Reinaldo Bezerra Braga

Clustering user trajectories to find patterns for social interaction applications

Sharing of user data has substantially increased over the past few years facilitated by sophisticated Web and mobile applications, including social networks. For instance, users can easily register their trajectories over time based on their daily trips captured with GPS receivers as well as share and relate them with trajectories of other users. Analyzing user trajectories over time can reveal habits and preferences. This information can be used to recommend content to single users or to group users together based on similar trajectories and/or preferences. Recording GPS tracks generates very large amounts of data. Therefore clustering algorithms are required to efficiently analyze such data. In this paper, we focus on investigating ways of efficiently analyzing user trajectories and extracting user preferences from them. We demonstrate an algorithm for clustering user GPS trajectories. In addition, we propose an algorithm to correlate trajectories based on near points between two or more users. The obtained results provided interesting avenues for exploring Location-based Social Network (LBSN) applications.

FRAMESEC: a framework for the application development with end-to-end security provision in the mobile computing environment

Mobile devices offer network connectivity through wireless system communication that makes possible for applications to get access to information at any time and any place. However, the wireless link is more vulnerable to passive and active attacks than the fixed medium in traditional networks. This kind of connectivity brings security problems to applications that deal with confidential data, such as mobile commerce. Although wireless communication systems, such as IEEE 802.11, implement protection mechanisms for data transmission, they have reported vulnerabilities and do not guarantee end-to-end security, which is desirable for these applications. Thus, the paper proposes an application FRAMEwork that provides a reusable structure with SECurity mechanisms (FRAMESEC), which enable end-to-end security in the mobile computing environment.

GeoSPIN: An Approach for Geocast Routing Based on SPatial INformation in VANETs

Vehicular Ad hoc NETworks (VANETs) have been widely used to provide data exchange services in Intelligent Transport Systems (ITS), which should facilitate users routines. At the same time that users routines are improved, they can also be used as an important source of data for helping the decision-making process of VANET services. These routines can be acquired from vehicles trajectories through the use of Global Positioning Systems (GPS). In this context, the combination of location-based data and data forwarding methods brings interesting challenges since these topics are not directly related. Therefore, the key idea of this work is to provide a geocast routing mechanism in VANETs based on daily movements of users in their vehicles. The main contribution is related to the delivery rate, which increases in partitioned and sparsely connected networks. The results show the efficiency of our new method to perform opportunistic routing based on location data, which discovers the best routes to forward packets through the network.

Clariisa, a context-aware framework based on geolocation for a health care governance system

Context-awareness has been successfully included in the mobile device applications due mainly to the presence of numerous sensors and the access to several communication networks. Therefore, this paper presents a context-aware framework based on geolocation for a health care governance system. While enabling remote health diagnosis of a patient using his/her own mobile device, the proposed system enriches the patients health data with geolocation before sending it to the Lariisa framework, an intelligent platform to support decision-making in public health governance. In order to collect information about a patients health status, the proposed application uses mobile devices equipped with medical sensors. While remotely registering a patients health diagnosis using a mobile device, the system allows the creation of an enriched description of the user context (e.g. weather, location, and date). The main contributions related to our framework include patient health diagnosis provided remotely, support for decision-making health systems, and context information for context-aware health systems.

USABle -- A Communication Framework for Ubiquitous Systems

The widespread use of mobile devices is reshaping the way users interact, allowing applications to explore physical proximity of devices to offer intelligent services. Although there are several communication technologies available (e.g., Wi- Fi, Wi-Fi Direct, LTE, UMTS, Bluetooth, NFC), building an application from scratch considering both communication and application requirements is not a trivial task. In order to help developers to implement communication primitives, this paper presents a communication framework for ubiquitous systems called USABle. Two important contributions of this framework can be highlighted: i) a set of technology-independent interfaces to handle communication requirements; and ii) a modular and extensible layer-based architecture that permits developers to implement new communication technologies and message dissemination strategies. The outcome of using this communication framework is a simpler way to build applications that explore physical proximity. To validate the claims presented in this paper, a performance evaluation using real devices is done, analyzing two multi-hop and three carry-and-forward implementations of routing algorithms that were implemented using the USABle framework.

Mobile Photo Recommendation and Logbook Generation Using Context-Tagged Images

Context-aware and semantic-based technologies have been successfully employed to improve multimedia management in mobile environments. Large sets of context-tagged images on the Web are a concrete example of this achievement. The authors present two mobile systems, MMedia2U and CAPTAIN, that take the concept of context-aware multimedia management beyond photo organization and annotation. CAPTAIN is a tool that helps generate logbooks using context-tagged images and tracking data. Crewmembers used this tool to manage multimedia content and publish it to a blog during a sea expedition. MMedia2U is a mobile photo recommender system that exploits the users context and context-tagged images to improve photo recommendation.

RETENTION: A reactive trust-based mechanism to detect and punish malicious nodes in ad hoc grid environments

In ad hoc grid environments, resources are not always available since nodes can spontaneously connect and disconnect at any time. Thus, these environments demand the correct execution of tasks to guarantee good performance. However, there are malicious users that affect the normal operation of these grids. These users modify tasks results and even cheat security mechanisms. Therefore, to assure high performance in these grid computing scenarios, it is essential to use punishment procedures based on trust models. These solutions have been used in wireless ad hoc networks, but not in the context of ad hoc grid computing. Thus, in this paper, we first present an analysis of mathematical trust models in ad hoc grid scenarios, using different ways to treat detection information passed on by other nodes. Then, we provide a comparison and a performance evaluation of these models using a grid simulator platform. Besides that, we choose the most accurate trust model among the evaluated ones to propose RETENTION: a reactive trust-based mechanism to detect and punish malicious nodes in ad hoc grid environments. Simulation results demonstrate the effectiveness of the proposed approach in detecting and punishing up to 100% of malicious nodes without generating false-positives. The results can be a valuable tool for network designers in planning trust models in ad hoc grid network deployments.

A context-aware web content generator based on personal tracking

Context-awareness has been successfully included in the mobile phone applications due mainly to the presence of numerous sensors and the access to several communication networks. Therefore, we present a Context-Aware Web Content Generator Based on Personal Tracking, which uses the user context information obtained by mobile devices to generate content for a large number of web applications. While registering the trajectory followed by the mobile device, it allows users to create multimedia documents (e.g. photo, audio, video), which are connected to an enriched description of the user context (e.g. weather, location, date). Finally, all this data and documents are combined to produce a new content, which is published on the Web. We also show results of tests performed in a real scenario and describe our strategy to avoid battery overconsumption and memory overflow in mobile phones. Moreover, a user evaluation is presented in order to measure the system performance, in terms of precision and system overall usability.

Using Bayesian networks to improve the decision-making process in public health systems

This paper proposes the use of Bayesian networks to support the decision-making process in public health systems. In particular, this paper presents LARIISA_Bay, a new component based on Bayesian networks that works together with LARIISA, a context-aware platform to support applications in public health systems. The main goal of the proposed component is to assist teams of health specialists in order to better diagnose diseases through data collected from users of LARIISA. As a case study, we focus on scenarios of dengue fever disease. We classify dengue cases into one of the following levels: normal, grave or emergency. Based on this classification, teams of health specialists can accurately make decisions, for example, to alert a health care agent to visit locations with a high incidence of the disease, to send a team of health specialists when a dengue emergency case has occurred, as well as give technical instructions on how to deal with specific cases. We present a prototype of LARIISA_Bay as well as the corresponding interfaces to support the interactions with the component. We compare the obtained results with real diagnosis of general practitioners. The results presented show the efficiency of the proposed approach.

FrameSTEP: A framework for annotating semantic trajectories based on episodes

Abstract We are witnessing an increasing usage of location data by a variety of applications. Consequently, information systems are required to deal with large datasets containing raw data to build high level abstractions. Semantic Web technologies offer powerful representation tools for pervasive applications. The convergence of location-based services and Semantic Web standards allows an easier interlinking and annotation of trajectories. However, due to the wide range of requirements on modeling mobile object trajectories, it is important to define a high-level data model for representing trajectory episodes and contextual elements with multiple levels of granularity and different options to represent spatial and temporal extents, as well as to express quantitative and qualitative semantic descriptions. In this article, we focus on modeling mobile object trajectories in the context of Semantic Web. First, we introduce a new version of the Semantic Trajectory Episodes (STEP) ontology to represent generic spatiotemporal episodes. Then, we present FrameSTEP as a new framework for annotating semantic trajectories based on episodes. As a result, we combine our ontology, which can represent spatiotemporal phenomena at different levels of granularity, with annotation algorithms, which allow to create instances of our model. The proposed spatial annotation algorithm explores the Linked Open Data cloud and OpenStreetMap tags to find relevant types of spatial features in order to describe the environment where the trajectory took place. Our framework can guide the development of future expert systems in trajectory analysis. It enables reasoning about knowledge gathered from large trajectory data and linked datasets in order to create several intelligent services.