A5074277827- Traffic Prediction and Management Techniques
- Human Mobility and Location-Based Analysis
- Traffic control and management
- Video Surveillance and Tracking Methods
- Advanced Photocatalysis Techniques
- Graphene and Nanomaterials Applications
- Microfluidic and Capillary Electrophoresis Applications
- Nanoplatforms for cancer theranostics
- Transportation Planning and Optimization
- Time Series Analysis and Forecasting
- Advanced Biosensing Techniques and Applications
- Evaluation Methods in Various Fields
- Evaluation and Optimization Models
- Advanced Graph Neural Networks
- Low-power high-performance VLSI design
- Advanced Nanomaterials in Catalysis
- Air Quality Monitoring and Forecasting
- Advanced oxidation water treatment
- Nanomaterials for catalytic reactions
- Data-Driven Disease Surveillance
- Advanced MIMO Systems Optimization
- Telecommunications and Broadcasting Technologies
- Constraint Satisfaction and Optimization
- Target Tracking and Data Fusion in Sensor Networks
- Cooperative Communication and Network Coding
Binghamton University
2022-2025
Soochow University
2023-2024
Nanjing University of Aeronautics and Astronautics
2024
Harbin Engineering University
2024
Huawei Technologies (Sweden)
2021-2023
Shandong Agricultural University
2021-2023
Northwestern Polytechnical University
2023
Shandong University of Finance and Economics
2023
Worcester Polytechnic Institute
2019-2022
University of Electronic Science and Technology of China
2019-2022
Soft, skin-interfaced microfluidic platforms are capable of capturing, storing, and assessing sweat chemistry total loss, which provides essential insight into human physiological health.
Given an urban development plan and the historical traffic observations over road network, Conditional Urban Traffic Estimation problem aims to estimate resulting status prior deployment of plan. This is great importance transportation management, yet very challenging because would change local travel demands drastically new demand pattern might be unprecedented in data. To tackle these challenges, we propose a novel Generative Adversarial Network (Curb-GAN), which provides estimations...
Global placement, a critical step in designing the physical layout of computer chips, is essential to optimize chip performance. Prior global placement methods each circuit design individually from scratch. Their neglect transferable knowledge limits solution efficiency and performance as complexity drastically increases. This study presents TransPlace, framework that learns place millions mixed-size cells continuous space. TransPlace introduces i) Netlist Graph efficiently model netlist...
Given historical traffic distributions and associated urban conditions observed in a city, the conditional estimation problem aims at estimating realistic future projections of under set new conditions, e.g. , bus routes, rainfall intensity travel demands. The is important reducing congestion, improving public transportation efficiency, facilitating planning. However, solving this challenging due to strong spatial dependencies patterns complex relations between conditions. Recently, we...
Spatial reasoning is an essential problem in embodied AI research. Efforts to enhance spatial abilities through supplementary data and fine-tuning have proven limited ineffective when addressing complex tasks, largely due their dependence on language-based outputs. While some approaches introduced a point-based action space mitigate this issue, they fall short managing more intricate tasks within environments. This deficiency arises from failure fully exploit the inherent thinking...
The complexity of scenes and variations in image quality result significant variability the performance semantic segmentation methods remote sensing imagery (RSI) supervised real-world scenarios. This makes evaluation such scenarios an issue to be resolved. However, most existing metrics are developed based on expert-labeled object-level annotations, which not applicable To address this issue, we propose RS-SQA, unsupervised assessment model for RSI vision language (VLM). framework leverages...
Recent advancements in Large Language Models (LLMs) and Vision-Language (VLMs) have made them powerful tools embodied navigation, enabling agents to leverage commonsense spatial reasoning for efficient exploration unfamiliar environments. Existing LLM-based approaches convert global memory, such as semantic or topological maps, into language descriptions guide navigation. While this improves efficiency reduces redundant exploration, the loss of geometric information language-based...
The COVID-19 pandemic has posed grand challenges to policy makers, raising major social conflicts between public health and economic resilience. Policies such as closure or reopen of businesses are made based on scientific projections infection risks obtained from dynamics models. While most parameters in models can be set using domain knowledge COVID-19, a key parameter - human mobility is often challenging estimate due complex contexts limited training data under escalating conditions. To...
Urban traffic status (e.g., speed and volume) is highly dynamic in nature, namely, varying across space evolving over time. Thus, predicting such dynamics of great importance to urban development transportation management. However, it very challenging solve this problem due spatial-temporal dependencies uncertainties. In article, we the prediction from Bayesian meta-learning perspective propose a novel continuous meta-learner (cST-ML), which trained on distribution tasks segmented by...
For the formation and obstacle avoidance challenges of UAVs (unmanned aerial vehicles) in complex scenarios, this paper proposes an improved collaborative strategy based on APF (artificial potential field). This combines graph theory, Leader–Follower method, APF. Firstly, we used theory to design topology dynamically adjust distances between real time. Secondly, introduced avoid obstacles complicated environments. algorithm innovatively integrates method. The attractive field is replaced by...
Abstract Highly efficient and stimulus‐responsive nanomedicines for cancer treatment are currently receiving tremendous attention. In this study, an acid‐triggered charge‐reversible graphene‐based all‐in‐one nanocomplex is appropriately designed by surface modification with multilayer polymers simultaneous co‐transportation of photosensitizer indocyanine green (ICG) oligonucleotide inhibitor miR‐21 (miR‐21i) to achieve highly genetic phototherapy in a controlled manner. The (denoted as...
Cr (VI) has been considered to be a harmful environmental pollutant due its toxicity, mobility and strong oxidation. It become challenging remove from wastewater. In this work, series of supported palladium-based catalysts were synthesized via facile wet chemical reduction method. Among all the as-synthesized catalysts, Pd/TiO2 (P25) showed optimized catalytic activity for (III) using formic acid (HCOOH) as reductant. More than 99% K2Cr2O7 (50 mg/L) was reduced completely within 30 min at 25...
Abstract Lake aquaculture in China has become more common, but there been only limited research on its effects the quality of lake water. We measured selected water parameters from July to September 2015 23 lakes middle reach Yangtze River basin investigate different types quality. The were classified as “low,” “medium,” “high,” or “fallow” based their stocking rate. results showed that turbidity, total suspended solids, chemical oxygen demand, conductivity, chloride, nitrogen, phosphorus,...
The rapid progress of urbanization has expedited the process urban planning, e.g., new residential, commercial areas, which in turn boosts local travel demand. We propose a novel "off-deployment traffic estimation problem", namely, to foresee condition changes region prior deployment construction plan. This problem is important city planners evaluate and develop plans. However, this task challenging. Traditional approaches lack ability solve problem, since no data about impact can be...
Herein, we report a simple and highly efficient approach for simultaneous in situ synthesis of Cu nanoparticles on Mg-Al-LDH (in reduced CuMgAl-LDH) from Cu-Mg-Al ternary LDH catalytic transfer hydrogenation furfural (FAL) to furfuryl alcohol (FOL) using isopropanol (2-PrOH) as reducing agent hydrogen source. The CuMgAl-LDH, especially Cu1.5Mg1.5Al1-LDH precursor, offered excellent performance the FAL FOL (achieving almost full conversion with 98.2% selectivity FOL). Strikingly, catalyst was...
Estimating human mobility responses to the large-scale spreading of COVID-19 pandemic is crucial, since its significance guides policymakers give Non-pharmaceutical Interventions, such as closure or reopening businesses. It challenging model due complex social contexts and limited training data. Recently, we proposed a conditional generative adversarial network (COVID-GAN) estimate response under set policy conditions integrated from multiple data sources. Although COVID-GAN achieves good...