- Transportation Planning and Optimization
- Traffic control and management
- Urban Transport and Accessibility
- Traffic Prediction and Management Techniques
- Transportation and Mobility Innovations
- Visual Attention and Saliency Detection
- Urban and Freight Transport Logistics
- Advanced Image and Video Retrieval Techniques
- Smart Parking Systems Research
- Topic Modeling
- Image Enhancement Techniques
- Video Analysis and Summarization
- Fatigue and fracture mechanics
- Advanced Text Analysis Techniques
- Advanced Neural Network Applications
- Forecasting Techniques and Applications
- Data Management and Algorithms
- Human Motion and Animation
- Data Stream Mining Techniques
- Virtual Reality Applications and Impacts
- Machine Learning in Healthcare
- Human Mobility and Location-Based Analysis
- Human Pose and Action Recognition
- Bayesian Modeling and Causal Inference
- Robotics and Automated Systems
Jiangnan University
2025
Xinjiang University
2025
University of Manchester
2024
Shanghai Jian Qiao University
2023
Xiamen University
2023
Nanjing Foreign Language School
2022
Southeast University
2020
Cloud Computing Center
2020
Southeast University
2013-2018
The Synergetic Innovation Center for Advanced Materials
2015
ABSTRACT The stability of prediction precision under complex loading paths is one the key challenges in task multiaxial fatigue life prediction. This study addresses unstable machine learning models, while further improving A novel neural network based on a transformer framework proposed to capture dependencies between data at multiple scales. Meanwhile, physical loss function with soft adjustments add constraints network. These two mechanisms assist each other accuracy and Performance...
Field Effect Transistors (FETs) are at the core of modern semiconductor technology, and miniaturization their size has posed challenges such as short-channel effects for traditional manufacturing processes. This paper reviews principles three novel fabrication techniques: Atomic Layer Deposition (ALD), Metal-Organic Chemical Vapor (MOCVD), Pulsed Laser (PLD). It analyzes role in optimizing FET characteristics provides directions overcoming bottlenecks processes, which will aid advancing technology.
Usually, the image search results contain multiple topics on semantic level and even semantically consistent images have diverse appearances visual level. How to organize into visually clusters becomes a necessary task facilitate users' navigation. To attack this, HiCluster, an effective method is designed in this paper, which employs both textual analysis. First, we extract some query-related key phrases enumerate specific semantics of given query cluster them using K-lines-based clustering...
We propose a multiagent-based reinforcement learning algorithm, in which the interactions between travelers and environment are considered to simulate temporal-spatial characteristics of activity-travel patterns city. Road congestion degree is added algorithm as medium that passes influence one traveler’s decision others. Meanwhile, agents used initialized from typical activity extracted travel survey diary data Shangyu city China. In simulation, both macroscopic such traffic flow...
Staggered working hours has the potential to alleviate excessive demands on urban transport networks during morning and afternoon peak influence travel behavior of individuals by affecting their activity schedules reducing commuting times. This study proposes a multi-agent-based Q-learning algorithm for evaluating staggered work simulating travelers’ time location choices in patterns. Interactions among multiple travelers were also considered. Various types agents identified based real...
A cellular automaton model is proposed to simulate mixed traffic flow composed of motor vehicles and bicycles near bus stops. Three typical types stops which are common in China considered the model, including two curbside one type bay Passenger transport capacity three stops, applied evaluate stop design, calculated based on corresponding rate. According simulation results, rates both exhibit phase transition from free saturation at critical point. The results also show that larger...
Bus travel time on road section is defined and analyzed with the effect of multiple bus lines. An analytical model formulated to calculate total red a encounters when travelling along arterial. Genetic algorithm used optimize offset scheme traffic signals minimize that all lines encounter in two directions The are applied major part Zhongshan North Street city Nanjing. results show methods this paper can reduce by 31.9% object arterial thus improve efficiency whole promote public transport priority.
The judgements in some sports competitions are subjective tasks, especially with high requirements on skills, which could lead to unfair results. Synchronized diving is such a skillful competition. Using computer judge automatically or assist referees can effectively decrease the This paper presents framework for analyzing synchronization synchronized videos. composed of three steps: (1) silhouette extraction, that get diverpsilas silhouette; (2) feature extraction and representation,...
Spatial distribution is of particular importance to market analysts, location analysts and transportation planners meanwhile plays an important role in traffic demand management (TDM). For most people, their living working places are rather steady, only the for shopping recreation can be freely chosen. In this study, agent-based modeling applied simulate destination choices discretionary activities. Travel diary survey data Tongling City utilized throughout whole process, including...
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
Abstract. Accurate stock price prediction is important for financial investors, as it directly influences investment strategies and decision-making. In this study, the author focuses on evaluating effectiveness of Elastic Net model in forecasting closing prices Apple Inc.'s stock. The dataset, spanning from 2014 to 2023, sourced Kaggle includes both historical a range technical indicators, thereby ensuring accuracy reliability research data. To enhance predictive model, paper carefully...
With the goal to improve accuracy of traffic assignment without increasing additional workload data collection and processing, a quantitative method determine analysis zone generation attraction points is proposed based on clustering land use data, including area interest, number households in residential community, building storey data. Taking morning rush hour as time period, multi-source urban were collected using web crawling technology. To obtain with activity intensity weights, was...
The statistical independence of time every two adjacent bus links plays a crucial role in deciding the feasibility using many mathematical models to analyze urban transit networks. Traditional research generally ignores that acts as ground their models. Assumption is usually made sound. This is, however, actually groundless and probably causes problematic conclusions reached by corresponding Many assignment such multinomial probit-based lose effects when not valid. In this paper, simple...
Transportation policy can be more efficient in attracting a considerable number of people to choose public transit as their travel mode when decision-makers tend develop specific policies considering different groups people. The market segmentation method based on bus commuters’ attitude towards trip and own risk preference is significant approach characterize various demands from commuters. Traditional approaches, however, rarely attempted reveal the connection between socioeconomics...
VR in virtual reality technology is a new applied the field of education and gaming recent years. This article describes current development games, demonstrates diversity applications to promote better understanding technology. First all, starting with education, this paper expounds that designed based on educational teaching objectives. we introduce performance education. section important role medical classroom The challenges were discussed. Then it practical exploration games value game...
This paper compares two effective path searching algorithms, the Kth shortest algorithm and depth-first algorithm, for a multi-modal public transport super-network. First, super-network model building method based on modeling approach is proposed. Then, procedures of algorithms are described in detail. Finally, simplified traffic network representing Wuxi, Jiangsu, China, case study carried out. The differences between analyzed from aspects computing time, result single OD pair, all pairs....