A5100621923- Metaheuristic Optimization Algorithms Research
- Energy Load and Power Forecasting
- High-Temperature Coating Behaviors
- Image and Signal Denoising Methods
- Remote-Sensing Image Classification
- High Entropy Alloys Studies
- Vehicle Dynamics and Control Systems
- Advanced Multi-Objective Optimization Algorithms
- Electricity Theft Detection Techniques
- Advanced Image Processing Techniques
- Advanced Vision and Imaging
- Target Tracking and Data Fusion in Sensor Networks
- Synthetic Aperture Radar (SAR) Applications and Techniques
- Hydraulic and Pneumatic Systems
- Intelligent Tutoring Systems and Adaptive Learning
- Smart Grid Energy Management
- Advanced Image Fusion Techniques
- Water Systems and Optimization
- Image Processing Techniques and Applications
- Evolutionary Algorithms and Applications
- Advanced Algorithms and Applications
- Data Management and Algorithms
- Online Learning and Analytics
- Service-Oriented Architecture and Web Services
- Traffic control and management
Xi’an University
2020-2024
Xi'an University of Technology
2015-2024
Shaanxi University of Technology
2020-2023
Northeast Electric Power University
2023
Tianjin Research Institute of Electric Science (China)
2023
Sichuan University
2022
Wuhan University of Technology
2021
Institute of Physics
2020
University of Cologne
2019
Zhejiang Energy Research Institute
2019
To fully mine the relationship between temporal features in load data, improve accuracy and efficiency of short-term forecasting overcome difficulties caused by nonlinearity volatility accurate forecasting. In this paper, a hybrid neural network model based on convolutional (TCN) gated recurrent unit (GRU) is proposed. Firstly, correlation meteorological measured with distance coefficient, fixed-length sliding time window method used to reconstruct features. Next, adopted extract hidden...
In this era of intelligence, the learning methods learners have substantially changed. Many choose to learn through online education platforms. Although may enjoy more high-quality educational resources, when they are faced with an abundance resource information, prone become lost in knowledge, among other problems. To solve problem, a multi-algorithm collaborative, personalized, path recommendation model is proposed provide guidance for First, learner constructed from four perspectives:...
The recent development of cloud computing has empowered the Internet-based services, which enable users to gain a broad scope access their applications, such as Internet Medical Things (IoMT). Considering efficiency performance, privacy protection is often kept at lower level in order ensure application can offer higher performance. However, this mechanism also causes serious concern hazards due information over collections operated by apps/applications. Addressing issue, paper proposes an...
In the process of power transmission and distribution, non-technical losses are usually caused by users' abnormal consumption behavior. It will not only affect dispatch operation distribution network, bring hidden dangers to security grid, but also damage operating costs companies disrupt market. Aiming at electricity behavior, this paper proposes a model based on particle swarm optimization long-short term memory with attention mechanism (PSO-Attention-LSTM). Firstly, according actual theft...
Images from different sensors can be in intensity or data structure to present the same object on ground. The distinct appearances make change detection task more difficult obtain accurate regions. This letter presents a novel bipartite adversarial autoencoders with structural self-similarity (BASNet) for detecting land cover changes heterogeneous remote sensing images. main novelty lies following two aspects. First, consistency loss is defined by crossmodal distance new affinity space. It...
One of the main problems for change detection in multitemporal synthetic aperture radar (SAR) images is presence speckle noise, since it degrades image quality significantly and may hide important details image. In this article, we investigate a novel class-relativity non-local means (CRNLM) algorithm that reduces effect noise principal component analysis (PCA) feature space SAR detection. Note averaging process particularly true when assumed model additive. Thus, adopt difference produced...
Detecting land cover change is an essential task in very-high-spatial-resolution (VHR) remote sensing applications. However, because VHR images can capture the details of ground objects, scenes are usually complex. For example, show distinct appearances or features same object, aroused by noise, climate conditions, imaging angles, etc. To address this issue, paper proposes a novel unsupervised approach named bipartite graph attention autoencoders (BGAAE) for image detection. BGAAE, further...
Traditional route planning methods usually plan the “fastest” or “lowest cost” travel for users with goal of finding shortest path lowest cost, but this method cannot meet needs tourism personalized and multifunctional routes. Given phenomenon, paper proposes a model based on urgency. First, uses visitor’s historical data public road network to extract their preferences, POI (point interest) relationships, edge scenic values other information. Then, planned function is determined according...
The artificial endocrine system (AES) is a new branch of natural computing which uses ideas and takes inspiration from the information processing mechanisms contained in mammalian system. It fast growing research field variety theoretical models technical methods have been studied for dealing with complex significant problems. An overview some recent advances AES modeling its applications provided this paper, based on major latest works. This review covers modeling, combinations algorithms,...
With the increase of resolution, effective characterization synthetic aperture radar (SAR) image becomes one most critical problems in many earth observation applications. Inspired by deep learning and probability mixture models, a generalized Gamma belief network (g Γ-DBN) is proposed for SAR statistical modeling land-cover classification this work. Specifically, Gamma-Bernoulli restricted Boltzmann machine (gΓB-RBM) to capture high-order characterizes from images after introducing...