Fabrizio Milazzo

Adaptive Distributed Outlier Detection for WSNs

The paradigm of pervasive computing is gaining more and more attention nowadays, thanks to the possibility of obtaining precise and continuous monitoring. Ease of deployment and adaptivity are typically implemented by adopting autonomous and cooperative sensory devices; however, for such systems to be of any practical use, reliability and fault tolerance must be guaranteed, for instance by detecting corrupted readings amidst the huge amount of gathered sensory data. This paper proposes an adaptive distributed Bayesian approach for detecting outliers in data collected by a wireless sensor network; our algorithm aims at optimizing classification accuracy, time complexity and communication complexity, and also considering externally imposed constraints on such conflicting goals. The performed experimental evaluation showed that our approach is able to improve the considered metrics for latency and energy consumption, with limited impact on classification accuracy.

Secure random number generation in wireless sensor networks

Reliable random number generation is crucial for many available security algorithms, and some of the methods presented in literature proposed to generate them based on measurements collected from the physical environment, in order to ensure true randomness. However the effectiveness of such methods can be compromised if an attacker is able to gain access to the measurements thus inferring the generated random number. In our paper, we present an algorithm that guarantees security for the generation process, in a real world scenario using wireless sensor nodes as the sources of the physical measurements. The proposed method uses distributed leader election for selecting a random source of data. We prove the robustness of the algorithm by discussing common security attacks, and we present theoretical and experimental evaluation regarding its complexity in terms of time and exchanged messages.

QoS-Aware Fault Detection in Wireless Sensor Networks

Wireless sensor networks (WSNs) are a fundamental building block of many pervasive applications. Nevertheless the use of such technology raises new challenges regarding the development of reliable and fault-tolerant systems. One of the most critical issues is the detection of corrupted readings amidst the huge amount of gathered sensory data. Indeed, such readings could significantly affect the quality of service (QoS) of the WSN, and thus it is highly desirable to automatically discard them. This issue is usually addressed through “fault detection” algorithms that classify readings by exploiting temporal and spatial correlations. Generally, these algorithms do not take into account QoS requirements other than the classification accuracy. This paper proposes a fully distributed algorithm for detecting data faults, taking into account the response time besides the classification accuracy. We adopt the Bayesian networks to perform classification of readings and the Pareto optimization to allow QoS requirements to be simultaneously satisfied. Our approach has been tested on a synthetic dataset in order to evaluate its behavior with respect to different values of QoS constraints. The experimental evaluation produced good results, showing that our algorithm is able to greatly reduce the response time at the cost of a small reduction in classification accuracy.

Reputation Management for Distributed Service-Oriented Architectures

Nowadays, several network applications require that consumer nodes acquire distributed services from unknown service providers on the Internet. The main goal of consumer nodes is the selection of the best services among the huge multitude provided by the network. As basic criteria for this choice, service cost and Quality-of-Service (QoS) can be considered, provided that the underlying Service-Oriented Architecture (SOA) be augmented in order to support the declaration of this information. The correct behavior of such new SOA platforms, however, will depend on the presence of some mechanisms that allow consumer nodes to evaluate trustworthiness of service providers. This work proposes a new methodology for discouraging antisocial behaviors of malicious service providers that declare QoS higher than the real one. The architecture is fully distributed over the network and emulates a decentralized hierarchical trusting authority capable of managing reputation values and of providing correct QoS assessments.

A distributed Bayesian approach to fault detection in sensor networks

Sensor networks are widely used in industrial and academic applications as the pervasive sensing module of an intelligent system. Sensor nodes may occasionally produce incorrect measurements due to battery depletion, dust on the sensor, manumissions and other causes. The aim of this paper is to develop a distributed Bayesian fault detection algorithm that classifies measurements coming from the network as corrupted or not. The computational complexity is polynomial so the algorithm scales well with the size of the network. We tested the approach on a synthetic dataset and obtained significant results in terms of correctly labeled measurements.

Predictive models for energy saving in Wireless Sensor Networks

ICT devices nowadays cannot disregard optimizations toward energy sustainability. Wireless Sensor Networks, in particular, are a representative class of a technology where special care must be given to energy saving, due to the typical scarcity and non-renewability of their energy sources, in order to enhance network lifetime. In our work we propose a novel approach that aims to adaptively control the sampling rate of wireless sensor nodes using prediction models, so that environmental phenomena can be consistently modeled while reducing the required amount of transmissions; the approach is tested on data available from a public dataset.

Adaptable data models for scalable Ambient Intelligence scenarios

In most real-life scenarios for Ambient Intelligence, the need arises for scalable simulations that provide reliable sensory data to be used in the preliminary design and test phases. This works present an approach to modeling data generated by a hybrid simulator for wireless sensor networks, where virtual nodes coexist with real ones. We apply our method to real data available from a public repository and show that we can compute reliable models for the quantities measured at a given reference site, and that such models are portable to different environments, so as to obtain a complete, scalable and reliable testing environment.

Body Gestures and Spoken Sentences: A Novel Approach for Revealing User’s Emotions

In the last decade, there has been a growing interest in emotion analysis research, which has been applied in several areas of computer science. Many authors have contributed to the development of emotion recognition algorithms, considering textual or non verbal data as input, such as facial expressions, gestures or, in the case of multi-modal emotion recognition, a combination of them. In this paper, we describe a method to detect emotions from gestures using the skeletal data obtained from Kinect-like devices as input, as well as a textual description of their meaning. The experimental results show that the correlation existing between body movements and spoken user sentence(s) can be used to reveal users emotions from gestures.

Modular Middleware for Gestural Data and Devices Management

In the last few years, the use of gestural data has become a key enabler for human-computer interaction (HCI) applications. The growing diffusion of low-cost acquisition devices has thus led to the development of a class of middleware aimed at ensuring a fast and easy integration of such devices within the actual HCI applications. The purpose of this paper is to present a modular middleware for gestural data and devices management. First, we describe a brief review of the state of the art of similar middleware. Then, we discuss the proposed architecture and the motivation behind its design choices. Finally, we present a use case aimed at demonstrating the potential uses as well as the limitations of our middleware.

Short-Term Sensory Data Prediction in Ambient Intelligence Scenarios

Predicting data is a crucial ability for resource-constrained devices like the nodes of a Wireless Sensor Network. In the context of Ambient Intelligence scenarios, in particular, short-term sensory data prediction becomes a key enabler for more difficult tasks such as prolonging network lifetime, reducing the amount of communication required and improving user-environment interaction. In this chapter we propose a software module designed for clustered wireless sensor networks, able to predict various environmental quantities, namely temperature, humidity and light. The software module is supported by an ontology that describes the topology of the AmI scenario and the effects of the actuators on the environment. We applied our module to real data gathered from a public office at our department and obtained significant results in terms of prediction error even in presence of environmental actuators.