User Access Patterns Research Articles

Workload-Based Ordering of Multi-Dimensional Data

Transforming multi-dimensional data into a one-dimensional sequence using space-filling curves such as the Hilbert curve, the Gray curve, and the Z-curve has been studied extensively. These techniques are not sensitive to data or workload skewness, however, in practice, user-access patterns and data distributions are often very skewed in high dimensional space. It is desirable to produce a one-dimensional sequence which keeps the multi-dimensional grid cells that are queried together close to each other. This generates sequences with higher spatial locality. We propose a workload-based approach to produce one-dimensional ordering from multi-dimensional data in this paper. An extensive experimental evaluation suggests that our approach produces a high quality ordering sequence which outperforms the existing state-of-the-art Hilbert curve by a factor of 4.84, the Gray curve by a factor of 6.66, and the Z-curve by a factor of 7.26 for the number of subsequences used to answer a query; and for IO time, it outperforms the Hilbert curve by a factor of 2.20, the Gray curve by a factor of 2.25, and the Z-curve by 2.38.

Prefetching Scheme for Massive Spatiotemporal Data in a Smart City

Employing user access patterns to develop a prefetching scheme can effectively improve system I/O performance and reduce user access latency. For massive spatiotemporal data, traditional pattern mining methods fail to directly reflect the spatiotemporal correlation and transition rules of user access, resulting in poor prefetching performance. This paper proposed a prefetching scheme based on spatial-temporal attribute prediction, named STAP. It maps the history of user access requests to the spatiotemporal attribute domain by analyzing the characteristics of spatiotemporal data in a smart city. According to the spatial locality and time stationarity of user access, correlation analysis is performed and variation rules are identified for the history of user access requests. Further, the STAP scheme mines the user access patterns and constructs a predictive function to predict the user's next access request. Experimental results show that the prefetching scheme is simple yet effective; it achieves a prediction accuracy of 84.3% for access requests and reduces the average data access response time by 44.71% compared with the nonprefetching scheme.

An Efficient Agglomerative Clustering Algorithm for Web Navigation Pattern Identification

Web log mining is analysis of web log files with web page sequences. Discovering user access patterns from web access are necessary for building adaptive web servers, to improve e-commerce, to carry out cross-marketing, for web personalization, to predict web access sequence etc. In this paper, a new agglomerative clustering technique is proposed to identify users with similar interest, and to determine the motivation for visiting a website. Using this approach, web usage mining is done through different stages namely data cleaning, preprocessing, pattern discovery and pattern analysis. Results are given to explain how this approach produces tight usage clusters than the existing web usage mining techniques. Rather than traditional distance based clustering, the similarity measure is considered during clustering process in order to reduce computational complexity. This paper also deals with the problem of assessing the quality of user session clusters and cluster validity is measured by using statistical test, which measures the distances of clusters distributions to infer their dissimilarity and distinguish level. Using such statistical measures, it is proved that cluster accuracy is improved to the extent of 0.83, over existing k-means clustering with validity measure 0.26, FCM (Fuzzy C Means) clustering with validity measure 0.56. Rough set based clustering with validity measure 0.54 Generation of dense clusters is essential for finding interesting patterns needed for further mining and analysis.

A fuzzy neural network based framework to discover user access patterns from web log data

Clustering data from web user sessions is extensively applied to extract customer usage behavior to serve customized content to individual users. Due to the human involvement, web usage data usually contain noisy, incomplete and vague information. Neural networks have the capability to extract embedded knowledge in the form of user session clusters from the huge web usage data. Moreover, they provide tolerance against imperfect and noisy data. Fuzzy sets are another popular tool utilized for handling uncertainty and vagueness hidden in the data. In this paper a fuzzy neural clustering network (FNCN) based framework is proposed that makes use of the fuzzy membership concept of fuzzy c-means (FCM) clustering and the learning rate of a modified self-organizing map (MSOM) neural network model and tries to minimize the weighted sum of the squared error. FNCN is applied to cluster the users’ web access data extracted from the web logs of an educational institution’s proxy web server. The performance of FNCN is compared with FCM and MSOM based clustering methods using various validity indexes. Our results show that FNCN produces better quality of clusters than FCM and MSOM.

Incremental sequential pattern mining algorithms of Web site access in grid structure database

Sequential pattern mining is a process of knowledge discovery which finds the frequent subsequence as a mode from the sequence database. Web log database is typically dynamic. Web log records are generated constantly, and user access patterns will change accordingly. This study focused on taking advantage of the dynamic characteristics of the Web access database, delivering a fast and efficient incremental mining algorithm. An IncWTP algorithm suitable for Web access sequence mode is developed to handle non-simple path with dynamic data storage structure, and detect and delete the failed sequence data timely.

Ranking Pages of Clustered Users using Weighted Page Rank Algorithm with User Access Period

The World Wide Web comprises billions of web pages and a tremendous amount of information accessible inside of web pages. To recover obliged data from the World Wide Web, search engines perform number of tasks in light of their separate structural planning. The point at which a user gives a query to the search engine, it commonly returns a bulky number of pages related to the user's query. To backing the users to explore in the returned list, different ranking techniques are connected on the search results. The vast majority of the ranking calculations, which are given in the related work, are either link or content based. The existing works don't consider user access patterns. In this paper, a page ranking approach of Weighted Page Rank Score Algorithm taking user access is being conceived for search engines, which deals with the premise of weighted page rank method and considers user access period of web pages into record. For this reason, the web users are clustered based on the Particle Swarm Optimization (PSO) approach. From those groups, the pages are ranked by improving the weighted page rank approach with usage based parameter of user access period. This calculation is utilized to discover more applicable pages as per user's query. In this way, this idea is extremely helpful to show the most important pages on the uppermost part of the search list on the principle of user searching behavior, which shrinks the search space on a huge scale.

Spatio-Temporal Analysis of Passive Consumption in Internet Media

Internet users can be classified as two types: (a) active users —actively contribute to blogs, publish opinions, write comments in Youtube, tweet messages, etc. and (b) passive consumers who only consume Internet information without contributing to it. While the majority of current social media research deals with active user analysis, there is very little work in understanding the dynamics of passive consumers and their influence. Our global scale Internet measurement of user access patterns of a diverse set of Internet media services indicates conclusively that majority of consumers are passive. In this paper, we develop a spatio-temporal mathematical model and the corresponding stochastic analysis to understand the passive consumer dynamics. Both discrete and continuous time analysis are presented. We also show how the analysis can be used to identify spatial points of influence, i.e., spatial locations that have maximum expertise or influence on a topic. The analysis takes into account, the initial level of consumption at each spatial location and the influence of different passive consumers at different geographic locations on each other. The effect of information noise is taken into account to derive fundamental limits of passive information consumption. Theoretical results are verified using real Internet measurement data. The large scale data have been made available for other researchers.

An Effective User Profiling Data Structure for Dynamic License

In this work, we defined and constructed an effective user profiling data structure for the dynamic license of digital contents. The user profiling data structure can be deduced from the analysis on existing digital music license purchase pattern included in the user profiling data. It is designed to trace the user's license purchase pattern and can be used to analyze and trace the user's license access pattern with the history based aged-MRU algorithm. Since dynamic license has more complicate features on describing license actions and relations with other persons than static license, the user profiling data structure also should have more member items in metadata. By comparing the difference of static license features with dynamic license features, we can validate the user profiling data structure for dynamic license and can get the effectiveness of the data structure on license purchase prediction of the dynamic license as like the static license. In order to construct the user profiling data structure for the dynamic license, several metadata items should be added to the user profiling data structure for the static license. In this work, we proposed a kind of simple user profiling data structure for dynamic license and evaluated its effectiveness of the next user license purchase prediction with the aged-MRU algorithm. The evaluation results show that the proposed user profiling data structure for the dynamic license can present the related metadata to the license purchase and can predict the next license purchase activity in dynamic license environment.

REGIONAL WEBGIS USER ACCESS PATTERNS BASED ON A WEIGHTED BIPARTITE NETWORK

Abstract. With the rapid development of geographic information services, Web Geographic Information Systems (WebGIS) have become an indispensable part of everyday life; correspondingly, map search engines have become extremely popular with users and WebGIS sites receive a massive volume of requests for access. These WebGIS users and the content accessed have regional characteristics; to understand regional patterns, we mined regional WebGIS user access patterns based on a weighted bipartite network. We first established a weighted bipartite network model for regional user access to a WebGIS. Then, based on the massive user WebGIS access logs, we clustered geographic information accessed and thereby identified hot access areas. Finally we quantitatively analyzed the access interests of regional users and the visitation volume characteristics of regional user access to these hot access areas in terms of user access permeability, user usage rate, and user access viscosity. Our research results show that regional user access to WebGIS is spatially aggregated, and the hot access areas that regional users accessed are associated with specific periods of time. Most regional user contact with hot accessed areas is variable and intermittent but for some users, their access to certain areas is continuous as it is associated with ongoing or recurrent objectives. The weighted bipartite network model for regional user WebGIS access provides a valid analysis method for studying user behaviour in WebGIS and the proposed access pattern exhibits access interest of regional user is spatiotemporal aggregated and presents a heavy-tailed distribution. Understanding user access patterns is good for WebGIS providers and supports better operational decision-making, and helpful for developers when optimizing WebGIS system architecture and deployment, so as to improve the user experience and to expand the popularity of WebGIS.

Efficient 3-D Scene Prefetching From Learning User Access Patterns

Rendering large-scale 3-D scenes on a thin client is attracting increasing attention with the development of the mobile Internet. Efficient scene prefetching to provide timely data with a limited cache is one of the most critical issues for remote 3-D data scheduling in networked virtual environment applications. Existing prefetching schemes predict the future positions of each individual user based on user traces. In this paper, we investigate scene content sequences accessed by various users instead of user viewpoint traces and propose a user access pattern-based 3-D scene prefetching scheme. We make a relationship graph-based clustering to partition history user access sequences into several clusters and choose representative sequences from among these clusters as user access patterns. Then, these user access patterns are prioritized by their popularity and users’ personal preference. Based on these access patterns, the proposed prefetching scheme predicts the scene contents that will most likely be visited in the future and delivers them to the client in advance. The experiment results demonstrate that our user access pattern-based prefetching approach achieves a high hit ratio and outperforms the prevailing prefetching schemes in terms of access latency and cache capacity.

Intelligent Web Information Retrieval based on User Navigational Patterns

The foremost mission of any information retrieval algorithm is the efficient extraction of user interests. The rapid growth of web data, intense competition and user’s option to choose from several alternatives increases this issue. In this context Web usage mining can provide valuable contributions in terms of ideas and methods, as it fissures useful knowledge from the pattern of user interactions with the Web. The user interest can be identified by analyzing the access pattern of user browse, the web pages they save, collect, or print. These valuable information’s are available in server logs, which can be exploited to satisfy user needs by optimizing the document-retrieval task. This article is a review conducted in the field of web usage mining and its latest works for supporting the research on efficient information retrieval based on user access pattern. This survey analyzes 25 released information retrieval models to find out the major mining techniques applied in them and also to analyze the effect of diverse parameters like feedbacks, time, content, frequency etc in information retrieval. The goal of this survey is to find the best composition of features to be included in an efficient information retrieval model. Using those features a new retrieval model is then proposed. General Terms Information Retrieval, Web Usage Mining.

ユーザ別アクセス・パターン情報の多様性を用いた顧客行動の予測とモデリング

ユーザ別アクセス・パターン情報の多様性を用いた顧客行動の予測とモデリング

Algorithm for Mining Web Access Patterns Based on User Access Sequences

Through analysis of user access sequences, this research studies the browsing behaviors of web users and pro- poses a user access pattern mining algorithm based on the maximal forward reference sequence to determine frequent ac- cess paths. Experiments have shown that this effective algorithm could obtain a satisfactory result. This algorithm is supe- rior to the traditional Full Scan algorithm in terms of execution time and performance.

A Comparative Analysis on Markov Model (MM) Association Rule Mining (ARM), Association Rule Mining-Statistical Features (ARM-SF), Boosting and Bagging Model (BBM) to Impervious Web Page Prediction

The web usage mining techniques are used to analyze the web usage patterns for a web site. To fetch the user access patterns from the user log files. The access patterns are used in the prediction process. Web prediction is a classification model attempts to predict the next set of Web pages that a user may visit based on the knowledge of the previously visited pages. By Predicting user’s behavior can be applied effectively in various critical applications in the internet environment.So that the application has traditional tradeoffs between modeling complexity and prediction accuracy. The association rule mining and classification techniques are used to perform the pattern extraction and prediction process. The technique as Markov model and all Kth Markov model are used in Web prediction. A modified Markov model is proposed to alleviate the issue of scalability in the number of paths. The framework can improve the prediction time without compromising prediction accuracy. The proposed system integrates the boosting and bagging models with the association rule mining technique to improve the prediction accuracy. The statistical features are also discovered and used in the proposed model. Standard benchmark data sets are used to analyze the web page prediction process. The proposed model reduces the number of paths without compromising accuracy. The system improves the accuracy with scalability considerations.

Web Log Mining Based-on Improved Double-Points Crossover Genetic Algorithm

Web log files have become important data source for discoveries of user behaviors. Analyzing web log files is one of the significant research fields of web mining. This paper proposes an improved double-points crossover genetic algorithm for mining user access patterns from web log files. Our work contains three different components. First, we design a coding rule according to pre-processed web log data. Second, a fitness function is presented by analyzing user sessions. Finally, a new genetic algorithm based on double-points crossover genetic algorithm is designed. In comparison with simple genetic algorithm, double-points crossover genetic algorithm demonstrates better convergence than the other, and it is more suitable for web log mining. We conducted an experiment to verify the effectiveness of the proposed algorithm. The results show that the proposed algorithm helps the website to easily gain access patterns.

English

Web Usage Mining is the part of Web mining for extraction of interesting knowledge from log files produced by Web Servers. It focuses on techniques that predict the user behaviours based on the previous user access patterns. Adaptive Web Sites are web sites that automatically enhance their organisation and presentation from the knowledge obtained from their user access patterns. These patterns can be collected directly on the website or web server log may be mined. Through this paper we present the various web usage mining techniques to extract the useful and relevant information on the web for adaptive web sites.

Web Usage Mining for Discovery and Evaluation of Online Navigation Pattern Prediction

Web mining is combination of two activated research areas Data Mining and World Wide Web. Web mining is used for mining the interested knowledge from World Wide Web. Web usage mining is used to discover the user access patterns from web server log files. The first step of web usage mining called as data pre-processing used for gaining an accurate web log mining results and good quality input data. The session identification is accomplished by time oriented heuristics. The focus is on referrer log which will which contain information about referrer page of the current page. An efficient approach for discovery of navigation pattern can be done by density based clustering algorithm. An online navigation pattern prediction is proposed by use of K nearest neighbor algorithm along with inverted index concept. The prediction accuracy of patterns can be increased by modifying TF-IDF values to include time spent on page.

Access-Pattern Aware Checkpointing Data Storage Scheme for Mobile Computing Environment

The rapid development of communication technology and mobile devices has facilitated the mobile computing applications such as location-based services, and information sharing. Characteristics of the mobile computing system, such as the space limitation, mobility handling, low bandwidth and limited battery life, make mobile computing applications more prone to failures. Checkpoint and rollback recovery technology, as a fault tolerance method for continuing services in mobile computing environment, is researched in this paper. Based on user access patterns, mainly considering the visit time of the mobile host(MH) to the sojourn mobile support stations (MSSs), a checkpointing data storage scheme is proposed. Only if the stay time in the current mobile support station is long enough, the mobile host should do the checkpoint and store the checkpoint data on the sojourn mobile support station. Based on the visited time to the MSS, the scheme manages checkpointing data high efficiently which is more cognitively flexible and adapt to the nomadic and mobile computing environmental conditions.

The cloud storage ciphertext retrieval scheme based on ORAM

Due to its characteristics distribution and virtualization, cloud storage also brings new security problems. User's data is stored in the cloud, which separated the ownership from management. How to ensure the security of cloud data, how to increase data availability and how to improve user privacy perception are the key issues of cloud storage research, especially when the cloud service provider is not completely trusted. In this paper, a cloud storage ciphertext retrieval scheme based on AES and homomorphic encryption is presented. This ciphertext retrieval scheme will not only conceal the user retrieval information, but also prevent the cloud from obtaining user access pattern such as read-write mode, and access frequency, thereby ensuring the safety of the ciphertext retrieval and user privacy. The results of simulation analysis show that the performance of this ciphertext retrieval scheme requires less overhead than other schemes on the same security level.

Video block device for user-friendly delivery in IaaS clouds

Peer-to-Peer (P2P) streaming technology based on various service requirements often remains on the elusive benefits of user-friendly video streaming in cloud computing environments. Cloud-assisted P2P media streaming gives an opportunity to enhance on-demand, dynamic and easily accessible videos. This paper outlines the fundamental video block device (VBD) method for user-friendly viewing patterns that inherits from user access patterns and provides efficient delivery using an enhanced BitTorrent protocol.