• Journal of The Korean Association For Science Education
• /
• v.41 no.3
• /
• pp.203-220
• /
• 2021

We explored the performance improvement method of automated scoring for scientific argumentation. We analyzed the pattern of argumentation using automated scoring models. For this purpose, we assessed the level of argumentation for student's scientific discourses in classrooms. The dataset consists of four units of argumentation features and argumentation levels for episodes. We utilized argumentation clusters and n-gram to enhance automated scoring accuracy. We used the three supervised learning algorithms resulting in 33 automatic scoring models. As a result of automated scoring, we got a good scoring accuracy of 77.59% on average and up to 85.37%. In this process, we found that argumentation cluster patterns could enhance automated scoring performance accuracy. Then, we analyzed argumentation patterns using the model of decision tree and random forest. Our results were consistent with the previous research in which justification in coordination with claim and evidence determines scientific argumentation quality. Our research method suggests a novel approach for analyzing the quality of scientific argumentation in classrooms.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.05
• /
• pp.395-397
• /
• 1997

We have applied the neural network method for the neural networkmethod for the automatic scoring of the sleep stage. 17 features are extracted from the recorded EEG, EOG and EMG signals. These features are inputed to tile multilayer perceptron model. Neural network was trained with error-back propagation method. Results are compared with manual scoring of the experts, and show the possibility of application of automatic method in sleep stage scoring.

• International Journal of Quality Innovation
• /
• v.5 no.2
• /
• pp.1-16
• /
• 2004

Credit scoring is widely used to make credit decisions, to reduce the cost of credit analysis and enable faster decisions. However, traditional credit scoring models do not account for the influence of noises. This study proposes a robust credit scoring system based on Mahalanobis-Taguchi System (MTS). The MTS, primary proposed by Taguchi, is a diagnostic and forecasting method using multivariate data. The proposed approach's effectiveness is demonstrated by using real case data from a large Taiwanese bank. The results reveal that the robust credit scoring system can be successfully implemented using MTS technique.

• Asian Journal of Innovation and Policy
• /
• v.6 no.2
• /
• pp.206-224
• /
• 2017

This article proposes a logic model for assessing the performance of the outcome of public research as a technology valuation method. It consists of two parts and eight steps. The first part is a scoring system and the second part is a validation process of the performance index derived from scoring by valuation method. The scoring in the first part generally requires a focus group method to find out the value drivers and make an evaluation table. The reason why we call it the technology valuation method is that the first part is derived from the simple evaluation of technology value using checklists for value drive. The second part is the regular technology valuation process. The model is designed for the measurement of unquantifiable outcome. Is knowledge or scientific outcome comparable to the measured outcome? If possible, how big is the unquantifiable outcome? This model is based on financial valuation techniques with clear or acceptable market data. Therefore, it cannot work solely for unquantifiable outcomes without comparable measurable outcomes, unlike economic valuation.

• Journal of Educational Research in Mathematics
• /
• v.8 no.1
• /
• pp.217-235
• /
• 1998

The purpose of this study is to define the altenative assessment and to suggest the method of scoring system. Alternative assessment includes any type of assessment in which student create reponses to a question rather than choosing a responses form given list( as for multiple choice, true/false, or matching). Alternative assessment can includes short answer questions, essay, performances, oral presentation, demonstrations, exhibitions, portfolios, and etc. To evaluate the each type of assessment, we can apply the method of holistic scoring and analytic scoring system. Also we have to concern the type of scoring mechanism directly relate to what we want to assess, our purpose for assessment fitting into the educational enterprise. Before applying the alternative assessment in our classroom, we need to step back and reconsider all our design features and teachers' responsibility.

• Speech Sciences
• /
• v.11 no.2
• /
• pp.217-226
• /
• 2004

An automatic pronunciation correction system provides users with correction guidelines for each pronunciation error. For this purpose, we develop a speech recognition system which automatically classifies pronunciation errors when Koreans speak a foreign language. In this paper, we propose a machine scoring method for automatic assessment of pronunciation quality by the speech recognizer. Scores obtained from an expert human listener are used as the reference to evaluate the different machine scores and to provide targets when training some of algorithms. We use a log-likelihood score and a normalized log-likelihood score as machine scoring methods. Experimental results show that the normalized log-likelihood score had higher correlation with human scores than that obtained using the log-likelihood score.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.25 no.4
• /
• pp.504-510
• /
• 2019

Practical test items were analyzed to extend the existing scoring method for boat operator licenses to an electronic scoring method. We have attempted to digitize the method within the current practical test system scope and have developed an electronic scoring system using LiDAR sensors and WAVE communication. The results of the study are as follows; the first, the scoring data entered into the LiDAR and examiner score device on the boat were transferred from an integrated processing unit to a land control center through WAVE communication. The system was constructed and verified to store and manage examinee data. Second, when testing the meandering task, accurate distance measurement was achieved by using LiDAR instead of visually observing the stick (3 m), and an accurate distance was displayed through the examiner score device quickly. Finally, we confirmed that it is possible to smoothly transmit and process the WAVE communication used to transfer the score data acquired from the boat to the monitoring center at a high speed without loss.

• Knowledge Management Research
• /
• v.6 no.2
• /
• pp.105-118
• /
• 2005

The future will see all industries become technology-driven in the competitive global market place. Firms with deep technological roots and innovation strategies have some advantages. Business valuation of technology is critical to the future of firm's business. In this situation widely used scoring valuation is not enough to evaluate relative business competitiveness associated with technology and to assign its relative ranking category. Therefore, a more useful and comprehensive new valuation approach, which is called business composite index, is needed to complement and to enhance the existing scoring valuation approach. In this research, statistical factor analysis is applied to determine the common factors and to estimate associated weights. And business composite index, which is a kind of weighted scoring method, is derived based on the results of factor analysis. This research shows that business composite index is considered very useful to measure the business relative strength of individual technology and also to assign its relative ranking category instead of absolute ranking based on scoring valuation approach.

• The Mathematical Education
• /
• v.63 no.2
• /
• pp.165-186
• /
• 2024

Despite the growing attention on artificial intelligence-based automated scoring technology as a support method for the introduction of descriptive items in school environments and large-scale assessments, there is a noticeable lack of foundational research in mathematics compared to other subjects. This study developed an automated scoring model for two descriptive items in first-year middle school mathematics using the Random Forest algorithm, evaluated its performance, and explored ways to enhance this performance. The accuracy of the final models for the two items was found to be between 0.95 to 1.00 and 0.73 to 0.89, respectively, which is relatively high compared to automated scoring models in other subjects. We discovered that the strategic selection of the number of evaluation categories, taking into account the amount of data, is crucial for the effective development and performance of automated scoring models. Additionally, text preprocessing by mathematics education experts proved effective in improving both the performance and interpretability of the automated scoring model. Selecting a vectorization method that matches the characteristics of the items and data was identified as one way to enhance model performance. Furthermore, we confirmed that oversampling is a useful method to supplement performance in situations where practical limitations hinder balanced data collection. To enhance educational utility, further research is needed on how to utilize feature importance derived from the Random Forest-based automated scoring model to generate useful information for teaching and learning, such as feedback. This study is significant as foundational research in the field of mathematics descriptive automatic scoring, and there is a need for various subsequent studies through close collaboration between AI experts and math education experts.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.4
• /
• pp.673-689
• /
• 2022

We propose an APT attack scoring method as a part of the process for detecting and responding to APT attacks. First, unlike previous work that considered inconsistent and subjective factors determined by cyber security experts in the process of scoring cyber attacks, we identify quantifiable factors from components of MITRE ATT&CK^Ⓡ techniques and propose a method of quantifying each identified factor. Then, we propose a method of calculating the score of the unit attack technique from the quantified factors, and the score of the entire APT attack composed of one or more multiple attack techniques. We present the possibility of quantification to determine the threat level and urgency of cyber attacks by applying the proposed scoring method to the APT attack reports, which contains the hundreds of APT attack cases occurred worldwide. Using our work, it will be possible to determine whether actual cyber attacks have occurred in the process of detecting APT attacks, and respond to more urgent and important cyber attacks by estimating the priority of APT attacks.