• 대한임베디드공학회논문지
• /
• 제14권5호
• /
• 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
• /
• 제29권1호
• /
• 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.

• 전자공학회논문지SC
• /
• 제49권4호
• /
• pp.10-16
• /
• 2012

영상 기반 반도체 검사 장비의 검사 고속화와 검사 정확도를 위해, 넓은 FOV와 고해상도를 동시에 가지는 2차원 영상을 획득하는 것은 검사 장비에 필수적이다. 본 논문에서는 정밀도와 FOV 측면에서 양질의 영상 획득을 위한 새로운 영상획득 시스템을 제안하였다. 제안시스템은 하나의 렌즈와 광분할기, 두 개의 카메라 센서, 스테레오 영상획득 보드로 구성되며, 하나의 렌즈를 통해 입력되는 영상을 두 개의 카메라 센서를 통해 동시에 영상 획득한다. 획득된 영상의 정합을 위해, 첫 번째로 Zhang의 카메라 교정 방법을 적용시켜 각각의 카메라를 교정한다. 두 번째로 다른 카메라에서 획득한 두 영상들 사이의 수학적인 정합 함수를 찾기 위해 각 영상의 호모그래피(homography)를 이용하여, 양측 카메라간의 정합 행렬을 계산한다. 영상 호모그래피를 통해서, 획득된 두 영상은 하나의 최종 검사 영상으로의 통합을 위해 최종적으로 정합될 수 있다. 다중 카메라로부터 입력되는 다중 영상들을 활용하는 제안 검사 시스템은 실시간 영상 정합을 위해 매우 빠른 프로세스 유닛의 도움이 필요하다. 이를 위해 CUDA (Compute Unified Device Architecture)기반 병렬 프로세싱 하드웨어 및 소프트웨어를 활용한다. 두 개의 분할된 영상으로부터 실시간으로 정합된 영상을 얻을 수 있었으며, 마지막으로 연속된 실험을 통해 획득한 호모그래피의 정확도를 확인할 수 있다. 실험으로 얻은 결과들은 제안된 시스템과 방법이 대영역 고해상도 검사영상 획득을 위해 효과적임을 보인다.

• 한국소음진동공학회논문집
• /
• 제21권12호
• /
• pp.1120-1131
• /
• 2011

Researches using time reversal acoustics(TRA) for impact localization have been paid attention to recently. Dispersion characteristics of Lamb waves, which restrict the utility of classical nondestructive evaluation based on time-of-flight information, can be compensated through the application of TRA to Lamb waves on a plate. This study investigates the spatial focusing performance of time reversal Lamb waves on a plate using finite element analysis. In particular, the virtual sensor effect caused by multiple wave reflections at the boundaries of a plate is shown to enable the spatial focusing of Lamb waves though a very small number of surface-bonded piezoelectric(PZT) sensors are available. The time window size of forward response signals, are normalized with respect to the number of virtual active sensors. Then their effects on the spatial focusing performance of Lamb waves are investigated.

• Bulletin of the Korean Chemical Society
• /
• 제34권6호
• /
• pp.1632-1636
• /
• 2013

$Ga_2O_3$ one-dimensional (1D) nanostructures were synthesized by using a thermal evaporation technique. The morphology, crystal structure, and sensing properties of the $Ga_2O_3$ nanostructures functionalized with Pt to $NO_2$ gas at room temperature under UV irradiation were examined. The diameters of the 1D nanostructures ranged from a few tens to a few hundreds of nanometers and the lengths ranged up to a few hundreds of micrometers. Pt nanoparticles with diameters of a few tens of nanometers were distributed around a $Ga_2O_3$ nanorod. The responses of the nanorods gas sensors fabricated from multiple networked $Ga_2O_3$ nanorods were improved 3-4 fold at $NO_2$ concentrations ranging from 1 to 5 ppm by Pt functionalization. The Pt-functionalized $Ga_2O_3$ nanorod gas sensors showed a remarkably enhanced response at room temperature under ultraviolet (UV) light illumination. In addition, the mechanisms via which the gas sensing properties of $Ga_2O_3$ nanorods are enhanced by Pt functionalization and UV irradiation are discussed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제3권5호
• /
• pp.423-443
• /
• 2009

We present the design and implementation of a unique sensing and actuation application -- the Illuminator: a sensor network-based intelligent light control system for entertainment and media production. Unlike most sensor network applications, which focus on sensing alone, a distinctive aspect of the Illuminator is that it closes the loop from light sensing to lighting control. We describe the Illuminator's design requirements, system architecture, algorithms, implementation and experimental results. The system uses the Illumimote, a multi-modal and high fidelity light sensor module well-suited for wireless sensor networks, to satisfy the high-performance light sensing requirements of entertainment and media production applications. The Illuminator system is a toolset to characterize the illumination profile of a deployed set of fixed position lights, generate desired lighting effects for moving targets (actors, scenic elements, etc.) based on user constraints expressed in a formal language, and to assist in the set up of lights to achieve the same illumination profile in multiple venues. After characterizing deployed lights, the Illuminator computes optimal light settings at run-time to achieve a user-specified actuation profile, using an optimization framework based on a genetic algorithm. Uniquely, it can use deployed sensors to incorporate changing ambient lighting conditions and moving targets into actuation. Experimental results demonstrate that the Illuminator handles various high-level user requirements and generates an optimal light actuation profile. These results suggest that the Illuminator system supports entertainment and media production applications.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.107-109
• /
• 2004

In this paper, authors propose the sensor fusion system that can recognize multiple 3D objects from 2D projection images and tactile information. The proposed system focuses on improving recognition performance of 3D object. Unlike the conventional object recognition system that uses image sensor alone, the proposed method uses tactual sensors in addition to visual sensor. Neural network is used to fuse these informations. Tactual signals are obtained from the reaction force by the pressure sensors at the fingertips when unknown objects are grasped by four-fingered robot hand. The experiment evaluates the recognition rate and the number of teaming iterations of various objects. The merits of the proposed systems are not only the high performance of the learning ability but also the reliability of the system with tactual information for recognizing various objects even though visual information has a defect. The experimental results show that the proposed system can improve recognition rate and reduce learning time. These results verify the effectiveness of the proposed sensor fusion system as recognition scheme of 3D object.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제11권4호
• /
• pp.280-285
• /
• 2011

Recently, with the development of service robots and the concept of ubiquitous, the position estimation of mobile objects has received great interest. Some of the localization schemes are introduced, which provide the relative location of the moving objects subjected to accumulated errors. To implement a real time localization system, a new absolute position estimation method for a mobile robot in indoor environment is proposed. Design and implementation of the localization system comes from the usage of active beacon systems (based upon RFID technology). The active beacon system is composed of an RFID receiver and an ultra-sonic transmitter. The RFID receiver gets the synchronization signal from the mobile robot and the ultra-sonic transmitter sends out the traveling signal to be used for measuring the distance. Position of a mobile robot in a three dimensional space can be calculated basically from the distance information from three beacons and the absolute position information of the beacons themselves. In some case, the mobile robot can acquire the ultrasonic signals from only one or two beacons, due to the obstacles located along the moving path. In this paper, a position estimation scheme using fewer than three sensors is developed. Also, the extended Kalman filter algorithm is applied for the improvement of position estimation accuracy of the mobile robot.

• 센서학회지
• /
• 제29권2호
• /
• pp.100-104
• /
• 2020

Thus far, several in vivo biosensing platforms have been proposed to measure the mechanical contractility of cultured cardiomyocytes. However, the low sensitivity and screening rate of the developed sensors severely limit their practical applications. In addition, intensive research and development in cardiovascular disease demand a high-throughput drug-screening platform based on biomimetic engineering. To overcome the drawbacks of the current state-of-the-art methods, we propose a high-throughput drug-screening platform based on 16 functional high-sensitivity well plates. The proposed system simulates the physiological accuracy of the heart function in an in vitro environment. We fabricated 64 cantilevers using highly flexible and optically transparent silicone rubber and placed in 16 independent wells. Nanogrooves were imprinted on the surface of the cantilever to promote cell alignment and maturation. The adverse effects of the cardiovascular drugs on the cultured cardiomyocytes were systematically investigated. The 64 cantilevers demonstrated a highly reliable and reproducible mechanical contractility of the drug-treated cardiomyocytes. Real-time high-throughput screening and simultaneous evaluation of the cardiomyocyte mechanical contractility under multiple drugs verified that the proposed system could be used as an efficient drugtoxicity test platform.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.766-769
• /
• 2005

In a ubiquitous environment made up of multiple sensors, most sensors participate in communications with limited battery, and the sensor node isn't able to participate in communications when all the battery is used up. When an existing authentication method is used for the sensor node which has to participate in a long term communication with limited battery, it creates a problem by making the length of network maintenance or sensor node's operation time relatively shorte. Therefore, a network structure where RM (Register Manager) node and AM (Authentication Manager) node are imported to solve the energy consumption problem during a communication process is presented in this thesis. This offers a low power protocol based on safety through a mutual authentication during communications. Through registration and authentication manager nodes, each sensor nodes are ensured of safety and the algorithm of key's generation, encryption/descramble and authentication is processed with faster operation speed. So the amount of electricity used up during the communications between sensor nodes has been evaluated. In case of the amount of electrical usage, an average of $34.783\%$ for the same subnet and 36.855 for communications with two different subnets, are reduced. The proposed method is a protocol which maintains the limited battery for a long time to increase the effectiveness of energy usage in sensor nodes and can also increase the participation rate of communication by sensor nodes.