• Title/Summary/Keyword: data set

Search Result 11,124, Processing Time 0.048 seconds

Region of Interest Extraction and Bilinear Interpolation Application for Preprocessing of Lipreading Systems (입 모양 인식 시스템 전처리를 위한 관심 영역 추출과 이중 선형 보간법 적용)

  • Jae Hyeok Han;Yong Ki Kim;Mi Hye Kim
    • The Transactions of the Korea Information Processing Society
    • /
    • v.13 no.4
    • /
    • pp.189-198
    • /
    • 2024
  • Lipreading is one of the important parts of speech recognition, and several studies have been conducted to improve the performance of lipreading in lipreading systems for speech recognition. Recent studies have used method to modify the model architecture of lipreading system to improve recognition performance. Unlike previous research that improve recognition performance by modifying model architecture, we aim to improve recognition performance without any change in model architecture. In order to improve the recognition performance without modifying the model architecture, we refer to the cues used in human lipreading and set other regions such as chin and cheeks as regions of interest along with the lip region, which is the existing region of interest of lipreading systems, and compare the recognition rate of each region of interest to propose the highest performing region of interest In addition, assuming that the difference in normalization results caused by the difference in interpolation method during the process of normalizing the size of the region of interest affects the recognition performance, we interpolate the same region of interest using nearest neighbor interpolation, bilinear interpolation, and bicubic interpolation, and compare the recognition rate of each interpolation method to propose the best performing interpolation method. Each region of interest was detected by training an object detection neural network, and dynamic time warping templates were generated by normalizing each region of interest, extracting and combining features, and mapping the dimensionality reduction of the combined features into a low-dimensional space. The recognition rate was evaluated by comparing the distance between the generated dynamic time warping templates and the data mapped to the low-dimensional space. In the comparison of regions of interest, the result of the region of interest containing only the lip region showed an average recognition rate of 97.36%, which is 3.44% higher than the average recognition rate of 93.92% in the previous study, and in the comparison of interpolation methods, the bilinear interpolation method performed 97.36%, which is 14.65% higher than the nearest neighbor interpolation method and 5.55% higher than the bicubic interpolation method. The code used in this study can be found a https://github.com/haraisi2/Lipreading-Systems.

A Study on the Classification System of Cadastral Cultural Heritage : Focusing on LX museum collection (지적 문화유산 분류체계 연구 - LX국토정보박물관 소장품을 중심으로 -)

  • Kim, Ji-Hyun
    • Journal of Cadastre & Land InformatiX
    • /
    • v.54 no.1
    • /
    • pp.63-74
    • /
    • 2024
  • The fundamental basis for revitalizing cultural resources and developing content is national heritage(cultural property). In national heritage, cultural heritage is a tangible cultural heritage that represents the uniqueness of history and tradition, identity, and changes in life. In the case of museums, the collections (a museum-owned cultural heritage) represent the unique characteristics of the institution. In South Korea, it is recommended that museum collections be registered and used in the Cultural Heritage Standard Management System so that cultural heritage can be managed and utilized in connection with academics, industry, and administration. However, due to a lack of awareness of modern and contemporary heritage, the thematic classification chronology of the system was set mainly before the Joseon Dynasty, and a cultural heritage classification system suitable for national land information has not been established. Therefore, this study aims to propose a classification system for cadastral cultural heritage, based on the modern era when cadastral terminology was first used, using the cultural heritage owned by the LX Museum. Cadastral cultural heritage is characterized by the fact that although it is a field of specialized technology, the surveying or the production of it is not done by specific individuals only, and that while the production is professional, there are many educational aspects in its use. Therefore, unlike other specialized museum collections that are classified based on the functional aspects of their production methods, intended use, and creators, the classification method for cadastral cultural artifacts should be based on the characteristics of the cadastral tools and the outputs. This classification follows a three-tier stages with reference to the items in the Cultural Heritage Standard Management System. This classification aims at the effective use of knowledge by categorizing concepts and systematizing the subjects of data into a series of orders. A safe conservation and management environment for cadastral cultural heritage can be established, and academic and socio-cultural interpretation of the collection is possible by this classfication. Moreover, It is also expected to serve the basis for the national land information as well as searching for the national land information research, planning a exhibition, and the field of education in museum.

Development and Application of the Teacher Education Model for Using Virtual and Augmented Reality Contents in Elementary Science Class (초등 과학 수업에서 가상현실과 증강현실 콘텐츠 활용을 위한 교사 교육 모델의 개발과 적용 사례)

  • Cha, Hyun-Jung;Ga, Seok-Hyun;Yoon, Hye-Gyoung
    • Journal of Korean Elementary Science Education
    • /
    • v.43 no.3
    • /
    • pp.415-432
    • /
    • 2024
  • This study developed and applied the teacher education model and its principles for science classes using Virtual and Augmented Reality (VR/AR) content and analyzed preservice elementary teachers' feedback on the teacher education model and the changes in their perceptions as to the use of VR/AR content. First, existing Technological Pedagogical Content Knowledge (TPACK) teacher education models and prior studies on the use of the VR/AR contents were reviewed to derive the teacher education model to cultivate the VR/AR-TPACK and set the key principles for each of its stages. The developed teacher education model has five stages: exploration, mapping, collaborative design, practice, and reflection. Second, to examine the appropriateness of the model's five stages and principles, we applied it within the regular course of instruction at the university of education, which was attended by 25 preservice elementary teachers. This study collected data from surveys on the perception of the usage of VR/AR contents before and after the course, as well as the group lesson plans prepared by the preservice teachers, and their feedback on the teacher education model. The feedback on the teacher education model and the survey conducted by the preservice teachers before and after the course were analyzed through open coding and categorization. As a result, most preservice teachers expressed positive opinions about the activities and experiences at each stage of the implementation of the teacher education model. Perceptions related to the usage of the VR/AR content changed in three aspects: first, the vague positive perception of the VR/AR content has changed to a positive perception based on specific educational affordance. Second, they recognized the need for preparedness by anticipating potential problems associated with the use of the VR/AR content. Third, they came to view the VR/AR contents as a useful instructional resource that the teachers could use. Based on these results, we discussed the implications for the VR/AR-TPACK teacher education model and assessed the limitations of the research.

Exploration of Organizational Members' ESG Attitudes and Recognition of Performance Obstacles: Focusing on Members of Public Institutions (조직구성원의 ESG 태도와 성과 장애요인 인식에 관한 탐색: 공공기관(직업능력개발조직) 구성원을 중심으로)

  • Dong-tae Kim;Eun-young Lee;Jae-kyu Myung
    • Journal of Practical Engineering Education
    • /
    • v.16 no.5_spc
    • /
    • pp.747-756
    • /
    • 2024
  • The purpose of this study was to discover the desirable ESG direction of public institutions and obstacles to promoting ESG management as perceived by members within public institutions. To this end, three research questions were set and FGI was conducted on eight groups of public institution members. As a result of the FGI data analysis, 9 subfactors and 43 meaning units in 3 dimensions corresponding to the answers to the 3 research questions were derived. The first dimension, public institution members' awareness of ESG, consisted of three subfactors: ESG was recognized as an environmental protection trend related to the climate change crisis, and as a marketing tool used by companies to enhance their image. In addition, it was recognized as a newly included public institution management evaluation index. The second dimension, obstacles to the promotion of ESG in public institutions, appeared to be four subfactors: a government-dependent management system strongly influenced by the government, a rigid internal communication system in a top-down manner, the possibility of lack of sincerity in promoting ESG management, limitations of the internal human resource management system, etc. The third dimension, the desirable ESG direction of public institutions, was found to be two subfactors, including priority promotion of activities that meet the unique purpose of public institutions and ESG activities that can grow together with the region as a member of the local community. This study is significant in that, unlike existing studies that discovered positive antecedent factors that affect a company's ESG management performance, it identified factors that impede performance achievement from the perspective of the members who drive ESG.

Analysis of Private Road Toll Discounts and Subsidy Payment Plan for Sunset-type Vehicles (민자도로의 통행료 할인 현황과 일몰형 통행차량의 보조금 지급 방안)

  • Kim, Ji-Myong;Lim, Kwangk-kyun
    • KSCE Journal of Civil and Environmental Engineering Research
    • /
    • v.44 no.4
    • /
    • pp.519-529
    • /
    • 2024
  • Vehicle toll discounts on private roads are categorized into two types: non-sunset and sunset. Sunset types refer to provisions in which all or part of a law loses its effect upon a specific legislator-set deadline. Vehicles eligible for 'sunset' discounts include cargo vehicles operating late at night and eco-friendly vehicles powered by electricity or hydrogen. Korean government has subsidized all reduced toll fees for vehicles classified as non-sunset types on private roads to operators, but no subsidies have been provided for toll reductions on sunset vehicles. The rapid increase in electric hydrogen vehicles escalates the burden of reduced toll revenue on private road operators. This study analyzed traffic volume and toll reduction data from eight private road operators nationwide as of the end of 2023 to propose the necessity and method of supporting sunset-type toll reduction subsidies. In 2022, the subsidy for non-sunset types amounted to 87.5 billion won, or 18.6 % of total traffic revenue. The toll exemption and reduction ratio under the concession agreement ranged from 4.0 % to 5.65 % of total traffic volume for each operator. Although the proportion of vehicles exempted from sunset traffic increased from 0.85 % in 2017 to 2.79 % in 2022, the reduction amount ratio reached 4.2 % (KRW 25.5 billion) of total traffic revenue in 2022. The escalating number of registered eco-friendly vehicles is gradually causing operating profit losses on private roads. In alignment with the government's policy to expand eco-friendly vehicles, it is imperative to consider including vehicles eligible for toll reductions listed under the sunset category for subsidy payments. The study established a minimum ratio for toll reduction assistance at 4.0 %, agreed upon between the road authorities and private operators. Three policy alternatives were proposed to ensure preservation of amounts exceeding this threshold for sustaining adequate toll revenue for private road operators.

Seed and Germination Characteristics of Allium koreanum H.J. Choi & B.U. Oh for Effective Propagation (효과적인 번식을 위한 돌부추의 종자 및 발아 특성)

  • Hee Sung Hwang;Jeong Hun Hwang;Ji Hye Yun;So Yeong Hwang;Ji Eun Park;Hyeon Eui Oh;Sang Jun Lee;Jeong Mi Park;Seung Jae Hwang
    • Journal of Bio-Environment Control
    • /
    • v.32 no.4
    • /
    • pp.359-365
    • /
    • 2023
  • Native plants are unique genetic resources that have the potential to be used as ornamental, medical, and food resources. Allium koreanum H.J. Choi & B.U. Oh is one of the native plants distributed in the coastal rocky land of Korea, which has high conservation value due to climate change and reduction of its habitat. This study was conducted to investigate the effects of temperature and hydrogen peroxide on the germination of A. koreanum. The seeds were prepared as untreated (control) or those treated with 1% hydrogen peroxide for 90 minutes (H2O2), and the treatments were placed in plant growth chambers set at 15, 20, and 25℃. Regardless of the H2O2 treatment, the germination percentage at 15℃, which was 42%, was more than two times higher than that at 20℃ and 25℃, which were 18% and 0%, respectively, 23 days after sowing. The number of days to attain 50% of the final germination percentage (T50) was the shortest at 20℃, but the mean daily germination (MDG) was the highest at 15℃. Therefore, 1% of H2O2 treatment did not have a significant effect on the germination percentage of A. koreanum, and a temperature of 15℃ was considered to be optimum to increase the germination percentage of A. koreanum. The results of this study can be used as basic research data for the germination of A. koreanum.

Comparison of Seedling Quality of Cucumber Seedlings and Growth and Production after Transplanting according to Differences in Seedling Production Systems (육묘 생산 시스템 차이에 따른 오이 모종의 묘소질과 정식 후 생육 비교)

  • Soon Jae Hyeon;Hwi Chan Yang;Young Ho Kim;Yun Hyeong Bae;Dong Cheol Jang
    • Journal of Bio-Environment Control
    • /
    • v.33 no.2
    • /
    • pp.88-98
    • /
    • 2024
  • This study provides basic data on the growth and production of seedlings produced in plant factories with artificial lighting by comparing seedling quality, growth and fruit characteristics, and production after transplanting cucumber seedlings according to environmental differences between plant factories with artificial lighting and conventional nurseries in greenhouse. The control group consisted of greenhouse seedlings (GH) grown in the conventional nursery before transplanting. Plant factory to greenhouse seedlings (PG) were grown for 9 days in a plant factory with artificial lighting and for 13 days in an conventional nursery. Plant factory seedlings (PF) were grown in a plant factory with artificial lighting for 22 days until planting. In terms of seedling quality, PFs had the highest relative growth rate and compactness and the best root zone development. After transplanting PFs tended to grow faster, the first harvest date was 2 days earlier than that of GHs, and the growing season ended 1 day earlier. The female flower flowering rate of the PFs was high, and the fruit set rate was of PF the lowest. The production per unit area was highest for PFs at 10.23kg Performance index on the absorption basis, the most sensitive chlorophyll fluorescence parameter, was highest at 4.14 for PFs at 4 weeks after transplantation. By comparing the maximum quantum yield of primary PS II photochemistry and dissipated energy flux per PS II reaction center electron at 4 weeks after transplantation, PFs tended to be the least stressed. PFs had the best seedling quality, growth, and production after planting, and fruit quality was consistent with that of greenhouse seedlings. Therefore, plant factory seedlings can be used in the field.

Why Is the Rate of Poor Subjective Health Notably High in South Korea? The Importance of Managing Healthcare Needs (한국인은 왜 주관적 건강상태가 매우 나쁠까? 의료필요 관리의 중요성)

  • Woojin Chung
    • Health Policy and Management
    • /
    • v.34 no.3
    • /
    • pp.334-346
    • /
    • 2024
  • Background: Research on the link between subjective health and unmet healthcare needs is limited. This study examines whether experiences of subjective healthcare needs and unmet needs are related to subjective health in South Korea, where the rate of poor subjective health is notably high. Methods: This analysis utilized data from the Korea Health Panel (2014-2018), incorporating 68,930 observations from 16,535 adults aged 19 or older. The dependent variable, subjective health, was dichotomized into poor (bad or very bad) and non-poor (fair, good, or very good) categories. The primary variables of interest were the experiences of subjective healthcare needs and unmet needs, while control variables included 14 socio-demographic, health, and functional characteristics. The study employed population proportion analysis and multivariable two-level binary logistic regression analysis for each gender, accounting for the complex sampling design. Results: In 2018, the rate of reporting poor health was 8.7% (95% confidence interval [CI], 8.0%-9.5%) for men and 14.7% (95% CI, 13.8%-15.6%) for women. For both genders, compared to individuals whose healthcare needs were met, those without healthcare needs were less likely to report poor subjective health (adjusted odds ratio [AOR], 0.58; 95% CI, 0.39-0.86 for men; AOR, 0.59; 95% CI, 0.37-0.93 for women). Conversely, individuals whose healthcare needs were not met were more likely to report poor subjective health (AOR, 2.31; 95% CI, 2.01-2.65 for men; AOR, 2.19; 95% CI, 1.98-2.43 for women). A policy simulation indicated that reducing the experience of subjective healthcare needs would be approximately 5 times more effective in reducing poor subjective health than a policy focused on reducing the experience of unmet needs. Conclusion: South Korea must make significant efforts to reduce the deterioration of subjective health and promote appropriate healthcare utilization. To achieve this, a set of policies is recommended to address subjective healthcare needs. These policies should include (1) prompting individuals to proactively manage their own health, (2) providing primary healthcare similar to that in advanced countries, (3) ensuring the healthcare delivery system operates effectively, (4) decentralizing the healthcare management system, and (5) reducing the likelihood of people being misled into thinking they have a healthcare need.

Development of a Model for MR-CT Bi-directional Conversion based on scCycleGAN (scCycleGAN 기반 MR-CT 상호 변환 모델의 구축)

  • Da-Um Jeong;Seung-Jin Park;Seung-Yeon Shin;Yong-Ah Lee;Seong-Bin Jang;Jong-Cheon Lim;Joo-Wan Hong;Dong-Kyoon Han
    • Journal of the Korean Society of Radiology
    • /
    • v.18 no.6
    • /
    • pp.715-724
    • /
    • 2024
  • We aimed to build an MR-CT interconversion model based on structure-constraints Cycle-constraints Generative Adversarial Neural Networks (scCycleGANs). We used MDCT (Somatom Definition Flash CT, SIEMENS, Germany) and 3.0T MRI (Ingenia 3.0T CX MRI, PHILIPS, Netherlands) as our hardware equipment and Python (3.12.6) and PyTorch (2.4.0) as software. The study model was scCycleGAN. We acquired 2,871 and 2,436 brain CT and MR (T2WI) images of 87 patients, respectively, and for a total of 5,307 medical images, CT and MR images taken at the same level were classified through primary evaluation, and 364, 27, and 8 pairs of images were labeled as training, validation, and test data, respectively. Then, we applied hybrid objective function to the GAN model based on the basic APS frameworks to build the model, and the evaluation of the generated model was divided into quantitative and qualitative evaluation. The qualitative evaluation was conducted on 10 radiologists with more than 20 years of experience, and the quantitative evaluation was set as PSNR, IOU, SSIM, and MAE. The results of the qualitative evaluation showed that the percentage of 'positive responses', defined as a response of 'Neutral' or better, was 63% and 96% for the Synthesis CT (sCT) and Synthesis MR (sMR) groups, respectively, while the quantitative evaluation metrics PSNR, SSIM, and MAE achieved the initial target values for both groups. Our study can be used as basic guided research in the field of medical image conversion and synthesis. And further research and complementary studies are expected to solve problems such as model lightweighting to reduce the dose burden on patients and medical costs if applied to clinical environments.

Lethal Concentration and Histological Changes of Juvenile Whitespotted Conger (Conger myriaster) Exposed to Various Salinity Concentrations (염분 농도에 따른 붕장어(Conger myriaster) 치어의 반수치사농도 및 조직학적 변화)

  • Jido Han;Hyo-Won Kim;Hyun Woo Gil;Jae-Kwon Cho;Young Guk Jin
    • Journal of Marine Life Science
    • /
    • v.9 no.2
    • /
    • pp.127-135
    • /
    • 2024
  • This study examined the survival rate, blood cortisol concentration, and histological changes in the gills and liver of juvenile Whitespotted conger Conger myriaster under acute low-salinity exposure. Experimental salinity levels were set at 33 (control), 30, 20, 10, 5, 3, and 0 psu, with water temperature maintained at 20.7±0.9℃. The experiment lasted 96 hours at each salinity level, and no feeding was provided during this period. As a result, no mortality occurred at salinity levels from 33 to 10 psu. However, at 5 psu, mortality began at 48 hours, resulting in a 40% survival rate by the end of the experiment, while complete mortality occurred at 3 and 0 psu at 72 and 24 hours, respectively. The lethal salinity concentration for 50% mortality (LC50) was determined to be 5.33 psu. Plasma cortisol concentration tended to increase as salinity decreased, with a significant increase observed at 3 psu compared to other groups (p<0.05). Histological observation of the liver showed decreased glycogen accumulation and an increase in vacuolated lipid droplets at 10 and 5 psu, while cell condensation, necrosis, and lipidization were observed in liver cells at 3 psu. In the gill tissue, increased blood flow in the lamellar capillaries was noted at 20 and 10 psu, while epithelial detachment, lamellar fusion, and clubbing were observed at 5 and 3 psu, with these effects more frequent at 3 psu. These findings indicate that Conger myriaster is a species with high salinity tolerance, and this data is expected to be useful as a foundational resource for the development of aquaculture techniques for this species.