Brain-inspired multisensory integration neural network for cross-modal recognition through spatiotemporal dynamics and deep learning.

The integration and interaction of cross-modal senses in brain neural networks can facilitate high-level cognitive functionalities. In this work, we proposed a bioinspired multisensory integration neural network (MINN) that integrates visual and audio senses for recognizing multimodal information across different sensory modalities. This deep learning-based model incorporates a cascading framework of parallel convolutional neural networks (CNNs) for extracting intrinsic features from visual and audio inputs, and a recurrent neural network (RNN) for multimodal information integration and interaction.

Deep source transfer learning for the estimation of internal brain dynamics using scalp EEG.

Electroencephalography (EEG) provides high temporal resolution neural data for brain-computer interfacing via noninvasive electrophysiological recording. Estimating the internal brain activity by means of source imaging techniques can further improve the spatial resolution of EEG and enhance the reliability of neural decoding and brain-computer interaction. In this work, we propose a novel EEG data-driven source imaging scheme for precise and efficient estimation of macroscale spatiotemporal brain dynamics across thalamus and cortical regions with deep learning methods.

Synthesis of chitosan-based flocculant by dielectric barrier discharge modification and its flocculation performance in wastewater treatment.

As a typical type of organic flocculant, chitosan is limited by its poor water solubility and narrow pH range application. Grafting modification can improve chitosan's solubility and availability through linking macromolecular chains with other types of water-soluble groups or functional side groups. In this study, dielectric barrier discharge (DBD) was used to active the surface of chitosan, then activated chitosan was polymerized with acrylamide to synthesize a chitosan-based flocculant, chitosan-acrylamide (CS-AM).

Dielectric barrier discharge plasma-modified chitosan flocculant and its flocculation performance.

The flocculation performance of chitosan can be enhanced by grafting modification to overcome its disadvantages of poor water solubility. In this study, chitosan was modified by dielectric barrier discharge plasma and polymerized with acrylamide and aluminum chloride to synthesize a new chitosan-based flocculant, namely, chitosan-acrylamide-aluminum chloride (CA-PAC). After optimizing the synthesis conditions of CA-PAC, the best conditions were as follows: discharge time of 3 min, discharge power of 50 W, polymerization temperature of 60 °C, polymerization time of 3 h, total monomer concentration of 100 g/L, and m(AlCl):m(CA) ratio of 2:1.

Decoding Digital Visual Stimulation From Neural Manifold With Fuzzy Leaning on Cortical Oscillatory Dynamics.

A crucial point in neuroscience is how to correctly decode cognitive information from brain dynamics for motion control and neural rehabilitation. However, due to the instability and high dimensions of electroencephalogram (EEG) recordings, it is difficult to directly obtain information from original data. Thus, in this work, we design visual experiments and propose a novel decoding method based on the neural manifold of cortical activity to find critical visual information.

Effect of MoS on phenol decomposition in water after high-voltage pulse discharge treatment.

Molybdenum disulfide (MoS) was added to the system after being treated with high-voltage pulse discharge plasma to improve the degradation efficiency of pollutants and reduce energy consumption. The discharge plasma-treated solution contains hydrogen peroxide and metal iron ions, and MoS addition can cause co-catalytic Fenton reaction. The effects of discharge time, initial pH, phenol concentration, MoS dosage, discharge voltage, and gas type on phenol removal and aqueous HO concentration were mainly investigated.