Smart, real-time, low-cost, and distributed ecosystem monitoring is essential for understanding and managing rapidly changing ecosystems. However, new techniques in the big data era have rarely been introduced into op...Smart, real-time, low-cost, and distributed ecosystem monitoring is essential for understanding and managing rapidly changing ecosystems. However, new techniques in the big data era have rarely been introduced into operational ecosystem monitoring, particularly for fragile ecosystems in remote areas.We introduce the Internet of Things(IoT) techniques to establish a prototype ecosystem monitoring system by developing innovative smart devices and using IoT technologies for ecosystem monitoring in isolated environments. The developed smart devices include four categories: large-scale and nonintrusive instruments to measure evapotranspiration and soil moisture, in situ observing systems for CO2 and d13 C associated with soil respiration, portable and distributed devices for monitoring vegetation variables, and Bi-CMOS cameras and pressure trigger sensors for terrestrial vertebrate monitoring. These new devices outperform conventional devices and are connected to each other via wireless communication networks. The breakthroughs in the ecosystem monitoring IoT include new data loggers and longdistance wireless sensor network technology that supports the rapid transmission of data from devices to wireless networks. The applicability of this ecosystem monitoring IoT is verified in three fragile ecosystems, including a karst rocky desertification area, the National Park for Amur Tigers, and the oasis-desert ecotone in China. By integrating these devices and technologies with an ecosystem monitoring information system, a seamless data acquisition, transmission, processing, and application IoT is created. The establishment of this ecosystem monitoring IoT will serve as a new paradigm for ecosystem monitoring and therefore provide a platform for ecosystem management and decision making in the era of big data.展开更多
考虑到非线性回声和非平稳噪声对智能设备回声消除算法的影响,论文提出一种基于双向长短时记忆(Bidirectional Long Short-Term Memory,BLSTM)神经网络的回声和噪声抑制算法。该算法首先采用多目标预处理模型,同步估计出回声和噪声信号...考虑到非线性回声和非平稳噪声对智能设备回声消除算法的影响,论文提出一种基于双向长短时记忆(Bidirectional Long Short-Term Memory,BLSTM)神经网络的回声和噪声抑制算法。该算法首先采用多目标预处理模型,同步估计出回声和噪声信号的幅度谱;然后将其作为回声和噪声抑制模型的输入特征,进而估计出目标语音信号的理想比例掩模;最后通过联合训练两个模型得到最优回声和噪声抑制模型。实验结果表明,在非线性回声和非平稳噪声的环境下,该算法均取得了较好的回声和噪声抑制效果,语音失真较小。展开更多
基金supported by the National Key Research & Development Program of China (2016YFC0500106)the Strategic Priority Research Program of the Chinese Academy of Sciences (XDA20100104)the 13th Five-year Informatization Plan of the Chinese Academy of Sciences (XXH13505-06)
文摘Smart, real-time, low-cost, and distributed ecosystem monitoring is essential for understanding and managing rapidly changing ecosystems. However, new techniques in the big data era have rarely been introduced into operational ecosystem monitoring, particularly for fragile ecosystems in remote areas.We introduce the Internet of Things(IoT) techniques to establish a prototype ecosystem monitoring system by developing innovative smart devices and using IoT technologies for ecosystem monitoring in isolated environments. The developed smart devices include four categories: large-scale and nonintrusive instruments to measure evapotranspiration and soil moisture, in situ observing systems for CO2 and d13 C associated with soil respiration, portable and distributed devices for monitoring vegetation variables, and Bi-CMOS cameras and pressure trigger sensors for terrestrial vertebrate monitoring. These new devices outperform conventional devices and are connected to each other via wireless communication networks. The breakthroughs in the ecosystem monitoring IoT include new data loggers and longdistance wireless sensor network technology that supports the rapid transmission of data from devices to wireless networks. The applicability of this ecosystem monitoring IoT is verified in three fragile ecosystems, including a karst rocky desertification area, the National Park for Amur Tigers, and the oasis-desert ecotone in China. By integrating these devices and technologies with an ecosystem monitoring information system, a seamless data acquisition, transmission, processing, and application IoT is created. The establishment of this ecosystem monitoring IoT will serve as a new paradigm for ecosystem monitoring and therefore provide a platform for ecosystem management and decision making in the era of big data.
文摘考虑到非线性回声和非平稳噪声对智能设备回声消除算法的影响,论文提出一种基于双向长短时记忆(Bidirectional Long Short-Term Memory,BLSTM)神经网络的回声和噪声抑制算法。该算法首先采用多目标预处理模型,同步估计出回声和噪声信号的幅度谱;然后将其作为回声和噪声抑制模型的输入特征,进而估计出目标语音信号的理想比例掩模;最后通过联合训练两个模型得到最优回声和噪声抑制模型。实验结果表明,在非线性回声和非平稳噪声的环境下,该算法均取得了较好的回声和噪声抑制效果,语音失真较小。
