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


Kyriaki A. Tychola has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Cyberthreats and Security Measures in Drone-Assisted Agriculture

    by Kyriaki A. Tychola, Konstantinos Rantos

    Nowadays, the use of Unmanned Aerial Vehicles (UAVs), or drones in agriculture for crop assessment and monitoring is a timely and important issue that concerns both researchers and farmers. Mapping agricultural land is imperative for making appropriate management decisions. As a result, the necessity of this technology is increasing, given its numerous benefits. However, as with any modern and automated technology, security concerns arise from various aspects. In this paper, we discuss cyberthreats to drones, as this technology is vulnerable to attackers during data collection, storage, and usage. Although various techniques and methods have been developed to address attacks on drones, this field remains in its infancy in many respects. This paper provides a comprehensive review of the security challenges associated with the use of agricultural drones. The security issues were thoroughly analyzed, with a particular focus on cybersecurity, categorized into four distinct levels: emerging threats, sensor vulnerabilities, hardware and software attacks, and communication-related threats. Additionally, we examined the limitations and challenges posed by cyberthreats to drone systems.


  • Comparison of Photogrammetric Reconstruction Methods

    by Kyriaki A. Tychola, Eleni Vrochidou, George A. Papakostas

    Digital photogrammetry is a passive contactless, easy, and low-cost 3D scanning technique, that provides effective and powerful tools for 3D realistic reconstruction, as well as precise and high-resolution models based on Structure from Motion (SfM). Photogrammetry leverages data obtained by Unmanned Aerial Vehicles (UAVs), which have reached significant maturity in the sense that they offer a fast, affordable, and effective method for the acquisition of high-resolution geospatial information and image block (nadir and oblique) with high geometric and temporal resolutions. Data are processed by different available commercial or open-source photogrammetric software aiming at 3D reconstruction modelling. Then, the 3D-generated models can be further processed for quantity assessment by applying geometrical measurements. In addition, models through various geovisualization techniques can be used for realistic representations of the physical world. The current research investigates 3D model reconstruction by applying two photogram-metric software, Agisoft Metashape and 3DF Zephyr, in an example of an archaeological site in Greece focusing on the performance of each approach. Moreover, different distance and noise metrics are applied to compare and geometrically assess the 3D dense point clouds, meshes and Digital Surface Models (DSMs). Furthermore, traditional, and modern geovisualization forms of 3D models are discussed towards approaching the 3D models' representation holistically, aiming to provide guidelines to researchers in this field through a comprehensive workflow from data acquisition to manipulation and capabilities combined with other fields such as Computer Vision. Finally, open issues and future research directions are highlighted as a stimulus to further investigations.


  • Emotional Learning Analytics in Education

    by Kyriaki A. Tychola, Eleni Vrochidou, George A. Papakostas

    Learning Analytics (LA) are constantly evolving in the analysis and representation of data related to learners and educators to improve the learning and education process. Data obtained by sensors or questionnaires are processed employing new technologies. The emotional experiences of learners constitute a significant factor in the assimilation of knowledge about the learning process. The emerging technology of Emotional Learning Analytics (ELA) is increasingly being considered in educational settings. In this work, the significance and contribution of ELA in educational data processing are discussed as an integral part of designing and implementing computational models reflecting the learning process. In addition, a comprehensive overview of different methods and techniques for both LA and ELA is provided, while a conceptual model of ELA is proposed in parallel. Moreover, advantages, disadvantages, and challenges are highlighted. The final focus of the chapter is on ethical issues and future research directions.


  • Photogrammetry

    by Kyriaki A. Tychola, Ioannis Tsimperidis, George A. Papakostas

    The use of new technologies in combination with automated systems is leveraged in various ways; increasingly, in education offering innovative learning techniques. Especially using drones' technology for instructional purposes, the knowledge and metacognitive process take on other dimensions. Drone-based photogrammetry is a powerful and effective tool for 3D reconstruction of realistic, accurate, and high-resolution models through various methods and techniques. In this light, some issues about the exploitation of Photogrammetry in the class from a learning aspect and pedagogy value, have emerged. Drone technology can be applied to various educational subjects, such as computer science, geography, history, and language. It is found in a wide range of educational levels, from early childhood development to academic research. This chapter investigates the photogrammetry contribution to all learning aspects, indicates a case study of a 3D reconstruction model through photogrammetric software, and highlights the impact of the learning results on the students' psychology and emotions.

  • Open Access

    Deep learning based computer vision under the prism of 3D point clouds: a systematic review

    by Kyriaki A. Tychola, Eleni Vrochidou, George A. Papakostas

    Point clouds consist of 3D data points and are among the most considerable data formats for 3D representations. Their popularity is due to their broad application areas, such as robotics and autonomous driving, and their employment in basic 3D vision tasks such as segmentation, classification, and detection. However, processing point clouds is challenging compared to other visual forms such as images, mainly due to their unstructured nature. Deep learning (DL) has been established as a powerful tool for data processing, reporting remarkable performance enhancements compared to traditional methods for all basic 2D vision tasks. However new challenges are emerging when it comes to processing unstructured 3D point clouds. This work aims to guide future research by providing a systematic review of DL on 3D point clouds, holistically covering all 3D vision tasks. 3D technologies of point cloud formation are reviewed and compared to each other. The application of DL methods for point cloud processing is discussed, and state-of-the-art models’ performances are compared focusing on challenges and solutions. Moreover, in this work the most popular 3D point cloud benchmark datasets are summarized based on their task-oriented applications, aiming to highlight existing constraints and to comparatively evaluate them. Future research directions and upcoming trends are also highlighted.


  • Open Access

    Tactile IoT and 5G & beyond schemes as key enabling technologies for the future metaverse

    by Kyriaki A. Tychola, Konstantinos Voulgaridis, Thomas Lagkas

    The Tactile Internet (TI) is a recently emerging field that has been developing and evolving to date, since its communications parallel the sense of human touch. Lately, the revolutionized concept, Metaverse, draws attention due to the evolved immersive experience of human perception of the surrounding environment. This technology supports the ultimate union between the physical and virtual world, facilitated by 5G and beyond communication networks. Users are capable of interacting with machines and devices in real-time, remotely, resembling the actions of their physical counterparts. The particular approaches are still in their infancy and expected to produce spectacular results in various sectors such as industry, healthcare, autonomous vehicles, etc. This immersion is further assisted by the Internet of Things, while expecting full wireless support by 5G networks. In this article, a systematic review studies the domains of TI, 5G and beyond networks, as well as their relations with the Metaverse, rendering the respective schemes Key Enabling Technologies for the future Metaverse. A thorough analysis is conducted on the underpinning schemes, relative architectures, structures, and operation modes. In addition, a comprehensive list is presented, focusing on related application fields and their benefits, considering the strengths and weaknesses of the involved technologies. Finally, challenges and issues arising are discussed, both from the perspective of technical requirements and the psychosomatic aspect of human experience.


  • Top Cited Papers
    Open Access

    Quantum Machine Learning—An Overview

    by Kyriaki A. Tychola, Theofanis Kalampokas, George A. Papakostas

    Quantum computing has been proven to excel in factorization issues and unordered search problems due to its capability of quantum parallelism. This unique feature allows exponential speed-up in solving certain problems. However, this advantage does not apply universally, and challenges arise when combining classical and quantum computing to achieve acceleration in computation speed. This paper aims to address these challenges by exploring the current state of quantum machine learning and benchmarking the performance of quantum and classical algorithms in terms of accuracy. Specifically, we conducted experiments with three datasets for binary classification, implementing Support Vector Machine (SVM) and Quantum SVM (QSVM) algorithms. Our findings suggest that the QSVM algorithm outperforms classical SVM on complex datasets, and the performance gap between quantum and classical models increases with dataset complexity, as simple models tend to overfit with complex datasets. While there is still a long way to go in terms of developing quantum hardware with sufficient resources, quantum machine learning holds great potential in areas such as unsupervised learning and generative models. Moving forward, more efforts are needed to explore new quantum learning models that can leverage the power of quantum mechanics to overcome the limitations of classical machine learning.


  • Open Access

    Identifying Historic Buildings over Time through Image Matching

    by Kyriaki A. Tychola, Stamatis Chatzistamatis, Eleni Vrochidou, George E. Tsekouras, George A. Papakostas

    The buildings in a city are of great importance. Certain historic buildings are landmarks and indicate the city’s architecture and culture. The buildings over time undergo changes because of various factors, such as structural changes, natural disaster damages, and aesthetic interventions. The form of buildings in each period is perceived and understood by people of each generation, through photography. Nevertheless, each photograph has its own characteristics depending on the camera (analog or digital) used for capturing it. Any photo, even depicting the same object, is impossible to capture in the same way in terms of illumination, viewing angle, and scale. Hence, to study two or more photographs depicting the same object, first they should be identified and then properly matched. Nowadays, computer vision contributes to this process by providing useful tools. In particular, for this purpose, several feature detection and description algorithms of homologous points have been developed. In this study, the identification of historic buildings over time through feature correspondence techniques and methods is investigated. Especially, photographs from landmarks of Drama city, in Greece, on different dates and conditions (weather, light, rotation, scale, etc.), were gathered and experiments on 2D pairs of images, implementing traditional feature detectors and descriptors algorithms, such as SIFT, ORB, and BRISK, were carried out. This study aims to evaluate the feature matching procedure focusing on both the algorithms’ performance (accuracy, efficiency, and robustness) and the identification of the buildings. SIFT and BRISK are the most accurate algorithms while ORB and BRISK are the most efficient.


  • Open Access

    On 3D Reconstruction Using RGB-D Cameras

    by Kyriaki A. Tychola, Ioannis Tsimperidis, George A. Papakostas

    The representation of the physical world is an issue that concerns the scientific community studying computer vision, more and more. Recently, research has focused on modern techniques and methods of photogrammetry and stereoscopy with the aim of reconstructing three-dimensional realistic models with high accuracy and metric information in a short time. In order to obtain data at a relatively low cost, various tools have been developed, such as depth cameras. RGB-D cameras are novel sensing systems that capture RGB images along with per-pixel depth information. This survey aims to describe RGB-D camera technology. We discuss the hardware and data acquisition process, in both static and dynamic environments. Depth map sensing techniques are described, focusing on their features, pros, cons, and limitations; emerging challenges and open issues to investigate are analyzed; and some countermeasures are described. In addition, the advantages, disadvantages, and limitations of RGB-D cameras in all aspects are also described critically. This survey will be useful for researchers who want to acquire, process, and analyze the data collected.


  • Open Access

    eCAD System Design - Applications in Architecture

    by Athanasios D. Styliadis, Debbie G. Konstantinidou, Kyriaki A. Tyxola

    The rapid advances in learning technologies, computer modeling, multimedia and spatial sciences, as well as the availability of many powerful graphics PCs and workstations, make 3-D modeling-based methods for personalized e-learning with eCAD (modeling) functionality feasible. Personalized eCAD learning is a new term in engineering, environment and architecture education, related to the development of learning educational units (3-D learning objects) with re-usable digital architecture functionality, and introduced to literature for the first time within this paper. In particular, for university education courses in eCAD, digital architecture, design computing and CAAD (reagarding spatial information systems, architectures, monuments, cultural heritage sites, etc.), such a e-learning methodolgy must be able to derive spatial, pictorial, geometric, spatial, topological, learning and semantic information from the target object (a 3-D model) or scene (a 3-D landscape environment) or procedure (a 3-D simulation approach to a phenomenon), in such a way that it can be directly used for e-learning purposes regarding the spatial topology, the history, the architecture, the structure and the temporal (time-based) 3-D geometry of the projected object, scene or procedure. This paper is about the system design of such a e-learning method. For this purpose, the requirements, objectives and pedagogical extensions are presented and discussed. Finaly, a practical project is used to demonstrate the functionality and the performance of the proposed methodology in architecture