BEGAN: Boltzmann-Reweighted Data Augmentation for Enhanced GAN-Based Molecule Design in Insect Pheromone Receptors.

Identifying small molecules that bind strongly to target proteins in rational molecular design is crucial. Machine learning techniques, such as generative adversarial networks (GAN), are now essential tools for generating such molecules. In this study, we present an enhanced method for molecule generation using objective-reinforced GANs.

Intrafibrillar calcium carbonate mineralization of electrospinning polyvinyl alcohol/collagen films with improved mechanical and bioactive properties.

Collagen films play an essential role in guided bone-regeneration (GBR) techniques, which create space, promote cell adhesion, and induce osteogenic differentiation. It is therefore crucial to design appropriate GBR films to facilitate bone regeneration. However, current electrospun collagen scaffolds used as bioactive materials have limited clinical applications due to their poor mechanical properties.

Tuning Electronic Friction in Structural Superlubric Schottky Junctions.

Friction at sliding interfaces, even in the atomistically smooth limit, can proceed through many energy dissipation channels, such as phononic and electronic excitation. These processes are often entangled and difficult to distinguish, eliminate, and control, especially in the presence of wear. Structural superlubricity (SSL) is a wear-free state with ultralow friction that closes most of the dissipation channels, except for electronic friction, which raises a critical concern of how to effectively eliminate and control such a channel.

Hybrid Space Calibrated 3D Network of Diffractive Hyperspectral Optical Imaging Sensor.

Diffractive multispectral optical imaging plays an essential role in optical sensing, which typically suffers from the image blurring problem caused by the spatially variant point spread function. Here, we propose a novel high-quality and efficient hybrid space calibrated 3D network "HSC3D" for spatially variant diffractive multispectral imaging that utilizes the 3D U-Net structure combined with space calibration modules of magnification and rotation effects to achieve high-accuracy eight-channel multispectral restoration. The algorithm combines the advantages of the space calibrated module and U-Net architecture with 3D convolutional layers to improve the image quality of diffractive multispectral imaging without the requirements of complex equipment modifications and large amounts of data.

A Study on the Influence of Central Edge Absence in Helical Grinding for Micro-Hole Fabrication.

The fabrication of micro-holes in hard-to-machine materials presents considerable challenges in precision machining. This study proposes a novel approach that employs high-strength micro-grinding tools with a central abrasive grain absence to create micro-holes through helical grinding. Due to the random distribution of abrasive grains, the absence of grains at the tool's center becomes an inevitable technical challenge.

A photocurable and thermocurable composite hydrogel and the application in a contraction resistant full-thickness skin model.

Three-dimensional (3D) organotypic skin in vitro has attracted increasing attention for drug development, cosmetics evaluation, and even clinical applications. However, the severe contraction of these models restricts their application, especially in the analyses based on barrier functions such as percutaneous penetration. For the full-thickness skin equivalents, the mechanical properties of the dermis scaffold plays an important role in the contraction resistance.

A multi-source domain feature adaptation network for potato disease recognition in field environment.

Accurate identification of potato diseases is crucial for reducing yield losses. To address the issue of low recognition accuracy caused by the mismatch between target domain and source domain due to insufficient samples, the effectiveness of Multi-Source Unsupervised Domain Adaptation (MUDA) method in disease identification is explored. A Multi-Source Domain Feature Adaptation Network (MDFAN) is proposed, employing a two-stage alignment strategy.

Adaptive CVgen: Leveraging reinforcement learning for advanced sampling in protein folding and chemical reactions.

Enhanced sampling techniques have traditionally encountered two significant challenges: identifying suitable reaction coordinates and addressing the exploration-exploitation dilemma, particularly the difficulty of escaping local energy minima. Here, we introduce Adaptive CVgen, a universal adaptive sampling framework designed to tackle these issues. Our approach utilizes a set of collective variables (CVs) to comprehensively cover the system's potential evolutionary phase space, generating diverse reaction coordinates to address the first challenge.

Machine learning-driven discovery of high-performance MEMS disk resonator gyroscope structural topologies.

The design of the microelectromechanical system (MEMS) disc resonator gyroscope (DRG) structural topology is crucial for its physical properties and performance. However, creating novel high-performance MEMS DRGs has long been viewed as a formidable challenge owing to their enormous design space, the complexity of microscale physical effects, and time-consuming finite element analysis (FEA). Here, we introduce a new machine learning-driven approach to discover high-performance DRG topologies.

Multi-resolution visual Mamba with multi-directional selective mechanism for retinal disease detection.

Introduction: Retinal diseases significantly impact patients' quality of life and increase social medical costs. Optical coherence tomography (OCT) offers high-resolution imaging for precise detection and monitoring of these conditions. While deep learning techniques have been employed to extract features from OCT images for classification, convolutional neural networks (CNNs) often fail to capture global context due to their focus on local receptive fields.

Design of Docking Interfaces for On-Orbit Assembly of Large Structures in Space.

Considering the complexity of on-orbit assembly during space missions and the super-large size of space structures, this paper presents the design for a new type of docking interface with an androgynous body that exhibits a number of advantages, including high connection strength and a compact structure. The androgynous body has a conical guided symmetric design with a symmetry of 90°. The geometric design of the docking surface is described in detail in order to prove its advantages.

Halogen-Bonding Nanoarchitectonics in Supramolecular Plasticizers for Breaking the Trade-Off between Ion Transport and Mechanical Strength of Polymer Electrolytes for High-Voltage Li-Metal Batteries.

The low ionic conductivity of poly(ethylene oxide) (PEO)-based polymer electrolytes at room temperature impedes their practical applications. The addition of a plasticizer into polymer electrolytes could significantly promote ion transport while inevitably decreasing their mechanical strength. Herein, we report a supramolecular plasticizer (SMP) to break the trade-off effect between ionic conductivity and mechanical properties in PEO-based polymer electrolytes.

Strong and efficient bismuth telluride-based thermoelectrics for Peltier microcoolers.

Thermoelectric Peltier coolers (PCs) are being increasingly used as temperature stabilizers for optoelectronic devices. Increasing integration drives PC miniaturization, requiring thermoelectric materials with good strength. We demonstrate a simultaneous gain of thermoelectric and mechanical performance in (Bi, Sb)Te, and successfully fabricate micro PCs (2 × 2 mm cross-section) that show excellent maximum cooling temperature difference of 89.

ChatDiff: A ChatGPT-based diffusion model for long-tailed classification.

Long-tailed data distributions have been a major challenge for the practical application of deep learning. Information augmentation intends to expand the long-tailed data into uniform distribution, which provides a feasible way to mitigate the data starvation of underrepresented classes. However, most existing augmentation methods face two significant challenges: (1) limited diversity in generated samples, and (2) the adverse effect of generated negative samples on downstream classification performance.

Active Learning Guided Discovery of High Entropy Oxides Featuring High H-production.

High entropy oxides (HEOs) represent a class of solid solutions comprising multiple elements, offering significant scientific potential. Due to the enormous combination types of elements, the design of HEOs with desirable properties within high-dimensional composition spaces has traditionally relied heavily on knowledge and intuition. In this study, we present an active learning (AL) strategy tailored to efficiently explore the vast compositional space of HEOs.

Optimization of Mechanical Properties during Cold Rolling and Wrap-Forming for Metal Helical Tubes.

The proposed method involves the utilization of a strip roll-forming technique to fulfill the specific requirements for constructing large-scale structures in orbit and space station trusses during extraterrestrial exploration. This involves progressively rolling out a metal strip with an L+V-shaped locking edge through multiple passes of forming rolls featuring different section shapes. The process of helical locking enables the formation of a slender, spiral-shaped tube, which can be utilized for the in-orbit assembly of exceptionally large structures.

Algorithm Analysis and Optimization of a Digital Image Correlation Method Using a Non-Probability Interval Multidimensional Parallelepiped Model.

Digital image correlation (DIC), a widely used non-contact measurement technique, often requires empirical tuning of several algorithmic parameters to strike a balance between computational accuracy and efficiency. This paper introduces a novel uncertainty analysis approach aimed at optimizing the parameter intervals of a DIC algorithm. Specifically, the method leverages the inverse compositional Gauss-Newton algorithm combined with a prediction-correction scheme (IC-GN-PC), considering three critical parameters as interval variables.

Damping Characteristics of a Novel Bellows Viscous Damper.

Micro-vibrations during the operation of space remote sensing equipment can significantly affect optical imaging quality. To address this issue, a bellows-type viscous damper serves as an effective passive damping and vibration isolation solution. This paper introduces a bellows-type viscous damper with adjustable damping capabilities, designed for mid- to high-frequency applications.

Hyperspectral Attention Network for Object Tracking.

Hyperspectral video provides rich spatial and spectral information, which is crucial for object tracking in complex scenarios. Despite extensive research, existing methods often face an inherent trade-off between rich spectral information and redundant noisy information. This dilemma arises from the efficient utilization of hyperspectral image data channels.