School of Engineering » Lab Research Students 2015/2016

Miss Sajeevie Pinnaduwe Hewa-BEng Student

Wed, 11 Oct 2017 10:44:31 GMT

Miss Sajeevie Pinnaduwe Hewa was a BEng Student in Engineering Business Management. She worked on Analytic Hierarchy process (AHP) to decide whether to adopt laparoscopy or open surgery in terms of prioritizing the different factors affecting the decision. AHP was used to solve this problem by constructing a consistent framework for step-by-step decision-making.

Mr Karan Hunjan-MEng Student

Wed, 11 Oct 2017 10:38:17 GMT

Mr Karan Hunjan was a MEng student in Electronic Engineering. He worked on early detection of disease worsening. In particular, he investigated the impact of mental stress on Heart Rate Variability, using machine learning predictive modelling. The study investigated the use of ultra-short (2 minute) HRV measurements by comparing their analysis with the more standard short (5 minute) measurements. It aimed to test whether or not a 2 minute recording, once processed, is significant in showing indication of significant physiological change such that a diagnosis could be completed or actions could be taken to address negative changes.

Miss Ruby Davies-BEng Student

Wed, 11 Oct 2017 10:31:39 GMT

Miss Ruby Davies was a BEng student in Engineering Business Management. She worked on Analytic Hierarchy process (AHP) applied to cardiology. She created a survey to discuss and analyse whether AHP is a realistic tool in cardiology to help healthcare professionals make decisions about the care of their patients finding a solution to a problem based on several different opinions within the same ward. Therefore, the aim of my project was to determine whether AHP is a useful tool when bringing different opinions together to decide on the best outcome, or whether AHP is not possible when there are many different opinions.

Mr Xu Haotian- MSc Student

Wed, 11 Oct 2017 10:27:01 GMT

Mr Xu Haotian was a MSc student in Communications and Information Engineering. He worked on mental stress detecion via ultra-short Heart Rate Variability analysis using wearable sensors. The study aimed to find out about the limit of existing methods to detect stress using wearable devices, as well as exploring new and alternative solutions. By analysing 5-minute, 3-minute, 2-minute, 1-minute, and 30-second segments of ECG data from 42 students under rest and stress conditions.

Miss Erin Charest-MSc Student

Wed, 11 Oct 2017 10:22:17 GMT

Miss Erin Chest was MSc student in Biomedical Engineering. She worked on actigraphy signals, investigating the difference between accelerometers signals acquired on the chest and wrist to assess sleep qiality. She used advanced signal processing to monitor sleep patterns.