CV

EDUCATION

• PhD @University College London
  • Research: Multimodal Machine Learning; Sensor-fusion System; Human-centred AI
• MSc Artificial Intelligence @University of Edinburgh
  • Courses: Machine Learning and Pattern Recognition; Big Data Analysis; Natural Language Processing; Computer Vision; Human Interaction Design;
  • Research: End-to-End Machine Learning Positioning System based on Smartphone Multi-sensory; Applied Machine Learning; Mobile Systems; Multimodal Machine Learning
• BEng (Honours) Electronics and Electrical Engineering @University of Edinburgh
  • Courses: Wearable Device; Signal Processing; Analogue/Digital Circuit Design; Microelectronics; Power System Design; Bioinformatics
  • Research: Indoor Positioning based on Smartphone Sensors using Machine Learning
  • Awards: International Student Scholarship (£2000)

SKILLS

• Machine Learning & Pattern Recognition
• C/JAVA/Python/Matlab/VHDL Programming
• Mobile Sensing System Design
• Multimodal Machine Learning
• Cyber Physical System Design
• Data Analyse and Processing
• Algorithms Design
• Electronics/Electrical System Design
• Analogue/Signal Circuit Design
• Human Computer Interaction
• English/Chinese
• Violin

PUBLICATIONS

Listening to the Mind: Earable Acoustic Sensing of Cognitive Load

Wei, Xijia, Dang, Ting, Al-Naimi, Khaldoon, Liu, Yang, Kawsar, Fahim, and Montanari, Alessandro. (2026). "Listening to the Mind: Earable Acoustic Sensing of Cognitive Load." Companion of the 2025 ACM International Joint Conference on Pervasive and Ubiquitous Computing. pp. 665-671.

Cognitive Load Monitoring via Earable Acoustic Sensing

Quan, Jiatao, Al-Naimi, Khaldoon, Wei, Xijia, Liu, Yang, Kawsar, Fahim, Montanari, Alessandro, and Dang, Ting. (2025). "Cognitive Load Monitoring via Earable Acoustic Sensing." ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). pp. 1-5.

Emotion in Art-Elicited Texts, Interpreted by GPT-4o: Self vs. Third-Person Perspectives

Narimatsu, Hiromi, Nomura, Keishi, Wei, Xijia, Berthouze, Nadia, and Kumano, Shiro. (2025). "Emotion in Art-Elicited Texts, Interpreted by GPT-4o: Self vs. Third-Person Perspectives."

CubeDN: Real-Time Drone Detection in 3D Space from Dual mmWave Radar Cubes

Fang, Yuan, Shi, Fangzhan, Wei, Xijia, Chen, Qingchao, Chetty, Kevin, and Julier, Simon. (2025). "CubeDN: Real-Time Drone Detection in 3D Space from Dual mmWave Radar Cubes." 2025 IEEE International Conference on Robotics and Automation (ICRA). pp. 3977-3983.

WiProt: A WiFi-RGBD Fusion System for Robust Protective Behaviour Recognition

Wei, Xijia, Fang, Yuan, Shi, Fangzhan, Wu, Shuang, Williams, Amanda, Gold, Nicolas, Chetty, Kevin, Cho, Youngjun, and Bianchi-Berthouze, Nadia. (2025). "WiProt: A WiFi-RGBD Fusion System for Robust Protective Behaviour Recognition." Proceedings of the Second International Workshop on Radio Frequency (RF) Computing. pp. 6-11.

Multi-Sensor Fusion for Indoor Smartphone Localization with Attention Mechanism

Li, Haoxuan, Wei, Xijia, Wei, Zhiqiang, Radu, Valentin, Wang, Cheng, and Li, Wenda. (2025). "Multi-Sensor Fusion for Indoor Smartphone Localization with Attention Mechanism." Proceedings of the 3rd ACM Workshop on Smart Wearable Systems and Applications. pp. 19-24.

mmWaveTryOn: The first mmWave-RGB Dataset for Clothes Try-On Multimodal Gesture Recognition

Wei, Xijia, Fang, Yuan, Liu, Zihan, Zhu, Xiyue, Wang, Jiawei, Liu, Yifu, Petreca, Bruna, Baurley, Sharon, Chetty, Kevin, Cho, Youngjun, et al. (2025). "mmWaveTryOn: The first mmWave-RGB Dataset for Clothes Try-On Multimodal Gesture Recognition." Proceedings of the 2025 ACM Workshop on Access Networks with Artificial Intelligence. pp. 31-35.

Vomee: A Multimodal Sensing Platform for Video, Audio, mmWave and Skeleton Data Capturing

Wei, Xijia, Fang, Yuan, Chetty, Kevin, Cho, Youngjun, and Bianchi-Berthouze, Nadia. (2025). "Vomee: A Multimodal Sensing Platform for Video, Audio, mmWave and Skeleton Data Capturing." Proceedings of the 2025 ACM Workshop on Access Networks with Artificial Intelligence. pp. 36-40.

SGANFuzz: A deep learning-based MQTT fuzzing method using generative adversarial networks

Wei, Zhiqiang, Wei, Xijia, Zhao, Xinghua, Hu, Zongtang, and Xu, Chu. (2024). "SGANFuzz: A deep learning-based MQTT fuzzing method using generative adversarial networks." IEEE Access. 12, pp. 27210-27224.

FabricTouch: A multimodal fabric assessment touch gesture dataset to slow down fast fashion

Olugbade, Temitayo, Lin, Lili, Sansoni, Alice, Warawita, Nihara, Gan, Yuanze, Wei, Xijia, Petreca, Bruna, Boccignone, Giuseppe, Atkinson, Douglas, Cho, Youngjun, et al. (2023). "FabricTouch: A multimodal fabric assessment touch gesture dataset to slow down fast fashion." 2023 11th International Conference on Affective Computing and Intelligent Interaction (ACII). pp. 1-8.

Leveraging WiFi Sensing Toward Automatic Recognition of Pain Behaviors

Wei, Xijia, Olugbade, Temitayo, Shi, Fangzhan, Wu, Shuang, Williams, Amanda, Gold, Nicholas, Cho, Youngjun, Chetty, Kevin, and Bianchi-Berthouze, Nadia. (2023). "Leveraging WiFi Sensing Toward Automatic Recognition of Pain Behaviors." International Conference on Affective Computing + Intelligent Interaction.

Understanding the Quality of Body Movement by Leveraging WiFi Sensing

Wei, Xijia, Shi, Fangzhan, Wu, Shuang, Chetty, Kevin, Cho, Youngjun, and Berthouze, Nadia. (2023). "Understanding the Quality of Body Movement by Leveraging WiFi Sensing." MobiUK 2023.

Leveraging Transfer Learning for Robust Multimodal Positioning Systems based on Smartphone Multisensory Data

Wei, Xijia and Radu, Valentin. (2022). "Leveraging Transfer Learning for Robust Multimodal Positioning Systems based on Smartphone Multisensory Data." 2022 International Conference on Indoor Positioning and Indoor Navigation (IPIN). pp. 1-8.

MMLoc+: A Transfer Learning based Multimodal Machine Learning Localization System for Dynamic Sensor Networks

Wei, Xijia and Radu, Valentin. (2022). "MMLoc+: A Transfer Learning based Multimodal Machine Learning Localization System for Dynamic Sensor Networks." MobiUK 2022.

MM-Loc: Cross-sensor indoor smartphone location tracking using multimodal deep neural networks

Wei, Xijia, Wei, Zhiqiang, and Radu, Valentin. (2021). "MM-Loc: Cross-sensor indoor smartphone location tracking using multimodal deep neural networks." 2021 International Conference on Indoor Positioning and Indoor Navigation (IPIN). pp. 1-8.

Sensor-fusion for smartphone location tracking using hybrid multimodal deep neural networks

Wei, Xijia, Wei, Zhiqiang, and Radu, Valentin. (2021). "Sensor-fusion for smartphone location tracking using hybrid multimodal deep neural networks." Sensors. 21(22), pp. 7488.

Calibrating Recurrent Neural Networks on Smartphone Inertial Sensors for Location Tracking

Wei, Xijia and Radu, Valentin. (2019). "Calibrating Recurrent Neural Networks on Smartphone Inertial Sensors for Location Tracking." 2019 International Conference on Indoor Positioning and Indoor Navigation (IPIN). pp. 1-8.

End-to-End Machine Learning for Smartphone-based Indoor Localisation and Tracking using Recurrent Neural Networks

Wei, Xijia and Radu, Valentin. (2018). "End-to-End Machine Learning for Smartphone-based Indoor Localisation and Tracking using Recurrent Neural Networks." Mobiuk 2018.

TALKS

Non-intrusive Multimodal Sensing with LLM for Human Understanding

October 01, 2025

Invited Talk at University of Macau, Science & Computing Science Dept., Macau, China

Towards Self Supervision for Sensing and Understanding Human Behaviours

July 01, 2024

Invited Talk at University College London, Computing Science Dept., London, UK

From Single Modality to Modality Fusion: The First Step Towards Robust Multisensory Based Localization

September 01, 2022

Invited Talk at The Hong Kong Polytechnic University, Engineering Dept., Hong Kong, China

End-to-end Multimodal Hybrid Neural Network for Sensor-fusion Systems

April 01, 2022

Invited Talk at Huawei Consumer BG, Shenzhen, China

WORK EXPERIENCE

• PhD Research Intern @Nokia Bell Labs, Cambridge, UK (June. 2023 - Sept. 2023)
  • Human-centred AI; Human Behaviour Understanding; Wearable Devices.
• AI Algorithm Researcher @Ubiquitous AI Lab, University of Sheffield (Nov. 2018 - Present)
  • Invest on an end-to-end multimodal deep learning network architecture for sensor-fusion smartphone based location tracking system
  • Lead research group in dataset collection, algorithm design, model optimisation and paper writing
• Fintech Department Manager @CNPC (Mar. 2019 - Present)
  • Director of Risk Management System Group
  • Director of Commercial Paper Exchange Platform Development Team
• AI Software Researcher @Scotland Microelectronics Centre, University of Edinburgh (Oct. 2016 - May 2017)
  • Develop an indoor positioning navigation system based on indoor WiFi received signal strength and electromagnetic distribution
  • Design electromagnetic distribution features based artificial neural network
  • Develop smartphone built-in sensors based indoor positioning navigation App
• Embedded Software Engineer @GUOZI Robots Automation Research Lab University of Zhejiang (Jun. 2016 - Aug. 2016)
  • Optimise the stability and efficiency of the control system of the chassis of the inspection robots
  • Improve system’s efficiency of 33% by self-clustering operating situations
• Mobile Software Engineer @Institute for Digital Communications, University of Edinburgh (Mar. 2016 - Dec. 2016)
  • Movement data collection and processing based on wearable devices
  • Instant user movement prediction AI system development. Clustering between walking, running, jumping, swimming and related complex non-periodical movements.
  • Deep neural network and convolutional neural network models based machine learning algorithm development and performance test
  • Improve the recognition accuracy from 60% to 97.4%
• Digital Security System Intern @Bank of England (Dec 2015 - Jan 2016)
  • Digital trading system development
  • Investment strategy
  • Risk management

Résumé

Download CV here