Federated learning (FL) for medical image segmentation becomes more challenging in multi-task settings where clients might have different categories of labels represented in their data. For example, one client might have patient data with healthy pan
creases only while datasets from other clients may contain cases with pancreatic tumors. The vanilla federated averaging algorithm makes it possible to obtain more generalizable deep learning-based segmentation models representing the training data from multiple institutions without centralizing datasets. However, it might be sub-optimal for the aforementioned multi-task scenarios. In this paper, we investigate heterogeneous optimization methods that show improvements for the automated segmentation of pancreas and pancreatic tumors in abdominal CT images with FL settings.
With the miniaturization and integration of nanoelectronic devices, efficient heat removal becomes a key factor affecting the reliable operation of the nanoelectronic device. With the high intrinsic thermal conductivity, good mechanical flexibility,
and precisely controlled growth, two-dimensional (2D) materials are widely accepted as ideal candidates for thermal management materials. In this work, by solving the phonon Boltzmann transport equation (BTE) based on first-principles calculations, we comprehensively investigated the thermal conductivity of novel 2D layered MSi$_2$N$_4$ (M = Mo, W). Our results point to competitive thermal conductivities (162 W/mK) of monolayer MoSi$_2$N$_4$, which is around two times larger than that of WSi$_2$N$_4$ and seven times larger than that of silicene despite their similar non-planar structures. It is revealed that the high thermal conductivity arises mainly from its large group velocity and low anharmonicity. Our result suggests that MoSi$_2$N$_4$ could be a potential candidate for 2D thermal management materials.
With the successful synthesis of the two-dimensional (2D) gallium nitride (GaN) in a planar honeycomb structure, the phonon transport properties of 2D GaN have been reported. However, it remains unclear for the thermal transport in Ga-based materials
by substituting N to other elements in the same main group, which is of more broad applications. In this paper, based on first-principles calculations, we performed a comprehensive study on the phonon transport properties of 2D GaX (X = N, P, and As) with planar or buckled honeycomb structures. The thermal conductivity of GaP (1.52 Wm-1K-1) is found unexpectedly ultra-low, which is in sharp contrast to GaN and GaAs despite their similar honeycomb geometry structure. Based on PJTE theory, GaP and GaAs stabilize in buckling structure, different from the planar structure of GaN. Compared to GaN and GaAs, strong phonon-phonon scattering is found in GaP due to the strongest phonon anharmonicity. Given electronic structures, deep insight is gained into the phonon transport that the delocalization of electrons in GaP is restricted due to the buckling structure. Thus, non-bonding lone pair electrons of P atoms induce nonlinear electrostatic forces upon thermal agitation, leading to increased phonon anharmonicity in the lattice, thus reducing thermal conductivity. Our study offers a fundamental understanding of phonon transport in GaX monolayers with honeycomb structure, which will enrich future studies of nanoscale phonon transport in 2D materials
Faults in photovoltaic (PV) systems can seriously affect the efficiency, energy yield as well as the security of the entire PV plant, if not detected and corrected quickly. Therefore, fault diagnosis of PV arrays is indispensable for improving the re
liability, efficiency, productivity and safety of PV power stations. Instead of conventional thresholding methods and artificial intelligent (AI) machine learning approaches, an innovative Gaussian Mixture Model (GMM) based fault detection approach is proposed in this work. This approach combines the superiority of GMM in modeling stochastic power outputs of PV modules and the flexibility and simplicity of Sandia PV Array Performance Model (SPAM) to accurately detect under-performing modules. Firstly, GMM is proposed to represent the probabilistic distribution functions (PDF) of different PV modules power outputs, and the parameter sets of which are obtained by Expectation Maximization algorithm. Secondly, a simplified explicit expression for output power of PV modules, which highlights the influences of tilt and azimuth angles, is deduced based on the SPAM. Then, an orientation independent vector C is developed to eliminate the probability distribution differences of power outputs caused by varying azimuth angles and tilt angles. Jensen-Shannon (JS) divergence, which captures the differences between probability density of C of each PV module, are generated and used as fault indicators. Simulation data acquired from the original SPAM are used to assess the performance of the proposed approach. Results show that the proposed approach successfully detects faults in PV systems. This work is especially suitable for the PV modules that have different installation parameters such as azimuth angles and tilt angles, and it does not require the use of irradiance or temperature sensors.
Existing deep learning technologies generally learn the features of chest X-ray data generated by Generative Adversarial Networks (GAN) to diagnose COVID-19 pneumonia. However, the above methods have a critical challenge: data privacy. GAN will leak
the semantic information of the training data which can be used to reconstruct the training samples by attackers, thereby this method will leak the privacy of the patient. Furthermore, for this reason that is the limitation of the training data sample, different hospitals jointly train the model through data sharing, which will also cause the privacy leakage. To solve this problem, we adopt the Federated Learning (FL) frame-work which is a new technique being used to protect the data privacy. Under the FL framework and Differentially Private thinking, we propose a FederatedDifferentially Private Generative Adversarial Network (FedDPGAN) to detectCOVID-19 pneumonia for sustainable smart cities. Specifically, we use DP-GAN to privately generate diverse patient data in which differential privacy technology is introduced to make sure the privacy protection of the semantic information of training dataset. Furthermore, we leverage FL to allow hospitals to collaboratively train COVID-19 models without sharing the original data. Under Independent and Identically Distributed (IID) and non-IID settings, The evaluation of the proposed model is on three types of chest X-ray (CXR) images dataset (COVID-19, normal, and normal pneumonia). A large number of the truthful reports make the verification of our model can effectively diagnose COVID-19 without compromising privacy.
Wavelength-sized microdisk resonators were fabricated on a single crystalline 4H-silicon-carbide-oninsulator platform (4H-SiCOI). By carrying out microphotoluminescence measurements at room temperature, we show that the microdisk resonators support w
hispering-gallery modes (WGMs) with quality factors up to $5.25 times 10^3$ and mode volumes down to $2.69 times(lambda /n)^3$ at the visible and near-infrared wavelengths. Moreover, the demonstrated wavelength-sized microdisk resonators exhibit WGMs whose resonant wavelengths compatible with the zero-phonon lines of spin defects in 4H-SiCOI, making them a promising candidate for applications in cavity quantum electrodynamics and integrated quantum photonic circuits.
Thermal management materials are of critical importance for engineering miniaturized electronic devices, where theoretical design of such materials demands the evaluation of thermal conductivities which are numerically expensive. In this work, we app
lied the recently developed machine learning interatomic potential (MLIP) to evaluate the thermal conductivity of hexagonal boron nitride monolayers. The MLIP is obtained using the Gaussian approximation potential (GAP) method, and the resulting lattice dynamical properties and thermal conductivity are compared with those obtained from explicit frozen phonon calculations. It is observed that accurate thermal conductivity can be obtained based on MLIP constructed with about 30% representative configurations, and the high-order force constants provide a more reliable benchmark on the quality of MLIP than the harmonic approximation.
Metasurfaces, the ultrathin media with extraordinary wavefront modulation ability, have shown versatile potential in manipulating waves. However, existing acoustic metasurfaces are limited by their narrow-band frequency-dependent capability, which se
verely hinders their real-world applications that usually require customized dispersion. To address this bottlenecking challenge, we report ultra-broadband achromatic metasurfaces that are capable of delivering arbitrary and frequency-independent wave properties by bottom-up topology optimization. We successively demonstrate three ultra-broadband functionalities, including acoustic beam steering, focusing and levitation, featuring record-breaking relative bandwidths of 93.3%, 120% and 118.9%, respectively. All metasurface elements show novel asymmetric geometries containing multiple scatters, curved air channels and local cavities. Moreover, we reveal that the inversely designed metasurfaces can support integrated internal resonances, bi-anisotropy and multiple scattering, which collectively form the mechanism underpinning the ultra-broadband customized dispersion. Our study opens new horizons for ultra-broadband high-efficiency achromatic functional devices on demand, with promising extension to the optical and elastic achromatic metamaterials.
In chance-constrained OPF models, joint chance constraints (JCCs) offer a stronger guarantee on security compared to single chance constraints (SCCs). Using Booles inequality or its improv
Based on high-throughput density functional theory calculations, we performed screening for stable magnetic MAB compounds and predicted potential strong magnets for permanent magnet and magnetocaloric applications. The thermodynamical, mechanical, an
d dynamical stabilities are systematically evaluated, resulting in 21 unreported compounds on the convex hull, and 434 materials being metastable considering convex hull tolerance to be 100 meV/atom. Analysis based on the Hume-Rothery rules revealed that the valence electron concentration and size factor difference are of significant importance in determining the stability, with good correspondence with the local atomic bonding. We found 71 compounds with the absolute value of magneto-crystalline anisotropy energy above 1.0 MJ/m$^3$ and 23 compounds with a uniaxial anisotropy greater than 0.4 MJ/m$^3$, which are potential gap magnets. Based on the magnetic deformation proxy, 99 compounds were identified as potential materials with interesting magnetocaloric performance.
