• 정보처리학회논문지B
• /
• 제17B권1호
• /
• pp.9-14
• /
• 2010

본 논문에서는 다중 센서를 선택하는 냄새 인식 시스템에서 최적의 센서 조합을 선택하기 위하여 통계적 분석 기반의 센서 사이의 상관계수를 이용하는 방법을 제안한다. 제안하는 센서 결정 방법은 금속 산화물 반도체(Metal Oxide Semiconductor : MOS) 센서 어레이를 사용하여 냄새 데이터를 획득한 후 획득한 냄새의 상관도를 기반으로 적합한 센서를 결정한다. 우선 측정 대상이 유사한 MOS 가스센서 중 응답의 크기가 작고 변화가 낮은 센서를 제외하여 총 16개의 센서를 선별한다. 입력되는 냄새로부터 16개의 센서를 사용하여 냄새 DB를 구축하고 각 센서별 상관계수를 계산한 후 상관도가 낮은 센서를 선택한다. 선택된 센서는 유사한 응답 특성을 갖는 센서를 제거한 것이며 제안한 방법으로 최적의 센서를 결정 할 수 있다. 제안된 센서 결정 방법의 성능 평가를 위해 꽃 냄새 인식 시스템에 적용하였다. 상관계수를 이용한 꽃 냄새 인식 시스템에 제안한 방법을 적용한 결과로 16개의 센서를 사용할 경우 95.67%의 인식률을 보이는 반면 제안한 센서 결정 방법을 적용한 꽃 냄새 인식 시스템은 6개를 사용한 경우 94.67%, 8개의 센서를 사용한 경우 96%의 인식률을 도출하는 것을 확인하였다.

• 디지털산업정보학회논문지
• /
• 제6권4호
• /
• pp.33-43
• /
• 2010

In this paper, we propose a floral scent recognition using odor sensors and a odor display using odor distribution system. Proposed odor recognition has method of correlation coefficient between sensors that select optimal sensors in floral scent recognition system of selective multi-sensors. Proposed floral scent recognition system consists of four module such as floral scent acquisition module, optimal sensor decision module, entropy-based floral scent detection module, and floral scent recognition module. Odor distribution system consists of generation module of distribution information, control module of distribution, output module of distribution. We applied to floral scent recognition for performance evaluation of proposed sensors decision method. As a result, application of proposed method with floral scent recognition obtained recognition rate of 95.67% case of using 16 sensors while applied floral scent recognition system of proposed sensor decision method confirmed recognition rate of 96% using only 8 sensors. Also, we applied to odor display of proposed method and obtained 3.18 thorough MOS experimentation.

• Journal of Communications and Networks
• /
• 제11권4호
• /
• pp.350-358
• /
• 2009

In a wireless sensor network (WSN) setting, this paper presents a distributed decision-making framework and illustrates its application in an online structural health monitoring (SHM) system. The objective is to recover a damage severity vector, which identifies, localizes, and quantifies damages in a structure, via distributive and collaborative decision-making among wireless sensors. Observing the fact that damages are generally scarce in a structure, this paper develops a nonlinear 0-norm minimization formulation to recover the sparse damage severity vector, then relaxes it to a linear and distributively tractable one. An optimal algorithm based on the alternating direction method of multipliers (ADMM) and a heuristic distributed linear programming (DLP) algorithm are proposed to estimate the damage severity vector distributively. By limiting sensors to exchange information among neighboring sensors, the distributed decision-making algorithms reduce communication costs, thus alleviate the channel interference and prolong the network lifetime. Simulation results in monitoring a steel frame structure prove the effectiveness of the proposed algorithms.

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 2001년도 The Seoul International Simulation Conference
• /
• pp.301-305
• /
• 2001

A novel approach based on parameters estimation is presented far fault detection and diagnosis in sensors. Based on known precise parameter of normal working sensors system model is built from real laboratory inputs-outputs data, sequentially residual serial is obtained. Where decision-making rule of detection the fault is given via the use of beys theory, whilst a filter least-square computative algorithm for estimating fault parameters is given. The algorithm is a fast and accurate to calculate value of sensors faults when system model contains noise and sensors outputs contain measured noise. The method can solve both gain type and bias type fault in sensors. Simulated numerical example is included to demonstrate the use of the proposed approaches.

• 전기학회논문지P
• /
• 제56권1호
• /
• pp.56-62
• /
• 2007

In this paper, design method for power tower hazard diagnosis/predition system based on UsN was proposed. The proposed method used multi-hybrid sensors to measure rotation, displacement, and inclination state of power tower, and made decision/prediction of hazard of power tower. System design was made with requirement analysis of monitoring for transmission power facility and use of MEMS and optic fiber sensors. For hazard decision, analysis of correlation was made using sensor output. LN based on IEC61850,international standard for digital substation, was also proposed. For transmission facility monitoring, digital substation and power tower were considered as parts of power facility networks.

• 한국태양에너지학회 논문집
• /
• 제37권2호
• /
• pp.23-33
• /
• 2017

Accurate prediction of stochastic behavior of occupants is a well known problem for improving prediction performance of building energy use. Many researchers have been tried various sensors that have information on the status of occupant such as $CO_2$ sensor, infrared motion detector, RFID etc. to predict occupants, while others have been developed some algorithm to find occupancy probability with those sensors or some indirect monitoring data such as energy consumption in spaces. In this research, various sensor data and energy consumption data are utilized for decision tree algorithms (C4.5 & CART) for estimation of sub-hourly occupancy status. Although the experiment is limited by space (private room) and period (cooling season), the prediction result shows good agreement of above 95% accuracy when energy consumption data are used instead of measured $CO_2$ value. This result indicates potential of IoT data for awareness of indoor environmental status.

• 한국군사과학기술학회지
• /
• 제15권1호
• /
• pp.1-8
• /
• 2012

Obstacle detection is much studied by using sensors such as laser, vision, radar and ultrasonic in path planning for UGV(Unmanned Ground Vehicle), but not much reported about its characterization. In this paper not only an obstacle classification method using 2-dimensional LMS(Laser Measurement System) but also a decision making method whether to avoid or traverse the obstacle is proposed. The basic idea of decision making is to classify the characteristics by 2D laser scanned data and intensity data. Roughness features are obtained by range data using a simple linear regression model. The standard deviations of roughness and intensity data are used as measures for decision making by comparing with those of reference data. The obstacle classification and decision making for the UGV can facilitate a short path to the target position and the survivability of the robot.

• 제어로봇시스템학회논문지
• /
• 제6권1호
• /
• pp.112-119
• /
• 2000

A die-casting junction method is usually used to manufacture the tub of an IH(induction heating) jar. If there is a very small air bubble in the junction area, the thermal conductivity is deteriorated and local overheat occurs. Such problem brings serious inferiority of the IH jar. In this paper, we propose a new method to detect such defect with simply measured thermal data. Thermal distribution of preheated tubs is obtained by scanning with infrared thermal sensors and analyzed with the statistic pattern recognition method. By defining the characteristic feature as the temperature difference between sensors and using ellipsoid function as decision boundary, a supervised learning method of genetic algorithm is proposed to obtain the required parpameters. After applying the proposed method to experiment, we have proved that the rate of recognition is high even for a small number of data set.

• 대한산업공학회지
• /
• 제37권3호
• /
• pp.180-190
• /
• 2011

Efficient energy consumption is a critical factor for deployment and operation of wireless sensor networks (WSNs). To achieve energy efficiency there have been several hierarchical routing protocols that organize sensors into clusters where one sensor is a cluster-head to forward messages received from its cluster-member sensors to the base station of the WSN. In this paper, we propose a self-organized clustering method for cluster-head selection and cluster based routing for a WSN. To select cluster-heads and organize clustermembers for each cluster, every sensor uses only local information and simple decision mechanisms which are aimed at configuring a self-organized system. By these self-organized interactions among sensors and selforganized selection of cluster-heads, the suggested method can form clusters for a WSN and decide routing paths energy efficiently. We compare our clustering method with a clustering method that is a well known routing protocol for the WSNs. In our computational experiments, we show that the energy consumptions and the lifetimes of our method are better than those of the compared method. The experiments also shows that the suggested method demonstrate properly some self-organized properties such as robustness and adaptability against uncertainty for WSN's.

• IEIE Transactions on Smart Processing and Computing
• /
• 제6권4호
• /
• pp.281-291
• /
• 2017

Nowadays, as traffic jams are a daily elementary problem in both developed and developing countries, systems to monitor, predict, and detect traffic conditions are playing an important role in research fields. Comparing them, researchers have been trying to solve problems by applying many kinds of technologies, especially roadside sensors, which still have some issues, and for that reason, any one particular method by itself could not generate sufficient traffic prediction results. However, these sensors have some issues that are not useful for research. Therefore, it may not be best to use them as stand-alone methods for a traffic prediction system. On that note, this paper mainly focuses on predicting traffic conditions based on a hybrid prediction approach, which stands on accuracy comparison of three prediction models: multinomial logistic regression, decision trees, and support vector machine (SVM) classifiers. This is aimed at selecting the most suitable approach by means of integrating proficiencies from these approaches. It was also experimentally confirmed, with test cases and simulations that showed the performance of this hybrid method is more effective than individual methods.