Online analysis of data stream is important in enabling timely response and forecasting, yet it is challenging, as upcoming data is unknown. The research area to detect changing patterns in an online data stream is called drift detection. In many real-world domains, noise or error in data is inevitable and prevalent. Robustness of machine learning methods against noise remains one of the main challenges in AI.
This PhD project aims to propose new algorithms of deep learning transform to achieve accurate and timely drift detection in noisy data streams.
The key problems to be tackled are:
- the inefficiency on the performance (accuracy, timeliness, and complexity) of the existing drift detection methods;
- The learning and modelling of noise in the data stream, using machine learning approaches, including both the deterministic and heuristic ones; and
- enabling the learned noise models to be adaptive to upcoming data. Here we focus on the scenarios where the signal-to-noise ratio is higher than 1.
This PhD project will evaluate the proposed algorithms into two real world applications:
- (a) an operating unmanned surface vehicle (USV) systems for environment monitoring; and
- (b) an IoT system for landslides prediction.
For more information about doctoral scholarship and PhD programme at Xi’an Jiaotong Liverpool University (XJTLU), please visit:
The candidate should have a first class or upper second class honours degree (BSc), or a master’s degree MSc (or equivalent qualification), in Computer Science, Software engineering, AI, Mathematics, or Engineering. The candidate should have solid backgrounds in algorithms and in programming in Python.
Evidence of good spoken and written English is essential. The candidate should have an IELTS score of 6.5 or above, if the first language is not English. This position is open to all qualified candidates irrespective of nationality.
The student will be awarded a PhD degree from the University of Liverpool (UK) upon successful completion of the program.
How to Apply:
Interested applicants are advised to email: Nanlin.Jin@xjtlu.edu.cn (XJTLU principal supervisor’s email address) the following documents for initial review and assessment (please put the project title in the subject line).
- Two formal reference letters
- Personal statement outlining your interest in the position
- Certificates of English language qualifications (IELTS or equivalent)
- Full academic transcripts in both Chinese and English (for international students, only the English version is required)
- Verified certificates of education qualifications in both Chinese and English (for international students, only the English version is required)
- PDF copy of Master Degree dissertation (or an equivalent writing sample) and examiners reports available