A5003841733- Transportation and Mobility Innovations
- Transportation Planning and Optimization
- Urban Transport and Accessibility
- Spectroscopy and Chemometric Analyses
- Food composition and properties
- Spectroscopy Techniques in Biomedical and Chemical Research
- Air Quality and Health Impacts
- Microbial Metabolites in Food Biotechnology
- Seed and Plant Biochemistry
- Fault Detection and Control Systems
- Vehicle emissions and performance
- Air Quality Monitoring and Forecasting
- Traffic control and management
- Polysaccharides Composition and Applications
- Supply Chain and Inventory Management
- Traffic Prediction and Management Techniques
- Water Quality Monitoring and Analysis
- Remote Sensing and Land Use
- Sustainable Supply Chain Management
- Sparse and Compressive Sensing Techniques
- Maritime Navigation and Safety
- Maritime Ports and Logistics
- Advanced Computing and Algorithms
- Environmental Quality and Pollution
- Machine Learning and ELM
Nanjing University of Finance and Economics
2021-2025
Anhui Agricultural University
2024
Hohai University
2021
Changjiang Water Resources Commission
2021
Northwestern University
2016-2019
Shanghai Jiao Tong University
2015-2019
Taipei Municipal Jen-Ai Hospital
2008
Abstract PM 2.5 mass concentration prediction is an important research issue because of the increasing impact air pollution on urban environment. In this paper, a forecasting framework incorporating meteorological factors based multiple kernel learning (MKL) proposed to forecast near future . addition, we develop novel two‐step algorithm for solving primal MKL problem. Compared with most existing 2‐step algorithms, does not require optimal step size updating combination coefficients by...
In this paper, we study the coordination issue in a dual-channel green supply chain with one manufacturer and retailer. The demand traditional channel is assumed to be dependent on retail price, sales effort degree. Due characteristic of live broadcast selling, direct price discount. On basis analyzing degree strategies under centralized model, two decentralized models are presented. Moreover, prove feasibility sharing R&D costs advertisement (CS-GS) contract through bargaining problems...
Integrating activity-based models (ABMs) with simulation-based dynamic traffic assignment (DTA) have gained attention from transportation planning agencies seeking tools to address the arising challenges as well policies such road pricing. Optimal paths least generalized cost are needed route travelers at DTA level, while ABM only information is (without fully specified paths). Thus, rerunning (executing) path-finding algorithm each iteration of and does not seem be efficient, especially for...
The dynamic multimodal network assignment problem at the daily schedule level is addressed by integrating an activity-based model and a traffic tool through unified framework. framework achieves this integration while retaining disaggregated individualized information. formulated as fixed-point problem, equilibrium achieved minimizing gap between expected travel time, which used to generate travelers’ individual household activity schedules, their experienced times, simulated tool....
This paper presents a first-order approach integrated with activity-based modeling and dynamic traffic assignment framework to model the impact of autonomous vehicles on household travel activity schedules. By considering shared rides among members, mode choices, re-planning departure times, rescheduling sequences, two optimization models—basic personal owned vehicle (POAV) enhanced POAV model—are presented. The proposed is tested for different models at level sizes. schedules each were...
With the complex and changeable environment, demand yield in perishable products supply chain are usually uncertain. This paper studies a joint contract that combines revenue sharing with quantity discount to coordinate under uncertainty, which consists of one manufacturer retailer. The retailer pays down payment at beginning, gives shares proportion profit from last. To make sure both members want adopt this contract, we prove feasibility achieving win–win situation. In addition,...
This paper presents the development, implementation, and evaluation of predictive active transportation demand management (ATDM) weather-responsive traffic (WRTM) strategies to support operations for weather-affected conditions with estimation prediction system models. First, problem is defined as a dynamic process evolution under impact operational (interventions). A list research questions be addressed provided. Second, systematic framework implementing evaluating weather-related ATDM...
This paper proposes a forecasting methodology that investigates set of different sparse structures for the vector autoregression (VAR) model using Ivanov‐based least absolute shrinkage and selection operator (LASSO) framework. The variant auxiliary problem principle method is used to solve various LASSO‐VAR variants, which supported by parallel computing with simple closed‐form iteration linear convergence rate. A test case ten crude oil spot prices demonstrate improvement in skills gained...
Raman spectroscopy has been more widely used recently in the quality detection of dairy products. Because can conduct rapid analyses small sample sizes at high dimensions, its use industry is becoming a hot topic for researchers. To improve robustness and accuracy logistic regression identification method, new method was proposed that combines distributionally robust optimization technique fused lasso with regression. Then, to analyze two types products were collected anti-jamming testing...
Aiming at the problem of inaccurate fruit recognition and diameter detection in persimmon inspection process, this research proposes a novel accurate algorithm based on Region-based Convolutional Neural Network (RCNN) Mask instance segmentation algorithm. The strategically targets object interest by integrating cropping, morphological processing, concave point modules into fully connected layer following Region Interest (RoI) feature. Initially, separates front back background cropped target...
Abstract :In addressing the machine recognition and detection of persimmon ripeness in orchards, this study comprehensively considers impact natural light on accuracy, as well precision speed requirements inspection robots. An optimization algorithm based an encoder-driven masked Region-Based Convolutional Neural Network (RCNN) is introduced research. The proposed method aims to accurately detect identify ripeness. It utilizes colour difference meticulously calculate components essential for...