• Journal of Korea Society of Industrial Information Systems
• /
• v.24 no.1
• /
• pp.23-30
• /
• 2019

As deep learning with the network-based algorithms evolve, artificial intelligence is rapidly growing around the world. Among them, finance is expected to be the field where artificial intelligence is most used, and many studies have been done recently. The existing financial strategy using deep-run is vulnerable to volatility because it focuses on stock price forecasts for a single stock. Therefore, this study proposes to construct ETF products constructed through portfolio methods by calculating the stocks constituting funds by using deep learning. We analyze the performance of the proposed model in the KOSPI 100 index. Experimental results showed that the proposed model showed improved results in terms of returns or volatility.

• Journal of Drive and Control
• /
• v.20 no.2
• /
• pp.15-23
• /
• 2023

In this study, two-dimensional location of crops for auto weeding was detected using deep learning. To construct a dataset for soybean detection, an image-capturing system was developed using a mono camera and single-board computer and the system was mounted on a weeding robot to collect soybean images. A dataset was constructed by extracting RoI (region of interest) from the raw image and each sample was labeled with soybean and the background for classification learning. The deep learning model consisted of four convolutional layers and was trained with a weakly supervised learning method that can provide object localization only using image-level labeling. Localization of the soybean area can be visualized via CAM and the two-dimensional position of the soybean was estimated by clustering the pixels associated with the soybean area and transforming the pixel coordinates to world coordinates. The actual position, which is determined manually as pixel coordinates in the image was evaluated and performances were 6.6(X-axis), 5.1(Y-axis) and 1.2(X-axis), 2.2(Y-axis) for MSE and RMSE about world coordinates, respectively. From the results, we confirmed that the center position of the soybean area derived through deep learning was sufficient for use in automatic weeding systems.

• ETRI Journal
• /
• v.44 no.2
• /
• pp.194-207
• /
• 2022

In the last decade, substantial progress has been achieved in intelligent traffic control technologies to overcome consistent difficulties of traffic congestion and its adverse effect on smart cities. Edge computing is one such advanced progress facilitating real-time data transmission among vehicles and roadside units to mitigate congestion. An edge computing-based deep reinforcement learning system is demonstrated in this study that appropriately designs a multiobjective reward function for optimizing different objectives. The system seeks to overcome the challenge of evaluating actions with a simple numerical reward. The selection of reward functions has a significant impact on agents' ability to acquire the ideal behavior for managing multiple traffic signals in a large-scale road network. To ascertain effective reward functions, the agent is trained withusing the proximal policy optimization method in several deep neural network models, including the state-of-the-art transformer network. The system is verified using both hypothetical scenarios and real-world traffic maps. The comprehensive simulation outcomes demonstrate the potency of the suggested reward functions.

• International Journal of Advanced Culture Technology
• /
• v.7 no.4
• /
• pp.289-294
• /
• 2019

As social network service platforms grow and one-person media market expands, people upload their own photos and/or videos through multiple open platforms. However, it can be illegal to upload the digital contents containing the faces of others on the public sites without their permission. Therefore, many people are spending much time and effort in editing such digital contents so that the faces of others should not be exposed to the public. In this paper, we propose an automatic face hiding system called 'autoblur', which detects all the unregistered faces and mosaic them automatically. The system has been implemented using the GitHub MIT open-source 'Face Recognition' which is based on deep learning technology. In this system, two dozens of face images of the user are taken from different angles to register his/her own face. Once the face of the user is learned and registered, the system detects all the other faces for the given photo or video and then blurs them out. Our experiments show that it produces quick and correct results for the sample photos.

• International journal of advanced smart convergence
• /
• v.10 no.4
• /
• pp.278-288
• /
• 2021

Recently, IoT systems are cloud-based, so that continuous and large amounts of data collected from sensor nodes are processed in the data server through the cloud. However, in the centralized configuration of large-scale cloud computing, computational processing must be performed at a physical location where data collection and processing take place, and the need for edge computers to reduce the network load of the cloud system is gradually expanding. In this paper, a cluster system consisting of 6 inexpensive Raspberry Pi boards was constructed to perform fast data processing. And we propose "Kubernetes cluster system(KCS)" for processing large data collection and analysis by model distribution and data pipeline method. To compare the performance of this study, an ensemble model of deep learning was built, and the accuracy, processing performance, and processing time through the proposed KCS system and model distribution were compared and analyzed. As a result, the ensemble model was excellent in accuracy, but the KCS implemented as a data pipeline proved to be superior in processing speed..

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.12
• /
• pp.11-19
• /
• 2018

In the Unmanned Aerial Vehicle Line-Of-Sight datalink system, there is a possibility that the communication line is disconnected because line of sight can not be secured by one antenna due to changes in position and posture of the air vehicle. In order to prevent this, both top and bottom of air vehicle are equipped with antennas. At this time, if the signal can be transmitted and received by switching to an antenna advantageous for securing the line of sight, communication disconnection can be minimized. The legacy antenna switching method has disadvantages such that diffraction, fading due to the surface or obstacles, interference and reflection of the air vehicle are not considered, or antenna switching standard is not clear. In this paper, we propose an airborne antenna switching method for improving the performance of UAV LOS datalink system. In the antenna switching method, the performance of each of the upper and lower parts of the mounted antenna according to the position and attitude of the air vehicle is predicted by using the deep learning in an UAV LOS datalink system in which only the antenna except the receiver is duplicated. Simulation using flying test dataset shows that it is possible to switch antennas considering the position and attitude of unmanned aerial vehicle in the datalink system.

• Journal of Korea Society of Industrial Information Systems
• /
• v.24 no.2
• /
• pp.25-31
• /
• 2019

As artificial intelligence technology has been developed rapidly, many researchers who are interested in next-generation vehicles have been studying on applying the artificial intelligence technology to advanced driver assistance systems (ADAS). In this paper, a method of applying deep learning algorithm to the lane departure warning system which is one of the main components of the ADAS was proposed. The performance of the proposed method was evaluated by taking a comparative experiments with the existing algorithm which is based on the line detection using image processing techniques. The experiments were carried out for two different driving situations with image databases for driving on a highway and on the urban streets. The experimental results showed that the proposed system has higher accuracy and precision than the existing method under both situations.

• Journal of IKEEE
• /
• v.25 no.2
• /
• pp.285-290
• /
• 2021

The existing aiming inspection use foreign-made aiming inspection equipment. However, the quantity is insufficient and the difficult to maintain. So it takes a lot of time to inspect the target. This system can reduces the time of aiming inspection and be maintained and distributed smoothly because it is a domestic product. In this paper, we develop a system that can detect targets and monitor shooting results through a target detection deep learning model. The system is capable of real-time detection of targets and has significantly increased the identification rate through several preprocessing of distant targets. In addition, a graphical user interface is configured to facilitate user camera manipulation and storage and management of training result data. Therefore the system can replace the currently used aiming inspection equipment and non-fire training.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.2
• /
• pp.24-29
• /
• 2023

In this paper, we propose a real-time bus arrival notification system using deep learning to guarantee movement rights for the visually impaired. In modern society, by using location information of public transportation, users can quickly obtain information about public transportation and use public transportation easily. However, since the existing public transportation information system is a visual system, the visually impaired cannot use it. In Korea, various laws have been amended since the 'Act on the Promotion of Transportation for the Vulnerable' was enacted in June 2012 as the Act on the Movement Rights of the Blind, but the visually impaired are experiencing inconvenience in using public transportation. In particular, from the standpoint of the visually impaired, it is impossible to determine whether the bus is coming soon, is coming now, or has already arrived with the current system. In this paper, we use deep learning technology to learn bus numbers and identify upcoming bus numbers. Finally, we propose a method to notify the visually impaired by voice that the bus is coming by using TTS technology.

• Korean Chemical Engineering Research
• /
• v.58 no.2
• /
• pp.230-234
• /
• 2020

A system that uses deep-learning techniques to predict properties from molecular structures has been developed to apply to chemical, biological and material studies. Based on the database where molecular structure and property information are accumulated, a deep-learning model looking for the relationship between the structure and the property can eventually provide a property prediction for the new molecular structure. In addition, experiments on the actual properties of the selected molecular structure will be carried out in parallel to carry out continuous verification and model updates. This allows for the screening of high-quality molecular structures from large quantities of molecular structures within a short period of time, and increases the efficiency and success rate of research. In this paper, we would like to introduce the overall composition of the materiality prediction system using deep-learning and the cases applied in the actual excavation of new structures in LG Chem.