• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.40 no.10
• /
• pp.24-34
• /
• 2003

In this paper, we investigated the problems of the offset time based service differentiation scheme for optical burst switching (OBS) networks, and proposed the preemption-based service differentiation scheme which combines a preemption channel selection algorithm and channel partitioning algorithm. The proposed preemption channel selection algorithm minimizes the length of preempted bursts to improve the channel efficiency, while the proposed channel partitioning algorithm controls the degree of service differentiation between service classes. The simulation results showed that the proposed schemes could improve the end-to-end performance and effectively provide controllable service differentiation in the multiple hop network environments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1919-1925
• /
• 2022

In this paper, we propose an image-to-image translation approach based on the conditional generative adversarial network for semantic segmentation. Semantic segmentation is the task of clustering parts of an image together which belong to the same object class. Unlike the traditional pixel-wise classification approach, the proposed method parses an input RGB image to its corresponding semantic segmentation mask using a pixel regression approach. The proposed method is based on the Pix2Pix image synthesis method. We employ residual connections-based convolutional neural network architectures for both the generator and discriminator architectures, as the residual connections speed up the training process and generate more accurate results. The proposed method has been trained and tested on the NYU-depthV2 dataset and could achieve a good mIOU value (49.5%). We also compare the proposed approach to the current methods in semantic segmentation showing that the proposed method outperforms most of those methods.

• Communications of Mathematical Education
• /
• v.13 no.2
• /
• pp.535-547
• /
• 2002

본 논문은 교육현장에서 자바(Java)를 이용한 수치계산 애플릿(Applet)을 개발할 경우 수식을 인식하여 그 결과를 실행하고 보여주는 심볼릭 연산을 구현하기 위한 알고리즘 개발과 다양한 입력식을 처리하기 위한 효율적인 자료구조를 제안한다. 구현된 패키지내의 클래스는 변수와 상수, 다양한 연산자를 처리하기에 적합하며 분석된 정보를 통해 사칙연산의 처리, 연산자 우선순위의 처리, 심볼릭 연산, 다항식, 방정식, 함수의 그래프 작성, 간단한 미적분 처리를 하는 알고리즘을 제안한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.4
• /
• pp.456-462
• /
• 2008

The classification is that a new data is classified into one of given classes and is one of the most generally used data mining techniques. Memory-Based Reasoning (MBR) is a reasoning method for classification problem. MBR simply keeps many patterns which are represented by original vector form of features in memory without rules for reasoning, and uses a distance function to classify a test pattern. If training patterns grows in MBR, as well as size of memory great the calculation amount for reasoning much have. NGE, FPA, and RPA methods are well-known MBR algorithms, which are proven to show satisfactory performance, but those have serious problems for memory usage and lengthy computation. In this paper, we propose DPA (Dynamic Partition Averaging) algorithm. it chooses partition points by calculating GINI-Index in the entire pattern space, and partitions the entire pattern space dynamically. If classes that are included to a partition are unique, it generates a representative pattern from partition, unless partitions relevant partitions repeatedly by same method. The proposed method has been successfully shown to exhibit comparable performance to k-NN with a lot less number of patterns and better result than EACH system which implements the NGE theory and FPA, and RPA.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.494-495
• /
• 2011

본 논문에서는 스마트 TV 시청시에 녹화하는 골프 동영상에서 오디오기반의 경계영역 검출를 이용하여 썸네일을 고속으로 생성하는 방법을 제안한다. 제안된 방법은 녹화되는 골프동영상의 인코딩된 오디오 정보로 부터 추출된 MDCT계수를 이용하여 온셋 구간 검출 및 오디오 세그먼테이션을 수행함으로써 골프 동영상을 6개의 오디오 클래스로 자동 분할한다. 분할된 오디오 세그먼트와 상응하는 비디오 프레임을 맵핑하여 골프 동영상의 썸네일을 생성한다. 제안된 오디오기반 경계영역 검출방법의 성능 측정 결과, 97.4%의 Recall과 96.85%의 Precision의 우수한 분류 성능을 나타내었다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2008.04a
• /
• pp.411-414
• /
• 2008

본 논문에서는 다중 출력을 가지는 퍼지 집합 기반 퍼지뉴럴네크워크(Fuzzy-Nueral Network; FNN)를 설계한다. 퍼지 집한 기반 퍼지뉴럴네트워크는 각 입력 변수에 따른 개별적인 입력 공간을 공간 분할함으로서 네트워크를 구성한다. 규칙의 전반부는 앞서 언급한 개별적인 입력 공간을 분할하여 표현하고, 규칙의 후반부는 다항식으로서 표현되며 오류역전파 알고리즘을 이용하여 연결가중치인 후반부 다항식의 계수를 학습한다. 또한, 각 입력에 대한 전반부 멤버쉽 함수의 정점과 학습률 및 모멤텀 계수를 유전자 알고리즘을 이용하여 최적 동조한다. 따라서 유전자 알고리즘을 이용하여 퍼지뉴럴네트워크를 최적 설계한다. 제안된 네트워크는 초고압 XLPE 케이블 절연접속함의 모의결함에 대해 부분방전 신호를 패턴인식한다. 부분방전 신호는 PRPDA 방법을 통해 200개의 입력 벡터와 4개의 출력 벡터를 가지며, 보이드 방전, 코로나 방전, 표면 방전, 노이즈의 4개 클래스를 분류한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.598-600
• /
• 2005

군집 유효화 평가란 기본적으로 클래스 (Class)에 대한 정보가 주어지지 않은 상태에서 다양한 입력 변수에 의해 발생되는 군집화의 결과들을 평가하여 그들 중에서 주어진 데이터 집합의 자연적인 분할 상태에 가장 적합한 결과를 찾는 기법을 말한다. 군집 유효화 평가에서 그 척도로 사용되는 것이 군집 유효화 지수이다. 본 논문에서는 우선 현존하는 다양한 군집 유효화 지수들 중에서 합 형식을 가지는 지수들을 다룬다. 구체적으로 이 지수들의 설계 원리와 각 지수들의 부합성 (Compliance) 분석한다. 다음으로 분석을 통해 밝혀진 그들의 단점을 보완할 수 있는 새로운 군집 유효화 지수들을 제안한다. 마지막으로 기존의 군집 유효화 지수들을 포함한 새로이 제안한 지수들의 성능을 실험 학습을 통해 평가한다.

• Journal of Advanced Navigation Technology
• /
• v.19 no.6
• /
• pp.484-491
• /
• 2015

Aerial scene is greatly increased by the introduction and supply of the image due to the growth of digital optical imaging technology and development of the UAV. It has been used as the extraction of ground properties, classification, change detection, image fusion and mapping based on the aerial image. In particular, in the image analysis and utilization of deep learning algorithm it has shown a new paradigm to overcome the limitation of the field of pattern recognition. This paper presents the possibility to apply a more wide range and various fields through the segmentation and classification of aerial scene based on the Deep learning(ConvNet). We build 4-classes image database consists of Road, Building, Yard, Forest total 3000. Each of the classes has a certain pattern, the results with feature vector map come out differently. Our system consists of feature extraction, classification and training. Feature extraction is built up of two layers based on ConvNet. And then, it is classified by using the Multilayer perceptron and Logistic regression, the algorithm as a classification process.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.3
• /
• pp.155-160
• /
• 2017

Recently, Deep learning has been used successfully to solve many recognition problems. It has many advantages over existing machine learning methods that extract feature points through hand-crafting. Deep neural networks for human activity recognition split video data into frame images, and then classify activities by analysing the connectivity of frame images according to the time. But it is difficult to apply to actual problems which has small-scale activity classes. Because this situations has a problem of overfitting and insufficient training data. In this paper, we defined 5 type of small-scale human activities, and classified them. We construct video database using 700 video clips, and obtained a classifying accuracy of 74.00%.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.11
• /
• pp.2751-2762
• /
• 1998

In this paper, a new priority assignment ploicy and concurrency control for improvement of transaction predictability and performance are proposed. We present a new priority assignment algorithm called classified priority assignment(CPA), which solves the defects of Earliest Deadline First(EDF) by using class and bucket, and deals with real-time transaction and time-sharing transaction effectively. Also, we present a new concurrency control policy called conditional optimistic concurrency control using lock. It uses optimistic concurrency control for improvement of predictability, and solves transaction conflict by considering priority and execution time of transaction to waste less system resource.