• International Journal of Naval Architecture and Ocean Engineering
• /
• 제6권3호
• /
• pp.598-625
• /
• 2014

To support the procedure for determining an optimal liquefaction cycle for FLNG FEED, an ontological modeling method which can automatically generate various alternative liquefaction cycles were carried out in this paper. General rules in combining equipment are extracted from existing onshore liquefaction cycles like C3MR and DMR cycle. A generic relational model which represents whole relations of the plant elements has all these rules, and it is expressed by using the system entity structure (SES), an ontological framework that hierarchically represents the elements of a system and their relationships. By using a process called pruning which reduces the SES to a candidate, various alternative relational models of the liquefaction cycles can be automatically generated. These alternatives were provided by XML-based formats, and they can be used for choosing an optimal liquefaction cycle on the basis of the assessments such as process simulation and reliability analysis.

• Journal of Information Processing Systems
• /
• 제17권5호
• /
• pp.892-904
• /
• 2021

An image semantic segmentation model is proposed based on improved ENet network in order to achieve the low accuracy of image semantic segmentation in complex environment. Firstly, this paper performs pruning and convolution optimization operations on the ENet network. That is, the network structure is reasonably adjusted for better results in image segmentation by reducing the convolution operation in the decoder and proposing the bottleneck convolution structure. Squeeze-and-excitation (SE) module is then integrated into the optimized ENet network. Small-scale targets see improvement in segmentation accuracy via automatic learning of the importance of each feature channel. Finally, the experiment was verified on the public dataset. This method outperforms the existing comparison methods in mean pixel accuracy (MPA) and mean intersection over union (MIOU) values. And in a short running time, the accuracy of the segmentation and the efficiency of the operation are guaranteed.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2018년도 하계학술대회
• /
• pp.175-177
• /
• 2018

This paper proposes an algorithm to speed up block structure partition of quad tree plus binary tree (QTBT) in Joint Exploration Test Model (JEM) encoder. The proposed fast encoding of QTBT block partition employs three spatially neighbor coded blocks, such as left, top-left, and top of current block, to early terminate QTBT block structure pruning. The propose algorithm is organized based on statistical similarity of those spatially neighboring blocks, such as block depths and coded block types, which are coded with overlapped block motion compensation (OBMC) and adaptive multi transform (AMT). The experimental results demonstrate about 30% encoding time reduction with 1.3% BD-rate loss on average compared to the anchor JEM-7.1 software under random access configuration.

• 전자통신동향분석
• /
• 제37권5호
• /
• pp.44-53
• /
• 2022

The Internet of Things (IoT) is growing exponentially, with the number of IoT devices multiplying annually. Accordingly, the paradigm is changing from cloud computing to edge computing and even tiny edge computing because of the low latency and cost reduction. Machine learning is also shifting its role from the cloud to edge or tiny edge according to the paradigm shift. However, the fragmented and resource-constrained features of IoT devices have limited the development of artificial intelligence applications. Edge MLaaS (Machine Learning as-a-Service) has been studied to easily and quickly adopt machine learning to products and overcome the device limitations. This paper briefly summarizes what Edge MLaaS is and what element of research it requires.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2022년도 하계학술대회
• /
• pp.1226-1228
• /
• 2022

FHD 이상을 넘어선 UHD급의 고해상도 동영상 콘텐츠의 수요 및 공급이 증가함에 따라 전반적인 산업 영역에서 네트워크 자원을 효율적으로 이용하여 동영상 콘텐츠를 제공하는 데에 관심을 두게 되었다. 기존 방법을 통한 bi-cubic, bi-linear interpolation 등의 방법은 딥 러닝 기반의 모델에 비교적 인풋 이미지의 특징을 잘 잡아내지 못하는 결과를 나타내었다. 딥 러닝 기반의 초 해상화 기술의 경우 기존 방법과 비교 시 연산을 위해 더 많은 자원을 필요로 하므로, 이러한 사용 조건에 따라 본 논문은 초 해상화가 가능한 딥 러닝 모델을 경량화 기법을 사용하여 기존에 사용된 모델보다 비교적 적은 자원을 효율적으로 사용할 수 있도록 연구 개발하는 데 목적을 두었다. 연구방법으로는 structure pruning을 이용하여 모델 자체의 구조를 경량화 하였고, 학습을 진행해야 하는 파라미터를 줄여 하드웨어 자원을 줄이는 연구를 진행했다. 또한, Residual Network의 개수를 줄여가며 PSNR, LPIPS, tOF등의 결과를 비교했다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권5호
• /
• pp.1433-1449
• /
• 2023

In recent years, the rapid development of social networks has led to a rapid increase in the amount of information available on the Internet, which contains a large amount of sensitive information related to pornography, politics, and terrorism. In the aspect of sensitive image detection, the existing machine learning algorithms are confronted with problems such as large model size, long training time, and slow detection speed when auditing and supervising. In order to detect sensitive images more accurately and quickly, this paper proposes a multiclassification sensitive image detection method based on lightweight Convolutional Neural Network. On the basis of the EfficientNet model, this method combines the Ghost Module idea of the GhostNet model and adds the SE channel attention mechanism in the Ghost Module for feature extraction training. The experimental results on the sensitive image data set constructed in this paper show that the accuracy of the proposed method in sensitive information detection is 94.46% higher than that of the similar methods. Then, the model is pruned through an ablation experiment, and the activation function is replaced by Hard-Swish, which reduces the parameters of the original model by 54.67%. Under the condition of ensuring accuracy, the detection time of a single image is reduced from 8.88ms to 6.37ms. The results of the experiment demonstrate that the method put forward has successfully enhanced the precision of identifying multi-class sensitive images, significantly decreased the number of parameters in the model, and achieved higher accuracy than comparable algorithms while using a more lightweight model design.

• Industrial Engineering and Management Systems
• /
• 제9권2호
• /
• pp.131-140
• /
• 2010

Biclustering is a method of finding meaningful subsets of objects and attributes simultaneously, which may not be detected by traditional clustering methods. It is popularly used for the analysis of microarray data representing the expression levels of genes by conditions. Usually, biclustering algorithms do not consider a sequential relation between attributes. For time series data, however, bicluster solutions should keep the time sequence. This paper proposes a new biclustering algorithm for time series data by modifying the plaid model. The proposed algorithm introduces a parameter controlling an interval between two selected time points. Also, the pruning step preventing an over-fitting problem is modified so as to eliminate only starting or ending points. Results from artificial data sets show that the proposed method is more suitable for the extraction of biclusters from time series data sets. Moreover, by using the proposed method, we find some interesting observations from real-world time-course microarray data sets and apartment price data sets in metropolitan areas.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권12호
• /
• pp.5782-5799
• /
• 2018

With the development of GPS and the popularity of mobile devices with positioning capability, collecting massive amounts of trajectory data is feasible and easy. The daily trajectories of moving objects convey a concise overview of their behaviors. Different social roles have different trajectory patterns. Therefore, we can identify users or groups based on similar trajectory patterns by mining implicit life patterns. However, most existing daily trajectories mining studies mainly focus on the spatial and temporal analysis of raw trajectory data but missing the essential semantic information or behaviors. In this paper, we propose a novel trajectory semantics calculation method to identify groups that have similar behaviors. In our model, we first propose a fast and efficient approach for stay regions extraction from daily trajectories, then generate semantic trajectories by enriching the stay regions with semantic labels. To measure the similarity between semantic trajectories, we design a semantic similarity measure model based on spatial and temporal similarity factor. Furthermore, a pruning strategy is proposed to lighten tedious calculations and comparisons. We have conducted extensive experiments on real trajectory dataset of Geolife project, and the experimental results show our proposed method is both effective and efficient.

• 한국컴퓨터정보학회논문지
• /
• 제9권4호
• /
• pp.109-116
• /
• 2004

본 논문은 여러 옷감 조각들을 이용하여 가상의 3차원 인체 모델에 옷을 입히기 위한 의복 시뮬레이션 시스템을 제안한다. 본 논문에서 의복은 서로 꿰매지는 2차원 재단 패턴으로 구성된다. 제안된 시스템은 3차원 인체 모델 파일과 2차원 재단 패턴 파일을 읽어 들인 다음에 질량-스프링 모델에 기반한 물리적 시뮬레이션에 의해 의복을 착용한 3D모델을 생성한다. 본 논문의 시스템은 사실적인 시뮬레이션을 위하여 인체 모델을 구성하는 삼각형과 의복을 구성하는 삼각형 사이의 충돌을 검사하고 반응 처리를 수행하였다. 인체를 구성하는 삼각형의 수가 매우 많으므로, 이러한 충돌 검사 및 반응 처리는 많은 시간을 필요로 한다. 이 문제를 해결하기 위하여, 본 논문에서는 공간 분할 기법을 이용하여 충돌 검사 및 반응 처리 수를 줄이는 방법을 제안한다. 실험 결과에 의하면 본 논문의 시스템은 사실적인 영상을 생성할 수 있었고 수초 이내에 가상 인체 모델에 의복을 입힐 수 있었다.

• 정보처리학회논문지D
• /
• 제15D권5호
• /
• pp.621-628
• /
• 2008

오늘날 대부분의 기업들은 외부상황에 신속하게 비즈니스를 바꿀 수 있도록 하는 온디맨드 비즈니스 (On-demand business)를 구현하기 위해 IT 시스템의 유연성을 필요로 한다. 서비스 지향 아키텍처(Service Oriented Architecture: SOA)는 온디맨드 운영환경에서의 비즈니스 유연성을 가능하게 하는 인프라스트럭처 (infrastructure)를 제공한다. 오늘날의 이러한 요구사항을 충족시키기 위하여 SOA 애플리케이션 개발에 맞게 비즈니스 프로세스의 유연성을 확보하고 재사용을 증진시키기 위한 접근법이 필요하다. 그러므로 본 논문에서는 소프트웨어 프로덕트 라인 방법의 가변성 분석 기법을 사용하여 비즈니스 프로세스 패밀리 (family)에서 나타날 수 있는 가변성을 분석하고 이를 명시적으로 비즈니스 프로세스 패밀리 모델 (Business Process Family Model: BPFM)로 표현하는 방법을 제시한다. 또한 이 방법의 사용을 지원하기 위해 개발한 도구에 대해 설명한다. 이는 BPFM을 모델링하고 BPFM으로부터 가변성 결정과 가지치기 과정을 거쳐 자동 비즈니스 프로세스 모델 (Business Process Model: BPM)을 생성하는 기능들을 가지고 있다. 본 논문에서 제시하는 비즈니스 프로세스 패밀리의 가변성 분석을 통하여 비즈니스와 이를 지원하는 IT 시스템은 비즈니스 환경의 변화에 신속하게 대응할 수 있게 된다.