• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.938-958
• /
• 2024

Unsupervised Video Object Segmentation (UVOS) is a highly challenging problem in computer vision as the annotation of the target object in the testing video is unknown at all. The main difficulty is to effectively handle the complicated and changeable motion state of the target object and the confusion of similar background objects in video sequence. In this paper, we propose a novel deep Dual-stream Co-enhanced Network (DC-Net) for UVOS via bidirectional motion cues refinement and multi-level feature aggregation, which can fully take advantage of motion cues and effectively integrate different level features to produce high-quality segmentation mask. DC-Net is a dual-stream architecture where the two streams are co-enhanced by each other. One is a motion stream with a Motion-cues Refine Module (MRM), which learns from bidirectional optical flow images and produces fine-grained and complete distinctive motion saliency map, and the other is an appearance stream with a Multi-level Feature Aggregation Module (MFAM) and a Context Attention Module (CAM) which are designed to integrate the different level features effectively. Specifically, the motion saliency map obtained by the motion stream is fused with each stage of the decoder in the appearance stream to improve the segmentation, and in turn the segmentation loss in the appearance stream feeds back into the motion stream to enhance the motion refinement. Experimental results on three datasets (Davis2016, VideoSD, SegTrack-v2) demonstrate that DC-Net has achieved comparable results with some state-of-the-art methods.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.85-107
• /
• 2019

Online consumers browse products belonging to a particular product line or brand for purchase, or simply leave a wide range of navigation without making purchase. The research on the behavior and purchase of online consumers has been steadily progressed, and related services and applications based on behavior data of consumers have been developed in practice. In recent years, customization strategies and recommendation systems of consumers have been utilized due to the development of big data technology, and attempts are being made to optimize users' shopping experience. However, even in such an attempt, it is very unlikely that online consumers will actually be able to visit the website and switch to the purchase stage. This is because online consumers do not just visit the website to purchase products but use and browse the websites differently according to their shopping motives and purposes. Therefore, it is important to analyze various types of visits as well as visits to purchase, which is important for understanding the behaviors of online consumers. In this study, we explored the clustering analysis of session based on click stream data of e-commerce company in order to explain diversity and complexity of search behavior of online consumers and typified search behavior. For the analysis, we converted data points of more than 8 million pages units into visit units' sessions, resulting in a total of over 500,000 website visit sessions. For each visit session, 12 characteristics such as page view, duration, search diversity, and page type concentration were extracted for clustering analysis. Considering the size of the data set, we performed the analysis using the Mini-Batch K-means algorithm, which has advantages in terms of learning speed and efficiency while maintaining the clustering performance similar to that of the clustering algorithm K-means. The most optimized number of clusters was derived from four, and the differences in session unit characteristics and purchasing rates were identified for each cluster. The online consumer visits the website several times and learns about the product and decides the purchase. In order to analyze the purchasing process over several visits of the online consumer, we constructed the visiting sequence data of the consumer based on the navigation patterns in the web site derived clustering analysis. The visit sequence data includes a series of visiting sequences until one purchase is made, and the items constituting one sequence become cluster labels derived from the foregoing. We have separately established a sequence data for consumers who have made purchases and data on visits for consumers who have only explored products without making purchases during the same period of time. And then sequential pattern mining was applied to extract frequent patterns from each sequence data. The minimum support is set to 10%, and frequent patterns consist of a sequence of cluster labels. While there are common derived patterns in both sequence data, there are also frequent patterns derived only from one side of sequence data. We found that the consumers who made purchases through the comparative analysis of the extracted frequent patterns showed the visiting pattern to decide to purchase the product repeatedly while searching for the specific product. The implication of this study is that we analyze the search type of online consumers by using large - scale click stream data and analyze the patterns of them to explain the behavior of purchasing process with data-driven point. Most studies that typology of online consumers have focused on the characteristics of the type and what factors are key in distinguishing that type. In this study, we carried out an analysis to type the behavior of online consumers, and further analyzed what order the types could be organized into one another and become a series of search patterns. In addition, online retailers will be able to try to improve their purchasing conversion through marketing strategies and recommendations for various types of visit and will be able to evaluate the effect of the strategy through changes in consumers' visit patterns.

• Geomechanics and Engineering
• /
• v.15 no.2
• /
• pp.769-774
• /
• 2018

The growth of cities requires the construction of new tunnels close to the existing ones. Prediction and control of ground movement around the tunnel are important especially in urban area. The ground respond due to EPB (Earth Pressure Balance) pressure are investigated using the finite element method by ABAQUS in intersection of the triplet tunnels (Line 2, 3 and 4) of Mashhad Urban Railway in Iran. Special attention is paid to the effect of EPB pressure on the tunnel face displacement. The results of the analysis show that in EPB tunneling, surface settlement and face displacement is related to EPB pressure. Moreover, it is found that tunnel construction sequence is a great effect in face displacement value. For this study, this value in Line 4 where is excavated after line 3, is smaller than that line. In addition, the trend of the displacement curves are changed with the depth for all lines where is located in above and below, close to and above the centerline tunnel face for Line 2, 3 and 4, respectively. It is concluded that: (i) the surface settlement decreases with increasing EPB pressure on the tunnel face; (ii) at a constant EPB pressure, the tunnel face displacement values increase with depth. In addition, this is depended on the tunneling sequence; (iii) the trend of the displacement curves change with the depth.

• Journal of KIISE:Databases
• /
• v.33 no.7
• /
• pp.693-707
• /
• 2006

To improve performance using a multidimensional index in similar sequence matching, we transform a high-dimensional sequence to a low-dimensional sequence, and then construct a low-dimensional MBR that contains multiple transformed sequences. In this paper we propose a formal method that transforms a high-dimensional MBR itself to a low-dimensional MBR, and show that this method significantly reduces the number of lower-dimensional transformations. To achieve this goal, we first formally define the new notion of MBR-safe. We say that a transform is MBR-safe if a low-dimensional MBR to which a high-dimensional MBR is transformed by the transform contains every individual low-dimensional sequence to which a high-dimensional sequence is transformed. We then propose two MBR-safe transforms based on DFT and DCT, the most representative lower-dimensional transformations. For this, we prove the traditional DFT and DCT are not MBR-safe, and define new transforms, called mbrDFT and mbrDCT, by extending DFT and DCT, respectively. We also formally prove these mbrDFT and mbrDCT are MBR-safe. Moreover, we show that mbrDFT(or mbrDCT) is optimal among the DFT-based(or DCT-based) MBR-safe transforms that directly convert a high-dimensional MBR itself into a low-dimensional MBR. Analytical and experimental results show that the proposed mbrDFT and mbrDCT reduce the number of lower-dimensional transformations drastically, and improve performance significantly compared with the $na\"{\i}ve$ transforms. These results indicate that our MBR- safe transforms provides a useful framework for a variety of applications that require the lower-dimensional transformation of high-dimensional MBRs.

• Journal of Aquaculture
• /
• v.20 no.4
• /
• pp.248-254
• /
• 2007

Representative cDNA libraries were constructed from various tissue sources of Hemibarbus mylodon, an endangered freshwater fish species in Korea, for the mining of expressed sequence tags (ESTs). Randomized and non-normalized EST analysis was performed with 7 unidirectional cDNA libraries generated from brain, intestine, kidney, liver, muscle, ovary or testis. Of 3,383 ESTs in total, the number of singleton was 2,029, and 333 contigs containing 1,354 ESTs were assembled (percent of unigene = 70.0%). Abundantly expressed gene transcripts and broad clustering of putative gene function were tissue-specific in general, and the redundancy was also variable among those libraries. Over half of H. mylodon ESTs were matched with orthologues from other teleosts among which zebrafish gene sequences were the most frequent in those matches. This initial setting of EST libraries achieved in the present study would be a fundamental basis for the banking of gene resources from this endangered fish species.

• Molecules and Cells
• /
• v.23 no.3
• /
• pp.287-303
• /
• 2007

Expressed sequence tags (ESTs) and differentially expressed cDNAs from the self-fertilizing fish, Kryptolebias marmoratus were mined to develop alternative biomarkers for endocrine-disrupting chemicals (EDCs). 1,577 K. marmoratus cDNA clones were randomly sequenced from the 5'-end. These clones corresponded to 1,518 and 1,519 genes in medaka dbEST and zebrafish dbEST, respectively. Of the matched genes, 197 and 115 genes obtained Unigene IDs in medaka dbEST and zebrafish dbEST, respectively. Many of the annotated genes are potential biomarkers for environmental stresses. In a differential display reverse transcriptase-polymerase chain reaction (DD RT-PCR) study, 56 differential expressed genes were obtained from fish liver exposed to bisphenol A. Of these, 16 genes were identified after BLAST search to GenBank, and the annotated genes were mainly involved in catalytic activity and binding. The expression patterns of these 16 genes were validated by real-time RT-PCR of liver tissue from fish exposed to bisphenol A. Our findings suggest that expression of these 16 genes is modulated by endocrine disrupting chemicals, and therefore that they are potential biomarkers for environmental stress including EDCs exposure.

• Journal of Korea Society of Industrial Information Systems
• /
• v.16 no.2
• /
• pp.19-29
• /
• 2011

Due to the development of web technologies and the increasing use of smart devices such as smart phone, in recent various web services are widely used in many application fields. In this environment, the topic of supporting personalized and intelligent web services have been actively researched, and an analysis technique on a web-click stream generated from web usage logs is one of the essential techniques related to the topic. In this paper, for efficient analyzing a web-click stream of sequences, a sequential pattern mining technique is proposed, which satisfies the basic requirements for data stream processing and finds a refined mining result. For this purpose, a concept of interesting sequential patterns with a time-interval constraint is defined, which uses not on1y the order of items in a sequential pattern but also their generation times. In addition, A mining method to find the interesting sequential patterns efficiently over a data stream such as a web-click stream is proposed. The proposed method can be effectively used to various computing application fields such as E-commerce, bio-informatics, and USN environments, which generate data as a form of data streams.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10b
• /
• pp.298-300
• /
• 2004

기존의 생물정보학 연구는 전체 서열들의 매칭을 통한 상동성 연구에 중점을 두고 진행되어 왔다 최근에 서열 데이터베이스의 급격한 증가와 게놈 정보가 축적됨에 따라 서열로부터 다양한 정보를 얻기 위해 서열 데이터 분석에 마이닝 기법을 접목시키고자 하는 다양한 기술들이 제안되고 있다. 단백질과 DNA의 서열 비교는 생물정보학의 기본 작업 기운데 하나이다. 신속하고 자동화 된 서열 비교 능력은 새로운 서열에 대한 기능 판별 및 분석 등 모든 작업을 용이하게 한다 본 논문에서는 동종의 단백질 서열들을 다중 정렬하여 일치하는 구간을 찾아내고, 그 구간에서 아미노산 코드와 위치정보를 이용해 동종 서열들 간의 특정한 패턴 규칙을 찾아내고, 새로운 서열에서 어떤 서열 필턴 특징이 발생하는지를 찾아냄으로써 서얼을 분류하는 방법을 제안한다.

• Proceedings of the Korean Society of Sericultural Science Conference
• /
• 2003.10a
• /
• pp.23-23
• /
• 2003

We made use of 81, 635 expressed sequence tags (ESTs) derived from 12 different cDNA libraries of Bombyx mori to identify high-quality candidate single nucleotide polymorphisms (SNPs). By PHRAP assembling, we obtained 12, 980 contigs containing 11, 531 contigs assembled by more than one reads. From 117 contig sequences, which were assembled by 1, 576 high-quality reads base-called with PHRED, we identified 101 candidate SNPs and 27 single base insertions/deletions based on a neighborhood quality standard(NQS) of SNP. (omitted)

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.224-227
• /
• 2003

The Intrsuion Detecion Systems(IDS) are required the accuracy, the adaptability, and the expansion in the information society to be changed quickly. Also, it is required the more structured, and intelligent IDS to protect the resource which is important and maintains a secret in the complicated network environment. The research has the purpose to build the model for the intelligent IDS, which creates the intrusion patterns. The intrusion pattern has extracted from the vast amount of data. To manage the large size of data accurately and efficiently, the link analysis and sequence analysis among the data mining techniqes are used to build the model creating the intrusion patterns. The model is consist of "Time based Traffic Model", "Host based Traffic Model", and "Content Model", which is produced the different intrusion patterns with each model. The model can be created the stable patterns efficiently. That is, we can build the intrusion detection model based on the intelligent systems. The rules prodeuced by the model become the rule to be represented the intrusion data, and classify the normal and abnormal users. The data to be used are KDD audit data.