arXiv subjects

Hao Gong

Publications and source records attributed to Hao Gong.

At least 19 recordsLinked to original sources

arXiv2026

Understanding Search and Decision Errors in Liver Metastasis Detection and the Effects of Lower Radiation Dose

The detection performance of liver metastases decreases with the reduction of radiation dose, but misses are heterogeneous. Previous eye tracking work has characterized missed metastases into two categories: search errors i.e., the eyes never land on the lesion, and decision errors i.e., the lesion is seen but not recognized as malignant. We integrated three prior reader studies to answer this question. In all studies, radiologists interpreted the same set of 40 contrast enhanced abdominal CT exams containing 91 liver metastases whose locations had been previously marked. In two studies, the workstation recorded their gaze and eye movements. Using eye dwell times, metastases were classified as search-error-dominant (majority of misses had <2 sec gaze time) or decision-error-dominant (>2 sec gaze time). In the third study, exams were interpreted both at 120 and 200 quality reference mAs (QRM) by ten radiologists. The third study did not include eye tracking. Out of 91 liver metastases, we excluded 16 that were never missed in the eye tracking studies and used 75 liver metastases for the present study.

physics.med-ph↗

arXiv2026

Clinically Structured Rank-Gated LoRA for Cross-Benchmark Medical Question Answering

Medical multiple-choice question answering requires parameter-efficient adaptation across heterogeneous knowledge domains and reasoning operations. A medication question, a diagnostic decision, a public-health item, and a nursing-action item may require different low-rank updates, while some recall items should preserve the base model's representation with only mild adapter intervention. We propose BiRG-LoRA, a single-adapter rank-gated LoRA method for medical question answering. BiRG-LoRA keeps one LoRA module per target layer but makes its rank dimension input-conditioned: for each question, a biaxial gate combines hidden semantic evidence with specialty/profession priors, clinical-operation priors, and their interaction to select a sparse top-$k$ subset of rank atoms. A scalar injection coefficient further controls the strength of the selected adapter update. Under a matched Qwen3-8B CMB-source protocol, BiRG-LoRA achieves the highest four-benchmark macro-average accuracy among trainable PEFT baselines and matched routing controls: 69.31% averaged over CMB, CMExam, MedQA, and MedMCQA. It improves over MoELoRA by 0.89 percentage points while using 28.1% fewer trainable parameters; a paired, benchmark-stratified bootstrap over final predictions gives a 95% confidence interval of [0.42, 1.37] for this macro-average gain. Basic controls show that BiRG-LoRA also improves over vanilla LoRA r16 and active-rank-matched LoRA r4 by 0.83 macro points, and an evaluation-time weak-axis perturbation check suggests that performance is not brittle to moderate tag noise. The results support a bounded claim: clinically structured rank allocation improves cross-benchmark medical QA under a matched single-seed protocol, while training-seed variance remains future work.

cs.CL↗

arXiv2025

Cation accumulation drives the preferential partitioning of DNA in an aqueous two-phase system

Mixtures of polyethylene glycol (PEG) and dextran (Dex) represent a widely used class of aqueous two-phase systems (ATPS), with applications ranging from the purification of various biomolecules such as nucleic acids to the synthesis of protocells. A key feature underlying these applications is the selective accumulation of biomolecules within Dex-rich droplets in an aqueous PEG phase, but the physical origin of this partitioning remains unclear. Entropic interactions were long assumed to be the primary driving force; however, our systematic experiments using DNA of different lengths indicate that entropy alone cannot fully explain the observed behavior. We identify an additional and previously underappreciated contribution from electrostatic interactions: Dex carries a slightly more negative charge than PEG, which drives preferential cation accumulation in the Dex-rich phase. These counterions facilitate the selective partitioning of DNA inside the Dex-rich droplets. This mechanism explains the dependency of DNA uptake in Dex-rich droplets on polymer length and salt concentration. Our findings establish that Donnan-type ion partitioning plays a crucial role in the localization of long nucleic acids in Dex-rich droplets, offering a unified explanation for this long-standing phenomenon. They lay the foundation for designing ATPS-based systems and help elucidate the physicochemical principles of biomolecular partition upon phase separation in cells.

cond-mat.soft↗

arXiv2025

A Deep Learning Approach to Anomaly Detection in High-Frequency Trading Data

This paper proposes an algorithm based on a staged sliding window Transformer architecture to detect abnormal behaviors in the microstructure of the foreign exchange market, focusing on high-frequency EUR/USD trading data. The method captures multi-scale temporal features through a staged sliding window, extracts global and local dependencies by combining the self-attention mechanism and weighted attention mechanism of the Transformer, and uses a classifier to identify abnormal events. Experimental results on a real high-frequency dataset containing order book depth, spread, and trading volume show that the proposed method significantly outperforms traditional machine learning (such as decision trees and random forests) and deep learning methods (such as MLP, CNN, RNN, LSTM) in terms of accuracy (0.93), F1-Score (0.91), and AUC-ROC (0.95). Ablation experiments verify the contribution of each component, and the visualization of order book depth and anomaly detection further reveals the effectiveness of the model under complex market dynamics. Despite the false positive problem, the model still provides important support for market supervision. In the future, noise processing can be optimized and extended to other markets to improve generalization and real-time performance.

cs.LG↗

arXiv2025

Robust Uplift Modeling with Large-Scale Contexts for Real-time Marketing

Improving user engagement and platform revenue is crucial for online marketing platforms. Uplift modeling is proposed to solve this problem, which applies different treatments (e.g., discounts, bonus) to satisfy corresponding users. Despite progress in this field, limitations persist. Firstly, most of them focus on scenarios where only user features exist. However, in real-world scenarios, there are rich contexts available in the online platform (e.g., short videos, news), and the uplift model needs to infer an incentive for each user on the specific item, which is called real-time marketing. Thus, only considering the user features will lead to biased prediction of the responses, which may cause the cumulative error for uplift prediction. Moreover, due to the large-scale contexts, directly concatenating the context features with the user features will cause a severe distribution shift in the treatment and control groups. Secondly, capturing the interaction relationship between the user features and context features can better predict the user response. To solve the above limitations, we propose a novel model-agnostic Robust Uplift Modeling with Large-Scale Contexts (UMLC) framework for Real-time Marketing. Our UMLC includes two customized modules. 1) A response-guided context grouping module for extracting context features information and condensing value space through clusters. 2) A feature interaction module for obtaining better uplift prediction. Specifically, this module contains two parts: a user-context interaction component for better modeling the response; a treatment-feature interaction component for discovering the treatment assignment sensitive feature of each instance to better predict the uplift. Moreover, we conduct extensive experiments on a synthetic dataset and a real-world product dataset to verify the effectiveness and compatibility of our UMLC.

cs.IR↗

arXiv2024

Research on Dynamic Data Flow Anomaly Detection based on Machine Learning

The sophistication and diversity of contemporary cyberattacks have rendered the use of proxies, gateways, firewalls, and encrypted tunnels as a standalone defensive strategy inadequate. Consequently, the proactive identification of data anomalies has emerged as a prominent area of research within the field of data security. The majority of extant studies concentrate on sample equilibrium data, with the consequence that the detection effect is not optimal in the context of unbalanced data. In this study, the unsupervised learning method is employed to identify anomalies in dynamic data flows. Initially, multi-dimensional features are extracted from real-time data, and a clustering algorithm is utilised to analyse the patterns of the data. This enables the potential outliers to be automatically identified. By clustering similar data, the model is able to detect data behaviour that deviates significantly from normal traffic without the need for labelled data. The results of the experiments demonstrate that the proposed method exhibits high accuracy in the detection of anomalies across a range of scenarios. Notably, it demonstrates robust and adaptable performance, particularly in the context of unbalanced data.

cs.LG↗

arXiv2024

A Lightweight GAN-Based Image Fusion Algorithm for Visible and Infrared Images

This paper presents a lightweight image fusion algorithm specifically designed for merging visible light and infrared images, with an emphasis on balancing performance and efficiency. The proposed method enhances the generator in a Generative Adversarial Network (GAN) by integrating the Convolutional Block Attention Module (CBAM) to improve feature focus and utilizing Depthwise Separable Convolution (DSConv) for more efficient computations. These innovations significantly reduce the model's computational cost, including the number of parameters and inference latency, while maintaining or even enhancing the quality of the fused images. Comparative experiments using the M3FD dataset demonstrate that the proposed algorithm not only outperforms similar image fusion methods in terms of fusion quality but also offers a more resource-efficient solution suitable for deployment on embedded devices. The effectiveness of the lightweight design is validated through extensive ablation studies, confirming its potential for real-time applications in complex environments.

eess.IV↗

arXiv2024

SKA sensitivity for possible radio emission from dark matter in Omega Centauri

Omega Centauri, the largest known globular cluster in the Milky Way, is believed to be the remains of a dwarf galaxy's core. Giving its potential abundance of dark matter (DM), it is an attractive target for investigating the nature of this elusive substance in our local environment. Our study demonstrates that by observing Omega Centauri with the SKA for 1000 hours, we can detect synchrotron radio or Inverse Compton (IC) emissions from the DM annihilation products. It enables us to constrain the cross-section of DM annihilation down to $\sim {\rm 10^{-30}~cm^3~s^{-1}}$ for DM mass from several $\rm{GeV}$ to $\rm{100~GeV}$, which is much stronger compared with other observations. Additionally, we explore the axion, another well-motivated DM candidate, and provide stimulated decay calculations. It turns out that the sensitivity can reach $g_{\rm{aγγ}} \sim 10^{-10} ~\rm{GeV^{-1}}$ for $2\times 10^{-7} ~\rm{eV} < m_a < 2\times 10^{-4} ~\rm{eV}$.

astro-ph.HE↗

arXiv2024

Comparison of Methods in Skin Pigment Decomposition

Decomposition of skin pigment plays an important role in medical fields. Human skin can be decomposed into two primitive components, hemoglobin and melanin. It is our goal to apply these results for diagnosis of skin cancer. In this paper, various methods for skin pigment decomposition are reviewed comparatively and the performance of each method is evaluated both theoretically and experimentally. In addition, isometric feature mapping (Isomap) is introduced in order to improve the dimensionality reduction performance in context of skin pigment decomposition.

cs.CV↗

arXiv2022

Kinetically stabilized inflation

In this work, we propose a string-inspired two fields inflation model to address the fine-tuning problem that the standard inflation model suffers. The fast-rolling tachyon $\mathcal{T}$ originated from the D-brane and anti-D-brane pair annihilation locks the inflaton $φ$ slowly rolling on a Higgs-like potential $V(φ)=-m_φ^2φ^2+λφ^4$ and drives a kinetically stabilized (KS) inflation. Our numerical simulation confirms such a solution is a dynamic attractor. In particular, for $λ< 0.8\times 10^{-3}$, the e-folding number contributed by the KS inflation phase can be larger than $62$ to solve the horizon and flatness problems of Big Bang theory. Notably, this KS inflation generates a nearly scale-invariant primordial curvature perturbations spectrum consistent with current cosmic microwave background (CMB) observations. It predicts a low tensor-to-scalar ratio, which the current primordial gravitational wave background (the B-modes in CMB) searches favor.

astro-ph.CO↗

arXiv2022

Modelling Power Consumptions for Multi-rotor UAVs

Unmanned aerial vehicles (UAVs) have various advantages, but their practical applications are influenced by their limited energy. Therefore, it is important to manage their power consumption and also important to establish corresponding power consumption models. However, most of existing works either establish theoretical power consumption models for fixed-wing UAVs and single-rotor UAVs, or provide heuristic power consumption models for multi-rotor UAVs without rigorous mathematical derivations. This paper aims to establish theoretical power consumption models for multi-rotor UAVs. To be specific, the closed-form power consumption models for a multi-rotor UAV in three flight statuses, i.e., forward flight, vertical ascent and vertical descent, are derived by leveraging the relationship between single-rotor UAVs and multi-rotor UAVs in terms of power consumptions. On this basis, a generic flight power consumption model for the UAV in a three-dimensional (3-D) scenario is obtained. Extensive experiments are conducted by using DJI M210 and a mobile app made by DJI Mobile SDK in real scenarios, and confirm the correctness and effectiveness of these models; in addition, simulations are performed to further investigate the effect of the rotor numbers on the power consumption for the UAV. The proposed power consumption models not only reveal how the power consumption of multi-rotor UAVs are affected by various factors, but also pave the way for introducing other novel applications.

cs.RO↗

arXiv2022

UserBERT: Modeling Long- and Short-Term User Preferences via Self-Supervision

E-commerce platforms generate vast amounts of customer behavior data, such as clicks and purchases, from millions of unique users every day. However, effectively using this data for behavior understanding tasks is challenging because there are usually not enough labels to learn from all users in a supervised manner. This paper extends the BERT model to e-commerce user data for pre-training representations in a self-supervised manner. By viewing user actions in sequences as analogous to words in sentences, we extend the existing BERT model to user behavior data. Further, our model adopts a unified structure to simultaneously learn from long-term and short-term user behavior, as well as user attributes. We propose methods for the tokenization of different types of user behavior sequences, the generation of input representation vectors, and a novel pretext task to enable the pre-trained model to learn from its own input, eliminating the need for labeled training data. Extensive experiments demonstrate that the learned representations result in significant improvements when transferred to three different real-world tasks, particularly compared to task-specific modeling and multi-task representation learning

cs.LG↗

arXiv2020

Learning to Profile: User Meta-Profile Network for Few-Shot Learning

Meta-learning approaches have shown great success in vision and language domains. However, few studies discuss the practice of meta-learning for large-scale industrial applications. Although e-commerce companies have spent many efforts on learning representations to provide a better user experience, we argue that such efforts cannot be stopped at this step. In addition to learning a strong profile, the challenging question about how to effectively transfer the learned representation is raised simultaneously. This paper introduces the contributions that we made to address these challenges from three aspects. 1) Meta-learning model: In the context of representation learning with e-commerce user behavior data, we propose a meta-learning framework called the Meta-Profile Network, which extends the ideas of matching network and relation network for knowledge transfer and fast adaptation; 2) Encoding strategy: To keep high fidelity of large-scale long-term sequential behavior data, we propose a time-heatmap encoding strategy that allows the model to encode data effectively; 3) Deep network architecture: A multi-modal model combined with multi-task learning architecture is utilized to address the cross-domain knowledge learning and insufficient label problems. Moreover, we argue that an industrial model should not only have good performance in terms of accuracy, but also have better robustness and uncertainty performance under extreme conditions. We evaluate the performance of our model with extensive control experiments in various extreme scenarios, i.e. out-of-distribution detection, data insufficiency and class imbalance scenarios. The Meta-Profile Network shows significant improvement in the model performance when compared to baseline models.

cs.LG↗

arXiv2019

Learning low-dimensional state embeddings and metastable clusters from time series data

This paper studies how to find compact state embeddings from high-dimensional Markov state trajectories, where the transition kernel has a small intrinsic rank. In the spirit of diffusion map, we propose an efficient method for learning a low-dimensional state embedding and capturing the process's dynamics. This idea also leads to a kernel reshaping method for more accurate nonparametric estimation of the transition function. State embedding can be used to cluster states into metastable sets, thereby identifying the slow dynamics. Sharp statistical error bounds and misclassification rate are proved. Experiment on a simulated dynamical system shows that the state clustering method indeed reveals metastable structures. We also experiment with time series generated by layers of a Deep-Q-Network when playing an Atari game. The embedding method identifies game states to be similar if they share similar future events, even though their raw data are far different.

cs.LG↗

arXiv2014

Gold on WSe2 Single Crystal Film as a Substrate for Surface Enhanced Raman Scattering (SERS) Sensing

Synthesis and characterization of high-quality single-crystal WSe2 films on highly-insulating substrate is presented. We demonstrate for the first time that the presence of gold nanoparticles in the basal plane of a WSe2 film can enhance its Raman scattering intensity. The experimentally observed enhancement ratio in the Raman signal correlates well with the simulated electric field intensity using a three-dimensional electromagnetic software and theoretical calculation. This work provides guidelines for the use of two-dimensional WSe2 films as a SERS substrate.

cond-mat.mes-hall↗

arXiv2013

Low-Contact-Resistance Graphene Devices with Nickel-Etched-Graphene Contacts

The performance of graphene-based transistors is often limited by the large electrical resistance across the metal-graphene contact. We report an approach to achieve ultra-low resistance metal contacts to graphene transistors. Through a process of metal-catalyzed etching in hydrogen, multiple nano-sized pits with zigzag edges are created in the graphene that form strong chemical bonds with deposited nickel metallization for source-drain contacts without the need for further annealing. This facile contact treatment prior to electrode metallization results in contact resistance as low as 100 ohm-um in single-layer graphene field-effect transistors, and 11 ohm-um in bilayer graphene transistors. The treatment is compatible with complementary metal-oxide-semiconductor fabrication processes, and holds great promise to meet the contact performance required for the integration of graphene in future integrated circuits.

cond-mat.mes-hall↗

arXiv2012

Implementation of Sink Particles in the Athena Code

We describe implementation and tests of sink particle algorithms in the Eulerian grid-based code Athena. Introduction of sink particles enables long-term evolution of systems in which localized collapse occurs, and it is impractical (or unnecessary) to resolve the accretion shocks at the centers of collapsing regions. We discuss similarities and differences of our methods compared to other implementations of sink particles. Our criteria for sink creation are motivated by the properties of the Larson-Penston collapse solution. We use standard particle-mesh methods to compute particle and gas gravity together. Accretion of mass and momenta onto sinks is computed using fluxes returned by the Riemann solver. A series of tests based on previous analytic and numerical collapse solutions is used to validate our method and implementation. We demonstrate use of our code for applications with a simulation of planar converging supersonic turbulent flow, in which multiple cores form and collapse to create sinks; these sinks continue to interact and accrete from their surroundings over several Myr.

astro-ph.IM↗

arXiv2012

The Wigner solution of quark gap equation at nonzero current quark mass and partial restoration of chiral symmetry at finite chemical potential

According to the generally accepted phase diagram of QCD, at low temperature and high baryon number density the chiral phase transition of QCD is of first order and the co-existence of the Nambu-Goldstone phase and the Wigner phase should appear. This is in conflict with the usual claim that the quark gap equation has no Wigner solution in the case of nonzero current quark mass. In this paper we analyze the reason why the Wigner solution does not exist in the usual treatment and try to propose a new approach to discuss this question. As a first step, we adopt a modified Nambu-Jona-Lasinio (NJL) model to study the Wigner solution at finite current quark mass. We then generalize this approach to the case of finite chemical potential and discuss partial restoration of chiral symmetry at finite chemical potential and compare our results with those in the normal NJL model.

hep-ph↗