• Journal of Energy Engineering
• /
• v.5 no.2
• /
• pp.160-169
• /
• 1996

Parametric studies are conducted for optimizing the integration design between gas turbine compressor and air separation unit (ASU) of integrated gasification combined cycle power plant. The present study adopts the ASU of double-distillation column process, from which integration conditions with compressor such as the heat exchanger condition between air and nitrogen, the amount and the pressure of extracted air are defined and mathematically formulated. The performance variations of the compressor integrated with ASU are analyzed by combining streamline curvature method and pressure loss models, and the predicted results are compared with the performance test results of actual compressors to verify the prediction accuracy. Using the present performance prediction method, the effects of pinch-point temperature difference (PTD) in the heat exchanger, the amount and the pressure of extracted air on compressor performances are quantitatively examined. As the extraction air amount or the PTD is increased, the pressure ratio and the power consumption of compressor are increased. The compressor efficiency deteriorates as the increase of the flow rate of air extracted at higher pressure level while improving at lower pressure air extraction. Furthermore, through the characteristic curve between generalized inlet condition and efficiency of compressor, optimal integration condition is presented to maximize the compressor efficiency.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.4
• /
• pp.1400-1418
• /
• 2020

In the development of commercial promotion, chatbot is known as one of significant skill by application of natural language processing (NLP). Conventional design methods are using bag-of-words model (BOW) alone based on Google database and other online corpus. For one thing, in the bag-of-words model, the vectors are Irrelevant to one another. Even though this method is friendly to discrete features, it is not conducive to the machine to understand continuous statements due to the loss of the connection between words in the encoded word vector. For other thing, existing methods are used to test in state-of-the-art online corpus but it is hard to apply in real applications such as telemarketing data. In this paper, we propose an improved chatbot design way using hybrid bag-of-words model and skip-gram model based on the real telemarketing data. Specifically, we first collect the real data in the telemarketing field and perform data cleaning and data classification on the constructed corpus. Second, the word representation is adopted hybrid bag-of-words model and skip-gram model. The skip-gram model maps synonyms in the vicinity of vector space. The correlation between words is expressed, so the amount of information contained in the word vector is increased, making up for the shortcomings caused by using bag-of-words model alone. Third, we use the term frequency-inverse document frequency (TF-IDF) weighting method to improve the weight of key words, then output the final word expression. At last, the answer is produced using hybrid retrieval model and generate model. The retrieval model can accurately answer questions in the field. The generate model can supplement the question of answering the open domain, in which the answer to the final reply is completed by long-short term memory (LSTM) training and prediction. Experimental results show which the hybrid word vector expression model can improve the accuracy of the response and the whole system can communicate with humans.

• Journal of Internet Computing and Services
• /
• v.21 no.3
• /
• pp.133-144
• /
• 2020

The number of elderly people with dementia is increasing as fast as the proportion of older people due to aging, which creates a social and economic burden. In particular, dementia care costs, including indirect costs such as increased care costs due to lost caregiver hours and caregivers, have grown exponentially over the years. In order to reduce these costs, it is urgent to introduce a management system to care for dementia patients. Therefore, this study proposes a sensor-based abnormal behavior detection system to manage dementia patients who live alone or in an environment where they cannot always take care of dementia patients. Existing studies were merely evaluating behavior or evaluating normal behavior, and there were studies that perceived behavior by processing images, not data from sensors. In this study, we recognized the limitation of real data collection and used both the auto-encoder, the unsupervised learning model, and the LSTM, the supervised learning model. Autoencoder, an unsupervised learning model, trained normal behavioral data to learn patterns for normal behavior, and LSTM further refined classification by learning behaviors that could be perceived by sensors. The test results show that each model has about 96% and 98% accuracy and is designed to pass the LSTM model when the autoencoder outlier has more than 3%. The system is expected to effectively manage the elderly and dementia patients who live alone and reduce the cost of caring.

• Journal of Food Hygiene and Safety
• /
• v.35 no.3
• /
• pp.252-260
• /
• 2020

This study was conducted to improve the standard method for vitamin B₁₂ and biotin contained in foods for special dietary uses to ensure the specificity of the complex matrix properties of foods. For the food code, the test method was improved to determine vitamin B₁₂ and biotin by high-performance liquid chromatography (HPLC)-UV using column-switching after concentration using immunoaffinity column. The immunoaffinity columns contain a gel suspension of monoclonal antibody specific to the vitamin of interest so that it can be used to concentrate the vitamin B₁₂ and biotin and remove interferences from the food extracts. Moreover, validation of advanced new methods was carried out to support the suitability of the proposed analytical procedure (specificity, linearity, detection limits (LOD), quantitative limits (LOQ), accuracy, and precision). The improved analytical method is being used to monitor relevant food items on sale. The results of this study showed that the new analytical method is suitable and appropriate for managing food intended for special dietary uses.

• Fire Science and Engineering
• /
• v.27 no.6
• /
• pp.1-7
• /
• 2013

In this study, the effects of various disk shapes of hydrant on the pressure drop are experimentally and numerically analyzed. The test methods for measuring pressure drop of hydrant are comply with standard of Underwriters Laboratory (UL). The hydrant as used in this study has one inlet, diameter 150 mm, and three outlet, 114.3 mm diameter for one outlet and 63.5 mm diameter for the others. The pressure of the hydrant are measured in the range 760 L/min~2,270 L/min for 63.5 mm outlet and 3,030 L/min~6,060 L/min for 114.3 mm outlet. Also, the numerical results of pressure drop are compared with the experiments to verify the accuracy and to analyze the of various valve shape of hydrant on the pressure drop. The engineering parameters, flow coefficients, are reduced from 181.57 to 136.35 ($L/min/kPa^{0.5}$) with inclined angle of disk from $0^{\circ}$ to $45^{\circ}$. These results are able to practical use for design hydrant to minimize pressure drop.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.6_1
• /
• pp.463-469
• /
• 2013

In addition to the VRS-RTK service, FKP-RTK service launched recently in Korea however unlike VRS, it is not yet applied to various surveying tasks. VRS system is operated in two way communication over the mobile Internet. When user send rover position data to network RTK server and the server provides correction data to users continuously. It causes to increase communications load and makes delaying or failure in data transmission depends on server capacity and number of concurrent users. In contrast, since FKP system is one way communication system, user only receives correction data and area correction parameters for the selected Continuous Reference Station from the server. Thus, there is no limitation to the number of concurrent users in FKP system and it would be more efficient than VRS system in terms of economic. To this end, we performed FKP-RTK test for Unified Control Points and Urban Control Points where are located at 5 regions in Korea to evaluate the accuracy. As a result, almost of FKP positioning data are in error range of ${\pm}6.2cm$ in horizontal and it would be enough for construction survey such as for earth work in limited except precise structure survey.

• Korean Journal of Pharmacognosy
• /
• v.41 no.2
• /
• pp.147-152
• /
• 2010

The capability of the solvents for extracting the bioactive saponins from the roots of Platycodon grandiflorum (Campanulaceae) was investigated to obtain an ideal extract which contained bioactive saponins with high quality and high quantity. The content of eight representative saponins in extracts, such as deapioplatycoside E, platycoside E, platyconic acid A and platycodin D, platycodin $D_3$, platycodin $D_2$, polygalacin $D_2$, polygalacin D were analyzed simultaneousely by the modified HPLC analytical method. The validation test of the modified qualitative and quantitative analytical method employing the ELSD equipped HPLC for eight representative saponins in the roots extract of P. grandiflorum showed a good linearity, precision and accuracy. the correlation coefficient ($r^2$) values of the calbration curves for each saponins were observed to be over 0.9990. LOD and LOQ of each saponin was calculated as $0.10{\mu}g{\sim}0.40{\mu}g$ (LOD) and $0.40{\mu}g{\sim}0.80{\mu}g$ (LOQ), respectively. Recovery rates of each saponin were also calculated as over 98%, respectively. With exception of two saponins, platyconic acid A and platycodin D, The content of eight saponins in extracts was decreased proportionally to the increment of the water ratio of solvent for extraction. Consequently, as aquous alcohol was used as a solvent for extracting the saponin components from powdered roots of P. grandiflorum, the water content in the aquous alcohol was seemed to be a critical factor for extracting efficacy. The 60-80% ratio of alcohol in the aquous alcohol were deduced to be suitable and recommendable for the preparation of roots extract of P. grandiflorum which contained saponins with high quality and high quantity.

• Tunnel and Underground Space
• /
• v.16 no.1 s.60
• /
• pp.50-57
• /
• 2006

Development of structures such as slope and tunnel, waste disposal, oil and LPG storages, and underground power house and so on, is increasing with the year. The method for appropriate estimation of rock state such as fresh or damaged rocks is also requested with increasing structural development. On these purposes, seismic logging system, which is a simple and easy way for handling as well as small and light, has been developed. Seismic logging method is one of logging tests, which is able to evaluate the state of rock mass with various shapes and is possible to obtain the relatively accuracy data at situ state. In addition, seismic logging method is at to apply to estimate structural behavior, before and after support installed. According to the results obtained from this study, firstly, it is clear that the extent of damage in rock slope due to blasting is able to be evaluated with quantity using seismic logging method, moreover to decide the damage zone in rock slope reasonably. Secondly, it is expected that installing depth of support is able to be decided more effectively and economically, using the results of seismic logging data. Finally, seismic logging method is also able to be applied safety supervision of structures, before and after support installed.

• Journal of radiological science and technology
• /
• v.40 no.2
• /
• pp.205-211
• /
• 2017

There is a need for aggressive diagnosis and treatment in middle-aged and high-risk individuals who are more likely to progress from nonalcoholic fatty liver to hepatitis. In this study, nonalcoholic fatty liver was divided into severe, moderate, and severe, and classified by quantitative method using computer analysis of GLCM algorithm. The purpose of this study was to evaluate the characteristics of ultrasound images in the local fat avoidance region. Normal, mild, moderate, severe fatty liver, and focal fat sparing area, 80 cases, respectively. Among the parameters of the GLCM algorithm, the values of the Autocorrelation, Square of the deviation, Sum of averages and Sum of variances with high recognition rate of the liver ultrasound image were calculated. The average recognition rate of the GLCM algorithm was 97.5%. The result of local fat avoidance image analysis showed the most similar value to the normal parenchyma. Ultrasonography can be easily accessed by primary screening, but there may be differences in the accuracy of the test method or the correspondence of results depending on proficiency. GLCM algorithm was applied to quantitatively classify the degree of fatty liver. Local fat avoidance region was similar to normal parenchyma, so it could be predicted to be homogeneous liver parenchyma without fat deposition. We believe that GLCM computer image analysis will provide important information for differentiating not only fatty liver but also other lesions.

• Korean Journal of Remote Sensing
• /
• v.33 no.6_2
• /
• pp.1061-1073
• /
• 2017

In this study, images were classified using convolutional neural network (CNN) - a deep learning technique - to investigate the feasibility of information production through a combination of artificial intelligence and spatial data. CNN determines kernel attributes based on a classification criterion and extracts information from feature maps to classify each pixel. In this study, a CNN network was constructed to classify materials with similar spectral characteristics and attribute information; this is difficult to achieve by conventional image processing techniques. A Compact Airborne Spectrographic Imager(CASI) and an Airborne Imaging Spectrometer for Application (AISA) were used on the following three study sites to test this method: Site 1, Site 2, and Site 3. Site 1 and Site 2 were agricultural lands covered in various crops,such as potato, onion, and rice. Site 3 included different buildings,such as single and joint residential facilities. Results indicated that the classification of crop species at Site 1 and Site 2 using this method yielded accuracies of 96% and 99%, respectively. At Site 3, the designation of buildings according to their purpose yielded an accuracy of 96%. Using a combination of existing land cover maps and spatial data, we propose a thematic environmental map that provides seasonal crop types and facilitates the creation of a land cover map.