• 동력기계공학회지
• /
• 제20권2호
• /
• pp.79-84
• /
• 2016

The thermodynamic performance of ocean thermal energy conversion with 1 kg/s geothermal water flow rate as a heat source was evaluated to obtain the basic data for the optimal design of cycle with respect to the classification of the working fluid. The basic thermodynamic model for cycle is rankine cycle and the geothermal water and deep seawater were adapted for the heat source of evaporator and condenser, respectively. R245fa, R134a are better to use as a working fluid than others in view of the use of geothermal water. It is important to select the proper working fluid to operate the ocean thermal energy conversion. So, this paper can be used as the basic data for the design of ocean thermal energy conversion with geothermal water and deep seawater.

• 환경위생공학
• /
• 제18권2호
• /
• pp.52-59
• /
• 2003

This study was progressed in photocatalysis of VOCs using $UV/TiO_2$ which was a benign process environmentally. The experiments were peformed to know photodegradation characteristics as crystalline structure of $TiO_2$ which had anatase, rutile and P-25 (anatase : rutile = 70 : 30). The main purpose of this study was to identify photocatalytic characteristics as inlet concentration of reactants, $H_2O$, and residence time. The inlet concentration of VOCs was changed 50, 100 and 200 ppmv, and amount of $H_2O$ was changed 0, 500 and $1000{\;}mg/m^3$, respectively. The deep conversion was increased as the inlet concentration decreased, and the amount of $H_2O$ increased. The deep conversion of benzene had the highest value at $1000{\;}mg/m^3${\;}H_2O$ and 50 ppmv of inlet concentration. The reactivity of reactants was decreased in order benzene > toluene > m-xylene. Also, the photocatalytic deep conversion was increased as residence time increased, because the contact time between reactants and catalyst was increased. In this study, intermediates had not found by GC/MSD analysis. Therefore, the reactants were completely converted to $H_2O{\;}and{\;}CO_2$.

• Asia pacific journal of information systems
• /
• 제33권3호
• /
• pp.737-767
• /
• 2023

With the availability of big customer data and advances in machine learning techniques, the prediction of customer behavior at the session-level has attracted considerable attention from marketing practitioners and scholars. This study aims to predict customer purchase conversion at the session-level by employing customer profile, transaction, and clickstream data. For this purpose, we develop a multimodal deep learning fusion model with dynamic and static features (i.e., DS-fusion). Specifically, we base page views within focal visist and recency, frequency, monetary value, and clumpiness (RFMC) for dynamic and static features, respectively, to comprehensively capture customer characteristics for buying behaviors. Our model with deep learning architectures combines these features for conversion prediction. We validate the proposed model using real-world e-commerce data. The experimental results reveal that our model outperforms unimodal classifiers with each feature and the classical machine learning models with dynamic and static features, including random forest and logistic regression. In this regard, this study sheds light on the promise of the machine learning approach with the complementary method for different modalities in predicting customer behaviors.

• Korean Journal of Radiology
• /
• 제24권4호
• /
• pp.294-304
• /
• 2023

Objective: We aimed to investigate whether image standardization using deep learning-based computed tomography (CT) image conversion would improve the performance of deep learning-based automated hepatic segmentation across various reconstruction methods. Materials and Methods: We collected contrast-enhanced dual-energy CT of the abdomen that was obtained using various reconstruction methods, including filtered back projection, iterative reconstruction, optimum contrast, and monoenergetic images with 40, 60, and 80 keV. A deep learning based image conversion algorithm was developed to standardize the CT images using 142 CT examinations (128 for training and 14 for tuning). A separate set of 43 CT examinations from 42 patients (mean age, 10.1 years) was used as the test data. A commercial software program (MEDIP PRO v2.0.0.0, MEDICALIP Co. Ltd.) based on 2D U-NET was used to create liver segmentation masks with liver volume. The original 80 keV images were used as the ground truth. We used the paired t-test to compare the segmentation performance in the Dice similarity coefficient (DSC) and difference ratio of the liver volume relative to the ground truth volume before and after image standardization. The concordance correlation coefficient (CCC) was used to assess the agreement between the segmented liver volume and ground-truth volume. Results: The original CT images showed variable and poor segmentation performances. The standardized images achieved significantly higher DSCs for liver segmentation than the original images (DSC [original, 5.40%-91.27%] vs. [standardized, 93.16%-96.74%], all P < 0.001). The difference ratio of liver volume also decreased significantly after image conversion (original, 9.84%-91.37% vs. standardized, 1.99%-4.41%). In all protocols, CCCs improved after image conversion (original, -0.006-0.964 vs. standardized, 0.990-0.998). Conclusion: Deep learning-based CT image standardization can improve the performance of automated hepatic segmentation using CT images reconstructed using various methods. Deep learning-based CT image conversion may have the potential to improve the generalizability of the segmentation network.

• 환경위생공학
• /
• 제16권4호
• /
• pp.69-76
• /
• 2001

The catalytic oxidation of volatile organic compounds (VOCs), which were benzene and toluene, was studied in the supercritical carbon dioxide($SC-CO_2$) media. In $SC-CO_2$ media, the deep oxidation conversion of VOCs was increased with the temperature and pressure. The deep oxidation conversion in SC -$CO_2$ media is better than that in air media at same pressure condition. This can be explained by the solubility of VOCs in $SC-CO_2$. The many intermediates produced by the partial oxidation of VOCs were detected from off-line samples. The intermediates were Identified as benzene, toluene, benzaldehyde, phenol, naphthalene, 1,1`-biphenyl, benzoic acid, 3-methylphenol, 1,1'-(1,2-ethanediyl)bis- benzene, 1,1'-(1,2-ethene- diyl)bis-benzene, anthracene, and so on. The amount of intermediates was decreased as the molar radio of oxygen to carbon dioxide was decreased. When the molar ratio of oxygen to carbon dioxide was 1 : 16, the deep conversion was kept constant. Thus, the catalytic oxidation process in $SC-CO_2$ media can be combined on-line with supercritical fluid extraction of environmental matrices and supercritical regeneration of used adsorbent. Thus, the nontoxic $SC-CO_2$ media process was suggested as the new VOCs control technology.

• 한국항해항만학회지
• /
• 제42권1호
• /
• pp.9-16
• /
• 2018

인류의 한정된 석유자원의 개발은 유가의 상승과 함께 필연적으로 심해지역의 유전을 탐사하고 개발하고 있다. 이러한 심해지역에는 심층수의 온도가 약 $4^{\circ}C$이고 표층수의 온도는 약 $30^{\circ}C$로 이때의 온도 차이를 이용하여 발전설비를 가동하는 Ocean Thermal Energy Conversion(OTEC) 기술에 대한 연구가 활발히 진행되고 있다. 본 연구에서는 기존의 심해지역에 설치되는 FPSO(Floating Production Storage Offloading; 부유식 생산설비)에서 수심 100m의 해수를 냉각수로 이용하는 조건을 400m까지 변경하는 조건으로 하고, FPSO에서 냉각수로 사용되고 배출되는 해수를 이용하여 Discharged Thermal Energy Conversion(DTEC) 발전장치를 적용하는 방안을 설계하고 해석하였다. 기존의 설계 수심보다 깊은 수심에서 냉각수를 취수하여 DTEC 시스템을 적용하면 수심에 따라 보다 많은 전력을 생산할 수 있는 시스템의 설계가 가능한 것을 확인하였다. FPSO와 OTEC 발전설비의 유사성을 고려하였을 때, 심해지역의 FPSO에 DTEC 시스템을 적용하여 기술을 축적하고 유전의 수명이 다한 뒤에 OTEC 발전설비로 개조한다면 자원개발과 지속가능한 발전이라는 두 가지 중요한 과제를 이룰 수 있을 것이다.

• 환경위생공학
• /
• 제16권3호
• /
• pp.72-79
• /
• 2001

The selective catalytic oxidation of toxic aromatic solvents (benzene, toluene, ethylbenzene, and styrene) and their mixtures were studied on a $Pt/{\;}{\gamma}-Al_2O_3$ catalyst at temperature ranging from $160~350^{\circ}C$. The deep conversion of aromatic solvents was increased as the inlet concentration was decreased and the reaction temperature was increased. The reactivity increases in order benzene > toluene > ethylbenzene > styrene. In mixture, remarkable effects on reaction rate and selectivity have been evidence ; the strongest inhibition effect is shown by styrene and increase in a reverse order with respect to that of reactivity. The inhibition effect was increased in order styrene > ethylbenzene > toluzene > benzene. This trend is due to the competition adsorption between the two or three reactants on the oxidized catalyst. Also, the deep conversion change of benzene was a small in tertiary mixtures(including of benzene and styrene) comparing with conversion characteristics of binary mixture with styrene. This result was due to small concentration of styrene. which had very strong inhibition effect.

• 환경위생공학
• /
• 제16권1호
• /
• pp.66-71
• /
• 2001

The objective of this study was to depict the kinetic behavior of the platinum catalyst for the deep oxidation of aromatic solvents and their binary mixtures. The oxidation kinetics of aromatic solvents, which were benzene, toluene and m-xylene, was studied on a 0.5% $Pt/{\gamma}-Al_2O_3$ catalyst. Deep oxidation of binary mixtures, which were 1:1 in volume, was carried out and the inlet concentration was controlled in the range of 133 and 333ppmv. An approach based on the two-stage redox model was used to analysis the results. The deep oxidation conversion of aromatic solvents was inversely proportional to inlet concentration in plug flow reactor. This trend is due to the zeroth-order kinetics with respect to inlet concentration. The kinetic parameters of multicomponent model were independently evaluated from the single compound oxidation experiments. A simple multicomponent model based on two-stage redox rate model made reasonably good predictions of conversion over the range of parameters studied.

• ETRI Journal
• /
• 제46권3호
• /
• pp.513-525
• /
• 2024

Deep neural networks trained on labeled medical data face major challenges owing to the economic costs of data acquisition through expensive medical imaging devices, expert labor for data annotation, and large datasets to achieve optimal model performance. The heterogeneity of diseases, such as Alzheimer's disease, further complicates deep learning because the test cases may substantially differ from the training data, possibly increasing the rate of false positives. We propose a reconstruction-based self-supervised anomaly detection model to overcome these challenges. It has a dual-subnetwork encoder that enhances feature encoding augmented by skip connections to the decoder for improving the gradient flow. The novel encoder captures local and global features to improve image reconstruction. In addition, we introduce an entropy-based image conversion method. Extensive evaluations show that the proposed model outperforms benchmark models in anomaly detection and classification using an encoder. The supervised and unsupervised models show improved performances when trained with data preprocessed using the proposed image conversion method.

• 말소리와 음성과학
• /
• 제15권3호
• /
• pp.69-74
• /
• 2023

This study introduces an innovative model for zero-shot voice conversion that utilizes the capabilities of HuBERT. Zero-shot voice conversion models can transform the speech of one speaker to mimic that of another, even when the model has not been exposed to the target speaker's voice during the training phase. Comprising five main components (HuBERT, feature encoder, flow, speaker encoder, and vocoder), the model offers remarkable performance across a range of scenarios. Notably, it excels in the challenging unseen-to-unseen voice-conversion tasks. The effectiveness of the model was assessed based on the mean opinion scores and similarity scores, reflecting high voice quality and similarity to the target speakers. This model demonstrates considerable promise for a range of real-world applications demanding high-quality voice conversion. This study sets a precedent in the exploration of HuBERT-based models for voice conversion, and presents new directions for future research in this domain. Despite its complexities, the robust performance of this model underscores the viability of HuBERT in advancing voice conversion technology, making it a significant contributor to the field.