• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.173-178
• /
• 2022

Recently, various computing technologies such as artificial intelligence, big data, and IoT are developing. In particular, artificial intelligence-based deepfake technology is being used in various fields such as the content and medical industry. Deepfake technology is a combination of deep learning and fake, and is a technology that synthesizes a person's face or body through deep learning, which is a core technology of AI, to imitate accents and voices. This paper uses deepfake technology to study the creation of virtual characters through the synthesis of animation models and real person photos. Through this, it is possible to minimize various cost losses occurring in the animation production process and support writers' work. In addition, as deepfake open source spreads on the Internet, many problems emerge, and crimes that abuse deepfake technology are prevalent. Through this study, we propose a new perspective on this technology by applying the deepfake technology to children's material rather than adult material.

• Journal of information and communication convergence engineering
• /
• v.21 no.3
• /
• pp.208-215
• /
• 2023

Deep learning techniques provide powerful solutions to several pattern-recognition problems, including Raman spectral classification. However, these networks require large amounts of labeled data to perform well. Labeled data, which are typically obtained in a laboratory, can potentially be alleviated by data augmentation. This study investigated various data augmentation techniques and applied multiple deep learning methods to Raman spectral classification. Raman spectra yield fingerprint-like information about chemical compositions, but are prone to noise when the particles of the material are small. Five augmentation models were investigated to build robust deep learning classifiers: weighted sums of spectral signals, imitated chemical backgrounds, extended multiplicative signal augmentation, and generated Gaussian and Poisson-distributed noise. We compared the performance of nine state-of-the-art convolutional neural networks with all the augmentation techniques. The LeNet5 models with background noise augmentation yielded the highest accuracy when tested on real-world Raman spectral classification at 88.33% accuracy. A class activation map of the model was generated to provide a qualitative observation of the results.

• Journal of information and communication convergence engineering
• /
• v.21 no.4
• /
• pp.346-350
• /
• 2023

Trajectory prediction is an essential element for driving autonomous vehicles, and various trajectory prediction models have emerged with the development of deep learning technology. Convolutional neural network (CNN) is the most commonly used neural network architecture for extracting the features of visual images, and the latest models exhibit high performances. This study was conducted to identify an efficient CNN backbone model among the components of deep learning models for trajectory prediction. We changed the existing CNN backbone network of multiple-trajectory prediction models used as feature extractors to various state-of-the-art CNN models. The experiment was conducted using nuScenes, which is a dataset used for the development of autonomous vehicles. The results of each model were compared using frequently used evaluation metrics for trajectory prediction. Analyzing the impact of the backbone can improve the performance of the trajectory prediction task. Investigating the influence of the backbone on multiple deep learning models can be a future challenge.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.173-173
• /
• 2023

The Mekong River Basin (MRB) is a crucial watershed in Asia, impacting over 60 million people across six developing nations. Accurate satellite-based precipitation products (SPPs) are essential for effective hydrological and watershed management in this region. However, the performance of SPPs has been varied and limited. The APHRODITE product, a unique gauge-based dataset for MRB, is widely used but is only available until 2015. In this study, we present a novel framework for correcting SPPs in the MRB by employing a deep learning approach that combines convolutional neural networks and encoder-decoder architecture to address pixel-by-pixel bias and enhance accuracy. The DLF was applied to four widely used SPPs (TRMM, CMORPH, CHIRPS, and PERSIANN-CDR) in MRB. For the original SPPs, the TRMM product outperformed the other SPPs. Results revealed that the DLF effectively bridged the spatial-temporal gap between the SPPs and the gauge-based dataset (APHRODITE). Among the four corrected products, ADJ-TRMM demonstrated the best performance, followed by ADJ-CDR, ADJ-CHIRPS, and ADJ-CMORPH. The DLF offered a robust and adaptable solution for bias correction in the MRB and beyond, capable of detecting intricate patterns and learning from data to make appropriate adjustments. With the discontinuation of the APHRODITE product, DLF represents a promising solution for generating a more current and reliable dataset for MRB research. This research showcased the potential of deep learning-based methods for improving the accuracy of SPPs, particularly in regions like the MRB, where gauge-based datasets are limited or discontinued.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.2
• /
• pp.459-463
• /
• 2024

Frequent closures among self-employed individuals lead to national economic losses. Given the high closure rates in the restaurant industry, predicting changes in this sector is crucial for business survival. While research on factors affecting restaurant industry survival is active, studies predicting commercial district changes are lacking. Thus, this study focuses on forecasting such alterations, designing a deep learning model for Seoul's administrative district commercial district changes. It collects 2023 and 2022 second-quarter variables related to these changes, converting yearly fluctuations into percentages for augmentation. The proposed deep learning model aims to predict commercial district changes. Future policies, considering this study, could support restaurant industry growth and economic development.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.301-307
• /
• 2023

Deep learning requires building a deep neural network, collecting a large amount of training data, and then training the built neural network for a long time. If training does not proceed properly or overfitting occurs, training will fail. When using deep learning tools that have been developed so far, it takes a lot of time to collect training data and learn. However, due to the rapid advent of the mobile environment and the increase in sensor data, the demand for real-time deep learning technology that can dramatically reduce the time required for neural network learning is rapidly increasing. In this study, a real-time deep learning system was implemented using an Arduino system equipped with a fine dust sensor. In the implemented system, fine dust data is measured every 30 seconds, and when up to 120 are accumulated, learning is performed using the previously accumulated data and the newly accumulated data as a dataset. The neural network for learning was composed of one input layer, one hidden layer, and one output. To evaluate the performance of the implemented system, learning time and root mean square error (RMSE) were measured. As a result of the experiment, the average learning error was 0.04053796, and the average learning time of one epoch was about 3,447 seconds.

• Journal of Convergence for Information Technology
• /
• v.12 no.1
• /
• pp.39-44
• /
• 2022

The purpose of this study is to extract the type, location, and absolute size of an object in an image using a deep learning algorithm, predict the relative distance between objects, and use this to detect contact between objects. To analyze the size ratio of objects, YOLO, a CNN-based object detection algorithm, is used. Through the YOLO algorithm, the absolute size and position of an object are extracted in the form of coordinates. The extraction result extracts the ratio between the size in the image and the actual size from the standard object-size list having the same object name and size stored in advance, and predicts the relative distance between the camera and the object in the image. Based on the predicted value, it detects whether the objects are in contact.

• Investigative Magnetic Resonance Imaging
• /
• v.25 no.3
• /
• pp.156-163
• /
• 2021

Recently, neuromelanin and nigrosome imaging techniques have been developed to evaluate the substantia nigra in Parkinson's disease. Previous studies have shown potential benefits of quantitative analysis of neuromelanin and nigrosome images in the substantia nigra, although visual assessments have been performed to evaluate structures in most studies. In this study, we investigate the potential of using deep learning based automatic region segmentation techniques for quantitative analysis of the substantia nigra. The deep convolutional neural network was trained to automatically segment substantia nigra regions on 3D nigrosome and neuromelanin sensitive MR images obtained from 30 subjects. With a 5-fold cross-validation, the mean calculated dice similarity coefficient between manual and deep learning was 0.70 ± 0.11. Although calculated dice similarity coefficients were relatively low due to empirically drawn margins, selected slices were overlapped for more than two slices of all subjects. Our results demonstrate that deep convolutional neural network-based method could provide reliable localization of substantia nigra regions on neuromelanin and nigrosome sensitive MR images.

• Journal of Korea Multimedia Society
• /
• v.23 no.1
• /
• pp.50-57
• /
• 2020

The work that detection and elimination to disease and pest have important in agricultural field because it is directly related to the production of the crops, early detection and treatment of the disease insects. Image classification technology based on traditional computer vision have not been applied in part such as disease and pest because that is falling a accuracy to extraction and classification of feature. In this paper, we proposed model that determine to disease and pest of shiitake based on deep-CNN which have high image recognition performance than exist study. For performance evaluation, we compare evaluation with Alexnet to a proposed deep learning evaluation model. We were compared a proposed model with test data and extend test data. The result, we were confirmed that the proposed model had high performance than Alexnet which approximately 48% and 72% such as test data, approximately 62% and 81% such as extend test data.

• Journal of the Korean Society of Industry Convergence
• /
• v.26 no.4_2
• /
• pp.657-668
• /
• 2023

It's important to note that air compressors in the industrial sector are major energy consumers, accounting for a significant portion of total energy costs in manufacturing plants, ranging from 12% to 40%. To address this issue, researchers have compared forecasting models that can predict the power consumption of air compressors. The forecasting models were designed to incorporate variables such as flow rate, pressure, temperature, humidity, and dew point, utilizing statistical methods, machine learning, and deep learning techniques. The model performance was compared using measures such as RMSE, MAE and SMAPE. Out of the 21 models tested, the Elastic Net, a statistical method, proved to be the most effective in power comsumption forecasting.