• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2013.10a
• /
• pp.338-345
• /
• 2013

Induction motors play an increasing importance in industrial manufacturing. Therefore, the state monitoring systems also have been considering as the key in dealing with their negative effect by absorbing faulty symptoms in motors. There are numerous proposed systems in literature, in which, several kinds of signals are utilized as the input. To solve the multiple faults problem of induction motors, like the proposed system, the vibration signals is good candidate. In this study, a new signal processing scheme was utilized, which transforms the time domain vibration signal into the spatial domain as an image. Then the spatial features of converted image then have been extracted by applying the dominant neighbourhood structure (DNS) algorithm. In addition, these feature vectors were evaluated to obtain the fruitful dimensions, which support to discriminate between states of motors. Because of reliability, the conventional one-against-all (OAA) multi-class support vector machines (MCSVM) have been utilized in the proposed system as classifier module. Even though examined in severity levels of signal-to-noise ratio (SNR), up to 15dB, the proposed system still reliable in term of two criteria: true positive (TF) and false positive (FP). Furthermore, it also offers better performance than five state-of-the-art systems.

• Journal of the Korean Society for Precision Engineering
• /
• v.15 no.11
• /
• pp.152-165
• /
• 1998

This study proposes the analysis and evaluation method of time series ultrasonic signal using the chaoral post-process system for precision rate enhancement of ultrasonic pattern recognition. Chaos features extracted from time series data for analysis quantitatively weld defects For this purpose, feature extraction objectives in this study are fractal dimension, Lyapunov exponent, shape of strange attrator. Trajectory changes in the strange attractor indicated that even same type of defects carried substantial difference in chaoticity resulting from distance shifts such as nearby 0.5, 1.0 skip distance. Such difference in chaoticity enables the evaluation of unique features of defects in the weld zone. In quantitative chaos fenture extraction, feature values of 0.835 and 0.823 in the case of slag inclusion and 0.609 and 0.573 in the case of crack were suggested on the basis of fractal dimension and Lyapunov exponent. Proposed chaoral post-process system in this study can enhances precision rate of ultrasonic pattern recognition results from defect signals of weld zone, such as slag inclusion and crack.

• Journal of Korea Multimedia Society
• /
• v.24 no.2
• /
• pp.178-185
• /
• 2021

Three-dimensional high-resolution magnetic resonance imaging (MRI) provides fine-level anatomical information for disease diagnosis. However, there is a limitation in obtaining high resolution due to the long scan time for wide spatial coverage. Therefore, in order to obtain a clear high-resolution(HR) image in a wide spatial coverage, a super-resolution technology that converts a low-resolution(LR) MRI image into a high-resolution is required. In this paper, we propose a super-resolution technique through filter learning based on information on the surrounding gradient information in 3D space from 3D MRI images. In the learning step, the gradient features of each voxel are computed through eigen-decomposition from 3D patch. Based on these features, we get the learned filters that minimize the difference of intensity between pairs of LR and HR images for similar features. In test step, the gradient feature of the patch is obtained for each voxel, and the filter is applied by selecting a filter corresponding to the feature closest to it. As a result of learning 100 T1 brain MRI images of HCP which is publicly opened, we showed that the performance improved by up to about 11% compared to the traditional interpolation method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.9
• /
• pp.2882-2903
• /
• 2022

Image super-resolution (SR) processing is of great value in the fields of digital image processing, intelligent security, film and television production and so on. This paper proposed a densely connected deep learning network based on cascade architecture, which can be used to solve the problem of super-resolution in the field of image quality enhancement. We proposed a more efficient residual scaling dense block (RSDB) and the multi-channel cascade architecture to realize more efficient feature reuse. Also we proposed a hybrid loss function based on L₁ error and L_∞ error to achieve better L_∞ error performance. The experimental results show that the overall performance of the network is effectively improved on cascade architecture and residual scaling. Compared with the residual dense net (RDN), the PSNR / SSIM of the new method is improved by 2.24% / 1.44% respectively, and the L_∞ performance is improved by 3.64%. It shows that the cascade connection and residual scaling method can effectively realize feature reuse, improving the residual convergence speed and learning efficiency of our network. The L_∞ performance is improved by 11.09% with only a minimal loses of 1.14% / 0.60% on PSNR / SSIM performance after adopting the new loss function. That is to say, the L_∞ performance can be improved greatly on the new loss function with a minor loss of PSNR / SSIM performance, which is of great value in L_∞ error sensitive tasks.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.2
• /
• pp.66.1-66.1
• /
• 2021

Extinction curves observed toward individual Active Galactic Nuclei (AGN) usually show a steep rise toward Far-Ultraviolet (FUV) wavelengths and can be described by the Small Magellanic Cloud (SMC)-like dust model. This feature suggests the dominance of small dust grains of size a < 0.1 ㎛ in the local environment of AGN, but the origin of such small grains is unclear. In this paper, we aim to explain this observed feature by applying the RAdiative Torque Disruption (RATD) to model the extinction of AGN radiation from FUV to Mid-Infrared (MIR) wavelengths. We find that in the intense radiation field of AGN, large composite grains of size a > 0.1 ㎛ are significantly disrupted to smaller sizes by RATD up to dRATD > 100 pc in the polar direction and dRATD ~ 10 pc in the torus region. Consequently, optical-MIR extinction decreases, whereas FUV-near-Ultraviolet extinction increases, producing a steep far-UV rise extinction curve. The resulting total-to selective visual extinction ratio thus significantly drops to RV < 3.1 with decreasing distances to AGN center due to the enhancement of small grains. The dependence of RV with the efficiency of RATD will help us to study the dust properties in the AGN environment via photometric observations. In addition, we suggest that the combination of the strength between RATD and other dust destruction mechanisms that are responsible for destroying very small grains of a <0.05 ㎛ is the key for explaining the dichotomy observed "SMC" and "gray" extinction curve toward many AGN.

• Journal of Information Processing Systems
• /
• v.19 no.6
• /
• pp.842-857
• /
• 2023

Currently, most sentiment classification models on microblogging platforms analyze sentence parts of speech and emoticons without comprehending users' emotional inclinations and grasping moral nuances. This study proposes a hybrid sentiment analysis model. Given the distinct nature of microblog comments, the model employs a combined stop-word list and word2vec for word vectorization. To mitigate local information loss, the TextCNN model, devoid of pooling layers, is employed for local feature extraction, while BiLSTM is utilized for contextual feature extraction in deep learning. Subsequently, microblog comment sentiments are categorized using a classification layer. Given the binary classification task at the output layer and the numerous hidden layers within BiLSTM, the Tanh activation function is adopted in this model. Experimental findings demonstrate that the enhanced TextCNN-BiLSTM model attains a precision of 94.75%. This represents a 1.21%, 1.25%, and 1.25% enhancement in precision, recall, and F1 values, respectively, in comparison to the individual deep learning models TextCNN. Furthermore, it outperforms BiLSTM by 0.78%, 0.9%, and 0.9% in precision, recall, and F1 values.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.35 no.2 s.121
• /
• pp.25-36
• /
• 2007

This case study offers fundamental data for the research and construction of future of water. It also provides an understanding of the design and characteristics of the existing water bodies in urban parks. This study was begun by conducting field research on the completion of the construction of 67 different urban parks located in the downtown areas of the following cities: Gimhae, Yangsan, Changwon, Masan, and Jinju. The field research was conducted from July to October of 2006. Additional research was performed in July of 2007. Construction trends were examined and the design and characteristics of the types of locations, shapes, scales, materials, and added objects for the enhancement of recreational value of the 31 water bodies constructed in 18 urban parks out of the 67 were analyzed. According to the results of the study, the most common design feature was a fountain that shot up. The bodies of water were designed by using a simple technique in accordance with the basic principles of location, shape, size, materials, and added objects for the enhancement of recreational value, with the exception of a few different factors in the research subjects. In conclusion, it can be recommended that further research be conducted in the consideration and various plans of location, shape, size, materials, and added objects for the enhancement of recreational value of future constructions of water bodies in urban parks in order to offer a more pleasant environment to the users.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.3
• /
• pp.371-380
• /
• 2011

The noise caused by a variety of reasons worsens the quality of input image when we use the images reproducing device. The basic difficulty to solve this problem is that the noise and the signal are difficult to be distinguished. Contrast enhancement such as unsharp masking is one of the most important procedures to improve the quality of input images. The conventional unsharp masking enhances the images by adding their amplified high frequency components. The noise component of the input images, however, also tends to be amplified due to the nature of the unsharp masking. This paper considers the block approach for detecting niose and image feature of the input image so that the unsharp masking could be adaptively applied accordingly. Simulation results show that it is made possible to enhance contrast of the image without boosting up the noisy components by applying the proposed algorithm.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.15 no.5
• /
• pp.227-234
• /
• 2020

In this paper, we propose wav-U-Net to improve speech enhancement in heavy noisy environments, and it has implemented three principal techniques. First, as input data, we use 128 modified Mel-scale filter banks which can reduce computational burden instead of 512 frequency bins. Mel-scale aims to mimic the non-linear human ear perception of sound by being more discriminative at lower frequencies and less discriminative at higher frequencies. Therefore, Mel-scale is the suitable feature considering both performance and computing power because our proposed network focuses on speech signals. Second, we add a simple ResNet as pre-processing that helps our proposed network make estimated speech signals clear and suppress high-frequency noises. Finally, the proposed U-Net model shows significant performance regardless of the kinds of noise. Especially, despite using a single channel, we confirmed that it can well deal with non-stationary noises whose frequency properties are dynamically changed, and it is possible to estimate speech signals from noisy speech signals even in extremely noisy environments where noises are much lauder than speech (less than SNR 0dB). The performance on our proposed wav-U-Net was improved by about 200% on SDR and 460% on NSDR compared to the conventional Jansson's wav-U-Net. Also, it was confirmed that the processing time of out wav-U-Net with 128 modified Mel-scale filter banks was about 2.7 times faster than the common wav-U-Net with 512 frequency bins as input values.

• Journal of Korea Multimedia Society
• /
• v.8 no.8
• /
• pp.1069-1079
• /
• 2005

Though there have been many methods to detect features in spatial domain, in the case of a compressed image it has to be decoded, processed and encoded again. Alternatively, we can manipulate a compressed image directly in the Discrete Cosine Transform (DCT) domain that has been used for compressing videos or images in the standards like MPEG and JPEG. In our previous work we proposed a model-based discontinuity evaluation technique in the DCT domain that had problems in the rotated or non-ideal discontinuities. In this paper, we propose a fuzzy filtering technique that consists of height fuzzification, direction fuzzification, and forty filtering of discontinuities. The enhancement achieved by the fuzzy tittering includes the linking, thinning, and smoothing of discontinuities in the DCT domain. Although the detected discontinuities are rough in a low-resolution image for the size (8${\times}$8 pixels) of the DCT block, experimental results show that this technique is fast and stable to enhance the qualify of discontinuities.