Data augmentation for fairness-aware machine learning: Preventing algorithmic bias in law enforcement systems

I Pastaltzidis, N Dimitriou, K Quezada-Tavarez… - Proceedings of the …, 2022 - dl.acm.org
Researchers and practitioners in the fairness community have highlighted the ethical and
legal challenges of using biased datasets in data-driven systems, with algorithmic bias …

Real-time adaptation of context-aware intelligent user interfaces, for enhanced situational awareness

Z Stefanidi, G Margetis, S Ntoa… - IEEE Access, 2022 - ieeexplore.ieee.org
In this work, a novel computational approach for the dynamic adaptation of User Interfaces
(UIs) is proposed, which aims at enhancing the Situational Awareness (SA) of users by …

Real-time stress level feedback from raw ecg signals for personalised, context-aware applications using lightweight convolutional neural network architectures

K Tzevelekakis, Z Stefanidi, G Margetis - Sensors, 2021 - mdpi.com
Human stress is intricately linked with mental processes such as decision making. Public
protection practitioners, including Law Enforcement Agents (LEAs), are forced to make …

Artificial intelligence, task complexity and uncertainty: analyzing the advantages and disadvantages of using algorithms in public service delivery under public …

S Nzobonimpa - Digital Transformation and Society, 2023 - emerald.com
Purpose This article revisits some theories and concepts of public administration, including
those related to public value, transaction costs and social equity, to analyze the advantages …

Real-time activity recognition for surveillance applications on edge devices

V Tsinikos, I Pastaltzidis, I Karakostas… - Proceedings of the 16th …, 2023 - dl.acm.org
Human Activity Recognition is a crucial task for surveillance systems that has seen great
advancements with the emergence of Artificial Intelligence. At the same time, hardware …

The disconnect between the goals of trustworthy AI for law enforcement and the EU research agenda

B Sanz-Urquijo, E Fosch-Villaronga, M Lopez-Belloso - AI and Ethics, 2023 - Springer
In this paper, we investigate whether AI deployment for law enforcement will enable or
impede the exercise of citizens' fundamental rights by juxtaposing the promises and policy …

Augmentation based on artificial occlusions for resilient instance segmentation

N Kilis, G Tsipouridis, I Karakostas, N Dimitriou… - … Conference on Image …, 2023 - Springer
Real-world instance segmentation applications usually demand real-time identification of
objects that are small in size, occluded from other objects, appearing and disappearing in …

A real-time wearable AR system for egocentric vision on the edge

I Karakostas, A Valakou, D Gavgiotaki, Z Stefanidi… - Virtual Reality, 2024 - Springer
Real-time performance is critical for Augmented Reality (AR) systems as it directly affects
responsiveness and enables the timely rendering of virtual content superimposed on real …

Integrating body-worn cameras, drones, and AI: A framework for enhancing police readiness and response

A Davies, G Krame - Policing: A Journal of Policy and Practice, 2023 - academic.oup.com
The combined use of body-worn cameras (BWCs), drones, and artificial intelligence (AI)
within the context of policing represents a significant advancement in policing methodology …

Context Driven MEC Resource Allocation for Time-Critical AR Applications

SI Raptis, I Karakostas, N Dimitriou… - 2023 IEEE 9th World …, 2023 - ieeexplore.ieee.org
Mobile Edge Computing (MEC) is a promising solution for delay-sensitive and
computationally intensive applications mitigating the increased latency that cloud computing …