Search

Deep learning has significantly advanced automatic medical diagnostics and released the occupation of human resources to reduce clinical pressure, yet the persistent challenge of data scarcity in this area hampers its further improvements and applications. To address this gap, we introduce a novel ensemble framework called `Efficient Transfer and Self-supervised Learning based Ensemble Framework' (ETSEF). ETSEF leverages features from multiple pre-trained deep learning models to efficiently learn powerful representations from a limited number of data samples. To the best of our knowledge, ETSEF is the first strategy that combines two pre-training methodologies (Transfer Learning and Self-supervised Learning) with ensemble learning approaches. Various data enhancement techniques, including data augmentation, feature fusion, feature selection, and decision fusion, have also been deployed to maximise the efficiency and robustness of the ETSEF model. Five independent medical imaging tasks, including endoscopy, breast cancer, monkeypox, brain tumour, and glaucoma detection, were tested to demonstrate ETSEF's effectiveness and robustness. Facing limited sample numbers and challenging medical tasks, ETSEF has proved its effectiveness by improving diagnostics accuracies from 10\% to 13.3\% when compared to strong ensemble baseline models and up to 14.4\% improvements compared with published state-of-the-art methods. Moreover, we emphasise the robustness and trustworthiness of the ETSEF method through various vision-explainable artificial intelligence techniques, including Grad-CAM, SHAP, and t-SNE. Compared to those large-scale deep learning models, ETSEF can be deployed flexibly and maintain superior performance for challenging medical imaging tasks, showing the potential to be applied to more areas that lack training data, Comment: 64 pages, 20 figures

Recently, transfer learning and self-supervised learning have gained significant attention within the medical field due to their ability to mitigate the challenges posed by limited data availability, improve model generalisation, and reduce computational expenses. Transfer learning and self-supervised learning hold immense potential for advancing medical research. However, it is crucial to recognise that transfer learning and self-supervised learning architectures exhibit distinct advantages and limitations, manifesting variations in accuracy, training speed, and robustness. This paper compares the performance and robustness of transfer learning and self-supervised learning in the medical field. Specifically, we pre-trained two models using the same source domain datasets with different pre-training methods and evaluated them on small-sized medical datasets to identify the factors influencing their final performance. We tested data with several common issues in medical domains, such as data imbalance, data scarcity, and domain mismatch, through comparison experiments to understand their impact on specific pre-trained models. Finally, we provide recommendations to help users apply transfer learning and self-supervised learning methods in medical areas, and build more convenient and efficient deployment strategies., Comment: 27 pages, 11 figures

Complex strain status can exist in 2D materials during their synthesis process, resulting in significant impacts on the physical and chemical properties. Despite their prevalence in experiments, their influence on the material properties and the corresponding mechanism are often understudied due to the lack of effective simulation methods. In this work, we investigated the effects of bending, rippling, and bubbling on the ferroelectric domains in In2Se3 monolayer by density functional theory (DFT) and deep learning molecular dynamics (DLMD) simulations. The analysis of the tube model shows that bending deformation imparts asymmetry into the system, and the polarization direction tends to orient towards the tensile side, which has a lower energy state than the opposite polarization direction. The energy barrier for polarization switching can be reduced by compressive strain according DFT results. The dynamics of the polarization switching is investigated by the DLMD simulations. The influence of curvature and temperature on the switching time follows the Arrhenius-style function. For the complex strain status in the rippling and bubbling model, the lifetime of the local transient polarization is analyzed by the autocorrelation function, and the size of the stable polarization domain is identified. Local curvature and temperature can influence the local polarization dynamics following the proposed Arrhenius-style equation. Through cross-scale simulations, this study demonstrates the capability of deep-learning potentials in simulating polarization for ferroelectric materials. It further reveals the potential to manipulate local polarization in ferroelectric materials through strain engineering.

Our recent intensive study has found that physics-informed neural networks (PINN) tend to be local approximators after training. This observation leads to this novel physics-informed radial basis network (PIRBN), which can maintain the local property throughout the entire training process. Compared to deep neural networks, a PIRBN comprises of only one hidden layer and a radial basis "activation" function. Under appropriate conditions, we demonstrated that the training of PIRBNs using gradient descendent methods can converge to Gaussian processes. Besides, we studied the training dynamics of PIRBN via the neural tangent kernel (NTK) theory. In addition, comprehensive investigations regarding the initialisation strategies of PIRBN were conducted. Based on numerical examples, PIRBN has been demonstrated to be more effective and efficient than PINN in solving PDEs with high-frequency features and ill-posed computational domains. Moreover, the existing PINN numerical techniques, such as adaptive learning, decomposition and different types of loss functions, are applicable to PIRBN. The programs that can regenerate all numerical results can be found at https://github.com/JinshuaiBai/PIRBN., Comment: 48 pages, 26 figures

Friction-induced vibration (FIV) is very common in engineering areas. Analysing the dynamic behaviour of systems containing a multiple-contact point frictional interface is an important topic. However, accurately simulating nonsmooth/discontinuous dynamic behaviour due to friction is challenging. This paper presents a new physics-informed neural network approach for solving nonsmooth friction-induced vibration or friction-involved vibration problems. Compared with schemes of the conventional time-stepping methodology, in this new computational framework, the theoretical formulations of nonsmooth multibody dynamics are transformed and embedded in the training process of the neural network. Major findings include that the new framework not only can perform accurate simulation of nonsmooth dynamic behaviour, but also eliminate the need for extremely small time steps typically associated with the conventional time-stepping methodology for multibody systems, thus saving much computation work while maintaining high accuracy. Specifically, four kinds of high-accuracy PINN-based methods are proposed: (1) single PINN; (2) dual PINN; (3) advanced single PINN; (4) advanced dual PINN. Two typical dynamics problems with nonsmooth contact are tested: one is a 1-dimensional contact problem with stick-slip, and the other is a 2-dimensional contact problem considering separation-reattachment and stick-slip oscillation. Both single and dual PINN methods show their advantages in dealing with the 1-dimensional stick-slip problem, which outperforms conventional methods across friction models that are difficult to simulate by the conventional time-stepping method. For the 2-dimensional problem, the capability of the advanced single and advanced dual PINN on accuracy improvement is shown, and they provide good results even in the cases when conventional methods fail., Comment: 37 Pages, 24 figures

Deep learning (DL) relies heavily on data, and the quality of data influences its performance significantly. However, obtaining high-quality, well-annotated datasets can be challenging or even impossible in many real-world applications, such as structural risk estimation and medical diagnosis. This presents a significant barrier to the practical implementation of DL in these fields. Physics-guided deep learning (PGDL) is a novel type of DL that can integrate physics laws to train neural networks. This can be applied to any systems that are controlled or governed by physics laws, such as mechanics, finance and medical applications. It has been demonstrated that, with the additional information provided by physics laws, PGDL achieves great accuracy and generalisation in the presence of data scarcity. This review provides a detailed examination of PGDL and offers a structured overview of its use in addressing data scarcity across various fields, including physics, engineering and medical applications. Moreover, the review identifies the current limitations and opportunities for PGDL in relation to data scarcity and offers a thorough discussion on the future prospects of PGDL., Comment: 26 Pages, 4 figures, 2 tables, 116 references. This work is going to submit to Nature Machine Intelligence

Physics-informed neural network (PINN) has recently gained increasing interest in computational mechanics. In this work, we present a detailed introduction to programming PINN-based computational solid mechanics. Besides, two prevailingly used physics-informed loss functions for PINN-based computational solid mechanics are summarised. Moreover, numerical examples ranging from 1D to 3D solid problems are presented to show the performance of PINN-based computational solid mechanics. The programs are built via Python coding language and TensorFlow library with step-by-step explanations. It is worth highlighting that PINN-based computational mechanics is easy to implement and can be extended for more challenging applications. This work aims to help the researchers who are interested in the PINN-based solid mechanics solver to have a clear insight into this emerging area. The programs for all the numerical examples presented in this work are available on https://github.com/JinshuaiBai/PINN_Comp_Mech., Comment: 32 pages, 20 figures are include in this manuscript

Magnetoelectric effect is a fundamental physics phenomenon that synergizes electric and magnetic degrees of freedom to generate distinct material responses like electrically tuned magnetism, which serves as a key foundation of the emerging field of spintronics. Here, we show by first-principles studies that ferroelectric (FE) polarization of an In2Se3 monolayer can modulate the magnetism of an adjacent transition-metal (TM) decorated graphene layer via an FE induced electronic transition. The TM nonbonding d-orbital shifts downward and hybridizes with carbon p states near the Fermi level, suppressing the magnetic moment, under one FE polarization, but on reversed FE polarization this TM d-orbital moves upward, restoring the original magnetic moment. This finding of robust magnetoelectric effect in TM decorated graphene/In2Se3 heterostructure offers powerful insights and a promising avenue for experimental exploration of FE controlled magnetism in 2D materials.

Two-dimensional ferroelectrics are important quantum materials which have found novel application in nonvolatile memories, however, the effects of reversible polarization on chemical reactions and interaction with environments are rarely studied despite of its importance. Here, based on the first-principles calculations, we found distinct gas adsorption behaviors on the surfaces of ferroelectric In2Se3 layer and the reversible gas caption and release controlled by ferroelectric switch. We rationalize the novel phenomena to the synergistic effect of the different electrostatic potential and electron transfer induced by band alignments between frontier molecular orbitals of gas and band edge states of substrate. Excitingly, the adsorption of paramagnetic gas molecules such as NO and NO2 can induce surface magnetism, which is also sensitive to ferroelectric polarization direction of In2Se3, indicating the application of In2Se3 as threshold magnetic sensors or switcher. Furthermore, it is suggested two NO molecules prefer to ferromagnetically couple with each other, the Curie temperature is polarization dependent which can reach up to 50K, leading to the long-sought 2D molecule multiferroics. The ferroelectric controllable adsorption behavior and molecule multiferroic feature will find extensive application in gas caption, selective catalytic reduction and spintronic device.

Two-dimensional (2D) multiferroics exhibit cross-control capacity between magnetic and electric responses in reduced spatial domain, making them well suited for next-generation nanoscale devices; however, progress has been slow in developing materials with required characteristic properties. Here we identify by first-principles calculations robust 2D multiferroic behaviors in decorated Fe2O3 monolayer, showcasing N@Fe2O3 as a prototypical case, where ferroelectricity and ferromagnetism stem from the same origin, namely Fe d-orbit splitting induced by the Jahn-Teller distortion and associated crystal field changes. The resulting ferromagnetic and ferroelectric polarization can be effectively reversed and regulated by applied electric field or strain, offering efficient functionality. These findings establish strong materials phenomena and elucidate underlying physics mechanism in a family of truly 2D multiferroics that are highly promising for advanced device applications., Comment: 4 figures

Carbon nanofibers (NFs) have been envisioned with broad promising applications, such as nanoscale actuators and energy storage medium. This work reports for the first-time super-elastic tensile characteristics of NFs constructed from a screw dislocation of carbon nanocones (NF-S). The NF-S exhibits three distinct elastic deformation stages under tensile, including an initial homogeneous deformation, delamination, and further stretch of covalent bonds. The delamination process endows the NF-S extraordinary tensile deformation capability, which is not accessible from its counterpart with a normal cup-stacked geometry. The failure of NF-S is governed by the inner edges of the nanocone due to the strain concentration, leading to a common failure force for NF-S with varying geometrical parameters. Strikingly, the delamination process is dominated by the inner radius and the apex angle of the nanocone. For a fixed apex angle, the yielding strain increases remarkably when the inner radius increases, which can exceed 1000%. It is also found that the screw dislocation allows the nanocones flattening and sliding during compression. This study provides a comprehensive understanding on the mechanical properties of NFs as constructed from carbon nanocones, which opens new avenues for novel applications, such as nanoscale actuators., Comment: 10 pages, 10 figures

Study on mechanical properties of one-dimensional layered titanate nanomaterials is crucial since they demonstrate important applications in various fields. Here, we conducted ex situ and in situ atomic-scale investigation on bending properties of a kind of ceramic layered titanate (Na2Ti2O4(OH)2) nanowires in a transmission electron microscopy. The nanowires showed flexibility along <100> direction and could obtain a maximum bending strain of nearly 37%. By analysing the defect behaviours, the unique bending properties of this ceramic material was found to correlate with a novel arrangement of dislocations, an accessible nucleation and movement along the axial direction resulting from the weak electrostatic interaction between the TiO6 layers and the low b/a ratio. These results provide pioneering and key understanding on bending behaviours of layered titanate nanowire families and potentially other one-dimensional nanomaterials with layered crystalline structures., Comment: 9 pages, 5 figures

This work summarizes recent progress on the thermal transport properties of three-dimensional (3D) nanostructures, with an emphasis on experimental results. Depending on the applications, different 3D nanostructures can be prepared or designed to either achieve a low thermal conductivity for thermal insulation or thermoelectric devices, or a high thermal conductivity for thermal interface materials used in the continuing miniaturization of electronics. A broad range of 3D nanostructures have been discussed, ranging from colloidal crystals/assemblies, array structures, holey structures, hierarchical structures, 3D nanostructured fillers for metal matrix composites and polymer composites. Different factors that impact the thermal conductivity of these 3D structures are compared and analyzed. This work provides an overall understanding of the thermal transport properties of various 3D nanostructures, which will shed light on the thermal management at nanoscale., Comment: 30 pages, 23 figures

The extremely high thermal conductivity of graphene has received great attention both in experiments and calculations. Obviously, new feature in thermal properties is of primary importance for application of graphene-based materials in thermal management in nanoscale. Here, we studied the thermal conductivity of graphene helicoid, a newly reported graphene-related nanostructure, using molecular dynamics simulation. Interestingly, in contrast to the converged cross-plane thermal conductivity in multi-layer graphene, axial thermal conductivity of graphene helicoid keeps increasing with thickness with a power law scaling relationship, which is a consequence of the divergent in-plane thermal conductivity of two-dimensional graphene. Moreover, the large overlap between adjacent layers in graphene helicoid also promotes higher thermal conductivity than multi-layer graphene. Furthermore, in the small strain regime (< 10%), compressive strain can effectively increase the thermal conductivity of graphene helicoid, while in the ultra large strain regime (~100% to 500%), tensile strain does not decrease the heat current, unlike that in generic solid-state materials. Our results reveal that the divergence in thermal conductivity, associated with the anomalous strain dependence and the unique structural flexibility, make graphene helicoid a new platform for studying fascinating phenomena of key relevance to the scientific understanding and technological applications of graphene-related materials., Comment: 7 figures

The "titanium fire" as produced during high pressure and friction is the major failure scenario for aero-engines. To alleviate this issue, Ti-V-Cr and Ti-Cu-Al series burn resistant titanium alloys have been developed. However, which burn resistant alloy exhibit better property with reasonable cost needs to be evaluated. This work unveils the burning mechanisms of these alloys and discusses whether burn resistance of Cr and V can be replaced by Cu, on which thorough exploration is lacking. Two representative burn resistant alloys are considered, including Ti14(Ti-13Cu-1Al-0.2Si) and Ti40(Ti-25V-15Cr-0.2Si)alloys. Compared with the commercial non-burn resistant titanium alloy, i.e., TC4(Ti-6Al-4V)alloy, it has been found that both Ti14 and Ti40 alloys form "protective" shields during the burning process. Specifically, for Ti14 alloy, a clear Cu-rich layer is formed at the interface between burning product zone and heat affected zone, which consumes oxygen by producing Cu-O compounds and impedes the reaction with Ti-matrix. This work has established a fundamental understanding of burning resistant mechanisms for titanium alloys. Importantly, it is found that Cu could endow titanium alloys with similar burn resistant capability as that of V or Cr, which opens a cost-effective avenue to design burn resistant titanium alloys., Comment: 6 figures

This chapter introduces the thermal conductivity of a novel one-dimensional carbon nanostructure - diamond nanothread. It starts by introducing the family of the diamond nanothread as acquired from density functional theory calculations and also its successful experimental synthesisation. It then briefs the mechanical properties of the diamond nanothreads as a fundamental for their engineering applications. After that, it focuses on the thermal transport properties of the diamond nanothreads by examining the influences from various parameters such as size, geometry, and temperature. Then, the application of diamond nanothread as reinforcements for nanocomposites is discussed. By the end of the chapter, future directions and their potential applications are discussed., Comment: 19 pages, 13 figures

The excellent mechanical properties of graphene have enabled it as appealing candidate in the field of impact protection or protective shield. By considering a monolayer graphene membrane, in this work, we assessed its deformation mechanisms under hypervelocity impact (from 2 to 6 km/s), based on a serial of in silico studies. It is found that the cracks are formed preferentially in the zigzag directions which are consistent with that observed from tensile deformation. Specifically, the boundary condition is found to exert an obvious influence on the stress distribution and transmission during the impact process, which eventually influences the penetration energy and crack growth. For similar sample size, the circular shape graphene possesses the best impact resistance, followed by hexagonal graphene membrane. Moreover, it is found the failure shape of graphene membrane has a strong relationship with the initial kinetic energy of the projectile. The higher kinetic energy, the more number the cracks. This study provides a fundamental understanding of the deformation mechanisms of monolayer graphene under impact, which is crucial in order to facilitate their emerging future applications for impact protection, such as protective shield from orbital debris for spacecraft., Comment: 10 pages, 9 figures

This review summarizes the current studies of the thermal transport properties of one-dimensional (1D) carbon nanomaterials and nanoarchitectures. Considering different hybridization states of carbon, emphases are laid on a variety of 1D carbon nanomaterials, such as diamond nanothreads, penta-graphene nanotubes, supernanotubes, and carbyne. Based on experimental measurements and simulation/calculation results, we discuss the dependence of the thermal conductivity of these 1D carbon nanomaterials on a wide range of factors, including the size effect, temperature influence, strain effect, and others. This review provides an overall understanding of the thermal transport properties of 1D carbon nanomaterials and nanoarchitectures, which paves the way for effective thermal management at nanoscale., Comment: 10 pages, 10 figures