Yumei Ren

Film materials exhibit excellent potential for intelligent wearable devices and flexible electronic components owing to their being lightweight, thin, and flexible. However, their application faces several challenges such as their poor mechanical and self-healing properties. Herein, a composite film comprising poly(vinyl alcohol) (PVA) as the matrix, a gallium-based liquid metal, and conductive magnetic nickel was fabricated. The film exhibits high conductivity, tensile strength, and self-healing ability as well as good electromagnetic interference (EMI) shielding performance. The excellent flexibility and overall EMI shielding performance of the PVA-based composite film are attributed to the introduction of liquid metals, containing abundant hydrogen bonding sites. This PVA-based composite film exhibits excellent mechanical characteristics (stress 28 MPa, strain 180%) owing to its superb flexibility. The composite film also has self-healing ability, allowing it to continue working after self-healing. In addition, the PVA-based composite film exhibits good EMI shielding performance through multiple loss mechanisms. The film (thickness 0.4 mm) exhibits an overall shielding performance of up to 26 dB in the X-band (8.2–12.4 GHz). The average total shielding effectiveness of the pure PVA film increased from 0.4 to 24.7 dB (a 6075% increase) after the introduction of nickel and liquid metals. This multifunctional magnetic composite film has excellent potential for intelligent wearable devices, flexible electronic components, and strain sensors.

This paper proposes a new random forest classification algorithm based on differential privacy protection. In order to reduce the impact of differential privacy protection on the accuracy of random forest classification, a hybrid decision tree algorithm is proposed in this paper. The hybrid decision tree algorithm is applied to the construction of random forest, which balances the privacy and classification accuracy of the random forest algorithm based on differential privacy. Experiment results show that the random forest algorithm based on differential privacy can provide high privacy protection while ensuring high classification performance, achieving a balance between privacy and classification accuracy, and has practical application value.

Abstract Objective: To study the therapeutic effect and mechanism of Suanzaoren Decoction on mice with depression. Methods: A model of depression was prepared by chronic unpredictable stimulation and reserpine induction. Behavioral tests, determination of norepinephrine and dopamine were performed. Results: The behavioral indicators of the model group were reduced, and the expression of norepinephrine and dopamine was decreased. Conclusion: Suanzaoren Decoction has an effect on the increase of serum norepinephrine and dopamine content, indicating that the jujube seed Soup has a certain effect on depression.

The stock market index typically mirrors the financial market's performance. Hence, accurate prediction of stock market index trends is essential for investors aiming to mitigate financial risk and enhance future investment returns. Traditional statistical approaches often struggle with the non-linear nature of stock market index data, leading to potential inaccuracies in long-term predictions. To address this issue, we introduce the TCN-LSTM-SNN (TLSNN) model, a hybrid framework that integrates Long Short-Term Memory (LSTM) and Temporal Convolutional Network (TCN) for robust feature extraction, within a highly efficient Spiking Neural Network (SNN) architecture. Additionally, we employ the Subtraction-Average-Based Optimizer (SABO) to refine the Variational Mode Decomposition (VMD) technique, thereby separating the periodic and trend components of stock indices, reducing noise interference, and establishing a decomposition ensemble framework to bolster the model's resilience. The experimental results show that the VMD-TLSNN hybrid model suggested in this study surpasses other individual benchmark models and their hybrid models in prediction accuracy. Additionally, it demonstrates notably lower energy consumption compared to other hybrid models.