Searcharxiv⌕ Search

arXiv subjects

Wei Huang

Publications and source records attributed to Wei Huang.

At least 271 records · Page 15Linked to original sources
arXiv2024

DaFoEs: Mixing Datasets towards the generalization of vision-state deep-learning Force Estimation in Minimally Invasive Robotic Surgery

Precisely determining the contact force during safe interaction in Minimally Invasive Robotic Surgery (MIRS) is still an open research challenge. Inspired by post-operative qualitative analysis from surgical videos, the use of cross-modality data driven deep neural network models has been one of the newest approaches to predict sensorless force trends. However, these methods required for large and variable datasets which are not currently available. In this paper, we present a new vision-haptic dataset (DaFoEs) with variable soft environments for the training of deep neural models. In order to reduce the bias from a single dataset, we present a pipeline to generalize different vision and state data inputs for mixed dataset training, using a previously validated dataset with different setup. Finally, we present a variable encoder-decoder architecture to predict the forces done by the laparoscopic tool using single input or sequence of inputs. For input sequence, we use a recurrent decoder, named with the prefix R, and a new temporal sampling to represent the acceleration of the tool. During our training, we demonstrate that single dataset training tends to overfit to the training data domain, but has difficulties on translating the results across new domains. However, dataset mixing presents a good translation with a mean relative estimated force error of 5% and 12% for the recurrent and non-recurrent models respectively. Our method, also marginally increase the effectiveness of transformers for force estimation up to a maximum of ~15%, as the volume of available data is increase by 150%. In conclusion, we demonstrate that mixing experimental set ups for vision-state force estimation in MIRS is a possible approach towards the general solution of the problem.

cs.CV↗
arXiv2024

Graph Relation Distillation for Efficient Biomedical Instance Segmentation

Instance-aware embeddings predicted by deep neural networks have revolutionized biomedical instance segmentation, but its resource requirements are substantial. Knowledge distillation offers a solution by transferring distilled knowledge from heavy teacher networks to lightweight yet high-performance student networks. However, existing knowledge distillation methods struggle to extract knowledge for distinguishing instances and overlook global relation information. To address these challenges, we propose a graph relation distillation approach for efficient biomedical instance segmentation, which considers three essential types of knowledge: instance-level features, instance relations, and pixel-level boundaries. We introduce two graph distillation schemes deployed at both the intra-image level and the inter-image level: instance graph distillation (IGD) and affinity graph distillation (AGD). IGD constructs a graph representing instance features and relations, transferring these two types of knowledge by enforcing instance graph consistency. AGD constructs an affinity graph representing pixel relations to capture structured knowledge of instance boundaries, transferring boundary-related knowledge by ensuring pixel affinity consistency. Experimental results on a number of biomedical datasets validate the effectiveness of our approach, enabling student models with less than $ 1\%$ parameters and less than $10\%$ inference time while achieving promising performance compared to teacher models.

cs.CV↗
arXiv2023

A New Explanation of the Mechanism of Hadley Circulation

The Hadley circulation (or Hadley cell) is traditionally described as a large-scale atmospheric circulation phenomenon driven by differential heating of the Earth surface: warm, moist air rises near the equator, diverges poleward in the upper troposphere, and subsides in the subtropics. In this article, the mechanism of the Hadley circulation is revisited and a new model is provided to explain its mechanism. The new model is based on a form of the atmospheric dynamic equation which substitutes pressure with temperature and density; thereby categorizing weather systems into thermal and dynamic systems. Such classification is useful for explaining large-scale weather systems such as the Hadley cell. The proposed explanation for the mechanism of the Hadley circulation argues that subtropical highs are the driving force of the Hadley cell, rather than the conventionally-believed ITCZ (Intertropical Convergence Zone). To support our theory, we analyze the atmospheric air density flux divergence with the results from the Community Earth System Model (CESM) and derive a new continuity equation by adding source/sink terms, in which evaporation serves as the air-mass source, and precipitation (condensation) as the air-mass sink. Results found that the equatorial easterlies could be linked to the solar diurnal cycle, demonstrating that the trade wind can be generated by the solar diurnal cycle, especially in the spring and fall seasons, as well as from the equatorial branch of the subtropical high.

physics.ao-ph↗
arXiv2023

Maximum Likelihood CFO Estimation for High-Mobility OFDM Systems: A Chinese Remainder Theorem Based Method

Orthogonal frequency division multiplexing (OFDM) is a widely adopted wireless communication technique but is sensitive to the carrier frequency offset (CFO). For high-mobility environments, severe Doppler shifts cause the CFO to extend well beyond the subcarrier spacing. Traditional algorithms generally estimate the integer and fractional parts of the CFO separately, which is time-consuming and requires high additional computations. To address these issues, this paper proposes a Chinese remainder theorem-based CFO Maximum Likelihood Estimation (CCMLE) approach for jointly estimating the integer and fractional parts. With CCMLE, the MLE of the CFO can be obtained directly from multiple estimates of sequences with varying lengths. This approach can achieve a wide estimation range up to the total number of subcarriers, without significant additional computations. Furthermore, we show that the CCMLE can approach the Cram$\acute{\text{e}}$r-Rao Bound (CRB), and give an analytic expression for the signal-to-noise ratio (SNR) threshold approaching the CRB, enabling an efficient waveform design. Accordingly, a parameter configuration guideline for the CCMLE is presented to achieve a better MSE performance and a lower SNR threshold. Finally, experiments show that our proposed method is highly consistent with the theoretical analysis and advantageous regarding estimated range and error performance compared to baselines.

eess.SP↗
arXiv2023

Fed-CO2: Cooperation of Online and Offline Models for Severe Data Heterogeneity in Federated Learning

Federated Learning (FL) has emerged as a promising distributed learning paradigm that enables multiple clients to learn a global model collaboratively without sharing their private data. However, the effectiveness of FL is highly dependent on the quality of the data that is being used for training. In particular, data heterogeneity issues, such as label distribution skew and feature skew, can significantly impact the performance of FL. Previous studies in FL have primarily focused on addressing label distribution skew data heterogeneity, while only a few recent works have made initial progress in tackling feature skew issues. Notably, these two forms of data heterogeneity have been studied separately and have not been well explored within a unified FL framework. To address this gap, we propose Fed-CO$_{2}$, a universal FL framework that handles both label distribution skew and feature skew within a \textbf{C}ooperation mechanism between the \textbf{O}nline and \textbf{O}ffline models. Specifically, the online model learns general knowledge that is shared among all clients, while the offline model is trained locally to learn the specialized knowledge of each individual client. To further enhance model cooperation in the presence of feature shifts, we design an intra-client knowledge transfer mechanism that reinforces mutual learning between the online and offline models, and an inter-client knowledge transfer mechanism to increase the models' domain generalization ability. Extensive experiments show that our Fed-CO$_{2}$ outperforms a wide range of existing personalized federated learning algorithms in terms of handling label distribution skew and feature skew, both individually and collectively. The empirical results are supported by our convergence analyses in a simplified setting.

cs.LG↗
arXiv2023

Deep Learning Enabled Design of Terahertz High-Q Metamaterials

Metamaterials open up a new way to manipulate electromagnetic waves and realize various functional devices. Metamaterials with high-quality (Q) resonance responses are widely employed in sensing, detection, and other applications. Traditional design of metamaterials involves laborious simulation-optimization and limits the efficiency. The high-Q metamaterials with abrupt spectral change are even harder to reverse design on-demand. In this paper, we propose novel solutions for designing terahertz high-Q metamaterials based on deep learning, including the forward prediction of spectral responses and the inverse design of structural parameters. For the forward prediction, we develop the Electromagnetic Response Transformer (ERT) model to establish the complex mapping relations between the highly sensitive structural parameters and the abrupt spectra, and realize precise prediction of the high-Q resonance in terahertz spectra from given structural parameters. For the inverse design, we introduce the Visual Attention Network (VAN) model with a large model capability to attentively learn the abrupt shifts in spectral resonances, which can efficiently reduce errors and achieve highly accurate inverse design of structural parameters according to the expected high-Q resonance responses. Both models exhibit outstanding performance, and the accuracy is improved one or two orders higher compared to the traditional machine learning methods. Besides, our ERT model can be 4000 times faster than the conventional full wave simulations in computation time. Our work provides new avenues for the deep learning enabled design of terahertz high-Q metamaterials, which holds potential applications in various fields, such as terahertz communication, sensing, imaging, and functional devices.

physics.optics↗
arXiv2023

Approaching the robust linearity in dual-floating van der Waals photodiode

Two-dimensional (2D) material photodetectors have gained great attention as potential elements for optoelectronic applications. However, the linearity of the photoresponse is often compromised by the carrier interaction, even in 2D photodiodes. In this study, we present a new device concept of dual-floating van der Waals heterostructures (vdWHs) photodiode by employing ambipolar MoTe2 and n-type MoS2 2D semiconductors. The presence of type II heterojunctions on both sides of channel layers effectively deplete carriers and restrict the photocarrier trapping within the channel layers. As a result, the device exhibits robust linear photoresponse under photovoltaic mode from the visible (405 nm) to near-infrared (1600 nm) band. With the built-in electric field of the vdWHs, we achieve a linear dynamic range of ~ 100 dB, responsivity of ~ 1.57 A/W, detectivity of ~ 4.28 * 10^11 Jones, and response speed of ~ 30 μs. Our results showcase a promising device concept with excellent linearity towards fast and low-loss detection, high-resolution imaging, and logic optoelectronics.

cond-mat.mes-hall↗
arXiv2023

A Simple Framework to Enhance the Adversarial Robustness of Deep Learning-based Intrusion Detection System

Deep learning based intrusion detection systems (DL-based IDS) have emerged as one of the best choices for providing security solutions against various network intrusion attacks. However, due to the emergence and development of adversarial deep learning technologies, it becomes challenging for the adoption of DL models into IDS. In this paper, we propose a novel IDS architecture that can enhance the robustness of IDS against adversarial attacks by combining conventional machine learning (ML) models and Deep Learning models. The proposed DLL-IDS consists of three components: DL-based IDS, adversarial example (AE) detector, and ML-based IDS. We first develop a novel AE detector based on the local intrinsic dimensionality (LID). Then, we exploit the low attack transferability between DL models and ML models to find a robust ML model that can assist us in determining the maliciousness of AEs. If the input traffic is detected as an AE, the ML-based IDS will predict the maliciousness of input traffic, otherwise the DL-based IDS will work for the prediction. The fusion mechanism can leverage the high prediction accuracy of DL models and low attack transferability between DL models and ML models to improve the robustness of the whole system. In our experiments, we observe a significant improvement in the prediction performance of the IDS when subjected to adversarial attack, achieving high accuracy with low resource consumption.

cs.CR↗
arXiv2023

An Ultra-fast Quantum Random Number Generation Scheme Based on Laser Phase Noise

Based on the intrinsic random property of quantum mechanics, quantum random number generators allow for access of truly unpredictable random sequence and are now heading towards high performance and small miniaturization, among which a popular scheme is based on the laser phase noise. However, this scheme is generally limited in speed and implementation complexity, especially for chip integration. In this work, a general physical model based on wiener process for such schemes is introduced, which provides an approach to clearly explain the limitation on the generation rate and comprehensively optimize the system performance. We present an insight to exploit the potential bandwidth of the quantum entropy source that contains plentiful quantum randomness with a simple spectral filtering method and experimentally boost the bandwidth of the corresponding quantum entropy source to 20 GHz, based on which an ultra-fast generation rate of 218 Gbps is demonstrated, setting a new record for laser phase noise based schemes by one order of magnitude. Our proposal significantly enhances the ceiling speed of such schemes without requiring extra complex hardware, thus effectively benefits the corresponding chip integration with high performance and low implementation cost, which paves the way for its large-scale applications.

quant-ph↗
arXiv2023

$p$-multilevel Monte Carlo for acoustic scattering from large deviation rough random surfaces

We study time harmonic acoustic scattering on large deviation rough random scatterers. Therein, the roughness of the scatterers is caused by a low Sobolev regularity in the covariance function of their deformation field. The motivation for this study arises from physical phenomena where small-scale material defects can potentially introduce non-smooth deviations from a reference domain. The primary challenge in this scenario is that the scattered wave is also random, which makes computational predictions unreliable. Therefore, it is essential to quantify these uncertainties to ensure robust and well-informed design processes. While existing methods for uncertainty quantification typically rely on domain mapping or perturbation approaches, it turns out that large and rough random deviations are not satisfactory covered. To close this gap, and although counter intuitive at first, we show that the $p$-multilevel Monte Carlo method can provide an efficient tool for uncertainty quantification in this setting. To this end, we discuss the stable implementation of higher-order polynomial approximation of the deformation field by means of barycentric interpolation and provide a cost-to-accuracy analysis. Our considerations are complemented by numerical experiments in three dimensions on a complex scattering geometry.

math.NA↗
arXiv2023

Single-Pass Contrastive Learning Can Work for Both Homophilic and Heterophilic Graph

Existing graph contrastive learning (GCL) techniques typically require two forward passes for a single instance to construct the contrastive loss, which is effective for capturing the low-frequency signals of node features. Such a dual-pass design has shown empirical success on homophilic graphs, but its effectiveness on heterophilic graphs, where directly connected nodes typically have different labels, is unknown. In addition, existing GCL approaches fail to provide strong performance guarantees. Coupled with the unpredictability of GCL approaches on heterophilic graphs, their applicability in real-world contexts is limited. Then, a natural question arises: Can we design a GCL method that works for both homophilic and heterophilic graphs with a performance guarantee? To answer this question, we theoretically study the concentration property of features obtained by neighborhood aggregation on homophilic and heterophilic graphs, introduce the single-pass augmentation-free graph contrastive learning loss based on the property, and provide performance guarantees for the minimizer of the loss on downstream tasks. As a direct consequence of our analysis, we implement the Single-Pass Graph Contrastive Learning method (SP-GCL). Empirically, on 14 benchmark datasets with varying degrees of homophily, the features learned by the SP-GCL can match or outperform existing strong baselines with significantly less computational overhead, which demonstrates the usefulness of our findings in real-world cases.

cs.LG↗
arXiv2023

Interpretable Modeling of Single-cell perturbation Responses to Novel Drugs Using Cycle Consistence Learning

Phenotype-based screening has attracted much attention for identifying cell-active compounds. Transcriptional and proteomic profiles of cell population or single cells are informative phenotypic measures of cellular responses to perturbations. In this paper, we proposed a deep learning framework based on encoder-decoder architecture that maps the initial cellular states to a latent space, in which we assume the effects of drug perturbation on cellular states follow linear additivity. Next, we introduced the cycle consistency constraints to enforce that initial cellular state subjected to drug perturbations would produce the perturbed cellular responses, and, conversely, removal of drug perturbation from the perturbed cellular states would restore the initial cellular states. The cycle consistency constraints and linear modeling in latent space enable to learn interpretable and transferable drug perturbation representations, so that our model can predict cellular response to unseen drugs. We validated our model on three different types of datasets, including bulk transcriptional responses, bulk proteomic responses, and single-cell transcriptional responses to drug perturbations. The experimental results show that our model achieves better performance than existing state-of-the-art methods.

q-bio.QM↗
arXiv2023

Future Full-Ocean Deep SSPs Prediction based on Hierarchical Long Short-Term Memory Neural Networks

The spatial-temporal distribution of underwater sound velocity affects the propagation mode of underwater acoustic signals. Therefore, rapid estimation and prediction of underwater sound velocity distribution is crucial for providing underwater positioning, navigation and timing (PNT) services. Currently, sound speed profile (SSP) inversion methods have a faster time response rate compared to direct measurement methods, however, most SSP inversion methods focus on constructing spatial dimensional sound velocity fields and are highly dependent on sonar observation data, thus high requirements have been placed on observation data sources. To explore the distribution pattern of sound velocity in the time dimension and achieve future SSP prediction without sonar observation data, we propose a hierarchical long short-term memory (H-LSTM) neural network for SSP prediction. By our SSP prediction method, the sound speed distribution could be estimated without any on-site data measurement process, so that the time efficiency could be greatly improved. Through comparing with other state-of-the-art methods, H-LSTM has better accuracy performance on prediction of monthly average sound velocity distribution, which is less than 1 m/s in different depth layers.

cs.SD↗
arXiv2023

Approaching the standard quantum limit of a Rydberg-atom microwave electrometer

The development of a microwave electrometer with inherent uncertainty approaching its ultimate limit carries both fundamental and technological significance. Recently, the Rydberg electrometer has garnered considerable attention due to its exceptional sensitivity, small-size, and broad tunability. This specific quantum sensor utilizes low-entropy laser beams to detect disturbances in atomic internal states, thereby circumventing the intrinsic thermal noise encountered by its classical counterparts. However, due to the thermal motion of atoms, the advanced Rydberg-atom microwave electrometer falls considerably short of the standard quantum limit by over three orders of magnitude. In this study, we utilize an optically thin medium with approximately 5.2e5 laser-cooled atoms to implement heterodyne detection. By mitigating a variety of noises and strategically optimizing the parameters of the Rydberg electrometer, our study achieves an electric-field sensitivity of 10.0 nV/cm/Hz^1/2 at a 100 Hz repetition rate, reaching a factor of 2.6 above the standard quantum limit and a minimum detectable field of 540 pV/cm. We also provide an in-depth analysis of noise mechanisms and determine optimal parameters to bolster the performance of Rydberg-atom sensors. Our work provides insights into the inherent capacities and limitations of Rydberg electrometers, while offering superior sensitivity for detecting weak microwave signals in numerous applications.

quant-ph↗
arXiv2023

Understanding and Improving Feature Learning for Out-of-Distribution Generalization

A common explanation for the failure of out-of-distribution (OOD) generalization is that the model trained with empirical risk minimization (ERM) learns spurious features instead of invariant features. However, several recent studies challenged this explanation and found that deep networks may have already learned sufficiently good features for OOD generalization. Despite the contradictions at first glance, we theoretically show that ERM essentially learns both spurious and invariant features, while ERM tends to learn spurious features faster if the spurious correlation is stronger. Moreover, when fed the ERM learned features to the OOD objectives, the invariant feature learning quality significantly affects the final OOD performance, as OOD objectives rarely learn new features. Therefore, ERM feature learning can be a bottleneck to OOD generalization. To alleviate the reliance, we propose Feature Augmented Training (FeAT), to enforce the model to learn richer features ready for OOD generalization. FeAT iteratively augments the model to learn new features while retaining the already learned features. In each round, the retention and augmentation operations are performed on different subsets of the training data that capture distinct features. Extensive experiments show that FeAT effectively learns richer features thus boosting the performance of various OOD objectives.

cs.LG↗
arXiv2023

Effects of impurity band on multiphoton photocurrent from InGaN and GaN photodetectors

Multiphoton absorption of wide band-gap semiconductors has shown great prospects in many fundamental researches and practical applications. With intensity-modulated femtosecond lasers by acousto-optic frequency shifters, photocurrents and yellow luminescence induced by two-photon absorption of InGaN and GaN photodetectors are investigated experimentally. Photocurrent from InGaN detector shows nearly perfect quadratic dependence on excitation intensity, while that in GaN detector shows cubic and higher order dependence. Yellow luminescence from both detectors show sub-quadratic dependence on excitation intensity. Highly nonlinear photocurrent from GaN is ascribed to absorption of additional photons by long-lived electrons in traps and impurity bands. Our investigation indicates that InGaN can serve as a superior detector for multiphoton absorption, absent of linear and higher order process, while GaN, which suffers from absorption by trapped electrons and impurity bands, must be used with caution.

physics.optics↗
arXiv2023

Robust Outlier Detection Method Based on Local Entropy and Global Density

By now, most outlier-detection algorithms struggle to accurately detect both point anomalies and cluster anomalies simultaneously. Furthermore, a few K-nearest-neighbor-based anomaly-detection methods exhibit excellent performance on many datasets, but their sensitivity to the value of K is a critical issue that needs to be addressed. To address these challenges, we propose a novel robust anomaly detection method, called Entropy Density Ratio Outlier Detection (EDROD). This method incorporates the probability density of each sample as the global feature, and the local entropy around each sample as the local feature, to obtain a comprehensive indicator of abnormality for each sample, which is called Entropy Density Ratio (EDR) for short in this paper. By comparing several competing anomaly detection methods on both synthetic and real-world datasets, it is found that the EDROD method can detect both point anomalies and cluster anomalies simultaneously with accurate performance. In addition, it is also found that the EDROD method exhibits strong robustness to the number of selected neighboring samples, the dimension of samples in the dataset, and the size of the dataset. Therefore, the proposed EDROD method can be applied to a variety of real-world datasets to detect anomalies with accurate and robust performances.

cs.IT↗
arXiv2023

Experimental Results of Underwater Sound Speed Profile Inversion by Few-shot Multi-task Learning

Underwater Sound Speed Profile (SSP) distribution has great influence on the propagation mode of acoustic signal, thus the fast and accurate estimation of SSP is of great importance in building underwater observation systems. The state-of-the-art SSP inversion methods include frameworks of matched field processing (MFP), compressive sensing (CS), and feedforeward neural networks (FNN), among which the FNN shows better real-time performance while maintain the same level of accuracy. However, the training of FNN needs quite a lot historical SSP samples, which is diffcult to be satisfied in many ocean areas. This situation is called few-shot learning. To tackle this issue, we propose a multi-task learning (MTL) model with partial parameter sharing among different traning tasks. By MTL, common features could be extracted, thus accelerating the learning process on given tasks, and reducing the demand for reference samples, so as to enhance the generalization ability in few-shot learning. To verify the feasibility and effectiveness of MTL, a deep-ocean experiment was held in April 2023 at the South China Sea. Results shows that MTL outperforms the state-of-the-art methods in terms of accuracy for SSP inversion, while inherits the real-time advantage of FNN during the inversion stage.

eess.AS↗