• Journal of Information Processing Systems
• /
• v.18 no.4
• /
• pp.480-488
• /
• 2022

Images of tobacco retail licenses have complex unstructured characteristics, which is an urgent technical problem in the robot process automation of tobacco marketing. In this paper, a novel recognition approach using a double attention mechanism is presented to realize the automatic recognition and information extraction from such images. First, we utilized a DenseNet network to extract the license information from the input tobacco retail license data. Second, bi-directional long short-term memory was used for coding and decoding using a continuous decoder integrating dual attention to realize the recognition and information extraction of tobacco retail license images without segmentation. Finally, several performance experiments were conducted using a largescale dataset of tobacco retail licenses. The experimental results show that the proposed approach achieves a correction accuracy of 98.36% on the ZY-LQ dataset, outperforming most existing methods.

• 한국태양에너지학회:학술대회논문집
• /
• 2011.11a
• /
• pp.249-255
• /
• 2011

This paper is about the study of a stand-alone photovoltaic power conditioning system with an energy storage system with battery. The paper proposes the appropriate circuit model of stand-alone PV PCS considering the maintenance of the battery system. It also proposes the buck converter modeling by a state-space averaging method considering characteristics of solar cell. Lastly, it shows the way to choose the suitable battery and to design the model of bi-directional converter for charging and discharging battery. PSIM simulation is used to validate the proposed algothim of the system.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06d
• /
• pp.46-48
• /
• 2006

현재 컴퓨터에서 사용되는 수의 체계는 컴퓨터의 메모리구조에서 사용하기 가장 알맞은 2진법과16진법이며 여러 프로그램들에서 효율적으로 사용되어 왔다. 그러나 어떠한 수의 체계든지 프로그램의 성질에 따라 예외적으로 드러나는 비효율적인 특성을 가지고 있다. 본 논문에서, 우리는 라우팅 관점에서의 2진법과 16진법의 예외적인 부분을 이용한 새로운 라우팅 어드레스의 표기법을 제안하며, 제안된 어드레스의 표기법을 이용한 라우팅 테이블과 라우팅 어드레스맵을 구성, 최소한의 메모리를 사용하여 센서네트워크 상에서 효율적인 Ad-Hoc 양방향 라우팅 방식을 구현하였다.

• Proceedings of the KIPE Conference
• /
• 2011.07a
• /
• pp.169-170
• /
• 2011

본 논문은 양방향 Buck 컨버터 DCM 구동 시 사용되는 스위치의 전류링잉현상을 상세히 분석하고 이에 따른 스위치 효율과 시스템 전력 효율 차이를 실험을 통해 검증한다. 분석을 통해 얻은 결과를 바탕으로 양방향 Buck 컨버터 설계 시 전력 효율을 높이는 스위치 및 다이오드를 선정하였다.

• Proceedings of the KIEE Conference
• /
• 2007.10c
• /
• pp.264-265
• /
• 2007

본 논문에서는 하이브리드 전기 자동차(Hybrid Electric Vehicle, HEV)의 실제 주행패턴 데이터를 기준으로 하이브리드 전력 시스템용 양방향 DC-DC 컨버터를 설계하고, 시뮬레이터를 구성한다. HEV의 주행패턴 데이터 중 가 감속 구간 일부를 선택하여 전기적 부하 변화로 모델링하고, 이를 통해 양방향 DC-DC 컨버터의 모드별 동작을 시뮬레이션 한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.6
• /
• pp.2444-2463
• /
• 2020

Significant detection of video can more rationally allocate computing resources and reduce the amount of computation to improve accuracy. Deep learning can extract the edge features of the image, providing technical support for video saliency. This paper proposes a new detection method. We combine the Convolutional Neural Network (CNN) and the Deep Bidirectional LSTM Network (DB-LSTM) to learn the spatio-temporal features by exploring the object motion information and object motion information to generate video. A continuous frame of significant images. We also analyzed the sample database and found that human attention and significant conversion are time-dependent, so we also considered the significance detection of video cross-frame. Finally, experiments show that our method is superior to other advanced methods.

• Journal of Korea Multimedia Society
• /
• v.7 no.10
• /
• pp.1452-1463
• /
• 2004

The requirement of automatic video summary is increasing as bi-directional broadcasting contents and various user requests and preferences for the bi -directional broadcast environment are increasing. Automatic video summary is needed for an efficient management and usage of many contents in service provider as well. In this paper, we propose a method to generate a content-based summary of linguistic educational videos automatically. First, shot-boundaries and keyframes are generated from linguistic educational video and then multiple(low-level) visual features are extracted. Next, the semantic parts (Explanation part, Dialog part, Text-based part) of the linguistic educational video are generated using extracted visual features. Lastly the XMI- document describing summary information is made based on HieraTchical Summary architecture oi MPEG-7 MDS (Multimedia I)escription Scheme). Experimental results show that our proposed algorithm provides reasonable performance for automatic summary of linguistic educational videos. We verified that the proposed method is useful ior video summary system to provide various services as well as management of educational contents.

• Journal of Internet Computing and Services
• /
• v.5 no.5
• /
• pp.17-26
• /
• 2004

Mobile multicast schemes are classified into remote subscription and bi-directional tunneling. While the former scheme has much overhead in the maintenances of multicast tree, the latter suffers from inefficient routing. In this paper, we propose dynamic mobile multicast routing (DMMR) scheme, which is operated on the basis of cost functions related with forwarding cost and tree reconstruction cost, Basically DMMR intends to find lower cost between forwarding cost and tree reconstruction cost. Forwarding cost is the cost of tunneling multicast packets from home agent, and tree reconstruction cost is the joining cost of foreign agent to multicast group. In the case that a mobile host moves to the other area, its foreign agent calculates cost functions related with forwarding cost and tree reconstruction cost. If forwarding cost is higher than tree reconstruction cost, foreign agent joins to multicast group and reconstructs the multicast tree. Accordingly, foreign agent can dynamically adapt remote subscription or bi-directional tunneling, Our scheme provides more stable multicast service to the mobile hosts regardless of the movements of mobile host and the number of mobile group members.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.5
• /
• pp.13-22
• /
• 2004

Because video sequence consists of dynamic objects in nature, the object motion in video is an effective feature in describing the contents of video sequence and motion feature plays an important role in video retrieval. In this paper, we propose a method that converts motion vectors (MVs) to a uniform set on MPEG coded domain, independent of the frame type and the direction of prediction, and utilizes these normalized MVs (N-MVs) as motion descriptor to understand video contents. We describe a frame-type independent representation of the various types of frames presented in an MPEG video in which all frames can be considered equivalently, without full-decoding. In the experiments, we show that the proposed method is better than the conventional one in terms of performance.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.12 s.354
• /
• pp.1-8
• /
• 2006

In this paper, we propose carrier phase synchronization algorithm which are base on turbo coded system for DVB-RCS. There have been two categories of phase estimator, single estimator outside turbo code decoder and multiple estimators inside turbo code decoder. In single estimator, we use the estimation algorithm that ML(Maximum Likelihood) and LMS(Least Mean Square), also three different soft decision methods are proposed. Multiple estimator apply PSP(Per Survivor Processing) algorithm additionally. We compared performance between single estimator and Multiple estimator in AWGN channel. We presented the two methods of PSP algorithm for performance elevation. First is the Bi-directional channel estimation and second is binding method.