• Journal of the Korea Convergence Society
• /
• v.12 no.2
• /
• pp.21-28
• /
• 2021

In this study, we propose a deep learning-based NILM technique using actual measured power data for 5 kinds of home appliances and verify its effectiveness. For about 3 weeks, the active power of the central power measuring device and five kinds of home appliances (refrigerator, induction, TV, washing machine, air cleaner) was individually measured. The preprocessing method of the measured data was introduced, and characteristics of each household appliance were analyzed through spectogram analysis. The characteristics of each household appliance are organized into a learning data set. All the power data measured by the central power measuring device and 5 kinds of home appliances were time-series mapping, and training was performed using a LSTM neural network, which is excellent for time series data prediction. An algorithm that can disaggregate five types of energies using only the power data of the main central power measuring device is proposed.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.4
• /
• pp.1-8
• /
• 2021

In this paper, we propose an approach that combines the technological advantages of P2P and cloud computing to support MMOGs that allowing a huge amount of users worldwide to share a real-time virtual environment. The proposed P2P system based on cloud computing can provide a greater level of scalability because their more resources are added to the infrastructure even when the amount of users grows rapidly. This system also relieves a lot of computational power and network traffic, the load on the servers in the cloud by exploiting the capacity of the peers. In this paper, we describe the concept and basic architecture of cloud computing-based P2P Systems for scalability of MMOGs. An efficient and effective provisioning of resources and mapping of load are mandatory to realize this architecture that scales in economical cost and quality of service to large communities of users. Simulation results show that by controlling the amount of cloud and user-provided resource, the proposed P2P system can reduce the bandwidth at the server while utilizing their enough bandwidth when the number of simultaneous users keeps growing.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.5
• /
• pp.518-524
• /
• 2022

In this paper, we propose a method for combining convolutional neural networks and attention mechanism to improve the recognition performance of emotional stress from Electroencephalogram (EGG) signals. In the proposed method, EEG signals are decomposed into five frequency domains, and spatial information of EEG features is obtained by applying a convolutional neural network layer to each frequency domain. As a next step, salient frequency information is learned in each frequency band using a gate transformer-based attention mechanism, and complementary frequency information is further learned through inter-frequency mapping to reflect it in the final attention representation. Through an EEG stress recognition experiment involving a DEAP dataset and six subjects, we show that the proposed method is effective in improving EEG-based stress recognition performance compared to the existing methods.

• Journal of The Korea Institute of Healthcare Architecture
• /
• v.29 no.2
• /
• pp.17-26
• /
• 2023

Purpose: The purpose of this study is to identify policy implications for the construction of public health facilities in the field of international cooperation, by examining the case of establishing a health care delivery system using a public health center in a rural area of Paraguay. Methods: Firstly, to map the capacity of the 20 public health centers that were studied, we used the WHO Capacity Mapping tool to select and analyze relevant items. Secondly, to assess the utilization of public health centers, we conducted a direct visit survey and analyzed the results using the M-survey tool. Results: The floor plan of each public health center, the structure of the health center, the size of the population served by each health center, the number of monthly visitors, medical human resources, and the budget were classified by health center for comparative analysis. In addition, by utilizing the M-survey tool, we analyzed the general characteristics of the respondents, their perceptions of the purpose and accessibility of public health centers, their satisfaction with using public health centers, and the level of demand for public health centers to play a role in promoting community health. Implications: The results of this study suggest that access to public health facilities for residents in the research area was improved. By classifying public health centers into two types, these centers can perform the functions and roles of primary health facilities. A patient request and evacuation system was established in the research area. Finally, a network, such as a social prescribing program, is needed so that public health centers can function as a "setting" for community members to live together.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.1
• /
• pp.42.1-42.1
• /
• 2021

In this study, we present a visual explanation of a deep learning solar flare forecast model and its relationship to physical parameters of solar active regions (ARs). For this, we use full-disk magnetograms at 00:00 UT from the Solar and Heliospheric Observatory/Michelson Doppler Imager and the Solar Dynamics Observatory/Helioseismic and Magnetic Imager, physical parameters from the Space-weather HMI Active Region Patch (SHARP), and Geostationary Operational Environmental Satellite X-ray flare data. Our deep learning flare forecast model based on the Convolutional Neural Network (CNN) predicts "Yes" or "No" for the daily occurrence of C-, M-, and X-class flares. We interpret the model using two CNN attribution methods (guided backpropagation and Gradient-weighted Class Activation Mapping [Grad-CAM]) that provide quantitative information on explaining the model. We find that our deep learning flare forecasting model is intimately related to AR physical properties that have also been distinguished in previous studies as holding significant predictive ability. Major results of this study are as follows. First, we successfully apply our deep learning models to the forecast of daily solar flare occurrence with TSS = 0.65, without any preprocessing to extract features from data. Second, using the attribution methods, we find that the polarity inversion line is an important feature for the deep learning flare forecasting model. Third, the ARs with high Grad-CAM values produce more flares than those with low Grad-CAM values. Fourth, nine SHARP parameters such as total unsigned vertical current, total unsigned current helicity, total unsigned flux, and total photospheric magnetic free energy density are well correlated with Grad-CAM values.

• Journal of Digital Convergence
• /
• v.18 no.6
• /
• pp.53-63
• /
• 2020

Electronic financial transactions are also actively increasing due to the rapid spread of information communication media such as the Internet, smart devices, and IoT, but as a derivative by-product, threats of financial security such as leakage of various personal information and hacking are also increasing. Therefore, the importance of financial security against this is increasing, but in Korea, financial security technology is relatively insufficient compared to advanced countries in the field of financial security, such as Active-X. Therefore, this study aims to present the major development direction in the domestic financial security field by comparing key technology trends with IPC classification frequency analysis, keyword frequency analysis, and keyword network analysis based on domestic and foreign financial security-related patent data. In conclusion, it seems that recent domestic and foreign trends have focused on the development of related technologies according to the development of smart device-based electronic financial services. Accordingly, it is intended to be used as the basis data for technology development of financial security by mapping the trend of financial security research trend and technology trend analysis through thesis data analysis that reflects the research of the preceding aspect as the technology of commercialization in the future.

• Investigative Magnetic Resonance Imaging
• /
• v.13 no.2
• /
• pp.127-136
• /
• 2009

Purpose : Functional magnetic resonance imaging (fMRI) was used to assess the temporal response of neural activation in healthy subjects while they performed the Iowa Gambling Test (IGT), which utilizes decisions involving ambiguity and risk. The IGT was divided into five blocks of 20 trials; analysis showed that activity in the medial prefrontal cortex (mPFC) moves gradually from the dorsal to the ventral mPFC over the course of the IGT. These findings suggest that cognitive division of the mPFC, including the dorsal portion of the anterior cingulated cortex (ACC), plays a major role in ambiguous decision making and that the aspect of the IGT corresponding to risky decision making is associated with significant activity within the corticolimbic network strongly implicated in emotion and reinforcement. Our results also suggest that decisions made under ambiguity and decisions made under risk situations can be further divided into sub-phases based on the neural network involved.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.33 no.5
• /
• pp.335-342
• /
• 2015

In this study, data linking module called GeoSWMM was developed using a typical secondary flooding model SWMM in order to improve the accuracy of the input data of SWMM and to map hourly inundation estimation areas that were not represented in the conventional inundation map. GeoSWMM is a data linking module of GIS and SWMM, which can generate a SWMM project file directly from sewer network GIS data. Utilizing the GeoSWMM the project file of SWMM model was constructed in the study area, Seocho 2-dong, Seoul. The actual flooding has occurred September 21, 2010 and the actual rainfall data were used for flood simulation. As a result, the outflow started from 2 PM due to the lack of water flow capacity of the sewage system. Based on the results, hourly inundation estimation maps were produced and compared with flood train map in 2010. The comparison showed about 66% matching in the overlap of inundation areas. By utilizing GeoSWMM that was developed in this study, it is easy to build the sewer network data for SWMM. In addition, the creation of hourly inundation estimation map using SWMM will be much help to flood disaster prevention plan.

• Journal of IKEEE
• /
• v.17 no.4
• /
• pp.407-417
• /
• 2013

In this paper, a reconfigurable peripheral unit for LED lighting communication is presented. Embedded lighting devices require various communication protocols. Usually, serial communication protocols and lighting control communication protocols such as DALI, DMX512, UART, SPI, IrDA, etc. are used in lighting devices. When the requirements of communication protocols are satisfied with separate IPs, the cost and the power consumption can considerably increase. We propose a reconfigurable communication peripheral unit which uses analysis of signal formats of the protocols. The gate count of the reconfigurable peripheral unit uses only 57% of the gate count of the separate implementation. Also, in this paper, a mapping table based DALI-ZigBee interfacing method for flexible lighting network configurations is proposed. Using this method, various DALI-ZigBee network systems can be easily set up. An LED lighting system platform is implemented to verify the operation of the DALI-ZigBee interfacing method. The reconfigurable peripheral unit and the DALI-ZigBee interfacing method can be efficiently used to implement various wired/wireless lighting communication systems.

• Journal of Internet Computing and Services
• /
• v.19 no.5
• /
• pp.43-54
• /
• 2018

Images taken in haze weather are characteristic of low contrast and poor visibility. The process of reconstructing clear-weather image from a hazy image is called dehazing. The main challenge of image dehazing is to estimate the transmission map or depth map for an input hazy image. In this paper, we propose a single image dehazing method by utilizing the Generative Adversarial Network(GAN) for accurate depth map estimation. The proposed GAN model is trained to learn a nonlinear mapping between the input hazy image and corresponding depth map. With the trained model, first the depth map of the input hazy image is estimated and used to compute the transmission map. Then a guided filter is utilized to preserve the important edge information of the hazy image, thus obtaining a refined transmission map. Finally, the haze-free image is recovered via atmospheric scattering model. Although the proposed GAN model is trained on synthetic indoor images, it can be applied to real hazy images. The experimental results demonstrate that the proposed method achieves superior dehazing results against the state-of-the-art algorithms on both the real hazy images and the synthetic hazy images, in terms of quantitative performance and visual performance.