• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.88-91
• /
• 2022

디지털 휴먼, 민원 상담, ARS 등 칫챗의 활용과 수요가 증가함에 따라 칫챗의 성능 향상을 위한 다양한 연구가 진행되고 있다. 특히, 오토 인코더(Auto-encoder) 기반의 생성 모델(Generative Model)은 높은 성능을 보이며 지속적인 연구가 이루어지고 있으나, 이전 대화들에 대한 충분한 문맥 정보의 반영이 어렵고 문법적으로 부적절한 답변을 생성하는 문제가 있다. 이를 개선하기 위해 검색 기반의 생성 모델과 관련된 연구가 진행되고 있으나, 현재 시점의 문장이 유사해도 이전 문장들에 따라 의도와 답변이 달라지는 멀티턴 대화 특징을 반영하여 대화를 검색하는 연구가 부족하다. 본 논문에서는 이와 같은 멀티턴 대화의 특징이 고려된 검색 방법을 제안하고 검색된 레퍼런스(준정답 문장)를 멀티턴 대화와 함께 생성 모델의 입력으로 활용하여 학습시키는 방안을 제안한다. 제안 방안으로 학습된 발화 생성 모델은 기존 모델과 비교 평가를 수행하며 Rouge-1 스코어에서 13.11점, Rouge-2 스코어에서 10.09점 Rouge-L 스코어에서 13.2점 향상된 성능을 보였고 이를 통해 제안 방안의 우수성을 입증하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.498-500
• /
• 2022

CCTV protects people and assets safely by identifying dangerous situations and responding promptly. However, it is difficult to continuously monitor the increasing number of CCTV images. For this reason, there is a need for a device that continuously monitors CCTV images and notifies when abnormal behavior occurs. Recently, many studies using artificial intelligence models for image data analysis have been conducted. This study simultaneously learns spatial and temporal characteristic information between image data to classify various abnormal behaviors that can be observed in CCTV images. As an artificial intelligence model used for learning, we propose a multi-classification deep learning model that combines an end-to-end 3D convolutional neural network(CNN) and ResNet.

• Journal of Engineering Education Research
• /
• v.26 no.3
• /
• pp.12-19
• /
• 2023

The purpose of this study is to develop the Artificial Intelligence thinking-based education program for improving AI literacy and verify its effectiveness for beginner. This program consists of 17 sessions, was designed according to the "ABCDE" model and is a project-based program. This program was conducted on 51 first-year middle school students and 36 respondents excluding missing values were analyzed in R language. The effect of this program on ethics, understanding, social competency, execution plan, data literacy, and problem solving of AI literacy is statistically significant and has very large practical significance. According to the result of this study, this program provided learners experiencing Artificial Intelligence education for the first time with Artificial Intelligence concepts and principles, collection and analysis of information, and problem-solving processes through application in real life, and served as an opportunity to enhance AI literacy. In addition, education program to enhance AI literacy should be designed based on AI thinking.

• The Journal of Korea Robotics Society
• /
• v.19 no.1
• /
• pp.106-116
• /
• 2024

Ensuring robust 3D object detection is a core challenge for autonomous driving systems operating in urban environments. To tackle this issue, various 3D representation, including point cloud, voxels, and pillars, have been widely adopted, making use of LiDAR, Camera, and Radar sensors. These representations improved 3D object detection performance, but real-world urban scenarios with unexpected situations can still lead to numerous false positives, posing a challenge for robust 3D models. This paper presents a post-processing algorithm that dynamically adjusts object detection thresholds based on the distance from the ego-vehicle. While conventional perception algorithms typically employ a single threshold in post-processing, 3D models perform well in detecting nearby objects but may exhibit suboptimal performance for distant ones. The proposed algorithm tackles this issue by employing adaptive thresholds based on the distance from the ego-vehicle, minimizing false negatives and reducing false positives in the 3D model. The results show performance enhancements in the 3D model across a range of scenarios, encompassing not only typical urban road conditions but also scenarios involving adverse weather conditions.

• Korean Journal of Artificial Intelligence
• /
• v.12 no.2
• /
• pp.1-7
• /
• 2024

In this paper, we compare three models (logistic regression, Random Forest, and XGBoost) for predicting stroke occurrence using data from the Korea National Health and Nutrition Examination Survey (KNHANES). We evaluated these models using various metrics, focusing mainly on recall and F1 score to assess their performance. Initially, the logistic regression model showed a satisfactory recall score among the three models; however, it was excluded from further consideration because it did not meet the F1 score threshold, which was set at a minimum of 0.5. The F1 score is crucial as it considers both precision and recall, providing a balanced measure of a model's accuracy. Among the models that met the criteria, XGBoost showed the highest recall rate and showed excellent performance in stroke prediction. In particular, XGBoost shows strong performance not only in recall, but also in F1 score and AUC, so it should be considered the optimal algorithm for predicting stroke occurrence. This study determines that the performance of XGBoost is optimal in the field of stroke prediction.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.29-36
• /
• 2022

In this paper, we propose an efficient agricultural products price prediction model based on dataset which provided in DACON. This model is XGBoost and CatBoost, and as an algorithm of the Gradient Boosting series, the average accuracy and execution time are superior to the existing Logistic Regression and Random Forest. Based on these advantages, we design a machine learning model that predicts prices 1 week, 2 weeks, and 4 weeks from the previous prices of agricultural products. The XGBoost model can derive the best performance by adjusting hyperparameters using the XGBoost Regressor library, which is a regression model. The implemented model is verified using the API provided by DACON, and performance evaluation is performed for each model. Because XGBoost conducts its own overfitting regulation, it derives excellent performance despite a small dataset, but it was found that the performance was lower than LGBM in terms of temporal performance such as learning time and prediction time.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.119-126
• /
• 2024

In building information model (BIM), it is difficult to train an artificial intelligence (AI) model due to the lack of sufficient data about individual projects in an architecture firm. In this paper, we present a methodology to correctly train an AI neural network model based on a large language model (LLM) to predict the steel structure product weight ratios in BIM. The proposed method, with the aid of the LLM, can overcome the inherent problem of limited data availability in BIM and handle a combination of natural language and numerical data. The experimental results showed that the proposed method demonstrated significantly higher accuracy than methods based on a smaller language model. The potential for effectively applying large language models in BIM is confirmed, leading to expectations of preventing building accidents and efficiently managing construction costs.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.5
• /
• pp.1019-1034
• /
• 2022

Malware attacks become more prevalent in the hyper-connected society of the 4th industrial revolution. To respond to such malware, automation of malware detection using artificial intelligence technology is attracting attention as a new alternative. However, using artificial intelligence without collateral for its reliability poses greater risks and side effects. The EU and the United States are seeking ways to secure the reliability of artificial intelligence, and the government announced a reliable strategy for realizing artificial intelligence in 2021. The government's AI reliability has five attributes: Safety, Explainability, Transparency, Robustness and Fairness. We develop four elements of safety, explainable, transparent, and fairness, excluding robustness in the malware detection model. In particular, we demonstrated stable generalization performance, which is model accuracy, through the verification of external agencies, and developed focusing on explainability including transparency. The artificial intelligence model, of which learning is determined by changing data, requires life cycle management. As a result, demand for the MLops framework is increasing, which integrates data, model development, and service operations. EXE-executable malware and documented malware response services become data collector as well as service operation at the same time, and connect with data pipelines which obtain information for labeling and purification through external APIs. We have facilitated other security service associations or infrastructure scaling using cloud SaaS and standard APIs.

• Journal of The Korean Association of Information Education
• /
• v.25 no.5
• /
• pp.705-712
• /
• 2021

This study aims to develop artificial intelligence education programs that can be easily applied in elementary schools according to the trend of the times called artificial intelligence. The training program designed the purpose and direction based on the analysis results of the needs of 70 elementary school teachers according to the steps of the ADDIE model. According to the survey, elementary school students developed a machine learning education program to set sound data as the theme of the most accessible in their daily lives and to learn the principles of artificial intelligence in solving problems using sound data in real life. These days, when the need for artificial intelligence education emerges, elementary machine learning education programs that solve daily life problems based on sound data developed in this study will lay the foundation for elementary artificial intelligence education.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.174-176
• /
• 2022

In this paper, we present a mobile application for 'personalized customized learning' for children with articulation disorders using an artificial intelligence (AI) algorithm. A dataset (Data Set) to analyze, judge, and predict the learner's articulation situation and degree. In particular, we designed a prototype model by looking at how AI can be improved and advanced compared to existing applications from the UX/UI (GUI) aspect. So far, the focus has been on visual experience, but now it is an important time to process data and provide a UX/UI (GUI) experience to users. The UX/UI (GUI) of the proposed mobile application was to be provided according to the learner's articulation level and situation by using CRNN (Convolution Recurrent Neural Network) of DeepLearning and Auto Encoder GPT-3 (Generative Pretrained Transformer). The use of artificial intelligence algorithms will provide a learning environment with a high degree of perfection to children with articulation disorders, thereby enhancing the learning effect. I hope that you do not have any fear or discomfort in conversation by improving the perfection of articulation with 'personalized and customized learning'.