arXiv subjects

Yimin Zhu

Publications and source records attributed to Yimin Zhu.

32 records · Page 2Linked to original sources

arXiv2025

Accurate grain boundary plane distributions for textured microstructures from stereological analysis of orthogonal two-dimensional electron backscatter diffraction orientation maps

We present a method for obtaining qualitatively accurate grain boundary plane distributions (GBPD) for textured microstructures using a stereological calculation applied to two-dimensional electron backscatter diffraction (EBSD) orientation maps. Stereology, applied to 2D EBSD orientation maps, is currently the fastest method of obtaining GBPDs. Existing stereological methods are not directly applicable to textured microstructures because of the biased viewing perspectives for different grain boundary types supplied from a single planar orientation map. The method presented in this work successfully removes part of this bias by combining data from three orthogonal EBSD orientation maps for stereology. This is shown here to produce qualitatively correct GBPDs for heavily textured synthetic microstructures with hexagonal and tetragonal crystal symmetries. Synthetic microstructures were generated to compare the stereological GBPD to a known ground truth, as the true GBPD could be obtained from a triangular mesh of the full grain boundary network in 3D. The triangle mesh data contained all five macroscopic parameters to fully describe the grain boundary structure. It was observed that our stereological method overestimated the GBPD anisotropy. However, qualitative analysis of the GBPD remains useful. Furthermore, it was found that combining data from three orthogonal sections gives reliable results when sectioning the texture's primary axes.

cond-mat.mtrl-sci↗

arXiv2025

Sparse Deformable Mamba for Hyperspectral Image Classification

Although Mamba models significantly improve hyperspectral image (HSI) classification, one critical challenge is the difficulty in building the sequence of Mamba tokens efficiently. This paper presents a Sparse Deformable Mamba (SDMamba) approach for enhanced HSI classification, with the following contributions. First, to enhance Mamba sequence, an efficient Sparse Deformable Sequencing (SDS) approach is designed to adaptively learn the ''optimal" sequence, leading to sparse and deformable Mamba sequence with increased detail preservation and decreased computations. Second, to boost spatial-spectral feature learning, based on SDS, a Sparse Deformable Spatial Mamba Module (SDSpaM) and a Sparse Deformable Spectral Mamba Module (SDSpeM) are designed for tailored modeling of the spatial information spectral information. Last, to improve the fusion of SDSpaM and SDSpeM, an attention based feature fusion approach is designed to integrate the outputs of the SDSpaM and SDSpeM. The proposed method is tested on several benchmark datasets with many state-of-the-art approaches, demonstrating that the proposed approach can achieve higher accuracy with less computation, and better detail small-class preservation capability.

cs.CV↗

arXiv2025

Can AI Master Construction Management (CM)? Benchmarking State-of-the-Art Large Language Models on CM Certification Exams

The growing complexity of construction management (CM) projects, coupled with challenges such as strict regulatory requirements and labor shortages, requires specialized analytical tools that streamline project workflow and enhance performance. Although large language models (LLMs) have demonstrated exceptional performance in general reasoning tasks, their effectiveness in tackling CM-specific challenges, such as precise quantitative analysis and regulatory interpretation, remains inadequately explored. To bridge this gap, this study introduces CMExamSet, a comprehensive benchmarking dataset comprising 689 authentic multiple-choice questions sourced from four nationally accredited CM certification exams. Our zero-shot evaluation assesses overall accuracy, subject areas (e.g., construction safety), reasoning complexity (single-step and multi-step), and question formats (text-only, figure-referenced, and table-referenced). The results indicate that GPT-4o and Claude 3.7 surpass typical human pass thresholds (70%), with average accuracies of 82% and 83%, respectively. Additionally, both models performed better on single-step tasks, with accuracies of 85.7% (GPT-4o) and 86.7% (Claude 3.7). Multi-step tasks were more challenging, reducing performance to 76.5% and 77.6%, respectively. Furthermore, both LLMs show significant limitations on figure-referenced questions, with accuracies dropping to approximately 40%. Our error pattern analysis further reveals that conceptual misunderstandings are the most common (44.4% and 47.9%), underscoring the need for enhanced domain-specific reasoning models. These findings underscore the potential of LLMs as valuable supplementary analytical tools in CM, while highlighting the need for domain-specific refinements and sustained human oversight in complex decision making.

cs.CL↗

arXiv2025

Spatial-Spectral Diffusion Contrastive Representation Network for Hyperspectral Image Classification

Although efficient extraction of discriminative spatial-spectral features is critical for hyperspectral images classification (HSIC), it is difficult to achieve these features due to factors such as the spatial-spectral heterogeneity and noise effect. This paper presents a Spatial-Spectral Diffusion Contrastive Representation Network (DiffCRN), based on denoising diffusion probabilistic model (DDPM) combined with contrastive learning (CL) for HSIC, with the following characteristics. First,to improve spatial-spectral feature representation, instead of adopting the UNets-like structure which is widely used for DDPM, we design a novel staged architecture with spatial self-attention denoising module (SSAD) and spectral group self-attention denoising module (SGSAD) in DiffCRN with improved efficiency for spectral-spatial feature learning. Second, to improve unsupervised feature learning efficiency, we design new DDPM model with logarithmic absolute error (LAE) loss and CL that improve the loss function effectiveness and increase the instance-level and inter-class discriminability. Third, to improve feature selection, we design a learnable approach based on pixel-level spectral angle mapping (SAM) for the selection of time steps in the proposed DDPM model in an adaptive and automatic manner. Last, to improve feature integration and classification, we design an Adaptive weighted addition modul (AWAM) and Cross time step Spectral-Spatial Fusion Module (CTSSFM) to fuse time-step-wise features and perform classification. Experiments conducted on widely used four HSI datasets demonstrate the improved performance of the proposed DiffCRN over the classical backbone models and state-of-the-art GAN, transformer models and other pretrained methods. The source code and pre-trained model will be made available publicly.

cs.CV↗

arXiv2024

Generalizing End-To-End Autonomous Driving In Real-World Environments Using Zero-Shot LLMs

Traditional autonomous driving methods adopt a modular design, decomposing tasks into sub-tasks. In contrast, end-to-end autonomous driving directly outputs actions from raw sensor data, avoiding error accumulation. However, training an end-to-end model requires a comprehensive dataset; otherwise, the model exhibits poor generalization capabilities. Recently, large language models (LLMs) have been applied to enhance the generalization capabilities of end-to-end driving models. Most studies explore LLMs in an open-loop manner, where the output actions are compared to those of experts without direct feedback from the real world, while others examine closed-loop results only in simulations. This paper proposes an efficient architecture that integrates multimodal LLMs into end-to-end driving models operating in closed-loop settings in real-world environments. In our architecture, the LLM periodically processes raw sensor data to generate high-level driving instructions, effectively guiding the end-to-end model, even at a slower rate than the raw sensor data. This architecture relaxes the trade-off between the latency and inference quality of the LLM. It also allows us to choose from a wide variety of LLMs to improve high-level driving instructions and minimize fine-tuning costs. Consequently, our architecture reduces data collection requirements because the LLMs do not directly output actions; we only need to train a simple imitation learning model to output actions. In our experiments, the training data for the end-to-end model in a real-world environment consists of only simple obstacle configurations with one traffic cone, while the test environment is more complex and contains multiple obstacles placed in various positions. Experiments show that the proposed architecture enhances the generalization capabilities of the end-to-end model even without fine-tuning the LLM.

cs.RO↗

arXiv2024

TactV: A Class of Hybrid Terrestrial/Aerial Coaxial Tilt-Rotor Vehicles

To enhance the obstacle-crossing and endurance capabilities of vehicles operating in complex environments, this paper presents the design of a hybrid terrestrial/aerial coaxial tilt-rotor vehicle, TactV, which integrates advantages such as lightweight construction and high maneuverability. Unlike existing tandem dual-rotor vehicles, TactV employs a tiltable coaxial dual-rotor design and features a spherical cage structure that encases the body, allowing for omnidirectional movement while further reducing its overall dimensions. To enable TactV to maneuver flexibly in aerial, planar, and inclined surfaces, we established corresponding dynamic and control models for each mode. Additionally, we leveraged TactV's tiltable center of gravity to design energy-saving and high-mobility modes for ground operations, thereby further enhancing its endurance. Experimental designs for both aerial and ground tests corroborated the superiority of TactV's movement capabilities and control strategies.

cs.RO↗

arXiv2023

Fast American Option Pricing using Nonlinear Stencils

We study the binomial, trinomial, and Black-Scholes-Merton models of option pricing. We present fast parallel discrete-time finite-difference algorithms for American call option pricing under the binomial and trinomial models and American put option pricing under the Black-Scholes-Merton model. For $T$-step finite differences, each algorithm runs in $O(\left(T\log^2{T}\right)/p + T)$ time under a greedy scheduler on $p$ processing cores, which is a significant improvement over the $Θ({T^2}/{p}) + Ω(T\log{T})$ time taken by the corresponding state-of-the-art parallel algorithm. Even when run on a single core, the $O(T\log^2{T})$ time taken by our algorithms is asymptotically much smaller than the $Θ(T^2)$ running time of the fastest known serial algorithms. Implementations of our algorithms significantly outperform the fastest implementations of existing algorithms in practice, e.g., when run for $T \approx 1000$ steps on a 48-core machine, our algorithm for the binomial model runs at least $15\times$ faster than the fastest existing parallel program for the same model with the speed-up factor gradually reaching beyond $500\times$ for $T \approx 0.5 \times 10^6$. It saves more than 80\% energy when $T \approx 4000$, and more than 99\% energy for $T > 60,000$. Our option pricing algorithms can be viewed as solving a class of nonlinear 1D stencil (i.e., finite-difference) computation problems efficiently using the Fast Fourier Transform (FFT). To our knowledge, ours are the first algorithms to handle such stencils in $o(T^2)$ time. These contributions are of independent interest as stencil computations have a wide range of applications beyond quantitative finance.

cs.CE↗

arXiv2023

Cache-Oblivious Parallel Convex Hull in the Binary Forking Model

We present two cache-oblivious sorting-based convex hull algorithms in the Binary Forking Model. The first is an algorithm for a presorted set of points which achieves $O(n)$ work, $O(\log n)$ span, and $O(n/B)$ serial cache complexity, where $B$ is the cache line size. These are all optimal worst-case bounds for cache-oblivious algorithms in the Binary Forking Model. The second adapts Cole and Ramachandran's cache-oblivious sorting algorithm, matching its properties including achieving $O(n \log n)$ work, $O(\log n \log \log n)$ span, and $O(n/B \log_M n)$ serial cache complexity. Here $M$ is the size of the private cache.

cs.DS↗

arXiv2021

A Visual Analytics Framework for Distributed Data Analysis Systems

This paper proposes a visual analytics framework that addresses the complex user interactions required through a command-line interface to run analyses in distributed data analysis systems. The visual analytics framework facilitates the user to manage access to the distributed servers, incorporate data from the source, run data-driven analysis, monitor the progress, and explore the result using interactive visualizations. We provide a user interface embedded with generalized functionalities and access protocols and integrate it with a distributed analysis system. To demonstrate our proof of concept, we present two use cases from the earth science and Sustainable Human Building Ecosystem research domain.

cs.DC↗

arXiv2021

Fast Stencil Computations using Fast Fourier Transforms

Stencil computations are widely used to simulate the change of state of physical systems across a multidimensional grid over multiple timesteps. The state-of-the-art techniques in this area fall into three groups: cache-aware tiled looping algorithms, cache-oblivious divide-and-conquer trapezoidal algorithms, and Krylov subspace methods. In this paper, we present two efficient parallel algorithms for performing linear stencil computations. Current direct solvers in this domain are computationally inefficient, and Krylov methods require manual labor and mathematical training. We solve these problems for linear stencils by using DFT preconditioning on a Krylov method to achieve a direct solver which is both fast and general. Indeed, while all currently available algorithms for solving general linear stencils perform $Θ(NT)$ work, where $N$ is the size of the spatial grid and $T$ is the number of timesteps, our algorithms perform $o(NT)$ work. To the best of our knowledge, we give the first algorithms that use fast Fourier transforms to compute final grid data by evolving the initial data for many timesteps at once. Our algorithms handle both periodic and aperiodic boundary conditions, and achieve polynomially better performance bounds (i.e., computational complexity and parallel runtime) than all other existing solutions. Initial experimental results show that implementations of our algorithms that evolve grids of roughly $10^7$ cells for around $10^5$ timesteps run orders of magnitude faster than state-of-the-art implementations for periodic stencil problems, and 1.3$\times$ to 8.5$\times$ faster for aperiodic stencil problems.

cs.DS↗

arXiv2020

Context-Aware Design of Cyber-Physical Human Systems (CPHS)

Recently, it has been widely accepted by the research community that interactions between humans and cyber-physical infrastructures have played a significant role in determining the performance of the latter. The existing paradigm for designing cyber-physical systems for optimal performance focuses on developing models based on historical data. The impacts of context factors driving human system interaction are challenging and are difficult to capture and replicate in existing design models. As a result, many existing models do not or only partially address those context factors of a new design owing to the lack of capabilities to capture the context factors. This limitation in many existing models often causes performance gaps between predicted and measured results. We envision a new design environment, a cyber-physical human system (CPHS) where decision-making processes for physical infrastructures under design are intelligently connected to distributed resources over cyberinfrastructure such as experiments on design features and empirical evidence from operations of existing instances. The framework combines existing design models with context-aware design-specific data involving human-infrastructure interactions in new designs, using a machine learning approach to create augmented design models with improved predictive powers.

cs.AI↗

arXiv2019

Improving Prediction Accuracy in Building Performance Models Using Generative Adversarial Networks (GANs)

Building performance discrepancies between building design and operation are one of the causes that lead many new designs fail to achieve their goals and objectives. One of main factors contributing to the discrepancy is occupant behaviors. Occupants responding to a new design are influenced by several factors. Existing building performance models (BPMs) ignore or partially address those factors (called contextual factors) while developing BPMs. To potentially reduce the discrepancies and improve the prediction accuracy of BPMs, this paper proposes a computational framework for learning mixture models by using Generative Adversarial Networks (GANs) that appropriately combining existing BPMs with knowledge on occupant behaviors to contextual factors in new designs. Immersive virtual environments (IVEs) experiments are used to acquire data on such behaviors. Performance targets are used to guide appropriate combination of existing BPMs with knowledge on occupant behaviors. The resulting model obtained is called an augmented BPM. Two different experiments related to occupant lighting behaviors are shown as case study. The results reveal that augmented BPMs significantly outperformed existing BPMs with respect to achieving specified performance targets. The case study confirms the potential of the computational framework for improving prediction accuracy of BPMs during design.

cs.LG↗

arXiv2019

Why do you take that route?

The purpose of this paper is to determine whether a particular context factor among the variables that a researcher is interested in causally affects the route choice behavior of drivers. To our knowledge, there is limited literature that consider the effects of various factors on route choice based on causal inference.Yet, collecting data sets that are sensitive to the aforementioned factors are challenging and the existing approaches usually take into account only the general factors motivating drivers route choice behavior. To fill these gaps, we carried out a study using Immersive Virtual Environment (IVE) tools to elicit drivers' route choice behavioral data, covering drivers' network familiarity, educationlevel, financial concern, etc, apart from conventional measurement variables. Having context-aware, high-fidelity properties, IVE data affords the opportunity to incorporate the impacts of human related factors into the route choice causal analysis and advance a more customizable research tool for investigating causal factors on path selection in network routing. This causal analysis provides quantitative evidence to support drivers' diversion decision.

cs.CY↗

arXiv2019

Improving Route Choice Models by Incorporating Contextual Factors via Knowledge Distillation

Route Choice Models predict the route choices of travelers traversing an urban area. Most of the route choice models link route characteristics of alternative routes to those chosen by the drivers. The models play an important role in prediction of traffic levels on different routes and thus assist in development of efficient traffic management strategies that result in minimizing traffic delay and maximizing effective utilization of transport system. High fidelity route choice models are required to predict traffic levels with higher accuracy. Existing route choice models do not take into account dynamic contextual conditions such as the occurrence of an accident, the socio-cultural and economic background of drivers, other human behaviors, the dynamic personal risk level, etc. As a result, they can only make predictions at an aggregate level and for a fixed set of contextual factors. For higher fidelity, it is highly desirable to use a model that captures significance of subjective or contextual factors in route choice. This paper presents a novel approach for developing high-fidelity route choice models with increased predictive power by augmenting existing aggregate level baseline models with information on drivers' responses to contextual factors obtained from Stated Choice Experiments carried out in an Immersive Virtual Environment through the use of knowledge distillation.

cs.LG↗