• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.703-705
• /
• 2023

본 연구는 대화 중 생체신호 데이터를 활용하여 감정 인식 분야에서 더욱 정확하고 범용성이 높은 인식 기술을 제안한다. 이를 위해, 먼저 대화별 길이에 따른 측정값의 개수를 동일하게 조정하고 효과적인 생체신호 데이터의 조합을 비교 및 분석하기 위해 차원 축소 기법인 T-SNE (T-distributed Stochastic Neighbor Embedding)을 활용하여 감정 라벨의 분포를 확인한다. 또한, AutoML (Automated Machine Learning)을 이용하여 축소된 데이터로 감정을 분류 및 각성도와 긍정도를 예측하여 감정을 가장 잘 인식하는 생체신호 데이터의 조합을 발견한다.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• v.29 no.2
• /
• pp.113-122
• /
• 2007

Purpose: Platelet-rich plasma (PRP) is known to accelerate and/or enhance hard and soft tissue healing and regeneration. As such, PRP has been used in various clinical fields of surgery. Recently there have been several attempts to use PRP in the field of tissue engineering. However, some controversies still exist on exact mechanism and benefits of PRP. Therefore various animal experiments are necessary to reveal the effect of the PRP. However, even if animal experiment is performed, the efficacy of the experiment could not be validated due to absence of an animal PRP model. The purpose of this study is to establish rat PRP model by comparing several PRP fabricating methods, and to assay growth factor concentration in the PRP. Materials and methods: Rat blood samples were collected from nine SD rat (body weight: 600-800g). PRP was prepared using three different PRP fabricating methods according to previously reported literatures. (Method 1: 800 rpm, 15 minute, single centrifuge; Method 2: 1000 rpm, 10 minute, double centrifuge; Method 3: 3000 rpm, 4min and 2500 rpm, 8 min, double centrifuge). Platelet counts were evaluated in an automated machine before and after PRP fabrications. In terms of growth factor assay, prepared PRP were activated with 100 unit thrombin and 10% calcium chloride. Growth factor (PDGF-BB, VEGF) concentrations on incubation time were determined by sandwich-ELISA technique. Results: An average of 3ml (via infraorbital venous plexus) to 15ml (via celiac axis) the rat blood could be collected. By using Method 3 (3000 rpm, 4 min and 2500 rpm, 8 min, double centrifugation), around 1.5ml of PRP could be prepared. This method allowed us to concentrate platelet 3.77-fold on average. PDGF-BB concentration (mean, 1942.10 pg/ml after 1 hour incubation) and VEGF concentration (mean, 952.71 pg/ml after 1 hour incubation) in activated PRP were higher than those in untreated blood. Also PDGF-BB showed constant concentration during 4-hour incubation, while VEGF concentration was decreased after 1 hour. Conclusion: Total 11,000 g minute separation and condensation double centrifuge method can produce efficient platelet-rich plasma. Platelet-rich plasma activated with thrombin has showed higher concentrations of growth factors such as PDGF-BB and VEGF, compared to the control group. Platelet-rich plasma model in a rat model was confirmed in this study.

• The Journal of Engineering Geology
• /
• v.30 no.3
• /
• pp.315-325
• /
• 2020

This study was performed to develop a model to predict landslides and determine the variable importance of landslides susceptibility factors based on the probabilistic prediction of landslides occurring on slopes along the road. Field survey data of 30,615 slopes from 2007 to 2020 in Korea were analyzed to develop a landslide prediction model. Of the total 131 variable factors, 17 topographic factors and 114 geological factors (including 89 bedrocks) were used to predict landslides. Automated machine learning (AutoML) was used to classify landslides and non-landslides. The verification results revealed that the best model, an extremely randomized tree (XRT) with excellent predictive performance, yielded 83.977% of prediction rates on test data. As a result of the analysis to determine the variable importance of the landslide susceptibility factors, it was composed of 10 topographic factors and 9 geological factors, which was presented as a percentage for each factor. This model was evaluated probabilistically and quantitatively for the likelihood of landslide occurrence by deriving the ranking of variable importance using only on-site survey data. It is considered that this model can provide a reliable basis for slope safety assessment through field surveys to decision-makers in the future.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1341-1352
• /
• 2023

The normalized difference vegetation index (NDVI) derived from satellite images is a crucial tool to monitor forests and agriculture for broad areas because the periodic acquisition of the data is ensured. However, optical sensor-based vegetation indices(VI) are not accessible in some areas covered by clouds. This paper presented a synthetic aperture radar (SAR) based approach to retrieval of the optical sensor-based NDVI using machine learning. SAR system can observe the land surface day and night in all weather conditions. Radar vegetation indices (RVI) from the Sentinel-1 vertical-vertical (VV) and vertical-horizontal (VH) polarizations, surface elevation, and air temperature are used as the input features for an automated machine learning (AutoML) model to conduct the gap-filling of the Sentinel-2 NDVI. The mean bias error (MAE) was 7.214E-05, and the correlation coefficient (CC) was 0.878, demonstrating the feasibility of the proposed method. This approach can be applied to gap-free nationwide NDVI construction using Sentinel-1 and Sentinel-2 images for environmental monitoring and resource management.

• Progress in Medical Physics
• /
• v.17 no.4
• /
• pp.238-245
• /
• 2006

To assess the ability of an extravasation defection accessory (EDA) to detect the clinically important extravascular Injection of iodinated contrast material that was delivered with an automated mechanical power injector. The purpose of this study was to assess the ability of this device during clinically important episodes of extravasation. The EDA system was composed of a strain gage, an amplifier and a computer-based system. In the rabbit experimental cases, there were seven true-positive cases (range of the extravasation volumes: $14{\sim}23 ml$). The algorithm results showed seven true-positive cases (range of the extravasation volumes: $7{\sim}16ml$), nineteen true-negative cases, two false-positive cases and no false-negative cases. The EDA system had a sensitivity of 100% and a specificity of 90% for the detection of clinically important extravasation. The EDA system had good sensitivity for the detection of clinically important extravasation and the EDA system has the clinical potential for the early detection of extravasation of the contrast medium that is administered with power injectors.

• Journal of dental hygiene science
• /
• v.23 no.4
• /
• pp.369-377
• /
• 2023

Background: In this study, we investigated the potential use of keratin for oral tissue regeneration. Keratin is well-known for its effectiveness in skin regeneration by promoting keratinization and enhancing the elasticity and activity of fibroblasts. Because of its structural stability, high storability, biocompatibility, and safety in humans, existing research has predominantly focused on its role in skin wound healing. Herein, we propose using keratin proteins as biocompatible materials for dental applications. Methods: To assess the suitability of alpha-keratin protein as a substrate for cell culture, keratin was extracted from human hair via PEGylation. Viabilities of primary human gingival fibroblasts (HGFs) and human oral keratinocytes (HOKs) were assessed. Fluorescence immunostaining and migration assays were conducted using a fluorescence microscope and confocal laser scanning microscope. Wound healing and migration assays were performed using automated software to analyze the experimental readout and gap closure rate. Results: We confirmed the extraction of alpha-keratin and formation of the PEG-g-keratin complex. Treatment of HGFs with keratin protein at a concentration of 5 mg/ml promoted proliferation and maintained cell viability in the test group compared to the control group. HOKs treated with 5 mg/ml keratin exhibited a slight decrease in cell proliferation and activity after 48 hours compared to the untreated group, followed by an increase after 72 hours. Wound healing and migration assays revealed rapid closure of the area covered by HOKs over time following keratin treatment. Additionally, HOKs exhibited changes in cell morphology and increased the expression of the mesenchymal marker vimentin. Conclusion: Our study demonstrated the potential of hair keratin for soft tissue regeneration, with potential future applications in clinical settings for wound healing.

• Journal of the Korean Society of Radiology
• /
• v.18 no.3
• /
• pp.267-273
• /
• 2024

Using a cloud-based vertex AI platform that can develop an artificial intelligence learning model without coding, this study easily developed an artificial intelligence learning model by the non-professional general public and confirmed its clinical applicability. Nine dental diseases and 2,999 root disease X-ray images released on the Kaggle site were used for the learning data, and learning, verification, and test data images were randomly classified. Image classification and multi-label learning were performed through hyper-parameter tuning work using a learning pipeline in vertex AI's basic learning model workflow. As a result of performing AutoML(Automated Machine Learning), AUC(Area Under Curve) was found to be 0.967, precision was 95.6%, and reproduction rate was 95.2%. It was confirmed that the learned artificial intelligence model was sufficient for clinical diagnosis.

• Journal of Biomedical Engineering Research
• /
• v.29 no.1
• /
• pp.66-72
• /
• 2008

The major risk associated with the use of automated power injectors is the well known complication of contrast material extravasation at the injection site. Automated injection of computed tomography (CT) contrast media can produce the compartment syndrome. The purpose of this study was to assess the ability of this device during clinically important episodes of extravasation. The extravasation detection accessory (EDA) system was composed of a strain gage, an amplifier and a computer based system. A strain gage pliable adhesive patch was applied to the skin aver the intravenous catheter and the catheter was connected to the power injector with a cable to monitor the resolution data. If the programmed monitoring, which was developed with MS Visual C++, at the extravasation occurred, then the injection was interrupted the auto injector. CT was used to demonstrate the clinically important extravasation. This study was a prospective, observational study in which the EDA system was used to monitor the automated mechanical injection of contrast material in 7 dogs. There were two true-positive cases (range of extravasation volumes: $18{\sim}22ml$), twenty three true-negative cases, three false-positive cases and no false-negative cases. The EDA system had a sensitivity of 100% and a specificity of 88% for the detection of clinically important extravasation. The EDA system had good sensitivity for the detection of clinically important extravasation and the EDA system has the clinical potential for the early detection of extravasation of the contrast medium that is administered with power injectors. The EDA system is easy to use safe and accurate for the monitoring extravasation of the intravenous injections, and this system may prove especially useful in CT applications.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.613-618
• /
• 2022

효과적인 자연어 처리를 위해 제안된 Transformer 구조의 등장 이후, 이를 활용한 대규모 언어 모델이자 사전학습 모델인 BERT, GPT, OPT 등이 공개되었고, 이들을 한국어에 보다 특화한 KoBERT, KoGPT 등의 사전학습 모델이 공개되었다. 자연어 처리 모델의 확보를 위한 학습 자원이 늘어나고 있지만, 사전학습 모델을 각종 응용작업에 적용하기 위해서는 데이터 준비, 코드 작성, 파인 튜닝 및 저장과 같은 복잡한 절차를 수행해야 하며, 이는 다수의 응용 사용자에게 여전히 도전적인 과정으로, 올바른 결과를 도출하는 것은 쉽지 않다. 이러한 어려움을 완화시키고, 다양한 기계 학습 모델을 사용자 데이터에 보다 쉽게 적용할 수 있도록 AutoML으로 통칭되는 자동 하이퍼파라미터 탐색, 모델 구조 탐색 등의 기법이 고안되고 있다. 본 연구에서는 한국어 사전학습 모델과 한국어 텍스트 데이터를 사용한 자연어 처리 모델 산출 과정을 정형화 및 절차화하여, 궁극적으로 목표로 하는 예측 모델을 자동으로 산출하는 시스템의 설계를 소개한다.

• Proceedings of the Korean Society of Toxicology Conference
• /
• 2006.11a
• /
• pp.65-74
• /
• 2006

Modem drug discovery requires rapid pharmacokinetic evaluation of chemically diverse compounds for early candidate selection. This demands the development of analytical methods that offer high-throughput of samples. Naturally, liquid chromatography / tandem mass spectrometry (LC-MS/MS) is choice of the analytical method because of its superior sensitivity and selectivity. As a result of the short analysis time(typically 3-5min) by LC-MS/MS, sample preparation has become the rate- determining step in the whole analytical cycle. Consequently tremendous efforts are being made to speed up and automate this step. In a typical automated 96-well SPE(solid-phase extraction) procedure, plasma samples are transferred to the 96-well SPE plate, internal standard and aqueous buffer solutions are added and then vacuum is applied using the robotic liquid handling system. It takes only 20-90 min to process 96 samples by automated SPE and the analyst is physically occupied for only approximately 10 min. Recently, the ultra-high flow rate liquid chromatography (turbulent-flow chromatography)has sparked a huge interest for rapid and direct quantitation of drugs in plasma. There is no sample preparation except for sample aliquotting, internal standard addition and centrifugation. This type of analysis is achieved by using a small diameter column with a large particle size(30-5O ${\mu}$m) and a high flow rate, typically between 3-5 ml/min. Silica-based monolithic HPLC columns contain a novel chromatographic support in which the traditional particulate packing has been replaced with a single, continuous network (monolith) of pcrous silica. The main advantage of such a network is decreased backpressure due to macropores (2 ${\mu}$m) throughout the network. This allows high flow rates, and hence fast analyses that are unattainable with traditional particulate columns. The reduction of particle diameter in HPLC results in increased column efficiency. use of small particles (<2 urn), however, requires p.essu.es beyond the traditional 6,000 psi of conventional pumping devices. Instrumental development in recent years has resulted in pumping devices capable of handling the requirements of columns packed with small particles. The staggered parallel HPLC system consists of four fully independent binary HPLC pumps, a modified auto sampler, and a series of switching and selector valves all controlled by a single computer program. The system improves sample throughput without sacrificing chromatographic separation or data quality. Sample throughput can be increased nearly four-fold without requiring significant changes in current analytical procedures. The process of Bioanalytical Method Validation is required by the FDA to assess and verify the performance of a chronlatographic method prior to its application in sample analysis. The validation should address the selectivity, linearity, accuracy, precision and stability of the method. This presentation will provide all overview of the work required to accomplish a full validation and show how a chromatographic method is suitable for toxirokinetic sample analysis. A liquid chromatography/tandem mass spectrometry (LC-MS/MS) method developed to quantitate drug levels in dog plasma will be used as an example of tile process.