Jia Qian

  • Education:
    • Master Degree: Information Engineering in University Of Padova (Italy)
    • Bachelor Degree: Software Engineering in Fudan University (China)
  • Research Interests:
    • Federated Learning
    • Deep Learning
    • Graph neural Network
    • Data Privacy (Differential privacy, Adversarial Attack)
    • Active Learning
PhD Student

lainey.qian@gmail.com
jiaq@dtu.dk
LinkedIn
Google Scholar

Distributed real-time operational data analytics

Host: Technical University of Denmark (DTU)Cognitive System (CogSys) section.

  • Main supervisor: Prof. Lars Kai Hansen, lkai@dtu.dk (contact person)
  • Co-supervisor: Prof. Xenofon Fafoutis, xefa@dtu.dk

Objectives:

  1. Propose data analytics for Industry 4.0 that exploit the connectivity and data access features of the Fog Nodes.
  2. Implement a distributed real-time data analytics solution based on Machine-Learning-as-a-Service.
  3. Demonstrate the data analytics solution on an industrial use case.

Expected Results:

  • Distributed data representation and modeling, using the services provided by the Fog Nodes, which are close to the machines (robots, actuators, sensors).
  • Distributed real-time machine learning algorithms that use the Fog Computing Platform.
  • Implementation of the ML algorithms using ML-as-a-Service microservices.
  • Evaluation of the approaches, and quantification of value gains obtained from the improved operations.

Planned visits and collaboration:

  • University of Kaiserslautern: work on the data privacy issue under Federated Learning.

Publications:

  • Jia Qian, Sarada Prasad Gochhayat, and Lars Kai Hansen. Distributed active learning strategies on edge computing. In 2019 6th IEEE International Conference on Cyber Security and Cloud Computing (CSCloud)/2019 5th IEEE International Conference on Edge Computing and Scalable Cloud (EdgeCom) pages 221–226. IEEE, 2019. [pdf]

  • Jia Qian, Lars Kai Hansen, Xenofon Fafoutis, Prayag Tiwari, and Hari Mohan Pandey. Robustness analytics to data heterogeneity in edge computing. Computer Communications , 164:229–239, 2020. [pdf]

  • Jia Qian, Prayag Tiwari, Sarada Prasad Gochhayat, and Hari Mohan Pandey. A noble double-dictionary-based ecg compression technique for ioth. IEEE Internet of Things Journal, 7(10):10160–10170, 2020. [pdf]

  • Mohammadreza Barzegaran, Nitin Desai, Jia Qian, Koen Tange, Bahram Zarrin, Paul Pop, and Juha Kuusela. Fogification of electric drives: An industrial use case. In 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), volume 1, pages 77–84. IEEE, 2020. [pdf]

  • Mohammadreza Barzegaran, Nitin Desai, Jia Qian, and Paul Pop. Electric drives as fog nodes in a fog computing-based industrial use case. The Journal of Engineering, 2021. [pdf]

  • Prayag Tiwari, Jia Qian, Qiuchi Li, Benyou Wang, Deepak Gupta, Ashish Khanna, Joel JPC Rodrigues, and Victor Hugo C de Albuquerque. Detection of subtype blood cells using deep learning. Cognitive Systems Research, 52:1036–1044, 2018. [pdf]

  • Jia Qian, Hiba Nassar, and Lars Kai Hansen. Minimal conditions analysis of gradient-based reconstruction in federated learning (submitted). arXiv preprint arXiv:2010.15718 , 2020. [pdf]

  • Bebortta, S., Senapati, D., Rajput, N.K., Singh, A.K., Rathi, V.K., Pandey, H.M., Jaiswal, A.K., Qian, J. and Tiwari, P., 2020. Evidence of power-law behavior in cognitive IoT applications. Neural Computing and Applications32(20), pp.16043-16055.[pdf]

  • Jaiswal, A.K., Tiwari, P., Rathi, V.K., Qian, J., Pandey, H.M. and Albuquerque, V.H.C., 2020. Covidpen: A novel covid-19 detection model using chest x-rays and ct scans. Medrxiv. [pdf].

For the full publication list, please check Here.