arXiv subjects

Lu Gao

Publications and source records attributed to Lu Gao.

At least 37 records · Page 2Linked to original sources

arXiv2025

Assessing the Influence of Pavement Performance on Road Safety Through Crash Frequency and Severity Analysis

Road safety is impacted by a range of factors that can be categorized into human, vehicle, and roadway/environmental elements. This research explores the connection between pavement performance and road safety, particularly in relation to crash frequency and severity, using data from the Iowa Department of Transportation (DOT) for 2022. By merging crash data with pavement inventory data, we conduct a spatial analysis that incorporates the geographical coordinates of crash sites with the conditions of road segments. Statistical methods are applied to compare crash rates and severity across various pavement condition categories. To identify the most influential factors affecting crash rates and severity, we use machine learning models along with negative binomial and ordered probit regression models. The study's key findings reveal that higher speed limits, well-maintained roads, and improved friction scores correlate with lower crash rates, whereas rougher roads and adverse weather conditions are linked to higher crash severity. This analysis emphasizes the critical need for prioritizing pavement maintenance and integrating safety-focused design principles to boost road safety. Moreover, the study underscores the ongoing need for research to better understand and address the intricate relationship between pavement performance and road safety.

physics.soc-ph↗

arXiv2025

Cybersecurity-Focused Anomaly Detection in Connected Autonomous Vehicles Using Machine Learning

Anomaly detection in connected autonomous vehicles (CAVs) is crucial for maintaining safe and reliable transportation networks, as CAVs can be susceptible to sensor malfunctions, cyber-attacks, and unexpected environmental disruptions. This study explores an anomaly detection approach by simulating vehicle behavior, generating a dataset that represents typical and atypical vehicular interactions. The dataset includes time-series data of position, speed, and acceleration for multiple connected autonomous vehicles. We utilized machine learning models to effectively identify abnormal driving patterns. First, we applied a stacked Long Short-Term Memory (LSTM) model to capture temporal dependencies and sequence-based anomalies. The stacked LSTM model processed the sequential data to learn standard driving behaviors. Additionally, we deployed a Random Forest model to support anomaly detection by offering ensemble-based predictions, which enhanced model interpretability and performance. The Random Forest model achieved an R2 of 0.9830, MAE of 5.746, and a 95th percentile anomaly threshold of 14.18, while the stacked LSTM model attained an R2 of 0.9998, MAE of 82.425, and a 95th percentile anomaly threshold of 265.63. These results demonstrate the models' effectiveness in accurately predicting vehicle trajectories and detecting anomalies in autonomous driving scenarios.

cs.LG↗

arXiv2025

Evaluating Pavement Deterioration Rates Due to Flooding Events Using Explainable AI

Flooding can damage pavement infrastructure significantly, causing both immediate and long-term structural and functional issues. This research investigates how flooding events affect pavement deterioration, specifically focusing on measuring pavement roughness by the International Roughness Index (IRI). To quantify these effects, we utilized 20 years of pavement condition data from TxDOT's PMIS database, which is integrated with flood event data, including duration and spatial extent. Statistical analyses were performed to compare IRI values before and after flooding and to calculate the deterioration rates influenced by flood exposure. Moreover, we applied Explainable Artificial Intelligence (XAI) techniques, such as SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME), to assess the impact of flooding on pavement performance. The results demonstrate that flood-affected pavements experience a more rapid increase in roughness compared to non-flooded sections. These findings emphasize the need for proactive flood mitigation strategies, including improved drainage systems, flood-resistant materials, and preventative maintenance, to enhance pavement resilience in vulnerable regions.

cs.LG↗

arXiv2025

Large Language Model-Driven Code Compliance Checking in Building Information Modeling

This research addresses the time-consuming and error-prone nature of manual code compliance checking in Building Information Modeling (BIM) by introducing a Large Language Model (LLM)-driven approach to semi-automate this critical process. The developed system integrates LLMs such as GPT, Claude, Gemini, and Llama, with Revit software to interpret building codes, generate Python scripts, and perform semi-automated compliance checks within the BIM environment. Case studies on a single-family residential project and an office building project demonstrated the system's ability to reduce the time and effort required for compliance checks while improving accuracy. It streamlined the identification of violations, such as non-compliant room dimensions, material usage, and object placements, by automatically assessing relationships and generating actionable reports. Compared to manual methods, the system eliminated repetitive tasks, simplified complex regulations, and ensured reliable adherence to standards. By offering a comprehensive, adaptable, and cost-effective solution, this proposed approach offers a promising advancement in BIM-based compliance checking, with potential applications across diverse regulatory documents in construction projects.

cs.SE↗

arXiv2025

Exploring Traffic Simulation and Cybersecurity Strategies Using Large Language Models

Intelligent Transportation Systems (ITS) are increasingly vulnerable to sophisticated cyberattacks due to their complex, interconnected nature. Ensuring the cybersecurity of these systems is paramount to maintaining road safety and minimizing traffic disruptions. This study presents a novel multi-agent framework leveraging Large Language Models (LLMs) to enhance traffic simulation and cybersecurity testing. The framework automates the creation of traffic scenarios, the design of cyberattack strategies, and the development of defense mechanisms. A case study demonstrates the framework's ability to simulate a cyberattack targeting connected vehicle broadcasts, evaluate its impact, and implement a defense mechanism that significantly mitigates traffic delays. Results show a 10.2 percent increase in travel time during an attack, which is reduced by 3.3 percent with the defense strategy. This research highlights the potential of LLM-driven multi-agent systems in advancing transportation cybersecurity and offers a scalable approach for future research in traffic simulation and cyber defense.

cs.CR↗

arXiv2025

Effective Numerical Simulation of Fault Transient System

Power systems, including synchronous generator systems, are typical systems that strive for stable operation. In this article, we numerically study the fault transient process of a synchronous generator system based on the first benchmark model. That is, we make it clear whether an originally stable generator system can restore its stability after a short time of unstable transient process. To achieve this, we construct a structure-preserving method and compare it with the existing and frequently-used predictor-corrector method. We newly establish a reductive form of the circuit system and accelerate the reduction process. Also a switching method between two stages in the fault transient process is given. Numerical results show the effectiveness and reliability of our method.

math.NA↗

arXiv2024

Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition

Modern automatic speech recognition (ASR) model is required to accurately transcribe diverse speech signals (from different domains, languages, accents, etc) given the specific contextual information in various application scenarios. Classic end-to-end models fused with extra language models perform well, but mainly in data matching scenarios and are gradually approaching a bottleneck. In this work, we introduce Seed-ASR, a large language model (LLM) based speech recognition model. Seed-ASR is developed based on the framework of audio conditioned LLM (AcLLM), leveraging the capabilities of LLMs by inputting continuous speech representations together with contextual information into the LLM. Through stage-wise large-scale training and the elicitation of context-aware capabilities in LLM, Seed-ASR demonstrates significant improvement over end-to-end models on comprehensive evaluation sets, including multiple domains, accents/dialects and languages. Additionally, Seed-ASR can be further deployed to support specific needs in various scenarios without requiring extra language models. Compared to recently released large ASR models, Seed-ASR achieves 10%-40% reduction in word (or character, for Chinese) error rates on Chinese and English public test sets, further demonstrating its powerful performance.

eess.AS↗

arXiv2024

Hyper-sampling imaging

In our research, we have developed a novel mechanism that allows for a significant reduction in the smallest sampling unit of digital image sensors (DIS) to as small as 1/16th of a pixel, through measuring the intra-pixel quantum efficiency for the first time and recomputing the image. Employing our method, the physical sampling resolution of DIS can be enhanced by 16 times. The method has undergone rigorous testing in real-world imaging scenarios.

physics.optics↗

arXiv2024

Seed-TTS: A Family of High-Quality Versatile Speech Generation Models

We introduce Seed-TTS, a family of large-scale autoregressive text-to-speech (TTS) models capable of generating speech that is virtually indistinguishable from human speech. Seed-TTS serves as a foundation model for speech generation and excels in speech in-context learning, achieving performance in speaker similarity and naturalness that matches ground truth human speech in both objective and subjective evaluations. With fine-tuning, we achieve even higher subjective scores across these metrics. Seed-TTS offers superior controllability over various speech attributes such as emotion and is capable of generating highly expressive and diverse speech for speakers in the wild. Furthermore, we propose a self-distillation method for speech factorization, as well as a reinforcement learning approach to enhance model robustness, speaker similarity, and controllability. We additionally present a non-autoregressive (NAR) variant of the Seed-TTS model, named $\text{Seed-TTS}_\text{DiT}$, which utilizes a fully diffusion-based architecture. Unlike previous NAR-based TTS systems, $\text{Seed-TTS}_\text{DiT}$ does not depend on pre-estimated phoneme durations and performs speech generation through end-to-end processing. We demonstrate that this variant achieves comparable performance to the language model-based variant and showcase its effectiveness in speech editing. We encourage readers to listen to demos at \url{https://bytedancespeech.github.io/seedtts_tech_report}.

eess.AS↗

arXiv2024

Lagrangian Modelling and Motion Stability of Synchronous Generator Power Systems

This paper proposes to analyze the motion stability of synchro-nous generator power systems using a Lagrangian model derived in the configuration space of generalized position and speed. In the first place, a Lagrangian model of synchronous generators is derived based on Lagrangian mechanics. The generalized potential energy of inductors and generalized kinetic energy of capacitors are defined. The mechanical and electrical dynamics can be modelled in a unified manner through constructing a Lagrangian function. Taking the first benchmark model of subsynchronous oscillation as an example, a Lagragian model is construct-ed and numerical solution of the model is obtained to validate the accuracy and effectiveness of the model. Compared with the traditional EMTP model in PSCAD, the obtained Lagrangian model is able to accurately describe the electromagnetic transient process of the system. Moreover, the Lagrangian model is analytical, which enables to analyze the motion stability of the system using Lyapunov motion stability theory. The Lagrangian model can not only be used to discuss the power angle stability, but also used for analyzing the stability of node voltages and frequency. It provides the feasibility for studying the unified stability of power systems.

eess.SY↗

arXiv2023

Perfect crossed Andreev reflection in the proximitized graphene/superconductor/proximitized graphene junctions

We study the crossed Andreev reflection and the nonlocal transport in the proximitized graphene/supercondcutor/proximitized graphene junctions with the pseudospin staggered potential and the intrinsic spin-orbit coupling. The crossed Andreev reflection with the local Andreev reflection and the elastic cotunneling being completely eliminated can be realized for the electrons with the specific spin-valley index when the intrinsic spin-orbit couplings in the left graphene and the right graphene possess the opposite sign. The perfect crossed Andreev reflection with its probability equal to $100\%$ can be obtained in the space consisting of the incident angle and the energy of the electrons. The crossed conductance and its oscillation with the superconductor length are also investigated. The energy ranges for the crossed Andreev reflection without the local Andreev reflection and the elastic cotunneling are clarified for the different magnitudes of the pseudospin potential and the spin-orbit coupling. The spin-valley index of the electrons responsible for the perfect crossed Andreev reflection can be switched by changing the sign of the intrinsic spin-orbit coupling or exchanging the biases applied on the left graphene and the right graphene. Our results are helpful for designing the flexible and high-efficiency Cooper pair splitter based on the spin-valley degree of freedom.

cond-mat.supr-con↗

arXiv2023

Smart Roads: Roadside Perception, Vehicle-Road Cooperation and Business Model

Smart roads have become an essential component of intelligent transportation systems (ITS). The roadside perception technology, a critical aspect of smart roads, utilizes various sensors, roadside units (RSUs), and edge computing devices to gather real-time traffic data for vehicle-road cooperation. However, the full potential of smart roads in improving the safety and efficiency of autonomous vehicles only can be realized through the mass deployment of roadside perception and communication devices. On the one hand, roadside devices require significant investment but can only achieve monitoring function currently, resulting in no profitability for investors. On the other hand, drivers lack trust in the safety of autonomous driving technology, making it difficult to promote large-scale commercial applications. To deal with the dilemma of mass deployment, we propose a novel smart-road vehicle-guiding architecture for vehicle-road cooperative autonomous driving, based on which we then propose the corresponding business model and analyze its benefits from both operator and driver perspectives. The numerical simulations validate that our proposed smart road solution can enhance driving safety and traffic efficiency. Moreover, we utilize the cost-benefit analysis (CBA) model to assess the economic advantages of the proposed business model which indicates that the smart highway that can provide vehicle-guided-driving services for autonomous vehicles yields more profit than the regular highway.

eess.SP↗

arXiv2023

Spin-valley dependent double Andreev reflections in the proximitized graphene/superconductor junction

We study the Andreev reflections and the quantum transport in the proximitized graphene/superconductor junction. The proximitized graphene possesses the pseudospin staggered potential and the intrinsic spin-orbit coupling induced by substrate, which are responsible for the spin-valley dependent double Andreev reflections and the anomalous transport properties in the junction. The pure specular Andreev reflection can happen in the superconducting gap for the $K\uparrow$ and $K'\downarrow$ electrons while the pure retro-Andreev reflection happens for the $K\downarrow$ and $K'\uparrow$ electrons. The coexisting two types of Andreev reflections related to the fixed spin-valley indices strongly depend on the chemical potential of the proximitized graphene. The condition of the emergence of the specific type of Andreev reflection for the electrons with the fixed spin-valley index is clarified. The spin-valley dependent Andreev reflections bring about the peculiar conductance spectra of the junction, which can help determine the values of the pseudospin staggered potential and the intrinsic spin-orbit coupling induced in graphene. Hence, our research results not only provide an experimental method to detect the induced potential and coupling in graphene but also establish the foundation of the superconductor electronics based on the spin-valley indices.

cond-mat.mes-hall↗

arXiv2023

Imaging the Breathing of a Platinum Nanoparticle in Electrochemical Environment

Surface strain is widely used in gas phase catalysis and electrocatalysis to control the binding energies of adsorbates on metal surfaces. However, $in$ $situ$ or $operando$ strain measurements are experimentally challenging, especially on nanomaterials. Here, we take advantage of the 4$^{th}$ generation Extremely Brilliant Source at the European Synchrotron Radiation Facility (ESRF-EBS, Grenoble, France) to quantify the distribution of strain inside a Pt nanoparticle, and to determine its morphology in an electrochemical environment. Our results show for the first time evidence of heterogeneous and potential-dependent strain distribution between highly-coordinated ({100} and {111} facets) and under-coordinated atoms (edges and corners) as well as evidence of strain propagation from the surface to the bulk of the nanoparticle. These results provide dynamic structural insights to better simulate and design efficient nanocatalysts for energy storage and conversion applications.

cond-mat.mtrl-sci↗

arXiv2022

Group frame neural network of moving object ghost imaging combined with frame merging algorithm

The nature of multiple samples to extract correlation information limits the applications of ghost imaging of moving objects. A novel multi-to-one neural network is proposed and the concept of "batch frame" is introduced to improve the serial imaging method. The neural network extracts more correlation information from a small number of samples, thus reducing the sampling ratio of the ghost imaging technique. We combine the correlation characteristics between images to propose a frame merging algorithm, which eliminates the dynamic blur of high-speed moving objects and further improves the reconstruction quality of moving object images at a low sampling ratio. The experimental results are consistent with the simulation results.

eess.IV↗

arXiv2019

Transition fronts of two species competition lattice systems in random media

The current paper is devoted to the study of existence and non-existence of transition fronts for two species competition lattice system in random media, and explore the influence of randomness of the media on the wave profiles and wave speeds of such transition fronts. We first establish comparison principle for sub-solutions and super-solutions of the related cooperative system. Next, under some proper assumptions, we construct appropriate sub-solutions and super-solutions for the cooperative system. Finally, we show that random transition fronts exist if their least mean speed is greater than an explicit threshold and there is no random transition front with least mean speed less than the threshold.

math.DS↗

arXiv2019

Thermal light edge enhancement ghost imaging of phase objects

We propose a experimental scenario of edge enhancement ghost imaging of phase objects with nonlocal orbital angular momentum (OAM) phase filters. Spatially incoherent thermal light is separated into two daughter beams, the test and reference beams, in which the detected objects and phase filters are symmetrically placed,respectively. The results of simulation experiment prove that the edge enhanced ghost images of phase objects can be achieved through the second-order light field intensity correlation measurement owing to the OAM correlation characteristics. Further simulation results demonstrate that the edge enhanced ghost imaging system dose not violate a Bell-type inequality for the OAM subspace, which reveals the classical nature of the thermal light correlation.

quant-ph↗

arXiv2019

Nonlocal Quantum Erasure of Phase Objects

The Franson interference is a fourth order interference effect, which unlike the better known Hong-Ou-Mandel interference, does not require the entangled photon pairs to be present at the same space-time location for interference to occur - it is nonlocal. Here, we use a modified Franson interferometer to experimentally demonstrate the nonlocal erasure and correction of an image of a phase-object taken through coincidence imaging. This non-local quantum erasure technique can have several potential applications such as phase corrections in quantum imaging and microscopy and also user authentication of two foreign distant parties.

quant-ph↗