14,257 results on '"Wei, Hua"'
Search Results
2. SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation
- Author
-
Chen, Yi-Chia, Li, Wei-Hua, Sun, Cheng, Wang, Yu-Chiang Frank, and Chen, Chu-Song
- Subjects
Computer Science - Artificial Intelligence ,Computer Science - Computation and Language ,Computer Science - Computer Vision and Pattern Recognition - Abstract
We introduce SAM4MLLM, an innovative approach which integrates the Segment Anything Model (SAM) with Multi-Modal Large Language Models (MLLMs) for pixel-aware tasks. Our method enables MLLMs to learn pixel-level location information without requiring excessive modifications to the existing model architecture or adding specialized tokens. We introduce an inquiry-based approach that can effectively find prompt points for SAM to perform segmentation based on MLLM. It combines detailed visual information with the powerful expressive capabilities of large language models in a unified language-based manner without additional computational overhead in learning. Experimental results on pubic benchmarks demonstrate the effectiveness of our approach., Comment: ECCV 2024
- Published
- 2024
3. MalLight: Influence-Aware Coordinated Traffic Signal Control for Traffic Signal Malfunctions
- Author
-
Yang, Qinchen, Xie, Zejun, Wei, Hua, Zhang, Desheng, and Yang, Yu
- Subjects
Computer Science - Artificial Intelligence - Abstract
Urban traffic is subject to disruptions that cause extended waiting time and safety issues at signalized intersections. While numerous studies have addressed the issue of intelligent traffic systems in the context of various disturbances, traffic signal malfunction, a common real-world occurrence with significant repercussions, has received comparatively limited attention. The primary objective of this research is to mitigate the adverse effects of traffic signal malfunction, such as traffic congestion and collision, by optimizing the control of neighboring functioning signals. To achieve this goal, this paper presents a novel traffic signal control framework (MalLight), which leverages an Influence-aware State Aggregation Module (ISAM) and an Influence-aware Reward Aggregation Module (IRAM) to achieve coordinated control of surrounding traffic signals. To the best of our knowledge, this study pioneers the application of a Reinforcement Learning(RL)-based approach to address the challenges posed by traffic signal malfunction. Empirical investigations conducted on real-world datasets substantiate the superior performance of our proposed methodology over conventional and deep learning-based alternatives in the presence of signal malfunction, with reduction of throughput alleviated by as much as 48.6$\%$., Comment: Paper accepted to CIKM24 Full Research track
- Published
- 2024
4. SynTraC: A Synthetic Dataset for Traffic Signal Control from Traffic Monitoring Cameras
- Author
-
Chen, Tiejin, Shirke, Prithvi, Chakravarthi, Bharatesh, Vaghela, Arpitsinh, Da, Longchao, Lu, Duo, Yang, Yezhou, and Wei, Hua
- Subjects
Computer Science - Artificial Intelligence - Abstract
This paper introduces SynTraC, the first public image-based traffic signal control dataset, aimed at bridging the gap between simulated environments and real-world traffic management challenges. Unlike traditional datasets for traffic signal control which aim to provide simplified feature vectors like vehicle counts from traffic simulators, SynTraC provides real-style images from the CARLA simulator with annotated features, along with traffic signal states. This image-based dataset comes with diverse real-world scenarios, including varying weather and times of day. Additionally, SynTraC also provides different reward values for advanced traffic signal control algorithms like reinforcement learning. Experiments with SynTraC demonstrate that it is still an open challenge to image-based traffic signal control methods compared with feature-based control methods, indicating our dataset can further guide the development of future algorithms. The code for this paper can be found in \url{https://github.com/DaRL-LibSignal/SynTraC}.SynTraC, Comment: Accepted to IEEE ITSC2024
- Published
- 2024
5. The Multiband Emission of the two-component Gamma-Ray Burst jet influenced by progenitor winds within the Accretion Disk of Active Galactic Nuclei
- Author
-
Yuan, Hao-Yu and Lei, Wei-Hua
- Subjects
Astrophysics - High Energy Astrophysical Phenomena - Abstract
Gamma-ray bursts (GRBs), both from merger of binary compact objects (short GRBs) and collapse of massive stars (long GRBs), are expected to occur in the dense environments, e.g., the accretion disk of active galactic nuclei (AGN). The propagating of GRB jets in such dense environment will result in multiband transients. Investigating the properties of these transients plays important roles in their identification, understanding the jet structure and constraining population of the star and compact object in AGN disks. In this work, we intend to study the propagation and emission of a two-component GRB jet (a fast narrow component and wide slow one) in the AGN disk. We consider the influence of wind from the short and long GRB progenitors, which would reconstruct the surrounding density distribution and form a cavity in the AGN disk. We find that the long GRB jets will be chocked, the dynamcis and the emission are resemble to the case without cavity. The narrow and wide cocoon breakout emission can be detected by EP and HXMT, respectively. For short GRBs, we expect a non-thermal afterglow emission from the wide jet and a cocoon breakout emission from the chocked narrow jet, which can be monitored by EP and HXMT, respectively. Therefore, the joint observations by EP and HXMT might be helpful to distinguish the type of GRBs in the AGN disk and the jet components., Comment: 15 pages, 6 figures, 1 table
- Published
- 2024
6. Unveiling the Multifaceted GRB 200613A: Prompt Emission Dynamics, Afterglow Evolution, and the Host Galaxy's Properties
- Author
-
Fu, Shao-Yu, Xu, Dong, Lei, Wei-Hua, Postigo, Antonio de Ugarte, Kann, D. Alexander, Thöne, Christina C., Fernández, José Feliciano Agüí, Shuang-Xi, Yi, Xie, Wei, Zou, Yuan-Chuan, Liu, Xing, Jiang, Shuai-Qing, Lu, Tian-Hua, An, Jie, Zhu, Zi-Pei, Zheng, Jie, Tang, Qing-Wen, Zhao, Peng-Wei, Xin, Li-Ping, and Wei, Jian-Yan
- Subjects
Astrophysics - High Energy Astrophysical Phenomena - Abstract
We present our optical observations and multi-wavelength analysis of the GRB\,200613A detected by \texttt{Fermi} satellite. Time-resolved spectral analysis of the prompt $\gamma$-ray emission was conducted utilizing the Bayesian block method to determine statistically optimal time bins. Based on the Bayesian Information Criterion (BIC), the data generally favor the Band+Blackbody (short as BB) model. We speculate that the main Band component comes from the Blandford-Znajek mechanism, while the additional BB component comes from the neutrino annihilation process. The BB component becomes significant for a low-spin, high-accretion rate black hole central engine, as evidenced by our model comparison with the data. The afterglow light curve exhibits typical power-law decay, and its behavior can be explained by the collision between the ejecta and constant interstellar medium (ISM). Model fitting yields the following parameters: $E_{K,iso} = (2.04^{+11.8}_{-1.50})\times 10^{53}$ erg, $\Gamma_0=354^{+578}_{-217}$, $p=2.09^{+0.02}_{-0.03}$, $n_{18}=(2.04^{+9.71}_{-1.87})\times 10^{2}$ cm$^{-3}$, $\theta_j=24.0^{+6.50}_{-5.54}$ degree, $\epsilon_e=1.66^{+4.09}_{-1.39})\times 10^{-1}$ and $\epsilon_B=(7.76^{+48.5}_{-5.9})\times 10^{-6}$. In addition, we employed the public Python package \texttt{Prospector} perform a spectral energy distribution (SED) modeling of the host galaxy. The results suggest that the host galaxy is a massive galaxy ($\log(M_\ast / M_\odot)=11.75^{+0.10}_{-0.09}$) with moderate star formation rate ($\mbox{SFR}=22.58^{+13.63}_{-7.22} M_{\odot}$/yr). This SFR is consistent with the SFR of $\sim 34.2 M_{\odot}$ yr$^{-1}$ derived from the [OII] emission line in the observed spectrum., Comment: 30 pages, 16 figures, accepted by ApJ
- Published
- 2024
7. LLMExplainer: Large Language Model based Bayesian Inference for Graph Explanation Generation
- Author
-
Zhang, Jiaxing, Liu, Jiayi, Luo, Dongsheng, Neville, Jennifer, and Wei, Hua
- Subjects
Computer Science - Machine Learning ,Computer Science - Artificial Intelligence ,Computer Science - Computation and Language - Abstract
Recent studies seek to provide Graph Neural Network (GNN) interpretability via multiple unsupervised learning models. Due to the scarcity of datasets, current methods easily suffer from learning bias. To solve this problem, we embed a Large Language Model (LLM) as knowledge into the GNN explanation network to avoid the learning bias problem. We inject LLM as a Bayesian Inference (BI) module to mitigate learning bias. The efficacy of the BI module has been proven both theoretically and experimentally. We conduct experiments on both synthetic and real-world datasets. The innovation of our work lies in two parts: 1. We provide a novel view of the possibility of an LLM functioning as a Bayesian inference to improve the performance of existing algorithms; 2. We are the first to discuss the learning bias issues in the GNN explanation problem., Comment: Preprint Paper with 13 pages
- Published
- 2024
8. Shaded Route Planning Using Active Segmentation and Identification of Satellite Images
- Author
-
Da, Longchao, Chhibba, Rohan, Jaiswal, Rushabh, Middel, Ariane, and Wei, Hua
- Subjects
Computer Science - Computers and Society ,Computer Science - Artificial Intelligence ,Computer Science - Computer Vision and Pattern Recognition ,68T45, 68U35 ,I.2.10 ,I.4.8 - Abstract
Heatwaves pose significant health risks, particularly due to prolonged exposure to high summer temperatures. Vulnerable groups, especially pedestrians and cyclists on sun-exposed sidewalks, motivate the development of a route planning method that incorporates somatosensory temperature effects through shade ratio consideration. This paper is the first to introduce a pipeline that utilizes segmentation foundation models to extract shaded areas from high-resolution satellite images. These areas are then integrated into a multi-layered road map, enabling users to customize routes based on a balance between distance and shade exposure, thereby enhancing comfort and health during outdoor activities. Specifically, we construct a graph-based representation of the road map, where links indicate connectivity and are updated with shade ratio data for dynamic route planning. This system is already implemented online, with a video demonstration, and will be specifically adapted to assist travelers during the 2024 Olympic Games in Paris., Comment: Paper accepted to CIKM24 demo track
- Published
- 2024
9. GuideLight: 'Industrial Solution' Guidance for More Practical Traffic Signal Control Agents
- Author
-
Jiang, Haoyuan, Xiong, Xuantang, Li, Ziyue, Mao, Hangyu, Sui, Guanghu, Ruan, Jingqing, Cheng, Yuheng, Wei, Hua, Ketter, Wolfgang, and Zhao, Rui
- Subjects
Computer Science - Multiagent Systems ,Computer Science - Artificial Intelligence ,Computer Science - Machine Learning - Abstract
Currently, traffic signal control (TSC) methods based on reinforcement learning (RL) have proven superior to traditional methods. However, most RL methods face difficulties when applied in the real world due to three factors: input, output, and the cycle-flow relation. The industry's observable input is much more limited than simulation-based RL methods. For real-world solutions, only flow can be reliably collected, whereas common RL methods need more. For the output action, most RL methods focus on acyclic control, which real-world signal controllers do not support. Most importantly, industry standards require a consistent cycle-flow relationship: non-decreasing and different response strategies for low, medium, and high-level flows, which is ignored by the RL methods. To narrow the gap between RL methods and industry standards, we innovatively propose to use industry solutions to guide the RL agent. Specifically, we design behavior cloning and curriculum learning to guide the agent to mimic and meet industry requirements and, at the same time, leverage the power of exploration and exploitation in RL for better performance. We theoretically prove that such guidance can largely decrease the sample complexity to polynomials in the horizon when searching for an optimal policy. Our rigid experiments show that our method has good cycle-flow relation and superior performance., Comment: Under Review of IEEE Transactions on Intelligent Transportation Systems
- Published
- 2024
10. The white-light superflares from cool stars in GWAC triggers
- Author
-
Li, Guang-Wei, Wang, Liang, Yuan, Hai-Long, Xin, Li-Ping, Wang, Jing, Wu, Chao, Li, Hua-Li, Haerken, Hasitieer, Wang, Wei-Hua, Cai, Hong-Bo, Han, Xu-Hui, Xu, Yang, Huang, Lei, Lu, Xiao-Meng, Bai, Jian-Ying, Wang, Xiang-Yu, Dai, Zi-Gao, Liang, En-Wei, and Wei, Jian-Yan
- Subjects
Astrophysics - Solar and Stellar Astrophysics - Abstract
M-type stars are the ones that flare most frequently, but how big their maximum flare energy can reach is still unknown. We present 163 flares from 162 individual M2 through L1-type stars that triggered the GWAC, with flare energies ranging from $10^{32.2}$ to $10^{36.4}$ erg . The flare amplitudes range from $\triangle G = 0.84$ to $\sim 10$ mag. Flare energy increases with stellar surface temperature ($T_{\rm eff}$) but both $\triangle G$ and equivalent duration $\log_{10}(ED)$ seem to be independent of $T_{\rm eff}$. Combining periods detected from light curves of TESS and K2, spectra from LAMOST, SDSS and the 2.16 m Telescope, and the Gaia DR3 data, we found that these GWAC flare stars are young. For the stars that have spectra, we found that these stars are in or very near to the saturation region, and $\log_{10}(L_{\rm H\alpha}/L_{\rm bol})$ is lower for M7-L1 stars than for M2-M6 stars. We also studied the relation between GWAC flare bolometric energy $E_{\rm bol}$ and stellar hemispherical area $S$, and found that $\log_{10}E_{\rm bol}$ (in erg) increases with increasing $S$ (in cm$^2$), and the maximum flare energy $\log_{10}E_{\rm bol, max} \geqslant \log_{10}S + 14.25$. For M7-L1 stars, there seem to be other factors limiting their maximum flare energies in addition to stellar hemispherical area., Comment: 18 pages, 11 figures, 4 tables
- Published
- 2024
- Full Text
- View/download PDF
11. LLM Uncertainty Quantification through Directional Entailment Graph and Claim Level Response Augmentation
- Author
-
Da, Longchao, Chen, Tiejin, Cheng, Lu, and Wei, Hua
- Subjects
Computer Science - Computation and Language ,I.2.7 - Abstract
The Large language models (LLMs) have showcased superior capabilities in sophisticated tasks across various domains, stemming from basic question-answer (QA), they are nowadays used as decision assistants or explainers for unfamiliar content. However, they are not always correct due to the data sparsity in specific domain corpus, or the model's hallucination problems. Given this, how much should we trust the responses from LLMs? This paper presents a novel way to evaluate the uncertainty that captures the directional instability, by constructing a directional graph from entailment probabilities, and we innovatively conduct Random Walk Laplacian given the asymmetric property of a constructed directed graph, then the uncertainty is aggregated by the derived eigenvalues from the Laplacian process. We also provide a way to incorporate the existing work's semantics uncertainty with our proposed layer. Besides, this paper identifies the vagueness issues in the raw response set and proposes an augmentation approach to mitigate such a problem, we conducted extensive empirical experiments and demonstrated the superiority of our proposed solutions., Comment: 11 pages main content, 5 pages appendix
- Published
- 2024
12. Metacognitive AI: Framework and the Case for a Neurosymbolic Approach
- Author
-
Wei, Hua, Shakarian, Paulo, Lebiere, Christian, Draper, Bruce, Krishnaswamy, Nikhil, and Nirenburg, Sergei
- Subjects
Computer Science - Artificial Intelligence - Abstract
Metacognition is the concept of reasoning about an agent's own internal processes and was originally introduced in the field of developmental psychology. In this position paper, we examine the concept of applying metacognition to artificial intelligence. We introduce a framework for understanding metacognitive artificial intelligence (AI) that we call TRAP: transparency, reasoning, adaptation, and perception. We discuss each of these aspects in-turn and explore how neurosymbolic AI (NSAI) can be leveraged to address challenges of metacognition.
- Published
- 2024
13. Flexible Heteroscedastic Count Regression with Deep Double Poisson Networks
- Author
-
Young, Spencer, Jenkins, Porter, Da, Lonchao, Dotson, Jeff, and Wei, Hua
- Subjects
Computer Science - Machine Learning - Abstract
Neural networks that can produce accurate, input-conditional uncertainty representations are critical for real-world applications. Recent progress on heteroscedastic continuous regression has shown great promise for calibrated uncertainty quantification on complex tasks, like image regression. However, when these methods are applied to discrete regression tasks, such as crowd counting, ratings prediction, or inventory estimation, they tend to produce predictive distributions with numerous pathologies. We propose to address these issues by training a neural network to output the parameters of a Double Poisson distribution, which we call the Deep Double Poisson Network (DDPN). In contrast to existing methods that are trained to minimize Gaussian negative log likelihood (NLL), DDPNs produce a proper probability mass function over discrete output. Additionally, DDPNs naturally model under-, over-, and equi-dispersion, unlike networks trained with the more rigid Poisson and Negative Binomial parameterizations. We show DDPNs 1) vastly outperform existing discrete models; 2) meet or exceed the accuracy and flexibility of networks trained with Gaussian NLL; 3) produce proper predictive distributions over discrete counts; and 4) exhibit superior out-of-distribution detection. DDPNs can easily be applied to a variety of count regression datasets including tabular, image, point cloud, and text data.
- Published
- 2024
14. MagiNet: Mask-Aware Graph Imputation Network for Incomplete Traffic Data
- Author
-
Zhou, Jianping, Lu, Bin, Liu, Zhanyu, Pan, Siyu, Feng, Xuejun, Wei, Hua, Zheng, Guanjie, Wang, Xinbing, and Zhou, Chenghu
- Subjects
Computer Science - Machine Learning ,Computer Science - Artificial Intelligence - Abstract
Due to detector malfunctions and communication failures, missing data is ubiquitous during the collection of traffic data. Therefore, it is of vital importance to impute the missing values to facilitate data analysis and decision-making for Intelligent Transportation System (ITS). However, existing imputation methods generally perform zero pre-filling techniques to initialize missing values, introducing inevitable noises. Moreover, we observe prevalent over-smoothing interpolations, falling short in revealing the intrinsic spatio-temporal correlations of incomplete traffic data. To this end, we propose Mask-Aware Graph imputation Network: MagiNet. Our method designs an adaptive mask spatio-temporal encoder to learn the latent representations of incomplete data, eliminating the reliance on pre-filling missing values. Furthermore, we devise a spatio-temporal decoder that stacks multiple blocks to capture the inherent spatial and temporal dependencies within incomplete traffic data, alleviating over-smoothing imputation. Extensive experiments demonstrate that our method outperforms state-of-the-art imputation methods on five real-world traffic datasets, yielding an average improvement of 4.31% in RMSE and 3.72% in MAPE., Comment: 19 pages, 7 figures
- Published
- 2024
15. The Heavier the Faster: A Sub-population of Heavy, Rapidly Spinning and Quickly Evolving Binary Black Holes
- Author
-
Guo, Wei-Hua, Li, Yin-Jie, Wang, Yuan-Zhu, Shao, Yong, Wu, Shichao, Zhu, Tao, and Fan, Yi-Zhong
- Subjects
Astrophysics - High Energy Astrophysical Phenomena ,Astrophysics - Solar and Stellar Astrophysics - Abstract
The spins of binary black holes (BBHs) measured from gravitational waves carry notable information of the formation pathways. Here we propose a quantity "dimensionless net spin" ($\chi_{\rm N}$), which is related to the sum of angular momentum of component black holes in the system, to provide a novel perspective to study the origin(s) of BBHs. By performing hierarchical Bayesian inference on $\chi_{\rm N}$, we find strong evidence that the marginal distribution of this quantity can be better fitted by two Gaussian components rather than one: there is a narrow peak at $\chi_{\rm N} \sim 0.15$ and another extended peak at $\chi_{\rm N} \sim 0.47$. We also find that the rapidly spinning systems likely dominate the high-mass end of the population and they evolve with redshift much quicker. These findings bring new challenges to the field binary scenario, and suggest that dynamical process should plays a key role in forming high total mass BBHs., Comment: Submitted on 25 April 2024
- Published
- 2024
16. CoSLight: Co-optimizing Collaborator Selection and Decision-making to Enhance Traffic Signal Control
- Author
-
Ruan, Jingqing, Li, Ziyue, Wei, Hua, Jiang, Haoyuan, Lu, Jiaming, Xiong, Xuantang, Mao, Hangyu, and Zhao, Rui
- Subjects
Computer Science - Multiagent Systems ,Computer Science - Artificial Intelligence - Abstract
Effective multi-intersection collaboration is pivotal for reinforcement-learning-based traffic signal control to alleviate congestion. Existing work mainly chooses neighboring intersections as collaborators. However, quite an amount of congestion, even some wide-range congestion, is caused by non-neighbors failing to collaborate. To address these issues, we propose to separate the collaborator selection as a second policy to be learned, concurrently being updated with the original signal-controlling policy. Specifically, the selection policy in real-time adaptively selects the best teammates according to phase- and intersection-level features. Empirical results on both synthetic and real-world datasets provide robust validation for the superiority of our approach, offering significant improvements over existing state-of-the-art methods. The code is available at https://github.com/bonaldli/CoSLight., Comment: Accepted by KDD 2024
- Published
- 2024
17. X-Light: Cross-City Traffic Signal Control Using Transformer on Transformer as Meta Multi-Agent Reinforcement Learner
- Author
-
Jiang, Haoyuan, Li, Ziyue, Wei, Hua, Xiong, Xuantang, Ruan, Jingqing, Lu, Jiaming, Mao, Hangyu, and Zhao, Rui
- Subjects
Computer Science - Artificial Intelligence - Abstract
The effectiveness of traffic light control has been significantly improved by current reinforcement learning-based approaches via better cooperation among multiple traffic lights. However, a persisting issue remains: how to obtain a multi-agent traffic signal control algorithm with remarkable transferability across diverse cities? In this paper, we propose a Transformer on Transformer (TonT) model for cross-city meta multi-agent traffic signal control, named as X-Light: We input the full Markov Decision Process trajectories, and the Lower Transformer aggregates the states, actions, rewards among the target intersection and its neighbors within a city, and the Upper Transformer learns the general decision trajectories across different cities. This dual-level approach bolsters the model's robust generalization and transferability. Notably, when directly transferring to unseen scenarios, ours surpasses all baseline methods with +7.91% on average, and even +16.3% in some cases, yielding the best results., Comment: Accepted by IJCAI 2024
- Published
- 2024
18. SEVD: Synthetic Event-based Vision Dataset for Ego and Fixed Traffic Perception
- Author
-
Aliminati, Manideep Reddy, Chakravarthi, Bharatesh, Verma, Aayush Atul, Vaghela, Arpitsinh, Wei, Hua, Zhou, Xuesong, and Yang, Yezhou
- Subjects
Computer Science - Computer Vision and Pattern Recognition ,Computer Science - Machine Learning - Abstract
Recently, event-based vision sensors have gained attention for autonomous driving applications, as conventional RGB cameras face limitations in handling challenging dynamic conditions. However, the availability of real-world and synthetic event-based vision datasets remains limited. In response to this gap, we present SEVD, a first-of-its-kind multi-view ego, and fixed perception synthetic event-based dataset using multiple dynamic vision sensors within the CARLA simulator. Data sequences are recorded across diverse lighting (noon, nighttime, twilight) and weather conditions (clear, cloudy, wet, rainy, foggy) with domain shifts (discrete and continuous). SEVD spans urban, suburban, rural, and highway scenes featuring various classes of objects (car, truck, van, bicycle, motorcycle, and pedestrian). Alongside event data, SEVD includes RGB imagery, depth maps, optical flow, semantic, and instance segmentation, facilitating a comprehensive understanding of the scene. Furthermore, we evaluate the dataset using state-of-the-art event-based (RED, RVT) and frame-based (YOLOv8) methods for traffic participant detection tasks and provide baseline benchmarks for assessment. Additionally, we conduct experiments to assess the synthetic event-based dataset's generalization capabilities. The dataset is available at https://eventbasedvision.github.io/SEVD
- Published
- 2024
19. HumanLight: Incentivizing ridesharing via human-centric deep reinforcement learning in traffic signal control
- Author
-
Vlachogiannis, Dimitris M, Wei, Hua, Moura, Scott, and Macfarlane, Jane
- Subjects
Transportation ,Logistics and Supply Chains ,Engineering ,Civil Engineering ,Commerce ,Management ,Tourism and Services ,Sustainable Cities and Communities ,Affordable and Clean Energy ,Person-based traffic signal control ,Decentralized adaptive control ,Deep reinforcement learning ,Ridesharing ,Multimodal traffic environment ,Information and Computing Sciences ,Logistics & Transportation ,Commerce ,management ,tourism and services - Published
- 2024
20. eTraM: Event-based Traffic Monitoring Dataset
- Author
-
Verma, Aayush Atul, Chakravarthi, Bharatesh, Vaghela, Arpitsinh, Wei, Hua, and Yang, Yezhou
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
Event cameras, with their high temporal and dynamic range and minimal memory usage, have found applications in various fields. However, their potential in static traffic monitoring remains largely unexplored. To facilitate this exploration, we present eTraM - a first-of-its-kind, fully event-based traffic monitoring dataset. eTraM offers 10 hr of data from different traffic scenarios in various lighting and weather conditions, providing a comprehensive overview of real-world situations. Providing 2M bounding box annotations, it covers eight distinct classes of traffic participants, ranging from vehicles to pedestrians and micro-mobility. eTraM's utility has been assessed using state-of-the-art methods for traffic participant detection, including RVT, RED, and YOLOv8. We quantitatively evaluate the ability of event-based models to generalize on nighttime and unseen scenes. Our findings substantiate the compelling potential of leveraging event cameras for traffic monitoring, opening new avenues for research and application. eTraM is available at https://eventbasedvision.github.io/eTraM
- Published
- 2024
21. Are Classification Robustness and Explanation Robustness Really Strongly Correlated? An Analysis Through Input Loss Landscape
- Author
-
Chen, Tiejin, Huang, Wenwang, Pang, Linsey, Luo, Dongsheng, and Wei, Hua
- Subjects
Computer Science - Machine Learning ,Computer Science - Computer Vision and Pattern Recognition - Abstract
This paper delves into the critical area of deep learning robustness, challenging the conventional belief that classification robustness and explanation robustness in image classification systems are inherently correlated. Through a novel evaluation approach leveraging clustering for efficient assessment of explanation robustness, we demonstrate that enhancing explanation robustness does not necessarily flatten the input loss landscape with respect to explanation loss - contrary to flattened loss landscapes indicating better classification robustness. To deeply investigate this contradiction, a groundbreaking training method designed to adjust the loss landscape with respect to explanation loss is proposed. Through the new training method, we uncover that although such adjustments can impact the robustness of explanations, they do not have an influence on the robustness of classification. These findings not only challenge the prevailing assumption of a strong correlation between the two forms of robustness but also pave new pathways for understanding relationship between loss landscape and explanation loss.
- Published
- 2024
22. Privacy-preserving Fine-tuning of Large Language Models through Flatness
- Author
-
Chen, Tiejin, Da, Longchao, Zhou, Huixue, Li, Pingzhi, Zhou, Kaixiong, Chen, Tianlong, and Wei, Hua
- Subjects
Computer Science - Artificial Intelligence ,I.2 - Abstract
The privacy concerns associated with the use of Large Language Models (LLMs) have grown recently with the development of LLMs such as ChatGPT. Differential Privacy (DP) techniques are explored in existing work to mitigate their privacy risks at the cost of generalization degradation. Our paper reveals that the flatness of DP-trained models' loss landscape plays an essential role in the trade-off between their privacy and generalization. We further propose a holistic framework to enforce appropriate weight flatness, which substantially improves model generalization with competitive privacy preservation. It innovates from three coarse-to-grained levels, including perturbation-aware min-max optimization on model weights within a layer, flatness-guided sparse prefix-tuning on weights across layers, and weight knowledge distillation between DP \& non-DP weights copies. Comprehensive experiments of both black-box and white-box scenarios are conducted to demonstrate the effectiveness of our proposal in enhancing generalization and maintaining DP characteristics. For instance, on text classification dataset QNLI, DP-Flat achieves similar performance with non-private full fine-tuning but with DP guarantee under privacy budget $\epsilon=3$, and even better performance given higher privacy budgets. Codes are provided in the supplement., Comment: Accepted to ICLR 2024 SeT LLM Workshop
- Published
- 2024
23. Teaching MLP More Graph Information: A Three-stage Multitask Knowledge Distillation Framework
- Author
-
Li, Junxian, Shi, Bin, Cui, Erfei, Wei, Hua, and Zheng, Qinghua
- Subjects
Computer Science - Machine Learning ,Computer Science - Artificial Intelligence - Abstract
We study the challenging problem for inference tasks on large-scale graph datasets of Graph Neural Networks: huge time and memory consumption, and try to overcome it by reducing reliance on graph structure. Even though distilling graph knowledge to student MLP is an excellent idea, it faces two major problems of positional information loss and low generalization. To solve the problems, we propose a new three-stage multitask distillation framework. In detail, we use Positional Encoding to capture positional information. Also, we introduce Neural Heat Kernels responsible for graph data processing in GNN and utilize hidden layer outputs matching for better performance of student MLP's hidden layers. To the best of our knowledge, it is the first work to include hidden layer distillation for student MLP on graphs and to combine graph Positional Encoding with MLP. We test its performance and robustness with several settings and draw the conclusion that our work can outperform well with good stability., Comment: 20 pages, with Appendix
- Published
- 2024
24. Three-dimensional atomic interface between metal and oxide in Zr-ZrO2 nanoparticles
- Author
-
Zhang, Yao, Li, Zezhou, Tong, Xing, Xie, Zhiheng, Huang, Siwei, Zhang, Yue-E, Ke, Hai-Bo, Wang, Wei-Hua, and Zhou, Jihan
- Subjects
Condensed Matter - Materials Science - Abstract
Metal-oxide interfaces with poor coherency have unique properties comparing to the bulk materials and offer broad applications in the fields of heterogeneous catalysis, battery, and electronics. However, current understanding of the three-dimensional (3D) atomic metal-oxide interfaces remains limited because of their inherent structural complexity and limitations of conventional two-dimensional imaging techniques. Here, we determine the 3D atomic structure of metal-oxide interfaces in zirconium-zirconia nanoparticles using atomic-resolution electron tomography. We quantitatively analyze the atomic concentration and the degree of oxidation, and find the coherency and translational symmetry of the interfaces are broken. Moreover, we observe porous structures such as Zr vacancies and nano-pores and investigate their distribution. Our findings provide a clear 3D atomic picture of metal-oxide interface with direct experimental evidence. We anticipate this work could encourage future studies on fundamental problems of oxides such as interfacial structures in semiconductor and atomic motion during oxidation process., Comment: 35 pages, 4 main figures, 17 Supplementary figures
- Published
- 2024
25. CityFlowER: An Efficient and Realistic Traffic Simulator with Embedded Machine Learning Models
- Author
-
Da, Longchao, Chu, Chen, Zhang, Weinan, and Wei, Hua
- Subjects
Computer Science - Multiagent Systems ,Computer Science - Machine Learning ,G.3 - Abstract
Traffic simulation is an essential tool for transportation infrastructure planning, intelligent traffic control policy learning, and traffic flow analysis. Its effectiveness relies heavily on the realism of the simulators used. Traditional traffic simulators, such as SUMO and CityFlow, are often limited by their reliance on rule-based models with hyperparameters that oversimplify driving behaviors, resulting in unrealistic simulations. To enhance realism, some simulators have provided Application Programming Interfaces (APIs) to interact with Machine Learning (ML) models, which learn from observed data and offer more sophisticated driving behavior models. However, this approach faces challenges in scalability and time efficiency as vehicle numbers increase. Addressing these limitations, we introduce CityFlowER, an advancement over the existing CityFlow simulator, designed for efficient and realistic city-wide traffic simulation. CityFlowER innovatively pre-embeds ML models within the simulator, eliminating the need for external API interactions and enabling faster data computation. This approach allows for a blend of rule-based and ML behavior models for individual vehicles, offering unparalleled flexibility and efficiency, particularly in large-scale simulations. We provide detailed comparisons with existing simulators, implementation insights, and comprehensive experiments to demonstrate CityFlowER's superiority in terms of realism, efficiency, and adaptability., Comment: 4 pages, 4 figures
- Published
- 2024
26. A Bernoulli-barycentric rational matrix collocation method with preconditioning for a class of evolutionary PDEs
- Author
-
Luo, Wei-Hua, Gu, Xian-Ming, Carpentieri, Bruno, and Guo, Jun
- Subjects
Mathematics - Numerical Analysis ,65M70, 65Y05, 65D25 - Abstract
We propose a Bernoulli-barycentric rational matrix collocation method for two-dimensional evolutionary partial differential equations (PDEs) with variable coefficients that combines Bernoulli polynomials with barycentric rational interpolations in time and space, respectively. The theoretical accuracy $O\left((2\pi)^{-N}+h_x^{d_x-1}+h_y^{d_y-1}\right)$ of our numerical scheme is proven, where $N$ is the number of basis functions in time, $h_x$ and $h_y$ are the grid sizes in the $x$, $y$-directions, respectively, and $0\leq d_x\leq \frac{b-a}{h_x},~0\leq d_y\leq\frac{d-c}{h_y}$. For the efficient solution of the relevant linear system arising from the discretizations, we introduce a class of dimension expanded preconditioners that take the advantage of structural properties of the coefficient matrices, and we present a theoretical analysis of eigenvalue distributions of the preconditioned matrices. The effectiveness of our proposed method and preconditioners are studied for solving some real-world examples represented by the heat conduction equation, the advection-diffusion equation, the wave equation and telegraph equations., Comment: 23 pages, 6 figures, 9 tables (update some contexts)
- Published
- 2024
27. Generating In-Distribution Proxy Graphs for Explaining Graph Neural Networks
- Author
-
Chen, Zhuomin, Zhang, Jiaxing, Ni, Jingchao, Li, Xiaoting, Bian, Yuchen, Islam, Md Mezbahul, Mondal, Ananda Mohan, Wei, Hua, and Luo, Dongsheng
- Subjects
Computer Science - Machine Learning - Abstract
Graph Neural Networks (GNNs) have become a building block in graph data processing, with wide applications in critical domains. The growing needs to deploy GNNs in high-stakes applications necessitate explainability for users in the decision-making processes. A popular paradigm for the explainability of GNNs is to identify explainable subgraphs by comparing their labels with the ones of original graphs. This task is challenging due to the substantial distributional shift from the original graphs in the training set to the set of explainable subgraphs, which prevents accurate prediction of labels with the subgraphs. To address it, in this paper, we propose a novel method that generates proxy graphs for explainable subgraphs that are in the distribution of training data. We introduce a parametric method that employs graph generators to produce proxy graphs. A new training objective based on information theory is designed to ensure that proxy graphs not only adhere to the distribution of training data but also preserve explanatory factors. Such generated proxy graphs can be reliably used to approximate the predictions of the labels of explainable subgraphs. Empirical evaluations across various datasets demonstrate our method achieves more accurate explanations for GNNs., Comment: Accepted to International Conference on Machine Learning (ICML 2024)
- Published
- 2024
28. When eBPF Meets Machine Learning: On-the-fly OS Kernel Compartmentalization
- Author
-
Wang, Zicheng, Chen, Tiejin, Dai, Qinrun, Chen, Yueqi, Wei, Hua, and Zeng, Qingkai
- Subjects
Computer Science - Operating Systems ,Computer Science - Cryptography and Security ,Computer Science - Machine Learning - Abstract
Compartmentalization effectively prevents initial corruption from turning into a successful attack. This paper presents O2C, a pioneering system designed to enforce OS kernel compartmentalization on the fly. It not only provides immediate remediation for sudden threats but also maintains consistent system availability through the enforcement process. O2C is empowered by the newest advancements of the eBPF ecosystem which allows to instrument eBPF programs that perform enforcement actions into the kernel at runtime. O2C takes the lead in embedding a machine learning model into eBPF programs, addressing unique challenges in on-the-fly compartmentalization. Our comprehensive evaluation shows that O2C effectively confines damage within the compartment. Further, we validate that decision tree is optimally suited for O2C owing to its advantages in processing tabular data, its explainable nature, and its compliance with the eBPF ecosystem. Last but not least, O2C is lightweight, showing negligible overhead and excellent sacalability system-wide.
- Published
- 2024
29. Uncertainty Regularized Evidential Regression
- Author
-
Ye, Kai, Chen, Tiejin, Wei, Hua, and Zhan, Liang
- Subjects
Computer Science - Machine Learning ,Computer Science - Artificial Intelligence - Abstract
The Evidential Regression Network (ERN) represents a novel approach that integrates deep learning with Dempster-Shafer's theory to predict a target and quantify the associated uncertainty. Guided by the underlying theory, specific activation functions must be employed to enforce non-negative values, which is a constraint that compromises model performance by limiting its ability to learn from all samples. This paper provides a theoretical analysis of this limitation and introduces an improvement to overcome it. Initially, we define the region where the models can't effectively learn from the samples. Following this, we thoroughly analyze the ERN and investigate this constraint. Leveraging the insights from our analysis, we address the limitation by introducing a novel regularization term that empowers the ERN to learn from the whole training set. Our extensive experiments substantiate our theoretical findings and demonstrate the effectiveness of the proposed solution., Comment: Accepted to AAAI 2024 main track
- Published
- 2024
30. Real-time monitoring of intracellular biochemical response in locally stretched single cell by a nanosensor
- Author
-
Jin, Xue-Ke, Jin, Kai-Qi, Yang, Xiao-Ke, Wen, Ming-Yong, Liu, Yan-Ling, and Huang, Wei-Hua
- Published
- 2024
- Full Text
- View/download PDF
31. Open-TI: Open Traffic Intelligence with Augmented Language Model
- Author
-
Da, Longchao, Liou, Kuanru, Chen, Tiejin, Zhou, Xuesong, Luo, Xiangyong, Yang, Yezhou, and Wei, Hua
- Subjects
Computer Science - Artificial Intelligence ,I.2.1 ,I.2.7 ,I.2.8 - Abstract
Transportation has greatly benefited the cities' development in the modern civilization process. Intelligent transportation, leveraging advanced computer algorithms, could further increase people's daily commuting efficiency. However, intelligent transportation, as a cross-discipline, often requires practitioners to comprehend complicated algorithms and obscure neural networks, bringing a challenge for the advanced techniques to be trusted and deployed in practical industries. Recognizing the expressiveness of the pre-trained large language models, especially the potential of being augmented with abilities to understand and execute intricate commands, we introduce Open-TI. Serving as a bridge to mitigate the industry-academic gap, Open-TI is an innovative model targeting the goal of Turing Indistinguishable Traffic Intelligence, it is augmented with the capability to harness external traffic analysis packages based on existing conversations. Marking its distinction, Open-TI is the first method capable of conducting exhaustive traffic analysis from scratch - spanning from map data acquisition to the eventual execution in complex simulations. Besides, Open-TI is able to conduct task-specific embodiment like training and adapting the traffic signal control policies (TSC), explore demand optimizations, etc. Furthermore, we explored the viability of LLMs directly serving as control agents, by understanding the expected intentions from Open-TI, we designed an agent-to-agent communication mode to support Open-TI conveying messages to ChatZero (control agent), and then the control agent would choose from the action space to proceed the execution. We eventually provide the formal implementation structure, and the open-ended design invites further community-driven enhancements., Comment: 22 pages main content, 8 pages appendix
- Published
- 2023
32. Probabilistic Offline Policy Ranking with Approximate Bayesian Computation
- Author
-
Da, Longchao, Jenkins, Porter, Schwantes, Trevor, Dotson, Jeffrey, and Wei, Hua
- Subjects
Computer Science - Machine Learning ,Computer Science - Artificial Intelligence ,I.2.6 - Abstract
In practice, it is essential to compare and rank candidate policies offline before real-world deployment for safety and reliability. Prior work seeks to solve this offline policy ranking (OPR) problem through value-based methods, such as Off-policy evaluation (OPE). However, they fail to analyze special cases performance (e.g., worst or best cases), due to the lack of holistic characterization of policies performance. It is even more difficult to estimate precise policy values when the reward is not fully accessible under sparse settings. In this paper, we present Probabilistic Offline Policy Ranking (POPR), a framework to address OPR problems by leveraging expert data to characterize the probability of a candidate policy behaving like experts, and approximating its entire performance posterior distribution to help with ranking. POPR does not rely on value estimation, and the derived performance posterior can be used to distinguish candidates in worst, best, and average-cases. To estimate the posterior, we propose POPR-EABC, an Energy-based Approximate Bayesian Computation (ABC) method conducting likelihood-free inference. POPR-EABC reduces the heuristic nature of ABC by a smooth energy function, and improves the sampling efficiency by a pseudo-likelihood. We empirically demonstrate that POPR-EABC is adequate for evaluating policies in both discrete and continuous action spaces across various experiment environments, and facilitates probabilistic comparisons of candidate policies before deployment., Comment: 19 pages with 7 pages main paper, 10 pages appendix. Accepted to AAAI 2024 main track
- Published
- 2023
33. Characteristics of gamma-ray burst afterglows in the context of non-axisymmetric structured jets
- Author
-
Li, Jin-Da, Gao, He, Ai, Shunke, and Lei, Wei-Hua
- Subjects
Astrophysics - High Energy Astrophysical Phenomena - Abstract
As the most energetic explosions in the Universe, gamma-ray bursts (GRBs) are commonly believed to be generated by relativistic jets. Recent observational evidence suggests that the jets producing GRBs are likely to have a structured nature. Some studies have suggested that non-axisymmetric structured jets may be formed through internal non-uniform magnetic dissipation processes or the precession of the central engine. In this study, we analyze the potential characteristics of GRB afterglows within the framework of non-axisymmetric structured jets. We simplify the profile of the asymmetric jet as a step function of the azimuth angle, dividing the entire jet into individual elements. By considering specific cases, we demonstrate that the velocity, energy, and line-of-sight direction of each jet element can greatly affect the behaviour of the overall light curve. The radiative contributions from multiple elements may lead to the appearance of multiple distinct peaks or plateaus in the light curve. Furthermore, fluctuations in the rising and declining segments of each peak can be observed. These findings establish a theoretical foundation for future investigations into the structural characteristics of GRBs by leveraging GRB afterglow data., Comment: Monthly Notices of the Royal Astronomical Society, Volume 525, Issue 4, November 2023, Pages 6285-6294
- Published
- 2023
34. Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks
- Author
-
Zheng, Xu, Shirani, Farhad, Wang, Tianchun, Cheng, Wei, Chen, Zhuomin, Chen, Haifeng, Wei, Hua, and Luo, Dongsheng
- Subjects
Computer Science - Machine Learning - Abstract
Graph Neural Networks (GNNs) are neural models that leverage the dependency structure in graphical data via message passing among the graph nodes. GNNs have emerged as pivotal architectures in analyzing graph-structured data, and their expansive application in sensitive domains requires a comprehensive understanding of their decision-making processes -- necessitating a framework for GNN explainability. An explanation function for GNNs takes a pre-trained GNN along with a graph as input, to produce a `sufficient statistic' subgraph with respect to the graph label. A main challenge in studying GNN explainability is to provide fidelity measures that evaluate the performance of these explanation functions. This paper studies this foundational challenge, spotlighting the inherent limitations of prevailing fidelity metrics, including $Fid_+$, $Fid_-$, and $Fid_\Delta$. Specifically, a formal, information-theoretic definition of explainability is introduced and it is shown that existing metrics often fail to align with this definition across various statistical scenarios. The reason is due to potential distribution shifts when subgraphs are removed in computing these fidelity measures. Subsequently, a robust class of fidelity measures are introduced, and it is shown analytically that they are resilient to distribution shift issues and are applicable in a wide range of scenarios. Extensive empirical analysis on both synthetic and real datasets are provided to illustrate that the proposed metrics are more coherent with gold standard metrics. The source code is available at https://trustai4s-lab.github.io/fidelity., Comment: Accepted by International Conference on Learning Representations (ICLR 2024); 26 Pages, 12 figures
- Published
- 2023
35. Open-ti: open traffic intelligence with augmented language model
- Author
-
Da, Longchao, Liou, Kuanru, Chen, Tiejin, Zhou, Xuesong, Luo, Xiangyong, Yang, Yezhou, and Wei, Hua
- Published
- 2024
- Full Text
- View/download PDF
36. AT2022cmc: a Tidal Disruption Event with Two-component Jet in a Bondi-profile Circumnuclear Medium
- Author
-
Zhou, Chang, Zhu, Zi-Pei, Lei, Wei-Hua, Fu, Shao-Yu, Xie, Wei, and Xu, Dong
- Subjects
Astrophysics - High Energy Astrophysical Phenomena - Abstract
A supermassive black hole can launch a relativistic jet when it violently disrupts a star that passes too close. Such jetted tidal disruption events (TDEs) are rare and unique tools to investigate quiescent supermassive black holes, jet physics, and circumnuclear environment at high redshift. The newly discovered TDE AT2022cmc ($z\sim 1.193$) providing rich multi-band (X-ray, UV, optical, sub-millimeter, and radio) data, has been interpreted as the fourth on-axis jetted TDE. In this work, we constrain the circumnuclear medium (CNM) density profile with both closure relation (CR) test and detailed forward shock model fit with Markov chain Monte Carlo (MCMC) approach to the multi-band (optical, sub-millimeter, and radio) data of AT2022cmc.We find that the CNM density profile of AT2022cmc is $n\propto R^{-k}$ with $k \sim 1.68$, implying a Bondi accretion in history. Furthermore, our model fit result suggests a two-component jet in AT2022cmc, indicating a similar jet physics to well-studied jetted TDE Sw J1644+57., Comment: accepted in ApJ
- Published
- 2023
37. Uncertainty-aware Traffic Prediction under Missing Data
- Author
-
Mei, Hao, Li, Junxian, Liang, Zhiming, Zheng, Guanjie, Shi, Bin, and Wei, Hua
- Subjects
Computer Science - Machine Learning ,Computer Science - Artificial Intelligence - Abstract
Traffic prediction is a crucial topic because of its broad scope of applications in the transportation domain. Recently, various studies have achieved promising results. However, most studies assume the prediction locations have complete or at least partial historical records and cannot be extended to non-historical recorded locations. In real-life scenarios, the deployment of sensors could be limited due to budget limitations and installation availability, which makes most current models not applicable. Though few pieces of literature tried to impute traffic states at the missing locations, these methods need the data simultaneously observed at the locations with sensors, making them not applicable to prediction tasks. Another drawback is the lack of measurement of uncertainty in prediction, making prior works unsuitable for risk-sensitive tasks or involving decision-making. To fill the gap, inspired by the previous inductive graph neural network, this work proposed an uncertainty-aware framework with the ability to 1) extend prediction to missing locations with no historical records and significantly extend spatial coverage of prediction locations while reducing deployment of sensors and 2) generate probabilistic prediction with uncertainty quantification to help the management of risk and decision making in the down-stream tasks. Through extensive experiments on real-life datasets, the result shows our method achieved promising results on prediction tasks, and the uncertainty quantification gives consistent results which highly correlated with the locations with and without historical data. We also show that our model could help support sensor deployment tasks in the transportation field to achieve higher accuracy with a limited sensor deployment budget., Comment: 11 pages, 3 figures, a short version of this paper is accepted by ICDM 2023
- Published
- 2023
- Full Text
- View/download PDF
38. Prompt to Transfer: Sim-to-Real Transfer for Traffic Signal Control with Prompt Learning
- Author
-
Da, Longchao, Gao, Minquan, Mei, Hao, and Wei, Hua
- Subjects
Computer Science - Artificial Intelligence ,H.4.0 - Abstract
Numerous solutions are proposed for the Traffic Signal Control (TSC) tasks aiming to provide efficient transportation and mitigate congestion waste. In recent, promising results have been attained by Reinforcement Learning (RL) methods through trial and error in simulators, bringing confidence in solving cities' congestion headaches. However, there still exist performance gaps when simulator-trained policies are deployed to the real world. This issue is mainly introduced by the system dynamic difference between the training simulator and the real-world environments. The Large Language Models (LLMs) are trained on mass knowledge and proved to be equipped with astonishing inference abilities. In this work, we leverage LLMs to understand and profile the system dynamics by a prompt-based grounded action transformation. Accepting the cloze prompt template, and then filling in the answer based on accessible context, the pre-trained LLM's inference ability is exploited and applied to understand how weather conditions, traffic states, and road types influence traffic dynamics, being aware of this, the policies' action is taken and grounded based on realistic dynamics, thus help the agent learn a more realistic policy. We conduct experiments using DQN to show the effectiveness of the proposed PromptGAT's ability in mitigating the performance gap from simulation to reality (sim-to-real)., Comment: 9 pages, 7 figures. Accepted to AAAI 2024
- Published
- 2023
39. Polarization Signature of Companion-Fed Supernovae Arising from BH-NS/BH Progenitor Systems
- Author
-
Wen, Xudong, Gao, He, Ai, Shunke, liu, liangduan, Zhu, Jin-Ping, and Lei, Wei-Hua
- Subjects
Astrophysics - High Energy Astrophysical Phenomena ,14J60 (Primary) 14F05, 14J26 (Secondary) ,F.2.2 ,I.2.7 - Abstract
The formation of black hole-neutron star (BH-NS) or BH-BH systems may be accompanied with special supernova (SN) signals, due to the accretion feedback from the companion BH. The additional heating, which is mainly attributed to the Blandford-Payne mechanism, would disrupt the isotropic nature of the luminosity distribution on the surface of the SN ejecta, leading to the appearance of polarization. Here we develop a three dimensional (3D) Monte Carlo polarization simulation code (MCPSC) to conduct simulations for these special SNe. We find that the maximum polarization level of approximately \sim 2 occurs at the peak time of SN emission in the "close-binary" scenario, while in the "faraway-binary" case, maximum polarization (i.e. \sim 0.7) is observed at a considerably later time than the peak of the SN. The magnitude of polarization is dependent on the degree of unevenness in the luminosity distribution and the angle between the line of sight and the equatorial direction. When considering the geometric distortion of supernova ejecta at the same time, the magnitude of polarization may either increase (for a oblate ellipsoidal shape) or decrease (for a prolate ellipsoidal shape). The polarization signatures represent a promising auxiliary instrument to facilitate the identification of the companion-fed SNe. Moreover, by comparing the event rate of these special SNe with the event rate density of LIGO-Virgo detected BH-NS/BH systems could further help to distinguish the BH-NS/BH formation channel., Comment: 15 pages, 13 figures,accepted for publication in APJ
- Published
- 2023
40. Safety in Traffic Management Systems: A Comprehensive Survey
- Author
-
Du, Wenlu, Dash, Ankan, Li, Jing, Wei, Hua, and Wang, Guiling
- Subjects
Electrical Engineering and Systems Science - Systems and Control ,Computer Science - Artificial Intelligence ,Computer Science - Machine Learning - Abstract
Traffic management systems play a vital role in ensuring safe and efficient transportation on roads. However, the use of advanced technologies in traffic management systems has introduced new safety challenges. Therefore, it is important to ensure the safety of these systems to prevent accidents and minimize their impact on road users. In this survey, we provide a comprehensive review of the literature on safety in traffic management systems. Specifically, we discuss the different safety issues that arise in traffic management systems, the current state of research on safety in these systems, and the techniques and methods proposed to ensure the safety of these systems. We also identify the limitations of the existing research and suggest future research directions., Comment: Accepted by MDPI Designs journal, the Special Issue Design and Application of Intelligent Transportation Systems. 30 pages, 6 figures, published on 10 August 2023
- Published
- 2023
- Full Text
- View/download PDF
41. Uncertainty-aware Grounded Action Transformation towards Sim-to-Real Transfer for Traffic Signal Control
- Author
-
Da, Longchao, Mei, Hao, Sharma, Romir, and Wei, Hua
- Subjects
Computer Science - Machine Learning ,Computer Science - Artificial Intelligence ,H.4.0 - Abstract
Traffic signal control (TSC) is a complex and important task that affects the daily lives of millions of people. Reinforcement Learning (RL) has shown promising results in optimizing traffic signal control, but current RL-based TSC methods are mainly trained in simulation and suffer from the performance gap between simulation and the real world. In this paper, we propose a simulation-to-real-world (sim-to-real) transfer approach called UGAT, which transfers a learned policy trained from a simulated environment to a real-world environment by dynamically transforming actions in the simulation with uncertainty to mitigate the domain gap of transition dynamics. We evaluate our method on a simulated traffic environment and show that it significantly improves the performance of the transferred RL policy in the real world., Comment: 6 pages, 3 figures. This paper is accepted by IEEE-CDC 2023
- Published
- 2023
42. Enhanced photo-excitation and angular-momentum imprint of gray excitons in WSe$_{2}$ monolayers by spin-orbit-coupled vector vortex beams
- Author
-
Sanchez, Oscar Javier Gomez, Peng, Guan-Hao, Li, Wei-Hua, Shih, Ching-Hung, Chien, Chao-Hsin, and Cheng, Shun-Jen
- Subjects
Condensed Matter - Mesoscale and Nanoscale Physics - Abstract
A light beam can be spatially structured in the complex amplitude to possess orbital angular momentum (OAM), which introduces a new degree of freedom alongside the intrinsic spin angular momentum (SAM) associated with circular polarization. Moreover, super-imposing two twisted lights with distinct SAM and OAM produces a vector vortex beam (VVB) in non-separable states where not only complex amplitude but also polarization are spatially structured and entangled with each other. In addition to the non-separability, the SAM and OAM in a VVB are intrinsically coupled by the optical spin-orbit interaction and constitute the profound spin-orbit physics in photonics. In this work, we present a comprehensive theoretical investigation, implemented on the first-principles base, of the intriguing light-matter interaction between VVBs and WSe$_{2}$ monolayers (WSe$_{2}$-MLs), one of the best-known and promising two-dimensional (2D) materials in optoelectronics dictated by excitons, encompassing bright exciton (BX) as well as various dark excitons (DXs). One of the key findings of our study is the substantial enhancement of the photo-excitation of gray excitons (GXs), a type of spin-forbidden dark exciton, in a WSe$_2$-ML through the utilization of a twisted light that possesses a longitudinal field associated with the optical spin-orbit interaction. Our research demonstrates that a spin-orbit-coupled VVB surprisingly allows for the imprinting of the carried optical information onto gray excitons in 2D materials, which is robust against the decoherence mechanisms in materials. This observation suggests a promising method for deciphering the transferred angular momentum from structured lights to excitons.
- Published
- 2023
43. RegExplainer: Generating Explanations for Graph Neural Networks in Regression Task
- Author
-
Zhang, Jiaxing, Chen, Zhuomin, Mei, Hao, Luo, Dongsheng, and Wei, Hua
- Subjects
Computer Science - Machine Learning ,Computer Science - Artificial Intelligence - Abstract
Graph regression is a fundamental task and has received increasing attention in a wide range of graph learning tasks. However, the inference process is often not interpretable. Most existing explanation techniques are limited to understanding GNN behaviors in classification tasks. In this work, we seek an explanation to interpret the graph regression models (XAIG-R). We show that existing methods overlook the distribution shifting and continuously ordered decision boundary, which hinders them away from being applied in the regression tasks. To address these challenges, we propose a novel objective based on the information bottleneck theory and introduce a new mix-up framework, which could support various GNNs in a model-agnostic manner. We further present a contrastive learning strategy to tackle the continuously ordered labels in regression task. To empirically verify the effectiveness of the proposed method, we introduce three benchmark datasets and a real-life dataset for evaluation. Extensive experiments show the effectiveness of the proposed method in interpreting GNN models in regression tasks.
- Published
- 2023
44. MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentation
- Author
-
Zhang, Jiaxing, Luo, Dongsheng, and Wei, Hua
- Subjects
Computer Science - Machine Learning ,Computer Science - Artificial Intelligence - Abstract
Graph Neural Networks (GNNs) have received increasing attention due to their ability to learn from graph-structured data. However, their predictions are often not interpretable. Post-hoc instance-level explanation methods have been proposed to understand GNN predictions. These methods seek to discover substructures that explain the prediction behavior of a trained GNN. In this paper, we shed light on the existence of the distribution shifting issue in existing methods, which affects explanation quality, particularly in applications on real-life datasets with tight decision boundaries. To address this issue, we introduce a generalized Graph Information Bottleneck (GIB) form that includes a label-independent graph variable, which is equivalent to the vanilla GIB. Driven by the generalized GIB, we propose a graph mixup method, MixupExplainer, with a theoretical guarantee to resolve the distribution shifting issue. We conduct extensive experiments on both synthetic and real-world datasets to validate the effectiveness of our proposed mixup approach over existing approaches. We also provide a detailed analysis of how our proposed approach alleviates the distribution shifting issue.
- Published
- 2023
- Full Text
- View/download PDF
45. Three-dimensional atomic insights into the metal-oxide interface in Zr-ZrO2 nanoparticles
- Author
-
Yao Zhang, Zezhou Li, Xing Tong, Zhiheng Xie, Siwei Huang, Yue-E Zhang, Hai-Bo Ke, Wei-Hua Wang, and Jihan Zhou
- Subjects
Science - Abstract
Abstract Metal-oxide interfaces with poor coherency have specific properties comparing to bulk materials and offer broad applications in heterogeneous catalysis, battery, and electronics. However, current understanding of the three-dimensional (3D) atomic metal-oxide interfaces remains limited because of their inherent structural complexity and the limitations of conventional two-dimensional imaging techniques. Here, we determine the 3D atomic structure of metal-oxide interfaces in zirconium-zirconia nanoparticles using atomic-resolution electron tomography. We quantitatively analyze the atomic concentration and the degree of oxidation, and find the coherency and translational symmetry of the interfaces are broken. Atoms at the interface have low structural ordering, low coordination, and elongated bond length. Moreover, we observe porous structures such as Zr vacancies and nano-pores, and investigate their distribution. Our findings provide a clear 3D atomic picture of metal-oxide interface with direct experimental evidence. We anticipate this work could encourage future studies on fundamental problems of oxides, such as interfacial structures in semiconductor and atomic motion during oxidation process.
- Published
- 2024
- Full Text
- View/download PDF
46. Integrated analysis of facial microbiome and skin physio-optical properties unveils cutotype-dependent aging effects
- Author
-
Chuqing Sun, Guoru Hu, Liwen Yi, Wei Ge, Qingyu Yang, Xiangliang Yang, Yifan He, Zhi Liu, and Wei-Hua Chen
- Subjects
Facial microbiome ,Cutotype ,Metagenome-assembled genomes ,Aging ,Lifestyle ,Microbial ecology ,QR100-130 - Abstract
Abstract Background Our facial skin hosts millions of microorganisms, primarily bacteria, crucial for skin health by maintaining the physical barrier, modulating immune response, and metabolizing bioactive materials. Aging significantly influences the composition and function of the facial microbiome, impacting skin immunity, hydration, and inflammation, highlighting potential avenues for interventions targeting aging-related facial microbes amidst changes in skin physiological properties. Results We conducted a multi-center and deep sequencing survey to investigate the intricate interplay of aging, skin physio-optical conditions, and facial microbiome. Leveraging a newly-generated dataset of 2737 species-level metagenome-assembled genomes (MAGs), our integrative analysis highlighted aging as the primary driver, influencing both facial microbiome composition and key skin characteristics, including moisture, sebum production, gloss, pH, elasticity, and sensitivity. Further mediation analysis revealed that skin characteristics significantly impacted the microbiome, mostly as a mediator of aging. Utilizing this dataset, we uncovered two consistent cutotypes across sampling cities and identified aging-related microbial MAGs. Additionally, a Facial Aging Index (FAI) was formulated based on the microbiome, uncovering the cutotype-dependent effects of unhealthy lifestyles on skin aging. Finally, we distinguished aging related microbial pathways influenced by lifestyles with cutotype-dependent effect. Conclusions Together, our findings emphasize aging’s central role in facial microbiome dynamics, and support personalized skin microbiome interventions by targeting lifestyle, skin properties, and aging-related microbial factors. Video Abstract
- Published
- 2024
- Full Text
- View/download PDF
47. Identify truly high-risk TP53-mutated diffuse large B cell lymphoma patients and explore the underlying biological mechanisms
- Author
-
Kai-Xin Du, Yi-Fan Wu, Wei Hua, Zi-Wen Duan, Rui Gao, Jun-Heng Liang, Yue Li, Hua Yin, Jia-Zhu Wu, Hao-Rui Shen, Li Wang, Yang Shao, Jian-Yong Li, Jin-Hua Liang, and Wei Xu
- Subjects
Diffuse large B cell lymphoma ,TP53 ,Missense mutation ,Prognostic index ,Biological mechanism ,Medicine ,Cytology ,QH573-671 - Abstract
Abstract TP53 mutation (TP53-mut) correlates with inferior survival in many cancers, whereas its prognostic role in diffuse large B-cell lymphoma (DLBCL) is still in controversy. Therefore, more precise risk stratification needs to be further explored for TP53-mut DLBCL patients. A set of 2637 DLBCL cases from multiple cohorts, was enrolled in our analysis. Among the 2637 DLBCL patients, 14.0% patients (370/2637) had TP53-mut. Since missense mutations account for the vast majority of TP53-mut DLBCL patients, and most non-missense mutations affect the function of the P53 protein, leading to worse survival rates, we distinguished patients with missense mutations. A TP53 missense mutation risk model was constructed based on a 150-combination machine learning computational framework, demonstrating excellent performance in predicting prognosis. Further analysis revealed that patients with high-risk missense mutations are significantly associated with early progression and exhibit dysregulation of multiple immune and metabolic pathways at the transcriptional level. Additionally, the high-risk group showed an absolutely suppressed immune microenvironment. To stratify the entire cohort of TP53-mut DLBCL, we combined clinical characteristics and ultimately constructed the TP53 Prognostic Index (TP53PI) model. In summary, we identified the truly high-risk TP53-mut DLBCL patients and explained this difference at the mutation and transcriptional levels.
- Published
- 2024
- Full Text
- View/download PDF
48. Nocardamine mitigates cellular dysfunction induced by oxidative stress in periodontal ligament stem cells
- Author
-
Hai-Peng He, Mei-Zhen Zhao, Wei-Hua Jiao, Zhi-Qiang Liu, Xian-Hai Zeng, Quan-Li Li, Tian-Yong Hu, and Bao-Hui Cheng
- Subjects
Periodontal destruction ,Periodontal ligament stem cells ,Oxidative stress ,Nocardamine ,Osteogenic differentiation ,Medicine (General) ,R5-920 ,Biochemistry ,QD415-436 - Abstract
Abstract Background The role of periodontal ligament stem cells (PDLSCs) in repairing periodontal destruction is crucial, but their functions can be impaired by excessive oxidative stress (OS). Nocardamine (NOCA), a cyclic siderophore, has been shown to possess anti-cancer and anti-bacterial properties. This study aimed to investigate the protective mechanisms of NOCA against OS-induced cellular dysfunction in PDLSCs. Methods The cytotoxicity of NOCA on PDLSCs was assessed using a CCK-8 assay. PDLSCs were then treated with hydrogen peroxide (H2O2) to induce OS. ROS levels, cell viability, and antioxidant factor expression were analyzed using relevant kits after treatment. Small molecule inhibitors U0126 and XAV-939 were employed to block ERK signaling and Wnt pathways respectively. Osteogenic differentiation was assessed using alkaline phosphatase (ALP) activity staining and Alizarin Red S (ARS) staining of mineralized nodules. Expression levels of osteogenic gene markers and ERK pathway were determined via real-time quantitative polymerase chain reaction (RT-qPCR) or western blot (WB) analysis. β-catenin nuclear localization was examined by western blotting and confocal microscopy. Results NOCA exhibited no significant cytotoxicity at concentrations below 20 µM and effectively inhibited H2O2-induced OS in PDLSCs. NOCA also restored ALP activity, mineralized nodule formation, and the expression of osteogenic markers in H2O2-stimulated PDLSCs. Mechanistically, NOCA increased p-ERK level and promoted β-catenin translocation into the nucleus; however, blocking ERK pathway disrupted the osteogenic protection provided by NOCA and impaired its ability to induce β-catenin nuclear translocation under OS conditions in PDLSCs. Conclusions NOCA protected PDLSCs against H2O2-induced OS and effectively restored impaired osteogenic differentiation in PDLSCs by modulating the ERK/Wnt signaling pathway.
- Published
- 2024
- Full Text
- View/download PDF
49. The triglyceride-glucose index is a predictor of major adverse cardiovascular events in patients with coronary artery disease and psoriasis: a retrospective cohort study
- Author
-
Bingqi Fu, Yan Zeng, Man Wang, Lin Zhao, Lin Sun, Tianjie Wang, Junle Dong, Weixian Yang, and Wei Hua
- Subjects
Triglyceride-glucose index ,Coronary artery disease ,Psoriasis ,MACE ,Nutritional diseases. Deficiency diseases ,RC620-627 - Abstract
Abstract Background The association between the triglyceride-glucose (TyG) index and clinical outcomes in patients with both coronary artery disease (CAD) and psoriasis is unclear. This study investigated the association between the TyG index and major adverse cardiovascular events (MACE) in patients with both CAD and psoriasis. Methods This retrospective cohort study included patients diagnosed with both CAD and psoriasis who underwent coronary angiography at the Fuwai Hospital, Beijing, China, between January 2017 and May 2022. The study endpoint was the occurrence of MACE or end of follow-up time. Multivariate Cox proportional analysis and restricted cubic splines (RCS) were used to determine the association between the TyG index and MACE. Receiver operating characteristic (ROC) curves were used to determine the optimal threshold value of the TyG index for predicting MACE. Results This study enrolled 293 patients with both CAD and psoriasis, including 258 (88.1%) males with a mean age of 58.89 ± 9.61 years. Patients were divided into four groups based on the TyG quartiles: Q1 (N = 74), Q2 (N = 73), Q3 (N = 73), and Q4 (N = 73). After adjusting for the potential confounders, the TyG index was independently associated with MACE, both as a continuous variable (HR = 1.53, 95% CI = 1.03–2.28, P = 0.035) and as a categorical variable (Q1: reference; Q2: HR = 1.85, 95% CI = 0.88–3.87, P = 0.105; Q3: HR = 2.39, 95% CI = 1.14-5.00, P = 0.021; Q4: HR = 2.19, 95% CI = 1.001–4.81, P = 0.0497; P for trend = 0.039). RCS analysis showed an linear association between the TyG index and MACE (P-overall = 0.027, P-non-linear = 0.589). ROC curve analysis showed that the TyG index of ≥ 8.73 was the optimal threshold value (area under the ROC curve = 0.60, 95% CI 0.53–0.67). TyG index ≥ 8.73 was significantly associated with MACE (HR = 2.10, 95% CI = 1.32–3.34, P = 0.002). After adjustment for confounders, the TyG index showed independent association with MACE (HR = 2.00, 95% CI = 1.17–3.42, P = 0.011). Conclusions The TyG index showed a positive linear correlation with MACE in patients with both CAD and psoriasis. The TyG index of ≥ 8.73 might be the optimal threshold for predicting MACE. Graphical Abstract
- Published
- 2024
- Full Text
- View/download PDF
50. Validity of the Chinese multimorbidity-weighted index in measuring disease burden using health check-ups data in primary care
- Author
-
Ying-Si Lai, Xin-Yuan Gao, Wei-Hua Hu, Yi-Xuan Liu, Yong-Jin Zhang, Jia-Cong Liu, Chun Yang, and Jing Liao
- Subjects
Chinese multimorbidity-weighted index ,Health check-ups data ,Primary care ,Public aspects of medicine ,RA1-1270 - Abstract
Abstract Background As multimorbidity becomes common that imposes a considerable burden to patients, but the extent to which widely-used multimorbidity indexes can be applied to quantify disease burden using primary care data in China is not clear. We applied the Chinese Multimorbidity-Weighted Index (CMWI) to health check-ups data routinely collected among older adults by primary care, to examine its validity in measuring multimorbidity associated risks of disability and mortality in annual follow-ups. Methods The study utilized data from annual health check-ups of older adults, which included information on individual age, sex, and 14 health conditions at primary care in a district of Guangzhou, Guangdong, China. The risk of CMWI for mortality was analysed in a total sample of 45,009 persons 65 years and older between 2014 and 2020 (average 2.70-year follow-up), and the risk for disability was in a subsample of 18,320 older adults free of physical impairment in 2019 and followed-up in 2020. Risk of death and disability were assessed with Cox proportional hazard regression and binary logistic regression, respectively, with both models adjusted for age and sex variables. The model fit was assessed by the Akaike information criterion (AIC), and C-statistic or the area under the receiver operating characteristic curve (AUC). Results One unit increase in baseline-CMWI (Median= 1.70, IQR: 1.30-3.00) was associated with higher risk in subsequent disability (OR = 1.12, 95%CI = 1.05,1.20) and mortality (OR = 1.18, 95%CI = 1.14, 1.22). Participants in the top tertile of CMWI had 99% and 152% increased risks of disability and mortality than their counterparts in the bottom tertile. Model fit was satisfied with adequate AUC (0.84) or C-statistic (0.76) for both outcomes. Conclusions CMWI, calculated based on primary care’s routine health check-ups data, provides valid estimates of disability and mortality risks in older adults. This validated tool can be used to quantity and monitor older patients’ health risks in primary care.
- Published
- 2024
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.