• 대한원격탐사학회지
• /
• 제24권5호
• /
• pp.517-524
• /
• 2008

In order to classify an satellite imagery into geospatial features of interest, the supervised classification needs to be trained to distinguish these features through training sampling. However, even though an imagery is classified, different results of classification could be generated according to operator's experience and expertise in training process. Users who practically exploit an classification result to their applications need the research accomplishment for the consistent result as well as the accuracy improvement. The experiment includes the classification results for training process used VITD polygons as a prior probability and training parameter, instead of manual sampling. As results, classification accuracy using VITD polygons as prior probabilities shows the highest results in several methods. The training using unsupervised classification with VITD have produced similar classification results as manual training and/or with prior probability.

• Journal of Yeungnam Medical Science
• /
• 제38권1호
• /
• pp.10-18
• /
• 2021

Endometriosis is a chronic disease associated with pelvic pain and infertility. Several classification systems for the severity of endometriosis have been proposed. Of these, the revised American Society for Reproductive Medicine classification is the most well-known. The ENZIAN classification was developed to classify deep infiltrating endometriosis and focused on the retroperitoneal structures. The endometriosis fertility index was developed to predict the fertility outcomes in patients who underwent surgery for endometriosis. Finally, the American Association of Gynecological Laparoscopists classification is currently being developed, for which 30 endometriosis experts are analyzing and researching data by assigning scores to categories considered important; however, it has not yet been fully validated and published. Currently, none of the classification systems are considered the gold standard. In this article, we review the classification systems, identify their pros and cons, and discuss what improvements need to be made to each system in the future.

• Asian Pacific Journal of Cancer Prevention
• /
• 제17권5호
• /
• pp.2679-2681
• /
• 2016

Background: Gastro-entero-pancreatic neuroendocrine neoplasms (GEP-NEN) are relatively rare tumors, not equally distributed in gastro-intestinal system. In 2010, a revised version of the WHO classification of GEP-NENs was published. This study reports for the first time the distribution and characteristics of GEP-NEN in a Lebanese population. Materials and Methods: This descriptive retrospective study concerns all the digestive neuroendocrine tumors with their characteristics diagnosed in $H\hat{o}tel$ Dieu de France in Beirut, Lebanon from 2001 to 2012, all the pathology reports being reanalyzed according to the latest WHO 2010 classification. The characteristics and features of GEP-NEN analyzed in this study were age, gender, grade and site. Results: A total of 89 GEP-NENs were diagnosed, representing 28.2% of all neuroendocrine tumors. The mean age of GEP-NEN patients was 58.7 years and the M/F sex ratio was 1.2. The primary localization was as follows: 21.3%(19) pancreatic, 18% (16) gastric, 15.7% (14) duodenal, 11.2% (10) appendix, 10.1% (9) intestinal, 10.1% (9) colorectal (7.9% colonic and 2.2% rectal), 5.6% (4) hepatic, 2.2% (2) ampulla, 1.1% (1) esophageal and 7.9%(5) NOS digestive (metastatic with unknown primary). Of the 89 patients with GEP-NEN, 56.2% (50) were diagnosed as grade I, 11.2% (10) as grade II, 20.2% (18) as grade III and 12.4% (11) were considered as mixed adeno-neuroendocrine carcinomas (MANEC). Conclusions: This study, one of the rare examples based on the 2010 WHO classification of neuroendocrine tumors in the literature, indicates that in the Lebanese population, all duodenal and appendicular tumors are G1 and the majority of MANEC tumors are gastric and pancreatic tumors. Moreover, more duodenal tumors and fewer rectal tumors were encountered in our study compared to European reports.

• Journal of Yeungnam Medical Science
• /
• 제28권1호
• /
• pp.1-12
• /
• 2011

Primary liver carcinomas have classified classified into hepatocellular carcinoma, cholangiocarcinoma, and combined hepatocellular-cholangiocarcinoma (CHC). CHC is a tumor containing unequivocal, intimately mixed elements of both hepatocellular carcinoma and cholangiocarcinoma. It forms a small but significant proportion of primary liver carcinomas. The origin and pathogenesis of CHC have not been well established. According to the 2010 WHO classification, CHCs are categorized into 2 groups: the classical type and a subtype with stem cell features. This review describes recent progress in pathology and classification of CHC.

• 한국응용과학기술학회지
• /
• 제41권3호
• /
• pp.673-684
• /
• 2024

This study aims to enhance the accuracy of severity classification by examining the usage patterns and characteristics of emergency department visits. It focuses on adult and elderly patients who visited a public hospital in Seoul. This descriptive study retrospectively reviewed the electronic medical records of patients who visited the emergency department of a public hospital between November and December 2023. The total number of participants was 1,033, with 46.4% (n=479) being elderly and 53.6% (n=554) being adults. The chief complaints of the participants were as follows: for the elderly, nervous system symptoms at 8.2% (n=85) and digestive symptoms at 7.5% (n=77) were the most common, while for adults, gastrointestinal symptoms at 11.0% (n=114) and trauma at 8.6% (n=89) were more prevalent. In the case of the elderly, patients classified as urgent accounted for the highest percentage at 23.9% (n=247), while for adults, non-emergency were more prevalent at 32.2% (n=333). The initial severity classification error rate for elderly patients in the urgent was 3.8%, indicating that the suitability of KTAS for elderly patients with high severity was low. To minimize severity classification errors and enhance KTAS accuracy, it's essential to address its current limitation of only classifying adults and children separately by developing a KTAS classification system that reflects the diverse characteristics of elderly patients.

• 대한지구과학교육학회지
• /
• 제4권2호
• /
• pp.151-165
• /
• 2011

Following a microgenetic design, this study was analysed the characteristic and the change of classification strategy that appear in college students' classification activity. The 4 tasks were developed for classification activity; a shell as a familiar real things, an animal fossil as a unfamiliar real things, a snow flake as a familiar picture cards and galaxy as a unfamiliar picture card. Achieved study to 6 college students who major in elementary education. Data were collected by interview with subjects, subject's classification schema, investigator's observation of subject's activity, and videotaped that record subject's subject classification process over an extended period of 6 times. Result proved in this study is as following. In the 6 times of the data collection procedures, a strategy F identifying concrete attribution of classification objects and a more detailed strategy X3 combining qualitative, spatial and dimensional attribution were found and more frequently used in both groups of college students which reported a classification process and did not report the process. While discovery and absorption of both a concrete classification strategy and a detailed classification strategy were rapidly developed in the reporting group, they were gradually developed in the non-reporting group. In addition to this, as the data collection procedures were progressing, the college students were familiar with change factors of classification tasks and in the case of pictures the classification strategy showed more desirable changes.

• 대한한의학회지
• /
• 제38권3호
• /
• pp.185-196
• /
• 2017

Backgrounds: Inpatient Classification System for Korean Medicine (KDRG-KM) was developed and has been applied for monitoring the costs of KM hospitals. Yet severity of patients' condition is not applied in the KDRG-KM. Objectives: This study aimed to develop the severity classification methods for KDRG-KM and assessed the explanation powers of severity adjusted KDRG-KM. Methods: Clinical experts panel was organized based on the recommendations from 12 clinical societies of Korean Medicine. Two expert panel workshops were held to develop the severity classification options, and the Delphi survey was performed to measure CCL(Complexity and Comorbidity Level) scores. Explanation powers were calculated using the inpatient EDI claim data issued by hospitals and clinics in 2012. Results: Two options for severity classification were deduced based on the severity classification principle in the domestic and foreign DRG systems. The option one is to classify severity groups using CCL and PCCL(Patient Clinical Complexity Level) scores, and the option two is to form a severity group with patients who belonged principal diagnosis-secondary diagnosis combinations which prolonged length of stay. All two options enhanced explanation powers less than 1%. For third option, patients who received certain treatments for severe conditions were grouped into severity group. The treatment expense of the severity group was significantly higher than that of other patients groups. Conclusions: Applying the severity classifications using principal diagnosis and secondary diagnoses can advance the KDRG-KM for genuine KM hospitalization. More practically, including patients with procedures for severe conditions in a severity group needs to be considered.

• 축산식품과학과 산업
• /
• 제4권2호
• /
• pp.2-6
• /
• 2015

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제3권3호
• /
• pp.285-307
• /
• 2009

This paper introduces DICE, a Domain-Independent text Classification Engine. DICE is robust, efficient, and domain-independent in terms of software and architecture. Each module of the system is clearly modularized and encapsulated for extensibility. The clear modular architecture allows for simple and continuous verification and facilitates changes in multiple cycles, even after its major development period is complete. Those who want to make use of DICE can easily implement their ideas on this test bed and optimize it for a particular domain by simply adjusting the configuration file. Unlike other publically available tool kits or development environments targeted at general purpose classification models, DICE specializes in text classification with a number of useful functions specific to it. This paper focuses on the ways to locate the optimal states of a practical text classification framework by using various adaptation methods provided by the system such as feature selection, lemmatization, and classification models.

• 한국식생활문화학회지
• /
• 제29권2호
• /
• pp.178-186
• /
• 2014

This study sought to prove the validity of Hansik Yangnyomjang classification Korean culinary education. survey was conducted among Korean Cuisine professionals, culinary instructors, culinary professionals and potential students from various backgrounds. ata were collected by self-administered questionnaires and analyzed by reliability analysis, frequency analysis and t-test. any differences in terms of the validity of Hansik Yangnyomjang classification between groups based on their majors, teaching experiences, and knowledge of sauce classification. First, the result showed that fermented Jang is core element Korean cuisine. Second, Hansik Yangnyomjang classification needs to be organized around Balhyojang. Third, Hansik Yangnyomjang classification for beginners and foreigners who want to learn Korean Cuisine relatively easily. Finally, the term 'sauce' is not suitable for replacing Yangnyomjang.