this study, a real-time deep learning system was implemented using an Arduino system equipped with a fine dust sensor. In the implemented system, fine dust data is measured every 30 seconds, and when up to 120 are accumulated, learning is performed using the previously accumulated data and the newly accumulated data as a dataset. The neural network for learning was composed of one input layer, one hidden layer, and one output. To evaluate the performance of the implemented system, learning time and root mean square error (RMSE) were measured. As a result of the experiment, the average learning error was 0.04053796, and the average learning time of one epoch was about 3,447 seconds.

• Korean Journal of Agricultural Science
• /
• v.51 no.3
• /
• pp.315-329
• /
• 2024

This study was conducted for simulation model development of an electric all-wheel-drive vehicle to adapt the agricultural machinery. Data measurement system was installed on a four-wheel electric driven vehicle using proximity sensor, torque-meter, global positioning system (GPS) and data acquisition (DAQ) device. Axle torque and rotational speed were measured using a torque-meter and a proximity sensor. Driving test was performed on an upland field at a speed of 7 km·h^-1. Simulation model was developed using a multi-body dynamics software, and tire properties were measured and calculated to reflect the similar road conditions. Measured and simulated data were compared to validate the developed simulation model performance, and axle rotational speed was selected as simulation input data and axle torque and power were selected as simulation output data. As a result of driving performance, an average axle rotational speed was 115 rpm for each wheel. Average axle torque and power were 4.50, 4.21, 4.04, and 3.22 Nm and 53.42, 50.56, 47.34, and 38.07 W on front left, front right, rear left, and rear right wheel, respectively. As a result of simulation driving, average axle torque and power were 4.51, 3.9, 4.16, and 3.32 Nm and 55.79, 48.11, 51.62, and 41.2 W on front left, front right, rear left, and rear right wheel, respectively. Absolute error of axle torque was calculated as 0.22, 7.36, 2.97, and 3.11% on front left, front right, rear left, rear right wheel, respectively, and absolute error of axle power was calculated as 4.44, 4.85, 9.04, and 8.22% on front left, front right, rear left, and rear right wheel, respectively. As a result of absolute error, it was shown that developed simulation model can be used for driving performance prediction of electric driven vehicle. Only straight driving was considered in this study, and various road and driving conditions would be considered in future study.

• Journal of Internet of Things and Convergence
• /
• v.10 no.4
• /
• pp.101-108
• /
• 2024

Indoor localization is a critical component for numerous applications, ranging from navigation in large buildings to emergency response. This paper presents an enhanced Pedestrian Dead Reckoning (PDR) scheme using smartphone sensors, integrating neural network-aided motion recognition, Kalman filter-based error correction, and multi-sensor data fusion. The proposed system leverages data from the accelerometer, magnetometer, gyroscope, and barometer to accurately estimate a user's position and orientation. A neural network processes sensor data to classify motion modes and provide real-time adjustments to stride length and heading calculations. The Kalman filter further refines these estimates, reducing cumulative errors and drift. Experimental results, collected using a smartphone across various floors of University, demonstrate the scheme's ability to accurately track vertical movements and changes in heading direction. Comparative analyses show that the proposed CNN-LSTM model outperforms conventional CNN and Deep CNN models in angle prediction. Additionally, the integration of barometric pressure data enables precise floor level detection, enhancing the system's robustness in multi-story environments. Proposed comprehensive approach significantly improves the accuracy and reliability of indoor localization, making it viable for real-world applications.

• Tuberculosis and Respiratory Diseases
• /
• v.41 no.5
• /
• pp.521-530
• /
• 1994

Background : The past studies on prediction formulas of pulmonary function parameters in healthy nonsmoking Korean adults have been performed in relatively small number of subjects and the reported results were restricted on a few parameters. Also there was no systematic investigation into the effect of smoking on pulmonary function parameters in smokers who have no respiratory symptoms. Therefore we attempted to establish prediction formulas of pulmonary function parameters and examined the effect of smoking on pulmonary function parameters. Methods We analyzed the result of parameters derived from the forced expiratory spirogram in 1,067 nonsmoking subjects from June in 1990 to December in 1991. They consisted of 306 males and 761 females and had neither respitatory symptoms nor history of respiratory disease. We derived prediction formulas by multiple linear regression method from their age, heights, and weights in each sex. To examine the effect of smoking on pulmonary function parameters, we classified 383 smoking men into three groups according to the past amount of smoking as follows : i.e. group of smokers who have smoked below 10 pack-years, 10-20 pack-years and above 20 pack-years. Regarding each group of past smoking as an independent dummy variable, we analyzed pulmonary function parameters including nonsmoking men as a baseline by multiple linear regression. We evaluated the smoking effect on pulmonary function parameters according to estimated p-value. Result : 1) Prediction formulas for pulmonary function parameters in each sex were derived. 2) The past smoking less than 10 pack-years does not give any effect on pulmonary function parameters. The past smoking of 10~20 pack-years showed significant negative correlation with $FEV_1$/FVC and FEF 25~75%, and the smoking above 20 pack years showed negative correlation with $FEV_1$ and $FEV_1$/FVC. Conclusion : We have got prediction formulas of pulmonary function parameters which is driven from forced expiratory spirogram in nonsmoking Korean adults by multiple linear regression from age, heights and weights of subjects. The past smoking more than 10 pack-years showed negative correlation with some pulmonary function parameters of airflow obstruction.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1255-1272
• /
• 2023

Satellite-based chlorophyll-a concentration, produced as a long-term time series, is crucial for global climate change research. The production of data without gaps through the merging of time-synthesized or multi-satellite data is essential. However, studies related to satellite-based chlorophyll-a concentration in the waters around the Korean Peninsula have mainly focused on evaluating seasonal characteristics or proposing algorithms suitable for research areas using a single ocean color sensor. In this study, a merging dataset of remote sensing reflectance from the geostationary sensor GOCI-II and polar-orbiting sensors (MODIS, VIIRS, OLCI) was utilized to achieve high spatial coverage of chlorophyll-a concentration in the waters around the Korean Peninsula. The spatial coverage in the results of this study increased by approximately 30% compared to polar-orbiting sensor data, effectively compensating for gaps caused by clouds. Additionally, we aimed to quantitatively assess accuracy through comparison with global chlorophyll-a composite data provided by Ocean Colour Climate Change Initiative (OC-CCI) and GlobColour, along with in-situ observation data. However, due to the limited number of in-situ observation data, we could not provide statistically significant results. Nevertheless, we observed a tendency for underestimation compared to global data. Furthermore, for the evaluation of practical applications in response to marine disasters such as red tides, we qualitatively compared our results with a case of a red tide in the East Sea in 2013. The results showed similarities to OC-CCI rather than standalone geostationary sensor results. Through this study, we plan to use the generated data for future research in artificial intelligence models for prediction and anomaly utilization. It is anticipated that the results will be beneficial for monitoring chlorophyll-a events in the coastal waters around Korea.

• Journal of Korea Water Resources Association
• /
• v.56 no.12
• /
• pp.919-928
• /
• 2023

Rainfall characteristics in Korea are concentrated during the summer flood season. In particular, when a large amount of turbid water flows into the dam due to the increasing trend of concentrated rainfall due to abnormal rainfall and abnormal weather conditions, prolonged turbid water phenomenon occurs due to the overturning phenomenon. Much research is being conducted on turbid water prediction to solve these problems. To predict turbid water, turbid water data from the upstream inflow is required, but spatial and temporal data resolution is currently insufficient. To improve temporal resolution, the development of the Turbidity-SS conversion equation is necessary, and to improve spatial resolution, multi-item water quality measurement instrument (YSI), Laser In-Situ Scattering and Transmissometry (LISST), and hyperspectral sensors are needed. Sensor-based measurement can improve the spatial resolution of turbid water by measuring line and surface unit data. In addition, in the case of LISST-200X, it is possible to collect data on particle size, etc., so it can be used in the Turbidity-SS conversion equation for fraction (Clay: Silt: Sand). In addition, among recent remote sensing methods, the spatial distribution of turbid water can be presented when using UAVs with higher spatial and temporal resolutions than other payloads and hyperspectral sensors with high spectral and radiometric resolutions. Therefore, in this study, the Turbidity-SS conversion equation was calculated according to the fraction through laboratory analysis using LISST-200X and YSI-EXO, and sensor-based field measurements including UAV (Matrice 600) and hyperspectral sensor (microHSI 410 SHARK) were used. Through this, the spatial distribution of turbidity and suspended sediment concentration, and the turbidity calculated using the Turbidity-SS conversion equation based on the measured suspended sediment concentration, was presented. Through this, we attempted to review the applicability of the Turbidity-SS conversion equation and understand the current status of turbid water occurrence.