Skip to main content

Beniamino Hadj-Amar

I am a third year PhD student in the Oxford-Warwick Statistics Programme (OxWaSP). Currently, I am working under the supervision of Professor Bärbel Finkenstädt Rand on non-stationary and multivariate spectral analysis of time series, with application to circadian biomarkers for cancer chronotherapy and experiments on rodents to detect instances of sleep apnoea. Outside of my research interests I am a passionate footballer, a poker player and an electronic music producer.

Current research

We propose a novel Bayesian methodology for analysing time series that exhibit oscillatory behaviour with unknown periodicities which may change at unknown time points. Our methodology is based on a trans-dimensional Markov chain Monte Carlo (MCMC) algorithm which simultaneously updates the change-points and the periodicities relevant to any segment between change-points. We show that the proposed methodology successfully identifies nonstationary features in two applications which are relevant to e-Health and sleep research, namely the occurence of ultradian oscillations in human skin temperature during the time of night rest, and the detection of instances of sleep apnea in plethysmographic respiratory traces.

Moreover, we are hoping to develop statistical methodologies, in particular novel univariate and multivariate spectral analysis tools that are able to address in real time the non stationary nature of the incoming data as an individual’s circadian timing systems changes over time with the development of the disease and intermittent treatment courses.

Teaching

15825947_1431903443494504_7329160501112256499_n.jpg

Beniamino Hadj-Amar

B.Hadj-Amar@warwick.ac.uk