Category / Computer Science

🌟Exciting News in Complex Networks Research🌟

conferences, international, Women's Academic Network

I am thrilled to share that I have been honoured to receive the Scholarship for Events on Complex Systems (SECS) from the Young Researchers of the Complex Systems Society (yrCSS). This prestigious award will allow me to attend the upcoming Complex Networks 2024 conference in Istanbul, Turkey from December 10-12, 2024.

          

My PhD research focuses on “Complex Urban Road Networks: Static Structures and Dynamic Processes”, exploring the intricate dynamics of urban transportation systems. This field has always sparked my curiosity, and I am eager to delve deeper into this complex interplay of structures and dynamics.

In addition to this incredible opportunity, I am also a finalist in the multi-modal category of the TRA Vision Young Researchers 2024 Competition with my research project “Transport Capacity Planning for Mega-events”. It is truly humbling to be recognised for my work in this competitive arena.

I am grateful for the guidance and support of my PhD supervisor, Dr. Wei Koong Chai, whose expertise and mentorship have been invaluable throughout my research journey. I am excited about the upcoming conference, where I hope to further contribute to the field of complex networks research. Thank you for joining me on this incredible academic adventure!

Best wishes,

Assemgul Kozhabek

🌐🔬 #ComplexSystems #ComplexNetworks

See yrCSS: https://yrcss.cssociety.org/

Complex Networks 2024 conference: https://complexnetworks.org/

Interdisciplinary Computational and Clinical Approaches at the Edge of Brain Research

BRIAN

We cordially invite you to the 3rd Symposium of the BU Interdisciplinary Neuroscience Research Centre on Wednesday, the 12th of June 2024, from 9:30-13:00 at the Inspire Lecture Theatre, Fusion Building (1st floor).

The symposium is entitled: “Interdisciplinary Computational and Clinical Approaches at the Edge of Brain Research”.

This third symposium revolves around contrasting computational and translational methodologies from a cross-disciplinary standpoint, leveraging synergies between BU and our collaborators in other universities and at the NHS. It is an opportunity for informal discussions on grant proposals and to explore shared interests with our external guests. The general schedule is as follows:

9:15. Welcome and coffee.

9:30. Keynote talk: Prof. Miguel Maravall, Sussex University.

10.20-10:40. Coffee and grants discussion.

10:40-11:40. Session I. Integrating Cognitive and Computational Neuroscience.

11.40 -12.00. Coffee and grants discussion.

12.00-13:00. Session II. Interdisciplinary Clinical Approaches & Concluding Remarks.

If you have any queries, please do not hesitate to contact Ellen Seiss, eseiss@bournemouth.ac.uk or Emili Balaguer-Ballester, eb-ballester@bournemouth.ac.uk.

Thank you very much, and we are looking forward to seeing you there.

Kind regards,

Ellen and Emili, on behalf of all of us.

 

 

 

 

Cross-university Multidisciplinary Research

conferences

In December, I had the pleasure of participating in an expert panel addressing AI testing at the International Conference on Artificial Intelligence at Peterhouse College, at the University of Cambridge. You might be wondering what brought a cybersecurity researcher to an AI-centric event. I had the same scepticism when my multi-university research group decided we conduct AI-related research; what would my contribution be?

Our work has focused on defining meta-data for AI provenance, contributing to advancements in various facets of AI, including testing and auditability. Specifically, my focus lies on evaluating the dimensions of risk and trust within this context. Given the widespread impact of AI across diverse domains, there is a compelling opportunity for multidisciplinary research, consecutively, our group, has diverse expertise ranging from machine learning to psychology.

An initial publication on our work can be found here.

Author Dr Andrew M’manga

OpenBright grant awardees from Bournemouth University

Awarded & submitted bids

OpenBright grants have been available since 2020 to support women in the development of research projects at the university level, focusing on subjects related to computing and technology. OpenBright offers small grants for students studying for degrees or postgraduate qualifications in areas such as software engineering, data science, digital media, artificial intelligence, and robotics.

We are thrilled to introduce the awardees:

Assemgul Kozhabek (Final year Ph.D. candidate): Assemgul is the second-time OpenBright grant awardee. Her plan is to upgrade her computer system to conduct a thorough analysis of road networks. This upgrade will greatly support her project, titled “Examining the Topology of Urban Road Networks in densely populated countries: China and India”. Assemgul and her supervisor Dr. Wei Koong Chai abstracted road networks as complex systems and employ tools from network science to study their properties.  This study introduces multi-level urban road network robustness metrics, which incorporates macro, meso and micro perspectives. Assemgul thanks her supervisor  Dr. Wei Koong Chai and Dr. Melanie Coles for their guidance and support!

Fatima Ahmad Muazu (1st year Ph.D. student): Fatima got funding for her project “The Use of Mobile Learning and Assistive Technologies for Enhancing Digital Inclusion in Special Education for Learners with Learning Disabilities in underserved regions of Northern and Southern Nigeria”. The funding will be used to conduct a preliminary needs analysis involving stakeholders and students in special education settings of 4 Nigerian secondary schools.

Maggie Foulds (Final year BSc Software Engineering student): Her project is the development of a mobile application to aid all-star cheerleading coaches in the creation of competition routines, and to help ensure athlete safety throughout the season. Maggie has been awarded funding from the OpenBright foundation to travel to a software development conference in Miami, to boost her coding skills to take her project to the next level. OpenBright is also supporting me to attend the Cheerleading World Championships in Orlando, where I will be able to test a prototype of my application with stakeholders.

Ayo Agbeja (MSc Data Science and Artificial Intelligence): Ayo’s research title is “Plastic Wastes and Sustainability Targets in Germany: A Policy Simulation Experiment using Machine Learning”. Her project has a primary focus on Germany and aims to investigate the relationship between policies related to plastic waste management and sustainability objectives, particularly in the context of reducing carbon emissions. This simulated model will take into account the key factors: economic growth, oil and coal production, the generation of renewable energy, and energy consumption, while making projections based on an optimal weighting of these factors.

Congratulations!

Discovering Causal Relations and Equations from Data

BRIAN, Fusion themes, open access, REF Subjects, staff profile pages

Discovering equations, laws, or invariant principles underpins scientific and technical advancement. Robust model discovery has typically emerged from observing the world and, when possible, performing interventions to falsify models.

Recently, data-driven approaches like classic and deep machine learning are evolving traditional equation discovery methods. These new tools can provide unprecedented advances in computer science, neuroscience, physics, philosophy, and many applied areas.

We have just published a new study discussing concepts and methods on causal and equation discovery, outlining current challenges and promising future lines of research. The work also showcases comprehensive case studies in diverse scientific areas ranging from earth and environmental science to neuroscience.

Our tenet is that discovering fundamental laws and causal relations by observing natural phenomena is revolutionised with the coalescence of observational data and simulations, modern machine learning algorithms and domain knowledge. Exciting times are ahead with many challenges and opportunities to improve our understanding of complex systems.

This study is a collaborative work between eight universities in Europe and the United States (Valencia, Berlin, Tübingen, Jena, Stockholm, New York, and Bournemouth Universities).

Camps-Valls, G., Gerhardus, A., Ninad, U., Varando, G., Martius, G., Balaguer-Ballester, E., Vinuesa, R., Diaz, E., Zanna, L. and Runge, J., 2023. Discovering causal relations and equations from data. Physics Reports, 1044, 1-68 (Impact Factor=30).

 

CuttingGardens2023 conference in Bournemouth

conferences

The MINE Research Cluster and EEG Lab are hosting a four-day CuttingGardens 2023 conference in Bournemouth during 16-19 October 2023. CuttingGardens is a distributed conference on cutting-edge methods for EEG/MEG data analysis, with 20+ “gardens” happening simultaneously at several locations across the world. The common global programme, broadcasted to all locations, includes cognitive neuroscience advances, real-time EEG analysis, reproducible research, and deep neural network. Our Bournemouth Garden’s local programme has hands-on #EEGLab and #MNE-Python tutorials, EEG-VR and EEG-eye tracking workshops, exciting talks and tour of state-of-the-art labs!

Key dates:
Abstract submission deadline: 15 September 2023
Registration deadline: 27 September 2023
Conference: 16-19 October 2023

More information can be found at https://cuttinggardens2023.org/gardens/bournemouth/. Please check the webpage if you are interested. This is an ideal event for anyone who is keen to elevate their EEG/MEG research skills. We welcome research students, postdocs, academics and professionals alike.

Bournemouth Garden Organising Committee:
Xun He, Ellen Seiss, Marina Kilintari, Federica Degno, Ruijie Wang, Andrew Hanson, and Biao Zeng (University of South Wales, BU’s Visiting Fellow)

 

INRC seminar by Dr Jie Sui, Friday the 8th of September at 14.00 h, Share Lecture Theatre (Fusion).

REF Subjects, Women's Academic Network

We want to draw your attention to a seminar organized by the Interdisciplinary Neuroscience Research Centre on this Friday, the 8th of September, from 14:00 h to 15:00 h at the Share Lecture Theatre (Fusion Building). There will be a networking event after the talk with coffee and biscuits.

Our guest speaker is Dr. Jie Sui (University of Aberdeen), invited by Dr. Ellen Seiss. Prof Dr Sui is renowned for her studies investigating the unique self, self-representation, and social interactions in VR. Her research combines multiple neural recording modalities, such as EEG and fMRI, with computational modelling.

The title of this exciting talk is: “Understanding the Self: Prospects for Translation”. Please find the abstract below.

We warmly invite you to attend this seminar.

Kind regards,

Ellen and Emili, on behalf of all of us.

Abstract:

“An understanding of the self helps explain not only human thoughts, feelings, and attitudes but also many aspects of everyday behaviours. This talk focuses on a particular perspective on self-processes. This perspective highlights the dynamics of the self that best connects with the development of the self over time and its realist orientation. We are using psychological experiments and data mining to comprehend the stability and flexibility of the self in different populations.

In this talk, I integrate experimental psychology, associative learning theory, computational neuroscience, and machine learning approaches to demonstrate why and how self-association affects cognition and how it is modulated by various social experiences and situational factors.”

INRC seminar by Dr Jie Sui, Friday the 8th of September at 14.00 h, Share Lecture Theatre (Fusion).

REF Subjects, Women's Academic Network

We want to draw your attention to a seminar organized by the Interdisciplinary Neuroscience Research Centre on Friday, the 8th of September, from 14:00 h to 15:00 h at the Share Lecture Theatre (Fusion Building). There will be a networking event after the talk with coffee and biscuits.

Our guest speaker is Dr. Jie Sui (University of Aberdeen), invited by Dr. Ellen Seiss. Prof Dr Sui is renowned for her studies investigating the unique self, self-representation, and social interactions in VR. Her research combines multiple neural recording modalities, such as EEG and fMRI, with computational modelling.

The title of this exciting talk is: “Understanding the Self: Prospects for Translation”. Please find the abstract below.

We warmly invite you to attend this seminar.

Kind regards,

Ellen and Emili, on behalf of all of us.

Abstract:

“An understanding of the self helps explain not only human thoughts, feelings, and attitudes but also many aspects of everyday behaviours. This talk focuses on a particular perspective on self-processes. This perspective highlights the dynamics of the self that best connects with the development of the self over time and its realist orientation. We are using psychological experiments and data mining to comprehend the stability and flexibility of the self in different populations.

In this talk, I integrate experimental psychology, associative learning theory, computational neuroscience, and machine learning approaches to demonstrate why and how self-association affects cognition and how it is modulated by various social experiences and situational factors.”

BU PhD candidate is the Winner of the British Computer Society (BCS) GreenIT 2023 Competition

Awarded & submitted bids, international, Women's Academic Network

BU Ph.D. candidate Assemgul Kozhabek from the SciTech Computing and Informatics department has won the HE Class  GreenIT 2023 competition run by the British Computer Society (BCS) – the chartered institute for IT.

The competition, open to students across the world, asked for suggestions for ‘How Computing can address the Energy Crisis.’ Assemgul’s winning entry was a poster that featured comics and anecdotes on urban traffic congestion as one of the main contributors to the energy crisis. It should be highlighted that she also focuses on congestion mitigation in her Ph.D. thesis.

Assemgul expressed her gratitude to Dr. Martyn Polkinghorne and Ph.D. supervisor Dr. Wei Koong Chai for their guidance and support.

Broadening horizons: Network Science at Utrecht Summer School

Women's Academic Network

We are thrilled to announce that Assemgul Kozhabek, one of our  PhD candidates, recently had the opportunity to participate in the Utrecht Summer School on “Data Science: Network Science” from July 10-14, 2023. Assemgul’s research, under the guidance of Dr. Wei Koong Chai, is centered around understanding and optimizing urban road networks. By attending this course, she was able to gain a deeper understanding of network science and its relevance to her research goals. The course covered various topics, including network modeling, analysis techniques, and practical application of network science in real-world scenarios.
The Utrecht Summer School provided Assemgul with a unique learning experience. Through interactive lectures, hands-on workshops, and networking opportunities with experts in the field, she was able to broaden her knowledge and enhance her skills in analyzing urban road networks. She expresses her gratitude to Dr. Wei Koong Chai for his support and guidance throughout this journey. Assemgul also immensely grateful for the OpenBright Award that made this opportunity possible.
Assemgul’s participation in the Utrecht Summer School on “Data Science: Network Science” has undoubtedly equipped her with valuable insights and tools that will contribute to her ongoing research. Stay tuned for exciting updates on her research journey!

BU and University of Cambridge Collaboration on Traffic Prediction

Fusion, Knowledge Exchange, REF Subjects

Bournemouth University (BU) has collaborated with the University of Cambridge on network wide road traffic prediction. The work, led by Dr. Wei Koong Chai in BU, address the problem of traffic prediction on large-scale road networks and propose a novel deep learning model, Virtual Dynamic Graph Convolution Neural Network and Transformer with Gate and Attention mechanisms (VDGCNeT), to comprehensively extract complex, dynamic and hidden spatial dependencies of road networks for achieving high prediction accuracy. The work advocates the use of a virtual dynamic road graph that captures the dynamic and hidden spatial dependencies of road segments in real road networks instead of purely relying on the physical road connectivity.

The team designed a novel framework based on Graph Convolution Neural Network (GCN) and Transformer to analyse dynamic and hidden spatial–temporal features. The gate mechanism is utilised for concatenating learned spatial and temporal features from Spatial and Temporal Transformers, respectively, while the Attention-based Similarity is used to update dynamic road graph.

Two real-world traffic datasets from large-scale road networks with different properties are used for training and testing the model. VDGCNeT is pitted against nine other well-known models in the literature. The results demonstrate that the proposed VDGCNeT is capable of achieving highly accurate predictions – on average 96.77% and 91.68% accuracy on PEMS-BAY and METR-LA datasets respectively. Overall, our VDGCNeT performs the best when compared against other existing models.

Reference:

G. Zheng, W. K. Chai, J. Zhang and V. Katos, “VDGCNeT: A novel network-wide Virtual Dynamic Graph Convolution Neural network and Transformer-based traffic prediction model,” Knowledge-based Systems, 110676, June 2023. DOI: https://doi.org/10.1016/j.knosys.2023.110676.

Neural Networks 2022 Best Paper Award

Publishing

2022 Best Paper Award

Dr Hari Mohan Pandey is a recipient of the 2022 Best Paper Award (visit: https://www.journals.elsevier.com/neural-networks/awards/announcement-of-the-neural-networks-2022-best-paper-award):

“Cross-modality paired-images generation and augmentation for RGB-infrared person re-identification”

This paper is published in Neural Networks, volume 128, pp. 294-304, August 2020. The paper can be accessed at: https://doi.org/10.1016/j.neunet.2020.05.008

The Neural Networks Best Paper Award recognizes a single outstanding paper published in Neural Networks annually.

BU PhD student receives OpenBright grant

Women's Academic Network

I am thrilled to announce that I have been awarded a grant from OpenBright to take part in a short summer course on “Data Science: Network Science” at Utrecht University, located in the Netherlands. OpenBright award grants to support women in computing to develop their research projects.
As a PhD student, I am currently working on a research project titled “Smart Transportation Networks for Smart Cities,” under the supervision of Dr. Wei Koong Chai. The research is match-funded by Bournemouth Christchurch Poole (BCP) Council.   Through the course, I am excited to further enhance my knowledge and skills in network science, which is crucial to my research work.
I am thankful for the support and recognition from OpenBright, which provides me with the opportunity to learn from some of the most renowned researchers and scholars in this field. This grant not only benefits me but also fosters the advancement of women in computing, promoting gender equity and diversity in science.
I would like to take this opportunity to thank my supervisor Dr. Wei Koong Chai, for his invaluable guidance and support throughout my PhD journey.
Author: Assemgul Kozhabek, 3rd year PhD student, SciTech, Computing and Informatics department