• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.517-520
• /
• 2003

The snow-fatting measurement system including the snow sensor applying the photo-coupler is investigated in this study and using this snow sensor the height of snow fallen is measured. To measure the snow depth, five photo sensors are arranged with 5 mm distance. The snow-falling measurement system, which is measuring the motor revolution controlled with stepping motor, is mounted above the snow surface. From this work, it is feasible to measure quantitatively the snow on real time. Its software implements a proven method to achieve valid measurements also under difficult conditions as future study. In cases where the snow sensor is applieded to the prediction of snow in the meteorological observation system and the snow removing system, it is recommend the GRS-Option in order to improve the quality of snow measurements for better compensation.

• Proceedings of the KIEE Conference
• /
• 2006.04a
• /
• pp.99-101
• /
• 2006

Auto-Cross Correlated time series (ACTS) model was constructed by using the backpropagation neural network. The performance of ACTS model was evaluated with sensor information collected from a large volume, industrial plasma-enhanced chemical vapor deposition system. A total of 18 sensor information were collected. The effect of inclusion of past and future information were examined. For all but three sensor information with a large data variance demonstrated a prediction error less than 3%. By integrating ACTS model into equipment software, process quality can be more stringently monitored while improving device throughput.

• Proceedings of the KIEE Conference
• /
• 2006.04a
• /
• pp.102-104
• /
• 2006

Auto-Correlated time series (ATS) model was constructed by using the backpropagation neural network. The performance of ATS model was evaluated with sensor information collected from a large volume, industrial plasma-enhanced chemical vapor deposition system. A total of 18 sensor information were collected. The effect of inclusion of past and future information were examined. For all but three sensor information with a large data variance demonstrated a prediction error less than 4%. By integrating ATS model into equipment software, process quality can be more stringently monitored while improving device throughput.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.16 no.1
• /
• pp.93-98
• /
• 2020

Research on underwater sensor networks is increasing due to such reasons as marine resource management, maritime disaster prediction and military protection. Many underwater sensor networks performs wireless communication using an acoustic sound wave band signal having a relatively low frequency. So the digital part of their modem can take charge of carrier band signal processing. To enable this, the sampling rate of the baseband band signal should be increased to a sampling rate at which carrier band signal processing is possible. In this paper, we designed a sampling rate increasing circuit based on a CIC interpolator for underwater sensor nodes. The CIC interpolator has a simple circuit structure. However, since the CIC interpolator has a large attenuation of the pass band and a wide transition band, an inverse sinc LPF is added to compensate for frequency response of the CIC interpolator. The proposed interpolator was verified in time domain and frequency domain using ModelSim and Matlab.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.3
• /
• pp.161-166
• /
• 2021

To prevent accidents caused by changes in the surrounding environment or other factors, various protection facilities are installed at the photovoltaic connection module. The main causes of fire are sparks due to foreign substances inside the photovoltaic connection module through high temperature rise and dew condensation in the photovoltaic connection module, and fire due to heat from the power diode. The proposed method can predict the fire by measuring flame, carbon dioxide, carbon monoxide, temperature, humidity, input voltage, and current on the photovoltaic connection module, and when the fire conditions are reached, fire alarm and power off can be sent to managers and users in real time to prevent fire in advance.

• Journal of Korea Multimedia Society
• /
• v.24 no.1
• /
• pp.67-74
• /
• 2021

As IoT(Internet Of Things) devices like a smart sensor have constrained power sources, a power strategy is critical in WSN(Wireless Sensor Networks). Therefore, it is necessary to figure out the residual power of each sensor node for managing power strategies in WSN, which, however, requires additional data transmission, leading to more power consumption. In this paper, a residual power estimation method was proposed, which uses ignorantly small amount of power consumption in the resource-constrained wireless networks including WSN. A residual power prediction is possible with the least data transmission by using Machine Learning method with some training data in this proposal. The performance of the proposed scheme was evaluated by machine learning method, simulation, and analysis.

• Annual Conference of KIPS
• /
• 2016.10a
• /
• pp.829-832
• /
• 2016

경로 예측 기반의 센서 레지스트리 시스템(Path Prediction-based Sensor Registry System, PP-SRS)는 이기종 환경에서 센서 네트워크 환경에서 센서 데이터의 즉각적인 활용과 끊김 없는 해석을 위해 사용자에게 센서 정보를 제공한다. PP-SRS는 사용자의 위치를 경로 단편으로 사상하여 표현한다. 그리고 경로 단편기반으로 사용자의 경로를 예측한다. 그러나 도로 정보에 대한 경로 단편을 미리 구성해야 사용할 수 있으며 구성된 도로 정보를 무시한 경로가 발생하는 문제점을 가지고있다. 이 논문에서는 이 문제점을 해결하기 위하여 PP-SRS를 위한 격자를 이용한 개선방안을 제안한다. 이 논문은 기존의 경로 단편 표현방법과 제안하는 격자 기반 경로 표현방법에 대하여 비교한 후 PP-SRS에 개선 방법에 대하여 서술한다.

• Annual Conference of KIPS
• /
• 2015.04a
• /
• pp.798-801
• /
• 2015

센서 레지스트리 시스템(SRS, Sensor Registry System)은 이기종 센서 네트워크에서 끊김 없는 의미 처리를 위하여 사용자에게 센서 정보를 제공한다. 불안정한 네트워크 상황에서의 원활한 서비스 제공을 위하여 빠른 근거리 사용자 이동 경로 예측 알고리즘(FCR, Fast and Close-Range Prediction) 기반의 SRS가 연구되었다. 이 연구는 경로 예측 기반의 SRS에서 이용되는 FCR 알고리즘이 지니는 한계를 극복하기 위하여 3-간선 패턴(TEP, Three-Edge Pattern) 기반의 경로 예측 알고리즘을 제안한다. TEP 알고리즘은 경로를 그래프로 표현할 때 사용자의 위치를 기준으로 이전 간선, 현재 간선, 다음 간선으로 패턴화 하여 학습하고, 이 패턴을 기반으로 하는 사용자의 이동 경로를 예측한다. 또한 실험 및 비교 평가에서, TEP 알고리즘이 FCR 알고리즘에 비해 높은 정확성을 지님을 보인다.

• Journal of information and communication convergence engineering
• /
• v.16 no.4
• /
• pp.242-247
• /
• 2018

The data of K-Water waterworks is collected from various sensors and used as basic data for the operation and analysis of various devices. In this way, the importance of the sensor data is very high, but it contains misleading data due to the characteristics of the sensor in the external environment. However, the cleansing method for the missing data is concentrated on the prediction of the missing data, so the research on the detection and prediction method of the missing data is poor. This is a study to detect wrong data by converting collected data into quintiles and patterning them. It is confirmed that the accuracy of detecting false data intentionally generated from real data is higher than that of the conventional method in all cases. Future research we will prove the proposed system's efficiency and accuracy in various environments.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2020.06a
• /
• pp.23-24
• /
• 2020

In this study, the concrete compressive strength estimation system Concrete IoT Management System (hereinafter referred to as CIMS) was developed, and CIMS was applied to domestic field structure slabs and wall concrete to check whether CIMS is practically available and to estimate the accuracy of the initial strength estimation of concrete. As a result, it shows a very high correlation when the compressive strength of the specimen for structural management is compared with the estimated strength of CIMS in terms of integrated temperature, and it is expected to be gradually applied to domestic construction sites in the future.