With the wide popularity of smart devices such as smartphones, smartwatches, and smart cameras, Mobile Crowdsensing (MCS) and Crowdsourcing (CS) have been broadly applied for collecting data from a large group of ordinary participants. The quality of participants' contributed data, however, is hard to guarantee, and as such it is critical to develop efficient and effective methods to automatically improve data quality over MCS/CS platforms. In this thesis, we propose three machine learning-based solutions for data quality enhancement in different participatory MCS/CS scenarios. Our solutions aim at the data extraction phase as well as the data collection phase of participatory MCS/CS, including (1) trustworthy information extraction from conflicting data, (2) recognition of learning patterns, and (3) worker recruitment based on interactive training and learning pattern extraction. The first one is designed for the data extraction phase and the other two for the data collection phase. First, to derive reliable data from diverse or even conflicting labels from the crowd, we design a mechanism to infuse knowledge from domain experts into the labels from the crowd to automatically make correct decisions on classification-based MCS tasks. Our solution, named EFusion, utilizes a probabilistic graphical model and the expectation maximization (EM) algorithm to infer the most likely expertise level of each crowd worker, the difficulty level of tasks, and the ground truth answers. Furthermore, we introduce a method to extend EFusion from solving binary classification problems to handling multi-class classification problems. We evaluate EFusion using real-world case studies as well as simulations. Evaluation results demonstrate that EFusion can return more accurate and stable classification results than the majority voting method and state-of-the-art methods. Second, we propose Goldilocks, an interactive learning pattern recognition framework that can identify suitable participants whose performance follows desired learning patterns. To accurately extract a participant's learning pattern, we first estimate the impact of previous training questions on the participant before she answers a new question. After the participant answers each new question, we adjust the estimation of her capability by considering a quantitative measure of the impact of previous questions and her answer to the new question. Based on the extracted learning curve of each participant, we recruit the candidates, who have showed good learning capability and desired learning patterns, for the formal MCS/CS task. We further develop a web service over Amazon Web Services (AWS) that automatically adjusts questions to maximize individual participants' learning performance. This website also profiles the participants' learning patterns, which can be used for task assignment in MCS/CS. Third, we present HybrTraining, a hybrid deep learning framework that captures each candidate’s capability from a long-term perspective and excludes the undesired candidates in the early stage of the training phase. Using two collaborative deep learning networks, HybrTraining can dynamically match participants and MCS/CS tasks. In detail, we build a deep Q-network (DQN) to match the candidates and training batches in the training phase, and develop a long short-term memory (LSTM) model that extracts the learning patterns of different candidates and helps the DQN make better worker-task matching decisions. We build HyberTraining on Compute Canada and evaluate it over two scientific datasets. For each dataset, the learning data of candidates is collected with a Python-based Django website over Amazon Elastic Compute Cloud (Amazon EC2). Evaluation results show that HybrTraining can increase data collection efficiency and improve data quality in MCS/CS. / Graduate / 2022-08-19

Location-based services have experienced substantial growth in the last decade. However, despite extensive research efforts, sub-meter location accuracy with low-cost infrastructure continues to be elusive. Comparing with infrastructure-based solutions, infrastructure-free indoor localization has the major advantage of avoiding extra cost for infrastructure deployment. There are two typical types of infrastructure-free indoor localization solutions, i.e., Pedestrian Dead Reckoning (PDR)-based and fingerprint-based. PDR-based solutions rely on inertial measurement units to estimate the user's relative location. Despite the effort, many issues still remain in PDR systems. For example, any deployed smartphone-based PDR system needs to cope with the changing orientation of smartphone that the phone might be putting in a pocket, or being taken out to use, etc. In addition, the outputs of Micro Electro-Mechanical Systems (MEMS) sensors on smart devices vary over time which results in rapidly accumulated localization errors without external references. Fingerprint-based solutions utilize different types of location dependent parameters to estimate user's absolute location. Although fingerprint-based solutions are usually more practical than PDR-based, they suffer from laborious site survey process. In this dissertation, we aim to mitigate these challenges. First of all, illumination intensity is introduced as a new type of fingerprints to provide location references for PDR-based indoor localization. We propose IDyLL -- an indoor localization system using inertial measurement units (IMU) and photodiode sensors on smartphones. Using a novel illumination peak detection algorithm, IDyLL augments IMU-based pedestrian dead reckoning with location fixes. Moreover, we devise a burned-out detection algorithm for simultaneous luminary-assisted IPS and burned-out luminary detection. Experimental study using data collected from smartphones shows that IDyLL is able to achieve high localization accuracy at low costs. As for fingerprint collection, several frameworks are proposed to ease the laborious site survey process, without compromising fingerprint quality. We propose TuRF, a path-based fingerprint collection mechanism for site survey. MobiBee, a treasure hunt game, is further designed to take advantage of gamification and incentive models for fast fingerprint collection. Motivated by applying mobile crowdsensing for fingerprint collection, we propose ALSense, a distributed active learning framework, for budgeted mobile crowdsensing applications. Novel stream-based active learning strategies are developed to orchestrate queries of annotation data and the upload of unlabeled data from mobile devices. Extensive experiments demonstrate that ALSense can indeed achieve higher classification accuracy given fixed data acquisition budgets. Facing malicious behaviors, three types of location-related attacks and their corresponding detection algorithms are investigated. Experiments on both crowdsensed and emulated dataset show that the proposed algorithms can detect all three types of attacks with high accuracy. / Thesis / Doctor of Philosophy (PhD)

As cidades estão a seu tempo e a seu modo, modernizando os serviços prestados à população. Entre os diversos fatores que estão contribuindo para esta evolução estão a diversificação e proliferação de sensores, nos diversos domínios de serviços das cidades, e os novos canais de comunicação com os munícipes, entre eles, as redes sociais e mais recentemente os sistemas crowdsensing, motivados pelos anseios sociais, por melhores serviços públicos e pela popularização dos dispositivos móveis. Nesta direção, a eficiência administrativa é um fator essencial, uma vez que as cidades estão se mostrando mais complexas na medida em que cresce a população nas áreas urbanas. A utilização de técnicas de sistemas distribuídos para que múltiplos domínios de serviços usufruam da mesma infraestrutura computacional, pode auxiliar na eficiência das cidades, evitando gastos administrativos duplicados e até mesmo, possibilitando a correlação de eventos entre os serviços, favorecendo a identificação de fatores de causalidades e assim, a tomada de decisões administrativas mais objetivas e precisas. Neste contexto, este trabalho concentra-se na análise de um middleware direcionado à gestão de cidades para coleta, integração e interpretação dos dados de sensores, pertencentes aos serviços disponíveis da própria cidade, junto com os dados do sensoriamento colaborado pelos cidadãos. Para avaliação do conceito foi investigado o cenário de monitoração da conservação de vias públicas. Após 3 meses de coletas de dados por um sistema de sensoriamento automático, totalizando mais de 360 mil pontos e também mais de 90 relatórios pelo sensoriamento participativo, verificou-se que um sistema distribuído pode realizar a interpretação de séries históricas, engajar os munícipes apoiar a manutenção dos serviços da cidade e também indicar objetivamente aos gestores públicos os pontos que devem ser prioritariamente atendidos. Aliar ferramentas pelas quais o cidadão pode, de acordo com sua necessidade, convicção e altruísmo, exercer influência nos gestores públicos com o suporte de informação contínua e critérios objetivos das redes de sensores, pode estimular a continua excelência dos serviços públicos. / The cities in their own way and time are improving their services provided to the population. Among several factors that are contributing to this trend are the diversification and proliferation of sensors in various services domains of cities and new communication ways with citizens, for instance, social networks and more recently, crowdsensing systems, motivated by social expectations for better public services and the popularity of mobile devices. In this direction, administrative efficiency is a key factor, since the cities are proving more complex with increasing the population in urban areas. Techniques of distributed systems to share the same computing infrastructure to multiple service domains, can assist in the efficiency of cities, avoiding duplicate administrative costs and even allowing event correlation between services, providing the identification of causality factors, thus making management decisions more objective and accurate. In this context, this research focuses on analysis of a middleware directed to city management for collection, integration and interpretation of sensors data, present in city services, along with the sensing data contributed by citizens. For concept evaluation, was investigated the scenario of conservation of public streets. After 3 months of data collection by an automatic sensing system comprising more than 360 thousand points and also 94 reports of collaborative sensing, it was found that a distributed system can perform the interpretation of historical series; engage the citizens to support maintenance of city services and indicate objectively the points that should primarily be fix by public managers. Combining tools, which citizens can, according to their need, conviction, altruism, exert their own influence in public management and the continuous information support to objective criteria of sensor networks, can stimulate the continued excellence of public services.

As cidades estão a seu tempo e a seu modo, modernizando os serviços prestados à população. Entre os diversos fatores que estão contribuindo para esta evolução estão a diversificação e proliferação de sensores, nos diversos domínios de serviços das cidades, e os novos canais de comunicação com os munícipes, entre eles, as redes sociais e mais recentemente os sistemas crowdsensing, motivados pelos anseios sociais, por melhores serviços públicos e pela popularização dos dispositivos móveis. Nesta direção, a eficiência administrativa é um fator essencial, uma vez que as cidades estão se mostrando mais complexas na medida em que cresce a população nas áreas urbanas. A utilização de técnicas de sistemas distribuídos para que múltiplos domínios de serviços usufruam da mesma infraestrutura computacional, pode auxiliar na eficiência das cidades, evitando gastos administrativos duplicados e até mesmo, possibilitando a correlação de eventos entre os serviços, favorecendo a identificação de fatores de causalidades e assim, a tomada de decisões administrativas mais objetivas e precisas. Neste contexto, este trabalho concentra-se na análise de um middleware direcionado à gestão de cidades para coleta, integração e interpretação dos dados de sensores, pertencentes aos serviços disponíveis da própria cidade, junto com os dados do sensoriamento colaborado pelos cidadãos. Para avaliação do conceito foi investigado o cenário de monitoração da conservação de vias públicas. Após 3 meses de coletas de dados por um sistema de sensoriamento automático, totalizando mais de 360 mil pontos e também mais de 90 relatórios pelo sensoriamento participativo, verificou-se que um sistema distribuído pode realizar a interpretação de séries históricas, engajar os munícipes apoiar a manutenção dos serviços da cidade e também indicar objetivamente aos gestores públicos os pontos que devem ser prioritariamente atendidos. Aliar ferramentas pelas quais o cidadão pode, de acordo com sua necessidade, convicção e altruísmo, exercer influência nos gestores públicos com o suporte de informação contínua e critérios objetivos das redes de sensores, pode estimular a continua excelência dos serviços públicos. / The cities in their own way and time are improving their services provided to the population. Among several factors that are contributing to this trend are the diversification and proliferation of sensors in various services domains of cities and new communication ways with citizens, for instance, social networks and more recently, crowdsensing systems, motivated by social expectations for better public services and the popularity of mobile devices. In this direction, administrative efficiency is a key factor, since the cities are proving more complex with increasing the population in urban areas. Techniques of distributed systems to share the same computing infrastructure to multiple service domains, can assist in the efficiency of cities, avoiding duplicate administrative costs and even allowing event correlation between services, providing the identification of causality factors, thus making management decisions more objective and accurate. In this context, this research focuses on analysis of a middleware directed to city management for collection, integration and interpretation of sensors data, present in city services, along with the sensing data contributed by citizens. For concept evaluation, was investigated the scenario of conservation of public streets. After 3 months of data collection by an automatic sensing system comprising more than 360 thousand points and also 94 reports of collaborative sensing, it was found that a distributed system can perform the interpretation of historical series; engage the citizens to support maintenance of city services and indicate objectively the points that should primarily be fix by public managers. Combining tools, which citizens can, according to their need, conviction, altruism, exert their own influence in public management and the continuous information support to objective criteria of sensor networks, can stimulate the continued excellence of public services.

Les réseaux sans fils et mobiles se sont énormément développés au cours de ces dernières années. Loin d'être réservés aux pays industrialisés, ces réseaux nécessitant une infrastructure fixe limitée se sont aussi imposés dans les pays émergents et les pays en voie de développement. En effet, avec un investissement structurel relativement très faible en comparaison de celui nécessaire à l'implantation d'un réseau filaire, ces réseaux permettent aux opérateurs d'offrir une couverture du territoire très large, avec un coût d'accès au réseau (prix du téléphone et des communications) tout à fait acceptable pour les utilisateurs. Aussi, il n'est pas surprenant qu'aujourd'hui, dans la majorité des pays, le nombre de téléphones sans fil soit largement supérieur à celui des téléphones fixes. Ce grand nombre de terminaux disséminé sur l'ensemble de la planète est un réservoir inestimable d'information dont une infime partie seulement est aujourd'hui exploitée. En effet, en combinant la position d'un mobile et sa vitesse de déplacement, il devient possible d'en déduire la qualité des routes ou du trafic routier. Dans un autre registre, en intégrant un thermomètre et/ou un hygromètre dans chaque terminal, ce qui à grande échelle impliquerait un coût unitaire dérisoire, ces terminaux pourraient servir de relai pour une météo locale plus fiable. Dans ce contexte, l'objectif de cette thèse consiste à étudier et analyser les opportunités offertes par l'utilisation des données issues des terminaux mobiles, de proposer des solutions originales pour le traitement de ces grands masses de données, en insistant sur les optimisations (fusion, agrégation, etc.) pouvant être réalisées de manière intermédiaire dans le cadre de leur transport vers les(s) centre(s) de stockage et de traitement, et éventuellement d'identifier les données non disponibles aujourd'hui sur ces terminaux mais qui pourraient avoir un impact fort dans les années à venir. Un prototype présentant un exemple typique d'utilisation permettra de valider les différentes approches. / Mobile and wireless networks have developed enormously over the recent years. Far from being restricted to industrialized countries, these networks which require a limited fixed infrastructure, have also imposed in emerging countries and developing countries. Indeed, with a relatively low structural investment as compared to that required for the implementation of a wired network, these networks enable operators to offer a wide coverage of the territory with a network access cost (price of devices and communications) quite acceptable to users. Also, it is not surprising that today, in most countries, the number of wireless phones is much higher than landlines. This large number of terminals scattered across the planet is an invaluable reservoir of information that only a tiny fraction is exploited today. Indeed, by combining the mobile position and movement speed, it becomes possible to infer the quality of roads or road traffic. On another level, incorporating a thermometer and / or hygrometer in each terminal, which would involve a ridiculous large-scale unit cost, these terminals could serve as a relay for more reliable local weather. In this context, the objective of this thesis is to study and analyze the opportunities offered by the use of data from mobile devices to offer original solutions for the treatment of these big data, emphasizing on optimizations (fusion, aggregation, etc.) that can be performed as an intermediate when transferred to center(s) for storage and processing, and possibly identify data which are not available now on these terminals but could have a strong impact in the coming years. A prototype including a typical sample application will validate the different approaches.

Aujourd’hui, il y a une demande croissante de fournir les informations d'environnement en temps réel tels que la qualité de l'air, le niveau de bruit, état du trafic, etc. pour les citoyens dans les zones urbaines a des fins diverses. La prolifération des capteurs de smartphones et la mobilité de la population font des Mobile Crowdsensing (MCS) un moyen efficace de détecter et de recueillir des informations a un coût faible de déploiement. En MCS, au lieu de déployer capteurs statiques dans les zones urbaines, les utilisateurs avec des périphériques mobiles jouent le rôle des capteurs de mobiles à capturer les informations de leurs environnements, et le réseau de communication (3G, WiFi, etc.) pour le transfert des données pour MCS applications. En général, l'application MCS (ou tâche) non seulement exige que chaque participant de périphérique mobile de posséder la capacité de réception missions de télédétection, de télédétection et de renvoi détecte résultats vers un serveur central, il exige également de recruter des participants, attribuer de télédétection tâches aux participants, et collecter les résultats obtenues par télédétection ainsi que représente les caractéristiques de la cible zone de détection. Afin de recruter un nombre suffisant de participants, l'organisateur d'une MCS tâche devrait considérer la consommation énergétique causée par MCS applications pour chaque participant et les questions de protection dans la vie privée, l'organisateur doit donner a chaque participant un certain montant des incitations comme un encouragement. En outre, afin de recueillir les résultats obtenues par télédétection et représentant la région cible, l'organisateur doit s'assurer que les données de télédétection qualité des résultats obtenues par télédétection, p. ex., la précision et la spatio-temporelle la couverture des résultats obtenus par télédétection. Avec la consommation d'énergie, la protection de la vie privée, les mesures d'incitation, de télédétection et qualité des données à l'esprit, dans cette thèse nous avons étudié quatre problèmes d'optimisation de mobile crowdsensing et mené après quatre travaux de recherche [...] / Nowadays, there is an increasing demand to provide real-time environment information such as air quality, noise level, traffic condition, etc. to citizens in urban areas for various purposes. The proliferation of sensor-equipped smartphones and the mobility of people are making Mobile Crowdsensing (MCS) an effective way to sense and collect information at a low deployment cost. In MCS, instead of deploying static sensors in urban areas, people with mobile devices play the role of mobile sensors to sense the information of their surroundings and the communication network (3G, WiFi, etc.) is used to transfer data for MCS applications. Typically, an MCS application (or task) not only requires each participant's mobile device to possess the capability of receiving sensing tasks, performing sensing and returning sensed results to a central server, it also requires to recruit participants, assign sensing tasks to participants, and collect sensed results that well represents the characteristics of the target sensing region. In order to recruit sufficient participants, the organizer of the MCS task should consider energy consumption caused by MCS applications for each individual participant and the privacy issues, further the organizer should give each participant a certain amount of incentives as encouragement. Further, in order to collect sensed results well representing the target region, the organizer needs to ensure the sensing data quality of the sensed results, e.g., the accuracy and the spatial-temporal coverage of the sensed results. With the energy consumption, privacy, incentives, and sensing data quality in mind, in this thesis we have studied four optimization problems of mobile crowdsensing and conducted following four research works: • EEMC - In this work, the MCS task is splitted into a sequence of sensing cycles, we assume each participant is given an equal amount of incentive for joining in each sensing cycle; further, given the target region of the MCS task, the MCS task aims at collecting an expected number of sensed results from the target region in each sensing cycle.Thus, in order to minimize the total incentive payments and the total energy consumption of the MCS task while meeting the predefined data collection goal, we propose EEMC which intends to select a minimal number of anonymous participants to join in each sensing cycle of the MCS task while ensuring an minimum number of participants returning sensed results. • EMC3 - In this work, we follow the same sensing cycles and incentives assumptions/settings from EEMC; however, given a target region consisting of a set of subareas, the MCS task in this work aims at collecting sensed results covering each subarea of the target region in each sensing cycle (namely full coverage constraint).Thus, in order to minimize the total incentive payments and the total energy consumption of the MCS task under the full coverage constraint, we propose EMC3 which intends to select a minimal number of anonymous participaNts to join in each sensing cycle of the MCS task while ensuring at least one participant returning sensed results from each subarea. • CrowdRecruiter - In this work, we assume each participant is given an equal amount of incentive for joining in all sensing cycles of the MCS task; further, given a target region consisting of a set of subareas, the MCS task aims at collecting sensed results from a predefined percentage of subareas in each sensing cycle (namely probabilistic coverage constraint).Thus, in order to minimize the total incentive payments the probabilistic coverage constraint, we propose CrowdRecruiter which intends to recruit a minimal number of participants for the whole MCS task while ensuring the selected participants returning sensed results from at least a predefined percentage of subareas in each sensing cycle. • CrowdTasker - In this work, we assume each participant is given a varied amount of incentives according to [...]

Le mobile crowdsensing consiste à acquérir des données géolocalisées et datées d'une foule de capteurs mobiles (issus de ou connectés à des smartphones). Dans cette thèse, nous nous intéressons au traitement des données issues du mobile crowdsensing environnemental. En particulier, nous proposons de revisiter le problème d'étalonnage aveugle de capteurs comme un problème informé de factorisation matricielle à données manquantes, où les facteurs contiennent respectivement le modèle d'étalonnage fonction du phénomène physique observé (nous proposons des approches pour des modèles affines et non linéaires) et les paramètres d'étalonnage de chaque capteur. Par ailleurs, dans l'application de surveillance de la qualité de l'air que nous considérons, nous supposons avoir à notre disposition des mesures très précises mais distribuées de manière très parcimonieuse dans le temps et l'espace, que nous couplons aux multiples mesures issues de capteurs mobiles. Nos approches sont dites informées car (i) les facteurs matriciels sont structurés par la nature du problème, (ii) le phénomène observé peut être décomposé sous forme parcimonieuse dans un dictionnaire connu ou approché par un modèle physique/géostatistique, et (iii) nous connaissons la fonction d'étalonnage moyenne des capteurs à étalonner. Les approches proposées sont plus performantes que des méthodes basées sur la complétion de la matrice de données observées ou les techniques multi-sauts de la littérature, basées sur des régressions robustes. Enfin, le formalisme informé de factorisation matricielle nous permet aussi de reconstruire une carte fine du phénomène physique observé. / Mobile crowdsensing aims to acquire geolocated and timestamped data from a crowd of sensors (from or connected to smartphones). In this thesis, we focus on processing data from environmental mobile crowdsensing. In particular, we propose to revisit blind sensor calibration as an informed matrix factorization problem with missing entries, where factor matrices respectively contain the calibration model which is a function of the observed physical phenomenon (we focus on approaches for affine or nonlinear sensor responses) and the calibration parameters of each sensor. Moreover, in the considered air quality monitoring application, we assume to pocee- some precise measurements- which are sparsely distributed in space and time - that we melt with the multiple measurements from the mobile sensors. Our approaches are "informed" because (i) factor matrices are structured by the problem nature, (ii) the physical phenomenon can be decomposed using sparse decomposition with a known dictionary or can be approximated by a physical or a geostatistical model, and (iii) we know the mean calibration function of the sensors to be calibrated. The proposed approaches demonstrate better performances than the one based on the completion of the observed data matrix or the multi-hop calibration method from the literature, based on robust regression. Finally, the informed matrix factorization formalism also provides an accurate reconstruction of the observed physical field.

Submitted by Cássia Santos (cassia.bcufg@gmail.com) on 2015-10-26T10:10:03Z No. of bitstreams: 2 Dissertação - Paulo César Ferreira Melo - 2014.pdf: 3222791 bytes, checksum: f18cd58c678bb5d11f8bd0cabb32f099 (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) / Approved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2015-10-26T13:03:05Z (GMT) No. of bitstreams: 2 Dissertação - Paulo César Ferreira Melo - 2014.pdf: 3222791 bytes, checksum: f18cd58c678bb5d11f8bd0cabb32f099 (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) / Made available in DSpace on 2015-10-26T13:03:05Z (GMT). No. of bitstreams: 2 Dissertação - Paulo César Ferreira Melo - 2014.pdf: 3222791 bytes, checksum: f18cd58c678bb5d11f8bd0cabb32f099 (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) Previous issue date: 2014-10-15 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES / Recent advances in ubiquitous computing have contributed to the rise of an emerging category of mobile devices that have computational and sensing capabilities, such as smartphones and wearable devices. The widespread use of these devices connected by communication networks contribute to the evolution of the Internet of Things. The presence of these mobile devices increases the chance for the development of applications using the sensing ability of these devices to measure, and understand the environmental indicators. Furthemore, data sensed by these applications can be shared among different mobile devices, giving rise to a paradigm called mobile crowdsensing. The complexity of applications in this domain is associated with factors such as interoperability between different mobile devices, data identification and capture from these devices, and adaptation of their use in heterogeneous and dynamic environments. Software engineering approaches such as Model-Driven Engineering (MDE) and, more specifically, models at runtime are an effective way of dealing with this complexity. We propose the use of an approach based on models at runtime for creating and processing mobile crowdsensing queries.We show how this approach can be used by defining a domain-specific modeling language for the mobile crowdsensing domain, called CSML. We built and validated the CSML metamodel which captures the main aspects of the domain, and its execution environment, which consists of an execution engine for models described in CSML, called CSVM. This approach facilitates the specification of mobile crowdsensing queries, also enabling their dynamic change during their processing. / Recentes avanços na computação ubíqua colaboraram para a ascensão de uma categoria emergente de dispositivos móveis que apresentam capacidades computacionais e de sensoriamento, tais como smartphones e dispositivos vestíveis. A proliferação desses dispositivos e sua conexão por meio de redes de comunicação contribui para a evolução da Internet das Coisas. A presença desses dispositivos móveis aumenta a oportunidade para o desenvolvimento de aplicações que utilizam sua capacidade de sensoriamento a fim de medir, inferir e entender os indicadores do ambiente. Por sua vez, os dados sensoriados por essas aplicações podem ser compartilhados entre diferentes dispositivos móveis, dando origem ao paradigma denominado CrowdSensing móvel. A complexidade de aplicações pertencentes ao domínio de CrowdSensing móvel está associada a fatores como interoperabilidade entre diferentes dispositivos móveis, identificação e captação de dados provenientes desses dispositivos e adaptação de seu uso em ambientes heterogêneos e dinâmicos. Abordagens baseadas na Engenharia Dirigida por Modelos (MDE), como modelos em tempo de execução constituem uma forma de lidar com complexidade desse domínio de aplicações. Neste trabalho propomos o uso de uma abordagem dirigida por modelos em tempo de execução para criação e processamento de consultas de crowdsensing móvel que são um importante elemento de aplicações de crowdsensing. Mostramos como essa abordagem pode ser empregada por meio da definição de uma linguagem de modelagem específica para o domínio de crowdsensing móvel, denominada CSML. Neste sentido, construímos e validamos o metamodelo da CSML, que captura os principais aspectos do domínio e seu ambiente de execução, que consiste em uma máquina de execução de modelos descritos em CSML, denominada CSVM . Essa abordagem dirigida por modelos facilita a especificação de consultas de crowdsensing móvel, além de possibilitar a alteração dinâmica dessas consultas durante seu processamento.

Participatory Sensing Systems (PSS) are a type of Mobile Crowdsensing System where users voluntarily participate in contributing information. Task initiators create tasks, targeting specific data that needs to be gathered by the users’ device sensors. Such systems have been designed with different requirements, such as data trustworthiness, accountability, and incentives, in a secure and private way. However, it is complex to protect user privacy without affecting the performance of the rest of the system. For example, with task assignment, either the user authenticates anonymously, or discloses its sensors for an efficient allocation. If the user identity is hidden from the system, it could receive a task it cannot perform. This thesis aims to design an anonymous authentication model for PSS based on privacy-preserving attribute-based signatures. The proposed solution allows the Participatory Sensing System to enforce sensor requirements for efficient task allocation. In addition to the design, experiments measuring the performance of the operations are included in the thesis, to prove it is suitable for real-world scenarios. / Participatory Sensing Systems (PSS) är en typ av mobilt Crowdsensing-system där användare frivilligt deltar i att bidra med information. Aktivitetsinitiatorer skapar uppgifter, inriktade på specifik data som behöver samlas in av användarnas enhetssensorer. Sådana system har utformats med olika krav, såsom datatillförlitlighet, ansvarighet och incitament, på ett säkert och privat sätt. Det är dock komplicerat att skydda användarnas integritet utan att påverka prestandan för resten av systemet. Till exempel, med uppgiftstilldelning, antingen autentiserar användaren anonymt eller avslöjar sina sensorer för en effektiv tilldelning. Om användaridentiteten är dold från systemet kan den få en uppgift som den inte kan utföra. Denna avhandling syftar till att designa en anonym autentiseringsmodell för PSS baserad på integritetsbevarande attributbaserade signaturer. Den föreslagna lösningen gör det möjligt för Participatory Sensing System att upprätthålla sensorkrav för effektiv uppgiftsallokering. Utöver designen ingår experiment som mäter verksamhetens prestanda i avhandlingen, för att bevisa att den är lämplig för verkliga scenarier.

Submitted by Geyciane Santos (geyciane_thamires@hotmail.com) on 2015-06-17T15:44:03Z No. of bitstreams: 1 Dissertação -Luis Victor Coutinho Menezes.pdf: 1659955 bytes, checksum: af6a8fcc18a270f59fe2aa0738b77b55 (MD5) / Approved for entry into archive by Divisão de Documentação/BC Biblioteca Central (ddbc@ufam.edu.br) on 2015-06-17T20:46:16Z (GMT) No. of bitstreams: 1 Dissertação -Luis Victor Coutinho Menezes.pdf: 1659955 bytes, checksum: af6a8fcc18a270f59fe2aa0738b77b55 (MD5) / Approved for entry into archive by Divisão de Documentação/BC Biblioteca Central (ddbc@ufam.edu.br) on 2015-06-17T20:47:18Z (GMT) No. of bitstreams: 1 Dissertação -Luis Victor Coutinho Menezes.pdf: 1659955 bytes, checksum: af6a8fcc18a270f59fe2aa0738b77b55 (MD5) / Made available in DSpace on 2015-06-17T20:47:19Z (GMT). No. of bitstreams: 1 Dissertação -Luis Victor Coutinho Menezes.pdf: 1659955 bytes, checksum: af6a8fcc18a270f59fe2aa0738b77b55 (MD5) Previous issue date: 2014-05-30 / CAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Every day mobile devices are perfected, gain new features, new sensors, better hardware and, therefore, greater ability to measure information of the medium they are used and to process them properly. Moreover, the tasks of day-to-day have been automated. On that basis, the trend that, in the future, mobile devices will have the ability to perform measurements and replace the need deployment of a fixed infrastructure responsible for collecting certain information, simple tasks - like checking prices - could be extinguished. Based on this, the participatory sensing and applying techniques collaboration systems have been gaining focus, and especially improving the collection information. Many are collaborative applications that inform your users they are wondering and thereby create a collaborative community, able to help with collections and receive information through other users. However, although similar in its base, there are tools capable auxiliary developing these applications more easily; reducing time and effort; saving resources to focus on developing better and finishing applications; enabling the creation of the best ways to encourage users and, consequently, better collection and an active community longer. For these reasons, this work proposes a framework capable of assisting in development of systems that integrate the various concepts shown above, with integration into social networks and aid in application development. To this, they were raised important requirements for application of this area from which the architecture and tool design was created. Furthermore, the paper presents a prototype an application using the framework, in order to serve as proof concept thereof. / A cada dia dispositivos móveis são aperfeiçoados, ganham novas funcionalidades, novos sensores, hardware melhor e, com isso, maior capacidade de medir informações do meio em que são utilizados e de processá-las de forma correta. Além disso, as tarefas do dia-a-dia vêm sendo automatizadas. Com base nisso, a tendência de que, no futuro, dispositivos móveis terão a capacidade de realizar medições e substituírem a necessidade de implantação de uma infra-estrutura fixa responsável pela coleta de determinada informação, tarefas simples - como a verificação de preços - poderão ser extinta. Com base nisso, a área de sensoriamento participativo e a aplicação de técnicas de colaboração em sistemas vêm ganhando foco e, principalmente, aprimorando a coleta de informações. Diversas são as aplicações colaborativas que informam aos seus usuários o que estes estão querendo saber e, com isso, criam uma comunidade colaborativa, capaz de ajudar com coletas e receber informações através de outros usuários. No entanto, apesar de parecidas em sua base, não existem ferramentas capazes de auxiliar o desenvolvimento destas aplicações de forma mais fácil; reduzindo tempo e esforço; poupando recursos para o foco em melhor desenvolvimento e acabamento de suas aplicações; possibilitando a criação de melhores formas de incentivo aos usuários e, consequentemente, melhores coletas e uma comunidade ativa por mais tempo. Por estes motivos, esta dissertação propõe um framework capaz de auxiliar no desenvolvimento de sistemas que integram os diversos conceitos mostrados acima, com integração em redes sociais e auxílio no desenvolvimento da aplicação. Para isso, foram levantados requisitos importantes às aplicações desta área a partir dos quais a arquitetura e projeto da ferramenta foi criada. Além disso, o trabalho apresenta um protótipo de uma aplicação utilizando o framework, com a finalidade de servir como prova de conceito do mesmo.