Maximal Forward References Research Articles

An Efficient Path Completion Technique based on Auxiliary Pages for Web Usage Mining

The frequent usage of website access the wide range of information in the internet world. There is a need of system to handle the web usage data efficiently. The preprocessing data is further used for knowledge discovery process. The data preprocessing system for web usage mining gives a new approach to the user with the help of path completion algorithm. The user session identification algorithm is also implemented to automatically append the user data and the missing pages of the user access paths are also identified and added using the referrer-based method which resolves the problems facing by proxy server and local caching. Maximal forward reference and reference algorithms are considered as a solution for the average reference length of the auxiliary pages which is estimated in advance. Web access log are used to retrieve data from the server which is generated by the client whenever the request is made. By using the proposed path completion algorithm with the web access log, it efficiently appends the lost information of the visitor and the reliability of the access data also shows better improvement.

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.

Mining the web data using data mining techniques for identifying and classifying the user access behavioral patterns

The one of the largest and most widely used document repository is worldwide web. It has been used for mining data since many decades. It has been proved as one of the most helping platform to assimilate, disseminate and retrieve information. But unfortunately its success has only become its enemy. It seems like an ocean of information in which users are drowning not sailing. The information is so huge, diverse, dynamic and unstructured natured that users face the problems of information overloaded while interacting with the web. Here the issue of QoS cops up. It's needed for web developer to know what the user really wants to do, predict which pages the user is interested in and provide the user the WebPages by knowledge of users navigational patterns to improve QoS. This project mainly focuses on cleaning the data i.e. sever web log file, processing the data according to some specific strategy, identifying the users using maximal forward reference algorithms and classifying them into predefined classes. Here supervised learning is used to train the classifier. We have carried out this project using an educational institute's log file as input data. Our project work has been used to implement the model for providing the desired information to the user if the data at the backend can be maintained appropriately and grouped into different classes. We have done the implementation using the corresponding data can be given to the user, ie instead of giving hundreds of links related topic to the user, more appropriate links pertaining to the user can be given. Hence the prevision rate can be increased. Keywords: QOS, WEBMINER, clustering, Session, GiniIndex, Raw web log data

Reference Scan Algorithm for Path Traversal Patterns

The paper focuses the path of exploring an algorithm which involves mining frequently used user traversals pattern while using the World Wide Web by the user. As the web’s becoming more and more popular, web servers gather the large amount of data from the web in the form of web server logs. The web server log provides important information aiding to analysing the user surfing behavior and thus extract important information. Web Usage Mining analyses the Web access logs to find how the users surf a website so as to bring out interesting patterns which can be used for improving user profile, web site design, business and marketing decision support and web server system. Firstly, the server log is scanned and the maximal forward references are obtained for which effect of backward references is not considered and secondly, the maximal forward references obtained in the first step are used to finally obtain the large references which are frequently accessed patterns by the user.

Discovery of Popular Structural Properties in a Website for Personalization and Adaptation

The massive growth in the size and complexity of websites, lead to increased demand on personalization systems and tools which can help in providing users with what they want or need without them having to ask for it explicitly. In this paper, we present a novel approach towards the discovery of target pages for shortcuts. The approach is based on the Maximal Forward Reference algorithm. Few changes to this algorithm are suggested to make it more suitable for the discovery of popular paths, pages and individual user behaviors in relation to the structural design of the sit. The major impetus for the selection of Maximal Forward Reference approach in our research was driven by two of our own convictions. First, forward traversals more realistically represent the navigational intentions of the user. Second, the algorithm has already been proven to generate a complete set of maximum references from the processed log file. The proposed approach aims at limiting the consolidation process of the MFR to the level of individual users which should help in providing more detailed site adaptation, personalization, and visualization on the user level.

Mining top- k maximal reference sequences from streaming web click-sequences with a damped sliding window

Online mining of path traversal patterns from continuous Web click streams is one of the challenging research problems of Web usage mining. Most of previous works focus on mining path traversal patterns over the entire history of Web click streams. Mining the recent changes of Web click streams can provide valuable information for the analysis of the Web click streams. In this paper, we propose a new, online mining algorithm, called Top-DSW (top- k path traversal patterns of stream Damped Sliding Window), to discover the set of top- k path traversal patterns from streaming maximal forward references, where k is the desired number of path traversal patterns to be mined. An effective summary data structure, called TKP-DSW-list (a list of top- k path traversal patterns of stream Damped Sliding Windows) is developed to maintain the essential information about the top- k path traversal patterns from the maximal forward references within a stream damped sliding window. An effective space pruning mechanism, called TKR-list-maintain, is developed to control the memory requirement of the TKP-DSW-list. Experimental studies show that the proposed Top-DSW algorithm is an efficient, single-pass algorithm for online mining of the set of top- k path traversal patterns over stream damped sliding windows.

A sliding window method for finding top- k path traversal patterns over streaming Web click-sequences

Online mining of path traversal patterns from Web click-streams is one of the most important problems of Web usage mining. In this paper, we propose a sliding window-based Web data mining algorithm, called Top-SW ( Top- k path traversal patterns of Stream sliding Window), to discover the set of top- k path traversal patterns from streaming maximal forward references, where k is the desired number of path traversal patterns to be mined. A new summary data structure, called Top-list (a list of Top- k path traversal patterns) is developed to maintain the essential information about the top- k path traversal patterns from the current maximal forward references stream. Experimental studies show that the proposed Top-SW algorithm is an efficient, single-pass algorithm for mining the set of top- k path traversal patterns from a continuous stream of maximal forward references.

DSM-PLW: Single-pass mining of path traversal patterns over streaming Web click-sequences

Mining Web click streams is an important data mining problem with broad applications. However, it is also a difficult problem since the streaming data possess some interesting characteristics, such as unknown or unbounded length, possibly a very fast arrival rate, inability to backtrack over previously arrived click-sequences, and a lack of system control over the order in which the data arrive. In this paper, we propose a projection-based, single-pass algorithm, called DSM-PLW (Data Stream Mining for Path traversal patterns in a Landmark Window), for online incremental mining of path traversal patterns over a continuous stream of maximal forward references generated at a rapid rate. According to the algorithm, each maximal forward reference of the stream is projected into a set of reference-suffix maximal forward references, and these reference-suffix maximal forward references are inserted into a new in-memory summary data structure, called SP-forest (Summary Path traversal pattern forest), which is an extended prefix tree-based data structure for storing essential information about frequent reference sequences of the stream so far. The set of all maximal reference sequences is determined from the SP-forest by a depth-first-search mechanism, called MRS-mining (Maximal Reference Sequence mining). Theoretical analysis and experimental studies show that the proposed algorithm has gently growing memory requirements and makes only one pass over the streaming data.

Dynamic Web log session identification with statistical language models

AbstractWe present a novel session identification method based on statistical language modeling. Unlike standard timeout methods, which use fixed time thresholds for session identification, we use an information theoretic approach that yields more robust results for identifying session boundaries. We evaluate our new approach by learning interesting association rules from the segmented session files. We then compare the performance of our approach to three standard session identification methods—the standard timeout method, the reference length method, and the maximal forward reference method—and find that our statistical language modeling approach generally yields superior results. However, as with every method, the performance of our technique varies with changing parameter settings. Therefore, we also analyze the influence of the two key factors in our language‐modeling–based approach: the choice of smoothing technique and the language model order. We find that all standard smoothing techniques, save one, perform well, and that performance is robust to language model order.

Efficient data mining for path traversal patterns

The authors explore a new data mining capability that involves mining path traversal patterns in a distributed information-providing environment where documents or objects are linked together to facilitate interactive access. The solution procedure consists of two steps. First, they derive an algorithm to convert the original sequence of log data into a set of maximal forward references. By doing so, one can filter out the effect of some backward references, which are mainly made for ease of traveling and concentrate on mining meaningful user access sequences. Second, they derive algorithms to determine the frequent traversal patterns-i.e., large reference sequences-from the maximal forward references obtained. Two algorithms are devised for determining large reference sequences; one is based on some hashing and pruning techniques, and the other is further improved with the option of determining large reference sequences in batch so as to reduce the number of database scans required. Performance of these two methods is comparatively analyzed. It is shown that the option of selective scan is very advantageous and can lead to prominent performance improvement. Sensitivity analysis on various parameters is conducted.