• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4326-4344
• /
• 2021

The SinGAN is one of generative adversarial networks that can be trained on a single nature image. It has poor ability to learn more global features from nature image, and losses much local detail information when it generates arbitrary size image sample. To solve the problem, a non-linear function is firstly proposed to control downsampling ratio that is ratio between the size of current image and the size of next downsampled image, to increase the ratio with increase of the number of downsampling. This makes the low-resolution images obtained by downsampling have higher proportion in all downsampled images. The low-resolution images usually contain much global information. Therefore, it can help the model to learn more global feature information from downsampled images. Secondly, the attention mechanism is introduced to the generative network to increase the weight of effective image information. This can make the network learn more local details. Besides, in order to make the output image more natural, the TVLoss function is introduced to the loss function of SinGAN, to reduce the difference between adjacent pixels and smear phenomenon for the output image. A large number of experimental results show that our proposed model has better performance than other methods in generating random samples with fixed size and arbitrary size, image harmonization and editing.

• Nuclear Engineering and Technology
• /
• v.54 no.8
• /
• pp.3043-3050
• /
• 2022

In Korea, all nuclear power plants (NPPs) participate in annual performance tests including in vivo measurements using the FastScan, a stand type whole body counter (WBC), manufactured by Canberra. In 2018, all Korean NPPs satisfied the testing criterion, the root mean square error (RMSE) ≤ 0.25, for the whole body configuration, but three NPPs which participated in an additional lung configuration test in the fission and activation product category did not meet the criterion. Due to the low resolution of the FastScan NaI(Tl) detectors, the conventional peak analysis (PA) method of the FastScan did not show sufficient performance to meet the criterion in the presence of interfering radioisotopes (RIs), ¹³⁴Cs and ¹³⁷Cs. In this study, we developed an artificial neural network (ANN) to improve the performance of the FastScan in the lung configuration. All of the RMSE values derived by the ANN satisfied the criterion, even though the photopeaks of ¹³⁴Cs and ¹³⁷Cs interfered with those of the analytes or the analyte photopeaks were located in a low-energy region below 300 keV. Since the ANN performed better than the PA method, it would be expected to be a promising approach to improve the accuracy and precision of in vivo FastScan measurement for the lung configuration.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.517-520
• /
• 2009

Healthcare application system has been actively researched to apply WSN technology to healthcare area with a mobile sensor node of low cost, low power, and small size. Sensor node has the problem for transmission range of RF power and time delay of the wireless routing connectivity between sensor nodes. In this paper, we proposes a new method utilizing mobile sensor nodes with relay sensor nodes for quick network routing changing using query technique in healthcare system. A query processor to control and manage the routing changing of sensor nodes in a wireless sensor network was designed and implemented. The user's PC transmits the beacon message which will change the quick link routing according to activity status of patient in wireless sensor network. We describe the implementation for query protocol that is very effective of power saving between sensor nodes.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.201-202
• /
• 2006

In this paper, we achieved software and hardware implementation of SHA-1 hash function for sensor network. We implemented the software to be compatible with TinySec. In hardware design, we optimized operation logics for small area of hardware and minimized data transitions of register memory for low power design. Designed the software and hardware is verified on commercial sensor motes and our secure motes respectively.

• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.461-462
• /
• 2007

DC Arc is an electric discharge which is occurred in two oppolsite electrode when system operating with DC current appliance. In this paper, DC arc detection system is designed for the display of DC arc fault current which is occurred in the local electric network with DC Power. This DC arc is one of the main causes of electric fire of dc system. Arc fault in electrical network has the characteristics of low current, high impedance and low frequency. DC Arc current detection device is designed for the display of arc fault current which has the modified arc characteristics.

• Smart Structures and Systems
• /
• v.6 no.5_6
• /
• pp.731-748
• /
• 2010

Impact detection and health monitoring are very important tasks for civil infrastructures, such as bridges. Piezoceramic based transducers are widely researched for these tasks due to the piezoceramic material's inherent advantages of dual sensing and actuation ability, which enables the active sensing method for structural health monitoring with a network of piezoceramic transducers. Wireless sensor networks, which are easy for deployment, have great potential in health monitoring systems for large civil infrastructures to identify early-age damages. However, most commercial wireless sensor networks are general purpose and may not be optimized for a network of piezoceramic based transducers. Wireless networks of piezoceramic transducers for active sensing have special requirements, such as relatively high sampling rate (at a few-thousand Hz), incorporation of an amplifier for the piezoceramic element for actuation, and low energy consumption for actuation. In this paper, a wireless network is specially designed for piezoceramic transducers to implement impact detection and active sensing for structural health monitoring. A power efficient embedded system is designed to form the wireless sensor network that is capable of high sampling rate. A 32 bit RISC wireless microcontroller is chosen as the main processor. Detailed design of the hardware system and software system of the wireless sensor network is presented in this paper. To verify the functionality of the wireless sensor network, it is deployed on a two-story concrete frame with embedded piezoceramic transducers, and the active sensing property of piezoceramic material is used to detect the damage in the structure. Experimental results show that the wireless sensor network can effectively implement active sensing and impact detection with high sampling rate while maintaining low power consumption by performing offline data processing and minimizing wireless communication.

• Journal of the Korea Society for Simulation
• /
• v.21 no.4
• /
• pp.47-56
• /
• 2012

In this study, we use a parallel simulator PASENS(Parallel SEnsor Network Simulator) to predict power consumption and data reception rate of the hierarchical routing protocols for sensor network - LEACH (Low-Energy Adaptive Clustering Hierarchy), TL-LEACH (Two Level Low-Energy Adaptive Clustering Hierarchy), M-LEACH (Multi hop Low-Energy Adaptive Clustering Hierarchy) and LEACH-C (LEACH-Centralized). According to simulation results, M-LEACH routing protocol shows the highest data reception rate for the wider area, since more sensor nodes are involved in the data transmission. And LEACH-C routing protocol, where the sink node considers the entire node's residual energy and location to determine the cluster head, results in the most efficient energy consumption and in the narrow area needed long life of sensor network.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.11 s.353
• /
• pp.1-7
• /
• 2006

This paper consider a code-division multiple-access(CDMA) wireless ad-hoc network in low-SINR regime. In previous research [6], there has been proposed a algorithm for achieving global optimum at high SINR regime, but has not been fully investigated at low-SINR regime. In this paper, we focus on a case where SINR is much smaller than 1, and propose a algorithm that is suitable for low-SINR regime.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.10a
• /
• pp.365-368
• /
• 2008

This paper presents a new concept of IP-based wireless sensor networks and also introduces a routing protocol that is based on clustering for global healthcare information system. Low-power wireless personal area networks (LoWPANs) conform the standard by IEEE 802.15.4-2003 to IPv6 that makes 6lowpan. It characterized by low bit rate, low power, and low cost as well as protocol for wireless connections. The 6lowpan node with biomedical sensor devices fixed on the patient body area network that should be connected to the gateway in personal area network. Each 6lowpan nodes have IP-addresses that would be directly connected to the internet. With the help of IP-address service provider can recognize or analysis patient biomedical data from anywhere on globe by internet service provider equipments such as cell phone, PDA, note book. The system has been evaluated by technical verification, clinical test, user survey and current status of patient. We used NS-2.33 simulator for our prototype and also simulate the routing protocols. The result shows the performance of biomedical data packets in multi-hope routing as well as represents the topology of the networks.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.11
• /
• pp.1879-1884
• /
• 2007

In the electric power industry, it is important that the supply of energy must be guaranteed. Many power utilities control and supervise the transmission line to avoid power failures. In case of underground tunnel, some troubles are reported in cable joint. To stabilize the power, it is needed to monitor the cable joint. Many researches of cable joint monitoring have been going on by partial discharge measurement and temperature measurement using optical cable. These methods need much cost to install and maintain, so it is only used in critical transmission line. In this research, we use wireless sensor technology, because of its low cost and easy installation. We develop the temperature monitoring system for cable joint. Temperature sensor is installed on the surface of cable joint and sends data to server through router node using wireless network. Generally Ad hoc routing is searched in wireless network. However, in this research, we design the static linear routing mechanism, which is suitable for electric power line monitoring and analyze the life time of the sensor node by measuring the amount of the battery consumption.