Environmental sound classification has received more attention in recent years. Analysis of environmental sounds is difficult because of its unstructured nature. However, the presence of strong spectro-temporal patterns makes the classification possible. Since LSTM neural networks are efficient at learning temporal dependencies we propose and examine a LSTM model for urban sound classification. The model is trained on magnitude mel-spectrograms extracted from UrbanSound8K dataset audio. The proposed network is evaluated using 5-fold cross-validation and compared with the baseline CNN. It is shown that the LSTM model outperforms a set of existing solutions and is more accurate and confident than the CNN.
2
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
Droughts are natural phenomena affecting the environment and human activities. There are various drought definitions and quantitative indices; among them is the Standardised Precipitation Index (SPI). In the drought investigations, historical events are poorly characterised and little data are available. To decipher past drought appearances in the southeastern Alps with a focus on Slovenia, precipitation data from HISTALP data repository were taken to identify extreme drought events (SPI ≤ -2.00) from the second half of the 19th century to the present day. Several long-term extreme drought crises were identified in the region (between the years 1888 and 1896; after World War I, during and after World War II). After 1968, drought patterns detected with SPI changed: shorter, extreme droughts with different time patterns appeared. SPI indices of different time spans showed correlated structures in space and between each other, indicating structured relations.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.