Searcharxiv⌕ Search

arXiv subjects

Ying Tan

Publications and source records attributed to Ying Tan.

At least 55 records · Page 3Linked to original sources
arXiv2024

TCGPN: Temporal-Correlation Graph Pre-trained Network for Stock Forecasting

Recently, the incorporation of both temporal features and the correlation across time series has become an effective approach in time series prediction. Spatio-Temporal Graph Neural Networks (STGNNs) demonstrate good performance on many Temporal-correlation Forecasting Problem. However, when applied to tasks lacking periodicity, such as stock data prediction, the effectiveness and robustness of STGNNs are found to be unsatisfactory. And STGNNs are limited by memory savings so that cannot handle problems with a large number of nodes. In this paper, we propose a novel approach called the Temporal-Correlation Graph Pre-trained Network (TCGPN) to address these limitations. TCGPN utilize Temporal-correlation fusion encoder to get a mixed representation and pre-training method with carefully designed temporal and correlation pre-training tasks. Entire structure is independent of the number and order of nodes, so better results can be obtained through various data enhancements. And memory consumption during training can be significantly reduced through multiple sampling. Experiments are conducted on real stock market data sets CSI300 and CSI500 that exhibit minimal periodicity. We fine-tune a simple MLP in downstream tasks and achieve state-of-the-art results, validating the capability to capture more robust temporal correlation patterns.

cs.LG↗
arXiv2024

Revisiting the dead time effects of Insight-HXMT/ME on timing analysis

Dead time is a common instrumental effect of X-ray detectors which would alter the behavior of timing properties of astronomical signals, such as distorting the shape of power density spectra (PDS), affecting the root-mean-square of potential quasi-periodic oscillation signals, etc. We revisit the effects of the dead time of Medium Energy X-ray telescope (ME) onboard Insight-HXMT, based on the simulation of electronic read-out mechanism that causes the dead time, and the real data. We investigate dead time effects on the pulse profile as well as the Quasi-Periodic Oscillation (QPO) signals. The dead time coefficient suggests a linear correlation with the observed count rate in each phase bin of the pulse profile according to the simulation of periodic signal as well as the real data observed on Swift J0243.6+6124. The Fourier-amplitude-difference (FAD) method could well recover the intrinsic shape of the observed PDS in the case that the PDS is from two identical detectors. We apply this technique on ME, by splitting the 9 FPGA modules into 2 groups. The results indicate that the FAD technique suits the case when two groups of detectors are not largely different; and the recovered PDS of Sco X-1 observed by ME slightly enhances the significance of the previously known QPO signal, meanwhile the root-mean-square of QPO is significantly improved. We provide the FAD correction tool implemented in HXMTDAS for users in the future to better analyze QPO signals.

astro-ph.HE↗
arXiv2024

Resilient control of networked switched systems subject to deception attack and DoS attack

In this paper, the resilient control for switched systems in the presence of deception attack and denial-of-service (DoS) attack is addressed. Due to the interaction of two kinds of attacks and the asynchronous phenomenon of controller mode and subsystem mode, the system dynamics becomes much more complex. A criterion is derived to ensure the mean square security level of the closed-loop system. This in turn reveals the balance of system resilience and control performance. Furthermore, a mixed-switching control strategy is put forward to make the system globally asymptotically stable. It is shown that the system will still converge to the equilibrium even if the deception attack occurs. Finally, simulations are carried out to verify the effectiveness of the theoretical results.

eess.SY↗
arXiv2024

Derivative-Free Optimization for Low-Rank Adaptation in Large Language Models

Parameter-efficient tuning methods such as LoRA could achieve comparable performance to model tuning by tuning a small portion of the parameters. However, substantial computational resources are still required, as this process involves calculating gradients and performing back-propagation throughout the model. Much effort has recently been devoted to utilizing the derivative-free optimization method to eschew the computation of gradients and showcase an augmented level of robustness in few-shot settings. In this paper, we prepend the low-rank modules into each self-attention layer of the model and employ two derivative-free optimization methods to optimize these low-rank modules at each layer alternately. Extensive results on various tasks and language models demonstrate that our proposed method achieves substantial improvement and exhibits clear advantages in memory usage and convergence speed compared to existing gradient-based parameter-efficient tuning and derivative-free optimization methods in few-shot settings.

cs.CL↗
arXiv2024

Edge-aware Hard Clustering Graph Pooling for Brain Imaging

Graph Convolutional Networks (GCNs) can capture non-Euclidean spatial dependence between different brain regions. The graph pooling operator, a crucial element of GCNs, enhances the representation learning capability and facilitates the acquisition of abnormal brain maps. However, most existing research designs graph pooling operators solely from the perspective of nodes while disregarding the original edge features. This confines graph pooling application scenarios and diminishes its ability to capture critical substructures. In this paper, we propose a novel edge-aware hard clustering graph pool (EHCPool), which is tailored to dominant edge features and redefines the clustering process. EHCPool initially introduced the 'Edge-to-Node' score criterion which utilized edge information to evaluate the significance of nodes. An innovative Iteration n-top strategy was then developed, guided by edge scores, to adaptively learn sparse hard clustering assignments for graphs. Additionally, a N-E Aggregation strategy is designed to aggregate node and edge features in each independent subgraph. Extensive experiments on the multi-site public datasets demonstrate the superiority and robustness of the proposed model. More notably, EHCPool has the potential to probe different types of dysfunctional brain networks from a data-driven perspective. Method code: https://github.com/swfen/EHCPool

cs.CV↗
arXiv2024

Zero-Shot Chain-of-Thought Reasoning Guided by Evolutionary Algorithms in Large Language Models

Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks and exhibited impressive reasoning abilities by applying zero-shot Chain-of-Thought (CoT) prompting. However, due to the evolving nature of sentence prefixes during the pre-training phase, existing zero-shot CoT prompting methods that employ identical CoT prompting across all task instances may not be optimal. In this paper, we introduce a novel zero-shot prompting method that leverages evolutionary algorithms to generate diverse promptings for LLMs dynamically. Our approach involves initializing two CoT promptings, performing evolutionary operations based on LLMs to create a varied set, and utilizing the LLMs to select a suitable CoT prompting for a given problem. Additionally, a rewriting operation, guided by the selected CoT prompting, enhances the understanding of the LLMs about the problem. Extensive experiments conducted across ten reasoning datasets demonstrate the superior performance of our proposed method compared to current zero-shot CoT prompting methods on GPT-3.5-turbo and GPT-4. Moreover, in-depth analytical experiments underscore the adaptability and effectiveness of our method in various reasoning tasks.

cs.CL↗
arXiv2023

VCD: Visual Causality Discovery for Cross-Modal Question Reasoning

Existing visual question reasoning methods usually fail to explicitly discover the inherent causal mechanism and ignore jointly modeling cross-modal event temporality and causality. In this paper, we propose a visual question reasoning framework named Cross-Modal Question Reasoning (CMQR), to discover temporal causal structure and mitigate visual spurious correlation by causal intervention. To explicitly discover visual causal structure, the Visual Causality Discovery (VCD) architecture is proposed to find question-critical scene temporally and disentangle the visual spurious correlations by attention-based front-door causal intervention module named Local-Global Causal Attention Module (LGCAM). To align the fine-grained interactions between linguistic semantics and spatial-temporal representations, we build an Interactive Visual-Linguistic Transformer (IVLT) that builds the multi-modal co-occurrence interactions between visual and linguistic content. Extensive experiments on four datasets demonstrate the superiority of CMQR for discovering visual causal structures and achieving robust question reasoning.

cs.CV↗
arXiv2023

Micro-transfer-printed Thin film lithium niobate (TFLN)-on-Silicon Ring Modulator

Thin-film lithium niobate (TFLN) has a proven record of building high-performance electro-optical (EO) modulators. However, its CMOS incompatibility and the need for non-standard etching have consistently posed challenges in terms of scalability, standardization, and the complexity of integration. Heterogeneous integration comes to solve this key challenge. Micro-transfer printing of thin-film lithium niobate brings TFLN to well-established silicon ecosystem by easy "pick and place", which showcases immense potential in constructing high-density, cost-effective, highly versatile heterogeneous integrated circuits. Here, we demonstrated for the first time a micro-transfer-printed thin film lithium niobate (TFLN)-on-silicon ring modulator, which is an important step towards dense integration of performant lithium niobate modulators with compact and scalable silicon circuity. The presented device exhibits an insertion loss of -1.5dB, extinction ratio of -37dB, electro-optical bandwidth of 16GHz and modulation rates up to 45Gps.

physics.optics↗
arXiv2023

ProtoCLIP: Prototypical Contrastive Language Image Pretraining

Contrastive Language Image Pretraining (CLIP) has received widespread attention, since its learned representations can be transferred well to various downstream tasks. During the training process of the CLIP model, the InfoNCE objective aligns positive image-text pairs and separates negative ones. We show an underlying representation grouping effect during this process: the InfoNCE objective indirectly groups semantically similar representations together via randomly emerged within-modal anchors. Based on this understanding, in this paper, Prototypical Contrastive Language Image Pretraining (ProtoCLIP) is introduced to enhance such grouping by boosting its efficiency and increasing its robustness against the modality gap. Specifically, ProtoCLIP sets up prototype-level discrimination between image and text spaces, which efficiently transfers higher-level structural knowledge. Further, Prototypical Back Translation (PBT) is proposed to decouple representation grouping from representation alignment, resulting in effective learning of meaningful representations under large modality gap. The PBT also enables us to introduce additional external teachers with richer prior language knowledge. ProtoCLIP is trained with an online episodic training strategy, which makes it can be scaled up to unlimited amounts of data. We train our ProtoCLIP on Conceptual Captions and achieved an +5.81% ImageNet linear probing improvement and an +2.01% ImageNet zero-shot classification improvement. On the larger YFCC-15M dataset, ProtoCLIP matches the performance of CLIP with 33% of training time. Codes are available at https://github.com/megvii-research/protoclip.

cs.CV↗
arXiv2023

Data-Driven Goal Recognition in Transhumeral Prostheses Using Process Mining Techniques

A transhumeral prosthesis restores missing anatomical segments below the shoulder, including the hand. Active prostheses utilize real-valued, continuous sensor data to recognize patient target poses, or goals, and proactively move the artificial limb. Previous studies have examined how well the data collected in stationary poses, without considering the time steps, can help discriminate the goals. In this case study paper, we focus on using time series data from surface electromyography electrodes and kinematic sensors to sequentially recognize patients' goals. Our approach involves transforming the data into discrete events and training an existing process mining-based goal recognition system. Results from data collected in a virtual reality setting with ten subjects demonstrate the effectiveness of our proposed goal recognition approach, which achieves significantly better precision and recall than the state-of-the-art machine learning techniques and is less confident when wrong, which is beneficial when approximating smoother movements of prostheses.

cs.RO↗
arXiv2023

Temporal Dynamic Synchronous Functional Brain Network for Schizophrenia Diagnosis and Lateralization Analysis

The available evidence suggests that dynamic functional connectivity (dFC) can capture time-varying abnormalities in brain activity in resting-state cerebral functional magnetic resonance imaging (rs-fMRI) data and has a natural advantage in uncovering mechanisms of abnormal brain activity in schizophrenia(SZ) patients. Hence, an advanced dynamic brain network analysis model called the temporal brain category graph convolutional network (Temporal-BCGCN) was employed. Firstly, a unique dynamic brain network analysis module, DSF-BrainNet, was designed to construct dynamic synchronization features. Subsequently, a revolutionary graph convolution method, TemporalConv, was proposed, based on the synchronous temporal properties of feature. Finally, the first modular abnormal hemispherical lateralization test tool in deep learning based on rs-fMRI data, named CategoryPool, was proposed. This study was validated on COBRE and UCLA datasets and achieved 83.62% and 89.71% average accuracies, respectively, outperforming the baseline model and other state-of-the-art methods. The ablation results also demonstrate the advantages of TemporalConv over the traditional edge feature graph convolution approach and the improvement of CategoryPool over the classical graph pooling approach. Interestingly, this study showed that the lower order perceptual system and higher order network regions in the left hemisphere are more severely dysfunctional than in the right hemisphere in SZ and reaffirms the importance of the left medial superior frontal gyrus in SZ. Our core code is available at: https://github.com/swfen/Temporal-BCGCN.

q-bio.NC↗
arXiv2023

A spectral-timing study of the inner flow geometry in MAXI J1535--571 with $Insight$-HXMT and NICER

We have performed a spectral-timing analysis on the black hole X-ray binary MAXI J1535--571 during its 2017 outburst, with the aim of exploring the evolution of the inner accretion flow geometry. X-ray reverberation lags are observed in the hard-intermediate state (HIMS) and soft-intermediate state (SIMS) of the outburst. During the HIMS, the characteristic frequency of the reverberation lags $ν_0$ (the frequency at which the soft lag turns to zero in the lag-frequency spectra) increases when the spectrum softens. This reflects a reduction of the spatial distance between the corona and accretion disc, when assuming the measured time lags are associated with the light travel time. We also find a strong correlation between $ν_0$ and type-C Quasi Periodic Oscillation (QPO) centroid frequency $ν_{QPO}$, which can be well explained by the Lense-Thirring (L-T) precession model under a truncated disk geometry. Despite the degeneracy in the spectral modellings, our results suggest that the accretion disc is largely truncated in the low hard state (LHS), and moves inward as the spectrum softens. Combine the spectral modelling results with the $ν_0$ - $ν_{QPO}$ evolution, we are inclined to believe that this source probably have a truncated disk geometry in the hard state.

astro-ph.HE↗
arXiv2023

The incompressible limit of the isentropic fluids in the analytic spaces

We consider the low Mach number limit problem of the Euler equations for isentropic fluids in the analytic spaces. We prove that, given general analytic initial data, the solution is uniformly bounded on a time interval independent of the small parameter and the incompressible limit holding in the analytic norm. The same results extend more generally to Gevrey initial data with convergence holds in a Gevrey norm. The results extend the isentropic fluids in arXiv:2102.11454 to more general pressure laws.

math.AP↗
arXiv2023

Robust Tracking Control for Nonlinear Systems: Performance optimization via extremum seeking

This paper presents a controller design and optimization framework for nonlinear dynamic systems to track a given reference signal in the presence of disturbances when the task is repeated over a finite-time interval. This novel framework mainly consists of two steps. The first step is to design a robust linear quadratic tracking controller based on the existing control structure with a Youla-type filter $\tilde Q$. Secondly, an extra degree of freedom: a parameterization in terms of $\tilde Q$, is added to this design framework. This extra design parameter is tuned iteratively from measured tracking cost function with the given disturbances and modeling uncertainties to achieve the best transient performance. The proposed method is validated with simulation placed on a Furuta inverted pendulum, showing significant tracking performance improvement.

eess.SY↗
arXiv2023

On Robust Observer Design for System Motion on SE(3) Using Onboard Visual Sensors

Onboard visual sensing has been widely used in the unmanned ground vehicle (UGV) and/or unmanned aerial vehicle (UAV), which can be modeled as dynamic systems on SE(3). The onboard sensing outputs of the dynamic system can usually be applied to derive the relative position between the feature marks and the system, but bearing with explicit geometrical constraint. Such a visual geometrical constraint makes the design of the visual observer on SE(3) very challenging, as it will cause a time-varying or switching visible set due to the varying number of feature marks in this set along different trajectories. Moreover, the possibility of having mis-identified feature marks and modeling uncertainties might result in a divergent estimation error. This paper proposes a new robust observer design method that can accommodate these uncertainties from onboard visual sensing. The key design idea for this observer is to estimate the visible set and identify the mis-identified features from the measurements. Based on the identified uncertainties, a switching strategy is proposed to ensure bounded estimation error for any given trajectory over a fixed time interval. Simulation results are provided to demonstrate the effectiveness of the proposed robust observer.

eess.SY↗
arXiv2023

Self-supervised Contrastive Learning for Audio-Visual Action Recognition

The underlying correlation between audio and visual modalities can be utilized to learn supervised information for unlabeled videos. In this paper, we propose an end-to-end self-supervised framework named Audio-Visual Contrastive Learning (AVCL), to learn discriminative audio-visual representations for action recognition. Specifically, we design an attention based multi-modal fusion module (AMFM) to fuse audio and visual modalities. To align heterogeneous audio-visual modalities, we construct a novel co-correlation guided representation alignment module (CGRA). To learn supervised information from unlabeled videos, we propose a novel self-supervised contrastive learning module (SelfCL). Furthermore, we build a new audio-visual action recognition dataset named Kinetics-Sounds100. Experimental results on Kinetics-Sounds32 and Kinetics-Sounds100 datasets demonstrate the superiority of our AVCL over the state-of-the-art methods on large-scale action recognition benchmark.

cs.CV↗
arXiv2023

Insight-HXMT and GECAM-C observations of the brightest-of-all-time GRB 221009A

GRB 221009A is the brightest gamma-ray burst ever detected since the discovery of this kind of energetic explosions. However, an accurate measurement of the prompt emission properties of this burst is very challenging due to its exceptional brightness. With joint observations of \textit{Insight}-HXMT and GECAM-C, we made an unprecedentedly accurate measurement of the emission during the first $\sim$1800 s of GRB 221009A, including its precursor, main emission (ME, which dominates the burst in flux), flaring emission and early afterglow, in the hard X-ray to soft gamma-ray band from $\sim$ 10 keV to $\sim$ 6 MeV. Based on the GECAM-C unsaturated data of the ME, we measure a record-breaking isotropic equivalent energy ($E_{\rm iso}$) of $\bf \sim 1.5 \times 10^{55}$ erg, which is about eight times the total rest-mass energy of the Sun. The early afterglow data require a significant jet break between 650 s and 1100 s, most likely at $\sim950$ s from the afterglow starting time $T_{AG}$, which corresponds to a jet opening angle of $\sim {0.7^\circ} \ (η_γn)^{1/8}$, where $n$ is the ambient medium density in units of $\rm cm^{-3}$ and $η_γ$ is the ratio between $γ$-ray energy and afterglow kinetic energy. The beaming-corrected total $γ$-ray energy $E_γ$ is $\sim 1.15 \times10^{51} \ (η_γn)^{1/4}$ erg, which is typical for long GRBs. These results suggest that this GRB may have a special central engine, which could launch and collimate a very narrowly beamed jet with an ordinary energy budget, leading to exceptionally luminous gamma-ray radiation per unit solid angle. Alternatively, more GRBs might have such a narrow and bright beam, which are missed by an unfavorable viewing angle or have been detected without distance measurement.

astro-ph.HE↗
arXiv2023

In-orbit Performance of ME onboard Insight-HXMT in the first 5 years

Introduction: The Medium Energy X-ray telescope (ME) is a collimated X-ray telescope onboard the Insight hard X-ray modulation telescope (Insight-HXMT) satellite. It has 1728 Si-PIN pixels readout using 54 low noise application-specific integrated circuits (ASICs). ME covers the energy range of 5-30 keV and has a total detection area of 952 cm2. The typical energy resolution of ME at the beginning of the mission is 3 keV at 17.8 keV (Full Width at Half Maximum, FWHM) and the time resolution is 255 us. In this study, we present the in-orbit performance of ME in its first 5 years of operation. Methods: The performance of ME was monitored using onboard radioactive sources and astronomical X-ray objects. ME carries six 241Am radioactive sources for onboard calibration, which can continuously illuminate the calibration pixels. The long-term performance evolution of ME can be quantified using the properties of the accumulated spectra of the calibration pixels. In addition, observations of the Crab Nebula and the pulsar were used to check the long-term evolution of the detection efficiency as a function of energy. Conclusion: After 5 years of operation, 742 cm2 of the Si-PIN pixels were still working normally. The peak positions of 241Am emission lines gradually shifted to the high energy region, implying a slow increase in ME gain of 1.43%. A comparison of the ME spectra of the Crab Nebula and the pulsar shows that the E-C relations and the redistribution matrix file are still acceptable for most data analysis works, and there is no detectable variation in the detection efficiency.

astro-ph.IM↗