• The Journal of the Acoustical Society of Korea
• /
• v.41 no.6
• /
• pp.655-661
• /
• 2022

Since speech impairment is prevalent in patients with Parkinson's disease (PD), speech recognition systems suitable for these patients are needed. In this paper, we propose a speech recognition system that effectively recognizes the speech of patients with PD. The speech recognition system is firstly pre-trained with the Globalformer using the speech data from healthy people, and then fine-tuned using relatively small amount of speech data from the patient with PD. For this analysis, we used the speech dataset of healthy people built by AI hub and that of patients with PD collected at Inha University Hospital. As a result of the experiment, the proposed speech recognition system recognized the speech of patients with PD with Character Error Rate (CER) of 22.15 %, which was a better result compared to other methods.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.3
• /
• pp.1-6
• /
• 2023

In the realm of dental prosthesis fabrication, obtaining accurate impressions has historically been a challenging and inefficient process, often hindered by hygiene concerns and patient discomfort. Addressing these limitations, Company D recently introduced a cutting-edge solution by harnessing the potential of intraoral scan images to create 3D dental models. However, the complexity of these scan images, encompassing not only teeth and gums but also the palate, tongue, and other structures, posed a new set of challenges. In response, we propose a sophisticated real-time image segmentation algorithm that selectively extracts pertinent data, specifically focusing on teeth and gums, from oral scan images obtained through Company D's oral scanner for 3D model generation. A key challenge we tackled was the detection of the intricate molar regions, common in dental imaging, which we effectively addressed through intelligent data augmentation for enhanced training. By placing significant emphasis on both accuracy and speed, critical factors for real-time intraoral scanning, our proposed algorithm demonstrated exceptional performance, boasting an impressive accuracy rate of 0.91 and an unrivaled FPS of 92.4. Compared to existing algorithms, our solution exhibited superior outcomes when integrated into Company D's oral scanner. This algorithm is scheduled for deployment and commercialization within Company D's intraoral scanner.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.6
• /
• pp.243-248
• /
• 2013

With rapid growth and fast diffusion of smartphone technologies, many users are deeply concerned about the smart applications and many mobile applications converged with various related technologies are rapidly disseminated. Especially, the convergence technologies like mobile apps that can establish the wireless ad hoc network between smartphone and other peripherals and exchange data are appear and progressed continuously. In this paper, we design and implement the smart app using bluetooth based wireless ad hoc sensor network that can connect smartphone with sensors and exchange data for various smart applications. The proposed smart application in this paper collects data obtained from more than 2 multi-sensors in real time and fulfills the decision making function by storing data at the database and analysing it. The smart application designed and implemented in this paper is the healthcare application that can analyze and evaluate the patient's health condition with sensing data from multi-sensors in real time through bluetooth module.

• Journal of Internet Computing and Services
• /
• v.11 no.2
• /
• pp.129-142
• /
• 2010

The ubiquitous healthcare environment is one of the systems that benefit from wireless sensor network. But one of the challenges with wireless sensor network is its high loss rates when transmitting data. Data from the biosensors may not reach the base stations which can result in missing values. This paper proposes the Health Monitor Agent (HMA) to gather data from the base stations, predict missing values, classify symptom patterns into medical conditions, and take appropriate action in case of emergency. This agent is applied in the Ubiquitous Healthcare Environment and uses data from the biosensors and from the patient’s medical history as symptom patterns to recognize medical conditions. In the event of missing data, the HMA uses a predictive algorithm to fill missing values in the symptom patterns before classification. Simulation results show that the predictive algorithm using the HMA makes classification of the symptom patterns more accurate than other methods.

• KIEAE Journal
• /
• v.12 no.6
• /
• pp.113-121
• /
• 2012

A hospital is the most important infra-facility of the places which take care of people's body in social environment. There exist several environmental factors in the ways to heal the human body in hospital ward, but this study tried to look into the improvable pleasant sickroom environment with focus on light environment among the factors. In other words, this study aims at the research on proper daylight inflow into sickroom space as basic data for understanding the link between healing environment and natural lighting. In the simulation analysis through this research, this study completed the initial simulation using Autodesk Revit 2011 with focus on two types of individual multi-bed room units of the two general hospitals located in Gwangju City. This study made a simulation analysis of The two multi-bed rooms looking to the west using the weather data on Gwangju district, which is the strong point of ECOTECT2011. Conclusively, looking into the analysis of the simulation model in time of attaching the length of in & outside light shelf, the angle controlling of light shelf, the daylight factor and DA were found to show the tendency to decrease in the numerical value due to the decrease in sunlight inflow as the simulation model moved more toward the room from the window in comparison with the existing analysis of multi-bed rooms. Particularly, this study was able to read that the daylight factor and DA were more decreasing to improve at the light shelf than the existing bedrooms; conclusively, this study judges that the natural lighting simulation analysis could be helpful in improving the healing environment as basic data.

• Journal of radiological science and technology
• /
• v.24 no.2
• /
• pp.71-75
• /
• 2001

As the adoption of PACS and hospital information system among university hospitals and hospital level institutions grows bigger, the need of sharing and transferring medical information among medical institutions is rising. For the medical information, which is saved in the hospital medical system, to be transferred within the same hospital, domestic, or foreign medical institutions, a standard protocol is necessary. But realistically, most of the domestic hospitals do not abide by H7L which is the HIS standard and so, information transferring is not possible as of present. As such, the purpose of this research is to implement the information between HIS and PACS to an international standard by constructing HL7 messages through HL7 Interface. which will eventually make possible information transferring between different hospitals. Our research team has developed a method which will make the PACS equip hospitals that do not follow HL7 standard which will make possible to transfer information between HIS and PACS through HL7 Message. By constructing message files, which follow the form of HL7 Message in the HL7 Interface, they can be transferred to PACS through the ftp protocol. The realization of the HIS/OCS Interface through HL7 enables data transferring between domestic and foreign medical institutions possible by implementing the international standard in the PACS and HIS data transferring process. The HL7 that our research team has developed made patient data transfer between medical institutions possible. The Interface is for a specific system model and in order for the data transfer between different systems to be realized, interfaces that are fit for each system must be needed. If the interface is improvised and implemented to each hospital's information system, the data sharing among medical institutions can be broadened.

• Neurospine
• /
• v.15 no.4
• /
• pp.329-337
• /
• 2018

Objective: Machine learning algorithms excel at leveraging big data to identify complex patterns that can be used to aid in clinical decision-making. The objective of this study is to demonstrate the performance of machine learning models in predicting postoperative complications following anterior cervical discectomy and fusion (ACDF). Methods: Artificial neural network (ANN), logistic regression (LR), support vector machine (SVM), and random forest decision tree (RF) models were trained on a multicenter data set of patients undergoing ACDF to predict surgical complications based on readily available patient data. Following training, these models were compared to the predictive capability of American Society of Anesthesiologists (ASA) physical status classification. Results: A total of 20,879 patients were identified as having undergone ACDF. Following exclusion criteria, patients were divided into 14,615 patients for training and 6,264 for testing data sets. ANN and LR consistently outperformed ASA physical status classification in predicting every complication (p < 0.05). The ANN outperformed LR in predicting venous thromboembolism, wound complication, and mortality (p < 0.05). The SVM and RF models were no better than random chance at predicting any of the postoperative complications (p < 0.05). Conclusion: ANN and LR algorithms outperform ASA physical status classification for predicting individual postoperative complications. Additionally, neural networks have greater sensitivity than LR when predicting mortality and wound complications. With the growing size of medical data, the training of machine learning on these large datasets promises to improve risk prognostication, with the ability of continuously learning making them excellent tools in complex clinical scenarios.

• Journal of The Korean Dental Society of Anesthesiology
• /
• v.12 no.3
• /
• pp.157-163
• /
• 2012

Background: The major goal of dental management before and after liver transplantation is the prevention of bacteremia from an oral source that could lead to systemic infection. However dental treatment in liver transplant patients have the risk of infection and bleeding. so it is needed special dental consideration. Methods: 42 liver transplant candidates who visited department of Advanced General Dentistry in Yonsei University College of dentistry from March 1, 2010 to February 29, 2012 were selected. The clinical data of those patients were analyzed; coagulation status such as PT, INR, aPTT, platelet count before and 6 months after liver transplantation, dental infectious foci, time interval between dental visit and operation date of liver transplantation. Results: Before liver transplant, the patient's PT and INR was prolonged, and the platelet count was lower than normal range. But 6 months later from liver transplantation, most of the figures turned into a normal range. The dental infection foci were chronic periodontitis, dental caries, chronic apical periodontitis, root rest et al but we did extraction of 6 root rest before liver transplantation and postponed other treatment after liver transplantation due to bleeding and infection risk of patients. Because of insufficient interval between dental visit and operation date, 64.3% of patients could not finish the dental treatment. Conclusions: The patients before liver transplantation have the risk of bleeding. The treatment of those patient should be removal of only factors that can cause dental infections after transplantation and other treatment must be postponed until the stable period of the transplant that patient's condition has improved.

• Research in Community and Public Health Nursing
• /
• v.7 no.2
• /
• pp.333-348
• /
• 1996

The purpose of this study was to examine the effect of nursing information on the level of need fulfillment and anxiety of the emergency patient's family members. The quasi-experimental study was designed using a noneqivalent control group non-synchronized design. During the first period, 30 subjects were assigned to the control group and 25 to the experimental group at a late period. The experimental group was provided with nursing information via guide booklet designed by the researcher. The control group received only routine care. Data was collected from January 31 to April 16 in 1996 at the K hospital in Taegu and analysed by chi-square test, t-test, ANOVA and Pearson correlation with SAS program. The instruments used for this study were the Family Needs Scale developed by Jung and the State-Trait Anxiety Inventory developed by Spielberger. The results of this study were summarized as follows : 1. The first hypothesis that the family members who received nursing information will have greater need fulfillment than family members who did not receive nursing information was supported. 2. The second hypothesis that the family members who received nursing information will have lower anxiety level than family members who did not receive nursing information was not supported. 3. The third hypothesis that the more the need of family member of emergency patient was met, the lower the anxiety level, was not supported. In conclusion, it was proved that nursing information about the emergency room provides family members with more need fulfillment, but did not decrease the anxiety level.

• Journal of the Korean Society of Radiology
• /
• v.12 no.3
• /
• pp.373-379
• /
• 2018

The purpose of this study was to investigate quantitative data on the difference in breast entrance surface dose with changes in focus-film distance, patient posture (anteroposterior-posteroanterior), thoracic wall thickness, rib bone thickness, lung tissue thickness, tube voltage, and high-voltage rectification method in Whole Spine Scanography, which is necessary for the treatment of scoliosis patients. Given a tube voltage of 90 kVp, kerma of 0.1 mGy, focus-film distance of 260 cm, tube voltage ripple rate of 0, filter thickness of 3.5 mm, and thickness of patient's thoracic wall of 120 mm as an X-ray exposure condition, from the simulation results using the Simulation of X-ray Spectra program to confirm the reduction effect of breast entrance surface dose according to the patient's posture (AP and PA), there was a dose reduction effect in aluminum filter thickness of 2.6 times at 3.5 mm, 25.7 times the thoracic wall thickness at 120 mm, 1.43 times higher tube voltage, and 0 to 1.14 times the tube voltage ripple rate. The total dose reduction effect was about 109 times. In order to confirm the dose reduction effect of RANDO phantom posture (AP and PA), from the results of the measurements taken under the conditions that the focus-film distance was 260 cm, the tube voltage was 90 kVp, the tube current was 270 mA, the exposure time was 0.31 sec, and the tube voltage ripple rate of X-ray generators was 0, the entrance surface dose reduction effect of the breast in the PA position was found to be 20.56 times lower than that of the AP position.