• 전기전자학회논문지
• /
• 제23권4호
• /
• pp.1166-1174
• /
• 2019

이 논문에서는 사람 재식별 모델인 PersonNet의 성능을 개선하는 방법을 제안하고 실험한다. 특징점 추출을 위해 인셉션 레이어를 접목하여, 기존 32개의 특징점을 154개로 증가시켜 강화하였다. 또한, PersonNet에서 사용하는 CND 방식을 수정하여 비대칭성을 완화하였고, 보행자 이미지의 특징점을 3부분으로 나누어 가중치를 적용한 방법을 적용하여 특징을 더 뚜렷하게 파악하도록 하였다. 성능 평가를 위해 CUHK01, CUHK03 그리고 Market-1501 3가지의 데이터베이스를 사용하였고 실험 결과 27~31% 성능이 개선되었다.

• 혜화의학회지
• /
• 제19권2호
• /
• pp.35-42
• /
• 2011

The purpose of this study is to evaluate the difference about pathogenesis of skin type. the theory that explains each individual react to certain stress is generally accepted in traditional oriental medicine. The aim of this experiment is to find out relationship between the effect of facial condition and the vital conditions of traditional Oriental medicine. We recognized that pattern identification of fluid-humor could be divided into 4 different groups. The reason is that the fluid-humor could be interpreted as Qi & Blood, furthermore Qi & Blood were categorized into deficiency and excess groups. Korean female volunteers in good health participated in this experiment. Three doctors of Oriental medicine classified them into 4 groups based on qi-blood and deficiency-excess concept(qi-deficiency; qi-excess:qi-stagnation; blood-deficiency; blood-excess:static-blood). Volunteers were assessed with non-invasive skin measuring devices. And we analyzed the correlation of skin physiological parameters with vital conditions; moisture, sebum and elasticity. Measurement moisture and sebum of facial skin tended to deacease only in static blood group.

• 센서학회지
• /
• 제25권6호
• /
• pp.431-434
• /
• 2016

Currently, the radial basis function network (RBFN) and various other neural networks are employed to classify gases using chemical sensors arrays, and their performance is steadily improving. In particular, the identification performance of the RBFN algorithm is being improved by optimizing parameters such as the center, width, and weight, and improved algorithms such as the radial basis function network-stochastic gradient (RBFN-SG) and radial basis function network-normalized stochastic gradient (RBFN-NSG) have been announced. In this study, we optimized the number of centers, which is one of the parameters of the RBFN-NSG algorithm, and observed the change in the identification performance. For the experiment, repeated measurement data of 8 samples were used, and the elbow method was applied to determine the optimal number of centers for each sample of input data. The experiment was carried out in two cases(the only one center per sample and the optimal number of centers obtained by elbow method), and the experimental results were compared using the mean square error (MSE). From the results of the experiments, we observed that the case having an optimal number of centers, obtained using the elbow method, showed a better identification performance than that without any optimization.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2005년도 추계학술대회 논문집
• /
• pp.169-174
• /
• 2005

AIS(Automatic Identification System)는 선박의 항해안전 및 실시간 모니터링을 위하여 국제해사기구(IMO)에서 채택한 것으로서 선박의 제원 및 운항정보를 선박-선박/육상 간에 자동 송수신 하는 장치이다. 연안해역의 관제, 수색 및 구조지원, 선박통항관제 수단을 제공하여 주는 유용한 장비이다. 본 연구에서는 AIS 장비를 항로표지에 설치하여 항로표지에 대한 실시간 정보를 수집하거나 감시 및 제어 또한 이를 직접 선박에 제공하기 위한 실시간 유비쿼터스 재상표지시설의 구축을 위하여 실시한 해상실험을 결과를 분석하여 구축을 위한방안을 제안 하고자 한다.

• Smart Structures and Systems
• /
• 제16권1호
• /
• pp.47-65
• /
• 2015

A novel finite element (FE) model updating method based on multi-resolution analysis (MRA) is proposed. The true stiffness of the FE model is considered as the superposition of two pieces of stiffness information of different resolutions: the pre-defined stiffness information and updating stiffness information. While the resolution of former is solely decided by the meshing density of the FE model, the resolution of latter is decided by the limited information obtained from the experiment. The latter resolution is considerably lower than the former. Second generation wavelet is adopted to describe the updating stiffness information in the framework of MRA. This updating stiffness in MRA is realized at low level of resolution, therefore, needs less number of updating parameters. The efficiency of the optimization process is thus enhanced. The proposed method is suitable for the identification of multiple irregular cracks and performs well in capturing the global features of the structural damage. After the global features are identified, a refinement process proposed in the paper can be carried out to improve the performance of the MRA of the updating information. The effectiveness of the method is verified by numerical simulations of a box girder and the experiment of a three-span continues pre-stressed concrete bridge. It is shown that the proposed method corresponds well to the global features of the structural damage and is stable against the perturbation of modal parameters and small variations of the damage.

• 대한임베디드공학회논문지
• /
• 제12권2호
• /
• pp.79-88
• /
• 2017

One of the important applications of activity sensing in the home is energy monitoring. Many previous methodologies for detecting and recognizing household appliances have been proposed. This paper presents an approach that uses an energy metering circuit (EMC) to classify and identify the various electrical devices in home based on root-mean-square (RMS) consumed current value. EMC gathers the RMS current values created by appliance state transition (e.g., on to off) and apparatus operating process. In this paper, an identification algorithm is proposed to detect a change in current levels using the standard deviation of current signals and their average values. In addition, characteristic of the appliance is extracted concerning four feature parameters concerning the number of current levels, the minimum level, the maximum level, and signal-to-noise ratio (SNR) of them. Experiment results validate the reliable performance of the proposed identification method for 11 representative appliances.

• 대한의용생체공학회:의공학회지
• /
• 제16권3호
• /
• pp.317-324
• /
• 1995

A need exists for the accurate identification of time series models having time varying parameters, as is important in the case of real time identification of nonstationary EMG signal. Thls paper describes real time identification and muscle fatigue monitoring method of nonstationary EMG signal. The method is composed of the efficient identifier which estimates the autoregressive parameters of nonstationary EMG signal model, and its real time implementation by using T805 parallel processing computer. The method is verified through experiment with real EMG signals which are obtained from surface electrode. As a result, the proposed method provides a new approach for real time Implementation of muscle fatigue monitoring and the execution time is 0.894ms/sample for 1024Hz EMG signal.

• Journal of Information Processing Systems
• /
• 제14권2호
• /
• pp.435-447
• /
• 2018

Fingerprint-based biometric identification is one of the most interesting automatic systems for identifying individuals. Owing to the poor sensing environment and poor quality of skin, biometrics remains a challenging problem. The main contribution of this paper is to propose a new approach to recognizing a person's fingerprint using the fingerprint's local characteristics. The proposed approach introduces the barycenter notion applied to triangles formed by the Delaunay triangulation once the extraction of minutiae is achieved. This ensures the exact location of similar triangles generated by the Delaunay triangulation in the recognition process. The results of an experiment conducted on a challenging public database (i.e., FVC2004) show significant improvement with regard to fingerprint identification compared to simple Delaunay triangulation, and the obtained results are very encouraging.

• 제어로봇시스템학회논문지
• /
• 제16권12호
• /
• pp.1189-1196
• /
• 2010

This paper provides an identification method for three-parameter models i.e. first order with dead time models and second order with dead time models. The proposed identification method is based on step response and can be easily implemented using digital microprocessors. The proposed method first identifies the order of the plant i.e. first order or second order from the behavior of the plant with constant input. After the order of the plant is determined, a test step input is applied to the system and the three parameters of the plant are obtained from the corresponding response of the plant. The output of the plant need not to be zero when the test signal is applied. The efficacy of proposed algorithms is verified through simulation and experiment.

• 소음진동
• /
• 제6권6호
• /
• pp.835-842
• /
• 1996

To identify the locations and strengths of acoustic sources, one may use a microphone line array. Apparent advantage of the source identification method utilizing a line array is that it requires less measurement points than intensity method and holography. This method is based on the information of magnitude and phase difference between pressure signals at each microphone. Since those differences are dependent on the source model, we have to assume them such as plane, monopole, etc. In this paper the conventional source identification methods such as beamforming method and MUSIC method are briefly reviewed by modeling a source as plane and spherical wave, then a modified method is introduced. This can be applied to sound field which may by either coherent or incoherent. Typical simulations and experiment are performed to confirm this identification method.