An Automatic Classification System for Environmental Sound in Smart Cities.

With the continuous promotion of "smart cities" worldwide, the approach to be used in combining smart cities with modern advanced technologies (Internet of Things, cloud computing, artificial intelligence) has become a hot topic. However, due to the non-stationary nature of environmental sound and the interference of urban noise, it is challenging to fully extract features from the model with a single input and achieve ideal classification results, even with deep learning methods. To improve the recognition accuracy of ESC (environmental sound classification), we propose a dual-branch residual network (dual-resnet) based on feature fusion. Furthermore, in terms of data pre-processing, a loop-padding method is proposed to patch shorter data, enabling it to obtain more useful information. At the same time, in order to prevent the occurrence of overfitting, we use the time-frequency data enhancement method to expand the dataset. After uniform pre-processing of all the original audio, the dual-branch residual network automatically extracts the frequency domain features of the log-Mel spectrogram and log-spectrogram. Then, the two different audio features are fused to make the representation of the audio features more comprehensive. The experimental results show that compared with other models, the classification accuracy of the UrbanSound8k dataset has been improved to different degrees.

Aqueous two-phase systems evolved double-layer film for enzymatic activity preservation: A universal protein storage strategy for paper based microdevice.

Integration and storage of bioactive reagents is an important and challenging task in microfluidic paper-based analytical devices (µPADs). Here, we developed a convenient and universal method to store proteins and preserve their activities in µPADs by using aqueous two-phase systems (ATPs) evolved film. A polyethylene glycol (PEG)-dextran (DEX) double-layer film was formed through dehydration of ATPs. Functional biomolecules were stored in the bottom DEX layer on the basis of the biased partitioning and rehydrated conveniently by simple addition of buffer solution at usage. As a demonstration, enzyme immunoassay (EIA) of carcinoembryonic antigen was performed successfully on µPAD integrated with antibodies. Even after 104 days of storage at 4 °C and ambient conditions, the EIA signal just lost less than 10% and 30%, which meet the storage requirements of invitro diagnosis reagents. The ATPs evolved double-layer film has double functions of stabilization and insulation, and provide a high efficiency of biomolecule preservation, thereby promoting the applications of µPADs in POC diagnostic assay.