• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.12
• /
• pp.2357-2364
• /
• 2008

In this paper, we consider the problem of exploiting a taxonomy of propositionalized attributes in order to generate compact and robust classifiers. We introduce Propositionalized Attribute Taxonomy guided Naive Bayes Learner (PAT-NBL), an inductive learning algorithm that exploits a taxonomy of propositionalized attributes as prior knowledge to generate compact and accurate classifiers. PAT-NBL uses top-down and bottom-up search to find a locally optimal cut that corresponds to the instance space from propositionalized attribute taxonomy and data. Our experimental results on University of California-Irvine (UCI) repository data set, show that the proposed algorithm can generate a classifier that is sometimes comparably compact and accurate to those produced by standard Naive Bayes learners.

• Journal of the Korea Convergence Society
• /
• v.12 no.10
• /
• pp.203-210
• /
• 2021

This study was conducted to develop a convergence education program using smart farms with both input data(temperature, humidity, etc.) and output data(vegetables, fruits, etc.) that are easily accessible in everyday life so that elementary school students can intuitively and easily understand the principles of artificial intelligence(AI) learning. In order to develop this program, we conducted a prior study analysis of a horticulture, software, robot units in the 2015 Practical Arts curriculum and artificial intelligence education. Based on this, 13 components and 16 achievement criteria were selected, and AI programs of 4 sessions(a total of 8 hours). This program can be used as a reference when developing various teaching materials for artificial intelligence education in the future.

• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.133-144
• /
• 2021

This paper derives the fire risk of buildings in Seoul through the prediction of property damage and the occurrence of fires. This study differs from prior research in that it utilizes variables that include not only a building's characteristics but also its affiliated administrative area as well as the accessibility of nearby fire-fighting facilities. We use Ensemble Voting techniques to merge different machine learning algorithms to predict property damage and fire occurrence, and to extract feature importance to produce fire risk. Fire risk prediction was made on 300 buildings in Seoul utilizing the established model, and it has been derived that with buildings at Level 1 for fire risks, there were a high number of households occupying the building, and the buildings had many factors that could contribute to increasing the size of the fire, including the lack of nearby fire-fighting facilities as well as the far location of the 119 Safety Center. On the other hand, in the case of Level 5 buildings, the number of buildings and businesses is large, but the 119 Safety Center in charge are located closest to the building, which can properly respond to fire.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.12
• /
• pp.323-330
• /
• 2021

In this paper, a study was conducted to understand how students' attitudes and tendencies toward reading affect the newly emerging coding education. Relevant data were collected by dividing it into three areas (reading, coding, and leisure). In the reading area, data on preference books, preferred types of reading and etc were collected. In the coding area, prior learning of coding, main tasks using a computer, time used for learning and etc were collected. In the leisure area, main leisure activities and hours of spent leisure time per one week were collected. Using the collected data, we classified and analyzed the data based on the preferred reading method to identify the problems of non-major students who have difficulties in coding education. In coding education, the excerpts reading student group showed the best achievement (average 60.1), and the extensive reading group showed the lowest achievement (average 48.4). The students who read extensively spent more time in coding study than the group of students who preferred other reading methods, but showed the lowest achievement.

• Journal of Ocean Engineering and Technology
• /
• v.33 no.5
• /
• pp.427-434
• /
• 2019

Artificial intelligence (AI)-aided research currently enjoys active use in a wide array of fields thanks to the rapid development of computing capability and the use of Big Data. Until now, forecasting methods were primarily based on physics models and statistical studies. Today, AI is utilized in disaster prevention forecasts by studying the relationships between physical factors and their characteristics. Current studies also involve combining AI and physics models to supplement the strengths and weaknesses of each aspect. However, prior to these studies, an optimization algorithm for the AI model should be developed and its applicability should be studied. This study aimed to improve the forecast performance by constructing a model for neural network optimization. An artificial neural network (ANN) followed the ever-changing path of a typhoon to produce similar typhoon predictions, while the optimization achieved by the neural network algorithm was examined by evaluating the activation function, hidden layer composition, and dropouts. A learning and test dataset was constructed from the available digital data of one typhoon that affected Korea throughout the record period (1951-2018). As a result of neural network optimization, assessments showed a higher degree of forecast accuracy.

• Journal of Integrative Natural Science
• /
• v.13 no.4
• /
• pp.132-140
• /
• 2020

With the recent introduction of artificial intelligence (AI) technology, the use of data is rapidly increasing, and newly generated data is also rapidly increasing. In order to obtain the results to be analyzed based on these data, the first thing to do is to classify the data well. However, when classifying data, if only one classification technique belonging to the machine learning technique is applied to classify and analyze it, an error of overfitting can be accompanied. In order to reduce or minimize the problems caused by misclassification of the classification system such as overfitting, it is necessary to derive an optimal classification by comparing the results of each classification by applying several classification techniques. If you try to interpret the data with only one classification technique, you will have poor reasoning and poor predictions of results. This study seeks to find a method for optimally classifying data by looking at data from various perspectives and applying various classification techniques such as LDA and QDA, such as linear or nonlinear classification, as a process before data analysis in data analysis. In order to obtain the reliability and sophistication of statistics as a result of big data analysis, it is necessary to analyze the meaning of each variable and the correlation between the variables. If the data is classified differently from the hypothesis test from the beginning, even if the analysis is performed well, unreliable results will be obtained. In other words, prior to big data analysis, it is necessary to ensure that data is well classified to suit the purpose of analysis. This is a process that must be performed before reaching the result by analyzing the data, and it may be a method of optimal data classification.

• Smart Media Journal
• /
• v.11 no.3
• /
• pp.62-73
• /
• 2022

Researches on the prediction of domestic apartment sales price have been continuously conducted, but it is not easy to accurately predict apartment prices because various characteristics are compounded. Prior to predicting apartment sales price, the analysis of major factors, influencing on sale prices, is of paramount importance to improve the accuracy of sales price. Therefore, this study aims to analyze what are the factors that affect the apartment sales price in Gwangju, which is currently showing a steady increase rate. With 6 years of Gwangju apartment transaction price and various social factor data, several maching learning techniques such as multiple regression analysis, random forest, and deep artificial neural network algorithms are applied to identify major factors in each model. The performances of each model are compared with RMSE (Root Mean Squared Error), MAE (Mean Absolute Error) and R² (coefficient of determination). The experiment shows that several factors such as 'contract year', 'applicable area', 'certificate of deposit', 'mortgage rate', 'leading index', 'producer price index', 'coincident composite index' are analyzed as main factors, affecting the sales price.

• 한국정보교육학회:학술대회논문집
• /
• 2021.08a
• /
• pp.419-424
• /
• 2021

The purpose of this study is to understand the educational context including the actual learning process and learner perception using the embodied metaphor in AI education. To this end, a class was designed to utilize the embodied metaphor-based unplugged activity through a qualitative approach. Matrix analysis technique was used to analyze the data collected throughout the course of the class to analyze the experiences and perceptions according to the characteristics of the learner, and the learning context. The results of the study were: First, there was a difference according to the learner's prior experience in the effect on the representative knowledge and the subsequent practice process. Next, the embodied metaphor-based unplugged activity showed soft landing effects on practice and text coding. Finally, the organic integration of unplugged and plugged-in classes helped learners understand the potential of computational thinking.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.43-50
• /
• 2024

This paper evaluates the Korean sentiment analysis performance of large language models like GPT-3.5 and GPT-4 using a zero-shot approach facilitated by the ChatGPT API, comparing them to pre-trained Korean models such as KoBERT. Through experiments utilizing various Korean sentiment analysis datasets in fields like movies, gaming, and shopping, the efficiency of these models is validated. The results reveal that the LMKor-ELECTRA model displayed the highest performance based on F1-score, while GPT-4 particularly achieved high accuracy and F1-scores in movie and shopping datasets. This indicates that large language models can perform effectively in Korean sentiment analysis without prior training on specific datasets, suggesting their potential in zero-shot learning. However, relatively lower performance in some datasets highlights the limitations of the zero-shot based methodology. This study explores the feasibility of using large language models for Korean sentiment analysis, providing significant implications for future research in this area.

• Smart Media Journal
• /
• v.13 no.7
• /
• pp.36-44
• /
• 2024

Identifying plant species and diseases is crucial for maintaining biodiversity and achieving optimal crop yields, making it a topic of significant practical importance. Recent studies have extended plant disease recognition from traditional closed-set scenarios to open-set environments, where the goal is to reject samples that do not belong to known categories. However, in open-world tasks, it is essential not only to define unknown samples as "unknown" but also to classify them further. This task assumes that images and labels of known categories are available and that samples of unknown categories can be accessed. The model classifies unknown samples by learning the prior knowledge of known categories. To the best of our knowledge, there is no existing research on this topic in plant-related recognition tasks. To address this gap, this paper utilizes knowledge distillation to model the category space relationships between known and unknown categories. Specifically, we identify similarities between different species or diseases. By leveraging a fine-tuned model on known categories, we generate pseudo-labels for unknown categories. Additionally, we enhance the baseline method's performance by using a larger pre-trained model, dino-v2. We evaluate the effectiveness of our method on the large plant specimen dataset Herbarium 19 and the disease dataset Plant Village. Notably, our method outperforms the baseline by 1% to 20% in terms of accuracy for novel category classification. We believe this study will contribute to the community.