Hello, I’m

Jordan Bird

I am a PhD Researcher.

ResearchGate Profile LinkedIn Profile

About Me

Hello, I’m Jordan Bird. Welcome to my website! I’ve always had an interest in the world of technology which has led me on the path of being a researcher. I have a vast curiosity of what the future holds and I also have a longstanding enjoyment for programming and academia. My main passions in life, first and foremost, have been related to the Sciences; I was always asking questions without answers as a kid and now I want to try to answer them too.

I am a founding member of ARVIS Lab (Aston Robotics, Vision and Intelligent Systems)

Research interests: Artificial Intelligence (AI), Computational Intelligence, Machine Learning, Human-machine Interaction, Robotics, Natural Language Processing.

Jordan Bird at Brum AI
Giving a talk on Artificial Intelligence at Brum AI during Birmingham Tech Week
Jordan J. Bird presenting work at the SAI Computing Conference 2019
Presenting a paper at the SAI Computing Conference 2019

Curriculum Vitae

Download CV LinkedIn Profile

Professional Experience

Jul 2018 – Present

Teaching Assistant

Aston University

Leading distance learning teaching sessions for the Capgemini Degree Apprenticeship Programme while studying for a PhD in Computer Science, I am responsible for the following modules:

  • Human Computer Interaction
  • Geographic Information Systems

On campus, I am also a Lab Session Lead for the following modules:

  • Computer Graphics (Second Year)
  • Computational Intelligence (Final Year) – Neural Networks

Jun 2018

Robot Engineer

Aston University

Contract work in preparation for the CompTIA 2018. Developed an app for a Softbank Robotics Pepper robot that would read business cards, detect text, and extract human names in order to greet visitors.

Sep 2017 – May 2018

Teaching Assistant

Aston University

Provided effective and professional teaching support for the following modules:

  • Java Programming Foundations
  • Computational Reasoning and Communication

Nov 2016 – Nov 2017

Web Developer

The Marketing People

As part of TMP, I was a member of a team whose goal it is to work with clients to create an online presence to gain new business from the internet. This is usually one segment of an entire marketing strategy and campaign built around both brand development and awareness via bespoke e-media and print products.

May 2016 – Sep 2016

EVM Officer

Education & IT

At EdIT, I was an IT Technician who project managed, configured, and finally installed Electronic Visitor Management Systems for schools and businesses across the UK – these were digital interfaces that replaced the traditional pen and paper signing in system. I also worked in web and app development to improve the system, engineering the possibilities of iOS and Android integration.

Jul 2014 – May 2016

Computer Technician

Itex Asset Management
  • Diagnostics, repair and refurbishment of computer hardware
  • Managing secure data destruction with NATO-Certified technology
  • Working as a team to achieve common goals and deadlines

Sep 2014 – Oct 2015

Content Creator

CV Plaza
  • Writing job descriptions for large, corporate customers
  • Self-edited and published to thousands of Students nationwide

Education

2018 – 2021

Doctor of Philosophy in Artificial Intelligence

Aston University

Awarded a scholarship to continue my studies at Aston University as a researcher in the field of Artificial Intelligence. Supervised by Dr. Diego R. Faria.

2014 – 2018

Bachelor’s Degree in Computer Science

Aston University

Graduated with a First Class Honours degree.

BSc. Dissertation peer reviewed and published at a popular Artificial Intelligence conference – https://link.springer.com/book/10.1007/978-3-319-97982-3

2011 – 2014

A-Levels

Erasmus Darwin Academy Sixth Form
  • IT – Distinction*
  • Game Development – Distinction*
  • Media Studies – A*

2007 – 2011

GCSE

Erasmus Darwin Academy
  • ICT – Distinction* (3x A*)
  • Science – A*
  • Additional Science – A*
  • Mathematics – A
  • English Language – A
  • History – A
  • English Literature – B

Testimonials

testo-01

Sarah Mathews

The MuseFuse

Jordan has a very clear thought process in regards to the projects. Good analytical and Marketing skills knowledge. He’s always prompt to revert and communication is smooth and makes working with him easy!

Published Works

ResearchGate Profile

7

Journal Articles

12

Conference Papers

1

Poster Paper

Journal Articles

British Sign Language Recognition via Late Fusion of Computer Vision and Leap Motion with Transfer Learning to American Sign Language

Bird, J. J., Ekárt, A., & Faria, D. R. (2020). British Sign Language Recognition via Late Fusion of Computer Vision and Leap Motion with Transfer Learning to American Sign Language. Sensors20(18), 5151.

View on ResearchGate View on MDPI

Towards AI-based Interactive Game Intervention to Monitor Concentration Levels in Children with Attention Deficit

Faria, D. R., Bird, J. J., Daquana, C., Kobylarz, J., & Ayrosa, P. P. (2020). Towards AI-based Interactive Game Intervention to Monitor Concentration Levels in Children with Attention Deficit. International Journal of Information and Education Technology, 10(9).

View on ResearchGate View on IJIET

Optimisation of phonetic aware speech recognition through multi-objective evolutionary algorithms

Bird, J. J., Wanner, E., Ekárt, A., and Faria, D.R. Optimisation of phonetic aware speech recognition through multi-objective evolutionary algorithms. Expert Systems with Applications, p. 113402, 2020. https://doi.org/10.1016/j.eswa.2020.113402

View on ResearchGate View on Elsevier

Cross-domain MLP and CNN Transfer Learning for Biological Signal Processing: EEG and EMG

Bird, J.J., Kobylarz, J., Faria, D.R., Ekárt, A., Ribeiro, E.P. Cross-domain MLP and CNN Transfer Learning for Biological Signal Processing: EEG and EMG. IEEE ACCESS. 2020. https://doi.org/10.1109/ACCESS.2020.2979074

View on ResearchGate View on IEEE

Thumbs up, thumbs down: non-verbal human-robot interaction through real-time EMG classification via inductive and supervised transductive transfer learning

Kobylarz, J., Bird, J.J., Faria, D.R., Ribeiro, E.P, Ekárt, A.. Thumbs up, thumbs down: non-verbal human-robot interaction through real-time EMG classification via inductive and supervised transductive transfer learning. Journal of Ambient Intelligence and Humanized Computing. 2020. https://doi.org/10.1007/s12652-020-01852-z

View on ResearchGate View on Springer

On the Effects of Pseudo and Quantum Random Number Generators in Soft Computing

Bird, J. J., Ekárt, A., & Faria, D. R. (2019). On the Effects of Pseudo and Quantum Random Number Generators in Soft Computing. Soft Computing2019. Springer, 16 pages, 2019.

View on ResearchGate View on Springer

A Deep Evolutionary Approach to Bioinspired Classifier Optimisation for Brain-Machine Interaction

Bird, J. J., Faria, D. R., Manso, L. J., Ekárt, A., & Buckingham, C. D. (2019). A Deep Evolutionary Approach to Bioinspired Classifier Optimisation for Brain-Machine Interaction. Complexity2019. vol. 2019, Article ID 4316548, 14 pages, 2019. https://doi.org/10.1155/2019/4316548.

View on ResearchGate View on Hindawi Download PDF

Conferences and Proceedings

Probabilistic Object Classification using CNN ML-MAP layers

Melotti, G., Premebida, C., Bird, J.J., Faria, D.R. and Gonçalves, N., (2020). Probabilistic Object Classification using CNN ML-MAP layers. The 16th European Conference on Computer Vision (ECCV’20). Springer.

View on ResearchGate

Overcoming Data Scarcity in Speaker Identification: Dataset Augmentation with Synthetic MFCCs via Character-level RNN

Bird, J. J., Faria, D. R., Premebida, C., Ekart, A., & Ayrosa, P. P. S. (2020). Overcoming Data Scarcity in Speaker Identification: Dataset Augmentation with Synthetic MFCCs via Character-level RNN. The 20th IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC’2020). IEEE.

View on ResearchGate Download PDF

From Simulation to Reality: CNN Transfer Learning for Scene Classification

Bird, J. J., Faria, D. R., Ayrosa, P. P. S., & Ekart, A. (2020). From Simulation to Reality: CNN Transfer Learning for Scene Classification. 10th International Conference on Intelligent Systems. IEEE.
View on ResearchGate Download PDF

Phoneme Aware Speech Synthesis via Fine Tune Transfer Learning with a Tacotron Spectrogram Prediction Network

Bird, J. J., Ekart, A., & Faria, D. R. (2019). Phoneme Aware Speech Synthesis via Fine Tune Transfer Learning with a Tacotron Spectrogram Prediction Network. 19th Annual UK Workshop on Computational Intelligence (UKCI).
View on ResearchGate

Classification of EEG Signals Based on Image Representation of Statistical Features

Ashford, J., Bird, J. J., Campelo, F., & Faria, D. R. (2019). Classification of EEG Signals Based on Image Representation of Statistical Features. 19th Annual UK Workshop on Computational Intelligence (UKCI).
View on ResearchGate

Accent Classification in Human Speech Biometrics for Native and Non-native English Speakers

Bird, J. J., Wanner, E. F., Ekart, A., & Faria, D. R. (2019). Accent Classification in Human Speech Biometrics for Native and Non-native English Speakers. PErvasive Technologies Related to Assistive Environments (PETRA’19).
View on ResearchGate

High Resolution Sentiment Analysis by Ensemble Classification

Bird, J. J., Ekart, A., Buckingham, C, D & Faria, D. R. (2019). High Resolution Sentiment Analysis by Ensemble Classification. SAI Computing Conference 2019.
View on ResearchGate Download PDF

Evolutionary Optimisation of Fully Connected Artificial Neural Network Topology

Bird, J. J., Ekart, A., Buckingham, C, D & Faria, D. R. (2019). Evolutionary Optimisation of Fully Connected Artificial Neural Network Topology. SAI Computing Conference 2019.
View on ResearchGate Download PDF

Mental Emotional Sentiment Classification with an EEG-based Brain-machine Interface

Bird, J. J., Ekart, A., Buckingham, C, D & Faria, D. R. (2019). Mental Emotional Sentiment Classification with an EEG-based Brain-machine Interface. The International Conference on Digital Image & Signal Processing (DISP’19).
View on ResearchGate Download PDF

A Study on Mental State Classification using EEG-based Brain-Machine Interface

Bird, J. J., Manso, L. J., Ribiero, E., P., Ekart, A., & Faria, D. R. (2018). A Study on Mental State Classification using EEG-based Brain-Machine Interface. 9th International Conference on Intelligent Systems. IEEE.
View on ResearchGate Download PDF

Learning from Interaction: An Intelligent Networked based Human-bot and Bot-bot Chatbot System

Bird, J. J., Ekart, A., & Faria, D. R. (2018). Learning from Interaction: An Intelligent Networked based Human-bot and Bot-bot Chatbot System. Advances in Intelligent Systems and Computing. Springer.
View on ResearchGate Download PDF

A Study on CNN Transfer Learning for Image Classification

Hussain, M., Bird, J. J., & Faria, D. R. (2018). A Study on CNN Transfer Learning for Image Classification. Advances in Intelligent Systems and Computing. Springer.
View on ResearchGate Download PDF

Preprints

Preprints and early-stage research may not have been peer reviewed yet.

British Sign Language Recognition via Late Fusion of Computer Vision and Leap Motion with Transfer Learning to American Sign Language

Bird, J. J., Ekart, A., & Faria, D. R. (2020). British Sign Language Recognition via Late Fusion of Computer Vision and Leap Motion with Transfer Learning to American Sign Language. Preprints 2020, 2020080209 (doi: 10.20944/preprints202008.0209.v1)

Look and Listen: A Multi-modality Late Fusion Approach to Scene Classification for Autonomous Machines

Bird, J. J., Faria, D. R., Premebida, C., Ekárt, A., & Vogiatzis, G. (2020). Look and Listen: A Multi-modality Late Fusion Approach to Scene Classification for Autonomous Machines. arXiv preprint arXiv:2007.10175.

LSTM and GPT-2 Synthetic Speech Transfer Learning for Speaker Recognition to Overcome Data Scarcity

Bird, J.J., Faria, D.R., Ekárt, A., Premebida, C. and Ayrosa, P.P., 2020. LSTM and GPT-2 Synthetic Speech Transfer Learning for Speaker Recognition to Overcome Data Scarcity. arXiv preprint arXiv:2007.00659.

Probabilistic Object Classification using CNN ML-MAP layers

Melotti, G., Premebida, C., Bird, J.J., Faria, D.R. and Gonçalves, N., 2020. Probabilistic Object Classification using CNN ML-MAP layers. arXiv preprint arXiv:2005.14565.

Poster Papers

Phoneme Aware Speech Recognition through Evolutionary Optimisation

Bird, J. J., Wanner, E. F., Ekart, A., & Faria, D. R. (2019). Phoneme Aware Speech Recognition through Evolutionary Optimisation. GECCO: The Genetic and Evolutionary Computation Conference 2019.
View on ResearchGate

Achievements

2020

Invited Reviewer for MDPI Brain Sciences

Invited Reviewer for the IEEE Robotics & Automation Magazine

Invited Reviewer for IEEE RO-MAN 2020 – International Symposium on Robot and Human Interactive Communication

Invited Reviewer for Hindawi’s Journal of Sensors

Guest Reviewer for Springer’s Journal of Ambient Intelligence and Humanized Computing

Invited Reviewer for IEEE EDUCON2020

2019

Founding Member of ARVIS Lab (Aston Robotics, Vision, and Intelligent Systems)

Invited Speaker at BrumAI – Birmingham Artificial Intelligence Meetup

Invited Reviewer for Hindawi’s Journal of Sensors

Invited Reviewer for Elsevier’s Biocybernetics and Biomedical Engineering Journal

Invited Reviewer for The 3rd International Conference on Computer Science and Application Engineering (CSAE) 2019 Conference

Invited Reviewer for the IEEE Access Journal

Guest Reviewer for the PErvasive Technologies Related to Assistive Environments (PETRA) 2019 Conference

2018

Invited Guest Laboratory Session Lead for Final Year BSc. Computer Science Computational Intelligence – Neural Networks and Hyperheuristic Optimisation of Neural Networks.

Robotics Demonstration for Think Beyond Data – SME Live 2018. The NEC, Birmingham, UK. (https://sme-live.co.uk/) (https://thinkbeyonddata.com/)

Robotics Demonstration – Brum Youth Trends 2018. Birmingham Town Hall, UK.

Artificial Intelligence Q&A meeting with Andy Street, Lord Mayor of the West Midlands. Birmingham, UK.

Laboratory session lead for Computer Graphics module. Aston University, Birmingham, UK.

Delegate for Aston University and Robotics Demonstration – West Midlands Forum for Growth 2018. The NEC, Birmingham, UK. (https://www.westmidlandsforumforgrowth.co.uk)

Invited Speaker – HeadStart 2018. Aston University, Birmingham, UK.

Robotics Demonstration – CompTIA 2018. Birmingham, UK.

Awarded Scholarship to study for a PhD. in Computer Science supervised by Dr. Diego R. Faria. Aston University, Birmingham, UK.

BSc. Dissertation peer-reviewed and published in Advances in Computational Intelligence Systems – https://link.springer.com/book/10.1007/978-3-319-97982-3

AI Art

A work in progress

This is art generated by Machine Learning algorithms. I am working on a pipeline that considers Progressively Growing Generative Adversarial Networks and Nearest-Neighbour Style Transfer in order to create high quality original artworks.

In the future, I hope to also train a super-resolution model in order to generate much larger images. Enjoy!

AI Art: A landscape painting generated by artificial intelligence algorithms

AI Music

music generated by AI
Music generated by a Deep Neural Network
An example of some music generated by the Neural Network

After reading Sigurður Skúli’s towards data science article ‘How to Generate Music using a LSTM Neural Network in Keras’ – I was astounded at how well LSTM classification networks were at predicting notes and chords in a sequence, and ultimately then how they could generate really nice music.

Sigurður’s approach had some really nice and useful functions for parsing the data, creating dictionaries to translate between notes and class labels, and then using the trained model to generate pieces of music.

The main limitations of this work is that notes generated are all the same length and offset from one another, so music can sound quite unnatural sometimes. In this extension, we instead use the Keras Functional API (instead of a Sequential model) to branch the neural network to consider multiple time series from the music. They are:

  1. The Notes and Chords in the sequence (just referred to as ‘notes’ from here on)
  2. The offsets of the note from the previous one (offset of the note from the start of the midi minus the current base (previous value))
  3. The durations of the notes in the sequence

The above also serve as three separate outputs to the network.

Thus, three tasks are trained. Classifying the next note, its offset, and its duration.

The network currently looks like this:

Deep Neural Network for Generating Music

As you can see, 100 notes/chords are fed into the network as input alongside their offsets and durations. The goal of the network is to learn to predict the next note/chord in the sequence along with its offset and duration.

The code for this is freely available on my GitHub page: https://github.com/jordan-bird/Keras-LSTM-Music-Generator

Have fun!