Colin Graeme Johnson
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Colin Graeme Johnson has a total of 142 co-authors. Here are the top co-authors by number of shared publications:
- Alex Alves Freitas
University of Kent, Canterbury, UK
9 shared publications Fernando E. B. Otero
University of Kent, Chatham Maritime, United Kingdom
7 shared publications- Tom Castle
University of Kent, Canterbury, United Kingdom
5 shared publications - Alberto Moraglio
University of Exeter
4 shared publications Alexander E.I. Brownlee
4 shared publicationsJohn R. Woodward
Stirling University, Stirling, United Kingdom
4 shared publications
Latest Publications
- 24 November 2025
- Published by Springer Nature
- p. 21-34
A Hybrid Reasoning System for Visual Arithmetic Learning
- 24 November 2025
- Published by Springer Nature
- p. 21-34
A Hybrid Reasoning System for Visual Arithmetic Learning
- Open Access
- 1 April 2025
- Published by Springer Nature in Genetic Programming and Evolvable Machines
- Vol. 26 (1) , 1-3
Editorial introduction to the special issue for the tenth anniversary of geometric semantic genetic programming
- 1 April 2025
- Published by Springer Nature in Genetic Programming and Evolvable Machines
- Vol. 26 (1) , 1-3
Open AccessEditorial introduction to the special issue for the tenth anniversary of geometric semantic genetic programming
- Open Access
- 5 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 91-97
Building Technological Improvisation Skills through Student-devised Coursework Topics
The ability of improvise solutions to problems using a variety of technologies is an important, if often tacit, desired outcome from advanced computer science education. This paper will describe experience from three modules at two universities where students design their own assessment topic, based on a set of requirements aligned with the learning outcomes. The paper discusses why these technological improvisation skills are important, and how students can learn to cope with combining a variety variety of techniques, ideas and technologies that don't immediately fit well together. This helps students to build important high-level and meta-cognitive skills, and at a practical level provides students with projects that they can demonstrate to prospective employers after graduation. We discuss how these assessments were presented to students, and how the resulting student activities were aligned with learning objectives. We describe how complex ideas such as added value were explained to students, and how these assignments encouraged students to work on projects of ambition and substance, and to encourage their curiosity. Finally, we discuss some difficulties with this kind of assessment, and how we have endeavoured to tackle these difficulties. These include how such a diversity of assessments were marked fairly and consistently, how students who are struggling with the core module content can engage effectively, and how these kind of assessments can be devised without an excessive burden on teaching staff.
- 5 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 91-97
Open AccessBuilding Technological Improvisation Skills through Student-devised Coursework Topics
The ability of improvise solutions to problems using a variety of technologies is an important, if often tacit, desired outcome from advanced computer science education. This paper will describe experience from three modules at two universities where students design their own assessment topic, based on a set of requirements aligned with the learning outcomes. The paper discusses why these technological improvisation skills are important, and how students can learn to cope with combining a variety variety of techniques, ideas and technologies that don't immediately fit well together. This helps students to build important high-level and meta-cognitive skills, and at a practical level provides students with projects that they can demonstrate to prospective employers after graduation. We discuss how these assessments were presented to students, and how the resulting student activities were aligned with learning objectives. We describe how complex ideas such as added value were explained to students, and how these assignments encouraged students to work on projects of ambition and substance, and to encourage their curiosity. Finally, we discuss some difficulties with this kind of assessment, and how we have endeavoured to tackle these difficulties. These include how such a diversity of assessments were marked fairly and consistently, how students who are struggling with the core module content can engage effectively, and how these kind of assessments can be devised without an excessive burden on teaching staff.
- Open Access
- 22 November 2023
- Published by Springer Nature in Genetic Programming and Evolvable Machines
- Vol. 24 (2) , 1-3
New directions in fitness evaluation: commentary on Langdon’s JAWS30
- 22 November 2023
- Published by Springer Nature in Genetic Programming and Evolvable Machines
- Vol. 24 (2) , 1-3
Open AccessNew directions in fitness evaluation: commentary on Langdon’s JAWS30
- Open Access
- 1 March 2022
- Published by Elsevier in European Journal of Operational Research
- Vol. 297 (2) , 393-406
Metaheuristics “In the Large”
- 1 March 2022
- Published by Elsevier in European Journal of Operational Research
- Vol. 297 (2) , 393-406
Open AccessMetaheuristics “In the Large”
- 2 April 2021
- Published by Springer Nature
- p. 427-442
Creating a Digital Mirror of Creative Practice
- Open Access
- 24 January 2021
- Published by Wiley in Expert Systems
- Vol. 38 (3)
Solving the Rubik's cube with stepwise deep learning
This paper explores a novel technique for learning the fitness function for search algorithms such as evolutionary strategies and hillclimbing. The aim of the new technique is to learn a fitness function (called a Learned Guidance Function) from a set of sample solutions to the problem. These functions are learned using a supervised learning approach based on deep neural network learning, that is, neural networks with a number of hidden layers. This is applied to a test problem: unscrambling the Rubik's Cube using evolutionary and hillclimbing algorithms. Comparisons are made with a previous LGF approach based on random forests, with a baseline approach based on traditional error‐based fitness, and with other approaches in the literature. This demonstrates how a fitness function can be learned from existing solutions, rather than being provided by the user, increasing the autonomy of AI search processes.
- 24 January 2021
- Published by Wiley in Expert Systems
- Vol. 38 (3)
Open AccessSolving the Rubik's cube with stepwise deep learning
This paper explores a novel technique for learning the fitness function for search algorithms such as evolutionary strategies and hillclimbing. The aim of the new technique is to learn a fitness function (called a Learned Guidance Function) from a set of sample solutions to the problem. These functions are learned using a supervised learning approach based on deep neural network learning, that is, neural networks with a number of hidden layers. This is applied to a test problem: unscrambling the Rubik's Cube using evolutionary and hillclimbing algorithms. Comparisons are made with a previous LGF approach based on random forests, with a baseline approach based on traditional error‐based fitness, and with other approaches in the literature. This demonstrates how a fitness function can be learned from existing solutions, rather than being provided by the user, increasing the autonomy of AI search processes.
- 8 December 2020
- Published by Springer Nature
- p. 259-272
Software Fault Localisation via Probabilistic Modelling
- 8 December 2020
- Published by Springer Nature
- p. 259-272
Software Fault Localisation via Probabilistic Modelling
- 1 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Annual International Conference of the IEEE Engineering in Medicine and Biology Society
- Vol. 2020, 653-656
Pose Estimation from Electromyographical Data using Convolutional Neural Networks
This work demonstrates the effectiveness of Convolutional Neural Networks in the task of pose estimation from Electromyographical (EMG) data. The Ninapro DB5 dataset was used to train the model to predict the hand pose from EMG data. The models predict the hand pose with an error rate of 4.6% for the EMG model, and 3.6% when accelerometry data is included. This shows that hand pose can be effectively estimated from EMG data, which can be enhanced with accelerometry data.
- 1 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Annual International Conference of the IEEE Engineering in Medicine and Biology Society
- Vol. 2020, 653-656
Pose Estimation from Electromyographical Data using Convolutional Neural Networks
This work demonstrates the effectiveness of Convolutional Neural Networks in the task of pose estimation from Electromyographical (EMG) data. The Ninapro DB5 dataset was used to train the model to predict the hand pose from EMG data. The models predict the hand pose with an error rate of 4.6% for the EMG model, and 3.6% when accelerometry data is included. This shows that hand pose can be effectively estimated from EMG data, which can be enhanced with accelerometry data.
- Open Access
- 25 June 2020
- Published by Association for Computing Machinery (ACM)
- p. 40-48
Exploratory path planning for mobile robots in dynamic environments with ant colony optimization
In the path planning task for autonomous mobile robots, robots should be able to plan their trajectory to leave the start position and reach the goal, safely. There are several path planning approaches for mobile robots in the literature. Ant Colony Optimization algorithms have been investigated for this problem, giving promising results. In this paper, we propose the Max-Min Ant System for Dynamic Path Planning algorithm for the exploratory path planning task for autonomous mobile robots based on topological maps. A topological map is an environment representation whose focus is the main reference points of the environment and their connections. Based on this representation, the path can be composed by a sequence of state/actions pairs, which facilitates the navigability of the path, with no need to have the information of the complete map. The proposed algorithm was evaluated in static and dynamic environments, showing promising results in both of them. Experiments in dynamic environments show the adaptability of our proposal.
- 25 June 2020
- Published by Association for Computing Machinery (ACM)
- p. 40-48
Open AccessExploratory path planning for mobile robots in dynamic environments with ant colony optimization
In the path planning task for autonomous mobile robots, robots should be able to plan their trajectory to leave the start position and reach the goal, safely. There are several path planning approaches for mobile robots in the literature. Ant Colony Optimization algorithms have been investigated for this problem, giving promising results. In this paper, we propose the Max-Min Ant System for Dynamic Path Planning algorithm for the exploratory path planning task for autonomous mobile robots based on topological maps. A topological map is an environment representation whose focus is the main reference points of the environment and their connections. Based on this representation, the path can be composed by a sequence of state/actions pairs, which facilitates the navigability of the path, with no need to have the information of the complete map. The proposed algorithm was evaluated in static and dynamic environments, showing promising results in both of them. Experiments in dynamic environments show the adaptability of our proposal.