• Journal of Digital Convergence
• /
• v.16 no.4
• /
• pp.87-94
• /
• 2018

Intelligent transportation systems are one of the most important new forms of infrastructure on domestic roads, and is a system that makes possible the most efficient movement of vehicles on a road. The High Pass system, which is a domestic intelligent transportation system, started a little later than in other countries but developed at a rapid pace. With the recent introduction of smart tolling technology, it provided an opportunity to stop and review the tolling system. This study aims to investigate the driving method and results of LDCC for domestic smart towing through case study. Unlike other companies, Lotte Data Communication Company has long invested in payment systems. It has little experience investing in infrastructure, but participated in the Smart Toll System at the Gwangan Bridge in cooperation with the Busan City government, to lead the development of intelligent transportation systems. LDCC, which has made new investments, not only exceeded its existing core competencies, but also upgraded Korea's tolling system's ability to reduce greenhouse gas emissions and improved its financial performance.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.6
• /
• pp.647-654
• /
• 2022

Although the fields in which is utilized children's speech recognition is on the rise, the lack of quality data is an obstacle to improving children's speech recognition performance. This paper proposes a new method for improving children's speech recognition performance by additionally using adult speech data. The proposed method is a transformer based domain adversarial training using dynamically weighted loss to effectively address the data imbalance gap between age that grows as the amount of adult training data increases. Specifically, the degree of class imbalance in the mini-batch during training was quantified, and the loss function was defined and used so that the smaller the data, the greater the weight. Experiments validate the utility of proposed domain adversarial training following asymmetry between adults and children training data. Experiments show that the proposed method has higher children's speech recognition performance than traditional domain adversarial training method under all conditions in which asymmetry between age occurs in the training data.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.12
• /
• pp.1780-1792
• /
• 2016

In this paper, we propose an efficient counter-based broadcast scheme for high reachability and energy efficiency. To achieve this, we propose a method to calculate additional coverage when a node receives the same broadcast message from both nodes, in order to rebroadcast by a node who can cover an large area. We also propose a formula to determine random access delay (RAD) considering addition coverage, distance, density, and remaining battery information, and a formula to determine count threshold ($C_{th}$) considering density and remaining battery information. In addition, we evaluate the performance of the proposed broadcast scheme compared with the existing counter-based broadcast schemes through simulation.