• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.7
• /
• pp.2449-2463
• /
• 2014

Hierarchical B-frame coding was introduced into H.264/SVC to provide temporal scalability and improve coding performance. A content analysis-based adaptive group of picture structure (AGS) can further improve the coding efficiency, but damages the inter-frame correlation and temporal scalability of hierarchical B-frame to different degrees. In this paper, we propose a group of pictures (GOP) adaptation coding method based on the positions of video cuts. First, the cut positions are accurately detected by the combination of motion coherence (MC) and mutual information (MI); then the GOP is adaptively and proportionately set by the analysis of MC in one scene. In addition, we propose a binary tree algorithm to achieve the temporal scalability of any size of GOP. The results for test sequences and real videos show that the proposed method reduces the bit rate by up to about 15%, achieves a performance gain of about 0.28-1.67 dB over a fixed GOP, and has the advantages of better transmission resilience and video summaries.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.10a
• /
• pp.251-254
• /
• 2003

In order for multidimensional infer structures to be integrated into an existing database management system, proper concurrency control methods that guarantee all isolation levels supported by the database management system. Several concurrency control methods have been proposed. They ran be classified into predicate locking based methods and granular locking based methods. Most of them are difficult to implement and ran not be applied to non-tree structured index structures. In this paper, we propose a new concurrency control method that guarantee all isolation levels. It is easy to implement and can be applied to any type of index structures. We implement the proposed method and existing methods, and perform various experiments to show the superiority of the proposed algorithm.

• The KIPS Transactions:PartD
• /
• v.12D no.4 s.100
• /
• pp.637-646
• /
• 2005

There are various problems while applying classification or clustering algorithm in that document classification which requires post processing or classification after getting as a web search result due to my keyword. Among those, two problems are severe. The first problem is the need to categorize the document with the help of the expert. And, the second problem is the long processing time the document classification takes. Therefore we propose a new method of web document clustering which can dramatically decrease the number of times to calculate a document similarity using the Transitive Closure Tree(TCT) and which is able to speed up the processing without loosing the precision. We also compare the effectivity of the proposed method with those existing algorithms and present the experimental results.

• Journal of Information Technology Services
• /
• v.15 no.1
• /
• pp.197-210
• /
• 2016

With the advent of text analytics, VOC (Voice of Customer) data become an important resource which provides the managers and marketing practitioners with consumer's veiled opinion and requirements. In other words, making relevant use of VOC data potentially improves the customer responsiveness and satisfaction, each of which eventually improves business performance. However, unstructured data set such as customers' complaints in VOC data have seldom used in marketing practices such as predicting service time as an index of service quality. Because the VOC data which contains unstructured data is too complicated form. Also that needs convert unstructured data from structure data which difficult process. Hence, this study aims to propose a prediction model to improve the estimation accuracy of the level of customer satisfaction by combining unstructured from textmining with structured data features in VOC. Also the relationship between the unstructured, structured data and service processing time through the regression analysis. Text mining techniques, sentiment analysis, keyword extraction, classification algorithms, decision tree and multiple regression are considered and compared. For the experiment, we used actual VOC data in a company.

• Journal of KIISE:Computer Systems and Theory
• /
• v.26 no.9
• /
• pp.1112-1125
• /
• 1999

최근 들어 멀티미디어를 지원하는 응용들의 서비스 품질 보장과 멀티캐스트 지원에 대한 요구가 증가되고 있으나 기존의 멀티캐스트 프로토콜로는 이러한 요구를 수용할 수 없는 문제가 발생하고 있다. 현재 인터넷에서 사용되고 있는 라우팅 메커니즘은 네트워크 자원 정보나 세션의 QoS 요구사항을 고려하지 않고 단순히 종단간의 연결에만 초점을 맞추고 있기 때문이다. 따라서 본 논문에서는 멀티캐스트 환경에서 서비스 품질보장을 지원하기 위한 새로운 프로토콜, LayeredQoS을 제안한다. 다중의 CP (Central Point)를 채택하고 각각의 CP에 적절한 QoS 레벨을 부여하여 사용함으로써 대역폭의 공유정도를 높일 뿐만 아니라 전체 트리 비용을 감소시켜 궁극적으로 네트워크 처리량이 증가되도록 하였다. 또한 시뮬레이션 방법을 통하여 다른 프로토콜보다 나은 성능을 가지는 것으로 평가하였다.Abstract Many emerging multimedia applications often require a guaranteed quality of service and multicast connection. But the traditional multicast protocol can't meet the needs since the routing mechanisms deployed in today's Internet are focused on connectivity, not on resource availability in the network or QoS requirements of flows. In this paper, we present LayeredQoS, a new QoS-based multicast routing algorithm. We adopt the multiple CPs(Central Points) and allocate QoS-levels for each CP in order to improve the degree of resource sharing and decrease the total tree cost, and then network throughput is increased. The proposed protocol is verified by simulations and it is shown that the performance of LayeredQoS is much better than the existing protocols.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.4 no.5
• /
• pp.799-818
• /
• 2010

In traditional unstructured P2P file sharing network, each peer establishes connections with a certain number of randomly chosen other peers. This would lead to redundant traffic and P2P network partition in mobile ad hoc network (MANET). We propose an approach to construct an efficient unstructured P2P overlay over MANET using underlying cluster-based routing (CBRP). One of the peers in the P2P network is used as a root-peer to connect all peers. Each peer maintains connection with physically closer peers such that it can reach the root-peer. The peer constructs a minimum-spanning tree consisting of itself, its directly connected neighbor peers and 2-hop away neighbor peers to remove far away redundant links and to build an overlay closer to the physical network. Due to on-demand nature of inter-cluster routing of CBRP, the positioning algorithm for MANET is used to retrieve the file by a peer from the source peer via shorter path in the physical network. We can show by simulation that our approach performs better in comparison with the existing approach.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.2
• /
• pp.785-804
• /
• 2017

Due to various factors such as postures, facial expressions and illuminations, face recognition by videos often suffer from poor recognition accuracy and generalization ability, since the within-class scatter might even be higher than the between-class one. Herein we address this problem by proposing a hierarchical cascaded classifier for video face recognition, which is a multi-layer algorithm and accounts for the misclassified samples plus their similar samples. Specifically, it can be decomposed into single classifier construction and multi-layer classifier design stages. In single classifier construction stage, classifier is created by clustering and the number of classes is computed by analyzing distance tree. In multi-layer classifier design stage, the next layer is created for the misclassified samples and similar ones, then cascaded to a hierarchical classifier. The experiments on the database collected by ourselves show that the recognition accuracy of the proposed classifier outperforms the compared recognition algorithms, such as neural network and sparse representation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.5
• /
• pp.1825-1839
• /
• 2015

The final draft of the latest video coding standard, High Efficiency Video Coding (HEVC), was approved in January 2013. The coding efficiency of HEVC surpasses its predecessor, H.264/MPEG-4 Advanced Video Coding (AVC), by using only half of the bitrate to encode the same sequence with similar quality. However, the complexity of HEVC is sharply increased compared to H.264/AVC. In this paper, a method is proposed to decrease the complexity of intra coding in HEVC. Early pruning and an early splitting strategy are applied to the quadtree structure of coding tree units (CTU) and residual quadtree (RQT). According to our experiment, when our method is applied to sequences from Class A to Class E, the coding time is decreased by 44% at the cost of a 1.08% Bjontegaard delta rate (BD-rate) increase on average.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.6
• /
• pp.1586-1605
• /
• 2012

With the prevalence of multimedia applications and the potential commercial usage of Mobile Ad hoc Networks (MANETs) in group communications, Quality of Service (QoS) support became a key requirement. Recently, some researchers studied QoS multicast issues in MANETs. Most of the existing QoS multicast routing protocols are designed with flat topology and small networks in mind. In this paper, we investigate the scalability problem of these routing protocols. In particular, a Position-Based QoS Multicast Routing Protocol (PBQMRP) has been developed. PBQMRP builds a source multicast tree guided by the geographic information of the mobile nodes, which helps in achieving more efficient multicast delivery. This protocol depends on the location information of the multicast members which is obtained using a location service algorithm. A virtual backbone structure has been proposed to perform this location service with minimum overhead and this structure is utilized to provide efficient packet transmissions in a dynamic mobile Ad hoc network environment. The performance of PBQMRP is evaluated by performing both quantitative analysis and extensive simulations. The results show that the used virtual clustering is very useful in improving scalability and outperforms other clustering schemes. Compared to On-Demand Multicast Routing Protocol (ODMRP), PBQMRP achieves competing packet delivery ratio and significantly lower control overhead.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.3725-3748
• /
• 2018

Text data distribution is often imbalanced. Imbalanced data is one of the challenges in text classification, as it leads to the loss of performance of classifiers. Many studies have been conducted so far in this regard. The proposed solutions are divided into several general categories, include sampling-based and algorithm-based methods. In recent studies, feature selection has also been considered as one of the solutions for the imbalance problem. In this paper, a novel one-sided feature selection known as probabilistic feature selection (PFS) was presented for imbalanced text classification. The PFS is a probabilistic method that is calculated using feature distribution. Compared to the similar methods, the PFS has more parameters. In order to evaluate the performance of the proposed method, the feature selection methods including Gini, MI, FAST and DFS were implemented. To assess the proposed method, the decision tree classifications such as C4.5 and Naive Bayes were used. The results of tests on Reuters-21875 and WebKB figures per F-measure suggested that the proposed feature selection has significantly improved the performance of the classifiers.