Frequent Traversal Patterns Research Articles

Mining Simple Path Traversal Patterns in Knowledge Graph

The data mining has remained a subject of unfailing charm for research. The knowledge graph is rising and showing infinite life force and strong developing potential in recent years, where it is observed that acyclic knowledge graph has capacity for enhancing usability. Though the development of knowledge graphs has provided an ample scope for appearing the abilities of data mining, related researches are still insufficient. In this paper, we introduce path traversal patterns mining to knowledge graph. We design a novel simple path traversal pattern mining framework for improving the representativeness of result. A divide-and-conquer approach of combining each path is proposed to discover the most frequent traversal patterns in knowledge graph. To support the algorithm, we design a linked list structure indexed by the length of sequences with handy operations. The correctness of algorithm is proven. Experiments show that our algorithm reaches a high coverage with low output amounts compared to existing frequent sequence mining algorithms.

Efficient Reduction of Access Latency through Object Correlations in Virtual Environments

Object correlations are common semantic patterns in virtual environments. They can be exploited to improve the effectiveness of storage caching, prefetching, data layout, and disk scheduling. However, we have little approaches for discovering object correlations in VE to improve the performance of storage systems. Being an interactive feedback-driven paradigm, it is critical that the user receives responses to his navigation requests with little or no time lag. Therefore, we propose a class of view-based projection-generation method for mining various frequent sequential traversal patterns in the virtual environments. The frequent sequential traversal patterns are used to predict the user navigation behavior and, through clustering scheme, help to reduce disk access time with proper patterns placement into disk blocks. Finally, the effectiveness of these schemes is shown through simulation to demonstrate how these proposed techniques not only significantly cut down disk access time, but also enhance the accuracy of data prefetching.

Efficient algorithms for incremental Web log mining with dynamic thresholds

With the fast increase in Web activities, Web data mining has recently become an important research topic and is receiving a significant amount of interest from both academic and industrial environments. While existing methods are efficient for the mining of frequent path traversal patterns from the access information contained in a log file, these approaches are likely to over evaluate associations. Explicitly, most previous studies of mining path traversal patterns are based on the model of a uniform support threshold, where a single support threshold is used to determine frequent traversal patterns without taking into consideration such important factors as the length of a pattern, the positions of Web pages, and the importance of a particular pattern, etc. As a result, a low support threshold will lead to lots of uninteresting patterns derived whereas a high support threshold may cause some interesting patterns with lower supports to be ignored. In view of this, this paper broadens the horizon of frequent path traversal pattern mining by introducing a flexible model of mining Web traversal patterns with dynamic thresholds. Specifically, we study and apply the Markov chain model to provide the determination of support threshold of Web documents; and further, by properly employing some effective techniques devised for joining reference sequences, the proposed algorithm dynamic threshold miner (DTM) not only possesses the capability of mining with dynamic thresholds, but also significantly improves the execution efficiency as well as contributes to the incremental mining of Web traversal patterns. Performance of algorithm DTM and the extension of existing methods is comparatively analyzed with synthetic and real Web logs. It is shown that the option of algorithm DTM is very advantageous in reducing the number of unnecessary rules produced and leads to prominent performance improvement.

MFTPM: Maximum Frequent Traversal Pattern Mining with Bidirectional Constraints

An important application of sequential mining technique is maximal frequent traversal pattern mining, since users' traversal pattern and motivation are latent in session sequence at some time segment. In this paper, a Frequent Traversal Pattern Tree structure with dwell time (FTP-Tree) is designed to store, compress the session database, and simplify the configuration of dwell time thresholds during mining. A novel algorithm based on bidirectional constraints, called Maximal Frequent Traversal Pattern Mining (MFTPM) is presented, which traverses quickly FTP-Tree and discovers maximal frequent traversal patterns from the session sequences. Experimental results show that MFTPM can significantly reduce the average execution time and the storage space for mining maximal frequent traversal patterns. Our performance study shows that MFTPM performs muth better than previous approaches in the time constraint environment.

An incremental data mining algorithm for discovering web access patterns

Mining frequent traversal patterns is to discover the reference paths traversed by a sufficient number of users from web logs, which can be used for prefetching and suggestion for web users. However, the discovered frequent traversal patterns may become invalid or inappropriate when the user behaviours are changed. In this paper, we propose an incremental updating technique to maintain the discovered frequent traversal patterns when the traversal paths are inserted into or deleted from the database. The experimental results show that our algorithms are more efficient than other algorithms for the maintenance of mining frequent traversal patterns.

WebPR :빈발 순회패턴 탐사에 기반한 동적 웹페이지 추천 알고리즘

월드 와이드 웹(World-Wide Web)은 가장 커다란 분산된 정보저장소로서 계속하여 빠른 속도로 성장해왔다. 그러나 비록 웹이 빠른 속도로 성장하고 있다 할지라도, 웹의 정보를 읽고 이해하는 데는 본질적으로 한계가 있다. 웹 사용자 입장에서 보면 웹의 정보 폭발, 꾸준하게 변화하는 환경, 사용자 요구에 대한 이해 부족 둥으로 오히려 혼란을 겪을 수 있다. 웹의 이러한 환경에서 사용자의 순회패턴(traversal patterns)을 탐사하는 것은 시스템 설계나 정보서비스 제공 측면에서 중요한 문제이다. 순회패턴 탐사에 관한 기존의 연구들은 세션(sessions)에 나타나는 페이지들간의 연관성 정보를 충분히 활용하지 못한다. 본 논문에서는 세션에 나타나는 페이지들간의 연관성 정보를 활용하여 빈발 k-페이지집합을 탐사하고, 이를 기반으로 하여 추천 페이지집합을 생성함으로써 효율적인 웹 정보서비스를 제공할 수 있는 Web Page Recommend(WebPR) 알고리즘들을 제안한다. 제안한 WebPR 알고리즘은 웹 사이트를 방문한 사용자에게 추천 페이지집합을 포함하는 새로운 페이지뷰(pageview)를 제공함으로써 궁극적으로 찾고자하는 목표 페이지에 효과적으로 접근할 수 있도록 해준다. 기존 연구들과의 가장 큰 차이점은 페이지들간의 연관성 정보를 활용하는 방법들을 일관성 있게 고려하고 있다는 점과 가장 효율적인 트리모델을 제안한다는 점이다. 두개의 실제 웹로그(Weblog) 데이터에 대한 실험은 제안한 방법이 기존의 방법들보다 성능이 우수함을 보여준다. The World-Wide Web is the largest distributed Information space and has grown to encompass diverse information resources. However, although Web is growing exponentially, the individual's capacity to read and digest contents is essentially fixed. From the view point of Web users, they can be confused by explosion of Web information, by constantly changing Web environments, and by lack of understanding needs of Web users. In these Web environments, mining traversal patterns is an important problem in Web mining with a host of application domains including system design and Information services. Conventional traversal pattern mining systems use the inter-pages association in sessions with only a very restricted mechanism (based on vector or matrix) for generating frequent k-Pagesets. We develop a family of novel algorithms (termed WebPR - Web Page Recommend) for mining frequent traversal patterns and then pageset to recommend. Our algorithms provide Web users with new page views, which Include pagesets to recommend, so that users can effectively traverse its Web site. The main distinguishing factors are both a point consistently spanning schemes applying inter-pages association for mining frequent traversal patterns and a point proposing the most efficient tree model. Our experimentation with two real data sets, including Lady Asiana and KBS media server site, clearly validates that our method outperforms conventional methods.

An Efficient Approach for Analyzing User Behaviors in a Web-Based Training Environment

Mining frequent traversal patterns is to discover the consecutive reference paths traversed by a sufficient number of users from Web logs in a Web environment where users can travel from one object to another through the corresponding hyperlinks. Previous approaches for mining frequent traversal patterns only consider the forward references, such that the information about backward references will be lost. In this paper, we propose an efficient algorithm to discover the non-simple frequent traversal patterns. The non-simple frequent traversal patterns include forward and backward references, and are used to suggest potentially interesting traversal path to the users, which are useful, especially, in a Web-based training environment. The experimental results show that the discovered patterns can present the complete browsing paths traversed by most of the users and our algorithm outperforms other algorithms in discovered information and execution times.

익명 웹로그 탐사에 기반한 동적 링크 추천

웹 공간(Webspace)에서 사용자의 순회패턴을 포착하는 것을 ‘순회패턴 탐사(mining traversal patterns)’라 한다. 순회패턴 탐사에서는 사용자가 원하는 정보를 탐색하기 위해 정보 제공 서비스에 따라 이동하기 때문에 객체(예 : URL)의 내용보다는 위치 때문에 방문될 수도 있는 독특한 특징을 가진다. 따라서 순회패턴 데이터로부터 의미있는 정보를 추출하는 작업의 복잡도를 크게 증가시킨다. 그러나 이러한 정보 제공 서비스의 질을 개선하기 위한 요구가 증가하고 있기 때문에 데이터 탐사 분야에서 순회패턴 탐사 문제는 최근 중요한 문제로 대두되고 있다. 본 논문에서는 빈발 순회패턴을 탐사하여 웹 사이트 상에서 추천을 수행하는 동적 링크 추천(Dynamic Link Recommendation : DLR) 알고리즘을 제안한다. 제안한 DLR 알고리즘은 방대한 자료를 포함하고 있는 대부분의 웹 사이트에 효과적으로 적용될 수 있다. 두 개의 실제 웹 사이트에 적용한 실험 결과는 제안한 방법의 성능이 우수함을 보여준다. In Webspace, mining traversal patterns is to understand user's path traversal patterns. On this mining, it has a unique characteristic which objects (for example, URLs) may be visited due to their positions rather than contents, because users move to other objects according to providing information services. As a consequence, it becomes very complex to extract meaningful information from these data. Recently discovering traversal patterns has been an important problem in data mining because there has been an increasing amount of research activity on various aspects of improving the quality of information services. This paper presents a Dynamic Link Recommendation (DLR) algorithm that recommends link sets on a Web site through mining frequent traversal patterns. It can be employed to any Web site with massive amounts of data. Our experimentation with two real Weblog data clearly validate that our method outperforms traditional method.