Academic Positions

  • Present 2017

    Postdoctoral Research Associate

    HomeOffshore.org Project, University of Manchester

  • 2017 2016

    Postdoctoral Research Associate

    MDSAS Project, University of Manchester

  • 2016 2013

    Teaching Assistant

    Data Engineering Course, University of Manchester

Education & Training

  • Ph.D. 2016

    Ph.D. Machine Learning

    University of Manchester, United Kingdom

  • MSc Machine Learning2012

    Master of Science,

    Johannes Kepler University, Austria

  • BSc Computer Science2009

    Software Engineering

    West University Timisoara, Romania

Certificates

  • 2018
    Deep Learning Specialization Deeplearning.ai
    image
    "Deep Learning, a 5-course specialization by deeplearning.ai on Coursera. Specialization Certificate earned on April 30, 2018"
  • 2018
    Sequence Models
    image
    "Sequence Models by deeplearning.ai on Coursera. Certificate earned at Monday, April 30, 2018 8:07 PM GMT"
  • 2018
    Convolutional Neural Networks
    image
    "Convolutional Neural Networks by deeplearning.ai on Coursera. Certificate earned at Monday, April 23, 2018 7:43 PM GMT"
  • 2018
    Structuring Machine Learning Projects
    image
    "Structuring Machine Learning Projects by deeplearning.ai on Coursera. Certificate earned at Wednesday, April 18, 2018 2:50 PM GMT"
  • 2018
    Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization
    image
    "Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization by deeplearning.ai on Coursera. Certificate earned at Tuesday, April 17, 2018 6:35 PM GMT"
  • 2018
    Neural Networks and Deep Learning
    image
    "Neural Networks and Deep Learning by deeplearning.ai on Coursera. Certificate earned at Monday, April 16, 2018 5:25 PM GMT"
  • 2016
    Computational Investing
    image
    "Computational Investing, Part I by Georgia Institute of Technology on Coursera. Certificate earned at Thursday, January 7, 2016 11:08 PM GMT"
  • 2016
    Econometrics: Methods and Applications
    image
    "Econometrics: Methods and Applications by Erasmus University Rotterdam on Coursera. Certificate earned at Saturday, April 9, 2016 8:34 PM GMT"
  • 2015
    Data Manipulation at Scale: Systems and Algorithms
    image
    "Data Manipulation at Scale: Systems and Algorithms by University of Washington on Coursera. Certificate earned at Tuesday, September 29, 2015 12:09 PM GMT"
  • 2015
    Text Mining and Analytics
    image
    "Text Mining and Analytics by University of Illinois at Urbana-Champaign on Coursera. Certificate earned at Wednesday, July 8, 2015 12:00 AM GMT"
  • 2014
    Cluster Analysis in Data Mining
    image
    "Cluster Analysis in Data Mining by University of Illinois at Urbana-Champaign on Coursera. Certificate earned at Thursday, June 4, 2015 12:00 AM GMT"
  • 2014
    Game Theory
    image
  • 2015
    Astronomy: Exploring time and space
    image

Research Summary - HomeOffshore Project

The cost decrease and ubiquity of sensors facilitates real-time collection of data from wind farms, data that can be characterized by large volume (many sensors), high velocity (high measurement rate), high variety (image, sensor time-series, text reports), and potentially plagued with issues of veracity (missing/out-of-range data).

Our aim is to develop state of the art data models and infrastructure for the future wind farms. Our next generation Condition Monitoring systems based on Machine Learning and robotics will learn to predict failures before they happen and will significantly reduce the cost of operations and maintenance.

Interests

  • Time Series Analysis
  • NoSQL databases
  • Distributed learning Machine Learning
  • Deep Learning

Filter by type:

Sort by year:

A Review of Machine Learning methods utilized in Wind Turbine Condition Monitoring

Adrian Stetco, Goran Nenadic, John Keane
Journal Papers to be decided

Abstract

Fuzzy C-means++: Fuzzy C-means with Effective Seeding Initialization

Adrian Stetco, Xiaojun-Zeng, John Keane
Journal Paper Expert Systems with Applications (Elsevier) | doi:10.1016/j.eswa.2015.05.014

Fuzzy C-means has been utilized successfully in a wide range of applications, extending the clustering capability of the K-means to datasets that are uncertain, vague and otherwise hard to cluster. This paper introduces the Fuzzy C-means++ algorithm which, by utilizing the seeding mechanism of the K-means++ algorithm, improves the effectiveness and speed of Fuzzy C-means. By careful seeding that disperses the initial cluster centers through the data space, the resulting Fuzzy C-means++ approach samples starting cluster representatives during the initialization phase. The cluster representatives are well spread in the input space, resulting in both faster convergence times and higher quality solutions. Implementations in R of standard Fuzzy C-means and Fuzzy C-means++ are evaluated on various data sets. We investigate the cluster quality and iteration count as we vary the spreading factor on a series of synthetic data sets. We run the algorithm on real world data sets and to account for the non-determinism inherent in these algorithms we record multiple runs while choosing different k parameter values. The results show that the proposed method gives significant improvement in convergence times (the number of iterations) of up to 40 (2.1 on average) times the standard on synthetic datasets and, in general, an associated lower cost function value and Xie–Beni value. A proof sketch of the logarithmically bounded expected cost function value is given.

Fuzzy cluster analysis of financial time series and their volatility assessment

Adrian Stetco, Xiaojun-Zeng, John Keane
Conference Paper IEEE International Conference on Systems, Man and Cybernetics

Abstract

Every company listed on the London Stock Exchange is classified into an industry sector based on its primary activity, however, it may be both more interesting and valuable to group similarly performing companies based on their historical stock price record over a long period of time. Using fuzzy clustering analysis with a correlation-based metric, we obtain a more insightful categorization of the companies into groups with fuzzy boundaries, giving arguably a more realistic and detailed view of their relationships. Once cluster analysis is performed, we analyze the behaviour of discovered groups in terms of the volatility of their returns using both standard deviation and exponentially weighted moving average. This approach has the potential to be of practical relevance in the context of diversified portfolio construction as it can detect fuzzy clusters of correlated stocks that have lower inter-cluster correlation, analyze their volatility and sample potentially less risky combination of assets.

  • image

    HomeOffshore.org

    Condition Monitoring with Machine Learning

    The HOME Offshore project will develop an intelligent decision support process, where experts will co-operate with the condition monitoring algorithms to identify key signals and actionable patterns to detect developing failures across components and subcomponents. The process will integrate time-stamped event data collected by various components, and then select, pre-process and transform target signals, to be analysed to infer integrated data-driven models. Such models will aim to reduce the quantity of monitored and analysed data by identifying diagnostic patterns and signals that can indicate a developing fault with minimal data, triggering dynamic requests for extra data capture as/when needed (e.g. via additional robot-assisted inspections of a sub-system; or analysis of low-granularity sensing data). We will combine these models with knowledge-driven models (e.g. existing reliability models and multi-signal component/turbine granular approaches) to identify actionable decisions.

  • image

    MDSAS

    Very short description of the project.

    The project aims to optimize the management of patient therapy through modeling the pharmacokinetics of the medicine (concentration in blood as function of time). Home treatments, where users log their times, dosages and medicine taken through smartphones, laptops, etc. (think FitBit) are becoming very popular especially for chronic diseases such as Hemophilia. We collaborate with Haemtrack (a highly successful online national system for Hemophilia patients) which provides us with a comprehensive dataset of patient background information, medicine logs, adverse effects.

    A parametrized model was implemented which takes as input a discrete set of temporal treatments from a database and produces a time series of pharmacokinetic curves representing drug concentration in the body. These pharmacokinetic curves allow modelling based on patient specific parameters such as half-life of a medicine, volume of distribution (e.g. plasma volume), etc.

Contact & Meet Me

I would be happy to talk to you about projects involving data mining.

At My Office

You can find me at office 2.58 located in the Kilburn Building at the University of Manchester.

I am at my office every day from 9:00 am until 17:00 pm, but you may consider a call to fix an appointment.