• Journal of Dental Rehabilitation and Applied Science
• /
• v.38 no.4
• /
• pp.196-203
• /
• 2022

Purpose: This study aimed to evaluate the accuracy and clinical usability of an identification model using deep learning for 79 dental implant types. Materials and Methods: A total of 45396 implant fixture images were collected through panoramic radiographs of patients who received implant treatment from 2001 to 2020 at 30 dental clinics. The collected implant images were 79 types from 18 manufacturers. EfficientNet and Meta Pseudo Labels algorithms were used. For EfficientNet, EfficientNet-B0 and EfficientNet-B4 were used as submodels. For Meta Pseudo Labels, two models were applied according to the widen factor. Top 1 accuracy was measured for EfficientNet and top 1 and top 5 accuracy for Meta Pseudo Labels were measured. Results: EfficientNet-B0 and EfficientNet-B4 showed top 1 accuracy of 89.4. Meta Pseudo Labels 1 showed top 1 accuracy of 87.96, and Meta pseudo labels 2 with increased widen factor showed 88.35. In Top5 Accuracy, the score of Meta Pseudo Labels 1 was 97.90, which was 0.11% higher than 97.79 of Meta Pseudo Labels 2. Conclusion: All four deep learning algorithms used for implant identification in this study showed close to 90% accuracy. In order to increase the clinical applicability of deep learning for implant identification, it will be necessary to collect a wider amount of data and develop a fine-tuned algorithm for implant identification.

• Journal of Nutrition and Health
• /
• v.52 no.5
• /
• pp.488-500
• /
• 2019

Purpose: This study examined the effects of a mobile app-based program to reduce the dietary sugar intake according to the stages of the behavioral change in dietary sugar reduction in female college students. Methods: The program used in this study can monitor the dietary sugar intake after recording the dietary intake and provide education message for the reduction of dietary sugar intake. In an eight-week pre-post intervention study, 68 female college students were instructed to record all the food they consumed daily and received weekly education information. At pre-post intervention, the subjects were asked to answer the questionnaire about sugar-related nutrition knowledge, sugar-intake behavior, and sugar-intake frequency. For statistical analysis, ANOVA and a paired t-test were used for comparative analysis according Precontemplation (PC), Contemplation Preparation (C P), and A M (Action Maintenance) stage. Results: Significant differences were observed in the frequency of snacking, experience of nutrition education, and preference for sweetness according to the stages of behavior change in dietary sugar reduction. After finishing an intervention, the sugar-related nutrition knowledge score was increased significantly in the stages of Precontemplation (PC) and Contemplation Preparation (C P). The score of the sugar intake behavior increased significantly in all stages. The intake frequency of chocolate, muffins or cakes, and drinking yogurt decreased significantly in the PC stage and the intake frequency of biscuits, carbonated beverages, and fruit juice decreased significantly in the C P stage. Subjects in the PC and C P stages had an undesirable propensity in nutrition knowledge, sugar-intake behavior, and sugar-intake frequency compared to the A M stage, but this intervention improved significantly their nutrition knowledge, sugar-intake behavior, and sugar-intake frequency. Conclusion: This program can be an effective educational tool in the stages of PC and C P, and is expected to further increase the usability and sustainability of mobile application if supplemented appropriately to a health platform program.

• Korean Circulation Journal
• /
• v.53 no.4
• /
• pp.254-267
• /
• 2023

Background and Objectives: Although the shortage of donor is a common problem worldwide, a significant portion of unutilized hearts are classified as marginal donor (MD) hearts. However, research on the correlation between the MD and the prognosis of heart transplantation (HTx) is lacking. This study was conducted to investigate the clinical impact of MD in HTx. Methods: Consecutive 73 HTxs during 2014 and 2021 in a tertiary hospital were analyzed. MD was defined as follows; a donor age >55 years, left ventricular ejection fraction <50%, cold ischemic time >240 minutes, or significant cardiac structural problems. Preoperative characteristics and postoperative hemodynamic data, primary graft dysfunction (PGD), and the survival rate were analyzed. Risk stratification by Index for Mortality Prediction after Cardiac Transplantation (IMPACT) score was performed to examine the outcomes according to the recipient state. Each group was sub-divided into 2 risk groups according to the IMPACT score (low <10 vs. high ≥10). Results: A total of 32 (43.8%) patients received an organ from MDs. Extracorporeal membrane oxygenation was more frequent in the non-MD group (34.4% vs. 70.7, p=0.007) There was no significant difference in PGD, 30-day mortality and long-term survival between groups. In the subgroup analysis, early outcomes did not differ between low- and high-risk groups. However, the long-term survival was better in the low-risk group (p=0.01). Conclusions: The outcomes of MD group were not significantly different from non-MD group. Particularly, in low-risk recipient, the MD group showed excellent early and long-term outcomes. These results suggest the usability of selected MD hearts without increasing adverse events.

• Journal of Intelligence and Information Systems
• /
• v.17 no.1
• /
• pp.53-69
• /
• 2011

Vision and voice-based technologies are commonly utilized for human-robot interaction. But it is widely recognized that the performance of vision and voice-based interaction systems is deteriorated by a large margin in the real-world situations due to environmental and user variances. Human users need to be very cooperative to get reasonable performance, which significantly limits the usability of the vision and voice-based human-robot interaction technologies. As a result, touch screens are still the major medium of human-robot interaction for the real-world applications. To empower the usability of robots for various services, alternative interaction technologies should be developed to complement the problems of vision and voice-based technologies. In this paper, we propose the use of accelerometer-based gesture interface as one of the alternative technologies, because accelerometers are effective in detecting the movements of human body, while their performance is not limited by environmental contexts such as lighting conditions or camera's field-of-view. Moreover, accelerometers are widely available nowadays in many mobile devices. We tackle the problem of classifying acceleration signal patterns of 26 English alphabets, which is one of the essential repertoires for the realization of education services based on robots. Recognizing 26 English handwriting patterns based on accelerometers is a very difficult task to take over because of its large scale of pattern classes and the complexity of each pattern. The most difficult problem that has been undertaken which is similar to our problem was recognizing acceleration signal patterns of 10 handwritten digits. Most previous studies dealt with pattern sets of 8~10 simple and easily distinguishable gestures that are useful for controlling home appliances, computer applications, robots etc. Good features are essential for the success of pattern recognition. To promote the discriminative power upon complex English alphabet patterns, we extracted 'motion trajectories' out of input acceleration signal and used them as the main feature. Investigative experiments showed that classifiers based on trajectory performed 3%~5% better than those with raw features e.g. acceleration signal itself or statistical figures. To minimize the distortion of trajectories, we applied a simple but effective set of smoothing filters and band-pass filters. It is well known that acceleration patterns for the same gesture is very different among different performers. To tackle the problem, online incremental learning is applied for our system to make it adaptive to the users' distinctive motion properties. Our system is based on instance-based learning (IBL) where each training sample is memorized as a reference pattern. Brute-force incremental learning in IBL continuously accumulates reference patterns, which is a problem because it not only slows down the classification but also downgrades the recall performance. Regarding the latter phenomenon, we observed a tendency that as the number of reference patterns grows, some reference patterns contribute more to the false positive classification. Thus, we devised an algorithm for optimizing the reference pattern set based on the positive and negative contribution of each reference pattern. The algorithm is performed periodically to remove reference patterns that have a very low positive contribution or a high negative contribution. Experiments were performed on 6500 gesture patterns collected from 50 adults of 30~50 years old. Each alphabet was performed 5 times per participant using $Nintendo{(R)}$ $Wii^{TM}$ remote. Acceleration signal was sampled in 100hz on 3 axes. Mean recall rate for all the alphabets was 95.48%. Some alphabets recorded very low recall rate and exhibited very high pairwise confusion rate. Major confusion pairs are D(88%) and P(74%), I(81%) and U(75%), N(88%) and W(100%). Though W was recalled perfectly, it contributed much to the false positive classification of N. By comparison with major previous results from VTT (96% for 8 control gestures), CMU (97% for 10 control gestures) and Samsung Electronics(97% for 10 digits and a control gesture), we could find that the performance of our system is superior regarding the number of pattern classes and the complexity of patterns. Using our gesture interaction system, we conducted 2 case studies of robot-based edutainment services. The services were implemented on various robot platforms and mobile devices including $iPhone^{TM}$. The participating children exhibited improved concentration and active reaction on the service with our gesture interface. To prove the effectiveness of our gesture interface, a test was taken by the children after experiencing an English teaching service. The test result showed that those who played with the gesture interface-based robot content marked 10% better score than those with conventional teaching. We conclude that the accelerometer-based gesture interface is a promising technology for flourishing real-world robot-based services and content by complementing the limits of today's conventional interfaces e.g. touch screen, vision and voice.

• The Journal of the Korean bone and joint tumor society
• /
• v.14 no.1
• /
• pp.33-43
• /
• 2008

Purpose: To evaluate the clinical usability of reconstructive methods, and how to select flap after wide excision of malignant soft tissue tumor in ankle and foot. Materials and Methods: The 15 cases shown in the 14 patients (In case of a male patient, reconstruction was performed two times due to local recurrence.) with malignant soft tissue tumor in ankle and foot, who underwent reconstruction after wide excision from March 2000 until March 2007. Oncologic, surgical and functional results were evaluated. Results: The method of reconstruction used were anterolateral thigh perforator flap (5cases), Reversed superficial sural artery flap (4 cases), dorsalis pedis flap (3 cases), local flap (3cases). The defect, mean size was $5.5{\times}5.7\;cm$, was reconstructed with rotation flap or free flap, mean size was $5.9{\times}6.0\;cm$, skin graft for remnant. The mean operation time was 310 minutes (120~540 minutes); it took 256 minutes to reconstruct by rotation flap, and 420 minutes by free flap. As oncologic results, 7 patients were no evidence of disease, 6 patients were alive with disease and 1 patient was expired by pulmonary metastasis at the time of the last follow-up. 4 patients had local recurrence and 4 pateints had distant metastases. As functional results, 14 patients were evaluated with average score of 68.8% using the system of the Musculoskeletal Tumor Society. Conclusion: The dorsalis pedis and reverse superficial sural artery rotation flap which is easy procedure, has less complication and takes short operation time, can be primarily considered to reconstruct a small defect. And the anterolateral thigh perforator flap is suitable for coverage of a large defects after wide excision of malignant soft tissue tumor in ankle and foot.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.89-115
• /
• 2019

This study was conducted to present the stylistic differences between Arthur Conan Doyle and Agatha Christie, famous as writers of classical mystery novels, through data analysis, and further to present the analytical methodology of the study of style based on text mining. The reason why we chose mystery novels for our research is because the unique devices that exist in classical mystery novels have strong stylistic characteristics, and furthermore, by choosing Arthur Conan Doyle and Agatha Christie, who are also famous to the general reader, as subjects of analysis, so that people who are unfamiliar with the research can be familiar with them. The primary objective of this study is to identify how the differences exist within the text and to interpret the effects of these differences on the reader. Accordingly, in addition to events and characters, which are key elements of mystery novels, the writer's grammatical style of writing was defined in style and attempted to analyze it. Two series and four books were selected by each writer, and the text was divided into sentences to secure data. After measuring and granting the emotional score according to each sentence, the emotions of the page progress were visualized as a graph, and the trend of the event progress in the novel was identified under eight themes by applying Topic modeling according to the page. By organizing co-occurrence matrices and performing network analysis, we were able to visually see changes in relationships between people as events progressed. In addition, the entire sentence was divided into a grammatical system based on a total of six types of writing style to identify differences between writers and between works. This enabled us to identify not only the general grammatical writing style of the author, but also the inherent stylistic characteristics in their unconsciousness, and to interpret the effects of these characteristics on the reader. This series of research processes can help to understand the context of the entire text based on a defined understanding of the style, and furthermore, by integrating previously individually conducted stylistic studies. This prior understanding can also contribute to discovering and clarifying the existence of text in unstructured data, including online text. This could help enable more accurate recognition of emotions and delivery of commands on an interactive artificial intelligence platform that currently converts voice into natural language. In the face of increasing attempts to analyze online texts, including New Media, in many ways and discover social phenomena and managerial values, it is expected to contribute to more meaningful online text analysis and semantic interpretation through the links to these studies. However, the fact that the analysis data used in this study are two or four books by author can be considered as a limitation in that the data analysis was not attempted in sufficient quantities. The application of the writing characteristics applied to the Korean text even though it was an English text also could be limitation. The more diverse stylistic characteristics were limited to six, and the less likely interpretation was also considered as a limitation. In addition, it is also regrettable that the research was conducted by analyzing classical mystery novels rather than text that is commonly used today, and that various classical mystery novel writers were not compared. Subsequent research will attempt to increase the diversity of interpretations by taking into account a wider variety of grammatical systems and stylistic structures and will also be applied to the current frequently used online text analysis to assess the potential for interpretation. It is expected that this will enable the interpretation and definition of the specific structure of the style and that various usability can be considered.

• Journal of Venture Innovation
• /
• v.4 no.1
• /
• pp.51-65
• /
• 2021

The HR policy in the public sector was closed and operated mainly on written tests, but in 2006, a new evaluation, promotion and education system based on competence was introduced in the promotion and selection system of civil servants. In particular, the seniority-oriented promotion system was evaluated based on competence by operating an Assessment Center related to promotion. Competency evaluation is known to be the most reliable and valid evaluation method among the evaluation methods used to date and is also known to have high predictive feasibility for performance. In 2001, 19 government standard competency models were designed. In 2006, the competency assessment was implemented with the implementation of the high-ranking civil service team system. In the public sector, the purpose of the competency evaluation is mainly to select third-grade civil servants, assign fourth-grade civil servants, and promotion fifth-grade civil servants. However, competency assessments in the public sector differ in terms of competency assessment objectives, assessment processes and competency assessment programmes compared to those in the private sector. For the purposes of competency assessment, the public sector is for the promotion of candidates, and the private sector focuses on career development and fostering. Therefore, it is not continuously developing capabilities than the private sector and is not used to enhance performance in performing its duties. In relation to evaluation items, the public sector generally operates a system that passes capacity assessment at 2.5 out of 5 for 6 competencies, lacks feedback on what competencies are lacking, and the private sector uses each individual's competency score. Regarding the selection and operation of evaluators, the public sector focuses on fairness in evaluation, and the private sector focuses on usability, which is inconsistent with the aspect of developing capabilities and utilizing human resources in the right place. Therefore, the public sector should also improve measures to identify outstanding people and motivate them through capacity evaluation and change the operation of the capacity evaluation system so that they can grow into better managers through accurate reports and individual feedback

• Korean Journal of Remote Sensing
• /
• v.39 no.5_2
• /
• pp.811-825
• /
• 2023

In accordance with the government's stance of actively promoting intelligent administrative service policies through data utilization, in the disaster and safety management field, it also is proceeding with disaster and safety management policies utilizing data and constructing systems for responding efficiently to new and complex disasters and establishing scientific and systematic safety policies. However, it is difficult to quickly and accurately grasp the on-site situation in the event of a disaster, and there are still limitations in providing information necessary for situation judgment and response only by displaying vast data. This paper focuses on deriving specific needs to make disaster situation management work more intelligent and efficient by utilizing intelligent information technology. Through individual interviews with workers at the Central Disaster and Safety Status Control Center, we investigated the scope of disaster situation management work and the main functions and usability of the geographic information system (GIS)-based integrated situation management system by practitioners in this process. In addition, the data built in the system was reclassified according to purpose and characteristics to check the status of data in the GIS-based integrated situation management system. To derive needed to make disaster situation management more intelligent and efficient by utilizing intelligent information technology, 3 strategies were established to quickly and accurately identify on-site situations, make data-based situation judgments, and support efficient situation management tasks, and implementation tasks were defined and task priorities were determined based on the importance of implementation tasks through analytic hierarchy process (AHP) analysis. As a result, 24 implementation tasks were derived, and to make situation management efficient, it is analyzed that the use of intelligent information technology is necessary for collecting, analyzing, and managing video and sensor data and tasks that can take a lot of time of be prone to errors when performed by humans, that is, collecting situation-related data and reporting tasks. We have a conclusion that among situation management intelligence strategies, we can perform to develop technologies for strategies being high important score, that is, quickly and accurately identifying on-site situations and efficient situation management work support.

• The Journal of Korean Society for Radiation Therapy
• /
• v.25 no.2
• /
• pp.123-129
• /
• 2013

Purpose: The way check the movement of the fiducial marker insertion in the treatment of patients with prostate cancer. However the existing methods of fiducial marker verification process difficult to identify the specific location of the marker behind the femur and pelvic bone. So to study the evaluation of maker match with using kilo voltage (KV) X-ray by On-board imager to both oblique verification method. Materials and Methods: Five patients were selected for rectal ballooning and inserted fiducial marker. Compare the position of the fiducial marker of reference plan 2D/2D Anterior/Posterior verification method and 2D/2D both oblique verification method. So to measurement the shift score of X, Y, Z (axis) and measure exposure dose given to patients and compare matching time. Results: 2 dimensional OBI KV X-ray imaging using two-dimensional matching image are orthogonal, so locating fiducial marker matching clear and useful DRR (digital reconstruction radiography) OBI souce angle ($45^{\circ}/315^{\circ}$) matching most useful. 2D/2D both oblique verification method was able to see clearly marker behind the pelvic bone. Also matching time can be reduced accordingly. According to the method of each matching results for each patient in each treatment fraction, X, Y, and Z axis the Mean $value{\pm}SD$ (standard deviation) is X axis (AP/LAT: $0.4{\pm}1.67$, OBLIQUE: $0.4{\pm}1.82$) mm, Y axis (AP/LAT: $0.7{\pm}1.73$, OBLIQUE: $0.2{\pm}1.77$) mm, Z axis (AP/LAT: $0.8{\pm}1.94$, OBLIQUE:$1.5{\pm}2.8$) mm. In addition, the KV X-ray source dose radiation exposure given to the patient taking average when AP/LAT matching is (0.1/2.1) cGY, when $315^{\circ}/45^{\circ}$ matching is (0.27/0.26) cGY. Conclusion: In conclusion for inserted fiducial marker of prostate cancer patients 2D/2D both oblique matching method is more accurate verification than 2D/2D AP/LAT matching method. Also the matching time less than the 2D/2D AP/LAT matching method. Taken as the amount of radiation exposure to patients less than was possible. Suggest would improve the treatment quality of care patients more useful to establish a protocol such as case.