1,922 research outputs found
Wireless Sensor Networking in the Internet of Things and Cloud Computing Era
No full textAbstractIn the recent past we have observed many technological revolutions, including the transition from the analog world into its digital counterpart and from centralized wired solutions to distributed and pervasive wireless systems. In particular, the advent of low- cost and low-power transceivers, together with the development of compact-size and open standard stacks, have made possible Wireless Sensor Networks (WSNs), largely adopted for both home/office and industrial monitoring applications. The nowadays ambitious goal is to sample, collect and analyze every piece of information around us, in order to improve production efficiency and ensure optimal resource consumption. The “Internet of Things” (IoT), i.e. the capability of connecting every possible device to the World Wide Web, is the practical answer to this request. The very large amount of information that is consequently generated could be profitably handled using “cloud” services, i.e. flexible and powerful hardware/software frameworks capable to deliver computing as a service. The aim of this work is to resume pros and cons of well-accepted WSN technologies, suggesting their possible extension towards already available cloud services
Flexible and Low-cost Interface Circuit for Electrochemical and Resistive Gas Sensors
No full textAbstractThis work presents a low-cost interface circuit for both electrochemical and semiconductor sensors for gas detection. The proposed circuit offers a high sampling rate, on the order of 25ms, allowing the monitoring of the sensor behaviour even in presence of fast transients. The front-end has a single-voltage 3.3V power supply and a time-coded digital signal output, thus it is suitable to be directly interfaced to a microcontroller for the management of the measurement process. Possible integration in a single-chip solution, together with the digital electronics is furthermore facilitated. Experimental results, conducted on a discrete component prototype and with sample resistors to emulate the sensor, have shown a maximum linearity error in the estimation of the sensor current or resistance of about 5% over a measurement range of seven decades, demonstrating the validity of the proposed solution. The power dissipation of the front-end is less than 30 mW (at 3.3V) and the front-end cost less than 10 EUR, making it suitable for the employment in low-cost and low-power gas detection systems
Audio Classification in Speech and Music: A Comparison between a Statistical and a Neural Approach
No full text We focus the attention on the problem of audio classification in speech and music for multimedia applications. In particular, we present a comparison between two different techniques for speech/music discrimination. The first method is based on Zero crossing rate and Bayesian classification. It is very simple from a computational point of view, and gives good results in case of pure music or speech. The simulation results show that some performance degradation arises when the music segment contains also some speech superimposed on music, or strong rhythmic components. To overcome these problems, we propose a second method, that uses more features, and is based on neural networks (specifically a multi-layer Perceptron). In this case we obtain better performance, at the expense of a limited growth in the computational complexity. In practice, the proposed neural network is simple to be implemented if a suitable polynomial is used as the activation function, and a real-time implementation is possible even if low-cost embedded systems are used.</p
UPM-UC3M system for music and speech segmentation
No full textThis paper describes the UPM-UC3M system for the Albayzín evaluation 2010 on Audio Segmentation. This evaluation task consists of segmenting a broadcast news audio document into clean speech, music, speech with noise in background and speech with music in background. The UPM-UC3M system is based on Hidden Markov Models (HMMs), including a 3-state HMM for every acoustic class. The number of states and the number of Gaussian per state have been tuned for this evaluation. The main analysis during system development has been focused on feature selection. Also, two different architectures have been tested: the first one corresponds to an one-step system whereas the second one is a hierarchical system in which different features have been used for segmenting the different audio classes. For both systems, we have considered long term statistics of MFCC (Mel Frequency Ceptral Coefficients), spectral entropy and CHROMA coefficients. For the best configuration of the one-step system, we have obtained a 25.3% average error rate and 18.7% diarization error (using the NIST tool) and a 23.9% average error rate and 17.9% diarization error for the hierarchical one
- …
