• Journal of Korean Neurosurgical Society
• /
• v.62 no.4
• /
• pp.442-449
• /
• 2019

Objective : Bone mineral density (BMD) is an important consideration during fusion surgery. Although dual X-ray absorptiometry is considered as the gold standard for assessing BMD, quantitative computed tomography (QCT) provides more accurate data in spine osteoporosis. However, QCT has the disadvantage of additional radiation hazard and cost. The present study was to demonstrate the utility of artificial intelligence and machine learning algorithm for assessing osteoporosis using Hounsfield units (HU) of preoperative lumbar CT coupling with data of QCT. Methods : We reviewed 70 patients undergoing both QCT and conventional lumbar CT for spine surgery. The T-scores of 198 lumbar vertebra was assessed in QCT and the HU of vertebral body at the same level were measured in conventional CT by the picture archiving and communication system (PACS) system. A multiple regression algorithm was applied to predict the T-score using three independent variables (age, sex, and HU of vertebral body on conventional CT) coupling with T-score of QCT. Next, a logistic regression algorithm was applied to predict osteoporotic or non-osteoporotic vertebra. The Tensor flow and Python were used as the machine learning tools. The Tensor flow user interface developed in our institute was used for easy code generation. Results : The predictive model with multiple regression algorithm estimated similar T-scores with data of QCT. HU demonstrates the similar results as QCT without the discordance in only one non-osteoporotic vertebra that indicated osteoporosis. From the training set, the predictive model classified the lumbar vertebra into two groups (osteoporotic vs. non-osteoporotic spine) with 88.0% accuracy. In a test set of 40 vertebrae, classification accuracy was 92.5% when the learning rate was 0.0001 (precision, 0.939; recall, 0.969; F1 score, 0.954; area under the curve, 0.900). Conclusion : This study is a simple machine learning model applicable in the spine research field. The machine learning model can predict the T-score and osteoporotic vertebrae solely by measuring the HU of conventional CT, and this would help spine surgeons not to under-estimate the osteoporotic spine preoperatively. If applied to a bigger data set, we believe the predictive accuracy of our model will further increase. We propose that machine learning is an important modality of the medical research field.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.599-608
• /
• 2023

The increasing interest in soil moisture data using satellite data for applications of hydrology, meteorology, and agriculture has led to the development of methods for generating soil moisture maps of variable resolution. This study demonstrated the capability of generating soil moisture maps using Sentinel-1 and Sentinel-2 data provided by Google Earth Engine (GEE). The soil moisture map was derived using synthetic aperture radar (SAR) image and optical image. SAR data provided by the Sentinel-1 analysis ready data in GEE was applied with normalized difference vegetation index (NDVI) based on Sentinel-2 and Environmental Systems Research Institute (ESRI)-based Land Cover map. This study produced a soil moisture map in the research area of Victoria, Australia and compared it with field measurements obtained from a previous study. As for the validation of the applied method's result accuracy, the comparative experimental results showed a meaningful range of consistency as 4-10%p between the values obtained using the algorithm applied in this study and the field-based ones, and they also showed very high consistency with satellite-based soil moisture data as 0.5-2%p. Therefore, public open data provided by GEE and the algorithm applied in this study can be used for high-resolution soil moisture mapping to represent regional land surface characteristics.

• Journal of Environmental Science International
• /
• v.25 no.2
• /
• pp.239-246
• /
• 2016

This study aims to analyze region-specific trends in changing greenhouse gas emissions in incineration plants of local government where waste heat generated during incineration are reused for the recent five years (2009 to 2013). The greenhouse gas generated from the incineration plants is largely $CO_2$ with a small amount of $CH_4$ and $N_2O$. Most of the incineration plants operated by local government produce steam with waste heat generated from incineration to produce electricity or reuse it for hot water/heating and resident convenience. And steam in some industrial complexes is supplied to companies who require it for obtaining resources for local government or incineration plants. All incineration plants, research targets of this study, are using LNG or diesel fuel as auxiliary fuel for incinerating wastes and some of the facilities are using LFG(Landfill Gas). The calculation of greenhouse gas generated during waste incineration was according to the Local Government's Greenhouse Emissions Calculation Guideline. As a result of calculation, the total amount of greenhouse gas released from all incineration plants for five years was about $3,174,000tCO_2eq$. To look at it by year, the biggest amount was about $877,000tCO_2eq$ in 2013. To look at it by region, Gyeonggido showed the biggest amount (about $163,000tCO_2eq$ annually) and the greenhouse gas emissions per capita was the highest in Ulsan Metropolitan City(about $154kCO_2eq$ annually). As a result of greenhouse gas emissions calculation, some incineration plants showed more emissions by heat recovery than by incineration, which rather reduced the total amount of greenhouse gas emissions. For more accurate calculation of greenhouse gas emissions in the future, input data management system needs to be improved.

• The Journal of the Korea Contents Association
• /
• v.10 no.7
• /
• pp.88-97
• /
• 2010

Recently the more convenient services are provided to people in the city in line with the change of city paradigm and the recent development of ubiquitous. For example, Information on bus arrivals an effective advertisement the combination of high technology and departures through smart-phones. However, in respect of the mobile advertisement, because of difficulties such as the means of transferring the mass storage data or the burden of communication charges. there need means to improve such difficulties. This study has been conducted aiming to overcome such difficulties. This study suggests the strategic differentiation plan through the analysis of the media characteristics such as real time service information when in traveling, U-Bus business model in the category of mobile advertisement, etc. and also the concrete system establishment plan from the operation center via network to the delivery of the advertisement through vehicle terminals. In respect that this study suggests the implications as a practical business model through the fusion of high technology and diverse media. It has great significance.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.36 no.5
• /
• pp.523-531
• /
• 2012

The performance simulation of a desiccant rotor, which is a core component of a desiccant cooling system, was conducted on the basis of a theoretical solution of the heat and mass transfer process in the rotor. The simulation model was validated by comparing simulation results with experimental data; reasonable agreement was observed. The effect of the rotation speed on the performance of the desiccant rotor was investigated for various operation conditions: temperature (50 to $70^{\circ}C$), humidity ratio (0.01 to 0.02 kg/kg DA), and flow rate of regeneration air. The optimum rotation speed was determined from the maximum moisture removal capacity (MRC) of the desiccant rotor, and it was found to vary with the operation conditions. Further, the correlation for the optimum rotation speed was determined by regression analysis.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.22 no.5
• /
• pp.560-567
• /
• 2011

In this paper, we reduced the optical noise interference using polarizers in a visible light communication system. In a transmitter, two light-emitting diodes(LEDs) are modulated synchronously by the original and the reversed signals of the transmitted data, and the two LED lights are radiated through orthogonal polarizers. In a receiver, two optical signals are detected through orthogonal polarizers and differentially amplified to remove the optical noise. In an environment that noise light from a fluorescent lamp is much stronger than the signal, the receiver with orthogonal polarizers removed the 120 Hz noise, and synchronous light transmission of the original and the reversed signals using two LEDs reduced the illumination flickering to about one-eighth that using one LED.

• Proceedings of the KSRS Conference
• /
• 2007.10a
• /
• pp.556-559
• /
• 2007

The Urban Environmental Quality (UEQ) indicates a complex and various parameters resulting from both human and natural factors in an urban area. Vegetation, climate, air quality, and the urban infrastructure may interact to produce effects in an urban area. There are relationships among air pollution, vegetation, and degrading environmental the urban heat island (UHI) effect. This study investigates the application of multi-spectral remote sensing data from the Landsat ETM and TM sensors for the mapping of air quality and UHI intensity in Seoul from 2000 to 2006 in fine resolution (30m) using the emissivity-fusion method. The Haze Optimized Transform (HOT) correction approach has been adopted for atmospheric correction on all bands except thermal band. The general UHI values (${\Delta}(T_{urban}-T_{rural})$) are 8.45 (2000), 9.14 (2001), 8.61 (2002), and $8.41^{\circ}C$ (2006), respectively. Although the UHI values are similar during these years, the spatial coverage of "hot" surface temperature (>$24^{\circ}C$) significantly increased from 2000 to 2006 due to the rapid urban development. Furthermore, high correlations between vegetation index and land surface temperature were achieved with a correlation coefficients of 0.85 (2000), 0.81 (2001), 0.84(2002), and 0.89 (2006), respectively. Air quality is shown to be an important factor in the spatial variation of UEQ. Based on the quantifiable fine resolution satellite image parameters, UEQ can promote the understanding of the complex and dynamic factors controlling urban environment.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.37 no.1
• /
• pp.75-79
• /
• 2013

Demands for semiconductor devices are dramatically increasing, and advancements in fabrication technology are allowing a step-up in the number of devices per unit area. As a result, semiconductor devices require higher heat dissipation, and thus, cooling solutions have become important for guaranteeing their operational reliability. In particular, in chip-in-board packages, in which chips and passives are embedded in the substrates for efficient device layout, heat dissipation is of greater importance. In this study, a thermal model for layers of different materials has been proposed, and then, the heat transfer has been simulated by imposing a set of appropriate boundary conditions. Heat generation can be predicted based on the results, which will be utilized as practical data for actual package design.

• Journal of Information Processing Systems
• /
• v.16 no.1
• /
• pp.6-29
• /
• 2020

Biometrics identification using multiple modalities has attracted the attention of many researchers as it produces more robust and trustworthy results than single modality biometrics. In this paper, we present a novel multimodal recognition system that trains a deep learning network to automatically learn features after extracting multiple biometric modalities from a single data source, i.e., facial video clips. Utilizing different modalities, i.e., left ear, left profile face, frontal face, right profile face, and right ear, present in the facial video clips, we train supervised denoising auto-encoders to automatically extract robust and non-redundant features. The automatically learned features are then used to train modality specific sparse classifiers to perform the multimodal recognition. Moreover, the proposed technique has proven robust when some of the above modalities were missing during the testing. The proposed system has three main components that are responsible for detection, which consists of modality specific detectors to automatically detect images of different modalities present in facial video clips; feature selection, which uses supervised denoising sparse auto-encoders network to capture discriminative representations that are robust to the illumination and pose variations; and classification, which consists of a set of modality specific sparse representation classifiers for unimodal recognition, followed by score level fusion of the recognition results of the available modalities. Experiments conducted on the constrained facial video dataset (WVU) and the unconstrained facial video dataset (HONDA/UCSD), resulted in a 99.17% and 97.14% Rank-1 recognition rates, respectively. The multimodal recognition accuracy demonstrates the superiority and robustness of the proposed approach irrespective of the illumination, non-planar movement, and pose variations present in the video clips even in the situation of missing modalities.

• The Korean Journal of Archival Studies
• /
• no.20
• /
• pp.3-32
• /
• 2009

When the record management faces to the information environment, the practices based on self-judgment needs more open and considerate policies. New viewpoint that treat records as information and treat information as records will produce new mutual-conscious behavior that create records based on the value of information usage and maintain information data based on the reliability as an record. As the internal aspect how to create records well, how to transfer them well, and how to archives them well used to be the focus of record management, existing legislation, guidelines, and training seem to be mainly related to this front steps. We should also address issues according to the succeeding information services, including opening to the relevant, sharing, duplicating, information security, privacy protection, and constructing collections with continual supplement. This paper observe the confusion of the viewpoints in the recent reports, explain the need of fusion viewpoint, and suggest interconnecting feedback cycle between record management system and general information system.