• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.10
• /
• pp.397-402
• /
• 2019

Accurately predicting cancer prognosis to provide appropriate treatment strategies for patients is one of the critical challenges in bioinformatics. Many researches have suggested machine learning models to predict patients' outcomes based on their gene expression data. Gene expression data is high-dimensional numerical data containing about 17,000 genes, so traditional researches used feature selection or dimensionality reduction approaches to elevate the performance of prognostic prediction models. These approaches, however, have an issue of making it difficult for the predictive models to grasp any biological interaction between the selected genes because feature selection and model training stages are performed independently. In this paper, we propose a novel two-dimensional image formatting approach for gene expression data to achieve feature selection and prognostic prediction effectively. Node2Vec is exploited to integrate biological interaction network and gene expression data and a convolutional neural network learns the integrated two-dimensional gene expression image data and predicts cancer prognosis. We evaluated our proposed model through double cross-validation and confirmed superior prognostic prediction accuracy to traditional machine learning models based on raw gene expression data. As our proposed approach is able to improve prediction models without loss of information caused by feature selection steps, we expect this will contribute to development of personalized medicine.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.2
• /
• pp.43-50
• /
• 2022

Even though the structural safety is confirmed in the design stage, the structural safety is not guaranteed in the construction stage because the structural system is not completed. In addition, since the construction period is shorter than the period of use of the building after completion, it is excessive to apply the same seismic load to the construction stage as in the design stage. ASCE 37-14 presents the concept of seismic load reduction factor during construction, but does not provide a clear application method. Therefore, in this study, the seismic load reduced according to the return period was applied to the example model of a residential middle-rise RC building. The construction stage of the example model was divided into five-story units, and seismic load with the change of the return period was applied to the construction stage models to analyze the change of seismic load during construction and to check the sectional performances of structural members. By comparing the design strength ratio of the shear wall at the design stage and the construction stage, the range of seismic load magnitudes that can assure the safety during construction of a residential middle-rise RC building was analyzed in terms of the return period.

• Journal of Industrial Convergence
• /
• v.21 no.7
• /
• pp.19-27
• /
• 2023

As the secondary battery market expands, the process of producing laterite ore using the rotary kiln and electric furnace method is expanding worldwide. As ESG management expands, the management of air pollutants such as nitrogen oxides in exhaust gases is strengthened. The rotary kiln, one of the main facilities of the pyrometallurgy process, is a facility for drying and preliminary reduction of ore, and it generate nitrogen oxides, thus prediction of nitrogen oxide is important. In this study, LSTM for regression prediction and LightGBM for classification prediction were used to predict and then model optimization was performed using AutoML. When applying LSTM, the predicted value after 5 minutes was 0.86, MAE 5.13ppm, and after 40 minutes, the predicted value was 0.38 and MAE 10.84ppm. As a result of applying LightGBM for classification prediction, the test accuracy rose from 0.75 after 5 minutes to 0.61 after 40 minutes, to a level that can be used for actual operation, and as a result of model optimization through AutoML, the accuracy of the prediction after 5 minutes improved from 0.75 to 0.80 and from 0.61 to 0.70. Through this study, nitrogen oxide prediction values can be applied to actual operations to contribute to compliance with air pollutant emission regulations and ESG management.

• Korean Journal of Radiology
• /
• v.20 no.5
• /
• pp.830-843
• /
• 2019

Objective: To examine the potential of intravoxel incoherent motion (IVIM) and blood oxygen level-dependent (BOLD) magnetic resonance imaging for detecting renal changes after iodinated contrast-induced acute kidney injury (CI-AKI) development in a diabetic rabbit model. Materials and Methods: Sixty-two rabbits were randomized into 2 groups: diabetic rabbits with the contrast agent (DCA) and healthy rabbits with the contrast agent (NCA). In each group, 6 rabbits underwent IVIM and BOLD imaging at 1 hour, 1 day, 2 days, 3 days, and 4 days after an iohexol injection while 5 rabbits were selected to undergo blood and histological examinations at these specific time points. Iohexol was administrated at a dose of 2.5 g I/kg of body weight. Further, the apparent transverse relaxation rate (R2^*), average pure molecular diffusion coefficient (D), pseudo-diffusion coefficient (D^*), perfusion fraction (f) were calculated. Results: The D and f values of the renal cortex (CO) and outer medulla (OM) were significantly decreased compared to baseline values in the 2 groups 1 day after the iohexol injection (p < 0.05). A marked reduction in the D^* values for both the CO and OM was also observed after 1 hour in each group (p < 0.05). In the OM, a persistent elevation of the R2^* was detected for 4 days in the DCA group (p < 0.05). Histopathological changes were prominent, and the pathological features of CI-AKI aggravated in the DCA group until day 4. The D, f, and R2^* values significantly correlated with the histological damage scores, hypoxia-inducible transcription factor-1α expression scores, and serum creatinine levels. Conclusion: A combination of IVIM and BOLD imaging may serve as a noninvasive method for detecting and monitoring CI-AKI in the early stages in the diabetic kidney.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.52 no.5
• /
• pp.83-95
• /
• 2024

This study evaluates the effectiveness of different Low-Impact Development (LID) scenarios in mitigating urban flooding in Yeongdeungpo-gu, Seoul, using the Storm Water Management Model (SWMM). Two key areas, an industrial zone, and a mixed residential-commercial zone, were chosen to explore how different LID implementations impact runoff. The study considers six types of LIDs, including green roofs and rain barrels for building-based scenarios; and permeable pavements, infiltration trenches, vegetative swales, and rain gardens for open space-based scenarios. The drainage network map and historical rainfall data from previous flooding events were applied in SWMM for simulation modeling using different LID scenarios: building-based, open space-based, and combined LID methods. Results show that the combined LID approach is the most effective method, reducing runoff by 26.8% and 21.1% and lowering peak runoff volumes by 7.5% and 12.6% for Block I and Block II, respectively. These scenarios demonstrate that Scenario II has a more significant impact compared to Scenario I, despite the amount of coverage area. In general, building-based LID measures alone show the least reduction in both surface runoff and peak runoff volumes. The proposed approach offers a robust solution that can shape a resilient and livable urban future.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.26 no.2
• /
• pp.165-171
• /
• 2013

Due to the difficulty in considering dynamic load in the view point of a computer resource and computing time, it is common that external load is assumed as ideal static loads. However, structural analysis under static load cannot guarantee the safety of design of the structures under dynamic loadings. Recently, the systematic method to construct equivalent static load from the given dynamic load has been proposed. Previous study has calculated equivalent static load through the optimization procedure under displacement constraints. However, previously reported works to distribute equivalent static load were based on ad-hoc methods. Improper selection of equivalent static loading positions may results in unreliable prediction of structural design. The present study proposes the selection method of the proper locations of equivalent static loads to dynamically applied loads when we consider transient dynamic structural problems. Moreover, it is appropriate to take into account the stress constraint as well as displacement constraint condition for the safety design. But the previously reported studies of equivalent static load design methods considered only displacement constraint conditions but not stress constraint conditions. In the present study we consider not only displacement constraint but also stress constraint conditions. Through a few numerical examples, the efficiency and reliability of proposed scheme is verified by comparison of the equivalent stress between equivalent static loading and dynamic loading.

• Journal of Korean Society of Steel Construction
• /
• v.22 no.5
• /
• pp.421-433
• /
• 2010

The most typical deterioration of steel structures is corrosion damage. However, a method to evaluate residual load-carrying capacity of corroded steel structures is not yet established. It is difficult to check current serviceability and safety of the structures. In this study, compressive tests and finite element analyses were conducted on H-beams with corroded web. Then, the effect of corrosion damage on web crippling strength and evaluation methods of the web crippling strength are studied. Based on the tests, 4 H-beam specimens used in a subway construction site and 9 H-beam specimens with different web-thickness and damaged-height underwent compression-tests. To consider loading and supporting areas in the site, compressive loading was applied in the entire region of the upper and bottom flange in 5 H-beam specimens and applied partially on the regions of the upper and bottom flange in 8 specimens. The finite element analysis of 38 parametric model specimens simulating different corrosion damages was also carried out. From experimental and analytical results, the relationships between corrosion damages in the web and residual web crippling strength are presented. Factors web crippling strength was reduced are formulated by using residual average thickness and the standard deviation of the corroded web thickness. Also, a simple evaluation method of residual web crippling strength was proposed.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.2 s.314
• /
• pp.1-11
• /
• 2007

H.264/AVC uses variable block sizes to achieve significant coding gain. It has 7 different coding modes having different motion compensation block sizes in Inter slice, and 2 different intra prediction modes in Intra slice. This fine-tuned new coding feature has achieved far more significant coding gain compared with previous video coding standards. However, extremely high computational complexity is required when rate-distortion optimization (RDO) algorithm is used. This computational complexity is a major problem in implementing real-time H.264/AVC encoder on computationally constrained devices. Therefore, there is a clear need for complexity reduction algorithm of H.264/AVC such as fast mode decision. In this paper, we propose a fast mode decision with early $P8\times8$ mode rejection based on block size activity using large block history map (LBHM). Simulation results show that without any meaningful degradation, the proposed method reduces whole encoding time on average by 53%. Also the hybrid usage of the proposed method and the early SKIP mode decision in H.264/AVC reference model reduces whole encoding time by 63% on average.

• Ocean and Polar Research
• /
• v.33 no.3
• /
• pp.309-319
• /
• 2011

This is a preliminary study of the feasibility of obtaining reliable tidal current harmonic constants, using one month of current observations, to verify the accuracy of a tidal model. An inference method is commonly used to separate out the tidal harmonic constituents when the available data spans less than a synodic period. In contrast to tidal constituents, studies of the separation of tidal-current harmonics are rare, basically due to a dearth of the long-term observation data needed for such experiments. We conducted concurrent and monthly harmonic analyses for tidal current velocities and heights, using 2 years (2006 and 2007) of current and sea-level records obtained from the Tidal Current Signal Station located in the narrow waterway in front of Incheon Lock, Korea. Firstly, the l-year harmonic analyses showed that, with the exception of $M_2$ and $S_2$ semidiurnal constituents, the major constituents were different for the tidal currents and heights. $K_1$, for instance, was found to be the 4th major tidal constituent but not an important tidal current constituent. Secondly, we examined monthly variation in the amplitudes and phase-lags of the $S_2$ and $K_1$ current-velocity and tide constituents over a 23-month period. The resultant patterns of variation in the amplitudes and phase-lags of the $S_2$ tidal currents and tides were similar, exhibiting a sine curve form with a 6-month period. Similarly, variation in the $K_1$ tidal constant and tidal current-velocity phase lags showed a sine curve pattern with a 6-month period. However, that of the $K_1$ tidal current-velocity amplitude showed a somewhat irregular sine curve pattern. Lastly, we investigated and tested the inference methods available for separating the $K_2$ and $S_2$ current-velocity constituents via monthly harmonic analysis. We compared the effects of reduction in monthly variability in tidal harmonic constants of the $S_2$ current-velocity constituent using three different inference methods and that of Schureman (1976). Specifically, to separate out the two constituents ($S_2$ and $K_2$), we used three different inference parameter (i.e. amplitude ratio and phase-lag diggerence) values derived from the 1-year harmonic analyses of current-velocities and tidal heights at (near) the short-term observation station and from tidal potential (TP), together with Schureman's (1976) inference (SI). Results from these four different methods reveal that TP and SI are satisfactorily applicable where results of long-term harmonic analysis are not available. We also discussed how to further reduce the monthly variability in $S_2$ tidal current-velocity constants.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.11
• /
• pp.104-109
• /
• 2017

The flooding and deterioration of water quality caused by urbanization and climate change are becoming more serious. In order to respond to this, studies on low impact development (LID) technology, which is designed to restore the hydrological system of the urban basin to its natural state, have been actively pursued all over the world, The announcement of the low carbon green growth law, hydrophilic area special law, etc., highlights the importance of technology such as the LID method. However, whereas various developments have been made in relation to the current LID element technology, there has been little research designed to verify its effectiveness. In this study, we analyzed the optimum spatial distribution of pitcher fire pitcher packing in parking lots using the K - LIDM model to verify the effectiveness of the low impact development (LID) method in the early stages. Using the eight package scenario and the three rain intensity scenarios, it was found that the lower 40% pitcher packaging results in an approximately 90% spill reduction effect, as in the case of the whole pitcher's package. The confirmation of these analyses and experimental verification is expected to ensure that the actual pitcher packaging will be used as a basis for arranging LID facilities such as urban planning and housing development in the future.