RESUMO
The larvae of some trunk-boring beetles barely leave traces on the outside of trunks when feeding within, rendering the detection of them rather difficult. One approach to solving this problem involves the use of a probe to pick up boring vibrations inside the trunk and distinguish larvae activity according to the vibrations. Clean boring vibration signals without noise are critical for accurate judgement. Unfortunately, these environments are filled with natural or artificial noise. To address this issue, we constructed a boring vibration enhancement model named VibDenoiser, which makes a significant contribution to this rarely studied domain. This model is built using the technology of deep learning-based speech enhancement. It consists of convolutional encoder and decoder layers with skip connections, and two layers of SRU++ for sequence modeling. The dataset constructed for study is made up of boring vibrations of Agrilus planipennis Fairmaire, 1888 (Coleoptera: Buprestidae) and environmental noise. Our VibDenoiser achieves an improvement of 18.57 in SNR, and it runs in real-time on a laptop CPU. The accuracy of the four classification models increased by a large margin using vibration clips enhanced by our model. The results demonstrate the great enhancement performance of our model, and the contribution of our work to better boring vibration detection.
RESUMO
Based on the remote sensing data in 2000, 2005, and 2010, this paper analyzed the variation trends of the land use type and landscape pattern in Daiyue District of Tai' an City from 2000 to 2010. The ecological risk index was built, that of the District was re-sampled and spatially interpolated, and the spatiotemporal pattern of the ecological risk in the rural-urban ecotone of the District was analyzed. In 2000-2010, the main variation trend of the land use type in the District was the shift from natural landscape to artificial landscape. The intensity of human disturbance was larger in cultivated land, garden plot, and forestland than in other landscape types, while the human disturbance in water area was smaller. The ecological loss degree of cultivated land and water area decreased somewhat, while that of the other land use types presented an increasing trend. The ecological risk distribution in the District was discrete in 2000 and 2010, but most centralized in 2005. The ecological risk of each ecological risk sub-area had an increasing trend in 2000-2005, but was in adverse in 2005-2010. In 2000-2010, the ecological risk of the District was mainly at medium level. Spatially, the distribution of the ecological risk in the District had an obvious differentiation, with an overall diffusive increasing from forestland as the center to the surrounding areas. In the District, the ecological risk was mainly at medium and higher levels, the area with lower ecological risk had an obvious dynamic change, while that with the lowest and highest ecological risk had less change.
