• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.1090-1100
• /
• 2024

While the incorporating ESG indicator is recognized as crucial for sustainability and increased firm value, inconsistent disclosure of ESG data and vague assessment standards have been key challenges. To address these issues, this study proposes an ambiguous text-based automated ESG rating strategy. Earnings Call Transcript data were classified as E, S, or G using the Refinitiv-Sustainable Leadership Monitor's over 450 metrics. The study employed advanced natural language processing techniques such as BERT, RoBERTa, ALBERT, FinBERT, and ELECTRA models to precisely classify ESG documents. In addition, the authors computed the average predicted probabilities for each label, providing a means to identify the relative significance of different ESG factors. The results of experiments demonstrated the capability of the proposed methodology in enhancing ESG assessment criteria established by various rating agencies and highlighted that companies primarily focus on governance factors. In other words, companies were making efforts to strengthen their governance framework. In conclusion, this framework enables sustainable and responsible business by providing insight into the ESG information contained in Earnings Call Transcript data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.9
• /
• pp.2782-2804
• /
• 2024

The integration of artificial intelligence technology with medicine has rapidly evolved, with increasing demands for quality of life. However, falls remain a significant risk leading to severe injuries and fatalities, especially among the elderly. Therefore, the development and application of computer vision-based fall detection technologies have become increasingly important. In this paper, firstly, the keypoint detection algorithm ViTPose++ is used to obtain the coordinates of human body keypoints from the camera images. Human skeletal feature maps are generated from this keypoint coordinate information. Meanwhile, human dense feature maps are produced based on the DensePose algorithm. Then, these two types of feature maps are confused as dual-channel inputs for the model. The convolutional gated recurrent unit is introduced to extract the frame-to-frame relevance in the process of falling. To further integrate features across three dimensions (spatio-temporal-channel), a dual-channel fall detection algorithm based on video streams is proposed by combining the Convolutional Block Attention Module (CBAM) with the ConvGRU. Finally, experiments on the public UR Fall Detection Dataset demonstrate that the improved ConvGRU-CBAM achieves an F1 score of 92.86% and an AUC of 95.34%.

• Korean Journal of Remote Sensing
• /
• v.36 no.1
• /
• pp.41-53
• /
• 2020

The production of near- and off-shore fisheries in South Korea is decreasing due to rapid changes in the fishing environment, particularly including higher sea temperature in recent years. To improve the competitiveness of the fisheries, it is necessary to provide fish catch information that changes spatiotemporally according to the sea state. In this study, artificial intelligence models that predict the CPUE (catch per unit effort) of mackerel, anchovies, and squid (Todarodes pacificus), which are three major fish species in the near- and off-shore areas of South Korea, on a 15-km grid and daily basis were developed. The models were trained and validated using the sea surface temperature, rainfall, relative humidity, pressure,sea surface wind velocity, significant wave height, and salinity as input data, and the fish catch statistics of Suhyup (National Federation of Fisheries Cooperatives) as observed data. The 10-fold blind test results showed that the developed artificial intelligence models exhibited accuracy with a corresponding correlation coefficient of 0.86. It is expected that the fish catch models can be actually operated with high accuracy under various sea conditions if high-quality large-volume data are available.

• Korean Journal of Radiology
• /
• v.25 no.3
• /
• pp.224-242
• /
• 2024

The emergence of Chat Generative Pre-trained Transformer (ChatGPT), a chatbot developed by OpenAI, has garnered interest in the application of generative artificial intelligence (AI) models in the medical field. This review summarizes different generative AI models and their potential applications in the field of medicine and explores the evolving landscape of Generative Adversarial Networks and diffusion models since the introduction of generative AI models. These models have made valuable contributions to the field of radiology. Furthermore, this review also explores the significance of synthetic data in addressing privacy concerns and augmenting data diversity and quality within the medical domain, in addition to emphasizing the role of inversion in the investigation of generative models and outlining an approach to replicate this process. We provide an overview of Large Language Models, such as GPTs and bidirectional encoder representations (BERTs), that focus on prominent representatives and discuss recent initiatives involving language-vision models in radiology, including innovative large language and vision assistant for biomedicine (LLaVa-Med), to illustrate their practical application. This comprehensive review offers insights into the wide-ranging applications of generative AI models in clinical research and emphasizes their transformative potential.

• Korean Journal of Artificial Intelligence
• /
• v.11 no.2
• /
• pp.7-17
• /
• 2023

Artificial Intelligence (AI) technology has already penetrated deeply into our daily lives, and we live with the convenience of it anytime, anywhere, and sometimes even without us noticing it. However, because AI is imitative intelligence based on human Intelligence, it inevitably has both good and evil sides of humans, which is why ethical principles are essential. The starting point of this study is the AI principles for companies or organizations to develop products. Since the late 2010s, studies on ethics and principles of AI have been actively published. This study focused on AI principles declared by global companies currently developing various products through AI technology. So, we surveyed the AI principles of the Global 500 companies by market capitalization at a given specific time and collected the AI principles explicitly declared by 46 of them. AI analysis technology primarily analyzed this text data, especially LDA (Latent Dirichlet Allocation) topic modeling, which belongs to Machine Learning (ML) analysis technology. Then, we conducted a Delphi technique to reach a meaningful consensus by presenting the primary analysis results. We expect to provide meaningful guidelines in AI-related government policy establishment, corporate ethics declarations, and academic research, where debates on AI ethics and principles often occur recently based on the results of our study.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.95-95
• /
• 2023

Common hydrological problems of developing countries include poor data management, insufficient measuring devices and ungauged watersheds, leading to small or unreliable data availability. This has greatly affected the adoption of artificial intelligence techniques for flood risk mitigation and damage control in several developing countries. While climate datasets have recorded resounding applications, but they exhibit more uncertainties than ground-based measurements. To encourage AI adoption in developing countries with small ground-based dataset, we propose data augmentation for regression tasks and compare performance evaluation of different AI models with and without data augmentation. More focus is placed on simple models that offer lesser computational cost and higher accuracy than deeper models that train longer and consume computer resources, which may be insufficient in developing countries. To implement this approach, we modelled and predicted streamflow data of the Asa River Watershed located in Ilorin, Kwara State Nigeria. Results revealed that adequate hyperparameter tuning and proper model selection improve streamflow prediction on small water dataset. This approach can be implemented in data-scarce regions to ensure timely flood intervention and early warning systems are adopted in developing countries.

• Journal of Information Science Theory and Practice
• /
• v.10 no.spc
• /
• pp.12-24
• /
• 2022

This study attempted to investigate changes in collaboration structure for each stage of national Research and Development (R&D) in the artificial intelligence (AI) field through analysis of a co-author network for papers written under national R&D projects. For this, author information was extracted from national R&D outcomes in AI from 2014 to 2019. For such R&D outcomes, NTIS (National Science & Technology Information Service) information from the KISTI (Korea Institute of Science and Technology Information) was utilized. In research collaboration in AI, power function structure, in which research efforts are led by some influential researchers, is found. In other words, less than 30 percent is linked to the largest cluster, and a segmented network pattern in which small groups are primarily developed is observed. This means a large research group with high connectivity and a small group are connected with each other, and a sporadic link is found. However, the largest cluster grew larger and denser over time, which means that as research became more intensified, new researchers joined a mainstream network, expanding a scope of collaboration. Such research intensification has expanded the scale of a collaborative researcher group and increased the number of large studies. Instead of maintaining conventional collaborative relationships, in addition, the number of new researchers has risen, forming new relationships over time.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.368-376
• /
• 2021

Artificial intelligence clouds help to efficiently develop the autonomous things integrating artificial intelligence technologies and control technologies by sharing the learned models and providing the execution environments. The existing autonomous things development technologies only take into account for the accuracy of artificial intelligence models at the cost of the increment of the complexity of the models including the raise up of the number of the hidden layers and the kernels, and they consequently require a large amount of computation. Since resource-constrained computing environments, could not provide sufficient computing resources for the complex models, they make the autonomous things violate time criticality. In this paper, we propose a digital twin software development framework that selects artificial intelligence models optimized for the computing environments. The proposed framework uses a load estimation DNN model to select the optimal model for the specific computing environments by predicting the load of the artificial intelligence models with digital twin data so that the proposed framework develops the control software. The proposed load estimation DNN model shows up to 20% of error rate compared to the formula-based load estimation scheme by means of the representative CNN models based experiments.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06c
• /
• pp.516-520
• /
• 2010

컴퓨터와 인간과의 상호작용에서 다양한 형태의 인터페이스에 대한 요구가 날로 커지고 있다. 그 가운데 실생활에서도 사물을 지칭하거나 의사소통의 수단으로 사용되는 손과 관련한 인터페이스에 대한 연구가 주목 받고 있다. 기존의 대부분의 연구들은 손을 입력 받으면 영상을 기반으로 손의 중심점을 찾아 그것의 위치를 인식하였는데 이는 물체에 의해 손이 가려진 것과 같이 잘못된 영상을 입력 받았을 때 원하는 결과를 얻지 못하는 상황을 야기할 수 있다. 본 논문은 이러한 점을 보완하기 위하여 손의 중심점을 찾을 때 방해 받는 물체에 덜 민감하게 반응하도록 칼만 필터를 적용하여 문제점을 개선할 수 있도록 하였다. 또한 결과의 정확도를 높일 수 있도록 손가락 끝점을 추출하여 칼만 필터의 매개변수에 반영시켜주었다. 그 결과 예기치 못한 상황이 발생했을 때에도 이것에 덜 민감하게 반응하면서 손의 위치를 비교적 정확하게 측정할 수 있었으며 시스템의 과정이 간단하여 실시간으로 응용하기에 적합한 것을 알 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.761-764
• /
• 2020

본 논문에서는 라이프로그 데이터를 기반으로 한 행동인식 결과로부터 일상생활의 활동유형을 분석하는 기술에 대해 제안한다. 실제 일상생활 중에 수집한 가속도 센서 데이터만을 이용하여 분석한 행동인식 결과를 정적-동적 행동으로 분류된 특징 벡터로 나타내었고, 이를 클러스터링하여 6개의 대표 활동유형으로 분류하였다. 50명의 사용자 데이터를 분석하여 정적-동적 활동의 비율에 따른 활동유형을 분류함으로써 실제 라이프로그 데이터로부터 일상생활 활동유형을 확인하였다.