• International journal of advanced smart convergence
• /
• v.12 no.3
• /
• pp.89-103
• /
• 2023

Obstructive sleep apnea (OSA) is one of the most prevalent sleep disorders that can lead to serious consequences, including hypertension and/or cardiovascular diseases, if not treated promptly. Continuous positive airway pressure (CPAP) is widely recognized as the most effective treatment for OSA, which needs the proper titration of airway pressure to achieve the most effective treatment results. However, the process of CPAP titration can be time-consuming and cumbersome. There is a growing importance in predicting personalized CPAP pressure before CPAP treatment. The primary objective of this study was to optimize the CPAP titration process for obstructive sleep apnea patients through EEG feature engineering with machine learning techniques. We aimed to identify and utilize the most critical EEG features to forecast key OSA predictive indicators, ultimately facilitating more precise and personalized CPAP treatment strategies. Here, we analyzed 126 OSA patients' PSG datasets before and after the CPAP treatment. We extracted 29 EEG features to predict the features that have high importance on the OSA prediction index which are AHI and SpO2 by applying the Shapley Additive exPlanation (SHAP) method. Through extracted EEG features, we confirmed the six EEG features that had high importance in predicting AHI and SpO2 using XGBoost, Support Vector Machine regression, and Random Forest Regression. By utilizing the predictive capabilities of EEG-derived features for AHI and SpO2, we can better understand and evaluate the condition of patients undergoing CPAP treatment. The ability to predict these key indicators accurately provides more immediate insight into the patient's sleep quality and potential disturbances. This not only ensures the efficiency of the diagnostic process but also provides more tailored and effective treatment approach. Consequently, the integration of EEG analysis into the sleep study protocol has the potential to revolutionize sleep diagnostics, offering a time-saving, and ultimately more effective evaluation for patients with sleep-related disorders.

• Journal of the Korea Society for Simulation
• /
• v.18 no.3
• /
• pp.35-45
• /
• 2009

Emergency medical center(EMC) is the place for patients who need medical treatment immediately due to a disease, childbirth, or all sorts of accidents. Currently, most of EMCs use temporary beds because regular EMC beds cannot afford to serve all incoming patients. However, since it decreases the quality of service(QoS) of EMC patients and their guardians and efficiency of the EMC, some improvements are highly required to diminish the usage of temporary beds. The system duration time is one of the typical QoSs. This thesis proposes the information which is critical to make a better decision for cut down the number of temporary beds without sacrificing QoS of patients. The key point is to control the duration time of medical treatments for the consultation and hospitalization process, since it is the major reason of overcrowding in EMC and the usage of temporary beds. In this paper, we proposed an Arena simulation model reflecting real world substantially. Arena is one of the most widely accepted simulation softwares in the world. Using the developed model, we can obtain the optimal EMC operation parameters through simulation experiments. Optquest, included in the Arena, is used to make the developed simulation model collaborate with an optimization model. The results showed one can determine the set of optimal operation parameters decreasing the required number of temporary beds without deteriorating EMC patient's QoS.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2003.09a
• /
• pp.44-44
• /
• 2003

As a basic measurement tool in the areas of animal models of human disease, gene expression and therapy, and drug discovery and development, small animal PET imaging is being used increasingly. An ideal small animal PET should have high sensitivity and high and uniform resolution across the field of view to achieve high image quality. However, the combination of long narrow pixellated crystal array and small ring diameter of small animal PET leads to the degradation of spatial resolution for the source located at off center. This degradation of resolution can be improved by determining the depth of interaction (DOI) in the crystal and by taking into account the information in sorting the coincident events. Among a number of 001 identification schemes, dual layer phsowich detector has been widely investigated by many research groups due to its practicability and effectiveness on extracting DOI information. However, the effects of each crystal length composing dual layer phoswich detector on DOI measurements and image qualities were not fully characterized. In order to minimize the DOI effect, the length of each layer of phoswich detector should be optimized. The aim of this study was to perform simulations using a simulation tool, GATE to design the optimum lengths of crystals composing a dual layer phoswich detector. The simulated small PET system employed LSO front layer LuYAP back layer phoswich detector modules and the module consisted of 8${\times}$8 arrays of dual layer crystals with 2 mm ${\times}$ 2 mm sensitive area coupled to a Hamamatsu R7600 00 M64 PSPMT. Sensitivities and variation of radial resolutions were simulated by varying the length of LSO front layer from 0 to 10 mm while the total length (LSO + LuYAP) was fixed to 20 mm for 10 cm diameter ring scanner. The radial resolution uniformity was markedly improved by using DOI information. There existed the optimal lengths of crystal layers to minimize the variation of radial resolutions. In 10 cm ring scanner configuration, the radial resolution was kept below 3.4 mm over 8 cm FOV while the sensitivity was higher than 7.4% for LSO 5 mm : LuYAP 15 mm phoswich detector. In this study, the optimal length of dual layer phoswich detector was derived to achieve high and uniform radial resolution.

• Nuclear Engineering and Technology
• /
• v.26 no.3
• /
• pp.401-410
• /
• 1994

Validation study of two radionuclide migration models for single fracture developed in geologic medium the hydrodynamic dispersion diffusion model(HDDM) and the channeling dispersion diffusion model(CDDM), was studied by migration experiment of tracers through an artificial granite fracture on the labolatory scale. The tracers used were Uranine and Sodium lignosulfonate know as nonsorbing material. The flow rate ranged 0.4 to 1.5 cc/min. Related parameters for the models were estimated by optimization technique. Theoretical breakthrough curves with experimental data were compared. In the experiment, it was deduced that the surface sorption for both tracers did not play an important role while the diffusion of Uranine into the rock matrix turned out to be an important mass transfer mechanism. The parameter characterizing the rock matrix diffusion of each model agreed well The simulated result showed that the amount of flow rate could not tell the CDDM from the HDDM quantitatively. On the other hand, the variation of fracture length gave influence on the two models in a different degree. The dispersivity of breakthrough curve of the CDDM was more amplified than that of the CDDM when the fracture length was increased. A good agreement between the models and experimental data gave a confirmation that both models were very useful in predicting the migration system through a single fracture.

• International Journal of Computer Science & Network Security
• /
• v.23 no.4
• /
• pp.55-68
• /
• 2023

In recent years, the Television White Space (TVWS) has attracted the interest of many researchers due to its propagation characteristics obtainable between 470MHz and 790MHz spectrum bands. The plenty of unused channels in the TV spectrum allows the secondary users (SUs) to use the channels for broadband services especially in rural areas. However, when the number of SUs increases in the TVWS wireless network the aggregate interference also increases. Aggregate interferences are the combined harmful interferences that can include both co-channel and adjacent interferences. The aggregate interference on the side of Primary Users (PUs) has been extensively scrutinized. Therefore, resource allocation (power and spectrum) is crucial when designing the TVWS network to avoid interferences from Secondary Users (SUs) to PUs and among SUs themselves. This paper proposes a model to improve the resource allocation for reducing the aggregate interface among SUs for broadband services in rural areas. The proposed model uses joint power and spectrum hybrid Firefly algorithm (FA), Genetic algorithm (GA), and Particle Swarm Optimization algorithm (PSO) which is considered the Co-channel interference (CCI) and Adjacent Channel Interference (ACI). The algorithm is integrated with the admission control algorithm so that; there is a possibility to remove some of the SUs in the TVWS network whenever the SINR threshold for SUs and PU are not met. We considered the infeasible system whereby all SUs and PU may not be supported simultaneously. Therefore, we proposed a joint spectrum and power allocation with an admission control algorithm whose better complexity and performance than the ones which have been proposed in the existing algorithms in the literature. The performance of the proposed algorithm is compared using the metrics such as sum throughput, PU SINR, algorithm running time and SU SINR less than threshold and the results show that the PSOFAGA with ELGR admission control algorithm has best performance compared to GA, PSO, FA, and FAGAPSO algorithms.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.36 no.4
• /
• pp.341-350
• /
• 2023

The templated grain growth (TGG) method has gained significant attention for its ability to produce highly textured piezoelectric ceramics with significantly enhanced performance, making it a promising method for transducer and actuator applications. However, the texturing process using the TGG method requires the optimization of multiple steps, which can be challenging for beginners in this field. Therefore, in this tutorial, we provide an overview of the TGG method mainly based on our previous published works, including its various processing steps such as synthesizing anisotropic-shaped templates with size and size distribution control using the molten salt synthesis technique, tape casting, and identifying key factors for proper alignment of the templates in the target matrix system. Our goal is to provide a resource that can serve as a basic reference for researchers and engineers looking to improve their understanding and utilization of the TGG method for producing textured piezoelectric ceramics.

• Korean Chemical Engineering Research
• /
• v.61 no.3
• /
• pp.388-393
• /
• 2023

The analysis of engineering data using neural network based on supervised learning has been utilized in various engineering fields such as optimization of chemical engineering process, concentration prediction of particulate matter pollution, prediction of thermodynamic phase equilibria, and prediction of physical properties for transport phenomena system. The supervised learning requires training data, and the performance of the supervised learning is affected by the composition and the configurations of the given training data. Among the frequently observed engineering data, the data is given in log-scale such as length of DNA, concentration of analytes, etc. In this study, for widely distributed log-scaled training data of virtual 100×100 images, available loss functions were quantitatively evaluated in terms of (i) confusion matrix, (ii) maximum relative error and (iii) mean relative error. As a result, the loss functions of mean-absolute-percentage-error and mean-squared-logarithmic-error were the optimal functions for the log-scaled training data. Furthermore, we figured out that uniformly selected training data lead to the best prediction performance. The optimal loss functions and method for how to compose training data studied in this work would be applied to engineering problems such as evaluating DNA length, analyzing biomolecules, predicting concentration of colloidal suspension.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.1D
• /
• pp.17-23
• /
• 2009

Due to the rapid increase of vehicles on the street, Korean society is facing worsening traffic congestions and air pollutions. Also, the oil price pickup has led to increasing need for the use of public transportation. In particular, transfering among public transportation may be a main factor for riders who are commuting for a long distance journey. In order to ensure such connectivity, transfer stations have been actively built in Korea. However, it would be necessary to shift those vehicles, from cars to public transportations by enhancing the users' satisfaction with public transportation through strategies for minimizing the users' waiting cost by building an efficient connective system between transportation modes as well as the preparation of aforementioned transfer stations. Therefore, this study aimed to develop an algorithm for minimizing transferring passengers' waiting costs based on service intervals of linked buses within the transfer facilities. In order to adjust the service interval, we calculated the total costs, involving the wait cost of transfer passengers and bus operation costs, and produced an allocation interval, that would minimize the costs. We selected a KTX departing from Seoul station, and a No. 6014 bus route in Gwangmyeong city where it starts from the Gwangmyeong station in order to for verifying the model. Then, the transfer passengers' total waitting cost was reduced equivalent to the maximum of 212 minutes, and it revealed that the model performed very effectively.

• Phonetics and Speech Sciences
• /
• v.15 no.3
• /
• pp.75-82
• /
• 2023

Automatic speech recognition (ASR) has been revolutionized with deep learning-based approaches, among which self-supervised learning methods have proven to be particularly effective. In this study, we aim to enhance the performance of OpenAI's Whisper model, a multilingual ASR system on the Korean language. Whisper was pretrained on a large corpus (around 680,000 hours) of web speech data and has demonstrated strong recognition performance for major languages. However, it faces challenges in recognizing languages such as Korean, which is not major language while training. We address this issue by fine-tuning the Whisper model with an additional dataset comprising about 1,000 hours of Korean speech. We also compare its performance against a Transformer model that was trained from scratch using the same dataset. Our results indicate that fine-tuning the Whisper model significantly improved its Korean speech recognition capabilities in terms of character error rate (CER). Specifically, the performance improved with increasing model size. However, the Whisper model's performance on English deteriorated post fine-tuning, emphasizing the need for further research to develop robust multilingual models. Our study demonstrates the potential of utilizing a fine-tuned Whisper model for Korean ASR applications. Future work will focus on multilingual recognition and optimization for real-time inference.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.5
• /
• pp.1-18
• /
• 2023

With the recent developments in big data and deep learning, a variety of traffic information is collected widely and used for traffic operations. In particular, long short-term memory (LSTM) is used in the field of traffic information prediction with time series characteristics. Since trends, seasons, and cycles differ due to the nature of time series data input for an LSTM, a trial-and-error method based on characteristics of the data is essential for prediction models based on time series data in order to find hyperparameters. If a methodology is established to find suitable hyperparameters, it is possible to reduce the time spent in constructing high-accuracy models. Therefore, in this study, a traffic information prediction model is developed based on highway vehicle detection system (VDS) data and LSTM, and an impact assessment is conducted through changes in the LSTM evaluation indicators for each hyperparameter. In addition, a methodology for finding hyperparameters suitable for predicting highway traffic information in the transportation field is presented.