• Journal of Korea Society of Industrial Information Systems
• /
• v.15 no.5
• /
• pp.37-51
• /
• 2010

In this paper, we discuss the program implementation and system optimization for the effective transfer of huge amount of data. In VLBI which is observing the celestial bodies by using radio telescope hundreds thousands km apart, it is necessary for each VLBI observatory to transfer up to terabytes of observed data. For this reason, e-VLBI research based on advanced network is being actively carried out for the transfer of data efficiently. Following this trend, in this paper, we discuss design & implementation of system for the high speed Gbps data transfer rates. As a data transfer protocol, we use UDP for designing data transmission program with much higher speeds than currently available via VTP(VLBI Transport Protocol). Tsunami-UDP algorithms is applied to implementing data transfer program so that transmission performance could be maximize, also we make it possible to transfer observed data more fast and reliable through optimization of computer systems in each VLBI statopm.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.7
• /
• pp.992-1001
• /
• 2023

OWEC (Overtopping Wave Energy Converter) is a wave power generation system using the wave overtopping. The performance and safety of the OWEC are affected by wave characteristics, such as wave height, period. To mitigate this issue, optimal OWEC designs based on wave characteristics must be investigated. In this study, the environmental conditions along the Ulleungdo coast were used. The hydraulic efficiency of the OWEC was calculated using SPH (Smoothed Particle Hydrodynamics) by comparing 4 models that changed the substructure. As a result, it was possible to change the substructure. Through design optimization, a new truss-type structure, which is a substructure capable of carrying the design load, was proposed. Through a case study using member diameter and thickness as design variables, structural safety was secured under allowable stress conditions. Considering wave load, the natural frequency of the proposed structure was compared with the wave period of the relevant sea area. Harmonic response analysis was performed using wave with a 1-year return period as the load. The proposed substructure had a reduced response magnitude at the same exciting force, and achieved weight reduction of more than 32%.

• Korean Chemical Engineering Research
• /
• v.59 no.2
• /
• pp.209-218
• /
• 2021

First principle-based modeling studies have been performed to improve the heat exchange efficiency of ORV and optimize operation, but the heat transfer coefficient of ORV is an irregular system according to time and location, and it undergoes a complex modeling process. In this study, FNN, LSTM, and AutoML-based modeling were performed to confirm the effectiveness of data-based modeling for complex systems. The prediction accuracy indicated high performance in the order of LSTM > AutoML > FNN in MSE. The performance of AutoML, an automatic design method for machine learning models, was superior to developed FNN, and the total time required for model development was 1/15 compared to LSTM, showing the possibility of using AutoML. The prediction of NG and seawater discharged temperatures using LSTM and AutoML showed an error of less than 0.5K. Using the predictive model, real-time optimization of the amount of LNG vaporized that can be processed using ORV in winter is performed, confirming that up to 23.5% of LNG can be additionally processed, and an ORV optimal operation guideline based on the developed dynamic prediction model was presented.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.8B
• /
• pp.661-673
• /
• 2003

To prevent performance degradation of TCP due to packet losses in the smooth handoff by the route optimization extension of Mobile IP protocol, a buffering of packets at a base station is needed. A buffering of packets at a base station recovers those packets dropped during handoff by forwarding buffered packets at the old base station to the mobile user. But, when the mobile user moves to a congested base station in a new foreign subnetwork, those buffered packets forwarded by the old base station are dropped and TCP transmission performance of a mobile user in the congested base station degrades due to increased congestion by those forwarded burst packets. In this paper, considering the general case that a mobile user moves to a congested base station, we propose a Priority Packet Forwarding to improve TCP performance in mobile networks. In the proposed scheme, without modification to Mobile IP protocol, the old base station marks a buffered packet as a priority packet during handoff. And priority queue at the new congested base station schedules the priority packet firstly. Simulation results show that proposed Priority Packet Forwarding can improve TCP transmission performance more than Implicit Priority Packet Forwarding and RED (Random Early Detection) schemes.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.5 no.6
• /
• pp.583-591
• /
• 2015

In order to evaluate the performance of TAS applied to the hybrid vehicle of the soft belt driven, acceleration performance and fuel consumption performance is to be superior to the existing vehicle. The key components of belt driven TAS(Torque Assist System), such as the engine, the motor and the battery, The key components of the driven belt TAS, such as the engine, the motor, and the battery, have a significant impact on fuel consumption performance of the vehicle. Therefore, in order to improve the efficiency at the point of view based on the overall system, the study of the power distribution algorithm for controlling the main source powers is necessary. In this paper, we propose the power distribution algorithm, applied the homogeneous analysis method in terms of fuel equivalent, for minimizing the fuel consumption. We have confirmed that the proposed algorithm is contribute to improving the fuel consumption performance satisfied the constraints considering the vehicle status information and the required power through the control parameters to minimize the fuel consumption of the engine. The optimization process of the proposed driving strategy can reduce the trial and error in the research and development process and monitor the characteristics of the control parameter quickly and accurately. Therefore, it can be utilized as a way to derive the operational strategy to minimize the fuel consumption.

• Phonetics and Speech Sciences
• /
• v.15 no.3
• /
• pp.75-82
• /
• 2023

Automatic speech recognition (ASR) has been revolutionized with deep learning-based approaches, among which self-supervised learning methods have proven to be particularly effective. In this study, we aim to enhance the performance of OpenAI's Whisper model, a multilingual ASR system on the Korean language. Whisper was pretrained on a large corpus (around 680,000 hours) of web speech data and has demonstrated strong recognition performance for major languages. However, it faces challenges in recognizing languages such as Korean, which is not major language while training. We address this issue by fine-tuning the Whisper model with an additional dataset comprising about 1,000 hours of Korean speech. We also compare its performance against a Transformer model that was trained from scratch using the same dataset. Our results indicate that fine-tuning the Whisper model significantly improved its Korean speech recognition capabilities in terms of character error rate (CER). Specifically, the performance improved with increasing model size. However, the Whisper model's performance on English deteriorated post fine-tuning, emphasizing the need for further research to develop robust multilingual models. Our study demonstrates the potential of utilizing a fine-tuned Whisper model for Korean ASR applications. Future work will focus on multilingual recognition and optimization for real-time inference.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.10
• /
• pp.537-544
• /
• 2024

The rapid advancement of artificial intelligence and machine learning technologies is driving innovation across various industries, with natural language processing offering substantial opportunities for the analysis and processing of text data. The development of effective text classification models requires several complex stages, including data exploration, preprocessing, feature extraction, model selection, hyperparameter optimization, and performance evaluation, all of which demand significant time and domain expertise. Automated machine learning (AutoML) aims to automate these processes, thus allowing practitioners without specialized knowledge to develop high-performance models efficiently. However, current AutoML frameworks are primarily designed for structured data, which presents challenges for unstructured text data, as manual intervention is often required for preprocessing and feature extraction. To address these limitations, this study proposes a web-based AutoML platform that automates text preprocessing, word embedding, model training, and evaluation. The proposed platform substantially enhances the efficiency of text classification workflows by enabling users to upload text data, automatically generate the optimal ML model, and visually present performance metrics. Experimental results across multiple text classification datasets indicate that the proposed platform achieves high levels of accuracy and precision, with particularly notable performance when utilizing a Stacked Ensemble approach. This study highlights the potential for non-experts to effectively analyze and leverage text data through automated text classification and outlines future directions to further enhance performance by integrating Large language models.

• Journal of Digital Convergence
• /
• v.18 no.11
• /
• pp.259-266
• /
• 2020

Many developments have been steadily carried out by researchers with applying knowledge-based expert system or machine learning algorithms to the financial field. In particular, it is now common to perform knowledge based system trading in using stock prices. Recently, deep learning technologies have been applied to real fields of stock trading marketplace as GPU performance and large scaled data have been supported enough. Especially, LSTM has been tried to apply to stock price prediction because of its compatibility for time series data. In this paper, we implement stock price prediction using LSTM. In modeling of LSTM, we propose a fitness combination of model parameters and activation functions for best performance. Specifically, we propose suitable selection methods of initializers of weights and bias, regularizers to avoid over-fitting, activation functions and optimization methods. We also compare model performances according to the different selections of the above important modeling considering factors on the real-world stock price data of global major companies. Finally, our experimental work brings a fitness method of applying LSTM model to stock price prediction.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.5
• /
• pp.25-36
• /
• 2016

The goal of the SmartGrid is to maximize energy efficiency by exchanging bi-directional real-time power information with the help of ICT(Information and Communication Technology). In this paper, we propose a "JRS-MS" (Joint Routing and Scheduling for Multi-channel SmartGrid) algorithm that uses numerical modeling methods in IEEE 802.11s based STDMA multi-channel SmartGrid NAN networks. The proposed algorithm controls the amount of data transmission adaptively at the link layer and finds a high data-rate path which has the least interference between traffic flows in multi-channel SmartGrid NAN networks. The proposed algorithm improve transmission performance by enhancing network utilization. By comparing the results of performance analysis between the proposed algorithm and the JRS-SG algorithm in the previous paper, we showed that the JRS-MS algorithm can improve transmission performance by maximally utilizing given network resources when the number of flows are increasing in the multi-hop NAN wireless mesh networks.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.12 no.1
• /
• pp.1-8
• /
• 2009

EMMC(Entrapped Mixed Microbial Cell) process which is a kind of active cell immobilizing method was applied to treat fisheries processing wastewater biologically. Kinetic constants were calculated for organic and nitrogen removal and effect of effluent recycling on system performance was evaluated also. Yield coefficient, Y showed relatively low value compared with Y value obtained from conventional activated sludge process. It means that EMMC process can reduce amount of excess sludge significantly compared with conventional activated sludge process. Endogenous respiration coefficient $k_e$ of EMMC process also showed relatively low value compared with that of conventional activated sludge process. Yield coefficient Y, endogenous respiration coefficient $k_e$ and half saturation constant $k_s$ obtained from EMMC process in terms of nitrification were compared with reported value from literature based on suspended growth nitrification system. The value of Y obtained from this study has no difference compared with values obtained from literature review and $k_e$ of this study was low but $k_s$ of this study was high compared than values obtained from suspended growth nitrification system. To evaluate the effect of internal recycling on system performance, system was operated with internal recycling ratio of 1.5Q, 2.0Q, 2.5Q and 3.0Q. increase of internal recycling ratio effect more greatly on improvement of denitrification efficiency than that of nitrification efficiency. Accordingly, optimization of internal recycling ratio has to be based on improvement of anoxic reactor performance.