• 한국융합학회논문지
• /
• 제13권3호
• /
• pp.11-22
• /
• 2022

최근 교육 분야에서 다양한 인공지능 기술을 활용한 연구와 개발이 이뤄지고 있다. 인공지능을 활용한 교육 중 특히 대화형 에이전트는 시간과 공간의 제약을 받지 않고 음성인식, 번역과 같은 다양한 인공지능 기술과 결합해 더 효과적인 언어 학습을 가능하게 한다. 본 논문은 상용화된 교육용 플랫폼 중 이용자 수가 많고 영어 학습을 위한 대화형 에이전트가 활용된 플랫폼에 대한 동향 분석을 진행하였다. 동향 분석을 통해 현재 상용화된 교육용 플랫폼의 대화형 에이전트는 여러 한계점과 문제점이 존재했다. 구체적인 문제점과 한계점 분석을 위해 사전 학습된 최신 대용량 대화 모델과 비교 실험을 진행하였고, 실험 방법으로 대화형 에이전트의 대답이 사람과 비슷한지를 평가하는 Sensibleness and Specificity Average (SSA) 휴먼 평가를 진행하였다. 실험 내용을 바탕으로, 효과적인 학습을 위해 개선방안으로 대용량 파라미터로 학습된 대화 모델, 교육 데이터, 정보 검색 기능의 필요성을 제안했다.

• International Journal of Computer Science & Network Security
• /
• 제22권5호
• /
• pp.359-367
• /
• 2022

Arabic skills are the tools by which children are prepared for the educational procedures on which their life depends. Deaf and hard of hearing students (DHH), must be able to grasp the same Arabic terms as hearing students and their different meanings in a context of different sentences less than what they are supposed to be due to their inability. However, problems arise in the same Arabic word and their different meanings in a context for (DHH) students since the way of comprehending such words does not meet the needs and circumstances of (DHH) students. Therefore, researchers introduce web-based method for Arabic words and their meanings in a context prototype that can overcome those problems. Methodology: The study sample consists of 30 (DHH) students at Al Amal City of Palestine, Gaza Region (GR). Those participants that agreed to take part in this study were recruited using a purposeful sampling method. Additionally, to examine the survey information descriptively, the Statistical Packages for social Sciences (SPSS) version 24.0 was used. A sign language teaching movie is utilized in the prototype to standardize the process and verify that Arabic vocabulary and their implications are comprehended. The Evolutionary Process Model of Prototype technique was utilized to create this system. Finding: The findings of this study show that the prototype built is workable and has the ability to help DHHS differentiate between phrases that have the same letters but distinct meanings. The findings of this study are expected to contribute to a better understanding and application of Development of Web-based Arabic Assessments for (DHH) Students in developing countries, which will help to increase the use of Development of Web-based Arabic for (HDD) students in those countries. The empirical models of Web-based Arabic for (DHH) students are established as a proof of concept for the proposed model. The results of this study are predicted to have a significant impact to the information system practitioners and to the body of knowledge.

• 한국산업정보학회논문지
• /
• 제28권4호
• /
• pp.11-19
• /
• 2023

본 논문에서는 사용자의 감정 분석에 따른 향을 추천하는 스마트 미러 시스템을 제안한다. 본 논문은 자연어 처리 중 임베딩 기법(CounterVectorizer와 TF-IDF 기법), 머신러닝 분류 기법 중 최적의 모델(DecisionTree, SVM, RandomForest, SGD Classifier)을 융합하여 시스템을 구축하고 그 결과를 비교한다. 실험 결과, 가장 높은 성능을 보이는 SVM과 워드 임베딩을 파이프라인 기법으로 감정 분류기 모델에 적용한다. 제안된 시스템은 Flask 웹 프레임워크를 이용하여 웹 서비스를 제공하는 개인감정 분석 기반 향 추천 미러를 구현한다. 본 논문은 Google Speech Cloud API를 이용하여 사용자의 음성을 인식하고 STT(Speech To Text)로 음성 변환된 텍스트 데이터를 사용한다. 제안된 시스템은 날씨, 습도, 위치, 명언, 시간, 일정 관리에 대한 정보를 사용자에게 제공한다.

• 한국시뮬레이션학회논문지
• /
• 제19권2호
• /
• pp.157-164
• /
• 2010

우수하고 신뢰성 있는 통신 시스템의 개발을 위해 시스템에 대한 기능 검증과 성능 평가가 모두 필수적인데 반해 이들은 주로 형식 언어 도구를 이용한 기능 모델링과 전문 네트워크 성능 평가 도구에 의한 성능 모델링을 통해 개별적으로 수행되어 왔다. 그러나 한 시스템을 별도로 중복하여 모델링 하는 것은 비용의 증가와 모델 간 불일치를 가져오게 된다. 본 논문은 이 문제를 해결하기 위해 SDL-OPNET 코-시뮬레이션을 통해 SDL로 설계된 통신 프로토콜의 성능을 평가하는 통합 설계 기법을 제안한다. 제안 기법은 Tau의 환경함수와 OPNET의 외부시스템 모듈을 이용하는 코-시뮬레이션 시스템의 설계 방법을 제시한다. InRes 프로토콜이 예로 사용되어 제안 기법의 적용가능성과 효용성을 보여준다.

• 방송공학회논문지
• /
• 제28권3호
• /
• pp.333-336
• /
• 2023

최근 자연어 처리에서 사용되던 트랜스포머 모델이 이미지 초해상화 분야에서도 적용되면서 좋은 성능을 보여주고 있다. 그러나 이러한 트랜스포머 기반 모델들은 복잡하고 많은 학습 파라미터를 가지고 있어 많은 하드웨어 자원을 요구하기 때문에 작은 모바일 기기에서는 사용하기 어렵다는 단점을 가지고 있다. 따라서 본 논문에서는 트랜스포머 기반 초해상화 모델의 크기를 효과적으로 줄일 수 있는 지식 증류 기법을 제안한다. 실험 결과 트랜스포머 블록의 개수를 줄인 학생 모델에서 제안 기법을 적용해 교사 모델과 비슷한 성능을 내거나 더 높일 수 있음을 확인하였다.

• Journal of Periodontal and Implant Science
• /
• 제53권1호
• /
• pp.38-53
• /
• 2023

Purpose: The current Classification of Periodontal and Peri-Implant Diseases and Conditions, published and disseminated in 2018, involves some difficulties and causes diagnostic conflicts due to its criteria, especially for inexperienced clinicians. The aim of this study was to design a decision system based on machine learning algorithms by using clinical measurements and radiographic images in order to determine and facilitate the staging and grading of periodontitis. Methods: In the first part of this study, machine learning models were created using the Python programming language based on clinical data from 144 individuals who presented to the Department of Periodontology, Faculty of Dentistry, Süleyman Demirel University. In the second part, panoramic radiographic images were processed and classification was carried out with deep learning algorithms. Results: Using clinical data, the accuracy of staging with the tree algorithm reached 97.2%, while the random forest and k-nearest neighbor algorithms reached 98.6% accuracy. The best staging accuracy for processing panoramic radiographic images was provided by a hybrid network model algorithm combining the proposed ResNet50 architecture and the support vector machine algorithm. For this, the images were preprocessed, and high success was obtained, with a classification accuracy of 88.2% for staging. However, in general, it was observed that the radiographic images provided a low level of success, in terms of accuracy, for modeling the grading of periodontitis. Conclusions: The machine learning-based decision system presented herein can facilitate periodontal diagnoses despite its current limitations. Further studies are planned to optimize the algorithm and improve the results.

• 디지털산업정보학회논문지
• /
• 제19권2호
• /
• pp.135-145
• /
• 2023

ChatGPT is an artificial intelligence-based conversation agent developed by OpenAI using natural language processing technology. In this study, an empirical study was conducted on incumbent teachers on the intention to use the newly emerged Chat GPT. First, we studied how accuracy, entertainment, system accessibility, perceived usefulness, and perceived ease of use affect ChatGPT's acceptance intention. In addition, we analyzed whether perceived usefulness and perceived ease of use differ in the intention to accept depending on the digital technology of teachers. As a result of the study, the suitability of the structural equation model was generally good. Accuracy and entertainment were found to have a significant effect on perceived usefulness, and system accessibility was found to have a significant effect on perceived ease of use. In the analysis of teachers' digital technology control effects, it was found that perceived usefulness and perceived ease of use had a control effect between acceptance intentions. It was found that the group with high digital skills of teachers was strongly intended to accept the service regardless of perceived usefulness and ease of use. In the group with low digital skills of teachers, it is thought that ChatGPT's service shows the acceptance intention only when the perceived usefulness and ease of use are high. Therefore, in the group with low digital technology, it is necessary to seek teaching activities such as the development of instructional models using ChatGPT.

• 국제학술발표논문집
• /
• The 7th International Conference on Construction Engineering and Project Management Summit Forum on Sustainable Construction and Management
• /
• pp.14-23
• /
• 2017

In high-density high-rise cities such as Hong Kong, buildings account for nearly 90% of energy consumption and 61% of carbon emissions. Therefore, it is important to study the design of buildings, especially high-rise buildings, to achieve lower carbon emissions in the city. The carbon emissions of a building consist of embodied carbon from the production of construction materials and operational carbon from energy consumption during daily operation (e.g., air-conditioning and lighting). An integrated analysis of both types of carbon emissions can strengthen the design of low carbon buildings, but most of the previous studies concentrated mainly on either embodied or operational carbon. Therefore, the primary objective of this study is to develop a holistic methodology framework considering both embodied and operational carbon, in order to enhance the sustainable design of low carbon high-rise buildings. The framework will be based on the building information modeling (BIM) technology because BIM can be integrated with simulation systems and digital models of different disciplines, thereby enabling a holistic design and assessment of low carbon buildings. Structural analysis program is first coupled with BIM to validate the structural performance of a building design. The amounts of construction materials and embodied carbon are then quantified by a BIM-based program using the Dynamo programming interface. Operational carbon is quantified by energy simulation software based on the green building extensible Markup Language (gbXML) file from BIM. Computational fluid dynamics (CFD) will be applied to analyze the ambient wind effect on indoor temperature and operational carbon. The BIM-based framework serves as a decision support tool to compare and explore more environmentally-sustainable design options to help reduce the carbon emissions in buildings.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권2호
• /
• pp.263-283
• /
• 2024

Users' comments after online shopping are critical to product reputation and business improvement. These comments, sometimes known as e-commerce reviews, influence other customers' purchasing decisions. To confront large amounts of e-commerce reviews, automatic analysis based on machine learning and deep learning draws more and more attention. A core task therein is sentiment analysis. However, the e-commerce reviews exhibit the following characteristics: (1) inconsistency between comment content and the star rating; (2) a large number of unlabeled data, i.e., comments without a star rating, and (3) the data imbalance caused by the sparse negative comments. This paper employs Bidirectional Encoder Representation from Transformers (BERT), one of the best natural language processing models, as the base model. According to the above data characteristics, we propose the F_MixBERT framework, to more effectively use inconsistently low-quality and unlabeled data and resolve the problem of data imbalance. In the framework, the proposed MixBERT incorporates the MixMatch approach into BERT's high-dimensional vectors to train the unlabeled and low-quality data with generated pseudo labels. Meanwhile, data imbalance is resolved by Focal loss, which penalizes the contribution of large-scale data and easily-identifiable data to total loss. Comparative experiments demonstrate that the proposed framework outperforms BERT and MixBERT for sentiment analysis of e-commerce comments.

• 경영정보학연구
• /
• 제23권4호
• /
• pp.127-146
• /
• 2021

가짜 뉴스는 정보화 시대라는 현대사회의 특성에 의해 진위 여부의 검증과는 상관없이 빠른 속도로 확대, 재생산되어 퍼진다. 전체 뉴스의 1%를 가짜라고 가정했을 경우 우리사회에 미치는 경제적 비용이 30조 원에 달한다고 하니 가짜 뉴스는 사회적, 경제적으로 매우 중요한 문제라고 할 수 있다. 이에 본 연구는 뉴스의 진위 여부를 신속하고 정확하게 확인하고자 자동화된 가짜 뉴스 탐지 모델을 개발하는데 목적을 두고 있다. 이를 위해 본 연구에서는 크롤링(crawling)을 통해 진위 여부가 밝혀진 뉴스 기사를 수집하였고, 워드 임베딩(Word2Vec, Fasttext)과 딥러닝 기법(LSTM, BiLSTM)을 이용하여 가짜 뉴스 예측 모델을 개발하였다. 실험 결과, Word2Vec과 BiLSTM의 조합이 가장 높은 84%의 정확도를 보였다.