I am a Ph.D. candidate at State Key Laboratory of Computer Architecture (SKLCA), Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS). My advisor is Prof. Zhiwei Xu (徐志伟) .
Sponsored by China Scholarship Council (CSC), I was a visiting Ph.D. student supervised by Prof. Weisong Shi (施巍松) in the Connected and Autonomous dRiving Laboratory (CAR) and Mobile and Internet Systems Laboratory (MIST), Wayne State University, USA.
xingzhou92@gmail.com (backup)
Address: China: Kexueyuan South Road #6, Haidian, Beijing 100190. Google Scholar: Xingzhou Zhang
Github: zxzStar I am on the job market for a research position in 2020. I am open to both industry and academia. Feel free to contact me if you find a match.
Research Interests
My research interests focus on computer system, edge computing, and machine learning. Currently, I am interested in solving how edge devices (e.g. vehicle, mobile phone) run costly machine learning algorithms with limited resources. The research points include algorithms, machine learning frameworks, and system optimization. The research scenes focus on autonomous driving and smart home.Experience
| Nov. 2017 - Apr. 2019 | Visiting student | Visiting the CAR Lab in Wayne State University, Michigan, USA |
| Sep. 2014 – Current | Ph.D. in Computer Architecture | Institute of Computing Technology (ICT), Chinese Academy of Sciences, China |
| Sep. 2010 – Jul. 2014 | B.S. in Computer Science and Technology | Shandong University, China |
Projects
-
OpenEI (Feb. 2019 - Current, Wayne State University and Institute of Computing Technology)
An open framework for edge intelligence.
[1] Xingzhou Zhang, Yifan Wang, Sidi Lu, Liangkai Liu, Lanyu Xu, Weisong Shi, OpenEI: An Open Framework for Edge Intelligence, in Proceedings of the 39th IEEE International Conference on Distributed Computing Systems (ICDCS), Vision/Blue Sky Track, July 7-10, 2019, Dallas, USA. -
pBEAM (Nov. 2017 - Nov. 2018, Wayne State University, IBM, Denso)
This work proposes pBEAM, a collaborative cloud-edge computation system for personalized driving behavior modeling. The driving behavior model is built on top of Generative Adversarial Recurrent Neural Networks (GARNN), which adapts to the dynamic change of normal driving. A personalized edge model is trained on top of the pruned model using CGARNN-Edge (Conditional GARNN), which considers drivers’ personal or contextual information as additional conditions.
[1] Xingzhou Zhang, Mu Qiao, Liangkai Liu, Pengfei Xu, and Weisong Shi, Collaborative Cloud-Edge Computation for Personalized Driving Behavior Modeling, in Proceedings of the fourth ACM/IEEE Symposium on Edge Computing (SEC), November 7-9, 2019, Arlington, VA, USA. -
pCAMP (Mar. 2018 - Current, Wayne State University and Institute of Computing Technology)
This work makes a comprehensive performance comparison and analysis of several state-of-the-art deep learning packages on the edges, including TensorFlow, Caffe2, MXNet, PyTorch, and TensorFlow Lite. It focuses on evaluating the latency, memory footprint and energy of these tools with four popular deep learning models on different edge devices, including MacBook, Intel FogNode, NVIDIA Jetson TX2, Raspberry Pi, and Nexus 6P.
[1]Xingzhou Zhang, Yifan Wang, and Weisong Shi, pCAMP: Performance Comparison of Machine Learning Packages on the Edges, USENIX Hotedge 18. -
SafeShareRide (Dec. 2017 - Oct. 2018, Wayne State University)
An edge-based attack detection in ridesharing services, namely SafeShareRide, which can detect dangerous events happening in the vehicle in near real time. The detection of SafeShareRide consists of three stages: speech recognition, driving behavior detection, and video capture and analysis. We implemented SafeShareRide system by leveraging open source algorithms.
[1] Liangkai Liu, Xingzhou Zhang, and Weisong Shi, SafeShareRide: Edge-based Attack Detection in Ridesharing Services, USENIX Hotedge 18.
[2] Liangkai Liu, Xingzhou Zhang, Mu Qiao, and Weisong Shi, SafeShareRide: Edge-based Attack Detection in Ridesharing Services, in Proceedings of the third ACM/IEEE Symposium on Edge Computing (SEC), Oct. 25-27, 2018. Bellevue, WA. -
OpenVDAP (Nov. 2017 - Current, Wayne State University)
An Open Vehicular Data Analytics Platform (OpenVDAP) for future Connected and Autonomous Vehicles (CAVs).
[1] Qingyang Zhang, Yifan Wang, Xingzhou Zhang, Liangkai Liu, Xiaopei Wu, Weisong Shi, etc. OpenVDAP: An Open Vehicular Data Analytics Platform for CAVs, ICDCS 2018.
[2] Liangkai Liu, Xingzhou Zhang, Qingyang Zhang, Andrew Weinert, Yifan Wang and Weisong Shi, AutoVAPS: An IoT-Enabled Public Safety Service on Vehicles, in Proceedings of 4th Workshop on Science of Smart City Operations and Platforms Engineering (SCOPE), April 15-18, 2019. -
IO Isolation (Apr. 2017 - Nov. 2017, Alibaba and Institute of Computing Technology)
Leveraging hardware and software co-design methods to improve the read performance (latency) under the write interference of NVMe SSD in data center.
Xingzhou Zhang, Yifan Wang, Li Zha, Zheng Liu, etc. -
IEHouse (Oct. 2015 - Feb. 2017, Institute of Computing Technology)
A Non-Intrusive Household Appliance State Recognition System. It aims to discern devices by identifying a single measurement from the aggregate data. It uses Deep Neural Network (DNN) and the average accuracy of recognizing 10 mixed typical appliance states is 92.9%.
[1] Xingzhou Zhang, Yifan Wang, Lu Chao, Zhiwei Xu, etc. IEHouse: A Non-Intrusive Household Appliance State Recognition System, UIC 2017.
[2] Yifan Wang, Xingzhou Zhang, Lu Chao, etc, PowerAnalyzer: An Energy-Aware Power Monitor System Aiming at Energy-Saving, IGSC 2017. -
Metcalfe's Law (July. 2014 - Feb. 2015, Institute of Computing Technology)
Expand Metcalfe’s law to developing country by utilizing the actual data of Tencent and Facebook. It finds that both Tencent and Facebook data fit Metcalfe’s law quite well.
Xingzhou Zhang, Jingjie Liu, and Zhiwei Xu, Tencent and Facebook data validate Metcalfe's law, Journal of Computer Science and Technology (JCST), Vol. 30, No. 2, pp. 246-251, 2015.
Publications
- Xingzhou Zhang, Mu Qiao, Liangkai Liu, Pengfei Xu, and Weisong Shi, Collaborative Cloud-Edge Computation for Personalized Driving Behavior Modeling, in Proceedings of the fourth ACM/IEEE Symposium on Edge Computing (SEC), November 7-9, 2019, Arlington, VA, USA.
- Xingzhou Zhang, Yifan Wang, Sidi Lu, Liangkai Liu, Lanyu Xu, Weisong Shi, OpenEI: An Open Framework for Edge Intelligence, in Proceedings of the 39th IEEE International Conference on Distributed Computing Systems (ICDCS), Vision/Blue Sky Track, July 7-10, 2019, Dallas, USA.
- Xingzhou Zhang, Sidi Lu, Weisong Shi, 边缘智能中的协同计算技术研究 (Collaborative Computing Techniques in Edge Intelligence), 《人工智能》（AI View), CCID, No. 12, Oct, 2019, China.
- Fang Liu, Guoming Tang, Youhuizi Li, Zhiping Cai, Xingzhou Zhang, Tongqing Zhou, A Survey on Edge Computing Systems and Tools, in Proceedings of the IEEE (PIEEE), Vol. 107, No. 8, August 2019. pp. 1537-1562.
- Yifan Wang, Liangkai Liu, Xingzhou Zhang, and Weisong Shi, HydraOne: An Indoor Experimental Research and Education Platform for CAVs, in Proceedings of the 2nd USENIX Workshop on Hot Topics in Edge Computing (HotEdge), July 9, 2019, Renton, WA, USA.
- Liangkai Liu, Xingzhou Zhang, Qingyang Zhang, Andrew Weinert, Yifan Wang and Weisong Shi, AutoVAPS: An IoT-Enabled Public Safety Service on Vehicles, in Proceedings of 4th Workshop on Science of Smart City Operations and Platforms Engineering (SCOPE), April 15-18, 2019.
- Weisong Shi, Xingzhou Zhang, Yifan Wang and Qingyang Zhang 边缘计算：现状与展望（Edge Computing: Start-of-the-Art and Future Directions),《计算机研究与发展(Journal of Computer Research and Development)》（60周年特刊） , Vol. 56, No. 1, January 2019.
- Xingzhou Zhang, Yifan Wang, and Weisong Shi, pCAMP: Performance Comparison of Machine Learning Packages on the Edges, in Proceedings of USENIX Workshop on Hot Topics in Edge Computing (HotEdge), July 10, 2018, Boston, USA.
- Liangkai Liu, Xingzhou Zhang, Mu Qiao, and Weisong Shi, SafeShareRide: Edge-based Attack Detection in Ridesharing Services, in Proceedings of the third ACM/IEEE Symposium on Edge Computing (SEC), Oct. 25-27, 2018. Bellevue, WA.
- Liangkai Liu, Xingzhou Zhang, Mu Qiao, and Weisong Shi, SafeShareRide: Edge-based Attack Detection in Ridesharing Services, in Proceedings of USENIX Workshop on Hot Topics in Edge Computing (HotEdge), July 10, 2018, Boston, USA.
- Qingyang Zhang, Yifan Wang, Xingzhou Zhang, Liangkai Liu, Xiaopei Wu, Weisong Shi and Hong Zhong, OpenVDAP: An Open Vehicular Data Analytics Platform for CAVs, in Proceedings of the 38th IEEE International Conference on Distributed Computing Systems (ICDCS), Vision/Blue Sky Track, July 2-5, 2018, Vienna, Austria.
- Xiaohui Peng, Xingzhou Zhang, Yifan Wang, and Lu Chao, Web使能的物端计算系统（Web Enabled Things Computing System),《计算机研究与发展（Journal of Computer Research and Development）》, Vol. 55, No. 3, pp. 572-584. Feb 2018. (Chinese)
- Xingzhou Zhang, Yifan Wang, Lu Chao, Lang Wu, Chundian Li, Xiaohui Peng, and Zhiwei Xu, IEHouse: A Non-Intrusive Household Appliance State Recognition System, in Proceedings of the 14th IEEE International Conference on Ubiquitous Intelligence and Computing (UIC). Aug 4-8, 2017, San Francisco, USA.
- Xingzhou Zhang, Jingjie Liu, and Zhiwei Xu, Tencent and Facebook data validate Metcalfe's law, Journal of Computer Science and Technology (JCST), Vol. 30, No. 2, pp. 246-251, 2015.
- Yifan Wang, Xingzhou Zhang, Lu Chao, Lang Wu and Xiaohui Peng, PowerAnalyzer: An Energy-Aware Power Monitor System Aiming at Energy-Saving, in Proceedings of the 8th IEEE International Conference on Green and Sustainable Computing Conference (IGSC). Oct 23-25, 2017, Orlando, Florida, USA.
2019
2018
2017 - 2015
Reviewer
Copyright (C) 2015-2019 by Xingzhou Zhang.
Last updated: 2019-10-20
