Autonomous Multi-Rotor Aerial Platform for Air Pollution Monitoring.

During the last few years, scientists have become increasingly concerned about air quality. Particularly in large cities and industrialised areas, air quality is affected by pollution from natural and anthropogenic sources and this has a significant impact on human health. Continuous monitoring of air quality is an important step in investigating the causes and reducing pollution. In this paper, we propose a new autonomous multi-rotor aerial platform that can be used to perform real-time monitoring of air quality in large cities. The air quality monitoring system is able to cover large areas, with high spatial resolution, even above average buildings, while being relatively low cost. We evaluate the proposed system in several locations throughout a metropolitan city, during different seasons and generate fine-grained heat-maps that display the level of pollution of specific areas based on different altitudes.

Detection of Anomalous Behavior in Modern Smartphones Using Software Sensor-Based Data.

This paper describes the steps involved in obtaining a set of relevant data sources and the accompanying method using software-based sensors to detect anomalous behavior in modern smartphones based on machine-learning classifiers. Three classes of models are investigated for classification: logistic regressions, shallow neural nets, and support vector machines. The paper details the design, implementation, and comparative evaluation of all three classes. If necessary, the approach could be extended to other computing devices, if appropriate changes were made to the software infrastructure, based upon mandatory capabilities of the underlying hardware.