• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.1
• /
• pp.82.3-82.3
• /
• 2019

In this study, we generate future full disk magnetograms in 12, 24, 36 and 48 hours advance from SDO/HMI images using deep learning. To perform this generation, we apply the convolutional generative adversarial network (cGAN) algorithm to a series of SDO/HMI magnetograms. We use SDO/HMI data from 2011 to 2016 for training four models. The models make AI-generated images for 2017 HMI data and compare them with the actual HMI magnetograms for evaluation. The AI-generated images by each model are very similar to the actual images. The average correlation coefficient between the two images for about 600 data sets are about 0.85 for four models. We are examining hundreds of active regions for more detail comparison. In the future we will use pix2pix HD and video2video translation networks for image prediction.

• Journal of the Korean Society of Industry Convergence
• /
• v.22 no.6
• /
• pp.749-756
• /
• 2019

Big data is structured and unstructured data that is so difficult to collect, store, and so on due to the huge amount of data. Many institutions, including universities, are building student convergence systems to foster talents for data science and AI convergence, but there is an absolute lack of research on what kind of education is needed and what kind of education is required for students. Therefore, in this paper, after conducting the correlation analysis based on the questionnaire on basic surveys and courses to improve the curriculum by grasping the satisfaction and demands of the participants in the "2019 Big Data Youth Talent Training Course" held at K University, Regression analysis was performed. As a result of the study, the higher the satisfaction level, the satisfaction with class or job connection, and the self-development, the more positive the evaluation of program efficiency.

• Geophysics and Geophysical Exploration
• /
• v.26 no.3
• /
• pp.114-125
• /
• 2023

The physics-informed neural network (PINN) has been proposed to overcome the limitations of various numerical methods used to solve partial differential equations (PDEs) and the drawbacks of purely data-driven machine learning. The PINN directly applies PDEs to the construction of the loss function, introducing physical constraints to machine learning training. This technique can also be applied to wave equation modeling. However, to solve the wave equation using the PINN, second-order differentiations with respect to input data must be performed during neural network training, and the resulting wavefields contain complex dynamical phenomena, requiring careful strategies. This tutorial elucidates the fundamental concepts of the PINN and discusses considerations for wave equation modeling using the PINN approach. These considerations include spatial coordinate normalization, the selection of activation functions, and strategies for incorporating physics loss. Our experimental results demonstrated that normalizing the spatial coordinates of the training data leads to a more accurate reflection of initial conditions in neural network training for wave equation modeling. Furthermore, the characteristics of various functions were compared to select an appropriate activation function for wavefield prediction using neural networks. These comparisons focused on their differentiation with respect to input data and their convergence properties. Finally, the results of two scenarios for incorporating physics loss into the loss function during neural network training were compared. Through numerical experiments, a curriculum-based learning strategy, applying physics loss after the initial training steps, was more effective than utilizing physics loss from the early training steps. In addition, the effectiveness of the PINN technique was confirmed by comparing these results with those of training without any use of physics loss.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.3
• /
• pp.1-12
• /
• 2024

In this paper, we fine-tuned KoAlpaca, a large-scale Korean language model, and implemented a blog text generation system utilizing it. Blogs on social media platforms are widely used as a marketing tool for businesses. We constructed training data of positive reviews through emotion analysis and refinement of collected sponsored blog texts and applied QLoRA for the lightweight training of KoAlpaca. QLoRA is a fine-tuning approach that significantly reduces the memory usage required for training, with experiments in an environment with a parameter size of 12.8B showing up to a 58.8% decrease in memory usage compared to LoRA. To evaluate the generative performance of the fine-tuned model, texts generated from 100 inputs not included in the training data produced on average more than twice the number of words compared to the pre-trained model, with texts of positive sentiment also appearing more than twice as often. In a survey conducted for qualitative evaluation of generative performance, responses indicated that the fine-tuned model's generated outputs were more relevant to the given topics on average 77.5% of the time. This demonstrates that the positive review generation language model for sponsored content in this paper can enhance the efficiency of time management for content creation and ensure consistent marketing effects. However, to reduce the generation of content that deviates from the category of positive reviews due to elements of the pre-trained model, we plan to proceed with fine-tuning using the augmentation of training data.

• Korean Medical Education Review
• /
• v.22 no.2
• /
• pp.99-114
• /
• 2020

The rapid development of artificial intelligence (AI), including deep learning, has led to the development of technologies that may assist in the diagnosis and treatment of diseases, prediction of disease risk and prognosis, health index monitoring, drug development, and healthcare management and administration. However, in order for AI technology to improve the quality of medical care, technical problems and the efficacy of algorithms should be evaluated in real clinical environments rather than the environment in which algorithms are developed. Further consideration should be given to whether these models can improve the quality of medical care and clinical outcomes of patients. In addition, the development of regulatory systems to secure the safety of AI medical technology, the ethical and legal issues related to the proliferation of AI technology, and the impacts on the relationship with patients also need to be addressed. Systematic training of healthcare personnel is needed to enable adaption to the rapid changes in the healthcare environment. An overall review and revision of undergraduate medical curriculum is required to enable extraction of significant information from rapidly expanding medical information, data science literacy, empathy/compassion for patients, and communication among various healthcare providers. Specialized postgraduate AI education programs for each medical specialty are needed to develop proper utilization of AI models in clinical practice.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.1
• /
• pp.1-8
• /
• 2021

Detecting Out-of-Distribution (OOD) data is fundamentally required when Deep Neural Network (DNN) is applied to real-world AI such as autonomous driving. However, modern DNNs are quite vulnerable to the over-confidence problem even if the test data are far away from the trained data distribution. To solve the problem, this paper proposes a novel Adversarial-Mixup training method to let the DNN model be more robust by detecting OOD data effectively. Experimental results show that the proposed Adversarial-Mixup method improves the overall performance of OOD detection by 78% comparing with the State-of-the-Art methods. Furthermore, we show that the proposed method can alleviate the over-confidence problem by reducing the confidence score of OOD data than the previous methods, resulting in more reliable and robust DNNs.

• Clinical and Experimental Pediatrics
• /
• v.65 no.5
• /
• pp.239-249
• /
• 2022

Cells survive and proliferate through complex interactions among diverse molecules across multiomics layers. Conventional experimental approaches for identifying these interactions have built a firm foundation for molecular biology, but their scalability is gradually becoming inadequate compared to the rapid accumulation of multiomics data measured by high-throughput technologies. Therefore, the need for data-driven computational modeling of interactions within cells has been highlighted in recent years. The complexity of multiomics interactions is primarily due to their nonlinearity. That is, their accurate modeling requires intricate conditional dependencies, synergies, or antagonisms between considered genes or proteins, which retard experimental validations. Artificial intelligence (AI) technologies, including deep learning models, are optimal choices for handling complex nonlinear relationships between features that are scalable and produce large amounts of data. Thus, they have great potential for modeling multiomics interactions. Although there exist many AI-driven models for computational biology applications, relatively few explicitly incorporate the prior knowledge within model architectures or training procedures. Such guidance of models by domain knowledge will greatly reduce the amount of data needed to train models and constrain their vast expressive powers to focus on the biologically relevant space. Therefore, it can enhance a model's interpretability, reduce spurious interactions, and prove its validity and utility. Thus, to facilitate further development of knowledge-guided AI technologies for the modeling of multiomics interactions, here we review representative bioinformatics applications of deep learning models for multiomics interactions developed to date by categorizing them by guidance mode.

• Electronics and Telecommunications Trends
• /
• v.37 no.4
• /
• pp.36-45
• /
• 2022

As the interest in achieving an intelligent society grows with the fourth industrial revolution's development, information and communications technologies technologies like artificial intelligence (AI), Internet of Things, virtual reality, information security, and blockchain technology are being actively employed in different fields for achieving an intelligent society. With these modifications, the information security paradigm in industrial and public institutions, like personal sensitive data, is quickly changing, and it is exposed to different cyber threats and breaches. Furthermore, as the number of cyber threats and breaches grows, so does the need for rapid detection and response. This demand can be satisfied by establishing cyber training programs and fostering experts that can improve cyber security abilities. In this study, we explored the domestic and international technology trends in cyber security education and training facilities for developing experts in information security. Additionally, the AI technology application in the cyber training ground, which can be established to respond to and deter cyber threats that are becoming more intelligent, was examined.

• Design & Manufacturing
• /
• v.15 no.3
• /
• pp.1-6
• /
• 2021

An artificial neural network model based on a deep learning algorithm is known to be more accurate than humans in image classification, but there is still a limit in the sense that there needs to be a lot of training data that can be called big data. Therefore, various techniques are being studied to build an artificial neural network model with high precision, even with small data. The transfer learning technique is assessed as an excellent alternative. As a result, the purpose of this study is to develop an artificial neural network system that can classify burr images of light guide plate products with 99% accuracy using transfer learning technique. Specifically, for the light guide plate product, 150 images of the normal product and the burr were taken at various angles, heights, positions, etc., respectively. Then, after the preprocessing of images such as thresholding and image augmentation, for a total of 3,300 images were generated. 2,970 images were separated for training, while the remaining 330 images were separated for model accuracy testing. For the transfer learning, a base model was developed using the NASNet-Large model that pre-trained 14 million ImageNet data. According to the final model accuracy test, the 99% accuracy in the image classification for training and test images was confirmed. Consequently, based on the results of this study, it is expected to help develop an integrated AI production management system by training not only the burr but also various defective images.

• Journal of Intelligence and Information Systems
• /
• v.5 no.1
• /
• pp.95-101
• /
• 1999

In this paper, a comparison between different methods to combine predictions from neural networks will be given. These methods are bagging, bumping, and balancing. Those are based on the analysis of the ensemble generalization error into an ambiguity term and a term incorporating generalization performances of individual networks. Neural Networks and AI machine learning models are prone to overfitting. A strategy to prevent a neural network from overfitting, is to stop training in early stage of the learning process. The complete data set is spilt up into a training set and a validation set. Training is stopped when the error on the validation set starts increasing. The stability of the networks is highly dependent on the division in training and validation set, and also on the random initial weights and the chosen minimization procedure. This causes early stopped networks to be rather unstable: a small change in the data or different initial conditions can produce large changes in the prediction. Therefore, it is advisable to apply the same procedure several times starting from different initial weights. This technique is often referred to as training ensembles of neural networks. In this paper, we presented a comparison of three statistical methods to prevent overfitting of neural network.