A5100634648- Transportation Planning and Optimization
- Traffic Prediction and Management Techniques
- Speech Recognition and Synthesis
- Speech and Audio Processing
- Music and Audio Processing
- Traffic and Road Safety
- Air Traffic Management and Optimization
- Geoscience and Mining Technology
- Human Mobility and Location-Based Analysis
- Economic and Environmental Valuation
- Vehicle emissions and performance
- Rough Sets and Fuzzy Logic
- Data Mining Algorithms and Applications
- Urban Transport and Accessibility
- Environmental Impact and Sustainability
- Smart Parking Systems Research
- Neural Networks and Reservoir Computing
- Reinforcement Learning in Robotics
- Recycling and Waste Management Techniques
- Anomaly Detection Techniques and Applications
- Autonomous Vehicle Technology and Safety
- Railway Systems and Energy Efficiency
- Educational Technology and Assessment
- Electric Vehicles and Infrastructure
- Karst Systems and Hydrogeology
Institute of Art
2024
Xi'an Jiaotong University
2010-2023
Nanyang Technological University
2023
Nanjing University of Aeronautics and Astronautics
2016-2022
Northwestern Polytechnical University
2022
China University of Mining and Technology
2017-2021
Beihang University
2020
Chinese People's Liberation Army
2018
University of Central Florida
2017
Shandong University of Science and Technology
2010
Large language models (LLMs) have shown great potential across various industries due to their remarkable ability generalize through instruction tuning. However, the limited availability of domain-specific data significantly hampers performance on specialized tasks. While existing methods primarily focus selecting training from general datasets that are similar target domain, they often fail consider joint distribution instructions, resulting in inefficient learning and suboptimal knowledge...
Existing self-supervised pre-trained speech models have offered an effective way to leverage massive unannotated corpora build good automatic recognition (ASR). However, many current are trained on a clean corpus from single source, which tends do poorly when noise is present during testing. Nonetheless, it crucial overcome the adverse influence of for real-world applications. In this work, we propose novel training framework, called deHuBERT, reduction encoding inspired by H. Barlow's...
Apart from promoting social-economic development and increasing social employment, the real estate industry in China has also brought up problems such as high energy consumption emissions. Scholars now focus more on conservation, emission reduction sustainable of companies their current research. The data used by this paper are three-year panel 2015 to 2018, with observations 15 representative companies. CO2 green credit index introduced undesirable output respectively. First, DEA model...
This study presents a combined Long Short-Term Memory and Extreme Gradient Boosting (LSTM-XGBoost) method for flight arrival flow prediction at the airport. Correlation analysis is conducted between historic input features. The XGBoost applied to identify relative importance of various variables. time-series data airport selected features are taken as variables, subsequent output variable. model parameters sequentially updated based on recently collected new predicting results. It found that...
The chemical forms of S, C and O high-sulphur bituminous coal were analysed before after microwave desulphurisation by using X-ray photoelectron spectroscopy (XPS). Sulphur existed as 17.908% mercaptan (sulfoether) 62.160% thiophene irradiation decreased to 4.644% 49.483% with assistance alkali solution. On the contrary, sulphur that occurred in form sulfone (sulfoxide) sulphates increased from 7.516% 12.416% 14.697% 31.176%, respectively. This increase may be due mobility sulphur-containing...
This study presents a multiobjective evaluation method to estimate the performance of various midblock crosswalk treatments on urban streets. The considered objectives included traffic operation, safety, environmental impacts, and costs. Data were collected at 16 crosswalks in Nanjing area China. Vissim simulation models developed calibrated with field data evaluate operational impacts treatments. For impact total control delay vehicles major streets pedestrians estimated. frequency...
This paper proposes a real-time trajectory prediction method for quadrotors based on bidirectional gated recurrent unit model. Historical data of ten types were obtained. The units constructed and utilized to learn the historic data. results compared with traditional test its performance. efficiency proposed algorithm was investigated by comparing training loss time. over testing datasets showed that model produced better than baseline models all scenarios datasets. It also found can...
As roadway resources are being occupied by curbside parking and because of the operational characteristics maneuvers, capacity adjacent travel lane can be significantly reduced. To analyze influence on bicycle lane, a conflict technique based additive flow was applied to establish base model. The actual with curb then established adjusting reflect influence: width, time proportion e-bikes. Eight datasets from exclusive lanes different widths maneuvers were collected in Nanjing, China for...
Noise robustness in keyword spotting remains a challenge as many models fail to overcome the heavy influence of noises, causing deterioration quality feature embeddings. We proposed contrastive regularization method called Inter-Intra Contrastive Regularization (I2CR) improve representations by guiding model learn fundamental speech information specific cluster. This involves maximizing similarity across Intra and Inter samples same class. As result, it pulls instances closer more...
Addressing calls for understanding the complexity of reward creativity on employee creativity, this study investigated how an individual's appraisal moderates relationship between and intrinsic motivation. We also explored whether effect creative performance via motivation is contingent reward. Two competence-related variables from Lazarus Folkman (1984) were adapted to context, representing expectations positive or negative competence outcomes reward, namely, challenge (perceived potential...