• Smart Media Journal
• /
• v.8 no.3
• /
• pp.62-69
• /
• 2019

Electrocardiogram (ECG) signals cannot be counterfeited and can easily acquire signals from both wrists. In this paper, we propose a method of generating a coupling image using direction information of ECG signals as well as its usage in a personal recognition method. The proposed coupling image is generated by using forward ECG signal and rotated inverse ECG signal based on R-peak, and the generated coupling image shows a unique pattern and brightness. In addition, R-peak data is increased through the ECG signal calculation of the same beat, and it is thus possible to improve the recognition performance of the individual. The generated coupling image extracts characteristics of pattern and brightness by using the proposed convolutional neural network and reduces data size by using multiple pooling layers to improve network speed. The experiment uses public ECG data of 47 people and conducts comparative experiments using five networks with top 5 performance data among the public and the proposed networks. Experimental results show that the recognition performance of the proposed network is the highest with 99.28%, confirming potential of the personal recognition.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.1
• /
• pp.106-113
• /
• 2019

In this paper, we propose an algorithm to classify the received active pulse when the active sonar system is operated as a non-cooperative mode. The proposed algorithm uses CNN (Convolutional Neural Networks) which shows good performance in various fields. As an input of CNN, time frequency analysis data which performs STFT (Short Time Fourier Transform) of the received signal is used. The CNN used in this paper consists of two convolution and pulling layers. We designed a database based neural network and a pulse feature based neural network according to the output layer design. To verify the performance of the algorithm, the data of 3110 CW (Continuous Wave) pulses and LFM (Linear Frequency Modulated) pulses received from the actual ocean were processed to construct training data and test data. As a result of simulation, the database based neural network showed 99.9 % accuracy and the feature based neural network showed about 96 % accuracy when allowing 2 pixel error.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.6
• /
• pp.1-8
• /
• 2021

In this paper, we propose reinforced VGG style network structure for low performance embedded system to classify low resolution infrared image. The combination of reinforced VGG style network structure and global average pooling makes lower computational complexity and higher accuracy. The proposed method classify the synthesize image which have 9 class 3,723,328ea images made from OKTAL-SE tool. The reinforced VGG style network structure composed of 4 filters on input and 16 filters on output from max pooling layer shows about 34% lower computational complexity and about 2.4% higher accuracy then the first parameter minimized network structure made for embedded system composed of 8 filters on input and 8 filters on output from max pooling layer. Finally we get 96.1% accuracy model. Additionally we confirmed the about 31% lower inference lead time in ported C code.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.3
• /
• pp.529-536
• /
• 2022

In the past two years, Severe Acute Respiratory Syndrome Coronavirus-2(SARS-CoV-2) has been hitting more and more to people. This paper proposes a novel U-Net Convolutional Neural Network to classify and segment COVID-19 lung CT images, which contains Sub Coding Block (SCB), Atrous Spatial Pyramid Pooling(ASPP) and Attention Gate(AG). Three different models such as FCN, U-Net and U-Net-SCB are designed to compare the proposed model and the best optimizer and atrous rate are chosen for the proposed model. The simulation results show that the proposed U-Net-MMFE has the best Dice segmentation coefficient of 94.79% for the COVID-19 CT scan digital image dataset compared with other segmentation models when atrous rate is 12 and the optimizer is Adam.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.321-321
• /
• 2023

가뭄은 수개월 혹은 수년간 지속적이며, 점진적으로 광범위하게 피해를 미치는 자연재해이다. 강수 부족과 같은 비정상적 기상환경으로 인해 발생하는 기상학적 가뭄이 지속되어 토양 수분량 감소 및 식생에 영향을 미치는 농업적 가뭄을 발생시킬 수 있으며, 하천유출량 및 가용수자원이 감소하는 수문학적 가뭄으로까지 진행된다. 이처럼 분야별 가뭄이 장시간 지속됨에 따라 다른 종류의 가뭄을 발생시키는 현상을 가뭄 전이라고 하며, 가뭄이 전이되지 않은 비전이 사상보다 지역에 큰 피해를 야기한다. 최근 우리나라에서도 가뭄 전이와 관련된 연구들이 진행되고 있다. 하지만 기상학적, 농업적 및 수문학적 가뭄에 대한 가뭄 전이를 모두 고려하여 가뭄의 전이 및 비전이사상간의 피해 양상을 비교하는 연구는 부족한 실정이다. 따라서, 본 연구에서는 전국 단위의 시군구별 SPI(Standardized Precipitation Index), SGI(Standardized Groundwater level Index) 및 PHDI(Palmer Hydrological Drought Index)를 사용하여 각각 기상학적, 농업적 및 수문학적 가뭄을 판단하였다. 각 분야별 가뭄간의 시간적 중복여부를 통해 가뭄의 전이 여부를 판단하고, 가뭄의 전이 특성(풀링, 감쇠, 지체, 연장) 분석을 수행하였다. 또한, 가뭄 전이 사상과 비전이 사상이 발생한 시기의 가뭄 피해 관련 자료를 수집하여, 지역별 가뭄 전이 사상 및 비전이 사상간의 피해 양상을 비교 및 분석하였다. 과거 충청북도 충주시는 2011년의 기상학적 가뭄(비전이 사상) 발생시 피해 인구가 없었으나, 2019년의 기상학적 가뭄에서 수문학적 가뭄으로 전이가 발생하여 999명의 피해 인구가 발생하였다. 즉, 동일한 지역에서 다른 시기에 발생한 가뭄 피해 및 동일한 연도에서 인접한 지역의 가뭄 피해를 분석한 결과, 비전이된 가뭄 사상에 비해 전이된 가뭄 사상에서 더욱 큰 피해를 가지는 것을 확인하였다.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.10
• /
• pp.935-943
• /
• 2017

CNN (Convolution neural network), which is used for image classification and speech recognition among neural networks learning based on positive data, has been continuously developed to have a high performance structure to date. There are many difficulties to utilize in an embedded system with limited resources. Therefore, we use GPU (General-Purpose Computing on Graphics Processing Units), which is used for general-purpose operation of GPU to solve the problem because we use pre-learned weights but there are still limitations. Since CNN performs simple and iterative operations, the computation speed varies greatly depending on the thread allocation and utilization method in the Single Instruction Multiple Thread (SIMT) based GPGPU. To solve this problem, there is a thread that needs to be relaxed when performing Convolution and Pooling operations with threads. The remaining threads have increased the operation speed by using the method used in the following feature maps and kernel calculations.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.4
• /
• pp.511-523
• /
• 2023

Research on the integration of unmanned aerial vehicles and deep learning for reinforced concrete damage detection is actively underway. Convolutional neural networks have a high impact on the performance of image classification, detection, and segmentation as backbones. The MobileNet, a pre-trained convolutional neural network, is efficient as a backbone for an unmanned aerial vehicle-based damage detection model because it can achieve sufficient accuracy with low computational complexity. Analyzing vanilla convolutional neural networks and MobileNet under various conditions, MobileNet was evaluated to have a verification accuracy 6.0~9.0% higher than vanilla convolutional neural networks with 15.9~22.9% lower computational complexity. MobileNetV2, MobileNetV3Large and MobileNetV3Small showed almost identical maximum verification accuracy, and the optimal conditions for MobileNet's reinforced concrete damage image feature extraction were analyzed to be the optimizer RMSprop, no dropout, and average pooling. The maximum validation accuracy of 75.49% for 7 types of damage detection based on MobilenetV2 derived in this study can be improved by image accumulation and continuous learning.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.497-504
• /
• 2020

Constructing speaker embeddings in speaker verification is an important issue. In general, a self-attention mechanism has been applied for speaker embedding encoding. Previous studies focused on training the self-attention in a high-level layer, such as the last pooling layer. In this case, the effect of low-level layers is not well represented in the speaker embedding encoding. In this study, we propose Masked Cross Self-Attentive Encoding (MCSAE) using ResNet. It focuses on training the features of both high-level and low-level layers. Based on multi-layer aggregation, the output features of each residual layer are used for the MCSAE. In the MCSAE, the interdependence of each input features is trained by cross self-attention module. A random masking regularization module is also applied to prevent overfitting problem. The MCSAE enhances the weight of frames representing the speaker information. Then, the output features are concatenated and encoded in the speaker embedding. Therefore, a more informative speaker embedding is encoded by using the MCSAE. The experimental results showed an equal error rate of 2.63 % using the VoxCeleb1 evaluation dataset. It improved performance compared with the previous self-attentive encoding and state-of-the-art methods.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.414-423
• /
• 2020

In this paper, we propose a Dilated Convolution Gate Linear Unit (DCGLU) to mitigate the lack of sparsity and small receptive field problems caused by the segmentation map extraction process in sound event detection with weak labels. In the advent of deep learning framework, segmentation map extraction approaches have shown improved performance in noisy environments. However, these methods are forced to maintain the size of the feature map to extract the segmentation map as the model would be constructed without a pooling operation. As a result, the performance of these methods is deteriorated with a lack of sparsity and a small receptive field. To mitigate these problems, we utilize GLU to control the flow of information and Dilated Convolutional Neural Networks (DCNNs) to increase the receptive field without additional learning parameters. For the performance evaluation, we employ a URBAN-SED and self-organized bird sound dataset. The relevant experiments show that our proposed DCGLU model outperforms over other baselines. In particular, our method is shown to exhibit robustness against nature sound noises with three Signal to Noise Ratio (SNR) levels (20 dB, 10 dB and 0 dB).

• Journal of Pharmaceutical Investigation
• /
• v.30 no.3
• /
• pp.191-199
• /
• 2000

Genomics is providing targets faster than we can validate them and combinatorial chemistry is providing new chemical entities faster than we can screen them. Historically, the drug discovery cascade has been established as a sequential process initiated with a potency screening against a selected biological target. In this sequential process, pharmacokinetics was often regarded as a low-throughput activity. Typically, limited pharmacokinetics studies would be conducted prior to acceptance of a compound for safety evaluation and, as a result, compounds often failed to reach a clinical testing due to unfavorable pharmacokinetic characteristics. A new paradigm in drug discovery has emerged in which the entire sample collection is rapidly screened using robotized high-throughput assays at the outset of the program. Higher-throughput pharmacokinetics (HTPK) is being achieved through introduction of new techniques, including automation for sample preparation and new experimental approaches. A number of in vitro and in vivo methods are being developed for the HTPK. In vitro studies, in which many cell lines are used to screen absorption and metabolism, are generally faster than in vivo screening, and, in this sense, in vitro screening is often considered as a real HTPK. Despite the elegance of the in vitro models, however, in vivo screenings are always essential for the final confirmation. Among these in vivo methods, cassette dosing technique, is believed the methods that is applicable in the screening of pharmacokinetics of many compounds at a time. The widespread use of liquid chromatography (LC) interfaced to mass spectrometry (MS) or tandem mass spectrometry (MS/MS) allowed the feasibility of the cassette dosing technique. Another approach to increase the throughput of in vivo screening of pharmacokinetics is to reduce the number of sample analysis. Two common approaches are used for this purpose. First, samples from identical study designs but that contain different drug candidate can be pooled to produce single set of samples, thus, reducing sample to be analyzed. Second, for a single test compound, serial plasma samples can be pooled to produce a single composite sample for analysis. In this review, we validated the issue whether the second method can be applied to practical screening of in vivo pharmacokinetics using data from seven of our previous bioequivalence studies. For a given drug, equally spaced serial plasma samples were pooled to achieve a 'Pooled Concentration' for the drug. An area under the plasma drug concentration-time curve (AUC) was then calculated theoretically using the pooled concentration and the predicted AUC value was statistically compared with the traditionally calculated AUC value. The comparison revealed that the sample pooling method generated reasonably accurate AUC values when compared with those obtained by the traditional approach. It is especially noteworthy that the accuracy was obtained by the analysis of only one sample instead of analyses of a number of samples that necessitates a significant man-power and time. Thus, we propose the sample pooling method as an alternative to in vivo pharmacokinetic approach in the selection potential lead(s) from combinatorial libraries.