Search

Location based social networks, such as Foursquare and Yelp, have inspired the development of novel recommendation systems due to the massive volume and multiple types of data that their users generate on a daily basis. More recently, research studies have been focusing on utilizing structural data from these networks that relate the various entities, typically users and locations. In this work, we investigate the information contained in unique structural data of social networks, namely the lists or collections of items, and assess their potential in recommendation systems. Our hypothesis is that the information encoded in the lists can be utilized to estimate the similarities amongst POIs and, hence, these similarities can drive a personalized recommendation system or enhance the performance of an existing one. This is based on the fact that POI lists are user generated content and can be considered as collections of related POIs. Our method attempts to extract these relations and express the notion of similarity using graph theoretic, set theoretic and statistical measures. Our approach is applied on a Foursquare dataset of two popular destinations in northern Greece and is evaluated both via an offline experiment and against the opinions of local populace that we obtain via a user study. The results confirm the existence of rich similarity information within the lists and the effectiveness of our approach as a recommendation system.

The function of logistics is to move objects from place A to place B Therefore it is an important task to determine the position of objects along the supply chain. Up to now, different technologies for indoor localization have been developed. During this technological evolution, two important aspects have been left behind, the communication between the systems and the central management of the data provided. Within the research project ‘Industrial Indoor Localization’, an open source software standard for environment modeling called ‘Reference Architecture Indoor Localization’ (RAIL) has been designed and tested. This protocol enables Location Based Services to allow querying location and object information quickly. Within the scope of the project, four services are being developed and exemplary described in this paper. At the beginning, a location-dependent order allocation algorithm for order picking is presented. This algorithm reduces the waiting time in narrow-aisle warehouses through forecasting. Secondly, an order orchestration service based on location data for picking control is evaluated. Furthermore, a functional area recognition to support picking and a service for finding points of interest is demonstrated, which includes navigation based on a routing algorithm. Using indoor localization, these services improve the intralogistical processes. These include increasing picking performance or reducing order throughput time by eliminating the need to scan the barcode. Finally, these services increase work safety, due to consideration of functional areas, and improve the transparency of the location of points of interest.

Recommender systems are important information filtering techniques that retrieve interesting and personalized items for users based on their profiles and past activities. The goal of most recommender systems is to identify a ranked list of items that are likely to be of interest to users. However, there are several applications such as trip planning, where the items to be selected are not intended for single users but for a group of users, and where the group members are interested in package recommendations as collections of items. Recent research on recommender systems has generalized recommendations to suggest packages of items to single users (Package recommendations), and single items to groups of users (Group recommendations). However, the package-to-group recommendation task has not gained much attention. In this paper, we focus on the task of recommending packages of items to groups of users. This is a task with several real life scenarios, such as recommending a set of Points of Interest packages to tourist groups. We formally define the problem of top-k package-to-group recommendations and propose two models for estimating the preference of a group for a package, incorporating features such as package constraint, user impact and package viability. We design ranking algorithms for finding the top-k package-to-group recommendations and we compare our proposed models with baseline approaches stemming from related works. The experimental evaluation of our proposals, using the Yelp dataset demonstrates that our models find packages of high quality considering important features of package-to-group recommendations.

The development of a city gradually fosters different functional zones, such as educational areas and business districts. Typically, a city is segmented into disjointed regions by major roads, such as highways and urban expressways. In this chapter, we propose a framework for discovering functional zones in a city through the analysis of human mobility among regions and points of interest (POIs) within regions. Specifically, we infer the functions of each region from the results of a topic-modeling-based approach, which regards a region as a document, a function as a topic, categories of POIs (e.g., restaurants and shopping malls) as metadata (such as authors, affiliations, and keywords), and human mobility patterns (origins/destinations and arrival/departure times) as words. As a result, a region can be represented by a distribution of functions. This type of representation enables functional zones to be identified, which are comprised of clusters of regions with similar distributions of functions. We then further identify the intensity of each functional zone type occurring in different locations. We evaluated our method using large-scale, real-world datasets, consisting of two POI datasets of Beijing (in 2010 and 2011) and two three-month GPS trajectory datasets (representing human mobility); these trajectories were generated by over 12,000 taxicabs in Beijing in 2010 and 2011 respectively. The results demonstrate the advantages of our approach over baseline methods which solely use POIs or human mobility.

It is often a hard task for novices to design their tour itineraries when visiting unfamiliar destinations on a tight schedule. To relieve them from such difficulty, we have developed a computer-aided tour planner, called CT-Planner. Unlike previous tour recommenders, CT-Planner prompts/encourages its users to design their tour plans with the system in a collaborative manner. This tool does not mandate that users specify their requests at the beginning of tour planning. In addition, it allows users to specify both direct requests (i.e., which points of interest (POIs) they want to visit or not) and indirect requests (i.e., what kind of tours they like). This chapter introduces its latest version, CT-Planner 4.3, which is available online at http://ctplanner.jp. We then discuss how the log data of such computer-aided tour planner will be highly useful for marketing analysis, since this data can tell, for instance, which POIs attract users’ attention and predict what kind of tour itineraries are endorsed by which group of users. Finally, we introduce our future plan that involves users in the creation of destination data for CT-Planner, consequently expanding its service coverage.

This paper presents the Discriminative Generalized Hough Transform (DGHT) as a technique to localize landmarks in 3D face scans. While the DGHT has been successfully used for the detection of landmarks in 2D and 3D images this work extends the framework to be used with triangle meshes for the first time. Instead of edge features and their respective gradient direction, the relative positions and orientations of the mesh faces are utilized to describe the geometric structures which are relevant for the detection of a specific landmark. Implementing a coarse-to-fine strategy at first a decimated version of the mesh is used to locate the global region of the point of interest, followed by more detailed localizations on higher resolution meshes. The utilized shape models are created in an automated, discriminative training process which assigns individual weights to the single model points, aiming at an increased localization rate. The technique has been applied to detect 38 anthropometric facial landmarks on 99 3D face scans. With an average error of 1.9mm, the most accurate detection was performed for the right alare, the average error when considering all landmarks amounts to 5.1 mm.

Existing cost analysis frameworks have been defined for cumulative resources which keep on increasing along the computation. Traditional cumulative resources are execution time, number of executed steps, amount of memory allocated, and energy consumption. Non-cumulative resources are acquired and possibly released along the execution. Examples of non-cumulative cost are memory usage in the presence of garbage collection, number of connections established that are later closed, or resources requested to a virtual host which are released after using them.We present, to the best of our knowledge, the first generic static analysis framework to infer an upper bound on the peak cost for non-cumulative types of resources. Our analysis comprises several components: 1 a pre-analysis to infer when resources are being used simultaneously, 2 a program-point resource analysis which infers an upper bound on the cost at the points of interest namely the points where resources are acquired and 3 the elimination from the upper bounds obtained in 2 of those resources accumulated that are not used simultaneously. We report on a prototype implementation of our analysis that can be used on a simple imperative language.

Descubre PUCP is a project developed and implemented in the Pontificia Universidad Catolica del Peru whose objective is the improvement and extension of academic experience in college outside the classroom. To achieve this, Descubre PUCP marks each place in campus as a point of interest, showing its location using an augmented reality interface or a Google Map, adding relevant information for each one. This information includes static data (descriptions, photos, telephone numbers and mail contact) and dynamic data (in real time), interacting with different services and applications of PUCP such as events about to start in the auditoriums, free computers in the laboratories, the dishes to be served in the cafeteria, the streaming transmission available in different congresses or seminars in the campus and also explaining how to get to these places.

Motion estimation is a fundamental problem in many computer vision applications. One solution to this problem consists in defining a large enough set of candidate motion vectors, and using a combinatorial optimization algorithm to find, for each point of interest, the candidate which best represents the motion at the point of interest. The choice of the candidate set has a direct impact in the accuracy and computational complexity of the optimization method. In this work, we show that a set containing the most representative maxima of the phase-correlation function between the two input images, computed for different overlapping regions, provides better accuracy and contains less spurious candidates than other choices in the literature. Moreover, a pre-selection stage, based in a local motion estimation algorithm, can be used to further reduce the cardinality of the candidate set, without affecting the accuracy of the results.

In this paper, we are interested in stitching specific types of images such as schemes, cartographies, documents or drawings that have been acquired using a scanner. Because of the size of these documents, it is not possible to make one acquisition even using large scanners. The result of the acquisition is then an image mosaic that needs to be stitched to obtain the entire image. For that purpose, we propose an adaptation of feature based methods that are not directly usable with the images we want to process. Indeed, points of interest (POIs) extraction on the entire image requires too much memory and matching are not always pertinent because of the particularity of these documents. To demonstrate the good performance of our proposition, we present quantitative and qualitative results obtained using two datasets: a set of images divided synthetically and a set of images that have been acquired manually using a scanner.

interpretation is an efficient means for approximating program behaviors before run-time. It can be used as the basis for a number of different useful techniques in static analysis more broadly, and can thus in-turn be used to prove properties needed for security or optimization. Polyvariance represents a way of obtaining higher precision in an abstract interpretation by producing multiple abstract states for each function or lexical point of interest in the program. This paper explores the role of polyvariance in these analyses and how it is manifested, unifying the disparate presentations in the literature.

With the rapid development of geo-positioning technologies, spatial information retrieval plays an important role in a wide spectrum of applications, e.g., online maps and location-based services. Specifically, spatial keyword query (SK query), considering both spatial proximity to the query location and textual relevance to the query keywords, is now a hot research topic in database community. This paper addresses a specific type of SK query, termed range constrained spatial keyword query (RC-SK query), which searches for all the POIs (points of interest) whose textual description is relevant to the query keywords within a specified area. Though RC-SK query has received extensive studies in Euclidean space, little is done to deal with it on road networks. In this paper, alternative approaches with different indexing strategies are proposed to solve this problem. Extensive empirical studies on multiple real datasets demonstrate the efficiency of these proposed approaches.

The main purpose of this paper is to present a research and development of an intelligent system for mobile phones that can helps users finding the shortest path from a point-of-interest to another point-of-interest within Universiti Sains Malaysia (USM) main campus. Research is done to acquire an optimal navigation solution which primary goals is to provide shortest-path calculation. A mobile application based on Android that allows user to find a location quickly with minimum effort and collaborate with other users to enhance the experience of route-planning has been developed. Preliminary evaluation suggests that the proposed methods and the mobile application are helpful for the users in finding their point of interest within shortest time possible.

We consider the focused coverage self-deployment problem in mobile sensor networks, where an area with maximum radius around a Point of Interest (POI) must be covered without sensing holes. Li et al. [9, 10] described several algorithms solving this problem. They showed that their algorithms terminate in finite time. We present a modified version of the Greedy-Rotation-Greedy (GRG) algorithm by Li et al., which drive sensors along the equilateral triangle tessellation (TT) graph to surround a POI. We prove that our modified GRG (mGRG) algorithm is collision free and always ends up in a hole-free network around the POI with maximum radius in \(O(D)\) steps, where \(D\) is the sum of the initial distances of the sensors from the POI. This significantly improves the previous bound on the coverage time. The theoretical results are also validated by simulations.

Millions of users use location-based applications (LBAs) to share their positions with friends, request information from points of interest finders, or get notifications from event finders, etc. Such LBAs are typically based on location servers (LSs) managing mobile object positions in a scalable fashion. However, storing precise user positions on LSs raises privacy concerns, in particular, if LS providers are non-trusted. To solve this problem, we present PShare-BSP, a novel approach for the secure management of private user positions on non-trusted LSs. PShare-BSP splits up precise user positions into position shares and distributes them to different LSs of different providers. Thus, a compromised provider only reveals user positions with degraded precision. Nevertheless, LBAs can combine several shares from different LSs to increase their precision.

Examination with echography greatly depends on the expertise and experience of an operator. Thus many kinds of researches to recognize left ventricular (LV) cavity were developed. However, most of these techniques require initial settings to indicate initial region or points of interest. Therefore, we have developed an automatically recognition software of LV without initial settings. The software includes the automatic detection of inner area of LV cavity and the automatic recognition to extract the contour of LV cavity. We have applied this algorithm to more than 100 diseased hearts. As the result, the proposed method correctly recognized left ventricular cavities. Furthermore, the calculation results of ejection fraction were agreed with that of conventional method by professional sonographers.

This paper presents work in interlinking social stream information with geographical spaces through the use of Linked Data technologies. The paper focuses on filtering, enriching, structuring and interlinking microposts of localised (i.e. geo-tagged) social streams (a.k.a localised forums) to profile geographical areas (e.g., cities, countries). For this purpose, we enriched social streams extracted from Twitter, Facebook and TripAdvisor and structured them into well-known vocabularies and data models, such as SIOC and SKOS. To integrate this information into a location profile we introduce the linkedPOI ontology. The linkedPOI ontology captures and leverages DBpedia categories to derive concepts which profile a geographic space.

In this paper, a hybrid indoor location tracking method is proposed for pedestrian using a set of inertial sensors embedded in smartphones. The method is composed of two localization techniques; one is dead-reckoning using inertial sensors and the other is Wi-Fi fingerprinting. The proposed method uses the concept of combined map of topological and geometric map. Introducing user-select points of interest in his/her workplace we can reduce the cost of building a radio map for Wi-Fi fingerprinting method. The dead-reckoning method can track incremental movements of user by detecting steps. Based on acceleration signals we proposed a method to estimate the orientation and position of the phone in a pocket of pants. Experiments verified the performance of the method.

Innovative services consist the main point of interest so for academics as for the business world. The basic objective of this paper is to demonstrate the way that innovative services may change the “consumer experience” in the airport environment. In the following lines we describe the procedure of designing innovative services, so for consumers’ and visitors’ needs as for the needs of the firms which are operated in the airport environment. In order to achieve this goal, we used so the qualitative approach (such as focus groups), as the quantitative approach (collection of 1106 questionnaires).

Applying wireless sensor network to emergency management is helpful to predict latent disaster and prevent or lessen the harm. In some cases of emergency management, it is not necessary to monitor the entire area all the time, and only need to employ a few of mobile sensors to monitor a number of Points of Interest (POIs) periodically. Due to the cost restriction, the number of mobile sensors is limited. Moreover, there may be some obstacles in the monitoring field, which makes mobile sensor cannot reach some POIs directly. In this paper, we address the Minimum-Delay POIs Coverage problem in Emergency Management, which is how to schedule the limited number of mobile sensors to monitor the POIs in a region with obstacles such that the POIs coverage delay is minimized. Firstly, we calculate the shortest distance between any two POIs in the monitoring field with obstacles to construct a weight complete graph. Secondly, we propose an algorithm named Obstacle − TSP − S to address the minimum-delay POIs coverage problem. By the comprehensive simulations, we evaluate the performance of the proposed algorithm. The simulation results show the efficiency of our algorithm.

The purpose of CBIR Content Based Image Retrieval systems is to allow users to retrieve pictures related to a semantic concept of their interest, when no other information but the images themselves is available. Commonly, a series of images are presented to the user, who judges on their relevance. Several different models have been proposed to help the construction of interactive systems based on relevance feedback. Some of these models consider that an optimal query point exists, and focus on adapting the similarity measure and moving the query point so that it appears close to the relevant results and far from those which are non-relevant. This implies a strong causality between the low level features and the semantic content of the images, an assumption which does not hold true in most cases. In this paper, we propose a novel method that considers the search as a multi-objective optimization problem. Each objective consists of minimizing the distance to one of the images the user has considered relevant. Representatives of the Pareto set are considered as points of interest in the search space, and parallel searches are performed for each point of interest. Results are then combined and presented to the user. A comparatively good performance has been obtained when evaluated against other baseline methods.

This contribution deals with search and implementation of optimization algorithms in analyzing and evaluating objects of interest present in ultrasound images as well as assessing the progress or regressions illustrated in these objects. These objects are highly significant from a medical perspective and include atherosclerotic plaque in carotid arteries, the intima-media thickness in the distal part of the common carotid artery, cerebral cortex size and brain stem findings in cases of Parkinson disease. Here, we describe procedures employing common principles and methods for recognizing points of interest in images that may serve in finding and determining pixel coordinates and other parameters and properties of analyzed objects. We use the stochastic optimization algorithm to optimize the energy function of deformable models used to approximate the locations and shapes of object boundaries in medical images. We suppose that evolutionary algorithm called SOMA can be used to find the desired global solution. Evolutionary algorithms are based on principles of evolution found in nature and respect the Darwin‘s theory of natural selection according to the defined cost function and gene recombination and mutation. As the computation of gradient vector flow field and also the evolution of active contour are computationally very expensive, we investigate the suitability of the GPU for a parallel implementation.

In the context of geographic information systems (GIS), points of interest (POIs) are descriptions that denote geographical locationswhichmight be of interest for some user purposes. Examples are public transport facilities, historical buildings, hotels and restaurants, recreation areas, hospitals etc. Because information gathering with respect to POIs is usually resource consuming, the user community is often involved in this task. In general, POI data originate from different sources (or users) and are therefore vulnerable to imperfections which might have a negative impact on data quality. Different POIs referring to, or describing the same physical geographical location might exist. Such POIs are said to be coreferent POIs. Coreferent POIs must be avoided as they could harm the data(base) quality and integrity. In this chapter, a novel soft computing technique for the (semi-)automated cleansing of POI databases is proposed. The proposed technique consists of two consecutive main steps: the detection of collections of coreferent POIs and the fusion, for each collection, of all coreferent POIs into a single consistent POI that represents all the POIs in the collection. The technique is based on fuzzy set theory, whereas possibility theory is used to cope with the uncertainties in the data. It can be used as a component of (semi-)automated data quality improvement strategies for databases and other information sources.

Location is considered the most significant element of context in ubiquitous computing. Location information, besides system context information, can offer rich queries for handling information especially in emergency systems. This paper introduces the Mona Emergency System that uses context information in providing emergency services such as sending warning messages to an identified location. MES context information includes actor, danger and point of interest information. This paper describes the MES methodology to obtain and distribute warning messages during emergency situations. MES is a new approach that defines message targets and content using spatial relations.

To promote the performance of Opportunistic Networks (ONs), novel network architecture with Fixed Infrastructure Nodes (FINs) is proposed. FINs have large storage capacity and short-range wireless communication ability. Two location strategies of FINs are compared in this paper including location at Points of Interest (POIs) and location at hot spots with high traffic. Routing protocol named PROPHET-F is proposed to employ the FINs' ability. The main difference between PROPHET-F and original PROPHET is that FINs own the highest message forwarding priority. FINs can collect all messages carried by the nodes passing by the FINs and transfer to other proper mobile nodes. The performance of this novel architecture is evaluated in ONE simulation platform. The simulation results indicate that Message Delivery Probability (MDP) in ONs with FINs is improved. MDP is higher while FINs are located at hot spots than at POIs. Furthermore, MDP of PROPHET-F protocol is superior to that of PROPHET.

The prevalence of digital photo capturing devices has gen- erated large-scale photos with geographical information, leading to in- teresting tasks like geographically organizing photos and location visual- ization. In this work, we propose to organize photos both geographically and thematically, and investigate the problem of location visualization from multiple themes. The novel visualization scheme provides a rich dis- play landscape for location exploration from all-round views. A two-level solution is presented, where we first identify the highly photographed places (POI) and discover their distributed themes, and then aggregate the lower-level themes to generate the higher-level themes for location visualization. We have conducted experiments on a Flickr dataset and ex- hibited the visualization for the Singapore city. The experimental results have validated the proposed method and demonstrated the potentials of location visualization from multiple themes.

In this paper we will introduce a new multi-agent algorithm for the use in search and rescue scenarios for exploration of unknown terrain. This method combines the concept of exploration from the flood algorithm and the path optimizing features of the ant algorithm. The first part leads to a fast exploration of the unknown terrain, while the second part constructs short paths from points of interest back to the base. Together this enables the starting of rescue operations parallel to the ongoing search. We demonstrate the feasibility of our approach by agent-based simulations. The simulations show, that our approach is comparable in speed and quality with already existing algorithms, delivering the additional benefit of short paths to points of interest, and adhering to the inherent limitations of these kind of scenarios.

With rapidly popular location-aware applications, location privacy becomes an emerging issue. This paper studies how to protect the two-fold privacy for both client-side and server-side in location-based queries. This technique is a significant component in privacy-friendly Location Based Services (LBS). Participants protect their own privacy. The LBS server protects against excessive disclose of location records in its Points of Interest (POIs) database while the mobile user protects his exact location by the cloaking technique. The proposed hybrid approach can achieve the challenging goal. Our solution integrates the cloaking technique with a cryptographic protocol, Private Set Intersection (PSI). In addition, this solution is secure in malicious model and also practical.

In this paper, an innovative Personalized Location Information System for the Semantic Web (called SPLIS) is presented. The proposed system adopts schema.org ontology and combines it with rule-based policies, to deliver fully contextualized information to the user of a location-based system. Owners of points of interest can add their own rule-based policies to SPLIS to expose and deploy their marketing strategy on special offers, discounts, etc. These rules are combined at run-time with information about relevant place properties and user (people) profiles. Additionally, owners of points of interest can extend the ontology by adding dynamically specific properties. Rules are encoded in RuleML for interchangeability and to Jess in order to be executed. All data and rules are stored in the form of triples, using Sesame. Rules are evaluated on-the-fly to deliver personalized information according to the rules that fired within the current user-location-time context. In the paper, a demonstration of SPLIS is given using data from Google Places API and Google map for visualization.

In this paper, we propose Tracommender, a context-aware recommender system, which uses background tracking information from smartphones to generate location-based recommendations. Based on the automatically collected data that consist of locations with timestamps, the dwell time at certain locations can be derived in order to use it as an implicit rating for a location-based collaborative filtering. We further introduce two alternative path matching algorithms that utilize continuous location sequences (paths) to compute path patterns between similar users. In addition, in order to overcome the cold-start problem of recommender systems, clustering algorithms are used to calculate so-called Activity Zones - locations taken from an existing database of categorized points of interest. Synthesized movement data has been applied to perform evaluations on performance, scalability and precision of an implemented prototype of the proposed recommendation algorithms.

This paper describes a Recommender System that implements a Multiagent System for making personalised context and intention-aware recommendations of Points of Interest (POIs). A two-parted agent architecture was used, with an agent responsible for gathering POIs from a location-based service, and a set of Personal Assistant Agents (PAAs) collecting information about the context and intentions of its respective user. In each PAA were embedded four Machine Learning algorithms, with the purpose of ascertaining how well-suited these classifiers are for filtering irrelevant POIs, in a completely automatic fashion. Supervised, incremental learning occurs when the feedback on the true relevance of each recommendation is given by the user to his PAA. To evaluate the recommendations’ accuracy, we performed an experiment considering three types of users, using different contexts and intentions. As a result, all the PAA had high accuracy, revealing in specific situations F 1 scores higher than 87%.

The research in Autonomata Too aimed at the development of new pronunciation modeling techniques that can bring the speech recognition component of a Dutch/Flemish POI (Points of Interest) information providing business service to the required level of accuracy. The automatic recognition of spoken POI is extremely difficult because of the existence of multiple pronunciations that are frequently used for the same POI and because of the presence of important cross-lingual effects one has to account for. In fact, the ASR (Automatic Speech Recognition) engine must be able to cope with pronunciations of (partly) foreign POI names spoken by native speakers and pronunciations of native POI names uttered by non-native speakers. In order to deal adequately with such pronunciations, one must model them at the level of the acoustic models as well as at the level of the recognition lexicon. This paper describes a novel lexical modeling approach that was developed and tested in the Autonomata Too project. The new method employs a G2P-P2P (grapheme-to-phoneme, phoneme-to-phoneme) tandem to generate suitable lexical pronunciation variants. It was shown to yield a significant improvement over a baseline system already embedding state-of-the-art acoustic and lexical models.

Recommender systems have typically been used in tourism applications to filter out irrelevant information and to provide personalized recommendations to the users. With the advent of mobile devices and ubiquitous computing, RSs have begun to incorporate Location Based Services (LBS) into mobile tourism guides to provide users with interesting points of interest (POIs) according to their contextual information, mainly physical location. In this paper, we propose a context-aware system for mobile devices that incorporates some implicit contextual information that is scarcely used in the literature: the user’s speed and his trajectory. This system has been specifically crafted to assist travelling users by providing them with smart and personalized POIs along their route taking into account their current location and driving speed.

Spatial-textual content is becoming increasingly prevalent: — Location-based services from major commercial search engines. For example, in Google Maps many (geo-referenced) points of interest--e.g., clinics, stores, tourist attractions, hotels, entertainment services, public transport, and public services--are being associated with descriptive texts. — Websites with location content. For example, online yellow pages, documents of Wikipedia, Tweets in Twitter, photos in Flickr, points of interest in Foursquare, etc. — Moving objects associated with texts. An example scenario is that each healthcare worker has certain skills, described in keywords, and moves around in a large hospital. These call for spatial-keyword search from the perspectives of both the users and the service providers. From the user's perspective, users may want to issue queries such as "health screening clinics near NTU, Singapore", which has a location component "NTU, Singapore" and a keyword component "health screening clinics". Indeed, location-based services (e.g., Google Maps) and Twitter already support such types of queries. From the perspective of service providers, they want to know the number of customers who are interested in their services compared with competitors. For example, a nutrition store may want to find potential customers whose profiles are relevant to the products of the store and whose locations are close to this store. The talk covers recent results [1---6] on spatial keyword querying obtained by the speaker and his colleagues.

In this paper we describe a Location-based Service (LBS) ‘point to query’ system called Haptic GeoWand where we use the orientation of the user to retrieve information for that user along a given street. Haptic GeoWand provides the user with location, orientation, and distance information using varying vibration patterns. This helps to reduce the visual mobile interaction required from the user. With the textual description of query results we use the vibration alarm to provide haptic feedback to the user about the availability and distance to their desired points of interests (POI) along a particular path or street. To test the usability of Haptic GeoWand we developed two mobile prototypes – whereHaptics and whichHaptics. The distance to Point of Interest (POI) information is provided by the whereHaptics which uses vibration feedback of varying frequency to represent distance to the POI. The whichHaptics uses vibration alarms of varying frequency to deliver information about the density of features along a particular street. With our system we demonstrate that the user can point and query the availability of POI along the street which are not directly visible to them but are along the path he/she intends to take. After selecting a POI, the user can follow this route without increased cognitive burden of interaction with the mobile interface. The user is not required to constantly look at the mobile screen. Haptics has proven to be powerful notification technique used to convey quantitative information. To test the system we integrated this with OpenStreetMap as the spatial data source.

Recently, Location Based Service (LBS) is expanding its service areas with the spread of smart phones and is offering more personalized contents according to the variety of needs from customers. Specially, Location Based Social Network Service (LBSNS) is emerging as the most promising service among the applications of LBS. This paper proposes a LBSNS service model to form a community adaptively based on the location of user’s mobile devices. The methodology suitable for implementing the effective management and the automatic update of this social network community is presented in this paper. In addition, we describe the significance of the proposed model to promote future researches of LBSNS under the upcoming domination of mobile environment.

X-ray mammography (XRM) and Magnetic Resonance Imaging (MRI) are likely to provide complementary diagnostic information for early breast cancer detection. However, topographic correlation of both modalities is challenging due to different dimensionality of images, patient positioning and compression state of the breast. In this paper we present an automated registration method, which allows prediction of the position of a lesion in the contrary modality. It is based on a FEM simulation mimicking the mammographic compression and is carried out using a patient-specific biomechanical model. An intensity-based optimization of the registration parameters is proposed to incorporate with the clinical variability of datasets. After registration, the position of a point of interest can be estimated within the three-dimensional MRI volume based on two mammograms acquired from different projection angles. The method was evaluated with 47 datasets from clinical routine. The mean registration error for localizing a lesion in the 3D MRI volume was 14.3 mm. The automatic registration method enables localization of e.g. microcalcifications which are only visible in XRM, within the corresponding MRI volume. It is therefore likely to assist radiologists in multimodal diagnosis.

In this paper, the idea of providing personalized, location-based information services via rule-based policies is demonstrated. After a short introduction about related technologies and approaches, an innovative Personalized Location Information System (PLIS) is designed and implemented. PLIS delivers personalized and contextualized information to users according to rule-based policies. More specifically, many categories of points of interest (e.g. shops, restaurants) have rule-based policies to expose and deploy their marketing strategy on special offers, discounts, etc. PLIS evaluates these rules on-the-fly and delivers personalized information according to the user's context and the corresponding rules fired within this context. After discussing the design and the implementation of PLIS, illustrative examples of PLIS functionality are presented. As a result, PLIS proves that combining contextual data and rules can lead to powerful personalized information services.