• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.10
• /
• pp.2232-2240
• /
• 2015

Recently in the field of Big Data, there is a trend of collecting and reprocessing the existing data such as products having high interest of customers and past purchase details to be utilized for the analysis of transaction propensity of users(product recommendations, sales forecasts, etc). Studies related to the propensity of previous users has limitations on its range of subjects and investigation timing and difficult to make predictions on detailed products with lack of real-time thus there exists difficult disadvantages of introducing appropriate and quick sales strategy against the trend. This paper utilizes the machine learning algorithm application to analyze the transaction propensity of users. As a result of applying the machine learning algorithm, it has demonstrated that various indicators which can be deduced by detailed product were able to be extracted.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.6
• /
• pp.635-644
• /
• 2020

Object recognition, detection and instance segmentation based on DL (Deep Learning) have being used in various practices, and mainly optical images are used as training data for DL models. The major objective of this paper is object segmentation and building detection by utilizing multimodal datasets as well as optical images for training Detectron2 model that is one of the improved R-CNN (Region-based Convolutional Neural Network). For the implementation, infrared aerial images, LiDAR data, and edges from the images, and Haralick features, that are representing statistical texture information, from LiDAR (Light Detection And Ranging) data were generated. The performance of the DL models depends on not only on the amount and characteristics of the training data, but also on the fusion method especially for the multimodal data. The results of segmenting objects and detecting buildings by applying hybrid fusion - which is a mixed method of early fusion and late fusion - results in a 32.65% improvement in building detection rate compared to training by optical image only. The experiments demonstrated complementary effect of the training multimodal data having unique characteristics and fusion strategy.

• Journal of Broadcast Engineering
• /
• v.25 no.6
• /
• pp.898-910
• /
• 2020

Single image-based super-resolution has been studied for a long time in computer vision because of various applications. Various deep learning-based super-resolution algorithms are introduced recently to improve the performance by reducing side effects like blurring and staircase effects. Most deep learning-based approaches have focused on how to implement the network architecture, loss function, and training strategy to improve performance. Meanwhile, Several approaches using Attention Module, which emphasizes the extracted features, are introduced to enhance the performance of the network without any additional layer. Attention module emphasizes or scales the feature map for the purpose of the network from various perspectives. In this paper, we propose the various channel attention and spatial attention in single image-based super-resolution and analyze the results and performance according to the architecture of the attention module. Also, we explore that designing multi-attention module to emphasize features efficiently from various perspectives.

• Journal of Information Technology Applications and Management
• /
• v.27 no.6
• /
• pp.171-180
• /
• 2020

With the recent increase in asthma, asthma has become recognized as one of the diseases. The perception that bronchial asthma is a chronic disease and requires treatment has been strengthened. In addition, asthma is recognized as a dangerous disease due to environmental changes and efforts are made to minimize these risks. However, the environmental impact on asthma is hardly a factor that individuals in asthmatic patients can cope with. Therefore, this study was conducted to see if the asthma disease could be replaced by the individual efforts of asthma patients. In particular, since the management of asthma is important during adolescence, we conducted research on asthma in teenagers. Utilizing support vector machines, artificial neural networks and deep learning techniques that have recently drawn attention, we propose models to predict the asthma of teenagers. The study also provides guidelines to avoid factors that can cause asthma in teenagers.

• Journal of Information Technology Applications and Management
• /
• v.29 no.5
• /
• pp.27-37
• /
• 2022

This study intends to link agricultural machine history data with related organizations or collect them through IoT sensors, receive input from agricultural machine users and managers, and analyze them through AI algorithms. Through this, the goal is to track and manage the history data throughout all stages of production, purchase, operation, and disposal of agricultural machinery. First, LSTM (Long Short-Term Memory) is used to estimate oil consumption and recommend maintenance from historical data of agricultural machines such as tractors and combines, and C-LSTM (Convolution Long Short-Term Memory) is used to diagnose and determine failures. Memory) to build a deep learning algorithm. Second, in order to collect historical data of agricultural machinery, IoT sensors including GPS module, gyro sensor, acceleration sensor, and temperature and humidity sensor are attached to agricultural machinery to automatically collect data. Third, event-type data such as agricultural machine production, purchase, and disposal are automatically collected from related organizations to design an interface that can integrate the entire life cycle history data and collect data through this.

• Journal of Convergence for Information Technology
• /
• v.11 no.5
• /
• pp.94-103
• /
• 2021

This study aims to propose technical trading rules for Bitcoin futures and empirically analyze investment performance. Investment strategies include standard trading rules such as VMA, TRB, FR, MACD, RSI, BB, using Bitcoin futures daily data from December 18, 2017 to March 31, 2021. The trend-following rules showed higher investment performance than the comparative strategy B&H. Compared to KOSPI200 index futures, Bitcoin futures investment performance was higher. In particular, the investment performance has increased significantly in Sortino Ratio, which reflects downside risk. This study can find academic significance in that it is the first attempt to systematically analyze the investment performance of standard technical trading rules of Bitcoin futures. In future research, it is necessary to improve investment performance through the use of deep learning models or machine learning models to predict the price of Bitcoin futures.

• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.1
• /
• pp.17-28
• /
• 2019

In the financial investment management strategy, the distributed investment selecting and combining various financial assets is called portfolio management theory. In recent years, the blockchain based financial assets, such as cryptocurrencies, have been traded on several well-known exchanges, and an efficient portfolio management approach is required in order for investors to steadily raise their return on investment in cryptocurrencies. On the other hand, deep learning has shown remarkable results in various fields, and research on application of deep reinforcement learning algorithm to portfolio management has begun. In this paper, we propose an efficient financial portfolio investment management method based on Asynchronous Advantage Actor-Critic (A3C), which is a representative asynchronous reinforcement learning algorithm. In addition, since the conventional cross-entropy function can not be applied to portfolio management, we propose a proper method where the existing cross-entropy is modified to fit the portfolio investment method. Finally, we compare the proposed A3C model with the existing reinforcement learning based cryptography portfolio investment algorithm, and prove that the performance of the proposed A3C model is better than the existing one.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.4
• /
• pp.246-254
• /
• 2020

In this paper, we propose a learning based compressive sensing algorithm for the purpose of side scan sonar image denoising. The proposed method is based on Iterative Shrinkage and Thresholding Algorithm (ISTA) framework and incorporates a powerful strategy that reinforces the non-linearity of deep learning network for improved performance. The proposed method consists of three essential modules. The first module consists of a non-linear transform for input and initialization while the second module contains the ISTA block that maps the input features to sparse space and performs inverse transform. The third module is to transform from non-linear feature space to pixel space. Superiority in noise removal and memory efficiency of the proposed method is verified through various experiments.

• KIISE Transactions on Computing Practices
• /
• v.23 no.12
• /
• pp.698-702
• /
• 2017

Since the introduction of Deep Neural Networks to the Natural Language Processing field, two major approaches have been considered for modeling text. One method involved learning embeddings, i.e. the distributed representations containing abstract semantics of words or sentences, with the textual context. The other strategy consisted of composing the embeddings trained by the above to get embeddings of longer texts. However, most studies of the composition methods just adopt word embeddings without consideration of the optimal embedding unit and the optimal method of composition. In this paper, we conducted experiments to analyze the optimal embedding unit and the optimal composition method for modeling longer texts, such as documents. In addition, we suggest a new discourse-based composition to overcome the limitation of the sequential composition method on composing sentence embeddings.

• Convergence Security Journal
• /
• v.22 no.3
• /
• pp.25-32
• /
• 2022

Recently, the image processing industry has been activated as deep learning-based technology is introduced in the image recognition and detection field. With the development of deep learning technology, learning model vulnerabilities for adversarial attacks continue to be reported. However, studies on countermeasures against poisoning attacks that inject malicious data during learning are insufficient. The conventional countermeasure against poisoning attacks has a limitation in that it is necessary to perform a separate detection and removal operation by examining the training data each time. Therefore, in this paper, we propose a technique for reducing the attack success rate by applying modifications to the training data and inference data without a separate detection and removal process for the poison data. The One-shot kill poison attack, a clean label poison attack proposed in previous studies, was used as an attack model. The attack performance was confirmed by dividing it into a general attacker and an intelligent attacker according to the attacker's attack strategy. According to the experimental results, when the proposed defense mechanism is applied, the attack success rate can be reduced by up to 65% compared to the conventional method.