In recent years, with the construction of intelligent cities, the importance of environmental sound classification (ESC) research has become increasingly prominent. However, due to the non-stationary nature of environment sound and the strong interference of ambient noise, the recognition accuracy of ESC is not high enough. Even with deep learning methods, it is difficult to fully extract features from models with a single input. Aiming to improve the recognition accuracy of ESC, this paper proposes a two-stream convolutional neural network (CNN) based on raw audio CNN (RACNN) and logmel CNN (LMCNN). In this method, a pre-emphasis module is first constructed to deal with raw audio signal. The processed audio data and logmel data are imported into RACNN and LMCNN, respectively to obtain both of time and frequency features of audio. In addition, a random-padding method is proposed to patch shorter data sequences. In such a way, the available data for experiment are greatly increased. Finally, the effectiveness of the methods has been verified based on UrbanSound8K dataset in experimental part. INDEX TERMS Environmental sound classification, sound recognition, convolutional neural networks, data processing, pre-emphasis, two stream model.
In the current non-intrusive load monitoring process, the states switching of some multi-state appliances is difficult to be correctly identified by the switch event detection method, and the energy consumption statistics due to poor multi-state identification of the electrical appliances are not accurate. This paper proposes a multi-state household appliance load identification method based on convolutional neural network and clustering model. First, a convolutional neural network is used to construct an appliance type identification model. Then, a multi-state identification model is established to identify the state of different multi-state appliances. The experimental results show that the proposed method achieves multi-state identification of electrical appliances and has good engineering and practical value.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.