• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.3
• /
• pp.1643-1647
• /
• 2013

Background: To identify the risk factors and assess the role of survivin in predicting progessivity precancerous cervical lesions. Materials and Methods: This case-control study was conducted from October 2009 until May 2010. We obtained 74 samples, classified according to the degree of cervical intraepithelial neoplasia (CIN): 19 samples for CIN 1, 18 samples for CIN 2, 18 samples for CIN 3, and 19 samples as controls. Demographic profiles and risk factors assesment, histopathologic examination, HPV DNA tests, immunocytochemistry (ICC) and immunohistochemistry (IHC) staining for survivin expression were performed on all samples. Data was analyzed with bivariate and multivariate analysis. Results: Multivariate analysis revealed significant risk factors for developing precancerous cervical lesions are age <41 years, women with ${\geq}2$ sexual partners, course of education ${\geq}13$ years, use of oral contraceptives, positive high-risk HPV DNA, and high survivin expression by ICC or IHC staining. These factors were fit to a prediction model and we obtained a scoring system to predict the progressivity of CIN lesions. Conclusions: Determination of survivin expression by immunocytochemistry staining, along with other significant risk factors, can be used in a scoring system to predict the progressivity of CIN lesions. Application of this scoring system may be beneficial in determining the action of therapy towards the patient.

• ETRI Journal
• /
• v.46 no.1
• /
• pp.82-95
• /
• 2024

As automated essay scoring (AES) has progressed from handcrafted techniques to deep learning, holistic scoring capabilities have merged. However, specific trait assessment remains a challenge because of the limited depth of earlier methods in modeling dual assessments for holistic and multi-trait tasks. To overcome this challenge, we explore providing comprehensive feedback while modeling the interconnections between holistic and trait representations. We introduce the DualBERT-Trans-CNN model, which combines transformer-based representations with a novel dual-scale bidirectional encoder representations from transformers (BERT) encoding approach at the document-level. By explicitly leveraging multi-trait representations in a multi-task learning (MTL) framework, our DualBERT-Trans-CNN emphasizes the interrelation between holistic and trait-based score predictions, aiming for improved accuracy. For validation, we conducted extensive tests on the ASAP++ and TOEFL11 datasets. Against models of the same MTL setting, ours showed a 2.0% increase in its holistic score. Additionally, compared with single-task learning (STL) models, ours demonstrated a 3.6% enhancement in average multi-trait performance on the ASAP++ dataset.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.408-410
• /
• 2021

In the NLP field, the pre-training model BERT launched by the Google team in 2018 has shown amazing results in various tasks in the NLP field. Subsequently, many variant models have been derived based on the original BERT, such as RoBERTa, ERNIEBERT and so on. In this paper, the WWMBERT (Whole Word Masking BERT) model suitable for Chinese text tasks was used as the baseline model of our experiment. The experiment is mainly for "Text-level Chinese text classification tasks" are improved, which mainly combines Tapt (Task-Adaptive Pretraining) and "Multi-Sample Dropout method" to improve the model, and compare the experimental results, experimental data sets and model scoring standards Both are consistent with the official WWMBERT model using Accuracy as the scoring standard. The official WWMBERT model uses the maximum and average values of multiple experimental results as the experimental scores. The development set was 97.70% (97.50%) on the "text-level Chinese text classification task". and 97.70% (97.50%) of the test set. After comparing the results of the experiments in this paper, the development set increased by 0.35% (0.5%) and the test set increased by 0.31% (0.48%). The original baseline model has been significantly improved.

• The Korean Journal of Applied Statistics
• /
• v.20 no.3
• /
• pp.423-440
• /
• 2007

Although various models have been developed to establish the enterprise credit scoring, no model has utilized the enterprise human resource so far. The purpose of this study was to build an enterprise credit scoring model using enterprise human resource factors. The data to measure the enterprise credit score were made by the first-year research material of HCCP was used to investigate the enterprise human resource and 2004 Credit Rating Score generated from KIS-Credit Scoring Model. The independent variables were chosen among questionnaires of HCCP based on Mclagan(1989)'s HR wheel model, and the credit score of Korean Information Service was used for the dependent variables. The statistical method used for data analysis was logistic regression. As a result of constructing a model, 22 variables were selected. To see these specifically by each large area, 6 variables in human resource development(HRD) area, 15 in human resource management(HRM) area, and 1 in the other area were chosen. As a consequence of 10 fold cross validation, misclassification rate and G-mean were 30.81 and 68.27 respectively. Decile having the highest response rate was bigger than the one having the lowest response rate by 6.08 times, and had a tendency to decrease. Therefore, the result of study showed that the proposed model was appropriate to measure enterprise credit score using enterprise human resource variables.

• Journal of Practical Engineering Education
• /
• v.15 no.1
• /
• pp.193-198
• /
• 2023

This paper analyzed the validity of exercise problems for each unit in Python programming education. Practice questions presented for each unit are presented through an online learning system, and each student uploads an answer code and is automatically graded. Data such as students' mid-term exam scores, final exam scores, and practice questions scores for each unit are collected through Python lecture that lasts for one semester. Through the collected data, it is possible to improve the exercise problems for each unit by analyzing the validity of the automatic scoring exercise problems. In this paper, Orange machine learning tool was used to analyze the validity of automatic scoring exercises. The data collected in the Python subject are analyzed and compared comprehensively by total, top, and bottom groups. From the prediction accuracy of the machine learning model that predicts the student's final grade from the Python unit-by-unit practice problem scores, the validity of the automatic scoring exercises for each unit was analyzed.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.8 no.4
• /
• pp.81-90
• /
• 2005

Based on the landslide hazard scoring system of Korea Forest Research Institute, a GIS model for predicting landslide hazards was developed. The risk of landslide hazards was analyzed as the function of 7 environmental site factors for the terrain, vegetation, and geological characteristics of the corresponding forest stand sites. Among the environmental factors, slope distance, relative height and shapes of slopes were interpreted using the forestland slope interpretation module developed by Chung et al. (2002). The program consists of three modules for managing spatial data, analyzing landslide hazard and report-writing, A performance test of the model showed that 72% of the total landslides in Youngin-Ansung landslides area took place in the highly vulnerable zones of grade 1 or 2 of the landslide hazard scoring map.

• Journal of Gastric Cancer
• /
• v.22 no.1
• /
• pp.24-34
• /
• 2022

Purpose: Total gastrectomy (TG) with lymph node (LN) dissection is recommended for early gastric cancer (EGC) but is not indicated for endoscopic resection (ER). We aimed to identify patients who could avoid TG by establishing a scoring system for predicting lymph node metastasis (LNM) in proximal EGCs. Materials and Methods: Between January 2003 and December 2017, a total of 1,025 proximal EGC patients who underwent TG with LN dissection were enrolled. Patients who met the absolute ER criteria based on pathological examination were excluded. The pathological risk factors for LNM were determined using univariate and multivariate logistic regression analyses. A scoring system for predicting LNM was developed and applied to the validation group. Results: Of the 1,025 cases, 100 (9.8%) showed positive LNM. Multivariate analysis confirmed the following independent risk factors for LNM: tumor size >2 cm, submucosal invasion, lymphovascular invasion (LVI), and perineural invasion (PNI). A scoring system was created using the four aforementioned variables, and the areas under the receiver operating characteristic curves in both the training (0.85) and validation (0.84) groups indicated excellent discrimination. The probability of LNM in mucosal cancers without LVI or PNI, regardless of size, was <2.9%. Conclusions: Our scoring system involving four variables can predict the probability of LNM in proximal EGC and might be helpful in determining additional treatment plans after ER, functioning as a good indicator of the adequacy of treatments other than TG in high surgical risk patients.

• Environmental Analysis Health and Toxicology
• /
• v.25 no.1
• /
• pp.41-55
• /
• 2010

The aims of this study were to develop the suitable "system software" in chemical ranking and scoring (CRS) for the food hazardous chemicals associated with environmental emission and to suggest the priority lists of food contamination by environmental-origined pollutants. Study materials were selected with reference to the priority pollutants list for environment and food management from domestic and foreign research and the number of study materials is 103 pollutants (18 heavy metals, 10 PBTs, 10 EDs, and 65 organic compounds). The Food-CRS-Korea system consisted of the environmental fate model via multimedia, transfer environment to food model, and health risk assessment by contaminated food intake. We have established that health risks of excess cancer risks, hazard quotients (HQs) by chronic toxicity and HQs by reproductive toxicity convert to score, respectively. The creditable scoring system was designed to consider uncertainty of quantitative risk assessment based on VOI (Value-Of-Information). The predictability of the Food-CRS-Korea model was evaluated by comparing the presumable values and the measured ones of the environmental media and foodstuffs. The priority lists based on emissions with background-level-correction are 15 pollutants such as arsenic, cadmium, and etc. The priority lists based on environmental monitoring date are 17 pollutants including DEHP, TCDD, and so on. Consequently, we suggested the priority lists of 13 pollutants by considering the several emission and exposure scenarios. According to the Food-CRS-Korea system, arsenics, cadmium, chromes, DEHP, leads, and nickels have high health risk rates and reliable grades.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.6
• /
• pp.1031-1039
• /
• 2010

The decathlon is an athletic event consisting of ten track and field events. Events are held over two consecutive days and the winners are determined by the combined performance in all. Performance is judged in meters, centimeters, minutes, and seconds. However, how to convert results into points is a difficult and controversial issue. We explored the distribution of decathlon results from the 1991 to 2009 using top 200 decathlons in the Olympic games and word championships. The conclusion is that the results from top level decathlon competition are normally distributed, and the current scoring system does not have the property that the performance with same difficulty should get same points. A new model for evaluating the decathlon score has been applied that display uniform characteristics over all events in order to meet the notion of allroundness. The proposed model is uniform over the events and support self-stabilization.

• Tuberculosis and Respiratory Diseases
• /
• v.67 no.5
• /
• pp.436-444
• /
• 2009

Background: Micro computed tomography (CT) is rapidly developing as an imaging tool, especially for mice, which have become the experimental animal of choice for many pulmonary disease studies. We evaluated the usefulness of micro CT for evaluating lung fibrosis in the murine model of bleomycin-induced lung inflammation and fibrosis. Methods: The control mice (n=10) were treated with saline. The murine model of lung fibrosis (n=60) was established by administering bleomycin intra-tracheally. Among the 70 mice, only 20 mice had successful imaging analyses. We analyzed the micro CT and pathological findings and examined the correlation between imaging scoring in micro CT and histological scoring of pulmonary inflammation or fibrosis. Results: The control group showed normal findings on micro CT. The abnormal findings on micro CT performed at 3 weeks after the administration of bleomycin were ground-glass opacity (GGO) and consolidation. At 6 weeks after bleomycin administration, micro CT showed various patterns such as GGO, consolidation, bronchiectasis, small nodules, and reticular opacity. GGO (r=0.84) and consolidation (r=0.69) on micro CT were significantly correlated with histological scoring that reflected pulmonary inflammation (p<0.05). In addition, bronchiectasis (r=0.63) and reticular opacity (r=0.83) on micro CT shown at 6 weeks after bleomycin administration correlated with histological scoring that reflected lung fibrosis (p<0.05). Conclusion: These results suggest that micro CT findings from a murine model of bleomycin-induced lung fibrosis reflect pathologic findings, and micro CT may be useful for predicting bleomycin-induced lung inflammation and fibrosis in mice.