• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.481-483
• /
• 2022

With the advent of the era of artificial intelligence, more and more fields have begun to use artificial intelligence technology, especially the medical field. Cancer is one of the biggest problems in the medical field. [1] If it can be detected early and treated early, the possibility of cure will be greatly increased. Malignant skin cancer, as one of the types of cancer with the highest fatality rate in recent years has problems such as relying on the experience of doctors and being unable to be detected and detected in time. Therefore, if artificial intelligence technology can be used to help doctors in early detection of skin cancer, or to allow everyone to detect skin lesions or spots anytime, anywhere, it will have great practical significance. In this paper we used attention residual learning convolutional neural network (ARL-CNN) model [2] to classify skin cancer pictures.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.5
• /
• pp.1141-1162
• /
• 2024

Humidity is an important parameter in meteorology and is closely related to weather, human health, and the environment. Due to the limitations of the number of observation stations and other factors, humidity data are often not as good as expected, so high-resolution humidity fields are of great interest and have been the object of desire in the research field and industry. This study presents a novel super-resolution algorithm for humidity fields based on the Wasserstein generative adversarial network(WGAN) framework, with the objective of enhancing the resolution of low-resolution humidity field information. WGAN is a more stable generative adversarial networks(GANs) with Wasserstein metric, and to make the training more stable and simple, the gradient cropping is replaced with gradient penalty, and the network feature representation is improved by sub-pixel convolution, residual block combined with convolutional block attention module(CBAM) and other techniques. We evaluate the proposed algorithm using ERA5 relative humidity data with an hourly resolution of 0.25°×0.25°. Experimental results demonstrate that our approach outperforms not only conventional interpolation techniques, but also the super-resolution generative adversarial network(SRGAN) algorithm.

• Journal of Korean Society of Environmental Engineers
• /
• v.38 no.2
• /
• pp.87-95
• /
• 2016

Turbidity is a key indicator to the user that the 'Discolored Water' phenomenon known to be caused by corrosion of the pipeline in the water supply system. 'Discolored Water' is defined as a state with a turbidity of the degree to which the user visually be able to recognize water. Therefore, this study used data mining techniques in order to estimate turbidity changes in water supply system. Decision tree analysis was applied in data mining techniques to develop estimation models for turbidity changes in the water supply system. The pH and residual chlorine dataset was used as variables of the turbidity estimation model. As a result, the case of applying both variables(pH and residual chlorine) were shown more reasonable estimation results than models only using each variable. However, the estimation model developed in this study were shown to have underestimated predictions for the peak observed values. To overcome this disadvantage, a high-pass filter method was introduced as a pretreatment of estimation model. Modified model using high-pass filter method showed more exactly predictions for the peak observed values as well as improved prediction performance than the conventional model.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.3
• /
• pp.63-69
• /
• 2013

This paper related with the performance of SE-MMA (Signed-Error MMA) that is the reduction of computational operation number in algorithm than MMA blind eualization algorithm which are possible to elimination of intersymbol interferance in the band limited and time dispersive nonlinear communication channel. In MMA algorithm which are possible to reduction of amplitude and phase rotation by intersymbol interference that is occurred in channel without using the training sequence, it uses the error signal that is the difference of the equalizer output and constant modulus, the statisticlly characteristic of transmitted signal. But in SE-MMA, it uses the polarity of the error signal, then it is possible to reduce the updating the tap coefficient and to simplify the H/W implementation. The computer simulation were performed in order to compare the performance of SE-MMA and conventional MMA algorithm. For this, the recovered signal constellation that is the output of the equalizer, the convergence performance by MSE, MD (maximum distortion) and residual isi characteristic learning curve, SER were used. As a result of simulation, the SE-MMA has more fast convergence speed than the MMA. But in the other index after reaching the seady state, it gives more worst performance values in the used index.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.6
• /
• pp.115-121
• /
• 2013

This paper related with the DSE-MMA (Dithered Sign-Error MMA) that is the simplification of computational arithmetic number in blind equalization algorithm in order to compensates the intersymbol interference which occurs the passing the nonlinear communication channel in the presence of the band limit and phase distortion. The SE-MMA algorithm has a merit of H/W implementation for the possible to reduction of computational arithmetic number using the 1 bit quantizer in stead of multiplication in the updating the equalizer tap weight. But it degradates the overall blind equalization algorithm performance by the information loss at the quantization process compare to the MMA. The DSE-MMA which implements the dithered signed-error concepts by using the dither signal before qualtization are added to MMA, then the improved SNR performance which represents the roburstness of equalization algorithm are obtained. It has a concurrently compensation capability of the amplitude and phase distortion due to intersymbol interference like as the SE-MMA and MMA algorithm. The paper uses the equalizer output signal, residual isi, MD, MSE learning curve and SER curve for the performance index of blind equalization algorithm, and the computer simulation were performed in order to compare the SE-MMA and DSE-MMA applying the same performance index. As a result of simulation, the DSE-MMA can improving the roburstness and the value of every performance index after steady state than the SE-MMA, and confirmed that the DSE-MMA has slow convergence speed which meaning the reaching the seady state from initial state of adaptive equalization filter.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.6
• /
• pp.536-543
• /
• 2023

Speaker diarization, which labels for "who spoken when?" in speech with multiple speakers, has been studied on a deep neural network-based end-to-end method for labeling on speech overlap and optimization of speaker diarization models. Most deep neural network-based end-to-end speaker diarization systems perform multi-label classification problem that predicts the labels of all speakers spoken in each frame of speech. However, the performance of the multi-label-based model varies greatly depending on what the threshold is set to. In this paper, it is studied a speaker diarization system using single-label classification so that speaker diarization can be performed without thresholds. The proposed model estimate labels from the output of the model by converting speaker labels into a single label. To consider speaker label permutations in the training, the proposed model is used a combination of Permutation Invariant Training (PIT) loss and cross-entropy loss. In addition, how to add the residual connection structures to model is studied for effective learning of speaker diarization models with deep structures. The experiment used the Librispech database to generate and use simulated noise data for two speakers. When compared with the proposed method and baseline model using the Diarization Error Rate (DER) performance the proposed method can be labeling without threshold, and it has improved performance by about 20.7 %.

• Korean Journal of Remote Sensing
• /
• v.36 no.3
• /
• pp.449-460
• /
• 2020

Super-resolution is a technique used to reconstruct an image with low-resolution into that of high-resolution. Recently, deep-learning based super resolution has become the mainstream, and applications of these methods are widely used in the remote sensing field. In this paper, we propose a super-resolution method based on the deep back-projection network model to improve the satellite image resolution by the factor of four. In the process, we customized the loss function with the edge loss to result in a more detailed feature of the boundary of each object and to improve the stability of the model training using generative adversarial network based on Wasserstein distance loss. Also, we have applied the detail preserving image down-scaling method to enhance the naturalness of the training output. Finally, by including the modified-residual learning with a panchromatic feature in the final step of the training process. Our proposed method is able to reconstruct fine features and high frequency information. Comparing the results of our method with that of the others, we propose that the super-resolution method improves the sharpness and the clarity of WorldView-3 and KOMPSAT-2 images.

• Geophysics and Geophysical Exploration
• /
• v.23 no.3
• /
• pp.117-130
• /
• 2020

Noises can distort acquired geophysical data, leading to their misinterpretation. Potential noises sources include anthropogenic activity, natural phenomena, and instrument noises. Conventional denoising methods such as wavelet transform and filtering techniques, are based on subjective human investigation, which is computationally inefficient and time-consuming. Recently, many researchers attempted to implement neural networks to efficiently remove noise from geophysical data. This study aims to review and analyze different types of neural networks, such as artificial neural networks, convolutional neural networks, autoencoders, residual networks, and wavelet neural networks, which are implemented to remove different types of noises including seismic, transient electromagnetic, ground-penetrating radar, and magnetotelluric surveys. The review analyzes and summarizes the key challenges in the removal of noise from geophysical data using neural network, while proposes and explains solutions to the challenges. The analysis support that the advancement in neural networks can be powerful denoising tools for geophysical data.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.10
• /
• pp.75-80
• /
• 2017

In this paper, we describe the effect of the regularization method and the network with identity mapping on the performance of the activation functions in deep convolutional neural networks. The activation functions act as nonlinear transformation. In early convolutional neural networks, a sigmoid function was used. To overcome the problem of the existing activation functions such as gradient vanishing, various activation functions were developed such as ReLU, Leaky ReLU, parametric ReLU, and ELU. To solve the overfitting problem, regularization methods such as dropout and batch normalization were developed on the sidelines of the activation functions. Additionally, data augmentation is usually applied to deep learning to avoid overfitting. The activation functions mentioned above have different characteristics, but the new regularization method and the network with identity mapping were validated only using ReLU. Therefore, we have experimentally shown the effect of the regularization method and the network with identity mapping on the performance of the activation functions. Through this analysis, we have presented the tendency of the performance of activation functions according to regularization and identity mapping. These results will reduce the number of training trials to find the best activation function.

• Health Policy and Management
• /
• v.17 no.1
• /
• pp.50-74
• /
• 2007

The purpose of this study was to identify a determent of mastery approach goal and performance approach goal using a basic concept of goal orientations and goal setting theory, and to evaluate a preference of goal achievement index as a balance score card (BSC). The study model proposed had a adoptable level of goodness of fit index(.94) and root mean square residual(.08). The meditating variable, goal contribution, totally mediated the impact of goal commitment, Y-theory human behavior, and self-efficacy but organizational resource contribution for pursuing goal orientation. Moreover, goal contribution significantly determined mastery approach goal(p<.01) and performance approach goal(.05). In standardized effects, the most powerful antecedent of mastery approach goal and performance approach goal were in order of organizational resource contribution(.27/.28), goal contribution(.21/.17), self-efficacy(.07/.06), and Y -theory human behavior and goal commitment(.05/.05), respectively. Moreover, goal contribution had a more powerful impact on mastery approach goal(.21) rather than performance approach goal(.17). In the preference of BSC, all job types preferred learning and growth index in first. In the second preference, medical doctors and pharmacists chose financial results, nurses customer service, and office managers internal processes. Each job type reflected its' own preferred BSC index to that of the other job types. In comparing a preference of four BSC index of each own job type, it was statistically different at p<.001. In conclusion, one who emphasize organizational goal contribution in pursuing goal orientation has a more strong orientation toward mastery approach goal rather than performance approach goal. A hospital should overcome and harmonize the different preferences of four BSC index since the differences might cause organizational conflicts among job types with having each unique professional norm.