Environmental sound classification is one of the important issues in the audio recognition field. Compared with structured sounds such as speech and music, the time–frequency structure of environmental sounds is more complicated. In order to learn time and frequency features from Log-Mel spectrogram more effectively, a temporal-frequency attention based convolutional neural network model (TFCNN) is proposed in this paper. Firstly, an experiment that is used as motivation in proposed method is designed to verify the effect of a specific frequency band in the spectrogram on model classification. Secondly, two new attention mechanisms, temporal attention mechanism and frequency attention mechanism, are proposed. These mechanisms can focus on key frequency bands and semantic related time frames on the spectrogram to reduce the influence of background noise and irrelevant frequency bands. Then, a feature information complementarity is formed by combining these mechanisms to more accurately capture the critical time–frequency features. In such a way, the representation ability of the network model can be greatly improved. Finally, experiments on two public data sets, UrbanSound 8 K and ESC-50, demonstrate the effectiveness of the proposed method.

Non-intrusive load monitoring (NILM) is crucial because it helps monitor the operating status of electrical appliances online; detailed power consumption data regarding the appliances can then be obtained. However, the identification of resistive appliances that have similar features in a power grid is still a major problem. In this study, the reconstructed image of a voltage-current (VI) trajectory is used as input data for a convolutional neural network (CNN) to classify the appliances, particularly resistive appliances. Two dataset PLAID and IDOUC are introduced to verify the performance of the proposed method. According to the results, the excellent performance of the reconstructed VI image method for the identification of the household appliances with similar waveform is validated by comparing it with the other two methods.

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.

Recently, with the construction of smart city, the research on environmental sound classification (ESC) has attracted the attention of academia and industry. The development of convolutional neural network (CNN) makes the accuracy of ESC reach a higher level, but the accuracy improvement brought by CNN is often accompanied by the deepening of network layers, which leads to the rapid growth of parameters and floating-point operations (FLOPs). Therefore, it is difficult to transplant CNN model to embedded devices, and the classification speed is also difficult to accept. In order to reduce the hardware requirements of running CNN and improve the speed of ESC, this paper proposes a resource adaptive convolutional neural network (RACNN). RACNN uses a novel resource adaptive convolutional (RAC) module, which can generate the same number of feature maps as conventional convolution operations more cheaply, and extract the time and frequency features of audio efficiently. The RAC block based on the RAC module is designed to build the lightweight RACNN model, and the RAC module can also be used to upgrade the existing CNN model. Experiments based on public datasets show that RACNN achieves higher performance than the state-of-the-art methods with lower computational complexity.

Nonintrusive load monitoring (NILM) plays a key role in the real-time electricity consumption monitoring of household appliances. However, it is difficult to realize high precision load identification by using a single waveform feature. Therefore, this article proposes a two-stream convolutional neural network based on current time-frequency feature fusion for nonintrusive load identification. First, a time series image coding method for current time-frequency multi-feature fusion is proposed. The method can extract the time domain and frequency domain features of the current timing signal effectively. Then, we present a two-stream neural network combining the gated recurrent unit (GRU) and a two-dimensional convolutional neural network (2D-CNN) to improve the load identification performance. Finally, the experimental results on the PLAID and IDOUC datasets show that the proposed model outperforms the state-of-the-art methods.

Soil nutrient prediction based on near-infrared spectroscopy has become the main research direction for rapid acquisition of soil information. The development of deep learning has greatly improved the prediction accuracy of traditional modeling methods. In view of the low efficiency and low accuracy of current soil prediction models, this paper proposes a soil multi-attribute intelligent prediction method based on convolutional neural networks, by constructing a dual-stream convolutional neural network model Multi_CNN that combines one-dimensional convolution and two-dimensional convolution, the intelligent prediction of soil multi-attribute is realized. The model extracts the characteristics of soil attributes from spectral sequences and spectrograms respectively, and multiple attributes can be predicted simultaneously by feature fusion. The model is based on two different-scale soil near-infrared spectroscopy data sets for multi-attribute prediction. The experimental results show that the $R_P^2$ of the three attributes of Total Carbon, Total Nitrogen, and Alkaline Nitrogen on the small dataset are 0.94, 0.95, 0.87, respectively, and the $R_P^2$ of the attributes of Organic Carbon, Nitrogen, and Clay on the LUCAS dataset are, respectively, 0.95, 0.91, 0.83, And compared with traditional regression models and new prediction methods commonly used in soil nutrient prediction, the multi-task model proposed in this paper is more accurate.