• 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.

• Journal of Korean Society for Quality Management
• /
• v.45 no.4
• /
• pp.677-696
• /
• 2017

Purpose: This study suggests that Six Sigma MBB should be used as a key talent to lead the fourth industrial revolution era by training them with big data processing capability. Methods: Through the analysis between articles on the fourth industrial revolution and Six Sigma related papers, common competencies of data scientists and Six Sigma MBBs were identified and the big data analysis capabilities needed for Six Sigma MBB were derived. Then, training was conducted to improve the big data analysis capabilities so that Six Sigma MBB is able to design algorithms required in the fourth industrial revolution era. Results: Six Sigma MBBs, equipped with the knowledge in field site improvement and basic statistics, were provided with 40 hours of big data analysis training and then were made to design a big data algorithm. Positive results were obtained after applying a AI algorithm which could forecast process defects in a field site. Conclusion: Six Sigma MBB equipped with big data capability will make the best talent for the fourth industrial revolution era. A Six Sigma MBB has an excellent capability for improving field sites. Utilizing the competencies of MBB can be a key to success in the fourth industrial revolution. We hope that the results of this study will be shared with many companies and many more improved case studies will arise in the future as a result of this study.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.19-27
• /
• 2022

In this study, we propose a language and platform to describe and manage the MLOps(Machine Learning Operations) workflow for time series data anomaly detection. Time series data is collected in many fields, such as IoT sensors, system performance indicators, and user access. In addition, it is used in many applications such as system monitoring and anomaly detection. In order to perform prediction and anomaly detection of time series data, the MLOps platform that can quickly and flexibly apply the analyzed model to the production environment is required. Thus, we developed Python-based AI/ML Modeling Language (AMML) to easily configure and execute MLOps workflows. Python is widely used in data analysis. The proposed MLOps platform can extract and preprocess time series data from various data sources (R-DB, NoSql DB, Log File, etc.) using AMML and predict it through a deep learning model. To verify the applicability of AMML, the workflow for generating a transformer oil temperature prediction deep learning model was configured with AMML and it was confirmed that the training was performed normally.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.1
• /
• pp.52.2-52.2
• /
• 2019

Global map of solar surface magnetic field, such as the synoptic map or daily synchronic frame, does not tell us real-time information about the far side of the Sun. A deep-learning technique based on Conditional Generative Adversarial Network (cGAN) is used to generate farside magnetograms from EUVI $304{\AA}$ of STEREO spacecrafts by training SDO spacecraft's data pairs of HMI and AIA $304{\AA}$. Farside(or backside) data of daily synchronic frames are replaced by the Ai-generated magnetograms. The new type of data is used to calculate the Potential Field Source Surface (PFSS) model. We compare the results of the global field with observations as well as those of the conventional method. We will discuss advantage and disadvantage of the new method and future works.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.2
• /
• pp.389-396
• /
• 2024

Generative AI has recently been utilized across all fields, achieving expert-level advancements in deep data analysis. However, identifying regional names in scientific literature remains a challenge due to insufficient training data and limited AI application. This study developed a standardized dataset for effectively classifying regional names using address data from Korean institution-affiliated authors listed in the Web of Science. It tested and evaluated the applicability of machine learning and deep learning models in real-world problems. The BERT model showed superior performance, with a precision of 98.41%, recall of 98.2%, and F1 score of 98.31% for metropolitan areas, and a precision of 91.79%, recall of 88.32%, and F1 score of 89.54% for city classifications. These findings offer a valuable data foundation for future research on regional R&D status, researcher mobility, collaboration status, and so on.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.12
• /
• pp.17-24
• /
• 2019

The biggest problem in the AI field, which has become a hot topic in recent years, is how to deal with the lack of training data. Since manual data construction takes a lot of time and efforts, it is non-trivial for an individual to easily build the necessary data. On the other hand, automatic data construction needs to handle data quality issue. In this paper, we introduce a method to automatically extract the data required to develop Korean speech command recognizer from the web and to automatically select the data that can be used for training data. In particular, we propose a modified ResNet model that shows modest performance for the automatically constructed Korean speech command data. We conducted an experiment to show the applicability of the command set of the health and daily life domain. In a series of experiments using only automatically constructed data, the accuracy of the health domain was 89.5% in ResNet15 and 82% in ResNet8 in the daily lives domain, respectively.