UKSim2024

UKSim-AMSS 26^th International Conference on

Mathematical Modelling & Computer Simulation in Artificial Intelligence

Cambridge University (Emmanuel College), 26 - 28 March 2024

View proceedings in IEEE Xplore Digital Library: UKSim2008, UKSim2009, UKSim2010,

UKSim2011, UKSim2012, UKSim2013, UKSim2014 (also in ACM Digital Library: UKSim2014), UKSim2015, UKSim2016, UKSim2017, UKSim2018, UKSim2019-IJSSST, UKSim2020-IJSSST, UKSim2021-IJSSST, , UKSim2022-IJSSST

Special theme this year: Modelling and Simulation in Artificial Intelligence

Download the Call for Papers file

Indexed in doi.org, EBSCO, Research Gate, Scope, Google Scholar and searchable online by all global search engines.

Application in progress to index the papers in Scopus.

Important Dates

Call for Papers

Paper Submission

Registration

Venue/Rooms

Cambridge

College Accommodation

Accommodation

Travel to Cambridge

Flights & Travel

Social Events

Keynote/Tutorial Speakers

Important Dates

Submission: See above

Notification

Paper Acceptance: from 20 Feb

Final Upload into EDAS for checking &

Registration by:

10 March

Credit Card on EDAS

Camera-ready by:

20 March

Conference Chairs

Glenn Jenkins, Cardiff Metropolitan University.

Tim Bashford, University of Wales Trinity Saint David

Taha Osman, Nottingham Trent University, UK.

Local Arrangements/

Venue/Program Chairs:

Tim Bashford, University of Wales Trinity Saint David

Glenn Jenkins, Cardiff Metropolitan University.

General Chair

Deputy/Co-Chair:

David Al-Dabass

Glenn Jenkins

Honorary General Co-Chair:

Frank Wang, University of Kent, UK

Honorary Conference/ Programme Co-Chair: Qiang Shen, Aberystwyth University, UK

Programme Co-Chair:

Publication Research Editors:

Zuwairie Ibrahim

Ibrahim Shaiai

EUROSIM Liaison Chair

Taha Osman

Papers submission, Deadline: 1 March 2024 (EDAS stays open for few more days for late papers)

Send paper as Word .docx or PDF file to general chair: david.al-dabass@ntu.ac.uk or david.aldabass@btinternet.com

Conference venue and accommodation: Emmanuel College, St Andrews Street, Cambridge, CB2 3AP.

Other accommodation in Cambridge

Published Papers and Program, Participants

Papers are invited on any aspect of modelling, simulation, algorithms, applications and technology related to Artificial Intelligence to be presented at UKSim2024, University of Cambridge (Emmanuel College). The accommodation, renowned catering and conference facilities are an ideal blend of modern and historic. The venue offers an especially attractive opportunity for both professional discussion and socialising.

Full Papers (six pages with figures), and short papers (4 pages with figures) are invited on any aspect of modelling, simulation and their applications. Papers on the theme of Artificial Intelligence are especially welcome.

Themes

- Simulated Reality and Artificial Intelligence

- Deep Learning

- Bio-Informatics and Bio-Medical Simulation

- Complexity Theory

- Hybrid Intelligent Systems

- Soft Computing and Hybrid Soft Computing

- Computational Intelligence

- Control of Intelligent Systems

- Robotics, Cybernetics, Engineering, Manufacturing and Control

- Methodologies, Tools and Operations Research

- Discrete Event and Real Time Systems

- Image, Speech and Signal Processing

- Natural Language Processing/language technologies

- Computer Generated Art (images to be exhibited at the conference and included in the proceedings)

- AI in Industry, Business and Management

- Human Factors and Social Issues

- Energy, Power Generation and Distribution

- Transport, Logistics, Harbour, Shipping and Marine Simulation

- Supply Chain Management

- Virtual Reality, Visualization and Computer Games

- Parallel and Distributed Architectures and Systems

- Internet Modelling, Semantic Web and Ontologies

- Mobile/Ad hoc wireless networks, mobicast, sensor placement, target tracking

- Performance Engineering of Computer & Communication Systems

- Circuits, Sensors and Devices

- Speculative issues: is our universe a simulation? Why classical physics break down and quantum mechanics take over at the subatomic level?

- AI related simulation methodologies and practice, languages, tools and techniques.

- Models and modelling tools. Data/object bases. Analytical and statistical tools.

- AI in Simulators and simulation hardware, training simulators.

- Agent-based simulation, decision support systems

- Philosophical issues: virtual and simulated reality, metaphors, knowledge modelling, deep learning, acquisition and synthesis of new knowledge/models, intelligent/adaptive behaviour

- Man/robot/machine interaction, control systems.

- Artificial Intelligence in parallel and distributed simulation, discrete event systems.

- Artificial neural networks

Applications: aerospace; remote sensing; electronic circuits and systems; communication and networks; business; management; finance; economics; leisure, games, war/conflict/rebellion modelling; psychology, cognitive functions, behaviour, emotion, subjectivity; humanities, literature, semantics modelling/dynamics; biology; medicine; public health; energy, power generation and distribution, manufacturing; planning; control; robotics; measurement; monitoring; energy; safety critica1 systems; transportation; structural mechanics and civil engineering, oil and gas; education and training; military.

Exhibitors: manufacturers of software and hardware, publishers, etc., are invited to apply to exhibit their products.

The registration fee for Virtual attendance is only $300 and $595 for Physical attendance at the conference, this will include refreshments and lunches for all 3 days. IEEE members get 5% cash discount at the conference after presenting their paper and the opportunity to apply to a limited number of bursaries for partial support of travel expenses to attend the conference to present the paper.

* * *

Accommodation in College: graduates from Cambridge colleges go on to become leading world scientists, prime ministers, parliamentarians and top civil servants. Share the experience of living-in by staying in college rooms. Full-board 3-day package is available for $630, and $690 en-suite, single occupancy. This includes a meal on the evening before the conference, all meals/conference dinner on day 1 and day 2 (including conference pre-dinner reception), and breakfast and lunch on day 3. For those wishing to take evening meal outside, a Bed & Breakfast 3 day package is available at $490 single occupancy, or $170 per night. Booking and pre-payment is essential, see EDAS Registration.

Submission Guidelines

You are invited to submit:
- full paper of 6 pages (Letter format) for oral presentation,

- computer generated art, submit title and abstract on EDAS as a normal paper then upload the image pdf file only as the Full paper

- proposal to organize a technical session and/or workshop.

Submissions must be original, unpublished work containing new and interesting results that demonstrate current research in all areas of modelling and simulation and their applications in science, technology, business and commerce. The conference is supported/co-sponsored by

- Nottingham Trent University, UK

- Cardiff Metropolitan University, Wales, UK

- University of Wales Trinity Saint David, Wales, UK.

- University of Stavanger, Norway.

- University of Kent in Canterbury, UK

- Aberystwyth University, Wales, UK.

- European Simulation Federation, EUROSIM

- European Council for Modelling and Simulation, ECMS 

Submission implies the willingness of at least one of the authors to register and present the paper. All papers are to be submitted electronically,- see full instructions under Paper Submission below, in PDF or Word format. All papers and artwork will be peer reviewed by at least three independent referees of the international program committee.

Paper Submission: the conference is using EDAS for submission, reviews and registration, authors need to:

- If you do not have an EDAS account: create an account at http://edas.info

- A list of all the tracks opens, click on the track you wish to submit the paper under

- enter your paper title & abstract

- upload file.

 In case of difficulty submit paper by email directly to the general chair: david.al-dabass@ntu.ac.uk

Paper Templates:

Word template (MS Word .doc format)

PDF template (PDF format)

Latex template (Latex format)

Conference website: http://uksim2024.info

Student Members Travel Grants: a limited number of travel bursaries are available for partial support of travel expenses to attend the conference to present the paper, contact the general chair david.al-dabass@ntu.ac.uk

Papers must not suffer from one or more of the following problems:

1. Below average English,

2. Excessive number of citations to the authors own work in References,

3. Little interaction with simulation and computing,

4. Not within the conference scope.

**      **      **

IPC

Kai Juslin (SIMS)

Esko Juuso (SIMS)

Khalid Al-Begain (UKSim)

Rashid Mehmood (UKSim)

Gaius Mulley (UKSim)

Miroslav Snorek (CSSS)

Andras Javor (HSS)

Franco Maceri (ISCS)

Peter Schwartz (ASIM)

Charles Patchett (BAE, Warton)

Henri Pierreval (FRANCOSIM)

Kambiz Badie (Iran)

Yuri Merkuryev (Latvia)

Zulkarnay Zakaria

(Malaysia)

Frank Wang (UK)

Gaby Neumann (ASIM)

Hosam Faiq (Malaysia)

Hissam Tawfik (UK)

Azian Azamimi Abdullah (Malaysia)

Sanjay Chaudhary (India)

Arijit Bhattacharya (Ireland)

Atulya Nagar (UK)

Gregorio Romero (Spain)

Kenneth Nwizege (UK)

Kathy Garden (NZ)

M Luisa Martinez (Spain)

Giuseppe De Francesco (Ireland)

Jerry John Kponyo (Ghana)

Maurizio Naldi (Italy)

Qiang Shen (UK)

Suiping Zhou (Singapore)

Mikulas Alexik (CSSS)

Borut Zupancic (SLOSIM)

Igor Skrjanc (SLOSIM)

Wan Hussain Wan Ishak (Malaysia)

Nitin Nitin (India)

Ford Gaol (Indonesia)

Glenn Jenkins (UKSim)

Martin Tunnicliffe (UK)

David Murray-Smith (UKSim)

Mahdi Mahfouf (UKSim)

Emelio Jimenez Macias (SPAIN)

Danilo Pelusi (Italy)

Vlatko Ceric

Theodoros Kostis (Greece)

Russell Cheng (UKSim)

Miguel Angel Piera (Spain)

Antonio Guasch (Spain)

David Al-Dabass (UKSim)

Jadranka Bozikov (CROSSIM)

Felix Breitenecker (Austria, ASIM, SNE)

Majida Alasady (Tikrit)

Eduard Babulak (USA)

Siegfried Wassertheurer (Germany, ASIM)

Valentina Colla (Italy)

Marco Vannucci (Italy)

Wolfgang Wiechert (ASIM)

Janos Sebestyen-Janosy (Hungary, HSS)

Olaf Ruhle (ASIM)

Zuwairie Ibrahim (Malaysia)

Marius Radulescu (ROMSIM)

Leon Bobrowski (PSCS)

Mojca Indihar Stemberger (Slovenia)

Rosni Abdulla (Malaysia)

Vesna Bosilj-Vuksic (Croatia)

Roland Wertz (Germany)

Andrejs Romanovs (Latvia)

S. Wassertheurer (Germany, ASIM)

Norlaili Safri (Malaysia)
Helen Karatza(Greece)

Nikolaos V. Karadimas (Greece)

Afrand Agah (USA)

Piers Campbell (UAE)
Marco Remondino (Italy)

Fabian Bottinger (Germany)

K.G. Subramanian (Malaysia)

Udhaya Kumar Dayalan

(USA)

Registration: Only one method of payment is available on EDAS:

Credit Card: payment is accepted online and confirmation is instant.

Here is the procedure:

1. go to EDAS at http://edas.info and click on Register yellow tab at the top, a list of conferences will appear

2. Scroll down to conference name (i.e. UKSim2024) line and click on the extreme right green money symbol at the end of this line, a new page will appear

3. Click on the extreme right button (Trolley symbol) after USD $595, a new table will immediately appear under a new line Registered, but no paid.

4. Under this table a list of credit card symbols and SWIFT. Click on the credit card symbol.  

5. A new page will appear, enter all card details, scroll down to the bottom and click Pay for Registration

6. REMEMBER: NO payment received by the set deadline means your paper will Not be in the Proceedings.

If you have problems meeting this deadline email david.al-dabass@ntu.ac.uk immediately.

Best wishes and look forward to meeting you at the conference.

Conference Chairs.

Keynote-A

Leveraging Causal Models to Craft AI Strategy

Dr Pravir Malik

Deep Order Technologies

San Francisco, USA

pravir.malik@deepordertechnologies.com

Abstract

In the dynamic field of Artificial Intelligence (AI), strategic integration is crucial to avoid the pitfall of optimizing peripheral processes at the expense of organizational goals. This paper presents a nuanced AI strategy framework that combines Causal Loop Diagrams (CLD) with Agent-Based Modelling (ABM) to address the intricacies of complex, growth-oriented organizations. By marrying empirical data with theoretical constructs and broad meta-knowledge, this approach enables the practical application of common sense to AI planning. The use of CLDs helps reveal and tackle ingrained patterns that could hinder organizational progress, while ABM facilitates the testing of AI strategies through extensive simulations within varied market and product scenarios. This study exemplifies the benefits of a causal-model-enabled AI strategy for strategic alignment and sustainable growth, suggesting a shift from mere efficiency-driven AI applications to those grounded in a thorough comprehension of complex system interdependencies. The proposed framework paves the way for organizations to develop a robust, anti-fragile AI ecosystem that is attuned to the nuances of their operational environment.

Biography

Dr. Pravir Malik, founder of QIQuantum and Forbes Technology Council's quantum computing group leader, redefines quantum computation by integrating systemic layers from the cellular to the quantum. His innovative fractal-based quantum computer is patent-pending, stemming from a comprehensive cosmology of light detailed in a ten-volume series and multiple IEEE and other technical articles. Holding a Ph.D. in the mathematics of innovation in complex adaptive systems, Malik's work spans 24 books, establishing a unified organizational theory and mathematics. His theoretical constructs have applications across AI, genetics, and more. At QI-Quantum, he harnesses complex systems modelling to guide future trajectories, while his EQ-based app has been adopted by global organizations for team development.

Keynote-B, Tutorial

Exploring New Horizons in Quantum Computation: A Multifaceted View of the Double-Slit Experiment

Dr Pravir Malik

Deep Order Technologies

San Francisco, USA

pravir.malik@deepordertechnologies.com

Abstract

Exploring potential new paths in quantum computation necessitates a fresh examination of the seminal double-slit experiment: a foundational study that catalyzed the exploration of the quantum domain and marked the inception of the quantum era. The behavior of light in this experiment, which exhibits both wave-like and particle-like characteristics, invites analysis from two distinct vantage points. The traditional bottom-up approach interprets these behaviours as superposition and entanglement, which are the cornerstones of contemporary quantum computing. However, adopting a top-down perspective reveals that photons may interact according to the "functional" properties of light. This alternative angle offers a novel understanding of superposition and entanglement, leading to diverse paths for advancing quantum computing. This discussion will bridge current quantum computing practices with one such observer perspective derived from the double-slit experiment. It will also illuminate a spectrum of observer perspectives that may yield unique strategies for engaging with the quantum realm. Furthermore, the session will discuss various potential quantum computational architectures that these new perspectives might inspire, broadening the scope of quantum computational methodologies.

Keynote-C

Quantum AI

Professor Frank Wang

Ex-Head of School of Computing, University of Kent, UK

Chairman, IEEE Computer Society (UK and Ireland Chapter)

Coordinator, IEEE Computer Society (Western Europe)

Email: frankwang@ieee.org; f.z.wang@kent.ac.uk

Abstract

Quantum Information Processing (Springer Nature) and IEEE Transactions on Quantum Engineering, detail Prof. Frank Wang recent advancements in spin-encoded quantum computing, which approaches the ultimate physical limits. These energy-efficient quantum computers have the potential to significantly enhance artificial intelligence by tackling computing-intensive and data-intensive problems beyond the capabilities of classical computers. Quantum computers excel in search tasks due to their ability to simultaneously search multiple elements in quantum superposition. Quantum algorithms enable the processing of tensors (multi-dimensional data arrays) and can complete years of training for deep learning and generative AI models within a short time. Quantum neural networks can uncover hidden knowledge from entangled quantum states and perform quantum reasoning amidst uncertainty. In conclusion, quantum AI stands out as a promising avenue for the next generation of artificial intelligence.

Most recently, Professor Frank Wang published an article on Quantum Information Processing in Springer Nature:

https://link.springer.com/article/10.1007/s11128-022-03707-2

to report on a new quantum computer that can break Landauers Bound:

https://en.m.wikipedia.org/wiki/Landauer%27s_principle

Biography

Frank Z. Wang is Professor in Future Computing and ex-Head of the School of Computing (2010-2016), University of Kent, UK. Professor Wang's research interests include quantum computing, artificial intelligence, neuromorphic computing, non-Turing architecture, memristors as a new computing paradigm, unconventional computing, brain-like computer, deep learning, green computing, grid/cloud computing, and data storage & data communication. He is now guest-editing a special issue on Quantum Computing and Artificial Intelligence for Information (IF=3.1). He has published intensively in top journals, including IEEE Transactions on Quantum Engineering, Quantum Information Processing (Springer Nature), IEEE Transactions on Computers, ACM Operating System Review, Neural Networks, Information Sciences, IEEE Transactions on Circuits and Systems, Applied Physics Letters, IEEE Electron Device Letters, Journal of Applied Physics, and top conferences, including ACM/IEEE Super-Computing, IEEE Big Data, IEEE Mobile Services, EuroPar, IC, and IEEE Non-Volatile Memory. So far, he has attracted research funding of over Sterling Pounds 5m from the UK government and the European Commission. Professor Wang has chaired over 10 international conferences/symposiums. He is a regular keynote/invited speaker worldwide, for example at Princeton University, Carnegie Mellon University, CERN, Hong Kong University of Sci. & Tech., Tsinghua University (Taiwan), Jawaharlal Nehru University, Aristotle University, and the University of Johannesburg. In 1996, Frank designed and developed a new type of random access memory using the spin-tunnelling effect at Tohoku University, Japan. This device was the first of its kind worldwide. Frank obtained his PhD degree in the UK in 1999. Only 5 years after his PhD degree, he was appointed Chair Professor and Director of the Centre for Grid Computing at CCHPCF (Cambridge-Cranfield High Performance Computing Facility). CCHPCF is a collaborative research facility at the Universities of Cambridge and Cranfield (with an investment size of Sterling Pounds 40 million). Prof Wang and his team won an ACM/IEEE Super Computing finalist award in USA in 2007. Between 2017 and 2018, he spent his sabbatical at Tsinghua University. Prof. Wang is a Fellow of the British Computer Society. He is the Chairman of UK & Republic of Ireland Chapter, of the IEEE Computer Society. Professor Wang is also the IEEE Computer Society Region 8 Area 2 Coordinator in charge of over 10 western European countries including the UK, France, Germany, Ireland, Netherlands, Luxemburg, Belgium, Denmark, Switzerland, Spain, Portugal, Austria and Iceland. He sat on the UK Government EPSRC e-Science, Hardware for Efficient Computing and ICT Panels and the Irish Government High End Computing Panel for Science Foundation Ireland (SFI).

Keynote-D

Activity-Oriented Petri Nets for Reducing the Complexities of Discrete Models

Professor Dr Reggie Davidrajuh

Department of Electrical Engineering and Computer Science

University of Stavanger, Norway.

Email: reggie.davidrajuh@uis.no

Abstract

Petri Net was popular in the 1980s and 1990s as an effective tool for the modelling and analysis of discrete systems. However, researchers soon discovered that Petri nets-based models become huge even for small real-life scenarios. Researchers then proposed methodologies for the compression of models; compression methodologies work for some cases, demanding some skills from the model developers as only some specific types of Petri nets (e.g., event graphs) can be compressed. Also, in most cases, the preservation of properties of the original model in the compressed model is not guaranteed. Researchers also proposed modular Petri Net models, partitioning the monolithic model into multiple modules. Though modular models offer many advantages (such as reuse and independent development and testing of modules), the overall size would still be huge, causing extensive simulation time. Also, some Petri nets cannot be modularized due to their crisscrossing connections.

General-purpose Petri Net Simulator (GPenSIM) offers a variety of solutions to solve the huge size of Petri Net models. GPenSIM allows not only modularisation but also allows modules to be run on different computers so that the simulation time can be drastically reduced, making the modules suitable for real-time applications. In addition to modular model development, it also provides Activity-Oriented Petri Nets (AOPN). AOPN is a two-phased model development. In the first phase (static phase), only the activities are considered resulting in a simpler static Petri Net model; the resources are not considered in the first phase. Then, in the second phase (run-time phase), the resources are added during the simulation. AOPN, in addition to modular models, provides a solution to reduce the size of Petri net models and remove some complexities.

Biography

Professor Reggie Davidrajuh received a Masters Degree in Control Systems Engineering and a PhD in Industrial Engineering, both from the Norwegian University of Science and Technology (NTNU). He also received a DSc (habilitation degree) from the AGH University of Science and Technology, Poland. He is now a professor of Informatics at the department of Electrical Engineering and Computer Science, the University of Stavanger, Norway. His current research interests are discrete-event dynamic systems, modelling, simulation and performance analysis, algorithms, and graph theory. He is a senior member of IEEE and a Fellow of British Computer Society. He is also a member of the Norwegian Academy of Technological Sciences (NTVA).

Keynote-E

AI Efficacy in Sparse Data Environments:

Exploring Approximate Knowledge Interpolation for Practical Applications

Professor Qiang Shen

Pro Vice-Chancellor for Business and Physical Sciences

Aberystwyth University, Wales, UK.

Email: qqs@aber.ac.uk

Abstract

AI stands at the forefront of transforming global industries, achieving remarkable progress in recent years, largely driven by advanced deep learning techniques adept at processing extensive datasets. However, a crucial question arises when confronted with limited and ambiguously characterised data for a novel problem: Can AI maintain its effectiveness under such constraints? This presentation delves into addressing this query, emphasising the role of fuzzy rule interpolation (FRI) in enabling approximate reasoning amidst sparse or incomplete knowledge. This becomes particularly crucial when traditional rule-based inference mechanisms struggle due to misalignment with observations.

Extensive research into FRI techniques within computational intelligence has yielded various methodologies. The focus of this presentation centres on a notable subset, Transformation-based FRI (T-FRI). T-FRI operates by mathematically adjusting rules that share similarities with unmatched observations, utilising linear transformations of the nearest rules chosen automatically relative to an unmatched observation.

The presentation will commence with an exploration of the foundational T-FRI approach, followed by a concise overview of its extended repertoire: adaptive T-FRI, backward T-FRI, higher-order T-FRI, dynamic T-FRI, and weighted T-FRI. Each of these variations addresses specific limitations inherent in the original method. Subsequently, real-world applications of these techniques will be showcased, demonstrating their effectiveness in addressing challenges in domains such as network security and medical diagnosis. These examples underscore AI's ability to operate effectively even when faced with incomplete knowledge and ambiguous data. The presentation concludes with a glimpse into potential advancements in this critical research domain.

Biography

Qiang Shen received a PhD in Computing and Electrical Engineering from Heriot-Watt University in 1990 and a DSc in Computational Intelligence from Aberystwyth University in 2013. He currently holds the Established Chair of Computer Science and serves as Pro Vice-Chancellor for Faculty of Business and Physical Sciences at Aberystwyth University. He is a Fellow of the Royal Academy of Engineering and a Fellow and Council Member of the Learned Society of Wales. He had the honour of being selected as a London 2012 Olympic Torch Relay torchbearer, in celebration of Alan Turing centenary. Also, he has been a panel member for two consecutive UK Research Excellence Framework (REF) exercises in 2014 and 2021, on Computer Science and Informatics. He is the recipient of the 2024 IEEE Fuzzy Systems Pioneer Award. Professor Shen has authored three research monographs and over 470 peer-reviewed papers. His publications include many receiving outstanding journal article or best conference paper awards, some are directly pertinent to the subject matter of this presentation.

Keynote-F

Understanding the Interplay between Trust, Reliability and Human Factors in the Age of Generative AI

Dr Simon Thorne

Cardiff School of Technologies, Cardiff Metropolitan University

sthorne@cardiffmet.ac.uk

Abstract

In the swiftly evolving landscape of Generative AI, particularly through Large Language Models (LLMs), there is a burgeoning utility across diverse applications. While these tools promise heightened accuracy, efficiency, and productivity, the potential for misinformation and "hallucinations" underscores the need for cautious implementation. Despite proficiency in meeting user-specific demands, LLMs lack a comprehensive problem-solving intelligence and struggle with input uncertainty, leading to inaccuracies. This paper critically examines the nuanced challenges surrounding Generative AI, delving into trust issues, system reliability, and the impact of human factors on objective judgments. As we navigate the complex terrain of Generative AI, the presentation advocates for a discerning approach, emphasizing the necessity of verification and validation processes to ensure the accuracy and reliability of generated outputs. The exploration serves to illuminate the multifaceted dimensions of trust in technology, providing insights into how human factors shape our ability to make objective assessments of the reliability and accuracy of artifacts produced by Generative AI. This contribution to the academic discourse fosters a comprehensive understanding of the intricate dynamics inherent in the responsible utilisation of Generative AI technologies.

Keywords: Generative AI, Trust in Technology, Human Factors, Software Engineering, Verification, Validation, Hallucinations

Biography

Dr Simon Thorne is a Senior Lecturer in Computer Science at Cardiff School of Technologies. Simon teaches and researches in the fields of Artificial Intelligence, Machine Learning, Neural Networks, End User Computing, Spreadsheet Error and Human Factors. Simon has personally published 30 papers since 2004 and has held the position as chair of the European Spreadsheets Risks Interest Group (EuSpRIG) since 2008. In that time he has published 13 proceedings containing 150 papers with about 1500 citations on spreadsheet error, risk, software engineering, computers in society and human factors. Simon is a subject specialist in Artificial Intelligence, Data Science, Machine Learning and visualisation for the Engineering and Physical Science Research Council (EPSRC) college. Simon also reviews for top tier computer science journals such as IEEE Access.

Keynote-G

Intelligent Transportation Systems - Connectivity in Connected and Autonomous Vehicles

Dr Evtim Peychev

School of Science and Technology

Nottingham Trent University

Nottingham, NG11 8NS.

Email: evtim.peychev@ntu.ac.uk

Abstract

This lecture introduces the Connectivity part in the domain of Connected and Autonomous Vehicles (CAV) for Intelligent Transportation Systems (ITS). Understanding the contemporary communication technologies like 4G and 5G, WiFi etc. is essentials for ITS. It goes into technical details and explains how multiple devices can communicate on the same wavelength at the same time. Furthermore, details of the different equipment components are given - e.g. handset, SIM card, base station etc. Special use of WiFi - Dedicated Short Range Communication (DSRC) and its use cases is considered. The intelligence embedded in this technology plays essential part.

Based on the connectivity technology, the lecture considers several reference implementations of a communication frameworks, where Vehicle to vehicle (V2V) and vehicle to infrastructure (V2I) communications are seamlessly integrated. Furthermore, five general requirements for building vehicular applications are introduced and explained.

One of the important wireless technologies for Intelligent Transportation Systems (ITS) is the introduction of a new wireless standard for the needs of the intelligent communications.

The presented material considers the 802.11p standard for communication between cars and highlights some differences between the American and European standards in using the 802.11p approach.

A closer look into the vehicle telematics basic concepts for ITS is also provided. The material in the lecture covers aspects of sensor equipment and functionality in vehicles. Significant part of the unit is dedicated to in-car computer networks like Controller Area Network (CAN) bus and others.

The lecture highlights the importance of the technology for ITS and indicates how it enhances the development of future sustainable Intelligence in transportation.

Biography

Dr Evtim Peytchev is Associate Professor in Wireless, Mobile and Pervasive Computing at Nottingham Trent University, UK. His research interests are in ICT for ITS and include connectivity for Connected and Autonomous Vehicles (CAV), traffic simulation, modelling, traffic telematics, mathematical modelling of the uncertainties in traffic modelling, distributed computing environments (shared memory design domain), ad-hoc wireless networks, building wireless communication models for future traffic information systems, telematics technology application in the urban traffic control. Dr Peytchevs primary interest is in novel algorithms for collaborative identification of traffic conditions through ad-hoc network wireless communications and building new generation of traffic control systems based on collaborative interaction between all cars.

He is experienced in real-time traffic simulation in distributed environment (various platforms), telecommunication, mobile hand-held computers use in traffic environment, real-time traffic control systems, programming in C++, cross-platform (iOS, OS X, Windows, UNIX and EPOC for PSION hand-held computers) TCP/IP programming, JAVA, SMS (small message service) for GSM networks, WAP, ad-hoc networks, WiFi installation and design, J2ME, GPRS experience. He has worked on H2020 research projects totalling 35mln Euro and has had numerous successful PhD students. He has previously served as president and currently serves as treasurer for the European Council for Simulation and Modelling (ECMS).

Keynote-H

Predictive Modelling for Mitigating Cyber-Violence by Leveraging AI for Proactive Intervention

Assoc. Prof. Dr. Lela Mirtskhulava

Ivane Javakhishvili Tbilisi State University and San Diego State University Georgia.

Email: lela.mirtskhulava@tsu.ge; lmirtskhulava@sdsu.edu

Abstract

The facilitation of digital technologies increased and hardened cyber-violence that has become a significant societal concern and encompassing a wide range of harmful behaviors occurring in online environments. The given work explores the potential of predictive modeling powered by artificial intelligence (AI) to forecast future instances of cyber-violence. By analyzing historical dataset and identifying key factors contributing to online aggression, predictive models can facilitate proactive measures aimed at mitigating the risk of cyber-violence. In the given work, we discuss the methodology, challenges, and implications of employing predictive modeling in the prevention of cyber-violence.

Cyber-violence forms such as cyberbullying, online harassment, hate speech, and digital abuse, poses significant threats to individuals' well-being and online communities' safety. Traditional reactive approaches to combating cyber-violence often fall short in addressing the root causes and preventing further occurrences. In response to that, the predictive modeling with AI technologies comes into play for anticipating and mitigating cyber-violence before it escalates.

The proposed predictive modeling involves the application of statistical algorithms and machine learning techniques to analyze historical data and predict or forecast future events. Predictive modeling aims to identify patterns, trends, and risk factors associated with online aggression in the context of cyber-violence prevention by leveraging vast datasets containing information about past instances of cyber-violence, machine learning algorithms can discern underlying factors contributing to such behaviors.

Keywords: Predictive Modelling, AI, Cyber-violence, machine learning

Biography

Lela Mirtskhulava earned her Ph.D. in Computer Science and currently serves as an associate professor in the Computer Science department at Ivane Javakhishvili Tbilisi State University/San Diego State University Georgia. Previously, she held a part-time faculty position in the Computer Engineering department at San Jose State University, CA. With a background as an ICT Senior Engineer at Ericsson and Geocell LLC, her professional experience spans diverse areas.

Her research pursuits encompass cybersecurity, AI, blockchains, AI modeling in Medicine, brainwave monitoring, wireless technologies, and mathematical modeling, resulting in the publication of over 80 scientific papers. Dr. Mirtskhulava's expertise has led to invitations as a visiting professor at the University of Cambridge, UK, and recognition through Fulbright and DAAD Scholarships.

In addition to her academic endeavors, she serves as a keynote speaker and holds roles as a technical committee member and advisory board member at various international conferences. Furthermore, she has contributed to Horizon Europe Program Georgia as a Pillar II coordinator and Health NCP. Currently, she is a Management Committee member of COST CA 19136 action, while concurrently holding the position of Protection/Technology Specialist at Mercy Corps Georgia.

Keynote-I

Finite Impulse Response Optimizer

Assoc. Prof Dr. Zuwairie Ibrahim

University Malaysia Pahang

Kuantan, Malaysia

zuwairie@ump.edu.my

Abstract

This talk introduces a metaheuristic optimization algorithm, named Finite Impulse Response Optimizer (FIRO). This algorithm is inspired by the estimation ability of the ultimate iterative Unbiased Finite Impulse Response (UFIR) filter. The UFIR filter is one of the variants of the Finite Impulse Response (FIR) filter, whereby in state space models the FIR filter can be used as an option other than the Kalman Filter (KF) for state estimation. Unlike the KF, the UFIR filter does not require any noise covariance, error covariance or initial condition to calculate the state estimate. The UFIR filter also provides an iterative Kalman-like form to improve the estimation process. In the FIRO algorithm, the agent works as an individual UFIR to find an optimal or a near-optimal solution, where the agent needs to perform two main tasks: measurement and estimation. The performance of the FIRO algorithm is compared with several well-known metaheuristic optimization algorithms based on CEC 2014 Benchmark Test Suite for single-objective optimization.

Biography

Associate Professor Dr Zuwairie Ibrahim graduated from Universiti Teknologi Malaysia with B.Eng in Electrical Engineering in 2000 and MSc by research in Image Processing in 2002. He received his PhD in DNA Computing from Meiji University, Japan, in 2006. He is currently with the Faculty of Manufacturing and Mechatronic Engineering Technology, Universiti Malaysia Pahang. He is one of the innovators who developed new estimation-based optimisation algorithms namely Simulated Kalman Filter Algorithm and Finite Impulse Response Optimiser. To date he has published over 130 conference papers and over 100 journal papers.

Keynote-J

Exploiting the Modelling of Problem Domain Knowledge to Advance Text Analytics: from Computational Linguistics to Large Language Models

Dr Taha Osman

School of Science and Technology

Nottingham Trent University

Nottingham, NG11 8NS.

Email: taha.osman@ntu.ac.uk

Abstract

The success of Large Language Models (LLM), most notably ChatGPT, has rejuvenated interest in Text Analytics and its applications. LLM-based systems utilise the new generation transformer neural networks that are trained on colossal amounts of text data (GPT-4 processes 100-trillion parameters) to power NLP/Text Analytics applications such as document summary and conversational agents. My rich track record in modelling the knowledge embedded in the problem domain into semantic ontologies (knowledge graphs) that have proven effective in improving the classification engines behind information retrieval and sentiment analysis applications. The research talk will explore the fundamentals of his hybrid knowledgebase - Machine Learning NLP methods and their application to different applications areas including digital media, mineral exploration, and social media analytics. The talk will also discuss the recent investigation in introducing domain knowledge to boost the classification accuracy of LLMs (BERT).

Short Biography

Dr Taha Osman is a principal lecturer in the Department of Computer Science at the Nottingham Trent University, where he also received his PhD in Fault-Tolerant Distributed Computing. His research interests include the Semantic Web, Knowledge-based Information Extraction, Intelligent Recommender Systems, Linked Open Data, Opinion Mining and Sentiment Analysis , and Arabic NLP Systems

Keynote-K

AI Classification of Respiratory Illness Through Vocal Biomarkers and A Bespoke Articulatory Speech Protocol

Dr Tim Bashford

University of Wales Trinity Saint David

Wales, United Kingdom.

Email: tim.bashford@uwtsd.ac.uk

Abstract

Speech biomarkers represent a powerful indicator for detecting, monitoring and categorising neurological, psychological, pathological and pulmonary conditions. Facilitated by advances in computational power and artificial intelligence (AI) techniques, we present a novel ecosystem for data acquisition, analysis and storage, using an articulatory speech task. By automatically segmenting, aligning and extracting features from the vocal recordings, we present a feature extraction pipeline toward the classification of pathological conditions, specifically respiratory disease through recorded voice. Data is stored within in a Trusted Research Environment, for which this work also presents a range of ethical considerations.

Biography

Dr Tim Bashford is research lead and deputy director for the Wales Institute of Digital Information (WIDI), a tripartite collaboration between the University of Wales Trinity Saint David, University of South Wales and Digital Health and Care Wales (DHCW), focused on digital healthcare and social innovation. Tim researches across the fields of artificial intelligence, machine learning, computational physics, computational biomedicine and digital healthcare. He has particular areas of interest in the simulation of light-tissue interaction, gamification of public health, detection and classification of respiratory disease through recorded voice and the impact of generative AI on academic integrity. Tim has a PhD in computer science, with numerous academic publications. His work was recently featured in the British Computer Society's ITNOW magazine.