• ETRI Journal
• /
• 제43권2호
• /
• pp.184-196
• /
• 2021

The research domain of underwater communication has garnered much interest among researchers exploring underwater activities. The underwater environment differs from the terrestrial setting. Some of the main challenges in underwater communication are limited bandwidth, low data rate, propagation delay, and high bit error rate (BER). As such, this study assessed the underwater acoustic (UWA) aspect and explored the expression of error performance based on t-distribution noise. Filter orthogonal frequency-division multiplexing refers to a new waveform candidate that has been adopted in UWA, along with turbo and polar codes. The empirical outcomes demonstrated that the noise did not adhere to Gaussian distribution, whereas the simulation results revealed that the filter applied in orthogonal frequency-division multiplexing could significantly suppress out-of-band emission. Additionally, the performance of the turbo code was superior to that of the polar code by 2 dB at BER 10-3.

• International Journal of Computer Science & Network Security
• /
• 제21권12spc호
• /
• pp.556-564
• /
• 2021

Numerous spatial and transform-domain-based conventional denoising algorithms struggle to keep critical and minute structural features of the image, especially at high noise levels. Although neural network approaches are effective, they are not always reliable since they demand a large quantity of training data, are computationally complicated, and take a long time to construct the model. A new framework of enhanced hybrid filtering is developed for denoising color images tainted by additive white Gaussian Noise with the goal of reducing algorithmic complexity and improving performance. In the first stage of the proposed approach, the noisy image is refined using a high-dimensional non-local means filter based on Principal Component Analysis, followed by the extraction of the method noise. The wavelet transform and SURE Shrink techniques are used to further culture this method noise. The final denoised image is created by combining the results of these two steps. Experiments were carried out on a set of standard color images corrupted by Gaussian noise with multiple standard deviations. Comparative analysis of empirical outcome indicates that the proposed method outperforms leading-edge denoising strategies in terms of consistency and performance while maintaining the visual quality. This algorithm ensures homogeneous noise reduction, which is almost independent of noise variations. The power of both the spatial and transform domains is harnessed in this multi realm consolidation technique. Rather than processing individual colors, it works directly on the multispectral image. Uses minimal resources and produces superior quality output in the optimal execution time.

• 대한의용생체공학회:의공학회지
• /
• 제28권2호
• /
• pp.199-204
• /
• 2007

In digital radiography, to improve the contrast of digital radiography image, the multi-scale nonlinear amplification algorithm based on unsharp masking is one of the major image enhancement algorithms. In this paper, we used the Laplacian pyramid to decompose a digital radiography(DR) image. In our simulation, the DR image was decomposed into seven layers and the coefficients of the each layer was amplified with nonlinear function. We also imported a noise containment algorithm to limit noise amplification. To enhance the contrast of image, we proposed a new adaptive non-linear gain amplification coefficients. As a result of having applied to some clinical data, a detail visibility was improved significantly without unacceptable noise boosting. Images that acquired with the proposed adaptive non-linear gain coefficients have shown superior quality to those that applied similar gain control method and expected to be accepted in the clinical applications.

• Communications for Statistical Applications and Methods
• /
• 제30권6호
• /
• pp.589-603
• /
• 2023

Deep generative models target to infer the underlying true data distribution, and it leads to a huge success in generating fake-but-realistic data. Regarding such a perspective, the data attributes can be a crucial factor in the data generation process since non-existent counterfactual samples can be generated by altering certain factors. For example, we can generate new portrait images by flipping the gender attribute or altering the hair color attributes. This paper proposes counterfactual disentangled variational autoencoder generative adversarial networks (CDVAE-GAN), specialized for data attribute level counterfactual data generation. The structure of the proposed CDVAE-GAN consists of variational autoencoders and generative adversarial networks. Specifically, we adopt a Gaussian variational autoencoder to extract low-dimensional disentangled data features and auxiliary Bernoulli latent variables to model the data attributes separately. Also, we utilize a generative adversarial network to generate data with high fidelity. By enjoying the benefits of the variational autoencoder with the additional Bernoulli latent variables and the generative adversarial network, the proposed CDVAE-GAN can control the data attributes, and it enables producing counterfactual data. Our experimental result on the CelebA dataset qualitatively shows that the generated samples from CDVAE-GAN are realistic. Also, the quantitative results support that the proposed model can produce data that can deceive other machine learning classifiers with the altered data attributes.

• Investigative Magnetic Resonance Imaging
• /
• 제26권2호
• /
• pp.104-116
• /
• 2022

The purpose of this study is to systematically determine an optimal percentile cut-off in histogram analysis for calculating the mean parameters obtained from a non-Gaussian continuous-time random-walk (CTRW) diffusion model for differentiating individual glioma grades. This retrospective study included 90 patients with histopathologically proven gliomas (42 grade II, 19 grade III, and 29 grade IV). We performed diffusion-weighted imaging using 17 b-values (0-4000 s/mm²) at 3T, and analyzed the images with the CTRW model to produce an anomalous diffusion coefficient (D_m) along with temporal (𝛼) and spatial (𝛽) diffusion heterogeneity parameters. Given the tumor ROIs, we created a histogram of each parameter; computed the P-values (using a Student's t-test) for the statistical differences in the mean D_m, 𝛼, or 𝛽 for differentiating grade II vs. grade III gliomas and grade III vs. grade IV gliomas at different percentiles (1% to 100%); and selected the highest percentile with P < 0.05 as the optimal percentile. We used the mean parameter values calculated from the optimal percentile cut-offs to do a receiver operating characteristic (ROC) analysis based on individual parameters or their combinations. We compared the results with those obtained by averaging data over the entire region of interest (i.e., 100th percentile). We found the optimal percentiles for D_m, 𝛼, and 𝛽 to be 68%, 75%, and 100% for differentiating grade II vs. III and 58%, 19%, and 100% for differentiating grade III vs. IV gliomas, respectively. The optimal percentile cut-offs outperformed the entire-ROI-based analysis in sensitivity (0.761 vs. 0.690), specificity (0.578 vs. 0.526), accuracy (0.704 vs. 0.639), and AUC (0.671 vs. 0.599) for grade II vs. III differentiations and in sensitivity (0.789 vs. 0.578) and AUC (0.637 vs. 0.620) for grade III vs. IV differentiations, respectively. Percentile-based histogram analysis, coupled with the multi-parametric approach enabled by the CTRW diffusion model using high b-values, can improve glioma grading.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.270-272
• /
• 2006

In this paper, we discuss optimal design of Fuzzy Polynomial Neural Networks by means of Genetic Algorithms(GAs) using symbolic coding for non-linear data. One of the major subject of genetic algorithms is representation of chromosomes. The proposed model optimized by the means genetic algorithms which used symbolic code to represent chromosomes. The proposed gFPNN used a triangle and a Gaussian-like membership function in premise part of rules and design the consequent structure by constant and regression polynomial (linear, quadratic and modified quadratic) function between input and output variables. The performance of the proposed model is quantified through experimentation that exploits standard data already used in fuzzy modeling. These results reveal superiority of the proposed networks over the existing fuzzy and neural models.

• Journal of applied mathematics & informatics
• /
• 제18권1_2호
• /
• pp.205-228
• /
• 2005

Let I(f) be the integral defined by : $I(f) = \int\limits_{a}^{b} f(x)w(x)dx$ with f a given function, w a nonclassical weight function and [a, b] an interval of IR (of finite or infinite length). We propose to calculate the approximate value of I(f) by using a new scheme for deriving a non-linear system, satisfied by the three-term recurrence coefficients of semi-classical orthogonal polynomials. Finally we studies the Stability and complexity of this scheme.

• 대한음성학회지:말소리
• /
• 제63호
• /
• pp.139-151
• /
• 2007

As the Internet becomes prevalent in our lives, harmful contents, such as phornographic videos, have been increasing on the Internet, which has become a very serious problem. To prevent such an event, there are many filtering systems mainly based on the keyword-or image-based methods. The main purpose of this paper is to devise a system that classifies pornographic videos based on the audio information. We use the mel-cepstrum modulation energy (MCME) which is a modulation energy calculated on the time trajectory of the mel-frequency cepstral coefficients (MFCC) as well as the MFCC as the feature vector. For the classifier, we use the well-known Gaussian mixture model (GMM). The experimental results showed that the proposed system effectively classified 98.3% of pornographic data and 99.8% of non-pornographic data. We expect the proposed method can be applied to the more accurate classification system which uses both video and audio information.

• 천문학회보
• /
• 제46권2호
• /
• pp.74.2-75
• /
• 2021

We demonstrate that a deep learning classifier that only uses to gravitational wave (GW) detectors auxiliary channel data can distinguish various types of non-Gaussian noise transients (glitches) with significant accuracy, i.e., ≳ 80%. The classifier is implemented using the multi-scale neural networks (MSNN) with PyTorch. The glitches appearing in the GW strain data have been one of the main obstacles that degrade the sensitivity of the gravitational detectors, consequently hindering the detection and parameterization of the GW signals. Numerous efforts have been devoted to tracking down their origins and to mitigating them. However, there remain many glitches of which origins are not unveiled. We apply the MSNN classifier to the auxiliary channel data corresponding to publicly available GravitySpy glitch samples of LIGO O1 run without using GW strain data. Investigation of the auxiliary channel data of the segments that coincide to the glitches in the GW strain channel is particularly useful for finding the noise sources, because they record physical and environmental conditions and the status of each part of the detector. By only using the auxiliary channel data, this classifier can provide us with the independent view on the data quality and potentially gives us hints to the origins of the glitches, when using the explainable AI technique such as Layer-wise Relevance Propagation or GradCAM.

• Journal of Electrical Engineering and Technology
• /
• 제13권4호
• /
• pp.1504-1514
• /
• 2018

The objective of this study is to compare the suitability of a non-parametric and 3 parametric distributions in the characterization of prediction intervals of photovoltaic power forecasts with high confidence levels. The prediction intervals of the forecasts are calculated using a method based on recent past data similar to the target forecast input data, and on a distribution assumption for the forecast error. To compare the suitability of the distributions, prediction intervals were calculated using the proposed method and each of the 4 distributions. The calculations were done for one year of day-ahead forecasts of hourly power generation of 432 PV systems. The systems have different sizes and specifications, and are installed in different locations in Japan. The results show that, in general, the non-parametric distribution assumption for the forecast error yielded the best prediction intervals. For example, with a confidence level of 85% the use of the non-parametric distribution assumption yielded a median annual forecast error coverage of 86.9%. This result was close to the one obtained with the Laplacian distribution assumption (87.8% of coverage for the same confidence level). Contrasting with that, using a Gaussian and Hyperbolic distributions yielded median annual forecast error coverage of 89.5% and 90.5%.