A5101624082- Transportation Planning and Optimization
- Traffic Prediction and Management Techniques
- Data Management and Algorithms
- Traffic control and management
- Advanced Memory and Neural Computing
- Ferroelectric and Negative Capacitance Devices
- Transition Metal Oxide Nanomaterials
- Smart Parking Systems Research
- Vehicle Routing Optimization Methods
- Agriculture Sustainability and Environmental Impact
- Machine Learning and ELM
- Electronic and Structural Properties of Oxides
- Coal and Its By-products
- Online Learning and Analytics
- Environmental Impact and Sustainability
- Innovative Teaching and Learning Methods
- Hydrogen Storage and Materials
- Indoor and Outdoor Localization Technologies
- Hybrid Renewable Energy Systems
- Sustainability and Ecological Systems Analysis
- Wireless Power Transfer Systems
- Seedling growth and survival studies
- Sustainable Agricultural Systems Analysis
- Odor and Emission Control Technologies
- Electrodeposition and Electroless Coatings
Jilin Agricultural University
2013-2024
University of Electronic Science and Technology of China
2017-2020
Nanyang Technological University
2014-2016
Shanghai Jiao Tong University
2013
Tianjin University
1996
With the ever-increasing demand in urban mobility and modern logistics sector, vehicle population has been steadily growing over past several decades. One natural consequence of growth is increase traffic congestion. Almost all (metropolitan) cities including major ones, like Los Angeles, Beijing, New York, are suffering from heavy Statistics show that, 2015, 43 China a prolonged travel time more than 1.5 h every day during rush hours. In meanwhile, accidents plaguing economic development as well.
This paper aims at solving the stochastic shortest path problem in vehicle routing, objective of which is to determine an optimal that maximizes probability arriving destination before a given deadline. To solve this problem, we propose data-driven approach, directly explores big data generated traffic. Specifically, first reformulate original as cardinality minimization based on samples travel time each road link, can be obtained from GPS trajectory vehicles. Then, apply ℓ <sub...
Reducing traffic delay is of crucial importance for the development sustainable transportation systems, which a challenging task in studies stochastic shortest path (SSP) problem. Existing methods based on probability tail model to solve SSP problem, seek that minimizes occurrence, equal maximizing reaching destination before deadline (i.e., arriving time). However, they suffer from low accuracy or high computational cost. Therefore, we design novel and practical Q-learning approach where...
More realistic than deterministic vehicle routing, stochastic routing considers uncertainties in traffic. Its two representative optimization models are the probability tail (PT) and shortest path problem with delay excess penalty (SSPD), which can be approximately solved by expressing them as mixed-integer linear programming (MILP) problems. The traditional method to solve these MILP problems, i.e., branch bound (B&B), suffers from exponential computation complexity because of integer...
The stochastic shortest path problem is of crucial importance for the development sustainable transportation systems. Existing methods based on probability tail model seek that maximizes arriving at destination before a deadline. However, they suffer from low accuracy and/or high computational cost. We design novel Q-learning method where converged Q-values have practical meaning as actual probabilities time so to improve accuracy. By further adopting dynamic neural networks learn value...
Abstract The corrosion behavior of electrodeposited Ni-P, Ni-W, Ni-W-P, and Fe-W alloys was tested, the effects additive elements W P on resistance amorphous deposit...
Non-recurring incidents such as accidents and vehicle breakdowns are the leading causes of severe traffic congestions in large cities. Consequently, anticipating duration events advance can be highly useful mitigating resultant congestion. However, availability partial information or ever-changing ground conditions makes task forecasting particularly challenging. In this paper, we propose an adaptive ensemble model that provide reasonable forecasts even when a limited amount is available...
This paper focuses on a specific stochastic shortest path (SSP) problem, namely the punctuality problem. It aims to determine that maximizes probability of arriving at destination before specified deadline. The popular solution this problem always formulates it as cardinality minimization by considering its data-driven nature, which is approximately solved 1 , -norm relaxation. To address accurately, we consider special character in cardinality-based and reformulate introducing additional...
Neuromorphic computation has been a hot research area over the past few years. Memristor, as one of neuromorphic materials retains conductance value and is able to adapt it with changing input voltages. This paper pioneers in computing paradigm implementation (through memristor) for Extreme Learning Machine (ELM), which most popular machine learning algorithms. By simulating biological synapses memristors combining memory property memristor high-efficient processing ability ELM, three-layer...
Increasing soil contamination with nickel (Ni) and copper (Cu) is a growing environmental concern, adversely affecting ecosystems the survival of both plants animals. This study investigated morphological physiological responses Euphorbia marginata Pursh seedlings to varying concentrations Ni Cu over 45-day period. The findings revealed that low enhanced indexes, root biomass, photosynthetic pigment content E. marginata, while high inhibited these parameters. Compared control, stresses...
This paper aims at solving a stochastic shortest path problem. The objective is to determine an optimal which maximizes the probability of arriving on time given constraint (i.e., deadline). To solve this problem, we propose data-driven approach. We first reformulate original finding problem as cardinality minimization Then, apply L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> norm technique transformed into mix integer linear...
In this study, the authors improve faster criterion in vehicle routing by extending bi‐delta distribution to bi‐normal distribution, which is a reasonable assumption for travel time on each road link. Based assumption, theoretical models are built an arbitrary path and subsequently adopted evaluate two candidate paths through probabilistic comparison. Experimental results demonstrate behaviour of link practice, verify criterion's superiority determining optimal either artificial network with...
In metropolitan areas, about 50% of traffic delays are caused by non-recurring incidents. Hence, accurate prediction the duration such events is critical for management authorities. this paper, we study predictability incidents considering various external factors. As incident data typically sparse, training a large number models (for instance, model each road) not possible. On other hand, one entire network may be suitable solution, as will too generalized and consequently unsuitable many...
Finding available parking spaces in dense urban areas is a globally recognized issue mobility. Whereas prior studies have focused on outdoor/street parking, we target at (indoor) garages where the infrastructure supports (e.g., GPS and Wi-Fi) assumed by existing proposals are unavailable counting vehicles crowdsensing difficult. To this end, present ParkGauge as system gauging congestion level of garages; it infers (coarse-grained) occupancy from crowdsensed characteristics instead parked...
Integrated crop–livestock systems (ICLSs) can improve the sustainability of agriculture. The configuration an ICLS to achieve sustainable development while maintaining effectiveness resource utilization is complicated due conflicts between economic performance and environmental protection. In this paper, a novel optimization model-based emergy evaluation (OMEE) method proposed for configuration. OMEE encompasses analysis improved non-dominated sorting genetic algorithm II (NSGA-II)...
Greenhouse gas emission is a key issue in the sustainable development of agriculture. To effectively predict greenhouse emissions beef cattle, model proposed based on system dynamics and calculation methods, scenario set as ‘Straw to Beef’ project Jilin Province. The was built baseline (feed precision: 60%, breeding environment: dry fattening farm, corn straw utilization: burning straw), with single- comprehensive reduction scenarios considered, predicting trends potentials from cattle...
Improving the performance of transportation network is a crucial task in traffic management. In this paper, we start with cooperative routing problem, which aims to minimize chance road breakdown. To address propose subgradient method, can be naturally implemented as semi-centralized pricing approach. Particularly, each link adopts scheme calculate and adjust local toll regularly, while vehicles update their routes costs by exploiting global information. prevent potential oscillation brought...
Compared with the traditional education, advantages represented by distance education are discussed in this paper.Based on analysis existing problems teaching process of leaner-centered model is proposed and "task-driven" system constructed to improve effectiveness education.