Ioannis Rallis
YOU?
Author Swipe
View article: DORIE: Dataset of Road Infrastructure Elements—A Benchmark of YOLO Architectures for Real-Time Patrol Vehicle Monitoring
DORIE: Dataset of Road Infrastructure Elements—A Benchmark of YOLO Architectures for Real-Time Patrol Vehicle Monitoring Open
Road infrastructure elements like guardrails, bollards, delineators, and traffic signs are critical for traffic safety but are significantly underrepresented in existing driving datasets, which primarily focus on vehicles and pedestrians. …
View article: A Comparative Analysis of U-Net Architectures with Dimensionality Reduction for Agricultural Crop Classification Using Hyperspectral Data
A Comparative Analysis of U-Net Architectures with Dimensionality Reduction for Agricultural Crop Classification Using Hyperspectral Data Open
The inherent high dimensionality of hyperspectral imagery presents both opportunities and challenges for agricultural crop classification. This study offers a rigorous comparative evaluation of three U-Net-based architectures, i.e., U-Net,…
View article: Assessing Coastal Degradation Through Spatiotemporal Earth Observation Data Cubes Analytics and Multidimensional Visualization
Assessing Coastal Degradation Through Spatiotemporal Earth Observation Data Cubes Analytics and Multidimensional Visualization Open
Coastal and maritime regions and their entities face accelerated degradation due to the combined effects of environmental stressors and anthropogenic activities. Coastal degradation can be identified, visualized and estimated through perio…
View article: Empowering Communities Through Gamified Urban Design Solutions
Empowering Communities Through Gamified Urban Design Solutions Open
The rapid urbanization of recent decades has intensified climate change challenges, demanding sophisticated solutions to build resilient and sustainable cities. A key aspect of sustainable urban planning is decentralizing and democratizing…
View article: Voting-Based Intervention Planning Using AI-Generated Images
Voting-Based Intervention Planning Using AI-Generated Images Open
The continuous evolution of artificial intelligence and advanced algorithms capable of generating information from simplified input creates new opportunities for several scientific fields. Currently, the applicability of such technologies …
View article: Quantum neural networks meet federated learning for DNA mutation prediction
Quantum neural networks meet federated learning for DNA mutation prediction Open
In this work, we introduce QuanGAT, a hybrid framework integrating quantum neural networks (QNNs), graph attention networks (GATs), and federated learning to tackle DNA mutation prediction in biomedical graphs in a privacy-preserving, nois…
View article: A Dilemma-Based Learning-to-Rank Approach for Generative Design in Urban Architectural Regeneration
A Dilemma-Based Learning-to-Rank Approach for Generative Design in Urban Architectural Regeneration Open
Continuous urbanization and climate change degrade urban living conditions. Nature-based solutions in architectural and urban design offer promising remedies but are often hindered by time, cost, and early design phase challenges. To addre…
View article: Deep Learning-Based Prediction of Seawater Intrusion Using recurrent architectures: application on Kalymnos Island
Deep Learning-Based Prediction of Seawater Intrusion Using recurrent architectures: application on Kalymnos Island Open
This study explores the application of deep learning models (DL) for the prediction of seawater intrusion in coastal aquifers, under time-varying recharge and pumping conditions, for Kalymnos Island, Greece. The models, based on recurrent …
View article: Segmentation of Remote Sensing Data with Missing Modalities Through Prototype Knowledge Distillation
Segmentation of Remote Sensing Data with Missing Modalities Through Prototype Knowledge Distillation Open
Segmentation of Remote Sensing Data with Missing Modalities Through Prototype Knowledge Distillation Abstract: Segmentation of remote sensing data is a critical task in various environmental and geospatial applications. However, the pre…
View article: Identifying False Negative Flood Events Using Interpretable Deep Learning Framework
Identifying False Negative Flood Events Using Interpretable Deep Learning Framework Open
Identifying False Negative Flood Events Using Interpretable Deep Learning Framework Abstract: An explainable AI framework for flood detection in SAR images is proposed. Compact encoder-decoder CNNs are used within the framework to achie…
View article: Quantifying the Impact of Nature based Interventions on Citizen Health and Well-being
Quantifying the Impact of Nature based Interventions on Citizen Health and Well-being Open
This paper presents a comprehensive exploration of the euPOLIS project's innovative approach to quantifying the impact of nature-based interventions on citizens health and well-being. The study leverages a sophisticated array of tools, inc…
View article: A Way Forward for the MDCG 2019-16 Medical Device Security Guidance
A Way Forward for the MDCG 2019-16 Medical Device Security Guidance Open
sponsorship: This work was funded by the European Commission under the following projects and grant IDs. NEMECYS: 101094323, CYLCOMED: 101095542, MEDSECURANCE: 101095448, SEPTON: 101094901, ENTRUST: 101095634. (European Commission|10109432…
View article: Ocean-DC: An analysis ready data cube framework for environmental and climate change monitoring over the port areas
Ocean-DC: An analysis ready data cube framework for environmental and climate change monitoring over the port areas Open
The environmental hazards and climate change effects causes serious problems in land and coastal areas. A solution to this problem can be the periodic monitoring over critical areas, like coastal region with heavy industrial activity (i.e.…
View article: Zeekflow+: A Deep LSTM Autoencoder with Integrated Random Forest Classifier for Binary and Multi-class Classification in Network Traffic Data
Zeekflow+: A Deep LSTM Autoencoder with Integrated Random Forest Classifier for Binary and Multi-class Classification in Network Traffic Data Open
This work proposes Zeekflow+, a Deep LSTM Autoencoder (AE) architecture with integrated Random Forest (RF) classifier for effective binary & multi-class classification of network traffic data. The Deep LSTM AE is used to extract underlying…
View article: A Deep Learning Framework for Segmentation of Road Defects Using ResUNet-a
A Deep Learning Framework for Segmentation of Road Defects Using ResUNet-a Open
We present a deep learning framework leveraging the ResUNet-a framework for pixel-wise semantic segmentation of cracks and potholes. By integrating key components including a U-Net encoder/decoder backbone, residual connections, atrous con…
View article: IKAROS: a UAV-based integrated system for monitoring road defects and managing vehicle traffic and emergencies on road transport networks
IKAROS: a UAV-based integrated system for monitoring road defects and managing vehicle traffic and emergencies on road transport networks Open
In recent years, there has been a notable rise in the adoption of Unmanned Aerial Vehicles (UAVs) for infrastructure inspection. This study focuses on presenting IKAROS, an integrated system that harnesses the combined capabilities of mult…
View article: Multi-scale Intervention Planning based on Generative Design
Multi-scale Intervention Planning based on Generative Design Open
The scarcity of green spaces, in urban environments, consists a critical challenge. There are multiple adverse effects, impacting the health and well-being of the citizens. Small scale interventions, e.g. pocket parks, is a viable solution…
View article: C2A-DC: A context-aware adaptive data cube framework for environmental monitoring and climate change crisis management
C2A-DC: A context-aware adaptive data cube framework for environmental monitoring and climate change crisis management Open
A context-aware adaptive data cube (C2A-DC) framework based on Earth Observation (EO) data for environmental monitoring to mitigate Climate Change (CC) effects is proposed. It has the property of combining DC formation, calculation of Remo…
View article: Lightweight machine learning for privacy-preserving and secure networked medical devices: The SEPTON project use cases
Lightweight machine learning for privacy-preserving and secure networked medical devices: The SEPTON project use cases Open
Cybersecurity incidents are among the greatest concerns of businesses, government agencies, and private citizens today. In the modern world, the protection of data and information assets has become nearly as important as maintaining the se…
View article: An integrated framework for classifying mammograms according to BIRADS scale and breast tissue density.
An integrated framework for classifying mammograms according to BIRADS scale and breast tissue density. Open
In this work, we present an integrated framework for classifying digital or digitized mammograms according to either BIRADS scale or breast density score. We propose unified data preparation procedure, a common training process that includ…
View article: Dynamically tangible cultural heritage monitoring from web video sources
Dynamically tangible cultural heritage monitoring from web video sources Open
Climate change is serious problem, which can negatively affect the tangible cultural heritage. An actively solution to this problem is the long-term continuous monitoring of the cultural heritage, which is impossible in many cases. In this…
View article: A Low-Cost Gamified Urban Planning Methodology Enhanced with Co-Creation and Participatory Approaches
A Low-Cost Gamified Urban Planning Methodology Enhanced with Co-Creation and Participatory Approaches Open
Targeted nature-based small-scale interventions is an approach commonly adopted by urban developers. The public acceptance of their implementation could be improved by participation, emphasizing residents or shopkeepers located close to th…
View article: Tensor-Based Learning for Detecting Abnormalities on Digital Mammograms
Tensor-Based Learning for Detecting Abnormalities on Digital Mammograms Open
In this study, we propose a tensor-based learning model to efficiently detect abnormalities on digital mammograms. Due to the fact that the availability of medical data is limited and often restricted by GDPR (general data protection regul…
View article: Using mHealth Technologies to Promote Public Health and Well-Being in Urban Areas with Blue-Green Solutions
Using mHealth Technologies to Promote Public Health and Well-Being in Urban Areas with Blue-Green Solutions Open
European and International cities face crucial global geopolitical, economic, environmental, and other changes. All these intensify threats to and inequalities in citizens’ health. The implementation of Blue-Green Solutions in urban and ru…
View article: Novel Insights in Spatial Epidemiology Utilizing Explainable AI (XAI) and Remote Sensing
Novel Insights in Spatial Epidemiology Utilizing Explainable AI (XAI) and Remote Sensing Open
The COVID-19 pandemic has affected many aspects of human life around the world, due to its tremendous outcomes on public health and socio-economic activities. Policy makers have tried to develop efficient responses based on technologies an…
View article: Pervasive Monitoring of Public Health and Well-Being in Urban Areas with Blue-Green Solutions
Pervasive Monitoring of Public Health and Well-Being in Urban Areas with Blue-Green Solutions Open
The urban environment seems to affect the citizens’ health. The implementation of Blue-Green Solutions (BGS) in urban areas have been used to promote public health and citizens well-being. The aim of this paper is to present the developmen…
View article: A mobile game for enhancing Tourism and Cultural Heritage
A mobile game for enhancing Tourism and Cultural Heritage Open
This paper briefly describes the overall concept of "TRAVEL TYCOON GREECE" (TTGR), a novel business simulation game which aims to simulate realistically a complete tourism experience. The latest image processing and computer graphics techn…
View article: Multiclass Confusion Matrix Reduction Method and Its Application on Net Promoter Score Classification Problem
Multiclass Confusion Matrix Reduction Method and Its Application on Net Promoter Score Classification Problem Open
The current paper presents a novel method for reducing a multiclass confusion matrix into a 2×2 version enabling the exploitation of the relevant performance metrics and methods such as the receiver operating characteristic and area under …
View article: Evaluating the Usefulness of Unsupervised Monitoring in Cultural Heritage Monuments
Evaluating the Usefulness of Unsupervised Monitoring in Cultural Heritage Monuments Open
In this paper, we scrutinize the effectiveness of various clustering techniques, investigating their applicability in Cultural Heritage monitoring applications. In the context of this paper, we detect the level of decomposition and corrosi…