This paper introduces SudokuSens, a generative framework for automated generation of training data in machine-learning-based Internet-of-Things (IoT) applications, such that the generated synthetic data mimic experimental configurations not encountered during actual sensor data collection. The framework improves the robustness of resulting deep learning models, and is intended for IoT applications where data collection is expensive. The work is motivated by the fact that IoT time-series data entangle the signatures of observed objects with the confounding intrinsic properties of the surrounding environment and the dynamic environmental disturbances experienced. To incorporate sufficient diversity into the IoT training data, one therefore needs to consider a combinatorial explosion of training cases that are multiplicative in the number of objects considered and the possible environmental conditions in which such objects may be encountered. Our framework substantially reduces these multiplicative training needs. To decouple object signatures from environmental conditions, we employ a Conditional Variational Autoencoder (CVAE) that allows us to reduce data collection needs from multiplicative to (nearly) linear, while synthetically generating (data for) the missing conditions. To obtain robustness with respect to dynamic disturbances, a session-aware temporal contrastive learning approach is taken. Integrating the aforementioned two approaches, SudokuSens significantly improves the robustness of deep learning for IoT applications. We explore the degree to which SudokuSens benefits downstream inference tasks in different data sets and discuss conditions under which the approach is particularly effective.

Foundational models have caused a paradigm shift in the way artificial intelligence (AI) systems are built. They have had a major impact in natural language processing (NLP), and several other domains, not only reducing the amount of required labeled data or even eliminating the need for it, but also significantly improving performance on a wide range of tasks. We argue foundation models can have a similar profound impact on network traffic analysis, and management. More specifically, we show that network data shares several of the properties that are behind the success of foundational models in linguistics. For example, network data contains rich semantic content, and several of the networking tasks (e.g., traffic classification, generation of protocol implementations from specification text, anomaly detection) can find similar counterparts in NLP (e.g., sentiment analysis, translation from natural language to code, out-of-distribution). However, network settings also present unique characteristics and challenges that must be overcome. Our contribution is in highlighting the opportunities and challenges at the intersection of foundation models and networking.

As neural networks gain importance with several successful applications of them, this paper raises the question of how they can be applied in the context of coalition operations. A key challenge in military coalition operations is that of energy and severe bandwidth constraints. We address this challenge by exploring the use of Deep Neural Networks (DNNs) and splitting them across multiple edge nodes. Further, we explore the idea of using spiking neural networks that can lower the energy consumption significantly. Preliminary results show that both these approaches can have significant impact on coalition operations.

Traditional service-based applications, in fixed networks, are typically constructed and managed centrally and assume stable service endpoints and adequate network connectivity. Constructing and maintaining such applications in dynamic heterogeneous wireless networked environments, where limited bandwidth and transient connectivity are commonplace, presents significant challenges and makes centralized application construction and management impossible. In this demonstration we present an architecture which is capable of providing an adaptable and resilient method for on-demand decentralized construction and management of complex time-critical applications in such environments. The approach uses a Vector Symbolic Architecture (VSA) to compactly represent an application as a single semantic vector that encodes the service interfaces, workflow, and the time-critical constraints required. By extending existing services interfaces, with a simple cognitive layer that can interpret and exchange the vectors, we show how the required services can be dynamically discovered and interconnected in a completely decentralized manner. There are a large number of workflow systems designed to work in various scientific domains, including support for the Internet of Things (IoT). One such workflow system is Node-RED, which is designed to bring workflow-based programming to IoT. The main focus of this demonstration is to show how we can migrate Node-RED workflows into a decentralized execution environment, so that such workflows can run on Edge networks.

With the widespread use of GPS-equipped smartphones and Internet of Things devices, a huge amount of data with location information is being generated at an unprecedented rate. To gain a deeper insight into such a plethora of spatial data, scientists and engineers are widely using spatial queries for their big data applications. However, because of not only the massive spatial data size but also the complexity of spatial query processing, they are struggling to efficiently process the spatial queries. In this paper, we propose lightweight and scalable indexing and querying services for big spatial data stored in distributed storage systems or graph-based systems. Our spatial services have several advantages over existing approaches. First, our services can be easily applied to existing storage systems or graph-based models without modifying the internal implementation of existing systems/models. Second, our services achieve high pruning power by efficiently selecting only relevant spatial objects based on a simple yet effective filter. Third, our services support a customizable and easy-to-use control of index data size by adjusting the precision of indexed geometries. Lastly, our services support efficient updates of spatial data. Our experimental results using real-world datasets validate the effectiveness and efficiency of our spatial services.

Vector space representations of text have increased in popularity and are used in various text classification problems. We present Doc2Img, a new approach to create document vectors that improves upon existing approaches such as Word2Vec and Doc2Vec in capturing similarities between words within a document and the differences across documents. We apply this new vector space representation to the problem of deriving the sensor requirements of apps (for smartphones and IoT devices) by learning a classification model using document vectors. We show that this learned model outperforms existing vector space representations (Word2Vec and Doc2Vec) by more than 10%. Further, this model can predict with an average accuracy of 75% and greater than 85% on the top-20 sensor requirements for 300 different applications.

Recent advances in computing infrastructure constitute edge nodes prominently (e.g., smartphones, cars) in their computation pipeline. Applications that combine sensor/IoT data from edge devices in a distributed fashion are growing. Dynamically composed applications that combine resources from edge nodes and the cloud are becoming common in various domains including urban and military settings. A key challenge in such applications is to bridge the gap between the application's description and its IoT resource requirements, where the application description is unstructured text and its IoT requirements are structured. In this paper, we describe an approach that develops a model which given unstructured text description of the service predicts its IoT sensor requirements. Our model can predict with an average accuracy of 77% and up to 88% on the top-20 sensor requirements for 300 different applications.

This paper presents improved results on classifying electroencephalography (EEG) recordings using deep learning. The task is to classify movements that the subject is thinking about (motor imagery), using only the recorded electrical activities on the scalp. The challenges are: poor signal-to-noise ratio; interference from numerous sources such as electrical line noise, muscle activity, and eye movements; considerable variability between individuals and even recording sessions. Traditional signal processing techniques such as frequency band analysis, common spatial pattern (CSP) algorithm or independent component analysis (ICA) fall short due to their limited capacity. Thanks to the rise of big data in healthcare, medical recordings now come in abundance. Therefore deep learning which relies on large amounts of training data is becoming the new cutting edge tool. We present a significant improvement of classification accuracy on the Brain-Computer Interfaces Competition IV dataset (2a), and compare the results of various state of the art neural network structures.

Trajectory clustering techniques help discover interesting insights from moving object data, including common routes for people and vehicles, anomalous sub-trajectories, etc. Existing trajectory clustering techniques fail to take in to account the uncertainty present in location data. In this paper, we investigate the problem of clustering trajectory data and propose a novel algorithm for clustering similar full and sub-trajectories together while modeling uncertainty in this data. We describe the necessary pre-processing techniques for clustering trajectory data, namely techniques to discretize raw location data using Possible World semantics to capture the inherent uncertainty in location data, and to segment full trajectories in to meaningful sub-trajectories. As a baseline, we extend the well known K-means algorithm to cluster trajectory data. We then describe and evaluate a new trajectory clustering algorithm, SOM-TC (Self-Organizing Map Based Trajectory Clustering), that is inspired from the self-organizing map technique and is at least 4x faster than the baseline K-means and current density based clustering approaches.

Emerging distributed in-memory computing frameworks, such as Apache Spark, can process a huge amount of cached data within seconds. This remarkably high efficiency requires the system to well balance data across tasks and ensure data locality. However, it is challenging to satisfy these requirements for applications that operate on a collection of dynamically loaded and evicted datasets. The dynamics may lead to time-varying data volume and distribution, which would frequently invoke expensive data re-partition and transfer operations, resulting in high overhead and large delay. To address this problem, we present Stark, a system specifically designed for optimizing in-memory computing on dynamic dataset collections. Stark enforces data locality for transformations spanning multiple datasets (e.g., join and cogroup) to avoid unnecessary data replications and shuffles. Moreover, to accommodate fluctuating data volume and skeweddata distribution, Stark delivers elasticity into partitions to balance task execution time andreduce job makespan. Finally, Stark achieves bounded failure recovery latency byoptimizing the data checkpointing strategy. Evaluations on a 50-server cluster show that Stark reduces the job makespan by 4X and improves system throughput by 6X compared to Spark.

Location data collection at a societal scale is increasingly becoming common - examples of this are call and data detail records in telecommunication companies, GPS samples collected by car companies, and GPS samples from mobile devices in mapping companies (e.g., Google, Microsoft). Such large scale mobility datasets have applications in urban planning, network planning, surveillance, and real-time traffic estimations. This paper addresses the problem of subsampling location traces while preserving the amount of information present in such datasets. We present a novel subsampling technique that is based on a hierarchical geographical encoding mechanism (geohash), that allows for efficient spatial cluster sampling. We analyze this subsampling technique through various information theoretic measures to quantify the total "amount" of information in a dataset from a location trace perspective and evaluate these metrics in the context of two large scale mobility datasets from telecommunication companies - one is that of call detail records and the second is that of data detail records. We show that subsampling data in both these cases by as much as 75% does not significantly reduce the total amount of information, i.e. the dataset can be used similar to the original version. This paves way for the creation of better space and CPU efficient models that can support various applications reliant on collective location traces.

This paper develops an algorithm that exploits picture-oriented social networks to localize urban events. We choose picture-oriented networks because taking a picture requires physical proximity, thereby revealing the location of the photographed event. Furthermore, most modern cell phones are equipped with GPS, making picture location, and time metadata commonly available. We consider Instagram as the social network of choice and limit ourselves to urban events (noting that the majority of the world population lives in cities). The paper introduces a new adaptive localization algorithm that does not require the user to specify manually tunable parameters. We evaluate the performance of our algorithm for various real-world datasets, comparing it against a few baseline methods. The results show that our method achieves the best recall, the fewest false positives, and the lowest average error in localizing urban events.

When modeling geo-spatial data, it is critical to capture spatial correlations for achieving high accuracy. Spatial Auto-Regression (SAR) is a common tool used to model such data, where the spatial contiguity matrix (W) encodes thespatial correlations. However, the efficacy of SAR is limited by two factors. First, it depends on the choice of contiguity matrix, which is typically not learnt from data, but instead, is assumed to be known apriori. Second, it assumes that the observations can be explained by linear models. In this paper, we propose a Convolutional Neural Network (CNN) framework to model geo-spatial data (specifically housing prices), to learn the spatial correlations automatically. We show that neighborhood information embedded in satellite imagery can be leveraged to achieve the desired spatial smoothing. An additional upside of our framework is the relaxation of linear assumption on the data. Specific challenges we tackle while implementing our framework include, (i) how much of the neighborhood is relevant while estimating housing prices? (ii) what is the right approach to capture multiple resolutions of satellite imagery? and (iii) what other data-sources can help improve the estimation of spatial correlations? We demonstrate a marked improvement of 57% on top of the SAR baseline through the use of features from deep neural networks for the cities of London, Birmingham and Liverpool.

In many mobile sensing applications, devices need to discover new neighbors and maintain the rendezvous with known neighbors continuously. Due to the limited energy supply, these devices have to duty cycle their radios to conserve the energy and bandwidth, making neighbor discovery and rendezvous maintenance even more challenging. To date, the main mechanism for device discover and rendezvous maintenance in existing solutions is pairwise, direct one-hop communication. We argue that such pairwise direct communication is sufficient but not necessary: there exist unnecessary active slots that can be eliminated, without affecting discovery and rendezvous. In this work, we propose a novel concept ofextended quorum system, which leveragesindirectdiscovery to further conserve energy. Specifically, we usequorum graphto capture all possible information flow paths where knowledge about known-neighbors can propagate among devices. By eliminating redundant paths, we can reduce the number of active slots significantly. Since a quorum graph can characterize arbitrary active schedules of mobile devices, our work can be broadly used to improve many existing quorum-based discovery and rendezvous solutions. We comprehensively evaluate$EQS$in three different scales of networks, and the results show that$EQS$reduces as much as 55 percent energy consumption with a maximal 5 percent increase in latency for existing solutions. To test the real-world values of$EQS$, we further propose a taxicab dispatching application called$EQS$-dispatch to navigate taxicab drivers to the area with less competition based on the discovery results of nearby taxicabs.

Participatory sensing services based on mobile phones constitute an important growing area of mobile computing. Most services start small and hence are initially sparsely deployed. Unless a mobile service adds value while sparsely deployed, it may not survive conditions of sparse deployment. The paper offers a generic solution to this problem and illustrates this solution in the context ofGreenGPS; a navigation service that allows drivers to find the most fuel-efficient routes customized for their vehicles between arbitrary end-points. Specifically, when the participatory sensing service is sparsely deployed, we demonstrate a general framework for generalization from sparse collected data to produce models extending beyond the current data coverage. This generalization allows the mobile service to offer value under broader conditions. GreenGPS uses our developed participatory sensing infrastructure and generalization algorithms to perform inexpensive data collection, aggregation, and modeling in an end-to-end automated fashion. The models are subsequently used by our backend engine to predict customized fuel-efficient routes for both members and non-members of the service. GreenGPS is offered as a mobile phone application and can be easily deployed and used by individuals. A preliminary study of our green navigation idea was performed in[1], however, the effort was focused on a proof-of-concept implementation that involved substantial offline and manual processing. In contrast, the results and conclusions in the current paper are based on a more advanced and accurate model and extensive data from a real-world phone-based implementation and deployment, which enables reliable and automatic end-to-end data collection and route recommendation. The system further benefits from lower cost and easier deployment. To evaluate the green navigation service efficiency, we conducted a user subject study consisting of 22 users driving different vehicles over the course of several months in Urbana-Champaign, IL. The experimental results using the collected data suggest that fuel savings of 21.5 over the fastest, 11.2 percent over the shortest, and 8.4 percent over the Garmin eco routes can be achieved by following GreenGPS green routes. The study confirms that our navigation service can survive conditions of sparse deployment and at the same time achieve accurate fuel predictions and lead to significant fuel savings.

Recent sensor network literature investigated the use of social networks as sensor networks, and formulated a physical event localization problem from social network data. This paper improves on the above results by formulating a joint localization problem of events and sources, leveraging the fact that sources on social networks often have a location affinity: They tend to comment more on events in their locations of interest. While social networks, such as Twitter, do not offer source location information for the majority of sources, we show that our algorithms for jointly inferring source and event location significantly improve localization quality by mutually enhancing location estimation of both events and sources. We evaluate the performance of our algorithm both in simulation and using Twitter data about current events. The results show that joint inference of source and event location allows us to localize many more of the events identified in real-world datasets.

The papers in this special section provide the opportunity for researchers, practitioners, and application developers to review and discuss the state-of-the-art and trends of MCS (mobile crowd sensing)techniques and applications or propose new solutions. The ubiquitous sensor-rich mobile devices (e.g., smartphones, wearable devices, and smart vehicles) have been playing an increasing important role in the evolution of the Internet of Things (IoTs), which bridges the digital space and physical space at a societal scale. Their powerful computing/communication capacities, huge population, and inherent mobility make mobile-device networks a much more flexible and cost-effective IoT solution than static sensor networks.

As a supporting primitive of many mobile applications, neighbor discovery identifies nearby devices so that they can exchange information and collaborate in a peer-to-peer manner. To date, discovery schemes trade a long latency for energy efficiency and require a collaborative duty cycle pattern, and thus they are not suitable for interactive mobile applications where a user is unable to configure others’ devices. In this article, we propose Acc , which serves as an on-demand generic discovery accelerating middleware for many deterministic neighbor discovery schemes. Acc leverages the discovery capabilities of neighbor devices, supporting both direct and indirect neighbor discoveries. Further, we present a proactive online rendezvous maintenance mechanism, which is used to reduce delays for the detection of leaving of neighbors. Our evaluations show that Acc -assisted discovery schemes reduce latency by up to 51.8% compared to schemes consuming the same amount of energy. More importantly, to prove the real-world value of Acc , we further present and evaluate a Crowd-Alert application where Acc is employed by taxi drivers to accelerate selection of a direction with fewer competing taxis and more potential passengers, based on a 280GB dataset of more than 14,000 taxis in Shenzhen, the most crowded city in China.

This paper complements the large body of social sensing literature by developing means for augmenting sensing data with inference results that "fill-in" missing pieces. Unlike trend-extrapolation methods, we focus on prediction in disaster scenarios where disruptive trend changes occur. A set of prediction heuristics (and a standard trend extrapolation algorithm) are compared that use either predominantly-spatial or predominantly-temporal correlations for data extrapolation purposes. The evaluation shows that none of them do well consistently. This is because monitored system state, in the aftermath of disasters, alternates between periods of relative calm and periods of disruptive change (e.g., aftershocks). A good prediction algorithm, therefore, needs to intelligently combine time-based data extrapolation during periods of calm, and spatial data extrapolation during periods of change. The paper develops such an algorithm. The algorithm is tested using data collected during the New York City crisis in the aftermath of Hurricane Sandy in November 2012. Results show that consistently good predictions are achieved. The work is unique in addressing the bi-modal nature of damage propagation in complex systems subjected to stress, and offers a simple solution to the problem.

Spatial queries are widely used in many data mining and analytics applications. However, a huge and growing size of spatial data makes it challenging to process the spatial queries efficiently. In this paper we present a lightweight and scalable spatial index for big data stored in distributed storage systems. Experimental results show the efficiency and effectiveness of our spatial indexing technique for different spatial queries.

The proliferation of location sensors has resulted in the wide availability of historical location and time data. A prominent use of such data is to develop models to estimate travel-times (between arbitrary points in a city) accurately. The problem of travel-time estimation/prediction has been well studied in the past, where the proposed techniques span a spectrum of statistical methods, such as k-nearest neighbors, Gaussian regression, Artificial Neural Networks, and Support Vector Machines. In this paper, we demonstrate that, contrary to popular intuition, empirical data suggests that simple travel time predictors come very close to the fundamental error bounds achievable in delay prediction. We derive such bounds by estimating entropy that remains in travel time distributions, even after all spatio-temporal delay-influencing factors have been accounted for. Our results are based on analysis of cab traces from New York City, that feature 15 million trips. While we cannot claim generalizability to other cities, the results suggest the diminishing return of complex travel-time predictors due to the inherent nature of uncertainty in trip delays. We demonstrate a simple travel-time predictor, whose error approaches the uncertainty bound. It predicts delay based only on total distance traveled and time-of-day and is close to the optimal solution.

The continued explosion of Twitter data has opened doors for many applications, such as location-based advertisement and entertainment using smartphones. Unfortunately, only about 0.58 percent of tweets are geo-tagged to date. To tackle the location sparseness problem, this paper presents a methodic

Hidden Markov Models (HMMs) based map matching - that matches a sequence of location samples to a road network - has received a lot of traction in recent years. In this paper we revisit the basic assumption underlying HMM-based map matching algorithms, namely, the hypothesis that the true mobility is Markovian. We use the Chapman-Kolmogorov test and argue that mobility is non-Markovian (especially when the moving object has an intent to reach a specific destination) using thousands of real taxicab mobility datasets spanning several weeks. Based on these observations we present an alternate approach to the map matching problem that relies exclusively on shortest path computations, which are at most linear in the number of road segments, and thus avoids expensive complexity of HMM-based map matching algorithms (e.g., using a Viterbi decoder). We present extensive experimental results to show that our approach vastly outperforms HMM-based approaches in terms of both computational complexity and accuracy.

Taxicabs equipped with real-time location sensing devices are increasingly becoming popular. Such location traces are a rich source of information and can be used for congestion pricing, taxicab placement, and improved city planning. An important problem to enable these application is to identify human mobility patterns from the taxicab traces, which translates to being able to identify pickup and dropoff points for a particular trip. In this paper, we show that while past approaches are effective in detecting hotspots using location traces, they are largely ineffective in identifying trips (pairs of pickup and dropoff points). We propose the use of a graph theory concept - stretch factor in a novel manner to identify trip(s) made by a taxicab and show that a Hidden Markov Model based algorithm can identify trips (using real datasets from taxicab deployments in Shanghai and partially simulated datasets from Stockholm) with precision and recall of 90-94%, a significant improvement over past approaches that result in a precision and recall of about 50-60%.

Location-based services are quickly becoming immensely popular. In addition to services based on users' current location, many potential services rely on users' location history, or their spatial-temporal provenance. Malicious users may lie about their spatial-temporal provenance without a carefully designed security system for users to prove their past locations. In this paper, we present the Spatial-Temporal provenance Assurance with Mutual Proofs (STAMP) scheme. In contrast to most existing location proof systems which rely on infrastructure like wireless APs, STAMP is based on co-located mobile devices mutually generating location proofs for each other. This makes STAMP desirable for a wider range of applications. STAMP ensures the integrity and non-transferability of the location proofs and protects users' privacy. We also examine different collusion scenarios and propose a light-weight entropy-based trust evaluation approach to detect fake proofs resulting from collusion attacks. Our prototype implementation on the Android platform shows that STAMP is low-cost in terms of computational and storage resources. Extensive simulation experiments show that our entropy-based trust model is able to achieve high (> 0.9) collusion detection accuracy.

This paper develops and evaluates algorithms for exploiting physical constraints to improve the reliability of social sensing. Social sensing refers to applications where a group of sources (e.g., individuals and their mobile devices) volunteer to collect observations about the physical world. A key challenge in social sensing is that the reliability of sources and their devices is generally unknown, which makes it non-trivial to assess the correctness of collected observations. To solve this problem, the paper adopts a cyber-physical approach, where assessment of correctness of individual observations is aided by knowledge of physical constraints on both sources and observed variables to compensate for the lack of information on source reliability. We cast the problem as one of maximum likelihood estimation. The goal is to jointly estimate both (i) the latent physical state of the observed environment, and (ii) the inferred reliability of individual sources such that they are maximally consistent with both provenance information (who claimed what) and physical constraints. We evaluate the new framework through a real-world social sensing application. The results demonstrate significant performance gains in estimation accuracy of both source reliability and observation correctness.

In many mobile sensing applications devices need to discover new neighbors and maintain the rendezvous with known neighbors continuously. Due to the limited energy supply, these devices have to cycle their radios to conserve energy, making neighbor discovery and rendezvous maintenance even more challenging. To date, the main mechanism for device discover and rendezvous maintenance in existing solutions is pair wise, direct one-hop communication. We argue that such pair wise direct communication is sufficient but not necessary: there exist unnecessary active slots that can be eliminated, without affecting discovery and rendezvous. In this work, we propose a novel concept of extended quorum system, which leverages indirect discovery to further conserve energy. Specifically, we use quorum graph to capture all possible information flow paths where knowledge about known-neighbors can propagate among devices. By eliminating redundant paths, we can reduce the number of active slots significantly. Since a quorum graph can characterize arbitrary active schedules of mobile devices, our work can be broadly used to improve many existing quorum based discovery and rendezvous solutions. The simulation and test bed experimental results show that our solution can reduce as much as 55% energy consumption with a maximal 5% increase in latency for existing solutions.

As a supporting primitive of many mobile device applications, neighbor discovery identifies nearby devices so that they can exchange information and collaborate in a peer-to-peer manner. To date, discovery schemes trade a long latency for energy efficiency and require a collaborative duty cycle pattern, and thus they are not suitable for interactive mobile applications where a user is unable to configure others' devices. In this paper, we propose Acc, which serves as an on-demand generic discovery accelerating middleware for many existing neighbor discovery schemes. Acc leverages the discovery capabilities of neighbor devices, supporting both direct and indirect neighbor discoveries. Our evaluations show that Acc-assisted discovery schemes reduce latency by a maximum of 51.8%, compared with the schemes consuming the same amount of energy. We further present and evaluate a Crowd-Alert application where Acc can be employed by taxi drivers to accelerate selection of a direction with fewer competing taxis and more potential passengers, based on a 10 GB dataset of more than 15,000 taxis in a metropolitan area.

At CPSWeek 2011, the authors presented a demonstration of Apollo, a fact-finder for participatory sensing that ranks archived human-centric and sensor data by credibility. The current demonstration significantly extends our previous work by allowing Apollo to operate on live streaming data; in this case, live Twitter feeds. As the role of humans as sensors increases in emerging sensing applications, a principled approach becomes necessary to address the problem of ascertaining the veracity of sources and observations made by them. Participatory and social sensing applications may use potentially unreliable or unverified sources, such as a phone-based sensing application that grows virally in a large un-vetted population, a disaster-response application, where conflicting damage assessment reports may come from large numbers of different volunteers, or a military application, where friendly observers at a remote location may make hard-to-verify claims about local events. Apollo analyzes noisy data that increasingly plagues human-centric sensing to determine which items of information are more likely to be true.

Quorum-based schemes, e.g., GQS, can ensure asynchronous neighbors to discover each other within bounded time under low-duty-cycle operations. But they are tightly based on the assumption that duty cycles of devices fit some specific prefixed patterns. We tackle this problem by proposing a distributed quorum system to speed up the discovery.

Smartphones with diverse sensing capabilities are becoming widely available and pervasive in use. With the phone becoming a mobile personal computer, integrated applications can use multi-sensory data to derive information about the user's actions and the context in which these actions occur. This paper develops a novel method to assess daily living patterns using a smartphone equipped with microphones and inertial sensors. We develop a feature-space combination approach for fusion of information from sensors sampled at different rates and present a computationally light-weight algorithm to identify various high level activities. Preliminary results from an initial deployment among eight users indicate the potential for accurate, context-aware, and personalized sensing.

This paper develops a navigation service, called GreenGPS, that uses participatory sensing data to map fuel consumption on city streets, allowing drivers to find the most fuel efficient routes for their vehicles between arbitrary end-points. The service exploits measurements of vehicular fuel consumption sensors, available via the OBD-II interface standardized in all vehicles sold in the US since 1996. The interface gives access to most gauges and engine instrumentation. The most fuel-efficient route does not always coincide with the shortest or fastest routes, and may be a function of vehicle type. Our experimental study shows that a participatory sensing system can influence routing decisions of individual users and also answers two questions related to the viability of the new service. First, can it survive conditions of sparse deployment? Second, how much fuel can it save? A challenge in participatory sensing is to generalize from sparse sampling of high-dimensional spaces to produce compact descriptions of complex phenomena. We illustrate this by developing models that can predict fuel consumption of a set of sixteen different cars on the streets of the city of Urbana-Champaign. We provide experimental results from data collection suggesting that a 1% average prediction error is attainable and that an average 10% savings in fuel can be achieved by choosing the right route.

Many participatory sensing applications use data collected by participants to construct a public model of a system or phenomenon. For example, a health application might compute a model relating exercise and diet to amount of weight loss. While the ultimately computed model could be public, the individual input and output data traces used to construct it may be private data of participants (e.g., their individual food intake, lifestyle choices, and resulting weight). This paper proposes and experimentally studies a technique that attempts to keep such input and output data traces private, while allowing accurate model construction. This is significantly different from perturbation-based techniques in that no noise is added. The main contribution of the paper is to show a certain data transformation at the client side that helps keeping the client data private while not introducing any additional error to model construction. We particularly focus on linear regression models which are widely used in participatory sensing applications. We use the data set from a map-based participatory sensing service to evaluate our scheme. The service in question is a green navigation service that constructs regression models from participant data to predict the fuel consumption of vehicles on road segments. We evaluate our proposed mechanism by providing empirical evidence that: i) an individual data trace is generally hard to reconstruct with any reasonable accuracy, and ii) the regression model constructed using the transformed traces has a much smaller error than one based on additive data-perturbation schemes.

Web-based social networks such as Linkedln, FaceBook and MySpace have gained wide popularity in recent years. With the advent of ubiquitous sensing, future social networks will be cyber-physical, combining measured elements of the physical world with manual human input. Microsoft SensorMap is an early example of a cyber-physical network in that it allows users to browse the physical world. In contrast to social networks, however, the main abstractions exported by SensorMap are those of physical objects (such as sensors), not people. This paper extends the concept of SensorMap to incorporate social entities such as individuals and special-interest communities to which they belong. In the extended network, called SenseWorld, SensorMap offers a geographical index into a cyber-physical social network with its own logical topology derived from social connections.

This paper develops mathematical foundations and architectural components for providing privacy guarantees on stream data in grassroots participatory sensing applications, where groups of participants use privately-owned sensors to collectively measure aggregate phenomena of mutual interest. Grassroots applications refer to those initiated by members of the community themselves as opposed to by some governing or official entities. The potential lack of a hierarchical trust structure in such applications makes it harder to enforce privacy. To address this problem, we develop a privacy-preserving architecture, called PoolView, that relies on data perturbation on the client-side to ensure individuals' privacy and uses community-wide reconstruction techniques to compute the aggregate information of interest. PoolView allows arbitrary parties to start new services, called pools, to compute new types of aggregate information for their clients. Both the client-side and server-side components of PoolView are implemented and available for download, including the data perturbation and reconstruction components. Two simple sensing services are developed for illustration; one computes traffic statistics from subscriber GPS data and the other computes weight statistics for a particular diet. Evaluation, using actual data traces collected by the authors, demonstrates the privacy-preserving aggregation functionality in PoolView.

Delay-tolerant networks (DTNs), where no connected path generally exists between a source and a destination at any given time, present significant challenges from a routing perspective. A plethora of routing approaches have been previously introduced that make use of node mobility models or probabilistic models of network topology. In this paper, we offer a new perspective by making an analogy between routing table construction in DTNs and caching in program execution. In this approach, each node uses a simple caching heuristic to choose a subset of previously encountered nodes to be its routing neighbors. The approach is evaluated and shows good performance while keeping the implementation very simple.

Sensor networks introduce a new application domain and set of challenges in distributed computing including new network-level programming languages, global system abstractions, and general-purpose communication protocols. These challenges are brought about by the tight integration of computation, communication, and distributed real-time interaction with the physical world. With the growing interest in interconnecting different sensor networks across a wide-area communication infrastructure, an overarching challenge becomes one of arriving at an agreed-upon global sensor network architecture that ensures interoperability. Unlike the Internet, where a layered communication stack (namely, the TCP/IP stack) defines the network architecture, a sensor network architecture must unify not only communication interfaces but also programming interfaces, since network communication and computation functions are tightly intertwined. In that sense, the sensor network architecture refers to a layered stack of distributed computing abstractions. This paper presents an architecture and key considerations in designing and interconnecting local and global sensor networks. Candidate protocols and middleware instantiations are described from the authors' ongoing work that meet the discussed considerations

Personal instrumentation and monitoring services that collect and archive the physical activities of a user have recently been introduced for various medical, personal, safety, and entertainment purposes. A general software architecture is needed to support different categories of such monitoring services. This paper presents a software architecture, implementation, and preliminary evaluation of SATIRE, a wearable personal monitoring service transparently embedded in user garments. SATIRE records the owner's activity and location for subsequent automated uploading and archiving. The personal archive can later be searched for particular events to answer questions regarding past and present user activity, location, and behavior patterns. A short feasibility and usage study of a prototype based on MicaZ motes provides a proof of concept for the SATIRE architecture.

Datalink layer framing in wireless sensor networks usually faces a trade-off between large frame sizes for high channel bandwidth utilization and small frame sizes for effective error recovery. Given the high error rates of intermote communications, TinyOS opts in favor of small frame sizes at the cost of extremely low channel bandwidth utilization. In this paper, we describe Seda: a streaming datalink layer that resolves the above dilemma by decoupling framing from error recovery. Seda treats the packets from the upper layer as a continuous stream of bytes. It breaks the data stream into blocks, and retransmits erroneous blocks only (as opposed to the entire erroneous frame). Consequently, the frame-error-rate (FER), the main factor that bounds the frame size in the current design, becomes irrelevant to error recovery. A frame can therefore be sufficiently large in great favor of high utilization of the wireless channel bandwidth, without compromising the effectiveness of error recovery. Meanwhile, the size of each block is configured according to the error characteristics of the wireless channel to optimize the performance of error recovery. Seda has been implemented as a new datalink layer in the TinyOS, and evaluated through both simulations and experiments in a testbed of 48 MicaZ motes. Our results show that, by increasing the TinyOS frame size from the default 29 bytes to 100 bytes (limited by the buffer space at MicaZ firmware), Seda improves the throughput around 25% under typical wireless channel conditions. Seda also reduces the retransmission traffic volume by more than 50%, compared to a framebased retransmission scheme. Our analysis also exposes that future sensor motes should be equipped with radios with more packet buffer space on the radio firmware to achieve optimal utilization of the channel capacity.