A5100353236- Traffic Prediction and Management Techniques
- Semantic Web and Ontologies
- Human Mobility and Location-Based Analysis
- Advanced Database Systems and Queries
- Data Management and Algorithms
- Transportation Planning and Optimization
- Advanced Graph Neural Networks
- Smart Parking Systems Research
- Video Surveillance and Tracking Methods
- Anomaly Detection Techniques and Applications
- Graph Theory and Algorithms
- Traffic control and management
- Constraint Satisfaction and Optimization
- Adversarial Robustness in Machine Learning
- Transportation and Mobility Innovations
- Geographic Information Systems Studies
- Service-Oriented Architecture and Web Services
- Evacuation and Crowd Dynamics
- Topic Modeling
- Energy Load and Power Forecasting
- Remote Sensing and Land Use
- Optimization and Search Problems
- Mining Techniques and Economics
- Asymmetric Hydrogenation and Catalysis
- Data Quality and Management
Shanghai Jiao Tong University
2011-2025
University of Illinois Urbana-Champaign
2025
Northeastern University
2024
Shandong University of Science and Technology
2024
Southwest University of Science and Technology
2024
University of Jinan
2024
Zhengzhou University
2024
Beijing University of Technology
2022-2023
Bridge University
2023
Tencent (China)
2023
Traffic signal control is an emerging application scenario for reinforcement learning. Besides being as important problem that affects people's daily life in commuting, traffic poses its unique challenges learning terms of adapting to dynamic environment and coordinating thousands agents including vehicles pedestrians. A key factor the success modern relies on a good simulator generate large number data samples The most commonly used open-source SUMO is, however, not scalable road network...
Load forecasting is an essential part of a power system. It enhances the energy-efficiency and reliable operation As depicted in proposal smart grid, increasing number meters have been being installed many utilities on global scale. Thus, large historical residential consumption data now can be obtainable easily which were not available past. However, traditional techniques may satisfy much higher demand precision load forecasting. In this paper, novel approach to short-term using LSTM (long...
A cascade [3 + 2] annulation and ring opening of N-aryloxyacetamides with 1-alkynylcyclobutanols via Rh(III)-catalyzed redox-neutral C–H/C–C activations using internal oxidative O–NHAc −OH as the dual directing groups has been achieved. This reaction provided an efficient regioselective approach to benzofuran derivatives good functional group compatibility high yields.
In general, enantioselective C–H functionalization of N-monosubstituted anilines is a highly challenging task owing to the competitive chemoselective N–H bond insertion reactions. this paper, we reported direct chemo-, site-, and para aminoalkylation aniline derivatives with isatin-derived ketimines in presence chiral phosphoric acids (CPAs) offered practical strategy for asymmetric containing bonds.
Post-industrial neighborhoods are valued for their historical and cultural significance but often contend with challenges such as physical deterioration, social instability, decay, which diminish residents’ satisfaction. Leveraging urban renewal a catalyst, it is essential to boost satisfaction by enhancing the environmental quality of these areas. This study, drawing on data from Shenyang, China, utilizes combined strengths gradient boosting decision trees (GBDTs) asymmetric...
Credit scoring is a crucial aspect of financial risk management, enabling lenders to evaluate the creditworthiness individ uals and entities. This paper presents comprehensive comparison various classical machine learning models determine most effective one for predicting credit scores. The evaluated include logistic regression, decision trees, random forests, support vector machines, gradient boosting, adaptive boosting (AdaBoost), k-nearest neighbors (KNN), Naive Bayes, eXtreme Gradient...
With the refinement of urban transportation network, more and passengers choose combined mode. To provide better inter-trip services, it is necessary to integrate forecast passenger flow multi-level rail transit network improve connectivity different transport modes. The difficulty prediction lies in complexity spatiotemporal characteristics data, composition, research. At present, most research focuses on one mode or within city, while comprehensive analysis under various modes less. This...
Accurate timely estimation of emissions nitrogen oxides (NOx) is a prerequisite for designing an effective strategy reducing O3 and PM2.5 pollution. The satellite-based top-down method can provide near-real-time constraints on emissions; however, its efficiency largely limited by efforts in dealing with the complex emission-concentration response. Here, we propose novel machine-learning-based using physically informed variational autoencoder (VAE) emission predictor to infer NOx from...
The MapReduce framework has proved to be very efficient for data-intensive tasks. Earlier work successfully applied large scale RDFS/OWL reasoning. In this paper, we move a step forward by considering scalable reasoning on semantic data under fuzzy pD* semantics (i.e., an extension of OWL with vagueness). To the best our knowledge, is first investigate how can solve scalability issue in OWL. While most optimizations considered existing are also applicable semantics, unique challenges arise...
The deterioration of physical spaces and changes in the social environment have led to significant challenges low life satisfaction among residents post-industrial neighborhoods. While resident is closely linked built environment, attributes alone do not directly influence human feelings. perception processing urban environments, or city images, play a critical mediating role. Previous studies often explored impact either image space on separately, lacking an integrated approach. This study...
The heavy traffic congestion problem has always been a concern for modern cities. To alleviate congestion, researchers use reinforcement learning (RL) to develop better signal control (TSC) algorithms in recent years. However, most RL models are trained and tested the same flow environment, which results serious overfitting problem. Since environment real world keeps varying, these can hardly be applied due lack of generalization ability. Besides, limited number accessible data brings extra...
Haulage cost typically accounts for around 30% of the total mass earthmoving projects. The temporary road network is a major factor influencing haulage and production efficiency. simulation operations considering networks, not only facilitates site formation design but also leads to realistic, cost-effective construction plans. Utilizing Floyd-Warshall algorithm linear programming, this study formulates problem sheds light on potential benefits selecting routes directions handling jobs. An...
The Web contains a large amount of documents and increasingly, also semantic data in the form RDF triples. Many these triples are annotations that associated with documents. While structured query is principal mean to retrieve data, keyword queries typically used for document retrieval. Clearly, hybrid search seamlessly integrates formalisms both can address more complex information needs. In this paper, we present CE2, an integrated solution leverages mature database retrieval technologies...
Wireless sensor networks (WSNs) can implement complicated tasks through collaboration among multiple nodes. The low-cost sensors in WSNs often generate noisy and even faulty measurements, which will degrade the network performance. Therefore developing collaborative signal processing (CSP) algorithms that has high fault tolerance ability is necessary for increasingly deployed WSNs. In this study, authors propose a novel tolerant fusion scheme to reliable vehicle classification by integrating...