Loizos Michael
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Loizos Michael has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Antonis Kakas
University of Cyprus
4 shared publications - Andreas Lanitis
Cyprus University of Technology
2 shared publications - Christos Rodosthenous
Open University of Cyprus
2 shared publications - Emmanuelle Dietz
Airbus Central R&T, Hamburg, Germany
2 shared publications - Harris Partaourides
Cyprus University of Technology
2 shared publications - Marios Thoma
CYENS Centre of Excellence, Nicosia, Cyprus
2 shared publications
Latest Publications
- Open Access
PEDESTRIAN: An Egocentric Vision Dataset for Obstacle Detection on Pavements
Walking has always been a primary mode of transportation and is recognized as an essential activity for maintaining good health. Despite the need for safe walking conditions in urban environments, sidewalks are frequently obstructed by various obstacles that hinder free pedestrian movement. Any object obstructing a pedestrian's path can pose a safety hazard. The advancement of pervasive computing and egocentric vision techniques offers the potential to design systems that can automatically detect such obstacles in real time, thereby enhancing pedestrian safety. The development of effective and efficient identification algorithms relies on the availability of comprehensive and well-balanced datasets of egocentric data. In this work, we introduce the PEDESTRIAN dataset, comprising egocentric data for 29 different obstacles commonly found on urban sidewalks. A total of 340 videos were collected using mobile phone cameras, capturing a pedestrian's point of view. Additionally, we present the results of a series of experiments that involved training several state-of-the-art deep learning algorithms using the proposed dataset, which can be used as a benchmark for obstacle detection and recognition tasks. The dataset can be used for training pavement obstacle detectors to enhance the safety of pedestrians in urban areas.
Open AccessPEDESTRIAN: An Egocentric Vision Dataset for Obstacle Detection on Pavements
Walking has always been a primary mode of transportation and is recognized as an essential activity for maintaining good health. Despite the need for safe walking conditions in urban environments, sidewalks are frequently obstructed by various obstacles that hinder free pedestrian movement. Any object obstructing a pedestrian's path can pose a safety hazard. The advancement of pervasive computing and egocentric vision techniques offers the potential to design systems that can automatically detect such obstacles in real time, thereby enhancing pedestrian safety. The development of effective and efficient identification algorithms relies on the availability of comprehensive and well-balanced datasets of egocentric data. In this work, we introduce the PEDESTRIAN dataset, comprising egocentric data for 29 different obstacles commonly found on urban sidewalks. A total of 340 videos were collected using mobile phone cameras, capturing a pedestrian's point of view. Additionally, we present the results of a series of experiments that involved training several state-of-the-art deep learning algorithms using the proposed dataset, which can be used as a benchmark for obstacle detection and recognition tasks. The dataset can be used for training pavement obstacle detectors to enhance the safety of pedestrians in urban areas.
- Open Access
- 3 July 2024
- Published by Springer Nature in Autonomous Agents and Multi-Agent Systems
- Vol. 38 (2) , 1-41
Beyond the echo chamber: modelling open-mindedness in citizens’ assemblies
A Citizens’ assembly (CA) is a democratic innovation tool where a randomly selected group of citizens deliberate a topic over multiple rounds to generate, and then vote upon, policy recommendations. Despite growing popularity, little work exists on understanding how CA inputs, such as the expert selection process and the mixing method used for discussion groups, affect results. In this work, we model CA deliberation and opinion change as a multi-agent systems problem. We introduce and formalise a set of criteria for evaluating successful CAs using insight from previous CA trials and theoretical results. Although real-world trials meet these criteria, we show that finding a model that does so is non-trivial; through simulations and theoretical arguments, we show that established opinion change models fail at least one of these criteria. We therefore propose an augmented opinion change model with a latent ‘open-mindedness’ variable, which sufficiently captures people’s propensity to change opinion. We show that data from the CA of Scotland indicates a latent variable both exists and resembles the concept of open-mindedness in the literature. We calibrate parameters against real CA data, demonstrating our model’s ecological validity, before running simulations across a range of realistic global parameters, with each simulation satisfying our criteria. Specifically, simulations meet criteria regardless of expert selection, expert ordering, participant extremism, and sub-optimal participant grouping, which has ramifications for optimised algorithmic approaches in the computational CA space.
- 3 July 2024
- Published by Springer Nature in Autonomous Agents and Multi-Agent Systems
- Vol. 38 (2) , 1-41
Open AccessBeyond the echo chamber: modelling open-mindedness in citizens’ assemblies
A Citizens’ assembly (CA) is a democratic innovation tool where a randomly selected group of citizens deliberate a topic over multiple rounds to generate, and then vote upon, policy recommendations. Despite growing popularity, little work exists on understanding how CA inputs, such as the expert selection process and the mixing method used for discussion groups, affect results. In this work, we model CA deliberation and opinion change as a multi-agent systems problem. We introduce and formalise a set of criteria for evaluating successful CAs using insight from previous CA trials and theoretical results. Although real-world trials meet these criteria, we show that finding a model that does so is non-trivial; through simulations and theoretical arguments, we show that established opinion change models fail at least one of these criteria. We therefore propose an augmented opinion change model with a latent ‘open-mindedness’ variable, which sufficiently captures people’s propensity to change opinion. We show that data from the CA of Scotland indicates a latent variable both exists and resembles the concept of open-mindedness in the literature. We calibrate parameters against real CA data, demonstrating our model’s ecological validity, before running simulations across a range of realistic global parameters, with each simulation satisfying our criteria. Specifically, simulations meet criteria regardless of expert selection, expert ordering, participant extremism, and sub-optimal participant grouping, which has ramifications for optimised algorithmic approaches in the computational CA space.
- Open Access
- 18 March 2024
- Published by Frontiers Media SA in Frontiers in Artificial Intelligence
- Vol. 7, 1382426
Editorial: Computational argumentation: a foundation for human-centric AI
Editorial: Computational argumentation: a foundation for human-centric AI
- 18 March 2024
- Published by Frontiers Media SA in Frontiers in Artificial Intelligence
- Vol. 7, 1382426
Open AccessEditorial: Computational argumentation: a foundation for human-centric AI
Editorial: Computational argumentation: a foundation for human-centric AI
- Open Access
Neural Sculpting: Uncovering hierarchically modular task structure in neural networks through pruning and network analysis
Natural target functions and tasks typically exhibit hierarchical modularity -- they can be broken down into simpler sub-functions that are organized in a hierarchy. Such sub-functions have two important features: they have a distinct set of inputs (input-separability) and they are reused as inputs higher in the hierarchy (reusability). Previous studies have established that hierarchically modular neural networks, which are inherently sparse, offer benefits such as learning efficiency, generalization, multi-task learning, and transfer. However, identifying the underlying sub-functions and their hierarchical structure for a given task can be challenging. The high-level question in this work is: if we learn a task using a sufficiently deep neural network, how can we uncover the underlying hierarchy of sub-functions in that task? As a starting point, we examine the domain of Boolean functions, where it is easier to determine whether a task is hierarchically modular. We propose an approach based on iterative unit and edge pruning (during training), combined with network analysis for module detection and hierarchy inference. Finally, we demonstrate that this method can uncover the hierarchical modularity of a wide range of Boolean functions and two vision tasks based on the MNIST digits dataset.
Open AccessNeural Sculpting: Uncovering hierarchically modular task structure in neural networks through pruning and network analysis
Natural target functions and tasks typically exhibit hierarchical modularity -- they can be broken down into simpler sub-functions that are organized in a hierarchy. Such sub-functions have two important features: they have a distinct set of inputs (input-separability) and they are reused as inputs higher in the hierarchy (reusability). Previous studies have established that hierarchically modular neural networks, which are inherently sparse, offer benefits such as learning efficiency, generalization, multi-task learning, and transfer. However, identifying the underlying sub-functions and their hierarchical structure for a given task can be challenging. The high-level question in this work is: if we learn a task using a sufficiently deep neural network, how can we uncover the underlying hierarchy of sub-functions in that task? As a starting point, we examine the domain of Boolean functions, where it is easier to determine whether a task is hierarchically modular. We propose an approach based on iterative unit and edge pruning (during training), combined with network analysis for module detection and hierarchy inference. Finally, we demonstrate that this method can uncover the hierarchical modularity of a wide range of Boolean functions and two vision tasks based on the MNIST digits dataset.
- 20 September 2023
- Published by Springer Nature
- p. 172-181
Performance Assessment of Fine-Tuned Barrier Recognition Models in Varying Conditions
- 20 September 2023
- Published by Springer Nature
- p. 172-181
Performance Assessment of Fine-Tuned Barrier Recognition Models in Varying Conditions
- 14 December 2022
- Published by Springer Nature
- p. 296-304
Prudens: An Argumentation-Based Language for Cognitive Assistants
- 14 December 2022
- Published by Springer Nature
- p. 296-304
Prudens: An Argumentation-Based Language for Cognitive Assistants
- Open Access
- 21 October 2022
- Published by Frontiers Media SA in Frontiers in Artificial Intelligence
- Vol. 5, 955579
Argumentation: A calculus for Human-Centric AI
This paper aims to expose and analyze the potential foundational role of Argumentation for Human-Centric AI, and to present the main challenges for this foundational role to be realized in a way that will fit well with the wider requirements and challenges of Human-Centric AI. The central idea set forward is that by endowing machines with the ability to argue with forms of machine argumentation that are cognitively compatible with those of human argumentation, we will be able to support a naturally effective, enhancing and ethical human-machine cooperation and “social” integration.
- 21 October 2022
- Published by Frontiers Media SA in Frontiers in Artificial Intelligence
- Vol. 5, 955579
Open AccessArgumentation: A calculus for Human-Centric AI
This paper aims to expose and analyze the potential foundational role of Argumentation for Human-Centric AI, and to present the main challenges for this foundational role to be realized in a way that will fit well with the wider requirements and challenges of Human-Centric AI. The central idea set forward is that by endowing machines with the ability to argue with forms of machine argumentation that are cognitively compatible with those of human argumentation, we will be able to support a naturally effective, enhancing and ethical human-machine cooperation and “social” integration.
- 4 January 2021
- Published by Springer Nature in Algorithmica
- Vol. 83 (5) , 1256-1315
The Price of Defense
- 4 January 2021
- Published by Springer Nature in Algorithmica
- Vol. 83 (5) , 1256-1315
The Price of Defense
- Open Access
Abduction and Argumentation for Explainable Machine Learning: A Position Survey
This paper presents Abduction and Argumentation as two principled forms for reasoning, and fleshes out the fundamental role that they can play within Machine Learning. It reviews the state-of-the-art work over the past few decades on the link of these two reasoning forms with machine learning work, and from this it elaborates on how the explanation-generating role of Abduction and Argumentation makes them naturally-fitting mechanisms for the development of Explainable Machine Learning and AI systems. Abduction contributes towards this goal by facilitating learning through the transformation, preparation, and homogenization of data. Argumentation, as a conservative extension of classical deductive reasoning, offers a flexible prediction and coverage mechanism for learning -- an associated target language for learned knowledge -- that explicitly acknowledges the need to deal, in the context of learning, with uncertain, incomplete and inconsistent data that are incompatible with any classically-represented logical theory.
Open AccessAbduction and Argumentation for Explainable Machine Learning: A Position Survey
This paper presents Abduction and Argumentation as two principled forms for reasoning, and fleshes out the fundamental role that they can play within Machine Learning. It reviews the state-of-the-art work over the past few decades on the link of these two reasoning forms with machine learning work, and from this it elaborates on how the explanation-generating role of Abduction and Argumentation makes them naturally-fitting mechanisms for the development of Explainable Machine Learning and AI systems. Abduction contributes towards this goal by facilitating learning through the transformation, preparation, and homogenization of data. Argumentation, as a conservative extension of classical deductive reasoning, offers a flexible prediction and coverage mechanism for learning -- an associated target language for learned knowledge -- that explicitly acknowledges the need to deal, in the context of learning, with uncertain, incomplete and inconsistent data that are incompatible with any classically-represented logical theory.
- Open Access
Neural-Symbolic Integration: A Compositional Perspective
Despite significant progress in the development of neural-symbolic frameworks, the question of how to integrate a neural and a symbolic system in a \emph{compositional} manner remains open. Our work seeks to fill this gap by treating these two systems as black boxes to be integrated as modules into a single architecture, without making assumptions on their internal structure and semantics. Instead, we expect only that each module exposes certain methods for accessing the functions that the module implements: the symbolic module exposes a deduction method for computing the function's output on a given input, and an abduction method for computing the function's inputs for a given output; the neural module exposes a deduction method for computing the function's output on a given input, and an induction method for updating the function given input-output training instances. We are, then, able to show that a symbolic module -- with any choice for syntax and semantics, as long as the deduction and abduction methods are exposed -- can be cleanly integrated with a neural module, and facilitate the latter's efficient training, achieving empirical performance that exceeds that of previous work.
Open AccessNeural-Symbolic Integration: A Compositional Perspective
Despite significant progress in the development of neural-symbolic frameworks, the question of how to integrate a neural and a symbolic system in a \emph{compositional} manner remains open. Our work seeks to fill this gap by treating these two systems as black boxes to be integrated as modules into a single architecture, without making assumptions on their internal structure and semantics. Instead, we expect only that each module exposes certain methods for accessing the functions that the module implements: the symbolic module exposes a deduction method for computing the function's output on a given input, and an abduction method for computing the function's inputs for a given output; the neural module exposes a deduction method for computing the function's output on a given input, and an induction method for updating the function given input-output training instances. We are, then, able to show that a symbolic module -- with any choice for syntax and semantics, as long as the deduction and abduction methods are exposed -- can be cleanly integrated with a neural module, and facilitate the latter's efficient training, achieving empirical performance that exceeds that of previous work.