A5100600226- Hydraulic and Pneumatic Systems
- Advanced Sensor and Control Systems
- Advanced Computational Techniques and Applications
- Fault Detection and Control Systems
- Advanced Algorithms and Applications
- Machine Fault Diagnosis Techniques
- Industrial Technology and Control Systems
- Sparse and Compressive Sensing Techniques
- Face and Expression Recognition
- Handwritten Text Recognition Techniques
- Acoustic Wave Phenomena Research
- Advanced Computing and Algorithms
- Fluid Dynamics Simulations and Interactions
- Environmental Impact and Sustainability
- Vehicle License Plate Recognition
- Remote Sensing and Land Use
- EEG and Brain-Computer Interfaces
- Geotechnical Engineering and Underground Structures
- Mining and Resource Management
- Climate Change, Adaptation, Migration
- Industrial Automation and Control Systems
- Multimodal Machine Learning Applications
- Distributed and Parallel Computing Systems
- Image Processing Techniques and Applications
- Underwater Acoustics Research
Hefei University of Technology
2025
Tsinghua University
2023
University Town of Shenzhen
2023
Jiangxi College of Applied Technology
2023
Ministry of Natural Resources
2023
Yanshan University
2011-2021
University of Shanghai for Science and Technology
2007-2020
Johns Hopkins University
2019
University of Electronic Science and Technology of China
2015
Zhejiang Normal University
2009
Sheng Zhang, Xutai Ma, Kevin Duh, Benjamin Van Durme. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint (EMNLP-IJCNLP). 2019.
The objective of this research is to enhance sound field rendering efficiency using a heterogeneous computing framework. By integrating GPU and CPU resources, we address performance challenges in complex environments large-scale ray tasks. Evaluations the NVIDIA RTX A6000 AMD 9754 led an task allocation mechanism, optimizing resource use maximizing computational efficiency. Experimental results show that strategy significantly accelerates rendering, achieving nearly 400 times faster than...
To address the problem that faults in axial piston pumps are complex and difficult to effectively diagnose, an integrated hydraulic pump fault diagnosis method based on modified ensemble empirical mode decomposition (MEEMD), autoregressive (AR) spectrum energy, wavelet kernel extreme learning machine (WKELM) methods is presented this paper. First, non-linear non-stationary vibration signals decomposed into several intrinsic function (IMF) components by MEEMD method. Next, AR analysis...
Aiming at the different health states of hydraulic pumps, this paper proposes to use convolutional neural network classify and identify time-frequency images volumetric efficiency pumps realize status monitoring pumps. After collecting vibration signal data pump, map is formed by short-time Fourier transform, wavelet Wigner-Will distribution, then generated divided into a training set test set, in which former used train latter verify recognition result. Finally, it proved that can well rate...
In situations where the vibration sensor is not suitable to be used and while fault diagnosis method based on signal processing has limitations, KPCA sound proposed. The basic theory of kernel principal component analysis its procedures for detection are introduced pre-processing depicted, multi-domain feature vector extracted from time, time-frequency frequency domain, faults diagnosed with method. new tested axial piston pump, result shows that effective it can overcome deficiencies signal.
In this paper, we focus on how to locate the relevant or discriminative brain regions related with external stimulus certain mental decease, which is also called support identification, based neuroimaging data. The main difficulty lies in extremely high dimensional voxel space and relatively few training samples, easily resulting an unstable region discovery (or feature selection context of pattern recognition). When samples are from different centers have between-center variations, it will...
This article has designed an low power granary temperature and humidity acquisition system, used the latest model MSP430F5438 belonging to TI company as processor of lower computer, colleceted by SHT11, transmitted collected physical data host computer through SIM300 wireless transmission module received stored in database. The was done using C + builder software, analysed real-time datas made reasonable warnings.
In this paper, we focus on how to locate the relevant or discriminative brain regions related with external stimulus certain mental decease, which is also called support identification, based neuroimaging data. The main difficulty lies in extremely high dimensional voxel space and relatively few training samples, easily resulting an unstable region discovery (or feature selection context of pattern recognition). When samples are from different centers have betweencenter variations, it will...
The research of this paper aims to develop a new form digital textbook for the course "Soil Mechanics" solve existing problems in higher vocational education. Soil Mechanics is out touch with actual production enterprises, and its content outdated. In order cultivate students adapt digitization requirements, we have co-developed loose-leaf textbooks conjunction front-line companies, which break through framework traditional syllabus textbooks, emphasizing work process learning projects....
Abstract In the automatic sorting process of express, express end label code is used to indicate that dispatched a specific address by courier. Since there are many areas on bill containing digital information, some may be improperly photographed, etc. The difficulty in positioning and recognizing region increased. To solve this problem, paper proposes an recognition method with convolutional recurrent neural network for specification, which has certain versatility. order improve overall...