• KSCE Journal of Civil and Environmental Engineering Research
• /
• 제26권6B호
• /
• pp.597-603
• /
• 2006

The purpose of this study is to improve the short term rainfall forecast skill using neural network model that can deal with the non-linear behavior between satellite data and ground observation, and minimize the flood damage. To overcome the geographical limitation of Korean peninsula and get the long forecast lead time of 3 to 6 hour, the developed rainfall forecast model took satellite imageries and wide range AWS data. The architecture of neural network model is a multi-layer neural network which consists of one input layer, one hidden layer, and one output layer. Neural network is trained using a momentum back propagation algorithm. Flood was estimated using rainfall forecasts. We developed a dynamic flood inundation model which is associated with 1-dimensional flood routing model. Therefore the model can forecast flood aspect in a protected lowland by levee failure of river. In the case of multiple levee breaks at main stream and tributaries, the developed flood inundation model can estimate flood level in a river and inundation level and area in a protected lowland simultaneously.

• Journal of Navigation and Port Research
• /
• 제46권6호
• /
• pp.483-490
• /
• 2022

Floating LiDAR is a system that provides a new paradigm for wind condition observation, which is essential when creating an offshore wind farm. As it can save time and money, minimize environmental impact, and even reduce backlash from local communities, it is emerging as the industry standard. However, the design and verification of a stable platform is very important, as disturbance factors caused by fluctuations of the buoy affect the reliability of observation data. In Korea, due to the nation's late entry into the technology, a number of foreign equipment manufacturers are dominating the domestic market. The west coast of Korea is a shallow sea environment with a very large tidal difference, so strong currents repeatedly appear depending on the region, and waves of strong energy that differ by season are formed. This paper conducted a study examining buoys suitable for LiDAR operation in the waters of Korea, which have such complex environmental characteristics. In this paper, we will introduce examples of optimized design and verification of ship-type buoys, which were applied first, and derive important concepts that will serve as the basis for the development of various platforms in the future.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• 제46권1호
• /
• pp.98-106
• /
• 2009

This work proposes a 1280-RGB $\times$ 800-Dot 70.78mW 0.l3um CMOS LCD driver IC (LDI) for high-performance 16M-color low temperature poly silicon (LTPS) thin film transistor liquid crystal display (TFT-LCD) systems such as ultra mobile PC (UMPC) and mobile applications simultaneously requiring high resolution, low power, and small size at high speed. The proposed LDI optimizes power consumption and chip area at high resolution based on a resistor-string based architecture. The single column driver employing a 1:12 MUX architecture drives 12 channels simultaneously to minimize chip area. The implemented class-AB amplifier achieves a rail-to-rail operation with high gain and low power while minimizing the effect of offset and output deviations for high definition. The supply- and temperature-insensitive current reference is implemented on chip with a small number of MOS transistors. A slew enhancement technique applicable to next-generation source drivers, not implemented on this prototype chip, is proposed to reduce power consumption further. The prototype LDI implemented in a 0.13um CMOS technology demonstrates a measured settling time of source driver amplifiers within 1.016us and 1.072us during high-to-low and low-to-high transitions, respectively. The output voltage of source drivers shows a maximum deviation of 11mV. The LDI with an active die area of $12,203um{\times}1500um$ consumes 70.78mW at 1.5V/5.5V.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• 제32권3호
• /
• pp.1-9
• /
• 2014

This article is the results of excavation data and it aims to interpret the composition facilities of the Royal garden at the Wanggung-ri site. The base of research was prepared through excavation and study on the royal garden at the Wanggung-ri site, which was constructed in Sa-bi period of Baek-je. The elements for the royal garden at the Wanggung-ri site were divided in 3 parts. - 1) Stonework facility 2) Installation for conveyance of water : Large moat-shaped ditch and Winding waterway(1~6 and water catchment) 3) Square cornerstone building. In this article, I arrange the basic data about facilities and function of the royal garden for making recovery of original form. First of all, I reason that stonework facilities were in charge to make space for catchment and boundary. Especially the Round angel rectangular stonework facility took charge of complex roles as catchment and water conveyance, and water can be transferred to the large moat-shaped ditch through joint between them. I confirmed that the round angel rectangular stonework facility and the large moat-shaped ditch which were connected by joint are one of the facilities in the royal garden. The large moat-shaped ditch protected the eastern, the northern walls and workshop site under the inclined plane to minimize the damage. Also, the large moat-shaped ditch took several roles, especially water catchments and landscaping. The large moat-shaped ditch was continually used from the period of Baek-je to the unified Silla, as a result it was completely deposited inside. After that, the 6 winding waterway were built in the western inclined plane with similar needs with the large moat-shaped ditch, and the square cornerstone building was built in same time. I noticed that the square cornerstone building was built as a part of the royal garden in Sa-bi period of Baek-je through the remains of Baek-je tiles around the building. After that, the square cornerstone building was built in same place as reconstruction.

• Journal of Intelligence and Information Systems
• /
• 제22권2호
• /
• pp.127-142
• /
• 2016

Deep learning model is a kind of neural networks that allows multiple hidden layers. There are various deep learning architectures such as convolutional neural networks, deep belief networks and recurrent neural networks. Those have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. Among those architectures, convolutional neural networks and recurrent neural networks are classified as the supervised learning model. And in recent years, those supervised learning models have gained more popularity than unsupervised learning models such as deep belief networks, because supervised learning models have shown fashionable applications in such fields mentioned above. Deep learning models can be trained with backpropagation algorithm. Backpropagation is an abbreviation for "backward propagation of errors" and a common method of training artificial neural networks used in conjunction with an optimization method such as gradient descent. The method calculates the gradient of an error function with respect to all the weights in the network. The gradient is fed to the optimization method which in turn uses it to update the weights, in an attempt to minimize the error function. Convolutional neural networks use a special architecture which is particularly well-adapted to classify images. Using this architecture makes convolutional networks fast to train. This, in turn, helps us train deep, muti-layer networks, which are very good at classifying images. These days, deep convolutional networks are used in most neural networks for image recognition. Convolutional neural networks use three basic ideas: local receptive fields, shared weights, and pooling. By local receptive fields, we mean that each neuron in the first(or any) hidden layer will be connected to a small region of the input(or previous layer's) neurons. Shared weights mean that we're going to use the same weights and bias for each of the local receptive field. This means that all the neurons in the hidden layer detect exactly the same feature, just at different locations in the input image. In addition to the convolutional layers just described, convolutional neural networks also contain pooling layers. Pooling layers are usually used immediately after convolutional layers. What the pooling layers do is to simplify the information in the output from the convolutional layer. Recent convolutional network architectures have 10 to 20 hidden layers and billions of connections between units. Training deep learning networks has taken weeks several years ago, but thanks to progress in GPU and algorithm enhancement, training time has reduced to several hours. Neural networks with time-varying behavior are known as recurrent neural networks or RNNs. A recurrent neural network is a class of artificial neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior. Unlike feedforward neural networks, RNNs can use their internal memory to process arbitrary sequences of inputs. Early RNN models turned out to be very difficult to train, harder even than deep feedforward networks. The reason is the unstable gradient problem such as vanishing gradient and exploding gradient. The gradient can get smaller and smaller as it is propagated back through layers. This makes learning in early layers extremely slow. The problem actually gets worse in RNNs, since gradients aren't just propagated backward through layers, they're propagated backward through time. If the network runs for a long time, that can make the gradient extremely unstable and hard to learn from. It has been possible to incorporate an idea known as long short-term memory units (LSTMs) into RNNs. LSTMs make it much easier to get good results when training RNNs, and many recent papers make use of LSTMs or related ideas.

• Journal of Intelligence and Information Systems
• /
• 제27권1호
• /
• pp.191-207
• /
• 2021

Up to this day, mobile communications have evolved rapidly over the decades, mainly focusing on speed-up to meet the growing data demands of 2G to 5G. And with the start of the 5G era, efforts are being made to provide such various services to customers, as IoT, V2X, robots, artificial intelligence, augmented virtual reality, and smart cities, which are expected to change the environment of our lives and industries as a whole. In a bid to provide those services, on top of high speed data, reduced latency and reliability are critical for real-time services. Thus, 5G has paved the way for service delivery through maximum speed of 20Gbps, a delay of 1ms, and a connecting device of 106/㎢ In particular, in intelligent traffic control systems and services using various vehicle-based Vehicle to X (V2X), such as traffic control, in addition to high-speed data speed, reduction of delay and reliability for real-time services are very important. 5G communication uses high frequencies of 3.5Ghz and 28Ghz. These high-frequency waves can go with high-speed thanks to their straightness while their short wavelength and small diffraction angle limit their reach to distance and prevent them from penetrating walls, causing restrictions on their use indoors. Therefore, under existing networks it's difficult to overcome these constraints. The underlying centralized SDN also has a limited capability in offering delay-sensitive services because communication with many nodes creates overload in its processing. Basically, SDN, which means a structure that separates signals from the control plane from packets in the data plane, requires control of the delay-related tree structure available in the event of an emergency during autonomous driving. In these scenarios, the network architecture that handles in-vehicle information is a major variable of delay. Since SDNs in general centralized structures are difficult to meet the desired delay level, studies on the optimal size of SDNs for information processing should be conducted. Thus, SDNs need to be separated on a certain scale and construct a new type of network, which can efficiently respond to dynamically changing traffic and provide high-quality, flexible services. Moreover, the structure of these networks is closely related to ultra-low latency, high confidence, and hyper-connectivity and should be based on a new form of split SDN rather than an existing centralized SDN structure, even in the case of the worst condition. And in these SDN structural networks, where automobiles pass through small 5G cells very quickly, the information change cycle, round trip delay (RTD), and the data processing time of SDN are highly correlated with the delay. Of these, RDT is not a significant factor because it has sufficient speed and less than 1 ms of delay, but the information change cycle and data processing time of SDN are factors that greatly affect the delay. Especially, in an emergency of self-driving environment linked to an ITS(Intelligent Traffic System) that requires low latency and high reliability, information should be transmitted and processed very quickly. That is a case in point where delay plays a very sensitive role. In this paper, we study the SDN architecture in emergencies during autonomous driving and conduct analysis through simulation of the correlation with the cell layer in which the vehicle should request relevant information according to the information flow. For simulation: As the Data Rate of 5G is high enough, we can assume the information for neighbor vehicle support to the car without errors. Furthermore, we assumed 5G small cells within 50 ~ 250 m in cell radius, and the maximum speed of the vehicle was considered as a 30km ~ 200 km/hour in order to examine the network architecture to minimize the delay.

• Journal of the Korean Institute of Landscape Architecture
• /
• 제41권6호
• /
• pp.52-61
• /
• 2013

This study was conducted to investigate the effects of pergola's shading on the thermal comfort index in the summer. The 3 type of pergolas($4m{\times}4m{\times}h2.7m$) which were screened overhead(I)/overhead west(II)/overhead west north(III) plane with reed blind for summer shading and winter wind break, were constructed on the 4th floor rooftop. Thereafter the meteorological variables(air temperature, humidity, radiation, and wind speed) of pergola I, III and rooftop were measured from 14 to 16 August 2013(1st experiment), those of pergola I, II and rooftop were measured from 26 to 28 August 2013(2nd experiment). The effects of pergola's shading on the radiation environment and mean radiant temperature($T_{mrt}$), standard effective temperature($SET^*$) were as follows. The maximum 1 h mean values of differences ${\Delta}$ of the sums of shortwave radiant flux densities absorbed by the human body (${\Delta}K_{abs,max}$) between pergola I, III and nearby sunny rooftop were $-119W/m^2$, $-158W/m^2$, those between pergola I, II and rooftop were $-145W/m^2$, $-159W/m^2$. The maximum 1 h mean values of differences ${\Delta}$ of the sums of long wave radiant flux densities absorbed by the human body (${\Delta}L_{abs,max}$) between pergola I, III and nearby sunny rooftop, were $-15W/m^2$, $-17W/m^2$, those between pergola I, II and nearby rooftop, were $-8W/m^2$, $-7W/m^2$. The response of the direction dependent long wave radiant flux densities $L_1$ on the pergola's shading turned out to be distinctly weaker as compared to shortwave radiant flux densities $K_1$. The pergola's shading leads to a lowering of $T_{mrt}$ and $SET^*$. The peak values of $T_{mrt}$ absorbed by the human body were decreased $16^{\circ}C$ and $21.4^{\circ}C$ under pergola I and III as compared to that of nearby rooftop in the 1st experiment. Those were decreased $18.8^{\circ}C$ and $20.8^{\circ}C$ under pergola I and II as compared to that of nearby rooftop in the 2nd experiment. The peak values of $SET^*$ absorbed by the human body were decreased $2.9^{\circ}C$ and $2.6^{\circ}C$ under pergola I and III as compared to that of nearby rooftop in the 1st experiment. Those were decreased $3.5^{\circ}C$ and $2.6^{\circ}C$ under pergola I and II as compared to that of nearby rooftop in the 2nd experiment. The relative $SET^*$ decrease in pergola II, III compared to nearby sunny rooftop $SET^*$ were lower than that in pergola I, revealing the influence of the wind speed. Therefore it is essential to design pergola to maximize wind speed and minimize solar radiation to achieve comfort in the hot summer. The $SET^*$ under pergola I, III were exceeded $28.7^{\circ}C$ and $30.4^{\circ}C$ which were the upper limit of thermal comfort and tolerable zone during all most daytimes in the 1st experiment(maximum air temperature $37.5^{\circ}C$). The $SET^*$ under pergola I was exceeded $28.7^{\circ}C$ which was the upper limit of thermal comfort zone at 13h, that under pergola II was exceeded $28.7^{\circ}C$ from 8h to 14h, meanwhile the $SET^*$ under pergola I, II were within thermal tolerable zone during most daytimes in the 2nd experiment(maximum air temperature $34.4^{\circ}C$). Therefore to ensure the thermal comfort of pergola for summer hottest days, pergola should be shaded with not only reed blind but also climbing and shade plants. $T_{mrt}$ and $SET^*$ were suitable index for the evaluation of pergola's shading effects and outdoors.

• Korean Journal of Environment and Ecology
• /
• 제24권4호
• /
• pp.395-405
• /
• 2010

This study was carried out to offer basic data to minimize the indiscreet development and damage of coastal wetlands through an evaluation from an ecological standpoint highlighting the importance of the coastal wetland in South Gyeongsang Province, Korea. The result of the macrobenthos survey for the coastal wetland assessment showed that Dongdal and Hwasan-ri, Yongnam-myeon, and Tongyeong city had the largest species number; Oegan-ri and Naegan-ri, Geoje-myeon, and Geoje city had the largest population and biomass; and Miryong-ri, Samsan-myeon, Goseong-gun had the highest species diversity. In the halophytes survey, Imyeong-ri, Jinjeon-myeon, Masan city and Oegan-ri and Naegan-ri, Geoje-myeon, Geoje city had the large character species and companion species. The evaluation results of the ecological values of the coastal wetlands were categorized into five grades based on the field surveys, and the sedimentary environment factor in the case of Danghang-ri, Hoehwa-myeon, and Goseong-gun; Miryong-ri, Samsan-myeon, Goseong-gun; Guho-ri, Gonyang-myeon, Sacheon city; Sulsang-ri Yangpo-ri, Jingyo-myeon, Hadong-gun; and Seokpyeong-ri, Idong-myeon, Namhae-gun, were appraised at the highest rating of grade II. The halophytes factor in the case of Imyeong-ri, Jinjeon-myeon, Masan city, Dongdal-ri and Hwasan-ri, Yongnam-myeon, Tongyeong city and Oegan-ri and Naegan-ri, Geoje-myeon, Geoje city, were highly evaluated as grade II. The macrobenthos factor in the case of Imyeong-ri, Jinjeon-myeon, Masan city and Oegan-ri and Naegan-ri, Geoje-myeon, Geoje city was highly evaluated as grade II. The final evaluation grade was calculated by the mean values of three evaluation factors, and Imyeong-ri, Jinjeon-myeon, Masan city and Oegan-ri and Naegan-ri, Geoje-myeon, and Geoje city had the highest rating of II. On the other hand, Seokpyeong-ri, Idong-myeon, Namhae-gun had the lowest rating of IV. These locations will require future research to survey and monitor the coastal wetland ecosystems by season, in addition to the construction of the GIS-based wetland information system with a view to manage the coastal wetlands.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• 제46권3호
• /
• pp.60-68
• /
• 2009

This work proposes a 10b 200MS/s 65nm CMOS ADC for high-definition video systems such as HDTV requiring high resolution and fast operating speed simultaneously. The proposed ADC employs a four-step pipeline architecture to minimize power consumption and chip area. The input SHA based on four capacitors reduces the output signal range from $1.4V_{p-p}$ to $1.0V_{p-p}$ considering high input signal levels at a low supply voltage of 1.2V. The proposed three-stage amplifiers in the input SHA and MDAC1 overcome the low output resistance problem as commonly observed in a 65nm CMOS process. The proposed multipath frequency-compensation technique enables the conventional RNMC based three-stage amplifiers to achieve a stable operation at a high sampling rate of 200MS/s. The conventional switched-bias power-reduction technique in the sub-ranging flash ADCs further reduces power consumption while the reference generator integrated on chip with optional off-chip reference voltages allows versatile system a locations. The prototype ADC in a 65nm CMOS technology demonstrates a measured DNL and INL within 0.19LSB and 0.61LSB, respectively. The ADC shows a maximum SNDR of 54.BdB and 52.4dB and a maximum SFDR of 72.9dB and 64.8dB at 150MS/S and 200MS/s, respectively. The proposed ADC occupies an active die area of $0.76mm^2$ and consumes 75.6mW at a 1.2V supply voltage.

• Journal of Intelligence and Information Systems
• /
• 제16권2호
• /
• pp.73-94
• /
• 2010

The attending system is a medical system that allows doctors in clinics to use the extra equipment in hospitals-beds, laboratory, operating room, etc-for their patient's care under a contract between the doctors and hospitals. Therefore, the system is very beneficial in terms of the efficiency of the usage of medical resources. However, it is necessary to develop a strong support system to strengthen its weaknesses and supplement its merits. If doctors use hospital beds under the attending system of hospitals, they would be able to check a patient's condition often and provide them with nursing care services. However, the current attending system lacks delivery and assistance support. Thus, for the successful performance of the attending system, a networking system should be developed to facilitate communication between the doctors and nurses. In particular, the nursing records in the attending system could help doctors monitor the patient's condition and provision of nursing care services. A nursing record is the formal documentation associated with nursing care. It is merely a data repository that helps nurses to track their activities; nursing records thus represent a resource of primary information that can be reused. In order to maximize their usefulness, nursing records have been introduced as part of computerized patient records. However, nursing records are internal data that are not disclosed by hospitals. Moreover, the lack of standardization of the record list makes it difficult to share nursing records. Under the attending system, nurses would want to minimize the amount of effort they have to put in for the maintenance of additional records. Hence, they would try to maintain the current level of nursing records in the form of record lists and record attributes, while doctors would require more detailed and real-time information about their patients in order to monitor their condition. Therefore, this study developed a system for assisting in the maintenance and sharing of the nursing records under the attending system. In contrast to previous research on the functionality of computer-based nursing records, we have emphasized the practical usefulness of nursing records from the viewpoint of the actual implementation of the attending system. We suggested that nurses could design a nursing record dictionary for their convenience, and that doctors and nurses could confirm the definitions that they looked up in the dictionary through negotiations with intelligent agents. Such an agent-based system could facilitate networking among medical institutes. Multi-agent systems are a widely accepted paradigm for the distribution and sharing of computation workloads in the scientific community. Agent-based systems have been developed with differences in functional cooperation, coordination, and negotiation. To increase such communication, a framework for a multi-agent based system is proposed in this study. The agent-based approach is useful for developing a system that promotes trade-offs between transactions involving multiple attributes. A brief summary of our contributions follows. First, we propose an efficient and accurate utility representation and acquisition mechanism based on a preference scale while minimizing user interactions with the agent. Trade-offs between various transaction attributes can also be easily computed. Second, by providing a multi-attribute negotiation framework based on the attribute utility evaluation mechanism, we allow both the doctors in charge and nurses to negotiate over various transaction attributes in the nursing record lists that are defined by the latter. Third, we have designed the architecture of the nursing record management server and a system of agents that provides support to the doctors and nurses with regard to the framework and mechanisms proposed above. A formal protocol has also been developed to create and control the communication required for negotiations. We verified the realization of the system by developing a web-based prototype. The system was implemented using ASP and IIS5.1.