• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.129-132
• /
• 2022

Super-resolution is the process of converting a low-quality image into a high-quality image. This study was conducted using ESPCN. In a super-resolution deep neural network, different quality images can be output even when receiving the same input data according to the activation function that determines the weight when passing through each node. Therefore, the purpose of this study is to find the most suitable activation function for super-resolution by applying the activation functions ReLU, ELU, and Swish and compare the quality of the output image for the same input images. The CelebaA Dataset was used as the dataset. Images were cut into a square during the pre-processing process then the image quality was lowered. The degraded image was used as the input image and the original image was used for evaluation. As a result, ELU and swish took a long time to train compared to ReLU, which is mainly used for machine learning but showed better performance.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.6
• /
• pp.511-516
• /
• 2002

The neural networks may have problem such that the amount of calculation for the network learning goes too big according to the dimension of the dimension. To overcome this problem, the wavelet neural networks(WNN) which use the orthogonal basis function in the hidden node are proposed. One can compose wavelet functions as activation functions in the WNN by determining the scale and center of wavelet function. In this paper, when we compose the WNN using wavelet functions, we set a single scale function as a node function together. We intend that one scale function approximates the target function roughly, the other wavelet functions approximate it finely During the determination of the parameters, the wavelet functions can be determined by the global search for solutions suitable for the suggested problem using the genetic algorithm and finally, we use the back-propagation algorithm in the learning of the weights.

• The Korean Journal of Physiology and Pharmacology
• /
• v.17 no.3
• /
• pp.223-228
• /
• 2013

The calcium-activated $K^+$ ($BK_{Ca}$) channel is one of the potassium-selective ion channels that are present in the nervous and vascular systems. $Ca^{2+}$ is the main regulator of $BK_{Ca}$ channel activation. The $BK_{Ca}$ channel contains two high affinity $Ca^{2+}$ binding sites, namely, regulators of $K^+$ conductance, RCK1 and the $Ca^{2+}$ bowl. Lysophosphatidic acid (LPA, 1-radyl-2-hydroxy-sn-glycero-3-phosphate) is one of the neurolipids. LPA affects diverse cellular functions on many cell types through G protein-coupled LPA receptor subtypes. The activation of LPA receptors induces transient elevation of intracellular $Ca^{2+}$ levels through diverse G proteins such as $G{\alpha}_{q/11}$, $G{\alpha}_i$, $G{\alpha}_{12/13}$, and $G{\alpha}s$ and the related signal transduction pathway. In the present study, we examined LPA effects on $BK_{Ca}$ channel activity expressed in Xenopus oocytes, which are known to endogenously express the LPA receptor. Treatment with LPA induced a large outward current in a reversible and concentration-dependent manner. However, repeated treatment with LPA induced a rapid desensitization, and the LPA receptor antagonist Ki16425 blocked LPA action. LPA-mediated $BK_{Ca}$ channel activation was also attenuated by the PLC inhibitor U-73122, $IP_3$ inhibitor 2-APB, $Ca^{2+}$ chelator BAPTA, or PKC inhibitor calphostin. In addition, mutations in RCK1 and RCK2 also attenuated LPA-mediated $BK_{Ca}$ channel activation. The present study indicates that LPA-mediated activation of the $BK_{Ca}$ channel is achieved through the PLC, $IP_3$, $Ca^{2+}$, and PKC pathway and that LPA-mediated activation of the $BK_{Ca}$ channel could be one of the biological effects of LPA in the nervous and vascular systems.

• Journal of Microbiology and Biotechnology
• /
• v.18 no.2
• /
• pp.355-364
• /
• 2008

Mushrooms are regarded as one of the well-known foods and biopharmaceutical materials with a great deal of interest. ${\beta}$-Glucan is the major component of mushrooms that displays various biological activities such as antidiabetic, anticancer, and antihyperlipidemic effects. In this study, we explored the molecular mechanism of its immunostimulatory potency in immune responses of macrophages, using exopolysaccharides prepared from liquid culture of Lentinus edodes. We found that fraction II (F-II), with large molecular weight protein polysaccharides, is able to strongly upregulate the phenotypic functions of macrophages such as phagocytic uptake, ROS/NO production, cytokine expression, and morphological changes. F-II triggered the nuclear translocation of NF-${\kappa}B$ and activated its upstream signaling cascades such as PI3K/Akt and MAPK pathways, as assessed by their phosphorylation levels. The function-blocking antibodies to dectin-1 and TLR-2, but not CR3, markedly suppressed F-II-mediated NO production. Therefore, our data suggest that mushroom-derived ${\beta}$-glucan may exert its immunostimulating potency via activation of multiple signaling pathways.

• The Journal of Korean Academy of Sensory Integration
• /
• v.13 no.2
• /
• pp.75-84
• /
• 2015

Objective : The aim of this study was to provide mechanism information of a link between arousal and sensory modulation to increase understanding of neurophysiological study. Subject : Optimal arousal state of a child is an important issue in sensory integration therapy. Limbic system and reticular formation are related to sensory modulation by sensory input. Sensory inputs processes from reticular formation to cortex via ascending reticular activation system for moderate arousal. A lot of neurotransmitters such as cholinergic neurons and monoamin neurons help this processes. Mechanism of arousal was measured by functions of central nervous system (CNS) and autonomic nervous system (ANS) using objective tools such as an electroencephalogram (EEG) and electrodermal responses. Functions of CNS and ANS showed differences between normal children and children with disabilities. Optimal sensory input using sensory integration therapy for children with disabilities helps to act reticular formation, limbic system, and cortex and to maintain appropriate arousal. Conclusion : Such quantitative studies by using neurophysiological methods provide evidence for sensory integration therapy.

• The Korea Journal of Herbology
• /
• v.35 no.5
• /
• pp.33-39
• /
• 2020

Objectives : Increasing evidence supports the biological and pharmacological activities of essential oils on the central nervous system such as pain, anxiety, attention, arousal, relaxation, sedation and learning and memory. The purpose of present work is to investigate the protective effect and molecular mechanism of cypress essential oil (CEO) against scopolamine (SCO)-induced cognitive impairments in C57BL/6 mice. Methods : A series of behavior tests such as Morris water maze, passive avoidance, and fear conditioning tests were conducted to monitor learning and memory functions. Immunoblotting and RT-PCR were also performed in the hippocampal tissue to determine the underlying mechanism of CEO. Results : SCO induced cognitive impairments as assessed by decreased step-through latency in passive avoidance test, relatively low freezing time in fear conditioning test, and increased time spent to find the hidden platform in Morris water maze test. Conversely, CEO inhalation significantly reversed the SCO-induced cognitive impairments in C57BL/6 mice comparable to control levels. To elucidate the molecular mechanisms of memory enhancing effect of CEO we have examined the expression of brain-derived neurotrophic factor (BDNF) in the hippocampus. CEO effectively elevated the protein as well as mRNA expression of BDNF via activation of cAMP response element binding protein (CREB). Conclusions : Our findings suggest that CEO inhalation effectively restored the SCO-impaired cognitive functions in C56BL/6 mice. This learning and memory enhancing effect of CEO was partly mediated by up-regulation of BDNF via activation of CREB.

• Korean Journal of Veterinary Research
• /
• v.56 no.1
• /
• pp.15-21
• /
• 2016

NAD(P)H-quinone oxidoreductase-1 (NQO1) is a down-stream target gene of nuclear factor erythroid 2-related factor 2 (Nrf2), and performs diverse biological functions. Recently, NQO1 is recognized as an effective gene for the cytotoxic inserts with its diverse biological functions, which is focused on antioxidant properties. The aim of present study was to assess the impact of NQO1 knockdown on cytoprotection-related protein expression in cisplatin cytotoxicity by using small interfering (si) RNA targeted on NQO1 gene. Cytotoxicity of cisplatin on ACHN cells was assessed in a dose- and time-dependent manner after siScramble or siNQO1 treatment. After cisplatin treatment, cells were subjected to cell viability assay, western-blot analysis, and immunofluorescence study. The cell viability was decreased in the siNQO1 cells (50%) than the siScramble cells (70%) after 24 h of cisplatin ($20{\mu}M$) treatment. Moreover, cytoprotection-related protein expressions were markedly suppressed in the siNQO1 cells after cisplatin treatment. The expression of Nrf2 and Klotho were decreased by 20% and 40%, respectively, of that in siScramble cells. Nrf2 and Klotho activation were also decreased in cisplatin treated siNQO1 cells, confirmed by cytoplasm-tonuclear translocation. Our findings demonstrate that the increased cisplatin-induced cytotoxicity was accompanied by suppressed Nrf2 activation and Klotho expression in siNQO1 cells.

• Nuclear Engineering and Technology
• /
• v.53 no.7
• /
• pp.2334-2340
• /
• 2021

Radioactive particle tracking (RPT) is a minimally invasive nuclear technique that tracks a radioactive particle inside a volume of interest by means of a mathematical location algorithm. During the past decades, many algorithms have been developed including ones based on artificial intelligence techniques. In this study, RPT technique is applied in a simulated test section that employs a simplified mixer filled with concrete, six scintillator detectors and a¹³⁷Cs radioactive particle emitting gamma rays of 662 keV. The test section was developed using MCNPX code, which is a mathematical code based on Monte Carlo simulation, and 3516 different radioactive particle positions (x,y,z) were simulated. Novelty of this paper is the use of a location algorithm based on a deep learning model, more specifically a 6-layers deep rectifier neural network (DRNN), in which hyperparameters were defined using a Bayesian optimization method. DRNN is a type of deep feedforward neural network that substitutes the usual sigmoid based activation functions, traditionally used in vanilla Multilayer Perceptron Networks, for rectified activation functions. Results show the great accuracy of the DRNN in a RPT tracking system. Root mean squared error for x, y and coordinates of the radioactive particle is, respectively, 0.03064, 0.02523 and 0.07653.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.5
• /
• pp.855-867
• /
• 2022

As the need for a deep learning accelerator increases with the development of IoT equipment, research on the implementation and safety verification of the deep learning accelerator is actively. In this paper, we propose a new side channel analysis methodology for secret information that overcomes the limitations of the previous study in Usenix 2019. We overcome the disadvantage of limiting the range of weights and restoring only a portion of the weights in the previous work, and restore the IEEE754 32bit single-precision with 99% accuracy with a new method using CPA. In addition, it overcomes the limitations of existing studies that can reverse activation functions only for specific inputs. Using deep learning, we reverse activation functions with 99% accuracy without conditions for input values with a new method. This paper not only overcomes the limitations of previous studies, but also proves that the proposed new methodology is effective.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.4
• /
• pp.611-616
• /
• 2023

ECG(electrocardiogram) is a test used to measure the rate and regularity of heartbeats, as well as the size and position of the chambers, the presence of any damage to the heart, and the cause of all heart diseases can be found. Because the ECG signal obtained using the ECG-KIT includes noise in the ECG signal, noise must be removed from the ECG signal to apply to the deep learning. In this paper, the noise of the ECG signal was removed using the digital IIR Butterworth low-pass filter. When the performance evaluation of the three activation functions, sigmoid(), ReLU(), and tanh() functions, was compared using the deep learning model of LSTM, it was confirmed that the activation function with the smallest error was the tanh() function. Also, When the performance evaluation and elapsed time were compared for LSTM and GRU models, it was confirmed that the GRU model was superior to the LSTM model.