Resources, Infrastructure Systems and built Environments

Department of Civil & Structural Engineering

Dr Peter Rockett


0114 222 5589

Department of Electronic & Electrical Engineering
The University of Sheffield
Velocity 2 - Level 1
3 Solly Street
S1 4DE


Peter 's interests include the following:

  • Statistical pattern recognition/machine learning
  • Evolutionary computation (genetic algorithms & genetic programming)
  • Multiobjective optimization using evolutionary algorithms
  • Application of evolutionary methods to pattern recognition
  • Evolutionary optimization of engineering design problems, especially 'design for manufacturing'.
  • Machine learning for building energy management systems (BEMS)

Recent activities and achievements

  • Multi-objective genetic programming, particularly for feature extraction in machine learning, and dynamical systems
  • Application of machine learning to energy management in domestic and non-domestic buildings
  • Pattern recognition/machine learning
  • Multi-objective evolutionary optimisation
  • Quantitative analysis of medical images for the diagnosis/treatment of occlusive vascular disease
  • Knowledge discovery in process control


A.Hathway, P.Rockett & P.Carpenter
The use of machine learning in model predictive control for the operation of non-domestic buildings
FutureBuild 2013
4-6 September 2013, Bath

L.Liu, L.Shao & P.Rockett
Human action recognition based on boosted feature selection and naive Bayes nearest-neighbor classification
Signal Processing
93(6), 1521-1530 (2013)

L.Liu, L.Shao & P.Rockett
Boosted key-frame selection and correlated pyramidal motion-feature representation for human action recognition
Pattern Recognition
46(7), 1810-1818 (2013)

J.Ni, R.H.Drieberg & P.I.Rockett
The use of an analytic quotient operator in genetic programming
IEEE Transactions on Evolutionary Computation
17(1), 146-152 (2013)

L.Liu, L.Shao & P.Rockett
Genetic programming-evolved spatio-temporal feature descriptor for human-action recognition
23rd British Machine Vision Conference
Guildford, Surrey , 3‑7 September 2012

D.Paredes Soto, P.Chan & P.Rockett
Performance comparison of low-level vessel detection algorithms for segmentation of X-ray angiograms
16th Medical Image Understanding and Analysis Conference
Swansea, 9-11 July 2012

K.Badran & P.I.Rockett
Multi-class pattern classification using single, multi-dimensional feature-space feature extraction evolved by multi-objective genetic programming and its application to network intrusion detection
Genetic Programming and Evolvable Machines
13(1), 33-63 (2012)

Y.Zhang & P.I.Rockett
A generic optimising feature extraction method using multiobjective genetic programming
Applied Soft Computing
11(1), 1087-1097 (2011)

Y.Zhang & P.I.Rockett
Domain-independent approaches to optimize feature extraction for multi-classification using multi-objective genetic programming
Pattern Analysis and Its Applications
13(3), 273-288 (2010)

R.Kumar, B.K.Bal & P.I.Rockett
Multiobjective genetic programming approach to evolving heuristics for the bounded-diameter minimum spanning tree problem
Genetic and Evolutionary Computation Conference (GECCO2009)
Montreal, Canada, 8-12 July 2009

Y.Zhang & P.I.Rockett
Application of multiobjective genetic programming to the design of robot failure recognition systems
IEEE Transactions on Automation and Systems Engineering
6(2), 372–376 (2009)

K.Badran & P.I.Rockett
The influence of mutation on population dynamics in multiobjective genetic programming
Genetic Programming & Evolvable Machines
11(1), 5-31 (2010). Published online at‑3 (2009)

P.Zou, P.Chan & P.I.Rockett
A model-based consecutive scanline tracking method for extracting vascular networks from 2D digital subtraction angiograms
IEEE Transactions on Medical Imaging
28(2), 241-249 (2009)

Y.Zhang & P.I.Rockett
A generic multi-dimensional feature extraction method using multiobjective genetic programming
Evolutionary Computation
17(1), 1-27 (2009)

Y.Zhang & P.I.Rockett
A comparison of three evolutionary approaches for multiobjective genetic programming
Artificial Intelligence Review
27(2-3), 149–163 (2007)

R.Kumar, K.K.Banka, A.H.Joshi & P.I.Rockett
Evolution of hyperheuristics for the biobjective 0/1 knapsack problems by multiobjective genetic programming
Genetic and Evolutionary Computation Conference (GECCO2008)
Atlanta, Georgia, USA, 12-16 July 2008

V.Kumar, A.Holzkaemper, B.Surridge, P.I.Rockett, M.Niranjan & D.N.Lerner
Bayesian challenges in integrated catchment modeling
International Congress on Environmental Modelling and Software (iEMSs 2008)
Barcelona, 7-10 July 2008

Y.Zhang, H.Li, M.Niranjan & P.I.Rockett
Applying cost-sensitive multiobjective genetic programming to feature extraction for spam e-mail filtering
11th European Conference on Genetic Programming (EuroGP2008)
Naples, 26-28 March 2008, in Lecture Notes in Computer Science vol. 4971, pp. 325-336, Springer-Verlag

K.Badran & P.I.Rockett
Integrating categorical variables with multiobjective genetic programming for classifier construction
11th European Conference on Genetic Programming (EuroGP2008)
Naples, 26-28 March 2008, in Lecture Notes in Computer Science vol. 4971, pp. 301-311, Springer-Verlag

Y.Zhang & P.I.Rockett
The Bayesian operating point of the Canny edge detector
IEEE Transactions on Image Processing
15(11), 3409- 3416 (2006)

Y.Zhang & P.I.Rockett
Multiobjective genetic programming feature extraction with optimized dimensionality
11th World Conference on Soft Computing in Industrial Applications
18 September – 6 October 2006 (Ranked one of the top six papers in the conference)

Y.Zhang & P.I.Rockett
Feature extraction using multi-objective genetic programming
Multi-Objective Machine Learning
(ed. Y.Jin) Springer, 2006

Y.Zhang & P.I.Rockett
Comparison of evolutionary strategies for multi-objective genetic programming
IEEE Systems, Man & Cybernetics Society Conference on Advances in Cybernetic Systems (AICS2006)
Sheffield, 7-8 September 2006, pp. 323-328

The evolutionary training of linear classifiers
IEEE Systems, Man & Cybernetics Society Conference on Advances in Cybernetic Systems (AICS2006)
Sheffield, 7-8 September 2006, pp. 214-246

Y.Zhang & P.I.Rockett
Evolving optimal feature extraction using multi-objective genetic programming: A methodology and preliminary study on edge detection
Genetic & Evolutionary Computation Conference (GECCO2005)
Washington, DC, 25-29 June 2005, pp. 795-802

An improved rotation-invariant thinning algorithm
IEEE Transactions on Pattern Analysis & Machine Intelligence
27(10), 1671- 1674 (2005)

B.P.Amavasai & P.I.Rockett
Multilayered-perceptron regularisation using a continuous degrees-of-freedom measure
IEEE UKRI Systems & Cybernetics Conference
Londonderry, 7-8 September 2004

R.Kumar & P.I.Rockett
Effective evolutionary multimodal optimization without explicit niching/sharing
Asian Applied Computing Conference (AACC) – 2nd International Conference on Information Technology (ITPC)
Kathmandu, Nepal, 29-31 October 2004. Published in Lecture Notes in Computer Science, vol. 3285, pp. 1- 8 (2004)

B.P.Amavasai & P.I.Rockett
Regularisation using a continuous measure of degrees-of-freedom for multilayered perceptrons
IEEE SMC UK-RI 3rd Workshop on Intelligent Cybernetic Systems
Londonderry, 7-8 September 2004.

R.Kumar & P.I.Rockett
Evolutionary Multimodal Optimization Revisited
Genetic & Evolutionary Computation Conference (GECCO-2003)
Chicago, 11-13 July 2003

Performance assessment of feature detection algorithms: A methodology and case study on corner detectors
IEEE Trans. Image Processing
12(12), 1668-1676, (2003)