Recently, the Internet of Things （loT） has attracted more and more attention. Multimedia sensor network plays an important role in the IoT, and audio event detection in the multimedia sensor net- works is one of the...Recently, the Internet of Things （loT） has attracted more and more attention. Multimedia sensor network plays an important role in the IoT, and audio event detection in the multimedia sensor net- works is one of the most important applications for the Internet of Things. In practice, it is hard to get enough real-world samples to generate the classifi- ers for some special audio events （e.g., car-crash- ing in the smart traffic system）. In this paper, we introduce a TrAdaBoost-based method to solve the above problem. By using the proposed approach, we can train a strong classifier by using only a tiny amount of real-world data and a large number of more easily collected samples （e.g., collected from TV programs）, even when the real-world data is not sufficient to train a model alone. We deploy this ap- proach in a smart traffic system to evaluate its per- formance, and the experiment evaluations demonstrate that our method can achieve satisfying results.展开更多
An algorithm for detecting low-frequency seismic events is developed and applied to the detection of low-frequency events before the 2008 Wenchuan and the 2013 Lushan earthquakes. Continuous vertical-component wavefor...An algorithm for detecting low-frequency seismic events is developed and applied to the detection of low-frequency events before the 2008 Wenchuan and the 2013 Lushan earthquakes. Continuous vertical-component waveforms of some broadband stations in the few months before the Wenchuan and Lushan earthquakes are processed by applying a bandpass filter in 2- 8Hz,and then converted to envelopes with a smoothing time of 10 s window and a median filter with a 20 min window. As a result,teleseismic,long-period noise and local small earthquakes are removed,the filtered amplitude is obviously larger than that of the noise and lasts for a dozen minutes to several hours during a few days in a few stations before the Wenchuan and Lushan earthquakes,respectively. The waveform and envelope are similar to that of a non-volcanic tremor( NVT). There are suspected NVT before the two earthquakes. Preliminary application demonstrates that this algorithm is potentially useful for extracting NVT signals from continuous seismic waveforms.展开更多
基金supported by the National Natural Science Foundation of China(No.60821001)the National Basic Research Program of China(No.2007CB311203)
文摘Recently, the Internet of Things （loT） has attracted more and more attention. Multimedia sensor network plays an important role in the IoT, and audio event detection in the multimedia sensor net- works is one of the most important applications for the Internet of Things. In practice, it is hard to get enough real-world samples to generate the classifi- ers for some special audio events （e.g., car-crash- ing in the smart traffic system）. In this paper, we introduce a TrAdaBoost-based method to solve the above problem. By using the proposed approach, we can train a strong classifier by using only a tiny amount of real-world data and a large number of more easily collected samples （e.g., collected from TV programs）, even when the real-world data is not sufficient to train a model alone. We deploy this ap- proach in a smart traffic system to evaluate its per- formance, and the experiment evaluations demonstrate that our method can achieve satisfying results.
基金funded by the National Science & Technology Pillar Program in the 12th "Five-year Plan" Period,China(2012BAKI9B02)
文摘An algorithm for detecting low-frequency seismic events is developed and applied to the detection of low-frequency events before the 2008 Wenchuan and the 2013 Lushan earthquakes. Continuous vertical-component waveforms of some broadband stations in the few months before the Wenchuan and Lushan earthquakes are processed by applying a bandpass filter in 2- 8Hz,and then converted to envelopes with a smoothing time of 10 s window and a median filter with a 20 min window. As a result,teleseismic,long-period noise and local small earthquakes are removed,the filtered amplitude is obviously larger than that of the noise and lasts for a dozen minutes to several hours during a few days in a few stations before the Wenchuan and Lushan earthquakes,respectively. The waveform and envelope are similar to that of a non-volcanic tremor( NVT). There are suspected NVT before the two earthquakes. Preliminary application demonstrates that this algorithm is potentially useful for extracting NVT signals from continuous seismic waveforms.
