• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.11
• /
• pp.996-1002
• /
• 2015

In this paper, we present an effective system for the 3D scene labeling of objects from RGB-D videos. Our system uses a Markov Random Field (MRF) over a voxel representation of the 3D scene. In order to estimate the correct label of each voxel, the probabilistic graphical model integrates both scores from sliding window-based object detectors and also from object location prior maps. Both the object detectors and the location prior maps are pre-trained from manually labeled RGB-D images. Additionally, the model integrates the scores from considering the geometric constraints between adjacent voxels in the label estimation. We show excellent experimental results for the RGB-D Scenes Dataset built by the University of Washington, in which each indoor scene contains tabletop objects.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.151-152
• /
• 2019

In this paper, we propose an improved learning method based on a small data set for animal image classification. First, CNN creates a training model for a small data set and uses the data set to expand the data set of the training set Second, a bottleneck of a small data set is extracted using a pre-trained network for a large data set such as VGG16 and stored in two NumPy files as a new training data set and a test data set, finally, learn the fully connected network as a new data set.

• Journal of Information Processing Systems
• /
• v.18 no.3
• /
• pp.344-358
• /
• 2022

Text summarization is the task of producing a shorter version of a long document while accurately preserving the main contents of the original text. Abstractive summarization generates novel words and phrases using a language generation method through text transformation and prior-embedded word information. However, newly coined words or out-of-vocabulary words decrease the performance of automatic summarization because they are not pre-trained in the machine learning process. In this study, we demonstrated an improvement in summarization quality through the contextualized embedding of BERT with out-of-vocabulary masking. In addition, explicitly providing precise pointing and an optional copy instruction along with BERT embedding, we achieved an increased accuracy than the baseline model. The recall-based word-generation metric ROUGE-1 score was 55.11 and the word-order-based ROUGE-L score was 39.65.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2022.04a
• /
• pp.229-230
• /
• 2022

With the development of digital technology, construction companies at home and abroad are in the process of computerizing work and site information for the purpose of improving work efficiency. To this end, various technologies such as BIM, digital twin, and AI-based safety management have been developed, but the accuracy and completeness of the related technologies are insufficient to be applied to the field. In this paper, the learning data that has undergone a pre-processing process optimized for recognition of construction information based on structural members is trained on an existing artificial intelligence model to improve recognition accuracy and evaluate its effectiveness. The artificial intelligence model optimized for the structural member created through this study will be used as a base technology for the technology that needs to confirm the safety of the structure in the future.

• Journal of the Korea Safety Management & Science
• /
• v.7 no.5
• /
• pp.155-174
• /
• 2005

Parametric life-cycle cost(LCC) models have been integrated with traditional design tools, and used in prior work to demonstrate the rapid solution of holistic, analytical tradeoffs between detailed design variations. During early designs stages there may be competing concepts with dramatic differences. Additionally, detailed information is scarce, and decisions must be models. for a diverse range of concepts, and the lack of detailed information make the integration make the integration of traditional LCC models impractical. This paper explores an approximate method for providing preliminary life-cycle cost. Learning algorithms trained using the known characteristics of existing products be approximated quickly during conceptual design without the overhead of defining new models. Artificial neural networks are trained to generalize on product attributes and life cycle cost date from pre-existing LCC studies. The Product attribute data to quickly obtain and LCC for a new and then an application is provided. In additions, the statistical method, called regression analysis, is suggested to predict the LCC. Tests have shown it is possible to predict the life cycle cost, and the comparison results between a learning LCC model and a regression analysis is also shown

• International Journal of Computer Science & Network Security
• /
• v.23 no.5
• /
• pp.73-88
• /
• 2023

Brain tumors can also be an abnormal collection or accumulation of cells in the brain that can be life-threatening due to their ability to invade and metastasize to nearby tissues. Accurate diagnosis is critical to the success of treatment planning, and resonant imaging is the primary diagnostic imaging method used to diagnose brain tumors and their extent. Deep learning methods for computer vision applications have shown significant improvements in recent years, primarily due to the undeniable fact that there is a large amount of data on the market to teach models. Therefore, improvements within the model architecture perform better approximations in the monitored configuration. Tumor classification using these deep learning techniques has made great strides by providing reliable, annotated open data sets. Reduce computational effort and learn specific spatial and temporal relationships. This white paper describes transfer models such as the MobileNet model, VGG19 model, InceptionResNetV2 model, Inception model, and DenseNet201 model. The model uses three different optimizers, Adam, SGD, and RMSprop. Finally, the pre-trained MobileNet with RMSprop optimizer is the best model in this paper, with 0.995 accuracies, 0.99 sensitivity, and 1.00 specificity, while at the same time having the lowest computational cost.

• Journal of the Korean Society of Systems Engineering
• /
• v.16 no.2
• /
• pp.38-46
• /
• 2020

The accurate measurement of critical heat flux (CHF) in flow boiling is important for the safety requirement of the nuclear power plant to prevent sharp degradation of the convective heat transfer between the surface of the fuel rod cladding and the reactor coolant. In this paper, a System Engineering approach is used to develop a model that predicts the CHF using machine learning. The model is built using artificial neural network (ANN). The model is then trained, tested and validated using pre-existing database for different flow conditions. The Talos library is used to tune the model by optimizing the hyper parameters and selecting the best network architecture. Once developed, the ANN model can predict the CHF based solely on a set of input parameters (pressure, mass flux, quality and hydraulic diameter) without resorting to any physics-based model. It is intended to use the developed model to predict the DNBR under a large break loss of coolant accident (LBLOCA) in APR1400. The System Engineering approach proved very helpful in facilitating the planning and management of the current work both efficiently and effectively.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.655-657
• /
• 2021

It is challenging to find breast ultrasound image training dataset to develop an accurate machine learning model due to various regulations, personal information issues, and expensiveness of acquiring the images. However, studies targeting transfer learning for ultrasound breast cancer images classification have not been able to achieve high performance compared to radiologists. Here, we propose an improved transfer learning model for ultrasound breast cancer classification using publicly available dataset. We argue that with a proper combination of ImageNet pre-trained model and optimizer, a better performing model for ultrasound breast cancer image classification can be achieved. The proposed model provided a preliminary test accuracy of 99.5%. With more experiments involving various hyperparameters, the model is expected to achieve higher performance when subjected to new instances.

• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.293-301
• /
• 2023

Unstandardized medical data collection and management are still being conducted manually, and studies are being conducted to classify CT data using deep learning to solve this problem. However, most studies are developing models based only on the axial plane, which is a basic CT slice. Because CT images depict only human structures unlike general images, reconstructing CT scans alone can provide richer physical features. This study seeks to find ways to achieve higher performance through various methods of converting CT scan to 2D as well as axial planes. The training used 1042 CT scans from five body parts and collected 179 test sets and 448 with external datasets for model evaluation. To develop a deep learning model, we used InceptionResNetV2 pre-trained with ImageNet as a backbone and re-trained the entire layer of the model. As a result of the experiment, the reconstruction data model achieved 99.33% in body part classification, 1.12% higher than the axial model, and the axial model was higher only in brain and neck in contrast classification. In conclusion, it was possible to achieve more accurate performance when learning with data that shows better anatomical features than when trained with axial slice alone.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.33 no.6
• /
• pp.367-373
• /
• 2021

In this study, deep learning model was set up to predict the wave heights inside a harbour. Various machine learning techniques were applied to the model in consideration of the transformation characteristics of offshore waves while propagating into the harbour. Pohang New Port was selected for model application, which had a serious problem of unloading due to swell and has lots of available wave data. Wave height, wave period, and wave direction at offshore sites and wave heights inside the harbour were used for the model input and output, respectively, and then the model was trained using deep learning method. By considering the correlation between the time series wave data of offshore and inside the harbour, the data set was separated into prevailing wave directions as a pre-processing method. As a result, It was confirmed that accuracy and stability of the model prediction are considerably increased.