• Journal of Sasang Constitutional Medicine
• /
• v.34 no.3
• /
• pp.31-40
• /
• 2022

Objectives Sasang constitutional medicine is a traditional Korean medicine that classifies humans into four constitutions in consideration of individual differences in physical, psychological, and physiological characteristics. In this paper, we proposed a method to classify Taeeum person (TE) and Non-Taeeum person (NTE), Soeum person (SE) and Non-Soeum person (NSE), and Soyang person (ST) and Non-Soyang person (NSY) using a convolutional neural network with only facial images. Methods Based on the convolutional neural network VGG16 architecture, transfer learning is carried out on the facial images of 3738 subjects to classify TE and NTE, SE and NSE, and SY and NSY. Data augmentation techniques are used to increase classification performance. Results The classification performance of TE and NTE, SE and NSE, and SY and NSY was 77.24%, 85.17%, and 80.18% by F1 score and 80.02%, 85.96%, and 72.76% by Precision-Recall AUC (Area Under the receiver operating characteristic Curve) respectively. Conclusions It was found that Soeum person had the most heterogeneous facial features as it had the best classification performance compared to the rest of the constitution, followed by Taeeum person and Soyang person. The experimental results showed that there is a possibility to classify constitutions only with facial images. The performance is expected to increase with additional data such as BMI or personality questionnaire.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.4
• /
• pp.701-708
• /
• 2024

The advent of transformer architectures in deep learning has been a major breakthrough in natural language processing research. Object name recognition is a branch of natural language processing and is an important research area for tasks such as information retrieval. It is also important in the biomedical field, but the lack of Korean biomedical corpora for training has limited the development of Korean clinical research using AI. In this study, we built a new biomedical corpus for Korean biomedical entity name recognition and selected language models pre-trained on a large Korean corpus for transfer learning. We compared the name recognition performance of the selected language models by F1-score and the recognition rate by tag, and analyzed the errors. In terms of recognition performance, KlueRoBERTa showed relatively good performance. The error analysis of the tagging process shows that the recognition performance of Disease is excellent, but Body and Treatment are relatively low. This is due to over-segmentation and under-segmentation that fails to properly categorize entity names based on context, and it will be necessary to build a more precise morphological analyzer and a rich lexicon to compensate for the incorrect tagging.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.6
• /
• pp.1-7
• /
• 2023

This paper developed a training model to classify normal roads and flooded roads using artificial intelligence technology. We expanded the diversity of learning data using various data augmentation techniques and implemented a model that shows good performance in various environments. Transfer learning was performed using the CNN-based Resnet152v2 model as a pre-learning model. During the model learning process, the performance of the final model was improved through various parameter tuning and optimization processes. Learning was implemented in Python using Google Colab NVIDIA Tesla T4 GPU, and the test results showed that flooding situations were detected with very high accuracy in the test dataset.

• Korean Journal of Remote Sensing
• /
• v.36 no.2_2
• /
• pp.293-307
• /
• 2020

Every year, the floating macroalgae, green and golden tide, are massively detected at the Yellow Sea and East China Sea. After influx of them to the aquaculture facility or beach, it occurs enormous economic losses to remove them. Currently, remote sensing is used effectively to detect the floating macroalgae flowed into the coast. But it has difficulties to detect the floating macroalgae exactly because of the wavelength overlapped with other targets in the ocean. Also, it is difficult to distinguish between green and golden tide because they have similar spectral characteristics. Therefore, we tried to distinguish between green and golden tide applying the Deep learning method to the satellite images. To determine the network, the optimal training conditions were searched to train the AlexNet. Also, Gaofen-1 WFV images were used as a dataset to train and validate the network. Under these conditions, the network was determined after training, and used to confirm the test data. As a result, the accuracy of test data is 88.89%, and it can be possible to distinguish between green and golden tide with precision of 66.67% and 100%, respectively. It is interpreted that the AlexNet can be pick up on the subtle differences between green and golden tide. Through this study, it is expected that the green and golden tide can be effectively classified from various objects in the ocean and distinguished each other.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.4
• /
• pp.203-210
• /
• 2017

In this paper, we propose an effective neural network model for image caption generation and model transfer. This model is a kind of multi-modal recurrent neural network models. It consists of five distinct layers: a convolution neural network layer for extracting visual information from images, an embedding layer for converting each word into a low dimensional feature, a recurrent neural network layer for learning caption sentence structure, and a multi-modal layer for combining visual and language information. In this model, the recurrent neural network layer is constructed by LSTM units, which are well known to be effective for learning and transferring sequence patterns. Moreover, this model has a unique structure in which the output of the convolution neural network layer is linked not only to the input of the initial state of the recurrent neural network layer but also to the input of the multimodal layer, in order to make use of visual information extracted from the image at each recurrent step for generating the corresponding textual caption. Through various comparative experiments using open data sets such as Flickr8k, Flickr30k, and MSCOCO, we demonstrated the proposed multimodal recurrent neural network model has high performance in terms of caption accuracy and model transfer effect.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.4
• /
• pp.365-384
• /
• 2024

The development of scanning technology is accelerating for safer and more efficient automated inspection than human-based inspection. Research on automatically detecting facility damage from images collected using computer vision technology is also increasing. The pixel size, quality, and quantity of an image can affect the performance of deep learning or image processing for automatic damage detection. This study is a basic to acquire high-quality raw image data and camera performance of a mobile tunnel scanning system for automatic detection of damage based on deep learning, and proposes a method to quantitatively evaluate image quality. A test chart was attached to a panel device capable of simulating a moving speed of 40 km/h, and an indoor test was performed using the international standard ISO 12233 method. Existing image quality evaluation methods were applied to evaluate the quality of images obtained in indoor experiments. It was determined that the shutter speed of the camera is closely related to the motion blur that occurs in the image. Modulation transfer function (MTF), one of the image quality evaluation method, can objectively evaluate image quality and was judged to be consistent with visual observation.

• KIPS Transactions on Computer and Communication Systems
• /
• v.13 no.1
• /
• pp.21-30
• /
• 2024

As the self-driving car market continues to grow, the need for charging infrastructure is growing. However, in the case of a wireless charging system, stability issues are being raised because it requires a large amount of power compared with conventional wired charging. SAE J2954 is a standard for building autonomous vehicle wireless charging infrastructure, and the standard defines a communication method between a vehicle and a power transmission system. SAE J2954 recommends using physical media such as Wi-Fi, Bluetooth, and UWB as a wireless charging communication method for autonomous vehicles to enable communication between the vehicle and the charging pad. In particular, UWB is a suitable solution for indoor and outdoor charging environments because it exhibits robust communication capabilities in indoor environments and is not sensitive to interference. In this standard, the process for building a wireless power transmission system is divided into several stages from the start to the completion of charging. In this study, UWB technology is used as a means of fine alignment, a process in the wireless power transmission system. To determine the applicability to an actual autonomous vehicle wireless power transmission system, experiments were conducted based on distance, and the distance information was collected from UWB. To improve the accuracy of the distance data obtained from UWB, we propose a Single Model and Multi Model that apply machine learning and deep learning techniques to the collected data through a three-step preprocessing process.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.37 no.4
• /
• pp.225-232
• /
• 2024

This study focuses on the determination of the fracture mode in composite laminates using deep learning. With the increase in the use of laminated composites in numerous engineering applications, the insurance of their integrity and performance is of paramount importance. However, owing to the complex nature of these materials, the identification of fracture modes is often a tedious and time-consuming task that requires critical domain knowledge. Therefore, to alleviate these issues, this study aims to utilize modern artificial intelligence technology to automate the fractographic analysis of laminated composites. To accomplish this goal, scanning electron microscopy (SEM) images of fractured tensile test specimens are obtained from laminated composites to showcase various fracture modes. These SEM images are then categorized based on numerous fracture modes, including fiber breakage, fiber pull-out, mix-mode fracture, matrix brittle fracture, and matrix ductile fracture. Next, the collective data for all classes are divided into train, test, and validation datasets. Two state-of-the-art, deep learning-based pre-trained models, namely, DenseNet and GoogleNet, are trained to learn the discriminative features for each fracture mode. The DenseNet models shows training and testing accuracies of 94.01% and 75.49%, respectively, whereas those of the GoogleNet model are 84.55% and 54.48%, respectively. The trained deep learning models are then validated on unseen validation datasets. This validation demonstrates that the DenseNet model, owing to its deeper architecture, can extract high-quality features, resulting in 84.44% validation accuracy. This value is 36.84% higher than that of the GoogleNet model. Hence, these results affirm that the DenseNet model is effective in performing fractographic analyses of laminated composites by predicting fracture modes with high precision.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.3
• /
• pp.377-383
• /
• 2021

Recently, in accordance with the 4th industrial revolution, The use of autonomous mobile robots for flexible logistics transfer is increasing in factories, the warehouses and the service areas, etc. In large factories, many manual work is required to use Simultaneous Localization and Mapping(SLAM), so the need for the improved mobile robot autonomous driving is emerging. Accordingly, in this paper, an algorithm for mapless navigation that travels in an optimal path avoiding fixed or moving obstacles is proposed. For mapless navigation, the robot is trained to avoid fixed or moving obstacles through Deep Q Network (DQN) and accuracy 90% and 93% are obtained for two types of obstacle avoidance, respectively. In addition, DQN requires a lot of learning time to meet the required performance before use. To shorten this, the target size change algorithm is proposed and confirmed the reduced learning time and performance of obstacle avoidance through simulation.

• Clinical and Experimental Reproductive Medicine
• /
• v.49 no.4
• /
• pp.225-238
• /
• 2022

The ultimate goal of human assisted reproductive technology is to achieve a healthy pregnancy and birth, ideally from the selection and transfer of a single competent embryo. Recently, techniques for efficiently evaluating the state and quality of preimplantation embryos using time-lapse imaging systems have been applied. Artificial intelligence programs based on deep learning technology and big data analysis of time-lapse monitoring system during in vitro culture of preimplantation embryos have also been rapidly developed. In addition, several molecular markers of the secretome have been successfully analyzed in spent embryo culture media, which could easily be obtained during in vitro embryo culture. It is also possible to analyze small amounts of cell-free nucleic acids, mitochondrial nucleic acids, miRNA, and long non-coding RNA derived from embryos using real-time polymerase chain reaction (PCR) or digital PCR, as well as next-generation sequencing. Various efforts are being made to use non-invasive evaluation of embryo quality (NiEEQ) to select the embryo with the best developmental competence. However, each NiEEQ method has some limitations that should be evaluated case by case. Therefore, an integrated analysis strategy fusing several NiEEQ methods should be urgently developed and confirmed by proper clinical trials.