• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10b
• /
• pp.490-492
• /
• 2003

Wireless Network과 Ubiquitous Computing의 확산은 다양한 대역폭과 다양한 단말 능력을 가능하게 하였다. 이런 환경에서 비디오 인코딩을 담당하는 단말은 자신의 능력이 제한됨에 따라서, 재생을 담당하는 장치의 능력을 충분히 활용하지 못 하고 있다. 이 논문에서는 이런 제한을 없애기 위해서 네트웍 구조 상에 위치한 서버의 능력을 인코딩에 사용함으로써, 인코딩 능력을 최대화하고, 재생을 담당하는 단말의 능력을 최대화하는 방법을 제시한다.

• KIISE Transactions on Computing Practices
• /
• v.24 no.3
• /
• pp.113-121
• /
• 2018

Position encoding is a method of applying weights according to position of words that appear in a sentence. Pointer networks is a deep learning model that outputs corresponding index with an input sequence. This model can be applied to coreference resolution using attribute. However, the pointer networks has a problem in that its performance is degraded when the length of input sequence is long. To solve this problem, we proposed two contributions to resolve the coreference. First, we applied position encoding and dynamic position encoding to pointer networks. Second, we stack deeply layers of encoder to make high-level abstraction. As results, the position encoding based stacked pointer networks model proposed in this paper had a CoNLL F1 performance of 71.78%, which was improved by 6.01% compared to vanilla pointer networks.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2009.01a
• /
• pp.189-192
• /
• 2009

게임에서 주인공 캐릭터나 MPC(Non Player Character)가 목적지까지의 경로를 찾는 것은 매우 중요하다. 또한 캐릭터가 이동 중 다양한 오브젝트와 벽을 만나면 이를 회피해야 하며 최단 경로로 이동해야 한다. 본 논문에서는 게임 맵에서 캐릭터의 길 찾기 방법으로 유전 알고리즘을 이용하는 방법을 제안하였다. 특히, 유전 알고리즘의 구성요소 중해 집합을 구성하는 염색체 인코딩 방법을 제안하였다. 본 논문에서 제안한 염색체의 인코딩은 캐릭터의 이동 방향을 비트 스트링으로 표현하였다. 캐릭터가 현재 위치에서 이동할 수 있는 방향은 8 방향이다. 따라서 하나의 방향을 표현하기 위해서는 3비트의 이진스트링으로 나타낼 수 있다. 하나의 해를 나타내는 염색체는 3비트의 이진 스트링을 맵을 나타내는 그래프의 노드 수만큼 할당하여 구성할 수 있다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.01a
• /
• pp.321-322
• /
• 2014

게임에서 캐릭터가 현재 위치에서 목적지까지 경로를 탐색하는 것은 매우 중요하다. 특히, 오브젝트나 벽 등의 장애물들이 배치된 복잡한 게임 맵에서는 이러한 장애물을 회피하면서 가능한 최단 경로를 찾아 이동해야 한다. 본 논문에서는 복잡한 게임 맵 상에서 캐릭터가 목적지까지 최단 경로를 탐색하는 방법으로 유전자 알고리즘을 적용하는 방법을 제안한다. 유전자 알고리즘은 모집단(Population)을 구성하는 염색체의 인코딩 및 디코딩, 진화를 위한 연산자인 교차연산(Crossover)과 돌연변이연산(Mutation), 그리고 염색체를 평가하는 목적함수로 구성된다. 본 논문에서는 염색체 구성을 시작 노드에서 목적지 노드까지의 전체 노드로 구성하기 보다는 캐릭터의 현재노드에서 이동할 수 있는 8방향만으로 구성하여 염색체의 크기를 줄였고, 이를 통해 염색체의 인코딩과 디코딩 연산 시간을 줄일 수 있었다.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.81-86
• /
• 2024

The Image Signal Processor (ISP) converts RAW images captured by the camera sensor into user-preferred sRGB images. While RAW images contain more meaningful information for image processing than sRGB images, RAW images are rarely shared due to their large sizes. Moreover, the actual ISP process of a camera is not disclosed, making it difficult to model the inverse process. Consequently, research on learning the conversion between sRGB and RAW has been conducted. Recently, the ParamISP[1] model, which directly incorporates camera parameters (exposure time, sensitivity, aperture size, and focal length) to mimic the operations of a real camera ISP, has been proposed by advancing the simple network structures. However, existing studies, including ParamISP[1], have limitations in modeling the camera ISP as they do not consider the degradation caused by lens shading, optical aberration, and lens distortion, which limits the restoration performance. This study introduces Positional Encoding to enable the camera ISP neural network to better handle degradations caused by lens. The proposed positional encoding method is suitable for camera ISP neural networks that learn by dividing the image into patches. By reflecting the spatial context of the image, it allows for more precise image restoration compared to existing models.

• Journal of KIISE:Software and Applications
• /
• v.32 no.10
• /
• pp.974-983
• /
• 2005

In genetic algorithms with lotus-based encoding, static gene reordering is to locate the highly related genes closely together. It helps the genetic algorithms to create and preserve the schema of high-quality effectively. In this paper, we propose a static reordering framework for linear locus-based encoding. It differs from existing reorderings in that it is independent of problem-specific knowledge. It makes a complete graph where weights represent the interelationship between each pair of genes. And, it transforms the graph into a unweighted sparse graph by choosing the edges having relatively high weight. It finds a gene reordering by graph search method. Through the wide experiments about several problems, the method proposed in this paper shows significant performance improvement as compared with the genetic algorithm that does not rearrange genes.

• Annual Conference of KIPS
• /
• 2008.05a
• /
• pp.879-880
• /
• 2008

본 논문은 제주 택시 텔레매틱스 시스템에 축적되고 있는 차량들의 이동이력 데이터에 대한 처리구조를 설계하고 구현한다. 각 차량은 1분마다 자신의 위치와 GPS 정보 및 택시의 상태에 관련된 보고를 발생시키며 중앙의 관제시스템은 이를 수합하여 이력데이터를 구성한다. 본 논문에서 구현하는 시스템은 위치 보고를 처리하여 인코딩 변환, 좌표 변환, 맵 매칭, 도로상에서의 위치 계산 등을 수행한 후 오라클 데이터베이스의 이력 테이블에 저장하도록 한다. 이를 위하여 도로 네트워크가 데이터베이스로 변환되었으며 도로망에의 가시화를 위하여 지도 인터페이스 프로그램이 구현되었다. 이러한 정보들은 이력 테이블과 아울러 공간 데이터베이스 엔진과 결합하여 C 언어나 SQL 문장에 의하여 다양한 위치기반 질의를 가능하게 할 뿐 아니라 배차 정보 분석, 현재 통행 속도 분석 등 부가가치가 높은 정보를 산출하는데 필수적인 역할을 수행한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.12
• /
• pp.2590-2598
• /
• 2011

AIS(Automatic Identification System) is a key of maritime information system to prevent maritime accident through communication among any adjacent ship and to establish information base by fusing information collected from ships with other information. The AIS information includes various potential information, but it is not easy to use due to insufficiency storing and management. Furthermore, we need AIS transponders to acquire the information. In this paper, we propose the vessel positional information service using AIS and XML. We decode the AIS information from the NMEA-0183 encoding data and store the AIS information to the database and provide the access service in the internet using XML.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.5
• /
• pp.188-199
• /
• 2018

In this study a novel dynamic lane-level location referencing method(LLRM) was developed. The terminologies were defined and the prerequisites were suggested for the LLRM. Then, the logical and physical data formats were proposed, followed by the development of encoding and decoding algorithms. To conduct a performance test of the proposed method, two different high precision digital maps were prepared as well as an evaluation tool. The test results demonstrated that the proposed method works perfectly in terms of accuracy. The processing speed and the data size were found to be less efficient, but it is expected that the defect would be compensated soon enough due to the fast growing technology of ICT and computer hardwares.

• Smart Media Journal
• /
• v.12 no.1
• /
• pp.9-16
• /
• 2023

Recently, a convolutional neural network (CNN) based system is being developed to overcome the limitations of human resources in the apple quality classification of farmhouse. However, since convolutional neural networks receive only images of the same size, preprocessing such as sampling may be required, and in the case of oversampling, information loss of the original image such as image quality degradation and blurring occurs. In this paper, in order to minimize the above problem, to generate a image patch based graph of an original image and propose a random walk-based positional encoding method to apply the graph transformer model. The above method continuously learns the position embedding information of patches which don't have a positional information based on the random walk algorithm, and finds the optimal graph structure by aggregating useful node information through the self-attention technique of graph transformer model. Therefore, it is robust and shows good performance even in a new graph structure of random node order and an arbitrary graph structure according to the location of an object in an image. As a result, when experimented with 5 apple quality datasets, the learning accuracy was higher than other GNN models by a minimum of 1.3% to a maximum of 4.7%, and the number of parameters was 3.59M, which was about 15% less than the 23.52M of the ResNet18 model. Therefore, it shows fast reasoning speed according to the reduction of the amount of computation and proves the effect.