Generating High-Precision Force Fields for Molecular Dynamics Simulations to Study Chemical Reaction Mechanisms Using Molecular Configuration Transformer.

Theoretical studies on chemical reaction mechanisms have been crucial in organic chemistry. Traditionally, calculating the manually constructed molecular conformations of transition states for chemical reactions using quantum chemical calculations is the most commonly used method. However, this way is heavily dependent on individual experience and chemical intuition. In our previous study, we proposed a research paradigm that used enhanced sampling in molecular dynamics simulations to study chemical reactions. This approach can directly simulate the entire process of a chemical reaction. However, the computational speed limited the use of high-precision potential energy functions for simulations. To address this issue, we presented a scheme for training high-precision force fields for molecular modeling using a previously developed graph-neural-network-based molecular model, molecular configuration transformer. This potential energy function allowed for highly accurate simulations at a low computational cost, leading to more precise calculations of the mechanism of chemical reactions. We applied this approach to study a Claisen rearrangement reaction and a carbonyl insertion reaction catalyzed by manganese.

ACG-EmoCluster: A Novel Framework to Capture Spatial and Temporal Information from Emotional Speech Enhanced by DeepCluster.

Speech emotion recognition (SER) is a task that tailors a matching function between the speech features and the emotion labels. Speech data have higher information saturation than images and stronger temporal coherence than text. This makes entirely and effectively learning speech features challenging when using feature extractors designed for images or texts. In this paper, we propose a novel semi-supervised framework for extracting spatial and temporal features from speech, called the ACG-EmoCluster. This framework is equipped with a feature extractor for simultaneously extracting the spatial and temporal features, as well as a clustering classifier for enhancing the speech representations through unsupervised learning. Specifically, the feature extractor combines an Attn-Convolution neural network and a Bidirectional Gated Recurrent Unit (BiGRU). The Attn-Convolution network enjoys a global spatial receptive field and can be generalized to the convolution block of any neural networks according to the data scale. The BiGRU is conducive to learning temporal information on a small-scale dataset, thereby alleviating data dependence. The experimental results on the MSP-Podcast demonstrate that our ACG-EmoCluster can capture effective speech representation and outperform all baselines in both supervised and semi-supervised SER tasks.

Robust, flexible, and high-performance electromagnetic interference shielding films with long-lasting service.

It is of great significance for electromagnetic interference (EMI) shielding materials to fulfill long-lasting service requirements. Here, waterborne polyurethane (WPU) was coated on the surface of a silver nanowire (AgNW) network with sputter-deposited nickel nanoparticles (NiNPs) by dip-coating technology to improve their durability. After five dip-coating cycles, a WPU layer nearly coated the whole surface of the hybrid papers, and only a fraction of the metal filler is bare. The resultant hybrid papers exhibit an electrical conductivity of ∼3500 S m-1, remnant magnetization of 0.03 emu g-1, saturation magnetization of 0.10 emu g-1, and coercivity of 256 Oe. On the one hand, the presence of the WPU coating does not affect the shielding effectiveness (SE) of the hybrid papers; on the other hand, the WPU coating enhances the ability to resist tape peeling. Moreover, the resultant hybrid papers still maintain the original SE value (∼80 dB), even after exposure to air for 5 months owing to the isolation effect of the WPU coating, implying long-lasting durability. The results confirm that the obtained hybrid papers can meet the requirements of practical applications.

High capacity reversible watermarking for audio by histogram shifting and predicted error expansion.

Being reversible, the watermarking information embedded in audio signals can be extracted while the original audio data can achieve lossless recovery. Currently, the few reversible audio watermarking algorithms are confronted with following problems: relatively low SNR (signal-to-noise) of embedded audio; a large amount of auxiliary embedded location information; and the absence of accurate capacity control capability. In this paper, we present a novel reversible audio watermarking scheme based on improved prediction error expansion and histogram shifting. First, we use differential evolution algorithm to optimize prediction coefficients and then apply prediction error expansion to output stego data. Second, in order to reduce location map bits length, we introduced histogram shifting scheme. Meanwhile, the prediction error modification threshold according to a given embedding capacity can be computed by our proposed scheme. Experiments show that this algorithm improves the SNR of embedded audio signals and embedding capacity, drastically reduces location map bits length, and enhances capacity control capability.

Dynamic multiobjective optimization algorithm based on average distance linear prediction model.

Many real-world optimization problems involve objectives, constraints, and parameters which constantly change with time. Optimization in a changing environment is a challenging task, especially when multiple objectives are required to be optimized simultaneously. Nowadays the common way to solve dynamic multiobjective optimization problems (DMOPs) is to utilize history information to guide future search, but there is no common successful method to solve different DMOPs. In this paper, we define a kind of dynamic multiobjectives problem with translational Paretooptimal set (DMOP-TPS) and propose a new prediction model named ADLM for solving DMOP-TPS. We have tested and compared the proposed prediction model (ADLM) with three traditional prediction models on several classic DMOP-TPS test problems. The simulation results show that our proposed prediction model outperforms other prediction models for DMOP-TPS.