ISSN ONLINE(2320-9801) PRINT (2320-9798)

Yakışıklı erkek tatil için bir beldeye gidiyor burada kendisine türk Porno güzel bir seksi kadın ayarlıyor Onunla beraber otel odasına gidiyorlar Otel odasına rokettube giren kadın ilk önce erkekle sohbet ederek işi yavaş halletmeye çalışıyor sex hikayeleri Kocası fabrikatör olan sarışın Rus hatun şehirden biraz uzak olan bir türk porno kasabaya son derece lüks bir villa yaptırıp yerleşiyor Kocasını işe gönderip mobil porno istediği erkeği eve atan Rus hatun son olarak fotoğraf çekimi yapmak üzere türk porno evine gelen genç adamı bahçede azdırıyor Güzel hatun zengin bir iş adamının porno indir dostu olmayı kabul ediyor Adamın kendisine aldığı yazlık evde sikiş kalmaya başlayan hatun bir süre sonra kendi erkek arkadaşlarını bir bir çağırarak onlarla porno izle yapıyor Son olarak çağırdığı arkadaşını kapıda üzerinde beyaz gömleğin açık sikiş düğmelerinden fışkıran dik memeleri ile karşılayıp içeri girer girmez sikiş dudaklarına yapışarak sevişiyor Evin her köşesine yayılan inleme seslerinin eşliğinde yorgun düşerek orgazm oluyor

A Survey on a Personalized Mobile Search Engine

Tushar Mohod1, Prof. S. N. Gujar2
  1. Smt. Kashibai Navale College of Engineering, Pune, India
  2. Department of Computer Engineering, Savitribai Phule Pune University, MH, India.
Related article at Pubmed, Scholar Google

Visit for more related articles at International Journal of Innovative Research in Computer and Communication Engineering

Abstract

In today’s world internet technology growing rapidly and people used internet on their mobile phones, desktops or laptops etc. for various purposes using various search engines which are not personalized. Personalized search engines catches user location and gives information associated to that location. For routinely optimizing the retrieval superiority of search engines by using clickthrough data method. Location is one of the important factors in mobile search and the information related to location categorize as content and location concepts. The user preferences are prepared by ontology based, wide-ranging user profiles, which are used to adapt a personalized ranking function for rank adaptation for search results. The personalized mobile search engine server is trustworthy for management of the weighty jobs .Server preparing for search results and reranking the search results according to the users content and location preferences sooner than they come back to client side. The personalized mobile search engine regulars keep records of the specific user’s profile and maintain user’s privacy. The GPS systems used for identification of the user’s location and also important to collect location related information. The preferences are controlled with the help on ontology and further useful in personalized ranking function for search results. This paper will provide the person who reads with the groundwork for research in personalized mobile search engine using the clickthrough data, user preferences as well as ontology etc.

Keywords

click through data, concept, ontology, search engine, user preferences.

INTRODUCTION

One of the most important difficulties in mobile search engine is the interfacing among the users and search engine is restricted due to the small form factors of mobile devices. On the World Wide Web plenty of information is available which is copious and personal electronic devices are everywhere. In the personalized mobile search engine various kind of concepts are used with diverse ontology’s. Mobile search engine in which location of the user is one of the important key factor as well as information related with particular location is having same importance. Personalized search engines catches user location and gives information associated to that location. For consistently optimizing the retrieval superiority of search engines by using clickthrough data method.
The information related to location categorize as content and location concepts. The user preferences are prepared by ontology-based, comprehensive user profile, which are used to adapt a personalized ranking function for rank adaptation for search results. The personalized mobile search engine server is trustworthy for management of the heavy tasks .Server preparing and re-ranking the search results according to the users content and location preferences sooner than they come back to client side. The personalized mobile search engine clients keep records of the specific user’s profile and maintain user’s privacy. Personalized mobile search engine profiles content and location preferences in the ontology based user profiles, which are involuntarily erudite from the clickthrough as well as GPS data exclusive of requiring additional efforts from the user.
There has been to a great extent of research work associated to personalization with the aim to gratify users diversified requirements in penetrating Web information This paper will provide the person who reads with the groundwork for research in personalized mobile search engine using the clickthrough data ,user preferences as well as ontology etc.

LITERATURE REVIEW

PMSE: A Personalized Mobile Search Engine [1]

Kenneth Wai-Ting Leung, Dik Lun Lee, and Wang-Chien Lee suggest a practical approach for Personalized Mobile Search Engine by assuming the metasearch method which is capable to reply on the commercial search engines, accomplish a indisputable search. In personalized mobile search engine process the user request are handled by the client who is submitted to the personalized mobile search engine server. Server replies with the results and users clickthrough data for obtaining the user’s unique preferences. The server of personalized mobile search engine is trustworthy for management of the heavy tasks .Server preparing and reranking the search results according to the users content and location preferences sooner than they come back to client side. The personalized mobile search engine clients keep records of the specific user’s profile and maintain user’s privacy. For validating the proposed scheme the personalized mobile search engine client prototyped with android and server on personal computer. For properly distinguishing variety of the concepts linked with query and their relevancy of the user the idea of content and location randomness’s for computing the amount of information related to location and content linked with query as well as interest of the user in content or location information.
1) Pros: In the proposed scheme privacy parameters is capable to alleviate smooth control of privacy experience at the same time as maintaining good ranking quality.
2) Future Scope: To enhancing the personalization effectiveness of personalized mobile search engine will explore methods to make use of standard travel patterns and query patterns from the GPS and clickthrough data

Mining User Preference Using Spy Voting for Search Engine Personalization [2]

Wilfred Ng, Lin Deng and Dik Lun Lee introducing a new scheme for search engine personalization. They were presenting a novel technique for mining user's preferences on the results of search engine using clickthrough data and revealed preferences to acclimatize the ranking function of the search engine for enhancing search quality. The mining technique is called as SpyNB (Spy Naive Bayes). In this paper, they deal with the difficulty of search engine adjustment by taking into consideration two major research issues. The preference pulling out is one of the research issues, which identifies user's preferences and second is the ranking function optimization, the ranking or retrival purpose of a search engine optimizes as per the user's preferences. The key thought is to use novel technique, SpyNB (Spy Naive Bayes), to create a set of preferences which is fed into the Ranking Support Vector Machine algorithm for optimizing the ranking function.
1) Pros: Proposed algorithm SpyNB is used to personalized metasearch engine enhanced the ranking superiority and capable to provide Users' specific interests.
2) Future Scope: To enhance SpyNB in other contexts that needs semi-supervised learning in classification. Also gear the spying system towards the RSVM in a straight line to mine preferences by voting on the rank order.

Personalized Concept-Based Clustering of Search Engine Queries[3]

Kenneth Wai-Ting Leung, Wilfred Ng, and Dik Lun Lee introducing an effective and efficient method to present personalized query suggestions which captures the user’s conceptual preferences. This objective accomplish with two new procedures. First, online ways that take out concepts from the web-snippets of the search result given by the queryand make use of the concepts to recognize correlated queries for that query and second, suggest a novel two stage personalized agglomerative clustering algorithm which is capable to provide personalized query clusters.
1) Pros: our method can effectively make personalized query suggestions as per the individual user conceptual needs and also improves prediction accuracy and computational cost.
2) Future Scope: to enhancing the associations between users’ preferences and concepts to achieve extra personalized and accurate query suggestions and also integrating the clickthrough data and concept relationship graphs into ranking algorithms.

Optimizing Search Engines using Clickthrough Data [4]

Thorsten Joachims introducing a method which is mechanically optimizing the retrieval superiority of search engines using clickthrough data. Spontaneously, a superior information retrieval method giving significant or most probable documents first in the ranking and less amount of relevancy documents following below. The main objective of is to build up a technique which utilizes clickthrough data for preparation, specifically the log record of the query search engine in association with the log of links on which users clicked on in the existing ranking. The clickthrough data is accessible in great quantity and can be recorded at small cost. With the help of Support Vector Machine mechanism, a process for learning retrieval functions. This technique is well suited in a risk minimization framework.
1) Pros: In the proposed method a Support Vector Machine algorithm which heads to a bulging program and wideranging to non linear ranking functions.
2) Future Work: In this framework it might also be possible to explore mechanisms that make the algorithm robust against “spamming”.

Applying Co-training to Clickthrough Data for Search Engine Adaptation [5]

Qingzhao Tan, Xiaoyong Chai, Wilfred Ng, Dik-Lun Lee propose a novel algorithm technique, Ranking Support Vector Machine in a Co-training Framework (RSCF). Basically, the algorithm considers the clickthrough data which includes the things in the search result that used or clicked by a user as an input, and produces adjustive rankers as an output. Analyzing the clickthrough data, RSCF distinguish the data as the labeled data set, containing the objects that scanned already, and the unlabelled data set containing the objects that not scanned. The labelled data is then improved as compare with the unlabelled data to achieve a superior data set for training the rankers.
1) Pros: The proposed method is capable to get better retrieval superiority of search result by learning from clickthrough data and algorithm does not put in any burden to the users for the duration of the process of web searching.
2) Future Work: To enhancing the ways to recognize sessions of clickthrough data into log files also to provide individual needs in accumulation to adapting the search engine to users.

Optimized Mobile Search Engine [6]

E.Chaitanya, Dr.Sai Satyanarayana Reddy, O.Srinivasa ReddyThey proposed a Optimized Personal Search Engine for mobile, which considers users preferences and analyzed clickthrough data in the type of related concepts. Location of the user is one of the important factors in the mobile search so the optimized personal search engine categorizes the concept into content and location concepts. The GPS system s used for identifying the users location and also important to collect location interrelated information. The preferences are controlled with the help on ontology and further useful in personalized ranking function for search results. To typify the concepts related with a query, its relevance’s to the users need to equilibrium the weights which linking the content and location facets. In this scheme the client brings together and stores locally the click through data and also responsible to defend Privacy, preparation is for performing at the Optimized Personal Search Engine server.
1) Pros: identifying distinctive characteristics of content and location concepts, to provide a logical policy using clientserver architecture to incorporate them into an identical solution for the mobile atmosphere. The confidentiality parameters make possible smooth control of privacy experience at the same time as maintaining good ranking superiority.
2) Future Work: enhance the normal travel patterns and query patterns from the GPS and clickthrough data.

CONCLUSIONS

We learn the personalized mobile search engine is the interfacing among the users and search engine is restricted due to the small form factors of mobile devices. Identify distinguishing characteristics of content and location concepts, to provide a logical policy using client-server architecture. The confidentiality parameters make possible smooth control of privacy experience for maintaining good ranking superiority. The preferences are controlled with the help on ontology and further useful in personalized ranking function for search results. To typify the concepts related with a query, its relevance’s to the users need to equilibrium the weights which linking the content and location facets.
This paper will provide the person who reads with the groundwork for research in personalized mobile search Engine.

ACKNOWLEDGMENT

We thank the mysterious referees for their valuable suggestions to improvise the content and quality of this paper. The author is grateful to our principal for providing necessary facilities towards carrying out this work. We acknowledge the diligent efforts of our Head of the Department to guide us towards implementation of this review paper.
 

Tables at a glance

Table icon
Table 1
 

References