arXiv subjects

Xin Zhang

Publications and source records attributed to Xin Zhang.

At least 721 records · Page 40Linked to original sources

arXiv2023

Self-supervised Fetal MRI 3D Reconstruction Based on Radiation Diffusion Generation Model

Although the use of multiple stacks can handle slice-to-volume motion correction and artifact removal problems, there are still several problems: 1) The slice-to-volume method usually uses slices as input, which cannot solve the problem of uniform intensity distribution and complementarity in regions of different fetal MRI stacks; 2) The integrity of 3D space is not considered, which adversely affects the discrimination and generation of globally consistent information in fetal MRI; 3) Fetal MRI with severe motion artifacts in the real-world cannot achieve high-quality super-resolution reconstruction. To address these issues, we propose a novel fetal brain MRI high-quality volume reconstruction method, called the Radiation Diffusion Generation Model (RDGM). It is a self-supervised generation method, which incorporates the idea of Neural Radiation Field (NeRF) based on the coordinate generation and diffusion model based on super-resolution generation. To solve regional intensity heterogeneity in different directions, we use a pre-trained transformer model for slice registration, and then, a new regionally Consistent Implicit Neural Representation (CINR) network sub-module is proposed. CINR can generate the initial volume by combining a coordinate association map of two different coordinate mapping spaces. To enhance volume global consistency and discrimination, we introduce the Volume Diffusion Super-resolution Generation (VDSG) mechanism. The global intensity discriminant generation from volume-to-volume is carried out using the idea of diffusion generation, and CINR becomes the deviation intensity generation network of the volume-to-volume diffusion model. Finally, the experimental results on real-world fetal brain MRI stacks demonstrate the state-of-the-art performance of our method.

eess.IV↗

arXiv2023

Gravitational capture of magnetic monopoles by primordial black holes in the early universe

It is intriguing to ask whether the existence of primordial black holes (PBHs) in the early universe could significantly reduce the abundance of certain stable massive particles (SMP) via gravitational capture, after which the PBHs evaporate before BBN to avoid conflict with stringent bounds. For example, this mechanism is relevant to an alternative solution of the monopole problem proposed by Stojkovic and Freese, in which magnetic monopoles produced in the early universe are captured by PBHs, thus freeing inflation from having to occur during or after the corresponding phase transitions that produced the monopoles. In this work, we reanalyze the solution by modelling the capture process in the same way as the coexisting monopole annihilation. A subtle issue which is not handled properly in the previous literature is the choice of an effective capture cross section for diffusive capture. We model this aspect properly and justify our treatment. A monochromatic PBH mass function and a radiation-dominated era before PBH evaporation are assumed. We find that for Pati-Salam monopoles corresponding to a symmetry breaking scale between $10^{10}\,\text{GeV}$ and $10^{15}\,\text{GeV}$, the capture rate is many orders of magnitude below what is needed to cause a significant reduction of the monopole density. Within our assumptions, we also find that the magnetic charge that is large enough to make an extremal magnetic black hole cosmologically stable cannot be obtained from magnetic charge fluctuation via monopole capture. The large magnetic charged required by cosmological stability can nevertheless be obtained from magnetic charge fluctuation at PBH formation, and if later the monopole abundance can be reduced significantly by some non-inflationary mechanism, long-lived near-extremal magnetic black holes of observational relevance might result.

hep-ph↗

arXiv2023

Real-time Strawberry Detection Based on Improved YOLOv5s Architecture for Robotic Harvesting in open-field environment

This study proposed a YOLOv5-based custom object detection model to detect strawberries in an outdoor environment. The original architecture of the YOLOv5s was modified by replacing the C3 module with the C2f module in the backbone network, which provided a better feature gradient flow. Secondly, the Spatial Pyramid Pooling Fast in the final layer of the backbone network of YOLOv5s was combined with Cross Stage Partial Net to improve the generalization ability over the strawberry dataset in this study. The proposed architecture was named YOLOv5s-Straw. The RGB images dataset of the strawberry canopy with three maturity classes (immature, nearly mature, and mature) was collected in open-field environment and augmented through a series of operations including brightness reduction, brightness increase, and noise adding. To verify the superiority of the proposed method for strawberry detection in open-field environment, four competitive detection models (YOLOv3-tiny, YOLOv5s, YOLOv5s-C2f, and YOLOv8s) were trained, and tested under the same computational environment and compared with YOLOv5s-Straw. The results showed that the highest mean average precision of 80.3% was achieved using the proposed architecture whereas the same was achieved with YOLOv3-tiny, YOLOv5s, YOLOv5s-C2f, and YOLOv8s were 73.4%, 77.8%, 79.8%, 79.3%, respectively. Specifically, the average precision of YOLOv5s-Straw was 82.1% in the immature class, 73.5% in the nearly mature class, and 86.6% in the mature class, which were 2.3% and 3.7%, respectively, higher than that of the latest YOLOv8s. The model included 8.6*10^6 network parameters with an inference speed of 18ms per image while the inference speed of YOLOv8s had a slower inference speed of 21.0ms and heavy parameters of 11.1*10^6, which indicates that the proposed model is fast enough for real time strawberry detection and localization for the robotic picking.

cs.CV↗

arXiv2023

ChatRadio-Valuer: A Chat Large Language Model for Generalizable Radiology Report Generation Based on Multi-institution and Multi-system Data

Radiology report generation, as a key step in medical image analysis, is critical to the quantitative analysis of clinically informed decision-making levels. However, complex and diverse radiology reports with cross-source heterogeneity pose a huge generalizability challenge to the current methods under massive data volume, mainly because the style and normativity of radiology reports are obviously distinctive among institutions, body regions inspected and radiologists. Recently, the advent of large language models (LLM) offers great potential for recognizing signs of health conditions. To resolve the above problem, we collaborate with the Second Xiangya Hospital in China and propose ChatRadio-Valuer based on the LLM, a tailored model for automatic radiology report generation that learns generalizable representations and provides a basis pattern for model adaptation in sophisticated analysts' cases. Specifically, ChatRadio-Valuer is trained based on the radiology reports from a single institution by means of supervised fine-tuning, and then adapted to disease diagnosis tasks for human multi-system evaluation (i.e., chest, abdomen, muscle-skeleton, head, and maxillofacial $\&$ neck) from six different institutions in clinical-level events. The clinical dataset utilized in this study encompasses a remarkable total of \textbf{332,673} observations. From the comprehensive results on engineering indicators, clinical efficacy and deployment cost metrics, it can be shown that ChatRadio-Valuer consistently outperforms state-of-the-art models, especially ChatGPT (GPT-3.5-Turbo) and GPT-4 et al., in terms of the diseases diagnosis from radiology reports. ChatRadio-Valuer provides an effective avenue to boost model generalization performance and alleviate the annotation workload of experts to enable the promotion of clinical AI applications in radiology reports.

cs.CL↗

arXiv2023

ChiMera: Learning with noisy labels by contrasting mixed-up augmentations

Learning with noisy labels has been studied to address incorrect label annotations in real-world applications. In this paper, we present ChiMera, a two-stage learning-from-noisy-labels framework based on semi-supervised learning, developed based on a novel contrastive learning technique MixCLR. The key idea of MixCLR is to learn and refine the representations of mixed augmentations from two different images to better resist label noise. ChiMera jointly learns the representations of the original data distribution and mixed-up data distribution via MixCLR, introducing many additional augmented samples to fill in the gap between different classes. This results in a more smoothed representation space learned by contrastive learning with better alignment and a more robust decision boundary. By exploiting MixCLR, ChiMera also improves the label diffusion process in the semi-supervised noise recovery stage and further boosts its ability to diffuse correct label information. We evaluated ChiMera on seven real-world datasets and obtained state-of-the-art performance on both symmetric noise and asymmetric noise. Our method opens up new avenues for using contrastive learning on learning with noisy labels and we envision MixCLR to be broadly applicable to other applications.

cs.CE↗

arXiv2023

Conformal Metamaterials with Active Tunability and Self-adaptivity for Magnetic Resonance Imaging

Ongoing effort has been devoted to applying metamaterials to boost the imaging performance of magnetic resonance imaging owing to their unique capacity for electromagnetic field confinement and enhancement. However, there are still major obstacles to widespread clinical adoption of conventional metamaterials due to several notable restrictions, namely: their typically bulky and rigid structures, deviations in their optimal resonance frequency, and their inevitable interference with the transmission RF field in MRI. Herein, we address these restrictions and report a conformal, smart metamaterial, which may not only be readily tuned to achieve the desired, precise frequency match with MRI by a controlling circuit, but is also capable of selectively amplifying the magnetic field during the RF reception phase by sensing the excitation signal strength passively, thereby remaining off during the RF transmission phase and thereby ensuring its optimal performance when applied to MRI as an additive technology. By addressing a host of current technological challenges, the metamaterial presented herein paves the way toward the wide-ranging utilization of metamaterials in clinical MRI, thereby translating this promising technology to the MRI bedside.

physics.med-ph↗

arXiv2023

Magnetic monopole meets primordial black hole: an extended analysis

We investigate gravitational capture of magnetic monopoles by primordial black holes (PBH) that evaporate before Big Bang Nucleosynthesis (BBN), a hypothetical process which was once proposed as an alternative solution to the monopole problem. Magnetic monopoles produced in phase transitions of a grand or partially unified gauge theory are considered. We prove analytically that for all extended PBH mass functions that preserve radiation domination, it is impossible to reduce the monopole abundance via gravitational capture by PBHs to values significantly below the one set by monopole annihilation (or below its initial abundance if it is smaller), regardless of the nature of the capture process (diffusive or non-diffusive). Therefore, the monopole problem cannot be solved by PBH capture in a radiation-dominated era in the early universe.

hep-ph↗

arXiv2023

IDECAMB: an implementation of interacting dark energy cosmology in CAMB

Interacting dark energy (IDE) scenario is a natural and important extension to the standard $Λ$CDM cosmology. We develop a full numerical routine, called IDECAMB, as a patch to the public Einstein-Boltzmann solver CAMB, to solve the background and perturbation equations of the IDE models. The IDECAMB solver provides a unified interface for the widely studied IDE models by employing a parametrization model with five free functions. By configuring these five functions, one can easily map the coupled quintessence (CQ) and coupled fluid (CF) models into the parametrization. We handle the perturbation evolutions of the CF models with the parametrized post-Friedmann (PPF) approach to avoid the possible large-scale instability. Compared with the previous established PPF approach whose form depends on a specific IDE model, the PPF approach in this work are model-independent, making it easy to use. We constrain a specific CQ model with the IDECAMB package. The fitting results are consistent with those obtained by Planck Collaboration, which confirms the validity of the package.

astro-ph.CO↗

arXiv2023

Holographic superfluid with gauge-axion coupling

We have constructed a holographic superfluid with gauge-axion coupling. Depending on whether the coupling is positive or negative, the system displays metallic or insulating behavior in its normal state. A significant feature of the system is the appearance of a mid-IR peak in the alternating current (AC) conductivity in a certain range of parameters. This peak arises due to competition between explicit symmetry breaking (ESB) and spontaneous symmetry breaking (SSB), which results in the presence of a pseudo-Goldstone mode. Moreover, a dip in low-frequency AC conductivity is observed, stemming from the excitation of the SSB Goldstone mode. In the superfluid phase, the effect of gauge-axion coupling on the condensation or superfluid energy gap is only amplified in the presence of strong momentum dissipation. Notably, for the case with negative gauge-axion coupling, a hard-gap-like behavior at low frequency and a pronounced peak at intermediate frequency are observed, indicating that the evolution of the superfluid component is distinct from that of positive coupling.

hep-th↗

arXiv2023

Cosmology with fast radio bursts in the era of SKA

We present a forecast of the cosmological parameter estimation using fast radio bursts (FRBs) from the upcoming Square Kilometre Array (SKA), focusing on the issues of dark energy, the Hubble constant, and baryon density. We simulate $10^5$ and $10^6$ localized FRBs from a 10-year SKA observation, and find that: (i) using $10^6$ FRB data alone can tightly constrain dark-energy equation of state parameters better than CMB+BAO+SNe, providing an independent cosmological probe to explore dark energy; (ii) combining the FRB data with gravitational-wave standard siren data from 10-year observation with the Einstein Telescope, the Hubble constant can be constrained to a sub-percent level, serving as a powerful low-redshift probe; (iii) using $10^6$ FRB data can constrain the baryon density $Ω_{\rm b}h$ to a precision of $\sim 0.1\%$. Our results indicate that SKA-era FRBs will provide precise cosmological measurements to shed light on both dark energy and the missing baryon problem, and help resolve the Hubble tension.

astro-ph.CO↗

arXiv2023

Eliminating polarization leakage effect for neutral hydrogen intensity mapping with deep learning

The neutral hydrogen (HI) intensity mapping (IM) survey is regarded as a promising approach for cosmic large-scale structure (LSS) studies. A major issue for the HI IM survey is to remove the bright foreground contamination. A key to successfully remove the bright foreground is to well control or eliminate the instrumental effects. In this work, we consider the instrumental effect of polarization leakage and use the U-Net approach, a deep learning-based foreground removal technique, to eliminate the polarization leakage effect. The thermal noise is assumed to be a subdominant factor compared with the polarization leakage for future HI IM surveys and ignored in this analysis. In this method, the principal component analysis (PCA) foreground subtraction is used as a preprocessing step for the U-Net foreground subtraction. Our results show that the additional U-Net processing could either remove the foreground residual after the conservative PCA subtraction or compensate for the signal loss caused by the aggressive PCA preprocessing. Finally, we test the robustness of the U-Net foreground subtraction technique and show that it is still reliable in the case of existing constraint error on HI fluctuation amplitude.

astro-ph.IM↗

arXiv2023

Model-independent measurement of cosmic curvature with the latest $H(z)$ and SNe Ia data: A comprehensive investigation

In the context of the discrepancies between the early and late universe, we emphasize the importance of independent measurements of the cosmic curvature in the late universe. We present an investigation of the model-independent measurement of the cosmic curvature parameter $Ω_k$ in the late universe with the latest Hubble parameter $H(z)$ measurements and type Ia supernovae (SNe Ia) data. For that, we use two reconstruction methods, the Gaussian process (GP) and artificial neural network (ANN) methods, to achieve the distance construction from $H(z)$ data. Our analysis reveals that the GP method provides the most precise constraint on $Ω_k$, with a constraint precision of $ξ(Ω_k)=0.13$, surpassing recent estimations using similar methods. The GP method consistently indicates a preference for a flat universe at the 2$σ$ confidence level. Moreover, we find that the choice of reconstruction method influences the estimation of $Ω_k$. The ANN reconstruction method exhibits higher sensitivity to the addition of BAO $H(z)$ data, resulting in comparable constraint precision to the GP method. A discrepancy exists between the best-fit values obtained by these two reconstruction methods, indicating their dependence on the reconstruction approach. However, we anticipate that with the improvement of sample size and precision of observational $H(z)$ data, the estimation of $Ω_k$ using this approach will become more robust and reliable.

astro-ph.CO↗

arXiv2023

Prospects for measuring the Hubble constant and dark energy using gravitational-wave dark sirens with neutron star tidal deformation

Using the measurements of tidal deformation in the binary neutron star (BNS) coalescences can obtain the information of redshifts of gravitational wave (GW) sources, and thus actually the cosmic expansion history can be investigated using solely such GW dark sirens. To do this, the key is to get a large number of accurate GW data, which can be achieved with the third-generation (3G) GW detectors. Here we wish to offer an answer to the question of whether the Hubble constant and the equation of state (EoS) of dark energy can be precisely measured using solely GW dark sirens. We find that in the era of 3G GW detectors ${\cal O}(10^5-10^6)$ dark siren data (with the NS tidal measurements) could be obtained in three-year observation if the EoS of NS is perfectly known, and thus using only dark sirens can actually achieve the precision cosmology. Based on a network of 3G detectors, we obtain the constraint precisions of $0.15\%$ and $0.95\%$ for the Hubble constant $H_0$ and the constant EoS of dark energy $w$, respectively; for a two-parameter EoS parametrization of dark energy, the precision of $w_0$ is $2.04\%$ and the error of $w_a$ is 0.13. We conclude that 3G GW detectors would lead to breakthroughs in solving the Hubble tension and revealing the nature of dark energy provided that the EoS of NS is perfectly known.

gr-qc↗

arXiv2023

Bayesian Variational Time-lapse Full-waveform Inversion

Time-lapse seismic full-waveform inversion (FWI) provides estimates of dynamic changes in the subsurface by performing multiple seismic surveys at different times. Since FWI problems are highly non-linear and non-unique, it is important to quantify uncertainties in such estimates to allow robust decision making. Markov chain Monte Carlo (McMC) methods have been used for this purpose, but due to their high computational cost, those studies often require an accurate baseline model and estimates of the locations of potential velocity changes, and neglect uncertainty in the baseline velocity model. Such detailed and accurate prior information is not always available in practice. In this study we use an efficient optimization method called stochastic Stein variational gradient descent (sSVGD) to solve time-lapse FWI problems without assuming such prior knowledge, and to estimate uncertainty both in the baseline velocity model and the velocity change. We test two Bayesian strategies: separate Bayesian inversions for each seismic survey, and a single join inversion for baseline and repeat surveys, and compare the methods with the standard linearised double difference inversion. The results demonstrate that all three methods can produce accurate velocity change estimates in the case of having fixed (exactly repeatable) acquisition geometries, but that the two Bayesian methods generate more accurate results when the acquisition geometry changes between surveys. Furthermore the joint inversion provides the most accurate velocity change and uncertainty estimates in all cases. We therefore conclude that Bayesian time-lapse inversion, especially adopting a joint inversion strategy, may be useful to image and monitor the subsurface changes, in particular where uncertainty in the results might lead to significantly different decisions.

physics.geo-ph↗

arXiv2023

Direct and in situ examination of Li+ transport kinetics in isotope labelled solid electrolyte interphase

Here, using unique in-situ liquid secondary ion mass spectroscopy on isotope-labelled solid-electrolyte-interphase (SEI), assisted by cryogenic transmission electron microscopy and constrained ab initio molecular dynamics simulation, for the first time we answer the question regarding Li+ transport mechanism across SEI, and quantitatively determine the Li+-mobility therein. We unequivocally unveil that Li+ transport in SEI follows a mechanism of successive displacement, rather than "direct-hopping". We further reveal, in accordance with spatial-dependence of SEI structure across the thickness, the apparent Li+ self-diffusivity varies from 6.7*10-19 m2/s to 1.0*10-20 m2/s, setting a quantitative gauging of ionic transport behavior of SEI layer against the underlining electrode as well as the rate limiting step of battery operation. This direct study on Li+ kinetics in SEI fills part of the decade-long knowledge gap about the most important component in advanced batteries and provides more precise guidelines to the tailoring of interphasial chemistries for future battery chemistries.

cond-mat.mtrl-sci↗

arXiv2023

Swin-transformer-yolov5 For Real-time Wine Grape Bunch Detection

In this research, an integrated detection model, Swin-transformer-YOLOv5 or Swin-T-YOLOv5, was proposed for real-time wine grape bunch detection to inherit the advantages from both YOLOv5 and Swin-transformer. The research was conducted on two different grape varieties of Chardonnay (always white berry skin) and Merlot (white or white-red mix berry skin when immature; red when matured) from July to September in 2019. To verify the superiority of Swin-T-YOLOv5, its performance was compared against several commonly used/competitive object detectors, including Faster R-CNN, YOLOv3, YOLOv4, and YOLOv5. All models were assessed under different test conditions, including two different weather conditions (sunny and cloudy), two different berry maturity stages (immature and mature), and three different sunlight directions/intensities (morning, noon, and afternoon) for a comprehensive comparison. Additionally, the predicted number of grape bunches by Swin-T-YOLOv5 was further compared with ground truth values, including both in-field manual counting and manual labeling during the annotation process. Results showed that the proposed Swin-T-YOLOv5 outperformed all other studied models for grape bunch detection, with up to 97% of mean Average Precision (mAP) and 0.89 of F1-score when the weather was cloudy. This mAP was approximately 44%, 18%, 14%, and 4% greater than Faster R-CNN, YOLOv3, YOLOv4, and YOLOv5, respectively. Swin-T-YOLOv5 achieved its lowest mAP (90%) and F1-score (0.82) when detecting immature berries, where the mAP was approximately 40%, 5%, 3%, and 1% greater than the same. Furthermore, Swin-T-YOLOv5 performed better on Chardonnay variety with achieved up to 0.91 of R2 and 2.36 root mean square error (RMSE) when comparing the predictions with ground truth. However, it underperformed on Merlot variety with achieved only up to 0.70 of R2 and 3.30 of RMSE.

cs.CV↗

arXiv2023

Towards General Text Embeddings with Multi-stage Contrastive Learning

We present GTE, a general-purpose text embedding model trained with multi-stage contrastive learning. In line with recent advancements in unifying various NLP tasks into a single format, we train a unified text embedding model by employing contrastive learning over a diverse mixture of datasets from multiple sources. By significantly increasing the number of training data during both unsupervised pre-training and supervised fine-tuning stages, we achieve substantial performance gains over existing embedding models. Notably, even with a relatively modest parameter count of 110M, GTE$_\text{base}$ outperforms the black-box embedding API provided by OpenAI and even surpasses 10x larger text embedding models on the massive text embedding benchmark. Furthermore, without additional fine-tuning on each programming language individually, our model outperforms previous best code retrievers of similar size by treating code as text. In summary, our model achieves impressive results by effectively harnessing multi-stage contrastive learning, offering a powerful and efficient text embedding model with broad applicability across various NLP and code-related tasks.

cs.CL↗

arXiv2023

Data-Driven Modeling with Experimental Augmentation for the Modulation Strategy of the Dual-Active-Bridge Converter

For the performance modeling of power converters, the mainstream approaches are essentially knowledge-based, suffering from heavy manpower burden and low modeling accuracy. Recent emerging data-driven techniques greatly relieve human reliance by automatic modeling from simulation data. However, model discrepancy may occur due to unmodeled parasitics, deficient thermal and magnetic models, unpredictable ambient conditions, etc. These inaccurate data-driven models based on pure simulation cannot represent the practical performance in physical world, hindering their applications in power converter modeling. To alleviate model discrepancy and improve accuracy in practice, this paper proposes a novel data-driven modeling with experimental augmentation (D2EA), leveraging both simulation data and experimental data. In D2EA, simulation data aims to establish basic functional landscape, and experimental data focuses on matching actual performance in real world. The D2EA approach is instantiated for the efficiency optimization of a hybrid modulation for neutral-point-clamped dual-active-bridge (NPC-DAB) converter. The proposed D2EA approach realizes 99.92% efficiency modeling accuracy, and its feasibility is comprehensively validated in 2-kW hardware experiments, where the peak efficiency of 98.45% is attained. Overall, D2EA is data-light and can achieve highly accurate and highly practical data-driven models in one shot, and it is scalable to other applications, effortlessly.

eess.SY↗