Search arXiv⌕ Search

arXiv subjects

Fei Chen

Publications and source records attributed to Fei Chen.

At least 73 records · Page 4Linked to original sources
arXiv2024

Parallelized Robust Distributed Model Predictive Control in the Presence of Coupled State Constraints

In this paper, we present a robust distributed model predictive control (DMPC) scheme for dynamically decoupled nonlinear systems which are subject to state constraints, coupled state constraints and input constraints. In the proposed control scheme, all subsystems solve their local optimization problem in parallel and neighbor-to-neighbor communication suffices. The approach relies on consistency constraints which define a neighborhood around each subsystem's reference trajectory where the state of the subsystem is guaranteed to stay in. Reference trajectories and consistency constraints are known to neighboring subsystems. Contrary to other relevant approaches, the reference trajectories are improved consecutively. The presented approach allows the formulation of convex optimization problems for systems with linear dynamics even in the presence of non-convex state constraints. Additionally, we employ tubes in order to ensure the controller's robustness against bounded uncertainties. In the end, we briefly comment on an iterative extension of the DMPC scheme. The effectiveness of the proposed DMPC scheme and its iterative extension are demonstrated with simulations.

eess.SY↗
arXiv2024

Attention-Based Beamformer For Multi-Channel Speech Enhancement

Minimum Variance Distortionless Response (MVDR) is a classical adaptive beamformer that theoretically ensures the distortionless transmission of signals in the target direction, which makes it popular in real applications. Its noise reduction performance actually depends on the accuracy of the noise and speech spatial covariance matrices (SCMs) estimation. Time-frequency masks are often used to compute these SCMs. However, most mask-based beamforming methods typically assume that the sources are stationary, ignoring the case of moving sources, which leads to performance degradation. In this paper, we propose an attention-based mechanism to calculate the speech and noise SCMs and then apply MVDR to obtain the enhanced speech. To fully incorporate spatial information, the inplace convolution operator and frequency-independent LSTM are applied to facilitate SCMs estimation. The model is optimized in an end-to-end manner. Experiments demonstrate that the proposed method outperforms baselines with reduced computation and fewer parameters under various conditions.

cs.SD↗
arXiv2024

Distributed Multi-Object Tracking Under Limited Field of View Heterogeneous Sensors with Density Clustering

We consider the problem of tracking multiple, unknown, and time-varying numbers of objects using a distributed network of heterogeneous sensors. In an effort to derive a formulation for practical settings, we consider limited and unknown sensor field-of-views (FoVs), sensors with limited local computational resources and communication channel capacity. The resulting distributed multi-object tracking algorithm involves solving an NP-hard multidimensional assignment problem either optimally for small-size problems or sub-optimally for general practical problems. For general problems, we propose an efficient distributed multi-object tracking algorithm that performs track-to-track fusion using a clustering-based analysis of the state space transformed into a density space to mitigate the complexity of the assignment problem. The proposed algorithm can more efficiently group local track estimates for fusion than existing approaches. To ensure we achieve globally consistent identities for tracks across a network of nodes as objects move between FoVs, we develop a graph-based algorithm to achieve label consensus and minimise track segmentation. Numerical experiments with synthetic and real-world trajectory datasets demonstrate that our proposed method is significantly more computationally efficient than state-of-the-art solutions, achieving similar tracking accuracy and bandwidth requirements but with improved label consistency.

cs.MA↗
arXiv2024

GLObal Building heights for Urban Studies (UT-GLOBUS) for city- and street- scale urban simulations: Development and first applications

We introduce University of Texas - Global Building heights for Urban Studies (UT-GLOBUS), a dataset providing building heights and urban canopy parameters (UCPs) for more than 1200 cities or locales worldwide. UT-GLOBUS combines open-source spaceborne altimetry (ICESat-2 and GEDI) and coarse-resolution urban canopy elevation data with a machine-learning model to estimate building-level information. Validation using LiDAR data from six US cities showed UT-GLOBUS-derived building heights had a root mean squared error (RMSE) of 9.1 meters. Validation of mean building heights within 1-km^2 grid cells, including data from Hamburg and Sydney, resulted in an RMSE of 7.8 meters. Testing the UCPs in the urban Weather Research and Forecasting (WRF-Urban) model resulted in a significant improvement (55% in RMSE) in intra-urban air temperature representation compared to the existing table-based local climate zone approach in Houston, TX. Additionally, we demonstrated the dataset's utility for simulating heat mitigation strategies and building energy consumption using WRF-Urban, with test cases in Chicago, IL, and Austin, TX. Street-scale mean radiant temperature simulations using the Solar and LongWave Environmental Irradiance Geometry (SOLWEIG) model, incorporating UT-GLOBUS and LiDAR-derived building heights, confirmed the dataset's effectiveness in modeling human thermal comfort in Baltimore, MD (daytime RMSE = 2.85 C). Thus, UT-GLOBUS can be used for modeling urban hazards with significant socioeconomic and biometeorological risks, enabling finer scale urban climate simulations and overcoming previous limitations due to the lack of building information.

cs.CE↗
arXiv2024

Intertwining operators in the Takeda-Wood isomorphism

Over any non-Archimedean local field of characteristic not equal to $2$, Takeda and Wood constructed types for the two blocks containing the even and odd Weil representations of the metaplectic group $\tilde{G}$, and identified the resulting Hecke algebras $H_ψ^{\pm}$ with the Iwahori-Hecke algebras of odd orthogonal groups $G^{\pm}$ of the same rank. We describe normalized parabolic induction and Jacquet modules in terms of Hecke modules using a suitable variant of Bushnell-Kutzko theory. Furthermore, we match the standard intertwining operators of $\tilde{G}$ and $G^{\pm}$ by proving a variant of Gindikin-Karpelevich formula for $\tilde{G}$. As an application, we describe the behavior of normalized intertwining operators of $\tilde{G}$ in these blocks under Aubert involution, reducing everything to the $G^{\pm}$ side. This is mainly motivated by Arthur's local intertwining relations.

math.RT↗
arXiv2024

Accelerating Diffusion Sampling with Optimized Time Steps

Diffusion probabilistic models (DPMs) have shown remarkable performance in high-resolution image synthesis, but their sampling efficiency is still to be desired due to the typically large number of sampling steps. Recent advancements in high-order numerical ODE solvers for DPMs have enabled the generation of high-quality images with much fewer sampling steps. While this is a significant development, most sampling methods still employ uniform time steps, which is not optimal when using a small number of steps. To address this issue, we propose a general framework for designing an optimization problem that seeks more appropriate time steps for a specific numerical ODE solver for DPMs. This optimization problem aims to minimize the distance between the ground-truth solution to the ODE and an approximate solution corresponding to the numerical solver. It can be efficiently solved using the constrained trust region method, taking less than $15$ seconds. Our extensive experiments on both unconditional and conditional sampling using pixel- and latent-space DPMs demonstrate that, when combined with the state-of-the-art sampling method UniPC, our optimized time steps significantly improve image generation performance in terms of FID scores for datasets such as CIFAR-10 and ImageNet, compared to using uniform time steps.

cs.CV↗
arXiv2024

Non-Intrusive Speech Intelligibility Prediction for Hearing Aids using Whisper and Metadata

Automated speech intelligibility assessment is pivotal for hearing aid (HA) development. In this paper, we present three novel methods to improve intelligibility prediction accuracy and introduce MBI-Net+, an enhanced version of MBI-Net, the top-performing system in the 1st Clarity Prediction Challenge. MBI-Net+ leverages Whisper's embeddings to create cross-domain acoustic features and includes metadata from speech signals by using a classifier that distinguishes different enhancement methods. Furthermore, MBI-Net+ integrates the hearing-aid speech perception index (HASPI) as a supplementary metric into the objective function to further boost prediction performance. Experimental results demonstrate that MBI-Net+ surpasses several intrusive baseline systems and MBI-Net on the Clarity Prediction Challenge 2023 dataset, validating the effectiveness of incorporating Whisper embeddings, speech metadata, and related complementary metrics to improve prediction performance for HA.

eess.AS↗
arXiv2024

TAnet: A New Temporal Attention Network for EEG-based Auditory Spatial Attention Decoding with a Short Decision Window

Auditory spatial attention detection (ASAD) is used to determine the direction of a listener's attention to a speaker by analyzing her/his electroencephalographic (EEG) signals. This study aimed to further improve the performance of ASAD with a short decision window (i.e., <1 s) rather than with long decision windows ranging from 1 to 5 seconds in previous studies. An end-to-end temporal attention network (i.e., TAnet) was introduced in this work. TAnet employs a multi-head attention (MHA) mechanism, which can more effectively capture the interactions among time steps in collected EEG signals and efficiently assign corresponding weights to those EEG time steps. Experiments demonstrated that, compared with the CNN-based method and recent ASAD methods, TAnet provided improved decoding performance in the KUL dataset, with decoding accuracies of 92.4% (decision window 0.1 s), 94.9% (0.25 s), 95.1% (0.3 s), 95.4% (0.4 s), and 95.5% (0.5 s) with short decision windows (i.e., <1 s). As a new ASAD model with a short decision window, TAnet can potentially facilitate the design of EEG-controlled intelligent hearing aids and sound recognition systems.

eess.SP↗
arXiv2024

Manifold Graph Signal Restoration using Gradient Graph Laplacian Regularizer

In the graph signal processing (GSP) literature, graph Laplacian regularizer (GLR) was used for signal restoration to promote piecewise smooth / constant reconstruction with respect to an underlying graph. However, for signals slowly varying across graph kernels, GLR suffers from an undesirable "staircase" effect. In this paper, focusing on manifold graphs -- collections of uniform discrete samples on low-dimensional continuous manifolds -- we generalize GLR to gradient graph Laplacian regularizer (GGLR) that promotes planar / piecewise planar (PWP) signal reconstruction. Specifically, for a graph endowed with sampling coordinates (e.g., 2D images, 3D point clouds), we first define a gradient operator, using which we construct a gradient graph for nodes' gradients in sampling manifold space. This maps to a gradient-induced nodal graph (GNG) and a positive semi-definite (PSD) Laplacian matrix with planar signals as the 0 frequencies. For manifold graphs without explicit sampling coordinates, we propose a graph embedding method to obtain node coordinates via fast eigenvector computation. We derive the means-square-error minimizing weight parameter for GGLR efficiently, trading off bias and variance of the signal estimate. Experimental results show that GGLR outperformed previous graph signal priors like GLR and graph total variation (GTV) in a range of graph signal restoration tasks.

eess.SP↗
arXiv2024

MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation

Text-to-image generation has achieved astonishing results, yet precise spatial controllability and prompt fidelity remain highly challenging. This limitation is typically addressed through cumbersome prompt engineering, scene layout conditioning, or image editing techniques which often require hand drawn masks. Nonetheless, pre-existing works struggle to take advantage of the natural instance-level compositionality of scenes due to the typically flat nature of rasterized RGB output images. Towards adressing this challenge, we introduce MuLAn: a novel dataset comprising over 44K MUlti-Layer ANnotations of RGB images as multilayer, instance-wise RGBA decompositions, and over 100K instance images. To build MuLAn, we developed a training free pipeline which decomposes a monocular RGB image into a stack of RGBA layers comprising of background and isolated instances. We achieve this through the use of pretrained general-purpose models, and by developing three modules: image decomposition for instance discovery and extraction, instance completion to reconstruct occluded areas, and image re-assembly. We use our pipeline to create MuLAn-COCO and MuLAn-LAION datasets, which contain a variety of image decompositions in terms of style, composition and complexity. With MuLAn, we provide the first photorealistic resource providing instance decomposition and occlusion information for high quality images, opening up new avenues for text-to-image generative AI research. With this, we aim to encourage the development of novel generation and editing technology, in particular layer-wise solutions. MuLAn data resources are available at https://MuLAn-dataset.github.io/.

cs.CV↗
arXiv2024

Fusion Dynamical Systems with Machine Learning in Imitation Learning: A Comprehensive Overview

Imitation Learning (IL), also referred to as Learning from Demonstration (LfD), holds significant promise for capturing expert motor skills through efficient imitation, facilitating adept navigation of complex scenarios. A persistent challenge in IL lies in extending generalization from historical demonstrations, enabling the acquisition of new skills without re-teaching. Dynamical system-based IL (DSIL) emerges as a significant subset of IL methodologies, offering the ability to learn trajectories via movement primitives and policy learning based on experiential abstraction. This paper emphasizes the fusion of theoretical paradigms, integrating control theory principles inherent in dynamical systems into IL. This integration notably enhances robustness, adaptability, and convergence in the face of novel scenarios. This survey aims to present a comprehensive overview of DSIL methods, spanning from classical approaches to recent advanced approaches. We categorize DSIL into autonomous dynamical systems and non-autonomous dynamical systems, surveying traditional IL methods with low-dimensional input and advanced deep IL methods with high-dimensional input. Additionally, we present and analyze three main stability methods for IL: Lyapunov stability, contraction theory, and diffeomorphism mapping. Our exploration also extends to popular policy improvement methods for DSIL, encompassing reinforcement learning, deep reinforcement learning, and evolutionary strategies.

cs.RO↗
arXiv2024

3S-TSE: Efficient Three-Stage Target Speaker Extraction for Real-Time and Low-Resource Applications

Target speaker extraction (TSE) aims to isolate a specific voice from multiple mixed speakers relying on a registerd sample. Since voiceprint features usually vary greatly, current end-to-end neural networks require large model parameters which are computational intensive and impractical for real-time applications, espetially on resource-constrained platforms. In this paper, we address the TSE task using microphone array and introduce a novel three-stage solution that systematically decouples the process: First, a neural network is trained to estimate the direction of the target speaker. Second, with the direction determined, the Generalized Sidelobe Canceller (GSC) is used to extract the target speech. Third, an Inplace Convolutional Recurrent Neural Network (ICRN) acts as a denoising post-processor, refining the GSC output to yield the final separated speech. Our approach delivers superior performance while drastically reducing computational load, setting a new standard for efficient real-time target speaker extraction.

cs.SD↗
arXiv2024

RHDLPP: A multigroup radiation hydrodynamics code for laser-produced plasmas

We introduce the RHDLPP, a flux-limited multigroup radiation hydrodynamics numerical code designed for simulating laser-produced plasmas in diverse environments. The code bifurcates into two packages: RHDLPP-LTP for low-temperature plasmas generated by moderate-intensity nanosecond lasers, and RHDLPP-HTP for high-temperature, high-density plasmas formed by high-intensity laser pulses. The core radiation hydrodynamic equations are resolved in the Eulerian frame, employing an operator-split method. This method decomposes the solution into two substeps: first, the explicit resolution of the hyperbolic subsystems integrating radiation and fluid dynamics, and second, the implicit treatment of the parabolic part comprising stiff radiation diffusion, heat conduction, and energy exchange. Laser propagation and energy deposition are modeled through a hybrid approach, combining geometrical optics ray-tracing in sub-critical plasma regions with a one-dimensional solution of the Helmholtz wave equation in super-critical areas. The thermodynamic states are ascertained using an equation of state, based on either the real gas approximation or the quotidian equation of state (QEOS). Additionally, RHDLPP includes RHDLPP-SpeIma3D, a three-dimensional spectral simulation post-processing module, for generating both temporally-spatially resolved and time-integrated spectra and imaging, facilitating direct comparisons with experimental data. The paper showcases a series of verification tests to establish the code's accuracy and efficiency, followed by application cases, including simulations of laser-produced aluminum (Al) plasmas, pre-pulse-induced target deformation of tin (Sn) microdroplets relevant to extreme ultraviolet lithography light sources, and varied imaging and spectroscopic simulations.

physics.plasm-ph↗
arXiv2023

Modeling Viral Information Spreading via Directed Acyclic Graph Diffusion

Viral information like rumors or fake news is spread over a communication network like a virus infection in a unidirectional manner: entity $i$ conveys information to a neighbor $j$, resulting in two equally informed (infected) parties. Existing graph diffusion works focus only on bidirectional diffusion on an undirected graph. Instead, we propose a new directed acyclic graph (DAG) diffusion model to estimate the probability $x_i(t)$ of node $i$'s infection at time $t$ given a source node $s$, where $x_i(\infty)~=~1$. Specifically, given an undirected positive graph modeling node-to-node communication, we first compute its graph embedding: a latent coordinate for each node in an assumed low-dimensional manifold space from extreme eigenvectors via LOBPCG. Next, we construct a DAG based on Euclidean distances between latent coordinates. Spectrally, we prove that the asymmetric DAG Laplacian matrix contains real non-negative eigenvalues, and that the DAG diffusion converges to the all-infection vector $\x(\infty) = \1$ as $t \rightarrow \infty$. Simulation experiments show that our proposed DAG diffusion accurately models viral information spreading over a variety of graph structures at different time instants.

cs.SI↗
arXiv2023

On Topological Conditions for Enabling Transient Control in Leader-follower Networks

We derive necessary and sufficient conditions for leader-follower multi-agent systems such that we can further apply prescribed performance control to achieve the desired formation while satisfying certain transient constraints. A leader-follower framework is considered in the sense that a group of agents with external inputs are selected as leaders in order to drive the group of followers in a way that the entire system can achieve target formation within certain prescribed performance transient bounds. We first derive necessary conditions on the leader-follower graph topology under which the target formation together with the prescribed performance guarantees can be fulfilled. Afterwards, the derived necessary conditions are extended to necessary and sufficient conditions for leader-follower formation control under transient constraints. Finally, the proposed results are illustrated with simulation examples.

eess.SY↗
arXiv2023

ConservationBots: Autonomous Aerial Robot for Fast Robust Wildlife Tracking in Complex Terrains

Today, the most widespread, widely applicable technology for gathering data relies on experienced scientists armed with handheld radio telemetry equipment to locate low-power radio transmitters attached to wildlife from the ground. Although aerial robots can transform labor-intensive conservation tasks, the realization of autonomous systems for tackling task complexities under real-world conditions remains a challenge. We developed ConservationBots-small aerial robots for tracking multiple, dynamic, radio-tagged wildlife. The aerial robot achieves robust localization performance and fast task completion times -- significant for energy-limited aerial systems while avoiding close encounters with potential, counter-productive disturbances to wildlife. Our approach overcomes the technical and practical problems posed by combining a lightweight sensor with new concepts: i) planning to determine both trajectory and measurement actions guided by an information-theoretic objective, which allows the robot to strategically select near-instantaneous range-only measurements to achieve faster localization, and time-consuming sensor rotation actions to acquire bearing measurements and achieve robust tracking performance; ii) a bearing detector more robust to noise and iii) a tracking algorithm formulation robust to missed and false detections experienced in real-world conditions. We conducted extensive studies: simulations built upon complex signal propagation over high-resolution elevation data on diverse geographical terrains; field testing; studies with wombats (Lasiorhinus latifrons; nocturnal, vulnerable species dwelling in underground warrens) and tracking comparisons with a highly experienced biologist to validate the effectiveness of our aerial robot and demonstrate the significant advantages over the manual method.

cs.RO↗
arXiv2023

Complexity Matters: Rethinking the Latent Space for Generative Modeling

In generative modeling, numerous successful approaches leverage a low-dimensional latent space, e.g., Stable Diffusion models the latent space induced by an encoder and generates images through a paired decoder. Although the selection of the latent space is empirically pivotal, determining the optimal choice and the process of identifying it remain unclear. In this study, we aim to shed light on this under-explored topic by rethinking the latent space from the perspective of model complexity. Our investigation starts with the classic generative adversarial networks (GANs). Inspired by the GAN training objective, we propose a novel "distance" between the latent and data distributions, whose minimization coincides with that of the generator complexity. The minimizer of this distance is characterized as the optimal data-dependent latent that most effectively capitalizes on the generator's capacity. Then, we consider parameterizing such a latent distribution by an encoder network and propose a two-stage training strategy called Decoupled Autoencoder (DAE), where the encoder is only updated in the first stage with an auxiliary decoder and then frozen in the second stage while the actual decoder is being trained. DAE can improve the latent distribution and as a result, improve the generative performance. Our theoretical analyses are corroborated by comprehensive experiments on various models such as VQGAN and Diffusion Transformer, where our modifications yield significant improvements in sample quality with decreased model complexity.

cs.LG↗