Energy-saving models for wireless sensor networks

Nowadays, wireless sensor networks are being used for a fast-growing number of different application fields (e.g., habitat monitoring, highway traffic monitoring, remote surveillance). Monitoring (i.e., querying) the sensor network entails the frequent acquisition of measurements from all sensors. Since sensor data acquisition and communication are the main sources of power consumption and sensors are battery-powered, an important issue in this context is energy saving during data collection. Hence, the challenge is to extend sensor lifetime by reducing communication cost and computation energy. This paper thoroughly describes the complete design, implementation and validation of the SeReNe framework. Given historical sensor readings, SeReNe discovers energy-saving models to efficiently acquire sensor network data. SeReNe exploits different clustering algorithms to discover spatial and temporal correlations which allow the identification of sets of correlated sensors and sensor data streams. Given clusters of correlated sensors, a subset of representative sensors is selected. Rather than directly querying all network nodes, only the representative sensors are queried by reducing the communication, computation and power costs. Experiments performed on both a real sensor network deployed at the Politecnico di Torino labs and a publicly available dataset from Intel Berkeley Research lab demonstrate the adaptability and the effectiveness of the SeReNe framework in providing energy-saving sensor network models.     

Trusting deep learning natural-language models via local and global explanations

Knowledge and Information Systems - Despite the high accuracy offered by state-of-the-art deep natural-language models (e.g., LSTM, BERT), their application in real-life settings is still widely...     

Characterizing network traffic by means of the NetMine framework

The NetMine framework allows the characterization of traffic data by means of data mining techniques. NetMine performs generalized association rule extraction to profile communications, detect anomalies, and identify recurrent patterns. Association rule extraction is a widely used exploratory technique to discover hidden correlations among data. However, it is usually driven by frequency constraints on the extracted correlations. Hence, it entails (i) generating a huge number of rules which are difficult to analyze, or (ii) pruning rare itemsets even if their hidden knowledge might be relevant. To overcome these issues NetMine exploits a novel algorithm to efficiently extract generalized association rules, which provide a high level abstraction of the network traffic and allows the discovery of unexpected and more interesting traffic rules. The proposed technique exploits (user provided) taxonomies to drive the pruning phase of the extraction process. Extracted correlations are automatically aggregated in more general association rules according to a frequency threshold. Eventually, extracted rules are classified into groups according to their semantic meaning, thus allowing a domain expert to focus on the most relevant patterns. Experiments performed on different network dumps showed the efficiency and effectiveness of the NetMine framework to characterize traffic data.     

Real-Time Analysis of Physiological Data to Support Medical Applications

This paper presents a flexible framework that performs real-time analysis of physiological data to monitor people's health conditions in any context (e.g., during daily activities, in hospital environments). Given historical physiological data, different behavioral models tailored to specific conditions (e.g., a particular disease, a specific patient) are automatically learnt. A suitable model for the currently monitored patient is exploited in the real-time stream classification phase. The framework has been designed to perform both instantaneous evaluation and stream analysis over a sliding time window. To allow ubiquitous monitoring, real-time analysis could also be executed on mobile devices. As a case study, the framework has been validated in the intensive care scenario. Experimental validation, performed on 64 patients affected by different critical illnesses, demonstrates the effectiveness and the flexibility of the proposed framework in detecting different severity levels of monitored people's clinical situations.