arXiv subjects

Xiaofang Chen

Publications and source records attributed to Xiaofang Chen.

7 recordsLinked to original sources

arXiv2025

Reducing Annotation Burden in Physical Activity Research Using Vision-Language Models

Introduction: Data from wearable devices collected in free-living settings, and labelled with physical activity behaviours compatible with health research, are essential for both validating existing wearable-based measurement approaches and developing novel machine learning approaches. One common way of obtaining these labels relies on laborious annotation of sequences of images captured by cameras worn by participants through the course of a day. Methods: We compare the performance of three vision language models and two discriminative models on two free-living validation studies with 161 and 111 participants, collected in Oxfordshire, United Kingdom and Sichuan, China, respectively, using the Autographer (OMG Life, defunct) wearable camera. Results: We found that the best open-source vision-language model (VLM) and fine-tuned discriminative model (DM) achieved comparable performance when predicting sedentary behaviour from single images on unseen participants in the Oxfordshire study; median F1-scores: VLM = 0.89 (0.84, 0.92), DM = 0.91 (0.86, 0.95). Performance declined for light (VLM = 0.60 (0.56,0.67), DM = 0.70 (0.63, 0.79)), and moderate-to-vigorous intensity physical activity (VLM = 0.66 (0.53, 0.85); DM = 0.72 (0.58, 0.84)). When applied to the external Sichuan study, performance fell across all intensity categories, with median Cohen's kappa-scores falling from 0.54 (0.49, 0.64) to 0.26 (0.15, 0.37) for the VLM, and from 0.67 (0.60, 0.74) to 0.19 (0.10, 0.30) for the DM. Conclusion: Freely available computer vision models could help annotate sedentary behaviour, typically the most prevalent activity of daily living, from wearable camera images within similar populations to seen data, reducing the annotation burden.

cs.CV↗

arXiv2024

DeepCRE: Transforming Drug R&D via AI-Driven Cross-drug Response Evaluation

The fields of therapeutic application and drug research and development (R&D) both face substantial challenges, i.e., the therapeutic domain calls for more treatment alternatives, while numerous promising pre-clinical drugs have failed in clinical trials. One of the reasons is the inadequacy of Cross-drug Response Evaluation (CRE) during the late stages of drug R&D. Although in-silico CRE models bring a promising solution, existing methodologies are restricted to early stages of drug R&D, such as target and cell-line levels, offering limited improvement to clinical success rates. Herein, we introduce DeepCRE, a pioneering AI model designed to predict CRE effectively in the late stages of drug R&D. DeepCRE outperforms the existing best models by achieving an average performance improvement of 17.7% in patient-level CRE, and a 5-fold increase in indication-level CRE, facilitating more accurate personalized treatment predictions and better pharmaceutical value assessment for indications, respectively. Furthermore, DeepCRE has identified a set of six drug candidates that show significantly greater effectiveness than a comparator set of two approved drugs in 5/8 colorectal cancer organoids. This demonstrates the capability of DeepCRE to systematically uncover a spectrum of drug candidates with enhanced therapeutic effects, highlighting its potential to transform drug R&D.

cs.AI↗

arXiv2024

Specific Emitter Identification Based on Joint Variational Mode Decomposition

Specific emitter identification (SEI) technology is significant in device administration scenarios, such as self-organized networking and spectrum management, owing to its high security. For nonlinear and non-stationary electromagnetic signals, SEI often employs variational modal decomposition (VMD) to decompose the signal in order to effectively characterize the distinct device fingerprint. However, the trade-off of VMD between the robustness to noise and the ability to preserve signal information has not been investigated in the current literature. Moreover, the existing VMD algorithm does not utilize the stability of the intrinsic distortion of emitters within a certain temporal span, consequently constraining its practical applicability in SEI. In this paper, we propose a joint variational modal decomposition (JVMD) algorithm, which is an improved version of VMD by simultaneously implementing modal decomposition on multi-frame signals. The consistency of multi-frame signals in terms of the central frequencies and the inherent modal functions (IMFs) is exploited, which effectively highlights the distinctive characteristics among emitters and reduces noise. Additionally, the complexity of JVMD is analyzed, which is proven to be more computational-friendly than VMD. Simulations of both modal decomposition and SEI that involve real-world datasets are presented to illustrate that when compared with VMD, the JVMD algorithm improves the accuracy of device classification and the robustness towards noise.

cs.CR↗

arXiv2023

Joint Radio Frequency Fingerprints Identification via Multi-antenna Receiver

In Internet of Things (IoT), radio frequency fingerprints (RFF) technology has been widely used for passive security authentication to identify the special emitter. However, few works took advantage of independent oscillator distortions at the receiver side, and no work has yet considered filtering receiver distortions. In this paper, we investigate the RFF identification (RFFI) involving unknown receiver distortions, where the phase noise caused by each antenna oscillator is independent. Three RFF schemes are proposed according to the number of receiving antennas. When the number is small, the Mutual Information Weighting Scheme (MIWS) is developed by calculating the weighted voting of RFFI result at each antenna; when the number is moderate, the Distortions Filtering Scheme (DFS) is developed by filtering out the channel noise and receiver distortions; when the number is large enough, the Group-Distortions Filtering and Weighting Scheme (GDFWS) is developed, which integrates the advantages of MIWS and DFS. Furthermore, the ability of DFS to filter out the channel noise and receiver distortions is theoretically analyzed at a specific confidence level. Experiments are provided when both channel noise and receiver distortions exist, which verify the effectiveness and robustness of the proposed schemes.

eess.SP↗

arXiv2018

Two-Dimensional Multiferroic Semiconductors with Coexisting Ferroelectricity and Ferromagnetism

Low-dimensional multiferroicity, though highly scarce in nature, has attracted great attention due to both fundamental and technological interests. Using first-principles density functional theory, we show that ferromagnetism and ferroelectricity can coexist in monolayer transition metal phosphorus chalcogenides (TMPCs) - CuMP$_2$X$_6$ (M=Cr, V; X=S, Se). These van der Waals layered materials represent a class of 2D multiferroic semiconductors that simultaneously possess ferroelectric and ferromagnetic orders. In these monolayer materials, Cu atoms spontaneously move away from the center atomic plane, giving rise to nontrivial electric dipole moment along the plane normal. In addition, their ferromagnetism originates from indirect exchange interaction between Cr/V atoms, while their out-of-plane ferroelectricity suggests the possibility of controlling electric polarization by external vertical electric field. Monolayer semiconducting TMPCs thus provide a solid-state 2D materials platform for realizing 2D nanoscale switches and memory devices patterned with top and bottom electrodes.

cond-mat.mtrl-sci↗

arXiv2016

Valley splitting in the transition-metal dichalcogenides monolayer via atoms adsorption

In this letter we study the valley degeneracy splitting of the transition-metal dichalcogenides monolayer by first-principles calculations. The local magnetic moments are introduced into the system when the transition-metal atoms are adsorbed to the monolayer surface. Zeeman effect arising from the local magnetic moment at transition-metal atom sites lifts the valley degeneracy. Anomalous charge, spin and valley Hall Effects can be accessed due to valley splitting when we can only excite carriers of one valley. The valley splitting depends on the direction of magnetization and thus can be tuned continuously by an external magnetic field. This tunable valley splitting offers a practical avenue for exploring device paradigms based on the spin and valley degrees of freedom.

cond-mat.mtrl-sci↗

arXiv2009

A study on the anomaly of $p$ over $π$ ratios in $Au+Au$ collisions with jet quenching

The ratios of $p/π$ at large transverse momentum in central $Au+Au$ collisions at RHIC are studied in the framework of jet quenching based on a next-to-leading order pQCD parton model. It is shown that theoretical calculations with a gluon energy loss larger than the quark energy loss will naturally lead to a smaller $p/π$ ratios at large transverse momentum in $Au+Au$ collisions than those in $p+p$ collisions at the same energy. Scenarios with equal energy losses for gluons and quarks and a strong jet conversion are both explored and it is demonstrated in both scenarios $p/π$ ratios at high $p_T$ in central $Au+Au$ collisions are enhanced and the calculated ratios of protons over pions approach to the experimental measurements. However, ${\bar p}/p$ in the latter scenario is found to fit data better than that in the former scenario.

hep-ph↗