Dr Jethro Shell

Job: VC2020 Senior Lecturer

Faculty: Computing, Engineering and Media

School/department: School of Computer Science and Informatics

Research group(s): Centre for Computational Intelligence (CCI)

Address: De Montfort University, The Gateway, Leicester, LE1 9BH, UK

T: 44 (0)116 207 8520

E: jethros@dmu.ac.uk

 

Personal profile

Whilst working for Panasonic Computer Products (Europe), Dr Shell completed a part time MSc in Information Technology at De Montfort University, finishing his studies in 2008. Following a 10 year career with Panasonic, he left industry to return to academia completing a PhD at De Montfort University. The focus of his PhD was on sparse data environments where the ability to gain labelled data is initially either extremely difficult or impossible. Environments such as extremely remote locations, ad-hoc structures or user groups that are very specific. These environments often also produce uncertain and vague data. To address these issues he constructed a framework that combined a fuzzy logic representation of the data with a transductive transfer learning approach.

Dr Shell has been a Principal Investigator (PI) on a number of internal and externally funded (including Horizon2020) projects that involve the application of Computational Intelligence (CI) and gaming applications.

The research interests of Dr Shell are focussed around the application of Computational Intelligence, specifically fuzzy logic and transfer learning across and within three main areas: gaming, healthcare and HCI.

He is currently a senior lecturer and researcher in Games and Information Systems at De Montfort University

Research group affiliations

Centre for Computational Intelligence (CCI)

De Montfort University Games And interactive MEdia Research (DMU:GAMER)

Publications and outputs

  • Designing VR training systems for children with attention deficit hyperactivity disorder (ADHD)
    Designing VR training systems for children with attention deficit hyperactivity disorder (ADHD) Shell, Jethro; Kwan, H. Y.; Lin, L.; Fahy, C.; Pang, S.; Xing, Y. Kwan, H.Y., Lin, L., Fahy, C., Shell, J., Pang, S. and Xing, Y. (2022) Designing VR training systems for children with attention deficit hyperactivity disorder (ADHD). In: 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW) pp. 88-89. IEEE.
  • Virtual Reality Research: Design Virtual Education System for Epidemic (COVID-19) Knowledge to Public
    Virtual Reality Research: Design Virtual Education System for Epidemic (COVID-19) Knowledge to Public xing, Yongkang; Liang, Zhanti; Fahy, Conor; Shell, Jethro; Guan, Kexin; Liu, Yuxi; Zhang, Qian Advances in information and communication technologies have created a range of new products and services for the well-being of society. Virtual Reality (VR) technology has shown enormous potential in educational, commercial, and medical fields. The recent COVID-19 outbreak highlights a poor global performance in communicating epidemic knowledge to the public. Considering the potential of VR, the research starts from analyzing how to use VR technology to improve public education in COVID-19. The research uses Virtual Storytelling Technology (VST) to promote enthusiasm in user participation. A Plot-based VR education system is proposed in order to provide an immersive, explorative, educational experiences. The system includes three primary modules: the Tutorial Module, the Preparation Module, and the Investigation Module. To remove any potential confusion in the user, the research aims to avoid extremely complicated medical professional content and uses interactive, entertainment methods to improve user participation. In order to evaluate the performance efficiency of the system, we conducted performance evaluations and a user study with 80 participants. Compared with traditional education, the experimental results show that the VR education system can used as an effective educational tool for epidemic (COVID-19) fundamental knowledge. The VR technology can assist government agencies and public organizations to increase public understanding of the spread the epidemic (COVID-19) open access article Xing, Y., Liang, Z., Fahy, C., Shell, J., Guan, K., Liu, Y. and Zhang, Q. (2021) Virtual Reality Research: Design Virtual Education System for Epidemic (COVID-19) Knowledge to Public. Applied Sciences, 11 (22), 10586
  • Historical Data Trend Analysis in Extended Reality Education Field
    Historical Data Trend Analysis in Extended Reality Education Field Shell, Jethro; Xing, Yongkang; Liang, Zhanti; Fahy, Conor; Guan, Kexin; Liu, Guan The arrival of the digital age brings Virtual Reality, Augmented Reality, and Mixed Reality technologies into our daily life. It provides a brand-new user experience to composite with real environments. Due to the development of related devices in recent years, the highly interactive connections between users and devices have gradually evolved. The paper starts from a literature review to discuss Virtual Reality, Augmented Reality, and Mixed Reality's history and social impact. The review reveals not only the traditional historical review but also contains a data research study. The research focuses on the case study paper, which proposed a bright, interactive future with technology in educational field. We compared the proposed future view and the current development. This paper collected 269 citations from 2005 to 2020 and analyzed them, assessing whether they belonged to technical or theoretical paper. The paper uses the collected data to discuss industrial developing trends and indicates the possible future view based on the data study result. Xing, Y., Liang, Z., Shell, J., Fahy, C., Guan, K. and Liu, B. (2021). Historical Data Trend Analysis in Extended Reality Education Field. In: 2021 IEEE 7th International Conference on Virtual Reality (ICVR), pp. 434-440
  • What Do We See: An Investigation Into the Representation of Disability in Video Games
    What Do We See: An Investigation Into the Representation of Disability in Video Games Shell, Jethro There has been a large body of research focused on the representation of gender in video games. Disproportionately, there has been very little research in respect to the representation of disability. This research was aimed at examining the representation of disabled characters through a method of content analysis of trailers combined with a survey of video gamers. The overall results showed that disabled characters were under-represented in videogames trailers, and respondents to the survey viewed disabled characters as the least represented group. Both methods of research concluded that the representation of disabled characters was low. Additionally, the characters represented were predominantly secondary, non-playable characters not primary. However, the research found that the defined character type was a mixture of protagonists and antagonists, bucking the standard view of disabled characters in video games. Shell, J., (2021) What Do We See: An Investigation Into the Representation of Disability in Video Games. arXiv preprint arXiv:2103.17100.
  • Healthcare Facility Coverage for Malaria and Sickle Cell Disease Treatment: A Spatial Analysis of Ikorodu Local Government Area of Lagos State
    Healthcare Facility Coverage for Malaria and Sickle Cell Disease Treatment: A Spatial Analysis of Ikorodu Local Government Area of Lagos State Olowofoyeku, Olukemi; Shell, Jethro; Goodyer, Eric A.; Deka, Lipika The escalating population growth in Nigeria calls for urgent attention to malaria control and the provision of accessible public health care for treatment of the disease (appropriate malaria treatment and intervention can, in turn, bring a reduction in the sickle cell disease (SCD) crisis). Malaria is a major cause of visits to healthcare facilities, which is amplified by the malaria interaction with SCD. Access to treatment is a basic need of the population in a country; however, in Nigeria, access to health care is generally poor. Healthcare facilities are sparsely distributed and services inadequate to take care of the health needs of the whole population. This article discusses malaria and SCD prevalence in Nigeria and analyses the spatial distribution of primary healthcare facilities in the Ikorodu Local Government Area of Lagos State, Nigeria, using Geographic Information System (GIS). Analysis is based on existing facility locations in relation to 15 and 30 minutes’ walking time in a 1-km and 2-km catchment radius, respectively. The results show primary health center (PHC) facilities’ coverage of 48 percent for 2-km catchment radius and 15 percent for 1-km catchment. Based on this analysis, this article argues that there is a need to increase the number of facilities for treatment that are optimally located to take care of travel distance and expand facility coverage. This will reduce mortality and morbidity rates due to the diseases. The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link. Olowofoyeku. O., Shell. J., Goodyer. E., Deka. L. (2019) Healthcare Facility Coverage for Malaria and Sickle Cell Disease Treatment: A Spatial Analysis of Ikorodu Local Government Area of Lagos State. The International Journal of Health, Wellness and Society, 10(2), pp. 33-51.
  • INNATE: Intelligent Non-invasive Nocturnal epilepsy Assistive TEchnology
    INNATE: Intelligent Non-invasive Nocturnal epilepsy Assistive TEchnology Malekmohamadi, Hossein; Shell, Jethro; Coupland, Simon Epilepsy is a neurological disease that affects the brain and is characterised by repeated seizures. Generalised, focal and unknown are three major types of seizures. Each type has several subgroups. For this reason, seizure detection and classification are expensive and erroneous. Other factors can also affect the detection. For example, patients can have a combination of different seizures or start with one type and finish with another. Nocturnal epilepsy can be prominent in many sufferers of this disease. This displays seizures that occur during the sleep cycle. The nature of such seizures makes the gathering of data and the subsequent detection and classification complex and costly. The current standard for seizure detection is the invasive use of electroencephalogram (EEG) monitoring. Both medical and research communities have expressed a large interest in the detection and classification of seizures automatically and non-invasively. This project proposes the use of 3D computer vision and pattern recognition techniques to detect seizures non-invasively. Malekmohamadi, H., Shell, J. and Coupland, S., (2016) INNATE: Intelligent Non-invasive Nocturnal epilepsy Assistive TEchnology. In Proceedings of the International Conference on Image Processing, Computer Vision, and Pattern Recognition (IPCV) (p. 351). The Steering Committee of The World Congress in Computer Science, Computer Engineering and Applied Computing (WorldComp).
  • Application of Artificial Neural Network and Support Vector Regression in Cognitive Radio Networks for RF Power Prediction Using Compact Differential Evolution Algorithm
    Application of Artificial Neural Network and Support Vector Regression in Cognitive Radio Networks for RF Power Prediction Using Compact Differential Evolution Algorithm Iliya, Sunday; Gongora, Mario Augusto; Goodyer, E. N.; Gow, J. A.; Shell, Jethro Cognitive radio (CR) technology has emerged as a promising solution to many wireless communication problems including spectrum scarcity and underutilization. To enhance the selection of channel with less noise among the white spaces (idle channels), the a priory knowledge of Radio Frequency (RF) power is very important. Computational Intelligence (CI) techniques cans be applied to these scenarios to predict the required RF power in the available channels to achieve optimum Quality of Service (QoS). In this paper, we developed a time domain based optimized Artificial Neural Network (ANN) and Support Vector Regression (SVR) models for the prediction of real world RF power within the GSM 900, Very High Frequency (VHF) and Ultra High Frequency (UHF) FM and TV bands. Sensitivity analysis was used to reduce the input vector of the prediction models. The inputs of the ANN and SVR consist of only time domain data and past RF power without using any RF power related parameters, thus forming a nonlinear time series prediction model. The application of the models produced was found to increase the robustness of CR applications, specifically where the CR had no prior knowledge of the RF power related parameters such as signal to noise ratio, bandwidth and bit error rate. Since CR are embedded communication devices with memory constrain limitation, the models used, implemented a novel and innovative initial weight optimization of the ANN’s through the use of compact differential evolutionary (cDE) algorithm variants which are memory efficient. This was found to enhance the accuracy and generalization of the ANN model Iliya, S. et al. (2015) Application of Artificial Neural Network and Support Vector Regression in Cognitive Radio Networks for RF Power Prediction Using Compact Differential Evolution Algorithm. 2015 Federated Conference on Computer Science and Information Systems (FedCSIS), pp. 55-66
  • Optimized Neural Network Using Differential Evolutionary and Swarm Intelligence Optimization Algorithms for RF Power Prediction in Cognitive Radio Network: A Comparative study
    Optimized Neural Network Using Differential Evolutionary and Swarm Intelligence Optimization Algorithms for RF Power Prediction in Cognitive Radio Network: A Comparative study Iliya, Sunday; Goodyer, E. N.; Shell, Jethro; Gow, J. A.; Gongora, Mario Augusto Cognitive radio (CR) technology has emerged as a promising solution to many wireless communication problems including spectrum scarcity and underutilization. The a priory knowledge of Radio Frequency (RF) power (primary signals and/ or interfering signals plus noise) in the channels to be exploited by CR is of paramount importance. This will enable the selection of channel with less noise among idle (free) channels. Computational Intelligence (CI) techniques can be applied to these scenarios to predict the required RF power in the available channels to achieve optimum Quality of Service (QoS). In this paper, we developed a time domain based optimized Artificial Neural Network (ANN) model for the prediction of real world RF power within the GSM 900, Very High Frequency (VHF) and Ultra High Frequency (UHF) TV bands. The application of the models produced was found to increase the robustness of CR applications, specifically where the CR had no prior knowledge of the RF power related parameters such as signal to noise ratio, bandwidth and bit error rate. The models used, implemented a novel and innovative initial weight optimization of the ANN’s through the use of differential evolutionary and swarm intelligence algorithms. This was found to enhance the accuracy and generalization of the ANN model. For this problem, DE/best/1/bin was found to yield a better performance as compared with the other algorithms implemented. Iliya, S. et al. (2014) Optimized Neural Network Using Differential Evolutionary and Swarm Intelligence Optimization Algorithms for RF Power Prediction in Cognitive Radio Network: A Comparative study. 2014 IEEE 6th International Conference On Adaptive Science & Technology (ICAST)
  • Fuzzy Transfer Learning: Methodology and application
    Fuzzy Transfer Learning: Methodology and application Shell, Jethro; Coupland, Simon Producing a methodology that is able to predict output using a model is a well studied area in Computational Intelligence (CI). However, a number of real-world applications require a model but have little or no data available of the specific environment. Predominantly, standard machine learning approaches focus on a need for training data for such models to come from the same domain as the target task. Such restrictions can severely reduce the data acquisition making it extremely costly, or in certain situations, impossible. This impedes the ability of these approaches to model such environments. It is on this particular problem that this paper is focussed. In this paper two concepts, Transfer Learning (TL) and Fuzzy Logic (FL) are combined in a framework, Fuzzy Transfer Learning (FuzzyTL), to address the problem of learning tasks that have no prior direct contextual knowledge. Through the use of a FL based learning method, uncertainty that is evident in dynamic environments is represented. By applying a TL approach through the combining of labelled data from a contextually related source task, and little or no unlabelled data from a target task, the framework is shown to be able to accomplish predictive tasks using models learned from contextually different data. The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link. Shell, J. and Coupland, S. (2015)Fuzzy Transfer Learning: Methodology and application. Information Sciences, 293, 1 pp. 59-79
  • Optimized Artificial Neural Network Using Differential Evolution for Prediction of RF Power in VHF/UHF TV and GSM 900 Bands for Cognitive Radio Networks
    Optimized Artificial Neural Network Using Differential Evolution for Prediction of RF Power in VHF/UHF TV and GSM 900 Bands for Cognitive Radio Networks Iliya, Sunday; Goodyer, E. N.; Gongora, Mario Augusto; Gow, J. A.; Shell, Jethro Cognitive radio (CR) technology has emerged as a promising solution to many wireless communication problems including spectrum scarcity and underutilization. The knowledge of Radio Frequency (RF) power (primary signals and/ or interfering signals plus noise) in the channels to be exploited by CR is of paramount importance, not just the existence or absence of primary users. If a channel is known to be noisy, even in the absence of primary users, using such channels will demand large quantities of radio resources (transmission power, bandwidth, etc) in order to deliver an acceptable quality of service to users. Computational Intelligence (CI) techniques can be applied to these scenarios to predict the required RF power in the available channels to achieve optimum Quality of Service (QoS). While most of the prediction schemes are based on the determination of spectrum holes, those designed for power prediction use known radio parameters such as signal to noise ratio (SNR), bandwidth, and bit error rate. Some of these parameters may not be available or known to cognitive users. In this paper, we developed a time domain based optimized Artificial Neural Network (ANN) model for the prediction of real world RF power within the GSM 900, Very High Frequency (VHF) and Ultra High Frequency (UHF) TV bands. The application of the models produced was found to increase the robustness of CR applications, specifically where the CR had no prior knowledge of the RF power related parameters. The models used implemented a novel and innovative initial weight optimization of the ANN’s through the use of differential evolutionary algorithms. This was found to enhance the accuracy and generalization of the approach Iliya, S. et al. (2014) Optimized Artificial Neural Network Using Differential Evolution for Prediction of RF Power in VHF/UHF TV and GSM 900 Bands for Cognitive Radio Networks. 14th UK Workshop on Computational Intelligence (UKCI), 2014

Click here to view a full listing of Jethro Shell's publications and outputs.

Research interests/expertise

  • Computational intelligence
  • Computer game AI
  • Fuzzy logic
  • Transfer learning
  • Dynamic content generation
  • Medical applications of CI
  • Human computer interface
  • Sensors
  • Virtual reality

Areas of teaching

  • Game design
  • Mobile games
  • Fuzzy logic
  • Games projects
  • UML
  • Game AI
  • Physics

Qualifications

  • MSc
  • PhD

Courses taught

  • IMAT1606: Game Architecture, Design and Development
  • IMAT2608: Mobile Games
  • IMAT2800: Mechanics and Artificial Intelligence For Simulation
  • IMAT3406: Fuzzy Logic and Knowledge Based Systems
  • IMAT3451: Computing Project

Externally funded research grants information

3D-TuneIn: H2020 project to produce digital games applied to hearing aids to address social inclusion, 01 June 2015 to 31 May 2018, Principal Investigator (Imperial College, University of Nottingham, Vianet, Reactify, University of Malaga)

Internally funded research project information

INNATE: HEIF Project to detect and predict nocturnal seizures using non-invasive techniques, 6 Jan - 01 June 2016, Principal Investigator.

Professional esteem indicators

  • IEEE Transactions on Neural Networks and Learning Systems, Jan 2014, current, reviewer
  • Sensors, March 2014, current, reviewer
  • IEEE Transactions on Computational Intelligence and AI in Games, Oct 2016, current, reviewer