A5101502386- Machine Fault Diagnosis Techniques
- Microgrid Control and Optimization
- Image and Signal Denoising Methods
- Integrated Energy Systems Optimization
- Distributed and Parallel Computing Systems
- Smart Grid Energy Management
- Natural Language Processing Techniques
- Advanced Computational Techniques and Applications
- Cloud Computing and Resource Management
- Advanced Malware Detection Techniques
- Network Security and Intrusion Detection
- Scientific Computing and Data Management
- Sentiment Analysis and Opinion Mining
- Elevator Systems and Control
- Fault Detection and Control Systems
- Network Packet Processing and Optimization
- Service-Oriented Architecture and Web Services
- Mathematical Analysis and Transform Methods
- Speech and Audio Processing
- Evaluation Methods in Various Fields
- Speech Recognition and Synthesis
- Mobile Agent-Based Network Management
- Big Data and Business Intelligence
- Advanced Steganography and Watermarking Techniques
- Reading and Literacy Development
Anhui University of Finance and Economics
2024
Zhejiang University
2024
North China Electric Power University
2019-2023
Peking University
2021
Beijing Institute of Technology
2017-2020
The University of Sydney
2020
Northeastern University
2020
Beijing Aerospace Flight Control Center
2020
Dalian Jiaotong University
2008-2020
Donghua University
2012-2019
An early warning system (EWS) is a core type of data driven Internet Things (IoTs) used for environment disaster risk and effect management. The potential benefits using semantic-type EWS include easier sensor source plug-and-play, simpler, richer, more dynamic metadata-driven analysis service interoperability orchestration. challenges faced during practical deployments semantic EWSs are the need scalable time-sensitive exchange processing (especially involving heterogeneous sources)...
Long-term video EEG epilepsy monitoring can help doctors diagnose and cure epilepsy. The workload of to read the signals patients be effectively reduced by automatic seizure detection. application partial directed coherence (PDC) analysis as mechanism for feature extraction in scalp recordings detection could reflect physiological changes brain activity before after onsets. In this study, a new approach on basis PDC was proposed detect intervals patients. First all, multivariate...
In this letter, an amplify-and-forward (AF) relaying system is considered, where energy constrained relay node harvests from the received radio frequency signal and uses harvested to AF source destination. Based on time switching (TS) power splitting (PS) receiver architectures, adaptive receiving architecture for harvesting information processing proposed (AR) protocol based it developed enable at relay. light of this, analytical expressions throughput are derived both delay-limited...
In this paper, a novel co-optimization model is proposed for integrated electricity-gas-heat urban energy systems to improve resilience during extreme events. This paper modelled and analysed data centres' optimal operation, workload redistribution, waste heat reuse. addition guaranteeing power supply as critical loads, centres also provide the generated customers via heating network. Meanwhile, considers complex interactions of multiple recovery decisions distribution system. Energy...
Graph convolutional networks (GCNs) have demonstrated superiority in graph-based learning tasks. However, training GCNs on full graphs is particularly challenging, due to the following two challenges: (1) associated feature tensors can easily explode memory and block communication bandwidth of modern accelerators, (2) computation workflow alternates between sparse dense matrix operations, complicating efficient utilization computational resources. Existing solutions for scalable distributed...
This paper proposes a co-optimal strategy using line hardening, mobile devices (mobile ice-melting device, emergency generator, energy storage system), and repair crew dispatching to improve distribution system resilience during ice storms.A multi-stage defender-attacker-defender model is established take into account interactions coupling relationships between different measures.In our proposed model, storms will attack the transportation in worst-case scenario, affecting performance from...
Despite the great burden of chronic respiratory diseases in China, few large multicentre, spirometry-based studies have examined its prevalence, rate underdiagnosis regionally or relevance socioeconomic and lifestyle factors.We analysed data from 512 891 adults China Kadoorie Biobank, recruited 10 diverse regions during 2004-2008. Air flow obstruction (AFO) was defined by lower limit normal criteria based on spirometry-measured lung function. The prevalence AFO region, age, status, body mass...
With the increasing attention of clean and efficient use energy, regional integrated energy system (RIES), as an measure to improve efficiency, is tending play important role in field supply. The configuration multiple storage equipment RIES can greatly economy system, which research direction planning. However, at present on optimization electric-gas-thermal multi-energy devices insufficient. Under this background, a method for configuring rated capacity power various under both off-grid...
Several common elevator malfunctions were diagnosed with a least square support vector machine (LS-SVM). After acquiring vibration signals of various functions, their energy characteristics and time domain indicators extracted by theoretically analyzing the optimal wavelet packet, in order to construct feature for identifying causes as input LS-SVM. Meanwhile, parameters about LS-SVM optimized K-fold cross validation (K-CV). diagnosing deviated guide rail, shape shoe, abnormal running...
Little is known about the long-term risks of stroke and ischemic heart disease (IHD) in women who had a hysterectomy alone (HA) or with bilateral oophorectomy (HBO) for benign diseases, particularly China where burden cardiovascular diseases (CVD) high. We assessed mean levels risk factors relative IHD Chinese HA HBO.A total 302 510 women, aged 30 to 79 years were enrolled Kadoorie Biobank from 2004 2008 followed up 9.8 years. The analysis involved premenopausal without prior cancer at...
The increasing complexity of energy internet integrated with multiple systems requires a more flexible management system. To exploit the potential complementarity, maximize consumption renewable sources (RES) and minimize operating costs, cooperative operation model for multi-energy (IMES) transmission losses is proposed in this paper. On basis, novel strategy developed to improve utilization efficiency regional by integrating alternative decomposition-based decoupling method flow dynamic...
Many software systems operate across different geographically distributed hardware platforms, operating and programming languages. Publish/subscribe based Message Oriented Middleware (MOM) provides loose coupling an efficient, asynchronous scalable way of communication. However, as the complexity such increase, manual verification reconfiguration policies becomes unrealistic. The task calls for automated means proof-checking configuration information in order to improve reliability...
This paper presents a comparison of three-dimensional (3-D) segmentations the prostate, based on two-dimensional (2-D) manually segmented contours, obtained using ultrasound (US) and magnetic resonance (MR) imaging data collected from 40 patients diagnosed with localized prostate cancer scheduled to receive brachytherapy treatment. The approach we propose here for 3-D segmentation first uses radial basis function interpolation construct point distribution model each prostate. Next, modified...
Efficient and scalable deduplication techniques are required to serve the need of removing duplicated data in big processing platforms such as Hadoop. In this paper, an integrated approach is proposed by taking features Hadoop into acount leveraging parallelism based on MapReduce HBase so speed up procedure. our approach, a new small-file aggregation scheme proposed, standard Secure Hash Algorithm-3, Keccak employed. The effectiveness demonstrated extensive experiments both artificial...
Fault detection is important for improving the reliability of spacecraft, ensuring long-term stable operation, and reducing economic loss caused by failure. In order to solve problems such as large amount test data, scarcity fault data samples real-time requirements in field spacecraft detection, an improved unsupervised deep learning algorithm based on Variational Autoencoder (VAE) proposed. The adopts Gated Recurrent Unit (GRU) recurrent neural networks encoder automatically extract...
In order to discover the fault with roller bearing in time, a new diagnosis method based on Empirical mode decomposition (EMD) and BP neural network is put forward paper. First, we get signal through experiments. Then use EMD decompose vibration into series of single signals. We can extract main information from The kurtosis coefficient signals forms feature vector which used as input data network. trained be for identification. Through analyzing, distinguish normal state, inner race fault,...