arXiv subjects

Yong Feng

Publications and source records attributed to Yong Feng.

At least 19 recordsLinked to original sources

arXiv2026

Double Coupling Architecture and Training Method for Optimization Problems of Differential Algebraic Equations with Parameters

Simulation and modeling are essential in product development, integrated into the design and manufacturing process to enhance efficiency and quality. They are typically represented as complex nonlinear differential algebraic equations. The growing diversity of product requirements demands multi-task optimization, a key challenge in simulation modeling research. A dual physics-informed neural network architecture has been proposed to decouple constraints and objective functions in parametric differential algebraic equation optimization problems. Theoretical analysis shows that introducing a relaxation variable with a global error bound ensures solution equivalence between the network and optimization problem. A genetic algorithm-enhanced training framework for physics-informed neural networks improves training precision and efficiency, avoiding redundant solving of differential algebraic equations. This approach enables generalization for multi-task objectives with a single, training maintaining real-time responsiveness to product requirements.

cs.LG↗

arXiv2026

RSHallu: Dual-Mode Hallucination Evaluation for Remote-Sensing Multimodal Large Language Models with Domain-Tailored Mitigation

Multimodal large language models (MLLMs) are increasingly adopted in remote sensing (RS) and have shown strong performance on tasks such as RS visual grounding (RSVG), RS visual question answering (RSVQA), and multimodal dialogue. However, hallucinations, which are responses inconsistent with the input RS images, severely hinder their deployment in high-stakes scenarios (e.g., emergency management and agricultural monitoring) and remain under-explored in RS. In this work, we present RSHallu, a systematic study with three deliverables: (1) we formalize RS hallucinations with an RS-oriented taxonomy and introduce image-level hallucination to capture RS-specific inconsistencies beyond object-centric errors (e.g., modality, resolution, and scene-level semantics); (2) we build a hallucination benchmark RSHalluEval (2,023 QA pairs) and enable dual-mode checking, supporting high-precision cloud auditing and low-cost reproducible local checking via a compact checker fine-tuned on RSHalluCheck dataset (15,396 QA pairs); and (3) we introduce a domain-tailored dataset RSHalluShield (30k QA pairs) for training-friendly mitigation and further propose training-free plug-and-play strategies, including decoding-time logit correction and RS-aware prompting. Across representative RS-MLLMs, our mitigation improves the hallucination-free rate by up to 21.63 percentage points under a unified protocol, while maintaining competitive performance on downstream RS tasks (RSVQA/RSVG). Code and datasets will be released.

cs.CV↗

arXiv2025

Automatic Classification and Segmentation of Tunnel Cracks Based on Deep Learning and Visual Explanations

Tunnel lining crack is a crucial indicator of tunnels' safety status. Aiming to classify and segment tunnel cracks with enhanced accuracy and efficiency, this study proposes a two-step deep learning-based method. An automatic tunnel image classification model is developed using the DenseNet-169 in the first step. The proposed crack segmentation model in the second step is based on the DeepLabV3+, whose internal logic is evaluated via a score-weighted visual explanation technique. Proposed method combines tunnel image classification and segmentation together, so that the selected images containing cracks from the first step are segmented in the second step to improve the detection accuracy and efficiency. The superior performances of the two-step method are validated by experiments. The results show that the accuracy and frames per second (FPS) of the tunnel crack classification model are 92.23% and 39.80, respectively, which are higher than other convolutional neural networks (CNN) based and Transformer based models. Also, the intersection over union (IoU) and F1 score of the tunnel crack segmentation model are 57.01% and 67.44%, respectively, outperforming other state-of-the-art models. Moreover, the provided visual explanations in this study are conducive to understanding the "black box" of deep learning-based models. The developed two-stage deep learning-based method integrating visual explanations provides a basis for fast and accurate quantitative assessment of tunnel health status.

cs.CV↗

arXiv2025

Pegasus: A Universal Framework for Scalable Deep Learning Inference on the Dataplane

The paradigm of Intelligent DataPlane (IDP) embeds deep learning (DL) models on the network dataplane to enable intelligent traffic analysis at line-speed. However, the current use of the match-action table (MAT) abstraction on the dataplane is misaligned with DL inference, leading to several key limitations, including accuracy degradation, limited scale, and lack of generality. This paper proposes Pegasus to address these limitations. Pegasus translates DL operations into three dataplane-oriented primitives to achieve generality: Partition, Map, and SumReduce. Specifically, Partition "divides" high-dimensional features into multiple low-dimensional vectors, making them more suitable for the dataplane; Map "conquers" computations on the low-dimensional vectors in parallel with the technique of fuzzy matching, while SumReduce "combines" the computation results. Additionally, Pegasus employs Primitive Fusion to merge computations, improving scalability. Finally, Pegasus adopts full precision weights with fixed-point activations to improve accuracy. Our implementation on a P4 switch demonstrates that Pegasus can effectively support various types of DL models, including Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), Convolutional Neural Network (CNN), and AutoEncoder models on the dataplane. Meanwhile, Pegasus outperforms state-of-the-art approaches with an average accuracy improvement of up to 22.8%, along with up to 248x larger model size and 212x larger input scale.

cs.NI↗

arXiv2023

ClickINC: In-network Computing as a Service in Heterogeneous Programmable Data-center Networks

In-Network Computing (INC) has found many applications for performance boosts or cost reduction. However, given heterogeneous devices, diverse applications, and multi-path network typologies, it is cumbersome and error-prone for application developers to effectively utilize the available network resources and gain predictable benefits without impeding normal network functions. Previous work is oriented to network operators more than application developers. We develop ClickINC to streamline the INC programming and deployment using a unified and automated workflow. ClickINC provides INC developers a modular programming abstractions, without concerning to the states of the devices and the network topology. We describe the ClickINC framework, model, language, workflow, and corresponding algorithms. Experiments on both an emulator and a prototype system demonstrate its feasibility and benefits.

cs.NI↗

arXiv2023

A Continuous-Time Stochastic Process for High-Resolution Network Data in Sports

Technological advances have paved the way for collecting high-resolution network data in basketball, football, and other team-based sports. Such data consist of interactions among players of competing teams indexed by space and time. High-resolution network data are vital to understanding and predicting the performance of teams, because the performance of a team is more than the sum of the strengths of its individual players: Whether a collection of players forms a strong team depends on the strength of the individual players as well as the interactions among the players. We introduce a continuous-time stochastic process as a model of interactions among players of competing teams indexed by space and time, discuss basic properties of the continuous-time stochastic process, and learn the stochastic process from high-resolution network data by pursuing a Bayesian approach. We present simulation results along with an application to Juventus Turin, Inter Milan, and other football clubs in the premier Italian soccer league.

stat.AP↗

arXiv2023

Panacea or Placebo? Exploring Causal Effects of Nonlocal Vehicle Driving Restriction Policies on Traffic Congestion Using Difference-in-differences Approach

Car dependence has been threatening transportation sustainability as it contributes to congestion and associated externalities. In response, various transport policies that restrict the use of private vehicle have been implemented. However, empirical evaluations of such policies have been limited. To assess these policies' benefits and costs, it is imperative to accurately evaluate how such policies affect traffic conditions. In this study, we compile a refined spatio-temporal resolution data set of the floating-vehicle-based traffic performance index to examine the effects of a recent nonlocal vehicle driving restriction policy in Shanghai, one of most populous cities in the world. Specifically, we explore whether and how the policy impacted traffic speeds in the short term by employing a quasi-experimental difference-in-differences modeling approach. We find that: (1) In the first month, the policy led to an increase of the network-level traffic speed by 1.47% (0.352 km/h) during evening peak hours (17:00-19:00) but had no significant effects during morning peak hours (7:00-9:00). (2) The policy also helped improve the network-level traffic speed in some unrestricted hours (6:00, 12:00, 14:00, and 20:00) although the impact was marginal. (3) The short-term effects of the policy exhibited heterogeneity across traffic analysis zones. The lower the metro station density, the greater the effects were. We conclude that driving restrictions for non-local vehicles alone may not significantly reduce congestion, and their effects can differ both temporally and spatially. However, they can have potential side effects such as increased purchase and usage of new energy vehicles, owners of which can obtain a local license plate of Shanghai for free.

econ.GN↗

arXiv2021

On the probability of generating a primitive matrix

Given a $k\times n$ integer primitive matrix $\bf{A}$ (i.e., a matrix can be extended to an $n\times n$ unimodular matrix over the integers) with the maximal absolute value of entries $\|\bf{A}\|$ bounded by {an integer} $\lambda$ from above, we study the probability that the $m\times n$ matrix extended from $\bf{A}$ by appending other $m-k$ row vectors of dimension $n$ with entries chosen randomly and independently from the uniform distribution over $\{0, 1,\ldots, \lambda-1\}$ is still primitive. We present a complete and rigorous proof of a lower bound on the probability, which is at least a constant for fixed $m$ in the range $[k+1, n-4]$. As an application, we prove that there exists a fast Las Vegas algorithm that completes a $k\times n$ primitive matrix $\bf{A}$ to an $n\times n$ unimodular matrix within expected $\tilde{O}(n^{\omega}\log \|\bf{A}\|)$ bit operations, where $\tilde{O}$ is big-$O$ but without log factors, $\omega$ is the exponent on the arithmetic operations of matrix multiplication.

cs.SC↗

arXiv2019

Visualizing Planar and Space Implicit Real Algebraic Curves with Singularities

We present a new method for visualizing implicit real algebraic curves inside a bounding box in the $2$-D or $3$-D ambient space based on numerical continuation and critical point methods. The underlying techniques work also for tracing space curve in higher-dimensional space. Since the topology of a curve near a singular point of it is not numerically stable, we trace only the curve outside neighborhoods of singular points and replace each neighborhood simply by a point, which produces a polygonal approximation that is $ε$-close to the curve. Such an approximation is more stable for defining the numerical connectedness of the complement of the projection of the curve in $\mathbb{R}^2$, which is important for applications such as solving bi-parametric polynomial systems. The algorithm starts by computing three types of key points of the curve, namely the intersection of the curve with small spheres centered at singular points, regular critical points of every connected components of the curve, as well as intersection points of the curve with the given bounding box. It then traces the curve starting with and in the order of the above three types of points. This basic scheme is further enhanced by several optimizations, such as grouping singular points in natural clusters, tracing the curve by a try-and-resume strategy and handling "pseudo singular points". The effectiveness of the algorithm is illustrated by numerous examples. This manuscript extends our preliminary results that appeared in CASC 2018.

cs.SC↗

arXiv2018

The PSLQ Algorithm for Empirical Data

The celebrated integer relation finding algorithm PSLQ has been successfully used in many applications. PSLQ was only analyzed theoretically for exact input data, however, when the input data are irrational numbers, they must be approximate ones due to the finite precision of the computer. When the algorithm takes empirical data (inexact data with error bounded) instead of exact real numbers as its input, how do we theoretically ensure the output of the algorithm to be an exact integer relation? In this paper, we investigate the PSLQ algorithm for empirical data as its input. Firstly, we give a termination condition for this case. Secondly, we analyze a perturbation on the hyperplane matrix constructed from the input data and hence disclose a relationship between the accuracy of the input data and the output quality (an upper bound on the absolute value of the inner product of the exact data and the computed integer relation), which naturally leads to an error control strategy for PSLQ. Further, we analyze the complexity bound of the PSLQ algorithm for empirical data. Examples on transcendental numbers and algebraic numbers show the meaningfulness of our error control strategy.

cs.SC↗

arXiv2016

Variable p norm constrained LMS algorithm based on gradient of root relative deviation.pdf

A new Lp-norm constraint least mean square (Lp-LMS) algorithm with new strategy of varying p is presented, which is applied to system identification in this letter. The parameter p is iteratively adjusted by the gradient method applied to the root relative deviation of the estimated weight vector. Numerical simulations show that this new algorithm achieves lower steady-state error as well as equally fast convergence compared with the traditional Lp-LMS and LMS algorithms in the application setting of sparse system identification in the presence of noise.

eess.SY↗

arXiv2015

Error Gradient-based Variable-Lp Norm Constraint LMS Algorithm for Sparse System Identification

Sparse adaptive filtering has gained much attention due to its wide applicability in the field of signal processing. Among the main algorithm families, sparse norm constraint adaptive filters develop rapidly in recent years. However, when applied for system identification, most priori work in sparse norm constraint adaptive filtering suffers from the difficulty of adaptability to the sparsity of the systems to be identified. To address this problem, we propose a novel variable p-norm constraint least mean square (LMS) algorithm, which serves as a variant of the conventional Lp-LMS algorithm established for sparse system identification. The parameter p is iteratively adjusted by the gradient descent method applied to the instantaneous square error. Numerical simulations show that this new approach achieves better performance than the traditional Lp-LMS and LMS algorithms in terms of steady-state error and convergence rate.

eess.SY↗

arXiv2015

Efficient algorithm for computing large scale systems of differential algebraic equations

In many mathematical models of physical phenomenons and engineering fields, such as electrical circuits or mechanical multibody systems, which generate the differential algebraic equations (DAEs) systems naturally. In general, the feature of DAEs is a sparse large scale system of fully nonlinear and high index. To make use of its sparsity, this paper provides a simple and efficient algorithm for computing the large scale DAEs system. We exploit the shortest augmenting path algorithm for finding maximum value transversal (MVT) as well as block triangular forms (BTF). We also present the extended signature matrix method with the block fixed point iteration and its complexity results. Furthermore, a range of nontrivial problems are demonstrated by our algorithm.

math.NA↗

arXiv2015

Index reduction of differential algebraic equations by differential algebraic elimination

High index differential algebraic equations (DAEs) are ordinary differential equations (ODEs) with constraints and arise frequently from many mathematical models of physical phenomenons and engineering fields. In this paper, we generalize the idea of differential elimination with Dixon resultant to polynomially nonlinear DAEs. We propose a new algorithm for index reduction of DAEs and establish the notion of differential algebraic elimination, which can provide the differential algebraic resultant of the enlarged system of original equations. To make use of structure of DAEs, variable pencil technique is given to determine the termination of differentiation. Moreover, we also provide a heuristics method for removing the extraneous factors from differential algebraic resultant. The experimentation shows that the proposed algorithm outperforms existing ones for many examples taken from the literature.

cs.SC↗

arXiv2015

Computing the determinant of a matrix with polynomial entries by approximation

Computing the determinant of a matrix with the univariate and multivariate polynomial entries arises frequently in the scientific computing and engineering fields. In this paper, an effective algorithm is presented for computing the determinant of a matrix with polynomial entries using hybrid symbolic and numerical computation. The algorithm relies on the Newton's interpolation method with error control for solving Vandermonde systems. It is also based on a novel approach for estimating the degree of variables, and the degree homomorphism method for dimension reduction. Furthermore, the parallelization of the method arises naturally.

cs.SC↗

arXiv2015

Gradient Compared Lp-LMS Algorithms for Sparse System Identification

In this paper, we propose two novel p-norm penalty least mean square (Lp-LMS) algorithms as supplements of the conventional Lp-LMS algorithm established for sparse adaptive filtering recently. A gradient comparator is employed to selectively apply the zero attractor of p-norm constraint for only those taps that have the same polarity as that of the gradient of the squared instantaneous error, which leads to the new proposed gradient compared p-norm constraint LMS algorithm (LpGC-LMS). We explain that the LpGC-LMS can achieve lower mean square error than the standard Lp-LMS algorithm theoretically and experimentally. To further improve the performance of the filter, the LpNGC-LMS algorithm is derived using a new gradient comparator which takes the sign-smoothed version of the previous one. The performance of the LpNGC-LMS is superior to that of the LpGC-LMS in theory and in simulations. Moreover, these two comparators can be easily applied to other norm constraint LMS algorithms to derive some new approaches for sparse adaptive filtering. The numerical simulation results show that the two proposed algorithms achieve better performance than the standard LMS algorithm and Lp-LMS algorithm in terms of convergence rate and steady-state behavior in sparse system identification settings.

eess.SY↗

arXiv2015

p Norm Constraint Leaky LMS Algorithm for Sparse System Identification

This paper proposes a new leaky least mean square (leaky LMS, LLMS) algorithm in which a norm penalty is introduced to force the solution to be sparse in the application of system identification. The leaky LMS algorithm is derived because the performance ofthe standard LMS algorithm deteriorates when the input is highly correlated. However, both ofthem do not take the sparsity information into account to yield better behaviors. As a modification ofthe LLMS algorithm, the proposed algorithm, named Lp-LLMS, incorporates a p norm penalty into the cost function ofthe LLMS to obtain a shrinkage in the weight update equation, which then enhances the performance of the filter in system identification settings, especially when the impulse response is sparse. The simulation results verify that the proposed algorithm improves the performance ofthe filter in sparse system settings in the presence ofnoisy input signals.

eess.SY↗

arXiv2015

p-norm-like Constraint Leaky LMS Algorithm for Sparse System Identification

In this paper, we propose a novel leaky least mean square (leaky LMS, LLMS) algorithm which employs a p-norm-like constraint to force the solution to be sparse in the application of system identification. As an extension of the LMS algorithm which is the most widely-used adaptive filtering technique, the LLMS algorithm has been proposed for decades, due to the deteriorated performance of the standard LMS algorithm with highly correlated input. However, both ofthem do not consider the sparsity information to have better behaviors. As a sparse-aware modification of the LLMS, our proposed Lplike-LLMS algorithm, incorporates a p-norm-like penalty into the cost function of the LLMS to obtain a shrinkage in the weight update, which then enhances the performance in sparse system identification settings. The simulation results show that the proposed algorithm improves the performance of the filter in sparse system settings in the presence of noisy input signals.

eess.SY↗