• Journal of Internet Computing and Services
• /
• v.25 no.4
• /
• pp.7-21
• /
• 2024

There are various machine learning techniques such as Reinforcement Learning, Deep Learning, Neural Network Learning, and so on. In recent, Large Language Models (LLMs) are popularly used for Generative AI based on Reinforcement Learning. It makes decisions with the most optimal rewards through the fine tuning process in a particular situation. Unfortunately, LLMs can not provide any explanation for how they reach the goal because the training is based on learning of black-box AI. Reinforcement Learning as black-box AI is based on graph-evolving structure for deriving enhanced solution through adjustment by human feedback or reinforced data. In this research, for mutually exclusive decision-making, Mutually Exclusive Learning (MEL) is proposed to provide explanations of the chosen goals that are achieved by a decision on both ends with specified conditions. In MEL, decision-making process is based on the tree-based structure that can provide processes of pruning branches that are used as explanations of how to achieve the goals. The goal can be reached by trade-off among mutually exclusive alternatives according to the specific contextual conditions. Therefore, the tree-based structure is adopted to provide feasible solutions with the explanations based on the pruning branches. The sequence of pruning processes can be used to provide the explanations of the inferences and ways to reach the goals, as Explainable AI (XAI). The learning process is based on the pruning branches according to the multi-dimensional contextual conditions. To deep-dive the search, they are composed of time window to determine the temporal perspective, depth of phases for lookahead and decision criteria to prune branches. The goal depends on the policy of the pruning branches, which can be dynamically changed by configured situation with the specific multi-dimensional contextual conditions at a particular moment. The explanation is represented by the chosen episode among the decision alternatives according to configured situations. In this research, MEL adopts the tree-based learning model to provide explanation for the goal derived with specific conditions. Therefore, as an example of mutually exclusive problems, employment process is proposed to demonstrate the decision-making process of how to reach the goal and explanation by the pruning branches. Finally, further study is discussed to verify the effectiveness of MEL with experiments.

• The KIPS Transactions:PartB
• /
• v.11B no.1
• /
• pp.117-124
• /
• 2004

This paper proposes an efficient algorithm of NaiveBayes without loss of its accuracy. The proposed method uses the transposition of category vectors, and minimizes the computation of the probability of NaiveBayes. The proposed method was implemented on the existing framework of the text categorization, so called, AI::Categorizer and it was compared with the conventional NaiveBayes with the well-known data, Router-21578. The comparisons show that the proposed method outperforms NaiveBayes about two times with respect to the executing time.

• Journal of information and communication convergence engineering
• /
• v.18 no.3
• /
• pp.176-182
• /
• 2020

In this paper, we propose a web-based open artificial intelligence (AI) platform which provides high convenience in input data pre-processing, artificial neural network training, and the configuration of subsequent operations according to inference results. The proposed platform has the advantages of the GUI-based environment which can be easily utilized by a user without complex installation. It consists of a web server implemented with the JavaScript Node.js library and a client running the tensorflow.js library. Using the platform, many users can simultaneously create, modify and run their projects to apply AI functionality into various smart services through an open web interface. With our implementation, we show the operability of the proposed platform. By loading a web page from the server, the client can perform GUI-based operations and display the results performed by three modules: the Input Module, the Learning Module and the Output Module. We also implement two application systems using our platform, called smart cashier and smart door, which demonstrate the platform's practicality.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.238-241
• /
• 2019

본 연구에서는 사회인들의 정해진 패턴을 IoT를 기반으로 AI 기술을 활용하여 Deep Learning 기술을 적용하여 행동패턴을 자동으로 시스템에 업로드 한다. 업로드된 데이터는 Deep Learnig 기술을 통해 유의미한 데이터를 추출하고 이를 각종 가전제품에 제공한다. 데이터의 정합도를 높이기 위해서 초기 데이터는 사용자가 입력한 정해진 생활 패턴을 바탕으로 하며 가우시안 분포를 따르는 난수를 생성하여 training data set으로 사용하여 실제 학습에 적용시켰다. 실생활에서 자동으로 데이터를 활용하기 위해서 IoT기기를 연결하여 AI 학습을 진행하였다. 사회인들은 이 시스템을 통해 집에 들어올 때와 집 밖에 외출할 때 댁내에 있는 편리한 서비스를 제공받을 수 있다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.381-382
• /
• 2019

Recently, various search techniques using artificial intelligence techniques have been introduced. It is also possible to use the artificial intelligence to grasp customer propensity. Analyzing the clothes that customers usually wear, it is possible to analyze various colors such as favorite colors, patterns, and fashion styles. In this study, we use artificial intelligence technology to create an application that distinguish between adults and children by combining various factors such as shape, type, color and size of human clothes. Through this, it will be possible to utilize it in a living area where children can be protected in advance by grasping the intrusion of unauthorized adults in the living area where children live mainly. In addition, in the future, we can obtain good results to detect stranger adult person if we apply this experimental result to the detection system using clothing information.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.333-335
• /
• 2023

최근 글을 이해하고 답을 추론하는 연구들이 많이 이루어지고 있으며, 대표적으로 기계 독해 연구가 존재한다. 기계 독해와 관련하여 다양한 데이터셋이 공개되어 있지만, 과거에서부터 현재까지 사람의 영어 능력 평가를 위해 많이 사용되고 있는 토익에 대해서는 공식적으로 공개된 데이터셋도 거의 존재하지 않으며, 이를 위한 연구 또한 활발히 진행되고 있지 않다. 이에 본 연구에서는 현재와 같이 데이터가 부족한 상황에서 기계 독해 모델의 성능을 향상시키기 위한 데이터 증강 기법을 제안하고자 한다. 제안하는 방법은 WordNet을 이용하여 유의어 및 반의어를 기반으로 굉장히 간단하면서도 효율적으로 실제 토익 문제와 유사하게 데이터를 증강하는 것이며, 실험을 통해 해당 방법의 유의미함을 확인하였다. 우리는 본 연구를 통해 토익에 대한 데이터 부족 문제를 해소하고, 사람 수준의 우수한 성능을 얻을 수 있도록 한다.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.737-745
• /
• 2023

This paper discusses a study on developing an artificial intelligence model to detect incidents of fires in distribution switchboard using thermal images. The objective of the research is to preprocess collected thermal images into suitable data for object detection models and design a model capable of determining the occurrence of fires within distribution panels. The study utilizes thermal image data from AI-HUB's industrial complex for training. Two CNN-based deep learning object detection algorithms, namely Faster R-CNN and RetinaNet, are employed to construct models. The paper compares and analyzes these two models, ultimately proposing the optimal model for the task.

• Industry Promotion Research
• /
• v.9 no.1
• /
• pp.223-230
• /
• 2024

This study aims to determine whether coach leadership behavior and group cohesion mediate in the relationship between grit and training satisfaction among Chinese college students. Data were collected through a survey targeting 313 college students purposively sampled at a university in Guangdong, China. The collected data was analyzed using SPSS PC+ Win ver. 25.0 and SPSS PROCESS macro ver. 4.2. The statistical methods applied were frequency analysis, reliability analysis, correlation analysis, and dual mediation effect analysis. The conclusion of the study is as follows. First, grit, coach leadership behavior, group cohesion, and training satisfaction all showed significant positive correlations. Second, the coach's leadership behavior and group cohesion double-mediated in the relationship between grit and training satisfaction. Based on these results, this study proposed a plan to utilize not only grit but also coach leadership behavior and group cohesion to improve college students' training satisfaction.

• The korean journal of orthodontics
• /
• v.51 no.2
• /
• pp.77-85
• /
• 2021

Objective: To evaluate the accuracy of a multi-stage convolutional neural network (CNN) model-based automated identification system for posteroanterior (PA) cephalometric landmarks. Methods: The multi-stage CNN model was implemented with a personal computer. A total of 430 PA-cephalograms synthesized from cone-beam computed tomography scans (CBCT-PA) were selected as samples. Twenty-three landmarks used for Tweemac analysis were manually identified on all CBCT-PA images by a single examiner. Intra-examiner reproducibility was confirmed by repeating the identification on 85 randomly selected images, which were subsequently set as test data, with a two-week interval before training. For initial learning stage of the multi-stage CNN model, the data from 345 of 430 CBCT-PA images were used, after which the multi-stage CNN model was tested with previous 85 images. The first manual identification on these 85 images was set as a truth ground. The mean radial error (MRE) and successful detection rate (SDR) were calculated to evaluate the errors in manual identification and artificial intelligence (AI) prediction. Results: The AI showed an average MRE of 2.23 ± 2.02 mm with an SDR of 60.88% for errors of 2 mm or lower. However, in a comparison of the repetitive task, the AI predicted landmarks at the same position, while the MRE for the repeated manual identification was 1.31 ± 0.94 mm. Conclusions: Automated identification for CBCT-synthesized PA cephalometric landmarks did not sufficiently achieve the clinically favorable error range of less than 2 mm. However, AI landmark identification on PA cephalograms showed better consistency than manual identification.

• Journal of The Korean Institute of Defense Technology
• /
• v.5 no.2
• /
• pp.1-9
• /
• 2023

The purpose of this study is to derive the need to improve the test and evaluation(T&E) performance system of the weapon systems to which advanced science and technology is applied, evaluate priorities, and present development plans. T&E of Al-based weapon systems through a literature research and case analysis on changes in the T&E environment for weapon system, 11 detailed evaluation items were derived from the in terms of the T&E system, structure, and technology. Al-based weapon system test evaluation should be performed in parallel with data-based performance evaluation and actual T&E, and performance measurement using a separate T&E data set is required for AI models performance evaluation. As a result of analyzing the importance of T&E through AHP analysis, the order of T&E system-technology-structure was evaluated, and the priority of detailed evaluation items was evaluated in the order of T&E result judgment-T&E organization and expert training-scientific T&E. For evaluation items with high priority, measures to improve the T&E performance system were presented.