Hao Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hao Zhu has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
Yaohua Xie
Yale University
4 shared publicationsMengshu Hou
University of Electronic Science and Technology of China
3 shared publicationsMulan Wang
Jiangsu Key Laboratory of Advanced Numerical Control Technology
3 shared publicationsWeiye Xu
Nanjing Institute of Technology
3 shared publicationsKai Yan
University of Electronic Science and Technology of China
2 shared publicationsKaiyun Xu
Jiangsu Key Laboratory of Advanced Numerical Control Technology
2 shared publications
Latest Publications
- Open Access
- 24 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 362-367
Fault Localization of EMU Air-Exchange Device Using SVM-Frame Based TDOA
We propose a non-contact fault detection and localization method for electric multiple unit (EMU) air-exchange devices based on acoustic signals. This method is oriented toward the Sound Event Localization and Detection (SELD) task. A cruciform microphone array is designed to collect sound signals, and then Mel-frequency Cepstral Coefficients (MFCCs) are extracted and a trained Support Vector Machine (SVM) classifier is then employed to identify frames containing fault-related acoustic signatures. Once a fault is detected, the Time Difference of Arrival (TDOA) between microphones is calculated to estimate the azimuth angle of the sound source. Experimental results demonstrate that the SVM model achieves a peak classification accuracy of 97.25% with optimized hyperparameters. Furthermore, performance evaluation under varying signal-to-noise ratios (SNRs) confirms that the Mel-frequency Cepstral Coefficient (MFCC) features maintain high discriminative power, sustaining a diagnostic accuracy of over 95.8% at 10 dB. Localization tests indicate that the angular deviation remains within a 15° margin at SNRs of 10 dB and higher. Our proposed method effectively enhances the operational efficiency of maintenance and can be widely used in the EMU trains.
- 24 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 362-367
Open AccessFault Localization of EMU Air-Exchange Device Using SVM-Frame Based TDOA
We propose a non-contact fault detection and localization method for electric multiple unit (EMU) air-exchange devices based on acoustic signals. This method is oriented toward the Sound Event Localization and Detection (SELD) task. A cruciform microphone array is designed to collect sound signals, and then Mel-frequency Cepstral Coefficients (MFCCs) are extracted and a trained Support Vector Machine (SVM) classifier is then employed to identify frames containing fault-related acoustic signatures. Once a fault is detected, the Time Difference of Arrival (TDOA) between microphones is calculated to estimate the azimuth angle of the sound source. Experimental results demonstrate that the SVM model achieves a peak classification accuracy of 97.25% with optimized hyperparameters. Furthermore, performance evaluation under varying signal-to-noise ratios (SNRs) confirms that the Mel-frequency Cepstral Coefficient (MFCC) features maintain high discriminative power, sustaining a diagnostic accuracy of over 95.8% at 10 dB. Localization tests indicate that the angular deviation remains within a 15° margin at SNRs of 10 dB and higher. Our proposed method effectively enhances the operational efficiency of maintenance and can be widely used in the EMU trains.
- 1 October 2025
- Published by Springer Nature
- p. 223-232
Comparative Study of Container Technology and Traditional Virtualization Technology
- 1 October 2025
- Published by Springer Nature
- p. 223-232
Comparative Study of Container Technology and Traditional Virtualization Technology
- 22 June 2021
- Published by Springer Nature
- p. 420-432
Research on Scattered Point Cloud Coordinate Reduction and Hole Repair Technology Based on Big Data Model
- 22 June 2021
- Published by Springer Nature
- p. 420-432
Research on Scattered Point Cloud Coordinate Reduction and Hole Repair Technology Based on Big Data Model
- 22 June 2021
- Published by Springer Nature
- p. 537-548
Design and Application of CMAC Neural Network Based on Software Hardening Technology
- 22 June 2021
- Published by Springer Nature
- p. 537-548
Design and Application of CMAC Neural Network Based on Software Hardening Technology
- Open Access
- 19 June 2021
- Published by Wiley in Security and Communication Networks
- Vol. 2021, 1-9
Research on Calibration Method of Binocular Vision System Based on Neural Network
In binocular vision inspection system, the calibration of detection equipment is the basis to ensure the subsequent detection accuracy. The current calibration methods have the disadvantages of complex calculation, low precision, and poor operability. In order to solve the above problems, the calibration method of binocular camera, the correction method of lens distortion, and the calibration method of projector in the binocular vision system based on surface structured light are studied in this paper. For lens distortion correction, on the basis of analyzing the traditional correction methods, a distortion correction method based on radial basis function neural network is proposed. Using the excellent nonlinear mapping ability of RBF neural network, the distortion correction models of different lenses can be obtained quickly. It overcomes the defect that the traditional correction model cannot adjust adaptively with the type of lens. The experimental results show that the accuracy of the method can meet the requirements of system calibration.
- 19 June 2021
- Published by Wiley in Security and Communication Networks
- Vol. 2021, 1-9
Open AccessResearch on Calibration Method of Binocular Vision System Based on Neural Network
In binocular vision inspection system, the calibration of detection equipment is the basis to ensure the subsequent detection accuracy. The current calibration methods have the disadvantages of complex calculation, low precision, and poor operability. In order to solve the above problems, the calibration method of binocular camera, the correction method of lens distortion, and the calibration method of projector in the binocular vision system based on surface structured light are studied in this paper. For lens distortion correction, on the basis of analyzing the traditional correction methods, a distortion correction method based on radial basis function neural network is proposed. Using the excellent nonlinear mapping ability of RBF neural network, the distortion correction models of different lenses can be obtained quickly. It overcomes the defect that the traditional correction model cannot adjust adaptively with the type of lens. The experimental results show that the accuracy of the method can meet the requirements of system calibration.
- Open Access
- 1 January 2021
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 66 (2) , 1799-1811
NURBS Modeling and Curve Interpolation Optimization of 3D Graphics
In order to solve the problem of complicated Non-Uniform Rational B-Splines (NURBS) modeling and improve the real-time performance of the high-order derivative of the curve interpolation process, the method of NURBS modeling based on the slicing and layering of triangular mesh is introduced. The research and design of NURBS curve interpolation are carried out from the two aspects of software algorithm and hardware structure. Based on the analysis of the characteristics of traditional computing methods with Taylor series expansion, the Adams formula and the Runge-Kutta formula are used in the NURBS curve interpolation process, and the process is then optimized according to the characteristics of NURBS interpolation. This can ensure accuracy, and avoid the calculation of higher-order derivatives. Furthermore, the hardware modules for the Adams and Runge-Kutta formulas are designed by using the parallel hardware construction technology of Field Programmable Gate Array (FPGA) chips. The parallel computing process using FPGA is compared with the traditional serial computing process using CPUs. Simulation and experimental results show that this scheme can improve the computational speed of the system and that the algorithm is feasible.
- 1 January 2021
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 66 (2) , 1799-1811
Open AccessNURBS Modeling and Curve Interpolation Optimization of 3D Graphics
In order to solve the problem of complicated Non-Uniform Rational B-Splines (NURBS) modeling and improve the real-time performance of the high-order derivative of the curve interpolation process, the method of NURBS modeling based on the slicing and layering of triangular mesh is introduced. The research and design of NURBS curve interpolation are carried out from the two aspects of software algorithm and hardware structure. Based on the analysis of the characteristics of traditional computing methods with Taylor series expansion, the Adams formula and the Runge-Kutta formula are used in the NURBS curve interpolation process, and the process is then optimized according to the characteristics of NURBS interpolation. This can ensure accuracy, and avoid the calculation of higher-order derivatives. Furthermore, the hardware modules for the Adams and Runge-Kutta formulas are designed by using the parallel hardware construction technology of Field Programmable Gate Array (FPGA) chips. The parallel computing process using FPGA is compared with the traditional serial computing process using CPUs. Simulation and experimental results show that this scheme can improve the computational speed of the system and that the algorithm is feasible.
- 13 September 2020
- Published by Springer Nature
- p. 607-617
Binocular Vision Detection and 3D Construction Based on Encoded Light
- 13 September 2020
- Published by Springer Nature
- p. 607-617
Binocular Vision Detection and 3D Construction Based on Encoded Light
- 13 September 2020
- Published by Springer Nature
- p. 596-606
Image Processing Method of 3D Scattered Point Cloud
- 13 September 2020
- Published by Springer Nature
- p. 596-606
Image Processing Method of 3D Scattered Point Cloud
- 2 October 2019
- Published by Springer Nature in Advances in Intelligent Systems and Computing
- p. 591-595
Research on the Application of RFID in Equipment Management in Universities
- 2 October 2019
- Published by Springer Nature in Advances in Intelligent Systems and Computing
- p. 591-595
Research on the Application of RFID in Equipment Management in Universities
- Open Access
- 9 July 2019
- Published by IOP Publishing in IOP Conference Series: Earth and Environmental Science
- Vol. 252 (5) , 052002
Research on Application of Beacon-based Location Technology in American Universities
With the popularity of smart phones, whether we are driving or walking, we are accustomed to using GPS for outdoor navigation. However, when you are in a library, shopping mall, etc., the GPS signal is blocked and the system will not be able to navigate for you. Then we need a technology that can provide indoor navigation. Beacon is a near-field sensing technology based on low-power Bluetooth technology that can be used to provide indoor positioning services for users with the Bluetooth capabilities of mobile phones. This paper describes the Beacon positioning technology principle and the application of Beacon-based location technology in American universities. In a university library, lab, conference room and other indoor environments, Beacon-based positioning technology can provide specific information transmission, indoor navigation, book recommendation based on big data analysis, and attendance check-in functions.
- 9 July 2019
- Published by IOP Publishing in IOP Conference Series: Earth and Environmental Science
- Vol. 252 (5) , 052002
Open AccessResearch on Application of Beacon-based Location Technology in American Universities
With the popularity of smart phones, whether we are driving or walking, we are accustomed to using GPS for outdoor navigation. However, when you are in a library, shopping mall, etc., the GPS signal is blocked and the system will not be able to navigate for you. Then we need a technology that can provide indoor navigation. Beacon is a near-field sensing technology based on low-power Bluetooth technology that can be used to provide indoor positioning services for users with the Bluetooth capabilities of mobile phones. This paper describes the Beacon positioning technology principle and the application of Beacon-based location technology in American universities. In a university library, lab, conference room and other indoor environments, Beacon-based positioning technology can provide specific information transmission, indoor navigation, book recommendation based on big data analysis, and attendance check-in functions.