A5045443775- Advanced Algorithms and Applications
- Industrial Technology and Control Systems
- Advanced Image and Video Retrieval Techniques
- Advanced Sensor and Control Systems
- Image Retrieval and Classification Techniques
- Smart Grid and Power Systems
- Mechanical Engineering and Vibrations Research
- Advanced Decision-Making Techniques
- Technology and Security Systems
- Power Systems and Technologies
- Evaluation Methods in Various Fields
- Medical Image Segmentation Techniques
- Advanced Neural Network Applications
- Vehicle Dynamics and Control Systems
- Energy Load and Power Forecasting
- Power Systems and Renewable Energy
- Spam and Phishing Detection
- Advanced Computational Techniques and Applications
- Evaluation and Optimization Models
- Robotic Path Planning Algorithms
- Wireless Sensor Networks and IoT
- Big Data Technologies and Applications
- Metaheuristic Optimization Algorithms Research
- Mechanical Failure Analysis and Simulation
- Sentiment Analysis and Opinion Mining
North China Electric Power University
2007-2023
Zhejiang University
2023
Wenzhou University of Technology
2023
Institute of Grassland Research
2022-2023
Beijing University of Technology
2022-2023
Zhejiang University of Science and Technology
2015-2023
Wenzhou University
2023
Heilongjiang University of Technology
2023
Xiamen University
2022
Samsung (China)
2021
Deep learning has been shown as a successful machine method for variety of tasks, and its popularity results in numerous open-source deep software tools. Training network is usually very time-consuming process. To address the computational challenge learning, many tools exploit hardware features such multi-core CPUs many-core GPUs to shorten training time. However, different exhibit running performance when types networks on platforms, which makes it difficult end users select an appropriate...
This paper proposed a method of path planning in three-dimensional space based on concentric spherical coordinate and improved particle swarm optimization algorithm. First the model UAV was analyzed. Then encoding system given. The constraints were combined with algorithm to make more rational searching efficiently. At same time using Matlab7.0 as development tool for simulation, simulation analyses showed that this is applicable acceptable, which could achieve goal terrain following threat...
The original local binary pattern (LBP) operator or LBP variants adopt the difference between neighboring pixels and center pixel to describe that does not consider relationship pixels. block region characteristics of an image are determined by pixels, just pixel. In this letter, a new neighborhood encoding method is proposed, which we call random sampling (RSLBP). Based on distribution signal, point pairs randomly selected in neighborhood, carried out after comparing sums point. Image more...
Recent works have validated the benefit of integrating spatial information into deep networks to improve pixel-level prediction tasks such as monocular depth estimation. However, how efficiently and robustly integrate cues retains an open problem. In this paper, we introduce Side Prediction Aggregation (termed SPA) method enhance embedding scene structural from low-level high-level layers. To estimation accuracy, proposed is further equipped with continuous Spatial Refinement Loss SRL) at...
Regarding to the daily load forecasting, sample selection and data preprocessing are crucial its' precision. In this paper, case-based reasoning (CBR) is adopted search historical whose features same as predict day. CBR realized through steps of case representation, indexing, retrieval, adaptation, key idea in involves use already existing knowledge about objects or situations aspects similar objects. This method uses not only specific past problems, but also additional derived from clusters...
The oily wastewater through union station was between 40-70 ℃. sewage injected to the ground or direct discharge after treatment and it resulted in heat waste station. In meaning time, there were many energy demands station, such as building heating, crude oil liquid heating so on. Paper summarized current status of oilfield absorption pump technology. paper took project Kenxi Oilfield Station an example. introduced program design. And consumption compared before transformation....
Background: The day-ahead power market is an important part of the spot market. In market, participants make short-term forecasts load and output to propose bidding curve more precisely. As energy aggregators that have regulatory resources, virtual plants (VPPs) need consider uncertainty distributed renewable when participating in transactions. Methods: This paper analyzes built optimization model for VPP considering from both inner parts environment. To verify model, a simulation study ran....
Knowledge Distillation (KD) is designed to train smaller student models using a larger pretrained teacher model. However, in decentralized data systems such as blockchain, privacy concerns may arise, making the inaccessible. To address this issue, Data-Free KD (DFKD) methods have been proposed, which extract prior knowledge from networks and use it synthesize for KD. Previous DFKD faced challenges due large search space of generation. Recently, deep generative (DGMs) proposed learn...