• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.9
• /
• pp.1025-1031
• /
• 2019

This study proposes a PCS that enables efficient operation of seawater pumps for ships by implementing ML-based algorithms. Seawater temperature, RPM and power consumption data are acquired from two ships with PCS, analyzed with regression analysis method, and new algorithms are presented. Using the algorithms presented, Ship A saved about 36% compared to the PCS application, and ML-based algorithms in certain sea temperatures of 19 to 27 degrees Celsius and above 32 degrees Celsius were about 1% lower than Ship A's PCS. Ship B saved about 50% compared to PCS not applied, and about 2% more than Ship B's PCS in waters above $19^{\circ}C$, a specified sea temperature. The derived data can be used to suggest the optimum pump speed and sea route. In addition, the trend of acquired data can be used to infer the performance of the pump or the timing of elimination of the MGPS when efficiency becomes poor.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.3
• /
• pp.165-171
• /
• 2019

The study of the computer architecture has shown that major improvements in price-to-energy performance stems from domain-specific hardware development. This paper analyzes the tensor processing unit (TPU) ASIC which can accelerate the reasoning of the artificial neural network (NN). The core device of the TPU is a MAC matrix multiplier capable of high-speed operation and software-managed on-chip memory. The execution model of the TPU can meet the reaction time requirements of the artificial neural network better than the existing CPU and the GPU execution models, with the small area and the low power consumption even though it has many MAC and large memory. Utilizing the TPU for the tensor flow benchmark framework, it can achieve higher performance and better power efficiency than the CPU or CPU. In this paper, we analyze TPU, simulate the Python modeled OpenTPU, and synthesize the matrix multiplication unit, which is the key hardware.

• Journal of Auto-vehicle Safety Association
• /
• v.11 no.2
• /
• pp.35-43
• /
• 2019

This paper describes the improved environment recognition algorithms using some type of sensors like LiDAR and cameras. Additionally, integrated control algorithm for an autonomous vehicle is included. The integrated algorithm was based on C++ environment and supported the stability of the whole driving control algorithms. As to the improved vision algorithms, lane tracing and traffic sign recognition were mainly operated with three cameras. There are two algorithms developed for lane tracing, Improved Lane Tracing (ILT) and Histogram Extension (HIX). Two independent algorithms were combined into one algorithm - Enhanced Lane Tracing with Histogram Extension (ELIX). As for the enhanced traffic sign recognition algorithm, integrated Mutual Validation Procedure (MVP) by using three algorithms - Cascade, Reinforced DSIFT SVM and YOLO was developed. Comparing to the results for those, it is convincing that the precision of traffic sign recognition is substantially increased. With the LiDAR sensor, static and dynamic obstacle detection and obstacle avoidance algorithms were focused. Therefore, improved environment recognition algorithms, which are higher accuracy and faster processing speed than ones of the previous algorithms, were proposed. Moreover, by optimizing with integrated control algorithm, the memory issue of irregular system shutdown was prevented. Therefore, the maneuvering stability of the autonomous vehicle in severe environment were enhanced.

• Journal of Advanced Navigation Technology
• /
• v.22 no.6
• /
• pp.491-499
• /
• 2018

Runway visual range (RVR), one of the important indicators of aircraft takeoff and landing, is affected by meteorological conditions such as temperature, humidity, etc. It is important to estimate the RVR at the time of arrival in advance. This study estimated the RVR of the local airport after 1 hour by upgrading the RVR estimation model using the proposed deep learning network. To this end, the advancement of the estimation model was carried out by changing the time interval of the meteorological data (temperature, humidity, wind speed, RVR) as input value and the linear conversion of the results. The proposed method generates estimation model based on the past measured meteorological data and estimates the RVR after 1 hour and confirms its validity by comparing with measured RVR after 1 hour. The proposed estimation model could be used for the RVR after 1 hour as reference in small airports in regions which do not forecast the RVR.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.25 no.1
• /
• pp.111-116
• /
• 2019

The fire detectors used in the engine rooms of ships offer only a slow response to emergencies because smoke or heat must reach detectors installed on ceilings, but the air flow in engine rooms can be very fluid depending on the use of equipment. In order to overcome these disadvantages, much research on video-based fire detection has been conducted in recent years. Video-based fire detection is effective for initial detection of fire because it is not affected by air flow and transmission speed is fast. In this paper, experiments were performed using images of smoke from a smoke generator in an engine room. Data generated using LBP and GLCM operators that extract the textural features of smoke was classified using SVM, which is a machine learning classifier. Even if smoke did not rise to the ceiling, where detectors were installed, smoke detection was confirmed using the image-based technique.

• Smart Media Journal
• /
• v.9 no.4
• /
• pp.134-143
• /
• 2020

Vehicle License Plate Recognition is one of the approaches for transportation and traffic safety networks, such as traffic control, speed limit enforcement and runaway vehicle tracking. Although it has been studied for decades, it is attracting more and more attention due to the recent development of deep learning and improved performance. Also, it is largely divided into license plate detection and recognition. In this study, experiments were conducted to improve license plate detection performance by utilizing various object detection methods and WPOD-Net(Warped Planar Object Detection Network) model. The accuracy was improved by selecting the method of detecting the vehicle(s) and then detecting the license plate(s) instead of the conventional method of detecting the license plate using the object detection model. In particular, the final performance was improved through the process of removing noise existing in the image by using the Fast-SRGAN model, one of the Super-Resolution methods. As a result, this experiment showed the performance has improved an average of 4.34% from 92.38% to 96.72% compared to previous studies.

• International Journal of Advanced Culture Technology
• /
• v.8 no.4
• /
• pp.279-286
• /
• 2020

This study was a phenomenological qualitative research that analyzed the experiences of Korean students studying in Korea after the COVID-19 incident. Participants in this study consisted of 22 international students aged 20 to 40 attending the International Exchange Center at C University. The interview period was from September 10, 2020 to October 10, 2020. Giogi qualitative research method was used to analyze vivid experiences of international students. As a result of the analysis, 26 semantic units, 7 subcomponents were derived. The description of the general structure sentence of phenomenology was a description of the meaning of experience from the perspective of participants, and the context and structure descriptions were integrated. The results of this study showed that: The students who came to Korea to study were concerned about Korea in various ways, but they had to adjust to unexpected changes in education methods, anxious about the unexpected COVID-19 disaster. Participants chose to study in Korea based on existing information, so they felt anxiety, regret, fear, and frustration over sudden changes, but taking online classes helped them learn repeatedly and voluntarily became an experience that suited their learning speed. As commuting time has decreased, they were more opportunities to make money in Korea also. Based on the results of this study, the following is suggested: First, the government should establish systematic online infection prevention measures for international students who have poor Korean language skills in preparation for unexpected disasters. Second, non-face-to-face teaching methods should be prepared with the same weight in the face-to-face teaching methods that have been carried out so far in preparation for unexpected disasters.

• Journal of Digital Convergence
• /
• v.19 no.2
• /
• pp.215-220
• /
• 2021

In order to reduce the harmful effects on the human body caused by the recent increase in the generation of fine dust in Korea, there is a need for technology to help predict the level of fine dust and take precautions. In this paper, we propose a 1D Convolutional-Recurrent Neural Network (1-D CRNN) model to predict the level of fine dust in Korea. The proposed model is a structure that combines the CNN and the RNN, and uses domestic and foreign fine dust, wind direction, and wind speed data for data prediction. The proposed model achieved an accuracy of about 76%(Partial up to 84%). The proposed model aims to data prediction model for time series data sets that need to consider various data in the future.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.6
• /
• pp.1067-1078
• /
• 2020

With the development of internet technology, a lot of content is produced, and the demand for it is increasing. Accordingly, the number of contents in circulation is increasing, while the number of distributing illegal copies that infringe on copyright is also increasing. The Korea Copyright Protection Agency operates a illegal content obstruction program based on substring matching, and it is difficult to accurately search because a large number of noises are inserted to bypass this. Recently, researches using natural language processing and AI deep learning technologies to remove noise and various blockchain technologies for copyright protection are being studied, but there are limitations. In this paper, noise is removed from data collected online, and keyword-based illegal copies are searched. In addition, the same heavy uploader is estimated through profiling analysis for heavy uploaders. In the future, it is expected that copyright damage will be minimized if the illegal copy search technology and blocking and response technology are combined based on the results of profiling analysis for heavy uploaders.

• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.1050-1057
• /
• 2020

Immersive 360-degree media has a problem of slowing down the video recognition speed when the video is processed by the conventional method using a variety of rendering methods, and the video size becomes larger with higher quality and extra-large volume than the existing video. In addition, in most cases, only one scene is captured by fixing the camera in a specific place due to the characteristics of the immersive 360-degree media, it is not necessary to extract feature information from all scenes. In this paper, we propose a reference frame selection method for immersive 360-degree media and describe its application process to copyright protection technology. In the proposed method, three pre-processing processes such as frame extraction of immersive 360 media, frame downsizing, and spherical form rendering are performed. In the rendering process, the video is divided into 16 frames and captured. In the central part where there is much object information, an object is extracted using an RGB vector per pixel and deep learning, and a reference frame is selected using object feature information.