Recently there is a great interest in artificial systems able to understand and recognize human emotions. In this paper an Emotion Recognition System based on classical neural networks and neuro-fuzzy classifiers is proposed. Emotion recognition is performed in real time starting from a video stream acquired by a common webcam monitoring the user's face. Neurofuzzy classifiers, in comparison with Multi Layer Perceptron trained by EBP algorithm, show very short training times, allowing applications with easy and automated set up procedures, to be used in a wide range of applications, from entertainment to safety. The algorithm yields very interesting performances and can be adopted to recognize emotions as well as possible pathological conditions of the individual to be monitored

No abstract

No abstract

In this paper an on-board unit for the monitoring and management of a small electric fleet is presented. The device includes a communication module and allows to provide data about the vehicles, sending information coming from various sensors to a remote server. Besides locating vehicles on a map and showing their real-time status, the device can also explore the functions of subsystems including energy modules, cells, and powertrain in Electric Vehicles (EV) by showing the instantaneous data and even trend charts. When an error occurs, the system will come with warning and maintenance suggestions; the control center may send short messages to the driver and system data are available for download for advanced engineering analysis. The system foresees a web application and data can be accessed anywhere and anytime thanks to a browser application and a database developed on purpose. The device has been initially tested on a laboratory available vehicle and it will be subsequently installed on the municipal fleet of electric vehicles and boats operating on the small island of Ventotene in Italy in order to investigate the behavior of the main components. The paper illustrates the main hardware characteristics of the system and provides some experimental results. © 2012 IEEE

In the paper, possible hybrid configurations of low power stand alone systems based on Renewable Energy Sources (RES) and alternative sources, suitable for applications in remote areas not connected to the grid such as Radio Base stations for mobile phone communications, are described and compared. As practical case, different alternative solutions for the powering of a Radio Base Station (RBS) are analysed: the windsolar technology including also a PEM fuel cell, supplying a conventional refrigeration system or an absorption system for the equipment cooling; a thermally insulated pre-fabricated system that uses the natural air circulation for the equipment cooling. © 2007 IEEE