• Proceedings of the KSRS Conference
• /
• v.1
• /
• pp.150-152
• /
• 2006

The DISCOVER Project (${\underline{D}}istributed$ ${\underline{I}}nformation$ ${\underline{S}}ervices$ for ${\underline{C}}limate$ and ${\underline{O}}cean$ products and ${\underline{V}}isualizations$ for ${\underline{E}}arth$ ${\underline{R}}esearch$) is a NASA funded Earth Science REASoN project that strives to provide highly accurate, carefully calibrated, long-term climate data records and near-real-time ocean products suitable for the most demanding Earth research applications via easy-to-use display and data access tools. A key element of DISCOVER is the merging of data from the multiple sensors on multiple platforms into geophysical data sets consistent in both time and space. The project is a follow-on to the SSM/I Pathfinder and Passive Microwave ESIP projects which pioneered the simultaneous retrieval of sea surface temperature, surface wind speed, columnar water vapor, cloud liquid water content, and rain rate from SSM/I and TMI observations. The ocean products available through DISCOVER are derived from multi-sensor observations combined into daily products and a consistent multi-decadal climate time series. The DISCOVER team has a strong track record in identifying and removing unexpected sources of systematic error in radiometric measurements, including misspecification of SSM/I pointing geometry, the slightly emissive TMI antenna, and problems with the hot calibration source on AMSR-E. This in-depth experience with inter-calibration is absolutely essential for achieving our objective of merging multi-sensor observations into consistent data sets. Extreme care in satellite inter-calibration and commonality of geophysical algorithms is applied to all sensors. This presentation will introduce the DISCOVER products currently available from the web site, http://www.discover-earth.org and provide examples of the scientific application of both the diurnally corrected optimally interpolated global sea surface temperature product and the 4x-daily global microwave water vapor product.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.2
• /
• pp.105-115
• /
• 2017

Conventional traffic detection sensors such as loop detectors and image sensors are expensive to install and maintain and require different detection algorithms depending on the night and day and have a disadvantage that the detection rate varies widely depending on the weather. On the other hand, the millimeter-wave radar is not affected by bad weather and can obtain constant detection performance regardless of day or night. In addition, there is no need for blocking trafficl for installation and maintenance, and multiple vehicles can be detected at the same time. In this study, a multi-target detection algorithm for a radar sensor with this advantage was devised / implemented by applying a conventional single target detection algorithm. We performed the evaluation and the meaningful results were obtained.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.6
• /
• pp.584-593
• /
• 2012

This paper introduces an AVP (Automated Valet Parking) system which applies an autonomous driving concept into the current PAS (Parking Assistant System). The present commercial PAS technology is limited into vehicle. It means vehicle only senses and controls by and for itself to assist the parking. Therefore, the present PAS is restricted to simple parking events. But AVP includes wider parking events and planning because it uses infra-sensor network as well as vehicle sensor. For the realization of AVP, the commercial steering system of a compact vehicle was modified into steer-by-wire structure and various sensors like LRF (Long Range Finder) and camera were installed in a parking area. And local & global server decides where and when the vehicle can go and park in the testing area after recognized the status of environment and vehicle from those sensors. GPS solution was used to validate the AVP performance. More various parking situations, vehicles and obstacles will be considered in the next research stages based on these results. And we expect this AVP solution with more intelligent vehicles can be applied in a big parking lot like a market, an amusement park, etc.

• Journal of Sensor Science and Technology
• /
• v.5 no.1
• /
• pp.43-50
• /
• 1996

This paper presents a manufacture of the multiple subjects biotelemetry system using custom CMOS IC fabricated $1.5{\mu}m$ n-well process technology. The implantable circuits of the system except sensor interface circuits including FM transmitter are fabricated on a single chip with the sire of $4{\times}4mm^{2}$. It is possible to assemble the implantable system in a hybrid package as small as $3{\times}3{\times}2.5cm$ by using this chip, It's main function is to enable continuous measurement simultaneously up to 7-channel physiological signals from the selected one among 8 subjects. Another features of this system are to enable continuous measurement of physiological signals, and to accomplish ON/OFF switching of an implanted battery by subject selection signal with command signal from the external circuit. If this system is coupled with another appropriate sensors in medical field, various physiological parameters such as pressure, pH and temperature are to be measured effectively in the near future.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.3
• /
• pp.700-712
• /
• 2011

Due to recently advanced electrical devices, human can access computer network regardless of working location or time restriction. However, currently widely used mouse, joystick, and trackball input system are not easy to carry and they bound user hands exclusively within working space. Those make user inconvenient in Ubiquitous environments.. In this paper, we propose multiple dimension human motion detection system based on wireless sensor networks. It is a portable input device and provides easy installation process and unbinds user hands during input processing stages. Our implemented system is comprised of three components. One is input unit that senses user motions and transmits collected data to receiver. Second is receiver that conveys the received data to application, which runs on server computer. Third is application that performs command operations according to received data. Experiments shows that proposed system accurately detect the characteristics of user arm motions and fully support corresponding input requests.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.1
• /
• pp.63-68
• /
• 2018

Recently, safety accidents that occur in laboratories have occurred in various forms, so that a system that can reduce safety accidents in laboratories is required. The existing system identifies the danger situation according to the change of the temperature and the humidity, but the type of the danger situation is not known and the operation of the device is manually performed. Therefore, in this paper, we propose a system that identifies the danger situation of a reagent cabinet using multiple sensors and automatically operates the device. The internal environment of the reagent cabinet is measured in real time through the sensors and the sensor data is used to identify the danger situation. Also, when a danger situation is identified, the appropriate device is selected and operated automatically. In this way, identification of the danger situation of the reagent cabinet and automatic operation of the device will reduce the safety accidents occurring in the reagent cabinet.

• Advances in robotics research
• /
• v.2 no.1
• /
• pp.45-57
• /
• 2018

Even though the popularity of projection mapping continues to increase and it is being implemented in more and more settings, most current projection mapping systems are limited to special purposes, such as outdoor events, live theater and musical performances. This lack of versatility arises from the large number of projectors needed and their proper calibration. Furthermore, we cannot change the positions and poses of projectors, or their projection targets, after the projectors have been calibrated. To overcome these problems, we propose a projection mapping method using a projector robot that can perform projection mapping in more general or ubiquitous situations, such as shopping malls. We can estimate a projector's position and pose with the robot's self-localization sensors, but the accuracy of this approach remains inadequate for projection mapping. Consequently, the proposed method solves this problem by combining self-localization by robot sensors with position and pose estimation of projection targets based on a 3D model. We first obtain the projection target's 3D model and then use it to accurately estimate the target's position and pose and thus achieve accurate projection mapping with a projector robot. In addition, our proposed method performs accurate projection mapping even after a projection target has been moved, which often occur in shopping malls. In this paper, we employ Ubiquitous Display (UD), which we are researching as a projector robot, to experimentally evaluate the effectiveness of the proposed method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.553-557
• /
• 2009

USS(Ubiquitous Smart Space) give services, that fit in with customer's goal, by cognizing various situations that happens in a space and cooperating autonomously objects or services in a space. In USS, U-Safety is a system that cognizes more exact situations with multiple sensors in USS, deals with this and take proper actions. When men reason on situations objectively, it is most ideal that image data among collected data with used various sensors in U-Safety. A senter collects a lot of image data from image input devices equipped in various points and work a multiple situation cognition and inference that are based on this. So, senters spend many resources for processing massive data. This paper proposes hierarchical image processing method that does the first situation cognization in image input devices, blocks only points that situation cognization possibility is high among a total image, and transfers to senters. It improves the efficiency of smooth situation cognization by reducing resources that a senter spends on image processing. So, it reduces proportion of image data in U-Safety.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.5
• /
• pp.277-286
• /
• 2019

In this paper, we propose an efficient hyperplane generation technique to classify human activity from combination of events and sequence information obtained from multiple-event sensors. By generating hyperplane efficiently, our machine learning algorithm classify with less memory and run time than the LSVM (Linear Support Vector Machine) for embedded system. Because the fact that light weight and high speed algorithm is one of the most critical issue in the IoT, the study can be applied to smart home to predict human activity and provide related services. Our approach is based on reducing numbers of hyperplanes and utilizing robust string comparing algorithm. The proposed method results in reduction of memory consumption compared to the conventional ML (Machine Learning) algorithms; 252 times to LSVM and 34,033 times to LSTM (Long Short-Term Memory), although accuracy is decreased slightly. Thus our method showed outstanding performance on accuracy per hyperplane; 240 times to LSVM and 30,520 times to LSTM. The binarized image is then divided into groups, where each groups are converted to binary number, in order to reduce the number of comparison done in runtime process. The binary numbers are then converted to string. The test data is evaluated by converting to string and measuring similarity between hyperplanes using Levenshtein algorithm, which is a robust dynamic string comparing algorithm. This technique reduces runtime and enables the proposed algorithm to become 27% faster than LSVM, and 90% faster than LSTM.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.93-103
• /
• 2022

With the wider availability of sensor technology through easily affordable sensor devices, several Structural Health Monitoring (SHM) systems are deployed to monitor vital civil infrastructure. The continuous monitoring provides valuable information about the health of the structure that can help provide a decision support system for retrofits and other structural modifications. However, when the sensors are exposed to harsh environmental conditions, the data measured by the SHM systems tend to be affected by multiple anomalies caused by faulty or broken sensors. Given a deluge of high-dimensional data collected continuously over time, research into using machine learning methods to detect anomalies are a topic of great interest to the SHM community. This paper contributes to this effort by proposing a relatively new time series representation named "Shapelet Transform" in combination with a Random Forest classifier to autonomously identify anomalies in SHM data. The shapelet transform is a unique time series representation based solely on the shape of the time series data. Considering the individual characteristics unique to every anomaly, the application of this transform yields a new shape-based feature representation that can be combined with any standard machine learning algorithm to detect anomalous data with no manual intervention. For the present study, the anomaly detection framework consists of three steps: identifying unique shapes from anomalous data, using these shapes to transform the SHM data into a local-shape space and training machine learning algorithms on this transformed data to identify anomalies. The efficacy of this method is demonstrated by the identification of anomalies in acceleration data from an SHM system installed on a long-span bridge in China. The results show that multiple data anomalies in SHM data can be automatically detected with high accuracy using the proposed method.