• Structural Monitoring and Maintenance
• /
• 제7권2호
• /
• pp.109-124
• /
• 2020

Benefiting from the massive monitoring data collected by the Structural health monitoring (SHM) system, scholars can grasp the complex environmental effects and structural state during structure operation. However, the monitoring data is often missing due to sensor faults and other reasons. It is necessary to study the recovery method of missing monitoring data. Taking the structural temperature monitoring data of Nanjing Dashengguan Yangtze River Bridge as an example, the long short-term memory (LSTM) network-based recovery method for missing structural temperature data is proposed in this paper. Firstly, the prediction results of temperature data using LSTM network, support vector machine (SVM), and wavelet neural network (WNN) are compared to verify the accuracy advantage of LSTM network in predicting time series data (such as structural temperature). Secondly, the application of LSTM network in the recovery of missing structural temperature data is discussed in detail. The results show that: the LSTM network can effectively recover the missing structural temperature data; incorporating more intact sensor data as input will further improve the recovery effect of missing data; selecting the sensor data which has a higher correlation coefficient with the data we want to recover as the input can achieve higher accuracy.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• 제8권8호
• /
• pp.1755-1759
• /
• 2004

Digital watermarking technology is one of method of protecting property from the illegal reproduction of digital data. This technology inserts the specific data in a certain file to identify the property, that is an author and rights, not for human to be seen and heard. In this paper, the watermarking technology which inserts a RGB color watermark in a JPEG2000 color image using the visual characteristics of wavelet coefficient was proposed. After applying various attack at a watermarked image according to proposed technology, the likeness between the original image, the watermark and the extracted watermark was measured and investigated. As a result, the PSNR value of image was varied depending on perceptual parameter, but we can obtain 32dB as a whole.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• 제13권8호
• /
• pp.1497-1504
• /
• 2009

This Paper Propose a method to reduce the calculation time in JPEG2000. That is, if a coefficient is estimate a upper-level subband and its descendents skip the scan process. There is a trade-off relationship between the calculation time and the image quality or the amount of output data, the calculation time and the amount of output data decreases, but the image degradation increases. The experimental results showed that in calculation time was 35% in average, which means that ls ge ses. The ein calculation time and output data can be obtls ed with a cost of an acceptlble image quality degradation.

• Proceedings of the IEEK Conference
• /
• 대한전자공학회 2002년도 ITC-CSCC -2
• /
• pp.1228-1231
• /
• 2002

Digital image watermarking scheme using adaptive block division is proposed. To increase the perceptual invisibility, the image is divided into blocks by local properties and the human visual system (HVS), then the significant blocks are selected in the divided blocks. The significant coefficient is determined by Weber's law in these blocks. To increase the robustness, low frequency domains of the discrete cosine transform (DCT) and the discrete wavelet transform (DWT) are used. The watermark is embedded into the selected significant blocks of the DCT's and DWT's low frequency domains with adaptive watermark strengths. The watermark strength is determined by the variance and the local properties of the significant block. The experimental results prove that the proposed scheme has a good robustness against several image processing operations (e.g. median filtering, cropping, scaling, JPEG, JPEG2000, etc.) without significant degradation of the watermarked image.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• 제7권2호
• /
• pp.72-77
• /
• 2008

In this study, we propose and develop PDMS-based modular actuators. The microactuator which looks like a small insect uses thermal expansion power of the PDMS (polydimethylsiloxane; $sylgar^{(R)}$ 184 silicone elastomer). The PDMS-based microactuator provides a large displacement due to a high thermal expansion coefficient (approximately 310ppm). The microacruator with 1mm length $350{\mu}m$ width is optimized by using a numerical analysis. The shape of the PDMS actuatoris variously designed. They are placed at several positions to find the optimal position that provides a high transformation ratio. The PDMS-based microactuators are fabricated using a conventional micromaching technique. The fabricated microactuator is heated using a hot-plate. The actuator displacement is measured as a function of temperature from $27^{\circ}C$ to $300^{\circ}C$. The experimental results are compared to the simulation result. When heating temperature up to $300^{\circ}C$ is applied to the PDMS actuator, each V-groove-shaped joint is actuated $30{\mu}$ mat $300^{\circ}C$. Anotherdesign of the microactuator has a maximum displacement of about 656mm.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• 제58권12호
• /
• pp.2520-2528
• /
• 2009

In this paper, we proposed tracking detection methodology using information granulation-based fuzzy radial basis function neural networks (IG-FRBFNN). According to IEC 60112, tracking device is manufactured and utilized for experiment. We consider 12 features that can be used to decide whether tracking phenomenon happened or not. These features are considered by signal processing methods such as filtering, Fast Fourier Transform(FFT) and Wavelet. Such some effective features are used as the inputs of the IG-FRBFNN, the tracking phenomenon is confirmed by using the IG-FRBFNN. The learning of the premise and the consequent part of rules in the IG-FRBFNN is carried out by Fuzzy C-Means (FCM) clustering algorithm and weighted least squares method (WLSE), respectively. Also, Hierarchical Fair Competition-based Parallel Genetic Algorithm (HFC-PGA) is exploited to optimize the IG-FRBFNN. Effective features to be selected and the number of fuzzy rules, the order of polynomial of fuzzy rules, the fuzzification coefficient used in FCM are optimized by the HFC-PGA. Tracking inference engine is implemented by using the LabVIEW and loaded into embedded system. We show the superb performance and feasibility of the tracking detection system through some experiments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권3호
• /
• pp.539-557
• /
• 2013

A novel multifocus image fusion algorithm based on NSCT is proposed in this paper. In order to not only attain the image focusing properties and more visual information in the fused image, but also sensitive to the human visual perception, a local multidirection variance (LEOV) fusion rule is proposed for lowpass subband coefficient. In order to introduce more visual saliency, a modified local contrast is defined. In addition, according to the feature of distribution of highpass subband coefficients, a direction vector is proposed to constrain the modified local contrast and construct the new fusion rule for highpass subband coefficients selection The NSCT is a flexible multiscale, multidirection, and shift-invariant tool for image decomposition, which can be implemented via the atrous algorithm. The proposed fusion algorithm based on NSCT not only can prevent artifacts and erroneous from introducing into the fused image, but also can eliminate 'block effect' and 'frequency aliasing' phenomenon. Experimental results show that the proposed method achieved better fusion results than wavelet-based and CT-based fusion method in contrast and clarity.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 한국정보통신학회 2015년도 추계학술대회
• /
• pp.757-758
• /
• 2015

The digital watermark is one of important techniques to solve copyright authentication problems of digital media. Researches on the digital watermark are rapidly increasing in various media. The watermark system can resist some attacks such as signal attack, geometric attack and protocol attach. However, so far the robustness of the watermark needs to be improved. This paper suggests a watermarking technique with which a watermark is embedded on a coefficient of wavelet-based frequency band and extracted from it for protection of property rights and authentication of Blackfin processor-based digital sound. By carrying out hardware implementation of the suggested sound watermarking, the commercialization of protection of property rights and robustness of watermarks resulted from development of high-level programs can be confirmed.

• Earthquakes and Structures
• /
• 제8권4호
• /
• pp.821-841
• /
• 2015

This paper proposes a two-stage imaging approach for quantitative inspection of damages in metallic plates using the fundamental anti-symmetric mode of ($A_0$) Lamb wave. The proposed approach employs a number of transducers to transmit and receive $A_0$ Lamb wave pulses, and hence, to sequentially scan the plate structures before and after the presence of damage. The approach is applied to image the corrosion damages, which are simplified as a reduction of plate thickness in this study. In stage-one of the proposed approach a damage location image is reconstructed by analyzing the cross-correlation of the wavelet coefficient calculated from the excitation pulse and scattered wave signals for each transducer pairs to determine the damage location. In stage-two the Lamb wave diffraction tomography is then used to reconstruct a thickness reduction image for evaluating the size and depth of the damage. Finite element simulations are carried out to provide a comprehensive verification of the proposed imaging approach. A number of numerical case studies considering a circular transducer network with eight transducers are used to identify the damages with different locations, sizes and thicknesses. The results show that the proposed methodology is able to accurately identify the damage locations with inaccuracy of the order of few millimeters of a circular inspection area of $100mm^2$ and provide a reasonable estimation of the size and depth of the damages.

• The Journal of the Korea institute of electronic communication sciences
• /
• 제5권3호
• /
• pp.309-314
• /
• 2010

In this paper, an intelligent security camera over internet is proposed. Among ISC methods, watersheds based methods produce a good performance in segmentation accuracy. But traditional watershed transform has been suffered from over-segmentation due to small local minima included in gradient image that is input to the watershed transform. And a zone face candidates of detection using skin-color model. last step, face to check at face of candidate location using SVM method. It is extract of wavelet transform coefficient to the zone face candidated. Therefore, it is likely that it is applicable to read world problem, such as object tracking, surveillance, and human computer interface application etc.