• The Journal of the Acoustical Society of Korea
• /
• v.22 no.5
• /
• pp.375-382
• /
• 2003

Lip-reading technique based on bimodal is to enhance speech recognition rate in noisy environment. It is most important to detect the correct lip-image. But it is hard to estimate stable performance in dynamic environment, because of many factors to deteriorate Lip-reading's performance. There are illumination change, speaker's pronunciation habit, versatility of lips shape and rotation or size change of lips etc. In this paper, we propose the IIR filtering in time-domain for the stable performance. It is very proper to remove the noise of speech, to enhance performance of recognition by digital filtering in time domain. While the lip-reading technique in whole lip image makes data massive, the Principal Component Analysis of pre-process allows to reduce the data quantify by detection of feature without loss of image information. For the observation performance of speech recognition using only image information, we made an experiment on recognition after choosing 22 words in available car service. We used Hidden Markov Model by speech recognition algorithm to compare this words' recognition performance. As a result, while the recognition rate of lip-reading using PCA is 64%, Time-domain filter applied to lip-reading enhances recognition rate of 72.4%.

• Nuclear Engineering and Technology
• /
• v.47 no.6
• /
• pp.678-699
• /
• 2015

Although the harsh space environment imposes many severe challenges to space pioneers, space exploration is a realistic and profitable goal for long-term humanity survival. One of the viable and promising options to overcome the harsh environment of space is nuclear propulsion. Particularly, the Nuclear Thermal Rocket (NTR) is a leading candidate for nearterm human missions to Mars and beyond due to its relatively high thrust and efficiency. Traditional NTR designs use typically high power reactors with fast or epithermal neutron spectrums to simplify core design and to maximize thrust. In parallel there are a series of new NTR designs with lower thrust and higher efficiency, designed to enhance mission versatility and safety through the use of redundant engines (when used in a clustered engine arrangement) for future commercialization. This paper proposes a new NTR design of the second design philosophy, Korea Advanced NUclear Thermal Engine Rocket (KANUTER), for future space applications. The KANUTER consists of an Extremely High Temperature Gas cooled Reactor (EHTGR) utilizing hydrogen propellant, a propulsion system, and an optional electricity generation system to provide propulsion as well as electricity generation. The innovatively small engine has the characteristics of high efficiency, being compact and lightweight, and bimodal capability. The notable characteristics result from the moderated EHTGR design, uniquely utilizing the integrated fuel element with an ultra heat-resistant carbide fuel, an efficient metal hydride moderator, protectively cooling channels and an individual pressure tube in an all-in-one package. The EHTGR can be bimodally operated in a propulsion mode of $100MW_{th}$ and an electricity generation mode of $100MW_{th}$, equipped with a dynamic energy conversion system. To investigate the design features of the new reactor and to estimate referential engine performance, a preliminary design study in terms of neutronics and thermohydraulics was carried out. The result indicates that the innovative design has great potential for high propellant efficiency and thrust-to-weight of engine ratio, compared with the existing NTR designs. However, the build-up of fission products in fuel has a significant impact on the bimodal operation of the moderated reactor such as xenon-induced dead time. This issue can be overcome by building in excess reactivity and control margin for the reactor design.

• Weed & Turfgrass Science
• /
• v.5 no.3
• /
• pp.111-125
• /
• 2016

Cordgrass (Spartina spp.) is recognized as a highly invasive plant in estuaries throughout the world because of remarkable versatility and resiliency, significant reproduction, strong adaptability, rapid spreading, and vigorous growth. In this review, therefore, to provide insights on the effective management practices, the previous research works were summarized and discussed. Spartina spp. is a perennial halophyte, warm-season (C4) grass that reproduces both sexually through seeds and asexually by rhizomes. Management strategies for cordgrass have included various physical, biological, and chemical controls. Herbicides are usually the most cost-effective means of control. Currently, glyphosate, imazapyr, fluazifop and haloxyfop have been practically used. To improve the control efficacy, a combination of two more than methods (example, mowing-spraying) is needed to be applied consistently every year for at least 3 to 4 years and to be sprayed with enough dry time (>4-6 hr) at an early growth stage (before flowering). Consistently repeated application of same herbicide have to be avoided to prevent an unexpected emergence of herbicide-resistant lines. On the other hand, Spartina spp. have many positive functions for agricultural and eco-engineering purposes. Thus, we have to give more intensive research for effectively managing advantages and disadvantages of Spartina plantations.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_1
• /
• pp.1669-1683
• /
• 2021

AI intelligent agriculture and digital agriculture are important for the science of agriculture. Leaf chlorophyll contents(LCC) are one of the most important indicators to determine the growth status of vegetable crops. In this study, a support vector machine (SVM) regression model was produced using an unmanned aerial vehicle-based RGB camera and a multispectral (MSP) sensor for onions and garlic, and the LCC estimation applicability of the RGB camera was reviewed by comparing it with the MSP sensor. As a result of this study, the RGB-based LCC model showed lower results than the MSP-based LCC model with an average R² of 0.09, RMSE 18.66, and nRMSE 3.46%. However, the difference in accuracy between the two sensors was not large, and the accuracy did not drop significantly when compared with previous studies using various sensors and algorithms. In addition, the RGB-based LCC model reflects the field LCC trend well when compared with the actual measured value, but it tends to be underestimated at high chlorophyll concentrations. It was possible to confirm the applicability of the LCC estimation with RGB considering the economic feasibility and versatility of the RGB camera. The results obtained from this study are expected to be usefully utilized in digital agriculture as AI intelligent agriculture technology that applies artificial intelligence and big data convergence technology.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.3
• /
• pp.282-289
• /
• 2019

Reflective and solar LED road studs are being used as a way of securing visibility for road environments. Road markers have various advantages and disadvantages in terms of versatility, efficiency, simplicity and visibility as individual products of reflective type and solar LED. However, in addition to the above, it is possible to prevent secondary accident after accident, It has a common drawback that it is difficult to have. In this paper, we propose a road stud system incorporating a wireless control function using RF - based communication with existing solar LED road studs and a system for controlling them. The proposed system is called the smart road stud system and it can control the equipment through the central control unit and the relay unit connected to the central control room by incorporating the RF communication function in the existing solar LED road stud. In addition, since it is possible to control the lighting method, color, etc. according to the road condition, it is possible to provide the driver with the state of the road to perform the function for preventing the second accident after the accident. It also adds features that minimize the ongoing power consumption of LED and RF communications. In order to verify the validity of the proposed system, prototypes were produced and it was confirmed that it is possible to act as a university for prevention of accident after accident by linking with other traffic system besides accident prevention function by securing existing visibility.

• The Journal of Bigdata
• /
• v.3 no.2
• /
• pp.59-70
• /
• 2018

In order to provide stable district heat supplying service to the certain limited residential area, it is the most important to forecast the short-term future demand more accurately and produce and supply heat in efficient way. However, it is very difficult to develop a universal heat demand forecasting model that can be applied to general situations because the factors affecting the heat consumption are very diverse and the consumption patterns are changed according to individual consumers and regional characteristics. In particular, considering all of the various variables that can affect heat demand does not help improve performance in terms of accuracy and versatility. Therefore, this study aims to develop a demand forecasting model using deep learning based on only limited information that can be acquired in real time. A demand forecasting model was developed by learning the artificial neural network of the Tensorflow using past data consisting only of the outdoor temperature of the area and date as input variables. The performance of the proposed model was evaluated by comparing the accuracy of demand predicted with the previous regression model. The proposed heat demand forecasting model in this research showed that it is possible to enhance the accuracy using only limited variables which can be secured in real time. For the demand forecasting in a certain region, the proposed model can be customized by adding some features which can reflect the regional characteristics.

• Nuclear Engineering and Technology
• /
• v.54 no.7
• /
• pp.2728-2735
• /
• 2022

The research on the flow and heat transfer characteristics of lead bismuth(LBE) is significant for the thermal-hydraulic calculation, safety analysis and practical application of lead-based fast reactors(LFR). In this paper, a new CFD model is proposed to solve the thermal-hydraulic analysis of LBE. The model includes two parts: turbulent model and turbulent Prandtl, which are the important factors for LBE. In order to find the best model, the experiment data and design of 19-pin hexagonal rod bundle with spacer grid, undertaken at the Karlsruhe Liquid Metal Laboratory (KALLA) are used for CFD calculation. Furthermore, the turbulent model includes SST k - 𝜔 and k - 𝜀; the turbulent Prandtl includes Cheng-Tak and constant (Pr_t =1.5,2.0,2.5,3.0). Among them, the combination between SST k - 𝜔 and Cheng-Tak is more suitable for the experiment. But in the low Pe region, the deviation between the experiment data and CFD result is too much. The reason may be the inlet-effect and when Pe is in a low level, the number of molecular thermal diffusion occupies an absolute advantage, and the buoyancy will enhance. In order to test and verify versatility of the model, the NCCL performed by the Nuclear Thermal-hydraulic Laboratory (Nuthel) of Xi'an Jiao tong University is used for CFD to calculate. This paper provides two verification examples for the new universal model.

• Journal of Life Science
• /
• v.32 no.2
• /
• pp.155-160
• /
• 2022

Kenaf (Hibiscus cannabinus L.), one of the four major fiber crops, is attracting attention for its efficient CO₂-absorbing ability and versatility for producing daily supplies, including textiles. In Korea, a new cultivar 'Jangdae' was established in 2013. The ease of cultivation and seed gathering of 'Jangdae' has led to its nationwide cultivation. However, evaluation of the bioactivities of the different parts of kenaf, and especially the 'Jangdae' cultivar, remains rudimentary. In this study, the antithrombosis and antioxidant activities of extracts prepared from different parts of the 'Jangdae' cultivar were evaluated by determining their effects on blood clot formation. Extracts prepared from seeds (HC-SD), seedpods (HC-SP), leaves (HC-L), stems (HC-S), and roots (HC-R) of the 'Jangdae' cultivar strongly inhibited blood clot formation. In particular, the HC-SD, HC-SP, and HC-S extracts showed strong inhibition against the coagulation factors prothrombin, and thrombin. The HC-SP extract showed strong antioxidant activities, such as scavenging ability against DPPH anion, ABTS cation, nitrite, and reducing power. Since blood clot formation is closely related to oxidative stress, the HC-SP extract could be developed as a novel anticoagulation and antioxidant resource. This is the first report of the antithrombosis activities of different parts of H. cannabinus L. cv. 'Jangdae'.

• Journal of Internet Computing and Services
• /
• v.23 no.6
• /
• pp.1-13
• /
• 2022

As the information and communication environment develops, the environment of military facilities is also development remarkably. In proportion to this, cyber threats are also increasing, and in particular, APT attacks, which are difficult to prevent with existing signature-based cyber defense systems, are frequently targeting military and national infrastructure. It is important to identify attack groups for appropriate response, but it is very difficult to identify them due to the nature of cyber attacks conducted in secret using methods such as anti-forensics. In the past, after an attack was detected, a security expert had to perform high-level analysis for a long time based on the large amount of evidence collected to get a clue about the attack group. To solve this problem, in this paper, we proposed an automation technique that can classify an attack group within a short time after detection. In case of APT attacks, compared to general cyber attacks, the number of attacks is small, there is not much known data, and it is designed to bypass signature-based cyber defense techniques. As an attack model, we used MITRE ATT&CK® which modeled many parts of cyber attacks. We design an impact score considering the versatility of the attack techniques and proposed a group similarity score based on this. Experimental results show that the proposed method classified the attack group with a 72.62% probability based on Top-5 accuracy.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1513-1513
• /
• 2001

Present Food Legislation compels dairy industry to carry out analyses in order to guarantee the food safety and quality of products. Furthermore, in many cases industry pays milk according to bacteriological or/and nutritional quality. In order to do these analyses, several expensive instruments are needed (Milkoscan, Fossomatic, Bactoscan). NIRS technology Provides a unique instrument to deal with all analytical requirements. It offers as main advantages its speed and, specially, its versatility, since not only allows determine all the parameters required in milk analysis, but also allows analyse other dairy products, like cheese or whey. The objective of this study is to develop NIRS calibration equations to predict several quality parameters in goat milk, cheese and whey. Three sets of 123 milk samples, 190 cheese samples and 109 whey samples, have been analysed in a FOSS NIR Systems 6500 I spectrophotometer equipped with a spinning module. Milk and whey were analysed by folded transmission, using circular cells with gold surface and pathlength of 0.1 m, while intact cheese was analysed by reflectance using standard circular cells. NIRS calibrations were obtained for the prediction of chemical composition in goat milk, for fat (r$^2$=0.92; SECV=0.20%), total solids (r$^2$=0.95: SECV=0.22%), protein (r$^2$=0.94; SECV=0.07%), casein (r$^2$=0.93; SECV=0.07%) and lactose (r$^2$=0.89; SECV=0.05%). Moreover, equations have been performed to determine somatic cells (r$^2$=0.81; SECV=276.89%) and total bacteria (r$^2$=0.58; SECV=499.32%) counts in goat milk. In the case of cheese, calibrations were obtained for the prediction of fat (r$^2$=0.92; SECV=0.57), total solids (r$^2$=0.80; SECV=0.92%) and protein (r$^2$=0.70; SECV=0.63%). In whey, fat (r$^2$=0.66; SECV=0.08%), total solids (r$^2$=0.67; SECV=0.19%) and protein (r$^2$=0.76; SECV=0.07%) NIRS equations were obtained. These results proved the viability of NIRS technology to predict chemical and microbiological parameters and somatic cells count in goat milk, as well as chemical composition of goat cheese and whey.