A5055567445- IoT and Edge/Fog Computing
- Cloud Computing and Resource Management
- Face recognition and analysis
- Face and Expression Recognition
- Caching and Content Delivery
- Energy Harvesting in Wireless Networks
- Blockchain Technology Applications and Security
- Metaheuristic Optimization Algorithms Research
- Advanced Manufacturing and Logistics Optimization
- Image Retrieval and Classification Techniques
- Vehicular Ad Hoc Networks (VANETs)
- Opportunistic and Delay-Tolerant Networks
- Industrial Vision Systems and Defect Detection
- Advanced Decision-Making Techniques
- Elevator Systems and Control
- Advanced Image and Video Retrieval Techniques
- Reinforcement Learning in Robotics
- Privacy-Preserving Technologies in Data
- Mobile Ad Hoc Networks
- Advanced Algorithms and Applications
- Energy Efficient Wireless Sensor Networks
- Age of Information Optimization
- Remote Sensing and Land Use
- Digital Media and Visual Art
- Sentiment Analysis and Opinion Mining
Beijing Wuzi University
2012-2024
Beijing University of Technology
2008-2020
Soochow University
2016-2017
Wuyi University
2017
Suzhou Art & Design Technology Institute
2016
Beijing Jiaotong University
2011-2014
China Youth University for Political Sciences
2013
In intelligent warehouse picking system, the allocation of tasks has an important influence on efficiency whole system because large number robots and orders.The paper proposes a method to solve task problem that multi-robot is transformed into transportation find collision-free scheme then improve capability processing.The time window power consumption (driving distance) are regarded as utility function maximized objective function.Then integer programming formulation constructed...
In intelligent unmanned warehouse goods-to-man systems, the allocation of tasks has an important influence on efficiency because dynamic performance AGV robots and orders. The paper presents a hierarchical Soft Actor-Critic algorithm to solve scheduling problem orders picking. method proposed is based classic reinforcement learning algorithm. this paper, model trained at different time scales by introducing sub-goals, with top-level policy bottom level achieve sub-goals. actor controller...
The advances in cloud computing promote the problem processing speed. Computing resources play a vital role solving user demands, which can be regarded as workflows. Efficient workflow scheduling is challenge reducing task execution time and cost. In recent years, deep reinforcement learning algorithm has been used to solve various combinatorial optimisation problems. However, trained models often have volatility not applied real situation. addition, evolutionary with complete framework...
Cloud computing is a major heterogeneous distributed system that can obtain the required resources for different needs of customers through network. With advancement technology, cloud workflow scheduling has become widely studied area aiming to utilise efficiently. In general, problem in environment parallel, dependent, and complex. So far, there are many algorithms field resource environment. However, most these only consider makespan or cost, research on multiple targets still relatively...
The accuracy of defects detection for logistics packaging box is a critical factor to ensure the quality goods under edge computing environment. Now, there are few works on this issue. This paper designs an image acquisition process system and then proposes novel approach in addressing defect (LPDD) basis support vector machine (SVM). Firstly, new mean denoising template Laplace sharpening template, which more suitable based preprocessing, enhancement other relevant technical theories. Then...
In the text sentiment classification task, some words are seemingly unrelated to but they have a direct impact on performance of model. For example, in sentences "I terminal cancer" and "Cancer is very common disease", it can be clearly found that word "cancer" has two different tendencies daily life domain medical domain. domain, shows an extremely negative tendency. While just simple term with relatively neutral Although current deep learning models already achieved good through their...
In this paper, a novel face representation approach, Haar Local Binary Pattern histogram (HLBPH), is proposed to represent the images. First, image decomposed into four-channel subimages in frequency domain by wavelet transform, and then LBP operator applied on each subimage extract features. After that, method (HLBPH) based two-layer weighted fusion scheme presented balance block regions for LBP, fuse multi-channel recognition stage, Chi square statistic( <inf...
Graph Convolutional Network (GCN) is extensively used in text classification tasks and performs well the process of non-euclidean structure data. Usually, GCN implemented with spatial-based method, such as Attention (GAT). However, current GCN-based methods still lack a more reasonable mechanism to account for problems contextual dependency lexical polysemy. Therefore, an improved (IGCN) proposed address above problems, which introduces Bidirectional Long Short-Term Memory (BiLSTM) Network,...