A5071914915- Advanced Wireless Communication Techniques
- Adaptive Dynamic Programming Control
- Energy Load and Power Forecasting
- Advanced Wireless Communication Technologies
- Wireless Communication Networks Research
- Advanced MRI Techniques and Applications
- Advanced Algorithms and Applications
- Image and Signal Denoising Methods
- Reinforcement Learning in Robotics
- Energy Efficient Wireless Sensor Networks
- Error Correcting Code Techniques
- Algorithms and Data Compression
- Fluid Dynamics and Mixing
- Energy Harvesting in Wireless Networks
- Mechanical Circulatory Support Devices
- Adaptive Control of Nonlinear Systems
- Cooperative Communication and Network Coding
- Industrial Technology and Control Systems
- Air Quality Monitoring and Forecasting
- Silicon Carbide Semiconductor Technologies
- Solar Radiation and Photovoltaics
- Indoor and Outdoor Localization Technologies
- PAPR reduction in OFDM
- Anomaly Detection Techniques and Applications
- Wireless Signal Modulation Classification
China Jiliang University
2012-2024
Shanghai East Hospital
2024
Siemens Healthcare (United States)
2015-2024
Ministry of Transport
2024
North China Electric Power University
2023-2024
Chinese Center For Disease Control and Prevention
2022-2024
Chengdu University of Technology
2024
Siemens (United States)
2024
Shanxi University
2023
China Telecom
2022
In this paper, we study the finite-horizon optimal control problem for discrete-time nonlinear systems using adaptive dynamic programming (ADP) approach. The idea is to use an iterative ADP algorithm obtain law which makes performance index function close greatest lower bound of all indices within ε-error bound. number steps can also be obtained by proposed algorithms. A convergence analysis algorithms in terms and policy made. order facilitate implementation algorithms, neural networks are...
Electric power consumption short-term forecasting for individual households is an important and challenging topic in the fields of AI-enhanced energy saving, smart grid planning, sustainable usage electricity market bidding system design. Due to variability each household’s personalized activity, difficulties exist traditional methods, such as auto-regressive moving average models, machine learning methods non-deep neural networks, provide accurate prediction single household electric...
In this paper, a neuro-optimal control scheme for class of unknown discrete-time nonlinear systems with discount factor in the cost function is developed. The iterative adaptive dynamic programming algorithm using globalized dual heuristic technique introduced to obtain optimal controller convergence analysis terms and law. order carry out algorithm, neural network constructed first identify controlled system. Then, based on learned system model, two other networks are employed as parametric...
In wireless sensor networks, nodes always have a limited power resource. The energy consumed by transferring data from the node to its destination raises as critical issue in designing reasonable network routing protocols. this paper we propose revised cluster algorithm named E-LEACH enhance hierarchical protocol LEACH. algorithm, original way of selection heads is random and round time for fixed. consider remnant order balance loads changes depends on optimal size. simulation results show...
We demonstrate model-based, visual robot manipulation of deformable linear objects. Our approach is based on a state-space representation the physical system that aims to control. This choice has multiple advantages, including ease incorporating physics priors in dynamics model and perception model, planning actions. In addition, states can naturally represent object instances different appearances. Therefore, state space be learned one setting directly used other visually settings. contrast...
Sentiment classification is an interesting and crucial research topic in the field of natural language processing (NLP). Data-driven methods, including machine learning deep techniques, provide one direct effective solution to solve sentiment problem. However, performance declines when input includes review comments for multiple tasks. The most appropriate way constructing a model under multi-tasking circumstances remains questionable related field. In this study, aiming at problem, we...
Every moment counts in action recognition. A comprehensive understanding of human activity video requires labeling every frame according to the actions occurring, placing multiple labels densely over a sequence. To study this problem we extend existing THUMOS dataset and introduce MultiTHUMOS, new dense unconstrained internet videos. Modeling multiple, benefits from temporal relations within across classes. We define novel variant long short-term memory (LSTM) deep networks for modeling...
Artificial intelligence-based air quality index (AQI) forecasting is a hot research topic in the fields of sustainable and smart industrial environment design. There are mainly two obstacles that hinder existing machine learning (ML) deep (DL) technologies providing accurate results to protect environment, which include intercorrelation between different AQI components highly volatile pattern changes. In this article, novel DL framework combining multiple nested long short term memory...
Mobile phone localization plays a key role in the fast-growing Location Based Applications domain. Most of existing schemes rely on infrastructure support such as GSM, WiFi or GPS. In this paper, we present FTrack, novel floor system to identify level multi-floor building which mobile user is located. FTrack uses phone's accelerometer only without any support. It does not require prior knowledge height. By capturing encounters and analyzing trails, finds mapping from traveling time (when...
Lithium-ion batteries are indispensable in various applications owing to their high specific energy and long service life. battery models used for investigating the behavior of enabling power control applications. The Doyle-Fuller-Newman (DFN) model is a popular electrochemistry-based model, which characterizes dynamics through diffusions solid electrolyte predicts current/voltage response. However, DFN contains large number parameters that need be estimated obtain an accurate model. In this...
Automated fault diagnosis (AFD) for various energy consumption components is one of the main topics efficiency solutions. However, lack faulty samples in training process remains as a difficulty data-driven AFD heating, ventilation and air conditioning (HVAC) subsystems, such handling units (AHU). Existing works show that semi-supervised learning theories can effectively alleviate issue by iteratively inserting newly tested data into pool when same happens again. research gap exists between...
Naked oats, a significant minor cereal crop in China popular for its nutrient richness, have experienced surge production recent years, fueled by the escalating demand wholesome healthy food. However, dispersed and disorganized cultivation plan of naked oats poses constraint on industrial progression. Considering dual influence cultivation, management techniques, global climate change this study explores potential impacts spatial distribution yield crop. Leveraging CMIP6 models (BCC-CSM2-MR,...
In this letter, we develop the wavelet basis function neural networks (WBFNNs). It is analogous to radial (RBFNNs) and (WNNs). WBFNNs, both scaling of a multiresolution approximation (MRA) are adopted as for approximating functions. A sequential learning algorithm WBFNNs presented compared RBFNNs. Experimental results show that have better generalization property require shorter training time than
Recent development of artificial intelligence (AI) technology enquires the traditional power grid system involving additional information and connectivity all devices for smooth transit to next generation smart system. In an AI-enhanced system, each device has its unique name, function, property, location, many more. A large number can form a complex knowledge graph through serial parallel connection relationships. The scale equipment is usually extremely large, with thousands millions...
A safe and stable operation power system is very important for the maintenance of national industrial security social economy. However, with increasing complexity grid topology its operation, new challenges in estimating evaluating structure performance have received significant attention. Complex network theory transfers to a nodes links, which helps evaluate conveniently global view. In this paper, we employ complex method address cascade failure process assessment simultaneously. Firstly,...