The web page ranking algorithms rank the search results depending upon their relevance to the search query. For this algorithms rank the search results in descending order of relevance to the query string being searched. A web page’s ranking for a specific query depends on factors like- its relevance to the words and concepts in the query, its overall link popularity etc. There are three categories of these algorithms viz. text based ranking, PageRank which is based on links and user based ranking.
The SEM model should be a hybrid model based on the integration of traditional statistical methods and various AI techniques to support a general system that operates automatically, adaptively and proactively (Hentea, 2003, 2004). Statistical methods have been used for building intrusion and fault detection models (Manikopoulos & Papavassiliou, 2002). AI techniques such as data mining, artificial neural networks, expert systems and knowledge discovery can be used for classification, detection and prediction of possible attacks or ongoing attacks. Machine learning technique is concerned with writing programs that can learn and adapt in real time. This means that the computer makes a prediction and then, based on the feedback as to whether it is correct, learns from this feedback. It learns through examples, domain knowledge and feedback. When a similar situation arises in the future, the feedback is used to make the same prediction.
also be useful for short-range, multi-hop communication (instead of long range communication) to conserve energy. We expect most sensor networks to be dedicated to a single application or a few collaborative applications, thus rather than node-level fairness, we focus on maximizing system-wide application performance. Techniques such as data aggregation can reduce traffic, while collaborative signal processing can reduce traffic and improve sensing quality. In-network processing, data will be processed as whole messages at a time in store-and- forward fashion, so packet or made-level interleaving from multiple sources only increases overall latency.
Both routing techniques were simulated in the same environment using Network Simulator (ns-2). Both AODV and DSDV were tested by the traffic i.e. TCP. The algorithms were tested using 50 nodes. The simulation area is 1000m by 1000m where the nodes location changes randomly. The connection used at a time is 30. Speed of nodes varies from 1m/s to 50m/s. by using CBR traffic we calculate performance of these two protocols.
Xing and Ghorbani represented the Weighted PageRank algorithm, which is an extended version of the PageRank. The Weighted PageRank takes into account the importance of both the in links and the out links of the pages and distributes rank scores based on the popularity of the pages. The Weighted PageRank is able to identify a larger number of relevant pages to a given query compared to the standard PageRank . Tyagi and Sharma proposed the Weighted PageRank algorithm based on Visits of Links (VOL), for the searchengines . Dinkar and Kumar have considered the time factor for the ranking of each web page. The rank of each page is calculated based on the unit per time page ranking algorithm . Peng and and his colleagues first off, analyze the traditional PageRank algorithm of the search engine deeply. Afterwards, According to its topic drift and putting emphasis on old web pages, suggest an improved PageRank algorithm which is based on the text content analysis and the time factor . Scarselli and and his colleagues used the neural network model graph to calculate the PageRank amounts for the web pages. The neural network graph could learn the ranking function via examples, and is capable of generalizing over unseen data . Sara Setayesh, Ali Haroonabadi and Amir Masoud Rahmani present a developed version of PageRank algorithm, in which the interest level of web page users and ant’s colony algorithm are used .
In , a similar approach has been integrated into artificial intelligence methodologies to address the problem of query answering. In query logs are used to construct a user profile to be used later to improve the accuracy of Web search. Semantic Web search from the user‟s point of view has also been addressed in  and , where the authors present two methodologies for capturing the user‟s information needs by trying to formalize its mental model. They analyze keywords provided during query definition, automatically associate the related concepts, and exploit the semantic knowledgebase to formulate formal queries automatically. Automatic evolution of searchengines via implicit feedback is proposed in . Here, the ranking of pages is done based on the implicit feedback from the users. In this method, they collect the user feedback from various user actions like save, copy, print, bookmark, etc. The user actions are tracked in the background and stored. During the ranking process these user feed backs are used to calculate the weight for a particular web page. According to the calculated weight, the web page is ranked and returned as result.
Abstract - The World Wide Web WWW is a huge resource of hyperlinked and heterogeneous information which comprises of billions of web pages . To retrieve required information from World Wide Web, searchengines perform various tasks based on its architecture and provide relevant and quality information to the internet users in response to its query. by using the web page contents and hyperlink between the web pages. Web mining is an active research area in present scenario. It is defined as the application of data mining techniques on the World Wide Web to find hidden information, This hidden information i.e. knowledge which contained in content of web pages or in link structure of World Wide Web or in web server logs. This paper deals with analysis and comparison of web page rankingalgorithms based on various parameter for the ranking of the web pages. Based on the analysis of various rankingalgorithms, a comparative search is done to search out out theirrelative strengths and limitations and furtherscope of analysis in web page ranking algorithmic rule.
The keyword terms you select must be relevant, salient and part of the vocabulary used by the audience you are seeking to attract. If that audience is a consumer one it is unlikely to use jargon. The opposite may be true if you are seeking B2B prospects. My experience suggests that consumers will often use entirely different vocabulary from marketing, advertising and IT people. To avoid confusion use simpler but more specific terms.Making your keyword choice In essence, you must synthesise all of the above five factors in selecting and refining your keywords. Ignoring any one of the factors could create problems. Do not rush into this process. Test out your keywords by making trial searches on the major engines and see what company results you might keep. Getting it wrong may involve a large amount of reworking.
capacity from hundreds of gigabytes to even several terabytes are now very common in personal computers. As a result, the number of documents stored in the local file system, and functionalities that support effective search for a particular document is of ever growing importance. However, achieving such kind of functionalities turns out to be quite challenging. Unlike in the case of Web search, where powerful ranking schemes such as PageRank  and HITS  can be employed, there is no computers in similar ways. Therefore, state-of-the-art desktop searchengines, such as Google Desktop Search, usually adopt pure text based ranking approaches (e.g., TF-IDF scores) lastly, is the Toolkit for similarity search. This toolkit will be different among the most search toolkits we have right now. The goal is to develop a toolkit that can be used to construct searchengines for various data types by plugging in specific data segmentations, feature extractions and distance calculation modules.
Abstract— Searching is a characteristic behaviour in our general life .Millions of users communicate with searchengines on day to day basis .They are checking on the links of results ,clicking on ads and bookmarking the set of web pages .The largest of all challenges is to find best ranked pages. This paper focuses on series of ranking algorithms and provides a methodology to combine these algorithms in order to produce a more relevant ranked results. A new approach also called re-ranking is presented in order to produce filtered and relevant ranked results to improve user satisfaction and goals.
Image search re-ranking is rectification of the search results by employing visual characteristics of images to reorder the initial search results. The retrieved search result may include noisy images. It decreases efficiency of image search. So we have to rank the search results. This reordering helps to satisfy user’s search experience in both accuracy and response time. The current image search re- ranking has two important steps, they are feature extraction and ranking function. It increases the image retrieval performance. This ranking function design is the main challenge in image search re-ranking. So it became an interested area of research. It can be classified into different area. That are classification based method, learning to rank based method and the graph based method. In classification based method, it first train the classifier with a training data which is get from initial search results. Then it reorders the result by the relevance scores. This methods takes the ranking as a classification problem. So the performance is poor as compared with rest techniques. In graph based methods, it implemented by a Bayesian perspective or random walk. Here re-ranking implement as random walk. Here the nodes represent the result of initial search. The stationary probability of this random walk is used for the computation of final re-ranking scores. But main limitation of this method is graph construction and ranking computation is expensive. So it limits its application to the large data sets. In learning to rank method, it utilize two popular learning to rank approaches. Here a content aware ranking model is used. By using this both textual and visual information are fetched in ranking learning process. But main limitation of this method is it require more training data to train a model, and it is not practical for re-ranking of real images.
As the number of sites on the Web increased in the mid-to-late 90s, searchengines started appearing to help people find information quickly. Searchengines developed business models to finance their services, such as pay per click programs offered by Open Text in 1996 and then Goto.com in 1998. Goto.com later changed its name to Overture in 2001, and was purchased by Yahoo! in 2003, and now offers paid search opportunities for advertisers through Yahoo! Search Marketing. Google also began to offer advertisements on search results pages in 2000 through the Google Ad Words program. By 2007, pay-per-click programs proved to be primary money-makers for searchengines. In a market dominated by Google, in 2009 Yahoo! and Microsoft announced the intention to forge an alliance. The Yahoo! & Microsoft Search Alliance eventually received approval from regulators in the US and Europe in February 2010. Search engine optimization consultants expanded their offerings to help businesses learn about and use the advertising opportunities offered by searchengines, and new agencies focusing primarily upon marketing and advertising through searchengines emerged. The term "Search Engine Marketing" was proposed by Danny Sullivan in 2001 to cover the spectrum of activities involved in performing SEO, managing paid listings at the searchengines, submitting sites to directories, and developing online marketing strategies for businesses, organizations, and individuals. Some of the latest theoretical advances include Search Engine Marketing Management (SEMM). SEMM relates to activities including SEO but focuses on return on investment (ROI) management instead of relevant traffic building (as is the case of mainstream SEO). SEMM also integrates organic SEO, trying to achieve top ranking without using paid means of achieving top in searchengines, and PayPerClick SEO. For example some of the attention is placed on the web page layout design and how content and information is displayed to the website visitor.
WWW is a vast resource of hyperlinked and heterogeneous information including text, audio, video and metadata. It is estimated that WWW is expanded by about 2000% since its evolution and is doubling in size every six to ten months . Due to the rapid growth of information resources in WWW it is difficult to manage the information on the web. Therefore it has increasingly necessary for the users to use efficient information retrieval techniques to find and order the desired information. Searchengines play an important role in searching web pages. The searchengines gather, analyze, organize and handle the data from the internet and offers the users an interface to retrieval the network resources . But the searchengines returns thousands of results which includes a mixture of relevant and irrelevant information . It is true that nearly 65% - 70% users will choose the first page of the return results and about 20% - 25% may choose the second page and very few of 3% - 4% users only check the remaining results . This means that searchengines must return good results which can satisfy the user’s interest. Fig.1 shows the concept of Searchengines. Searchengines are used to find information from the WWW. They download, index and store hundreds of millions of web pages. They answer millions of queries every day. They act like content aggregators as they keep record of every information available on the WWW .