Saroj Kaushik

Mining Popular Places in a Geo-spatial Region Based on GPS Data Using Semantic Information

The increasing availability of Global Positioning System (GPS) enabled devices has given an opportunity for learning patterns of human behavior from the GPS traces. This paper describes how to extract popular and significant places (locations) by analyzing the GPS traces of multiple users. In contrast to the existing techniques, this approach takes into account the semantic aspects of the places in order to find interesting places in a geo-spatial region. GPS traces of multiple users are used for mining the places which are frequently visited by multiple users. However, the semantic meanings, such as ‘historical monument’, ‘traffic signal’, etc can further improve the ranking of popular places. The end result is the ranked list of popular places in a given geo-spatial region. This information can be useful for recommending interesting places to the tourists, planning locations for advertisement hoardings, traffic planning, etc.

A survey on LBS: system architecture, trends and broad research areas

The Location Based Services (LBS) seem to be the next revolution on small computing handheld devices in terms of location aware advertising, security alerts, news updates, disaster management, geo-fencing, buddy-findings, gaming, criminal investigations, turn-by-turn navigation and so on. In todays scenario there is an explosion of technologies to communicate with mobile, connected devices and sensors. In this paper we are presenting a literature survey of LBS that includes the architecture of the LBS ecosystem, the key market players, and the latest trends in LBS development. Finally, the broad research areas such as location determination techniques, geo-sensor networks, and location based natural queries, location privacy and authorization, geo-social networks, LBS QoS, and Location Based Recommender Systems (LBRS) have been studied and presented briefly.

Machine Learning Approach for the Classification of Demonstrative Pronouns for Indirect Anaphora in Hindi News Items

Machine Learning Approach for the Classification of Demonstrative Pronouns for Indirect Anaphora in Hindi News Items In this paper, we present machine learning approach for the classification indirect anaphora in Hindi corpus. The direct anaphora is able to find the noun phrase antecedent within a sentence or across few sentences. On the other hand indirect anaphora does not have explicit referent in the discourse. We suggest looking for certain patterns following the indirect anaphor and marking demonstrative pronoun as directly or indirectly anaphoric accordingly. Our focus of study is pronouns without noun phrase antecedent. We analyzed 177 news items having 1334 sentences, 780 demonstrative pronouns of which 97 (12.44 %) were indirectly anaphoric. The experiment with machine learning approaches for the classification of these pronouns based on the semantic cue provided by the collocation patterns following the pronoun is also carried out.

Information Enrichment for Tourist Spot Recommender System Using Location Aware Crowdsourcing

With the increase in number of available interesting locations, it becomes difficult for users to find interesting ones, thus imposes a need for recommender systems to suggest interesting locations. Further, to ease the users decision making, the amount of supplementary information, such as right time to visit, weather conditions, traffic condition, right mode of transport, crowdedness, security alerts, etc., may be annotated with the list of recommended locations. This paper explores the possibility of enriching tourist locations using crowd sourcing approach, which can be used by Tourist Spot Recommender System (TSRS) for mobile users. Proposed crowd sourcing system focuses on getting work done from the crowd currently available at the location under consideration. In proposed system, the contributed information is not limited to ones available on blogs, web pages and sensor-readings from the device etc., but includes proactively-generated users opinions and perspectives, that are processed to offer immediate knowledge. Our system works in collaboration with a TSRS, takes the list of locations to be recommended to the current user and performs just-in-time information enrichment for those selected set of locations. We have implemented a prototype of proposed systems using java android software development toolkit and evaluated this system by 76 real users.

Extracting Region of Interest (ROI) Details Using LBS Infrastructure and Web-Databases

The geographical areas that are considered to be popular and interesting are called Region of Interest (ROI). There are multiple sources that can be used for erecting the ROIs such as user trajectory, POI databases, internet news etc. A tourist spot, historical region, monuments, a forest reserve, city, state or countrys administrative boundaries are considered as the ROI objects. The interesting facts of the regions can be used for on-the-spot infotainment (information + entertainment) while user is walking, driving or just sitting idle on the flight. One may want the information in different level of details based on the interests, travel direction, and speed. The best way to get the recent information is going through the internet news, discussion forums, and encyclopedias on the web. The challenge is that there is no universal database available that contains the region information along with the location based search capabilities. The maintaining the granularity of the information based on the size or the details of the region adds more challenges. The broader idea of our work is to use the existing LBS infrastructure to track the user and achieve other navigation objectives in the system. However, the freely available up-to-date internet infrastructure is used as the information source. Initially, the user location is determined by the conventional methods. In order to relate the location with the web content, we use the semantic labels associated to the underlying location. The semantic labels are fetched by using reverse geocoding that returns the local attractions, street city, state and country names etc. Then these labels are used to search the associated detailed content in the web. The region data is maintained in two forms i.e. locally populated database and the web databases. The locally populated database can be updated on the preconfigured time interval in order to avoid data staleness problem. We have used Wikipedia as the internet data source in our prototype. The further research is in progress extracting the ROI information from the POI databases with their spatial and non-spatial attributes.

A Non Functional Properties Based Web Service Recommender System

Web services provide a promising solution to an age old need of fast and flexible information sharing among people and businesses. Selection of web service has become a tedious job because of the increasing number of service providers providing services with similar functionality. Service registries are becoming very large preventing users from discovering desired service. Sometimes service users may not be aware of services that can be most beneficial to them. Therefore, a framework for selection of web service that can meet the users specific requirements is needed. In this work, we have proposed a personalized web service recommender system that will be very useful to the user in finding web service matching his/her needs. A recommender system helps product/service user to deal with information overload and provides personalized recommendation to them. There have been a few web service recommendation system in past, but most of them are either content based or collaborative filtering based recommendation. But all of these approaches have their own limitations. In our work we have proposed a web service recommender system based on hybrid technique which takes advantages of collaborative filtering based, content based and knowledge based approaches and minimize there individual limitations.

Defending Location Privacy Using Zero Knowledge Proof Concept in Location Based Services

The increasing trend of embedding positioning capabilities (e.g., GPS) in mobile devices facilitates the widespread use of Location Based Services. For such applications to succeed, privacy and confidentiality are key issues. Over all privacy will have to be managed through a combination of technology, legislation, corporate policy, and social norms. There are many data privacy schemes including Zero Knowledge Proof (ZKP) those can be used for location privacy. ZKP is also useful for removing the bottleneck problem introduced by use of trusted third party. In the earlier work, authors proposed the concept of middleware architecture in which, request and response are not routed through middleware for every transaction. This has reduced the dependency on middleware. This paper presents correspondence between the authentication techniques used in above said architecture and zero knowledge proof technique. Use of the concept of zero knowledge proof for authentication and authorization in the domain of location based services is also explored.

Reducing Dependency on Middleware for Pull Based Active Services in LBS Systems

The middleware is the most commonly used solution to address the location privacy. But it becomes a bottleneck in terms of system performance and availability as the entire client’s service transactions are routed through the middleware to the actual Location Based Service Providers (LSP). The proposed architecture mainly targets a variety of applications where the availability of the services is probably more important than the location security. In the new flexible middleware based architecture the client and the LSPs can communicate directly. Autonomy on the client-server communication increases the possibility of communication even in the scenarios where the middleware is not available. But it also introduces authentication and security challenges to be addressed. The trusted middleware is used to generate the authentication certificates containing the Proxy Identity (also called Pseudonyms) to fulfill the authentication requirements at the LSP servers. The rest of transactions among the clients and the LSPs are accomplished independently. Further, the level of anonymity can be tuned by altering pseudonyms generation techniques i.e. “One-to-One”, “One-to-Many” and “Many-to-One” depending on the type of the service and security requirements. It also attempts to maintain almost the same level of security for the targeted services.

Crowdsourcing Based Fuzzy Information Enrichment of Tourist Spot Recommender Systems

Tourist Spot Recommender Systems TSRS help users to find the interesting locations/spots in vicinity based on their preferences. Enriching the list of recommended spots with contextual information such as right time to visit, weather conditions, traffic condition, right mode of transport, crowdedness, security alerts etc. may further add value to the systems. This paper proposes the concept of information enrichment for a tourist spot recommender system. Proposed system works in collaboration with a Tourist Spot Recommender System, takes the list of spots to be recommended to the current user and collects the current contextual information for those spots. A new score/rank is computed for each spot to be recommender based on the recommenders rank and current context and sent back to the user. Contextual information may be collected by several techniques such as sensors, collaborative tagging folksonomy, crowdsourcing etc. This paper proposes an approach for information enrichment using just in time location aware crowdsourcing. Location aware crowdsourcing is used to get current contextual information about a spot from the crowd currently available at that spot. Most of the contextual parameters such as traffic conditions, weather conditions, crowdedness etc. are fuzzy in nature and therefore, fuzzy inference is proposed to compute a new score/rank, with each recommended spot. The proposed system may be used with any spot recommender system, however, in this work a personalized tourist spot recommender system is considered as a case for study and evaluation. A prototype system has been implemented and is evaluated by 104 real users.

Using middleware as a certifying authority in LBS applications

The trusted middleware is the most commonly used solution to address the location privacy in location based services as generally such service providers are un-trusted entities that can be adversary attack sensitive points. The authors proposed an alternative solution which helps in avoiding a bottleneck in the existing system in terms of performance and availability as the entire clients service transactions are routed through the middleware to the actual Location Based Service Providers (LSP). In the proposed solution, the client and the LSPs can directly communicate with the same level of location security, privacy and anonymity. The trusted middleware is used as certifying authority that generates authentication certificates which contains the Proxy Identity (also called Pseudonyms), and the services subscribed with validity period. The encrypted certificate fulfills the authentication requirements at the LSP servers. In this paper we are reporting the implementation of the proposed system as a proof of concept using Struts Technology of Java. While evaluating the system features such as response time, delay, drop rate etc., the Google Maps location services and the internet browser have been considered as a service provider and client respectively. Performance analysis of our solution and that of prevalent architecture is done using Packmime model for http traffic generation of NS2 (Network Simulator 2) tool. The comparative graphs of the simulation results show that the proposed solution is better in terms of throughput, response time, drop rate and scalability in comparison to the existing middleware architectures in which the request response is every time routed through middleware, thus increasing the overheads.