Constantinos Costa
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
Constantinos Costa has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Panos K. Chrysanthis
University of Pittsburgh
9 shared publications - Demetrios Zeinalipour-Yazti
University of Cyprus
5 shared publications - Andreas Konstantinidis
Frederick Research Center, Nicosia, Cyprus
4 shared publications - Herodotos Herodotou
Cyprus University of Technology
3 shared publications - Marios Costa
Rinnoco Ltd, Limassol, 3047, Cyprus
3 shared publications Andreas Charalampous
University of Cyprus
2 shared publications
Latest Publications
- Open Access
- 8 September 2026
- Published by CERN in Open Research Europe
A Multiple Compression Approach using Attribute-based Signatures
Background With the increasing volume of data collected for advanced analytical and AI applications, data storage remains a significant challenge. Despite advancements in storage technologies, the cost of maintaining vast datasets continues to grow. Compression techniques have been widely used to address this issue, but existing systems primarily rely on a single, typically lossless method, which limits adaptability to varying data characteristics. Methods This paper introduces COMPASS, a multiple compression approach that applies different compression techniques to distinct subsets of data within a database. COMPASS partitions relational data into rows or columns and selects the most suitable compression scheme for each column or column group. Two versions of COMPASS are proposed: (i) COMPASS-D, which utilizes K-Means clustering based on data values; and (ii) COMPASS-E, which employs K-Means clustering based on column entropy to group similar columns efficiently. The effectiveness of COMPASS is evaluated using the Envmon dataset, a real-world environmental monitoring database, and compared against monolithic compression methods. Results Experimental results demonstrate that COMPASS significantly reduces disk space usage compared to traditional compression techniques. COMPASS-E achieves superior performance in terms of compression time and proximity to the optimal compression ratio, outperforming COMPASS-D. In worst-case scenarios, COMPASS methods offer 22% more savings compared to baseline techniques, with best-case savings reaching 56% (~2× improvement). Conclusion The proposed COMPASS framework offers a flexible and adaptive approach to database compression by leveraging multiple schemes tailored to different data subsets. This results in improved storage efficiency and reduced computational overhead. Future work will explore additional data characteristics and clustering methods to further enhance COMPASS’s adaptability and efficiency.
- 8 September 2026
- Published by CERN in Open Research Europe
Open AccessA Multiple Compression Approach using Attribute-based Signatures
Background With the increasing volume of data collected for advanced analytical and AI applications, data storage remains a significant challenge. Despite advancements in storage technologies, the cost of maintaining vast datasets continues to grow. Compression techniques have been widely used to address this issue, but existing systems primarily rely on a single, typically lossless method, which limits adaptability to varying data characteristics. Methods This paper introduces COMPASS, a multiple compression approach that applies different compression techniques to distinct subsets of data within a database. COMPASS partitions relational data into rows or columns and selects the most suitable compression scheme for each column or column group. Two versions of COMPASS are proposed: (i) COMPASS-D, which utilizes K-Means clustering based on data values; and (ii) COMPASS-E, which employs K-Means clustering based on column entropy to group similar columns efficiently. The effectiveness of COMPASS is evaluated using the Envmon dataset, a real-world environmental monitoring database, and compared against monolithic compression methods. Results Experimental results demonstrate that COMPASS significantly reduces disk space usage compared to traditional compression techniques. COMPASS-E achieves superior performance in terms of compression time and proximity to the optimal compression ratio, outperforming COMPASS-D. In worst-case scenarios, COMPASS methods offer 22% more savings compared to baseline techniques, with best-case savings reaching 56% (~2× improvement). Conclusion The proposed COMPASS framework offers a flexible and adaptive approach to database compression by leveraging multiple schemes tailored to different data subsets. This results in improved storage efficiency and reduced computational overhead. Future work will explore additional data characteristics and clustering methods to further enhance COMPASS’s adaptability and efficiency.
- Open Access
- 12 June 2026
- Published by Springer Nature in The European Physical Journal C
- Vol. 86 (6)
Fine-tunings and renormalization of gluino bilinear operators in lattice SYM with stout-smeared links
In this paper, we compute the renormalization factors for the gluino and gluon fields, the gauge parameter, the coupling constant, as well as the scalar, pseudoscalar, and axial-vector gluino bilinear operators in $${\mathcal {N}} =1$$ supersymmetric Yang–Mills (SYM) theory, using improved lattice actions. Our lattice formulation employs clover fermions, a Symanzik-improved gauge action, and stout-smeared links, which suppress ultraviolet fluctuations and thus enable more accurate determinations of renormalization factors. Our methodology involves computing gauge-variant two-point and three-point Green’s functions at one-loop order in lattice perturbation theory, in order to extract the multiplicative renormalization factors and the critical gluino mass. By analyzing lattice discretization effects on the axial current and their dependence on the stout-smearing and clover parameters, we identify a value of the smearing parameter that ensures axial-current conservation at one loop. The results presented in this work provide practical guidance for the fine-tuning procedures required to set up and calibrate lattice simulations of SYM.- 12 June 2026
- Published by Springer Nature in The European Physical Journal C
- Vol. 86 (6)
Open AccessFine-tunings and renormalization of gluino bilinear operators in lattice SYM with stout-smeared links
In this paper, we compute the renormalization factors for the gluino and gluon fields, the gauge parameter, the coupling constant, as well as the scalar, pseudoscalar, and axial-vector gluino bilinear operators in $${\mathcal {N}} =1$$ supersymmetric Yang–Mills (SYM) theory, using improved lattice actions. Our lattice formulation employs clover fermions, a Symanzik-improved gauge action, and stout-smeared links, which suppress ultraviolet fluctuations and thus enable more accurate determinations of renormalization factors. Our methodology involves computing gauge-variant two-point and three-point Green’s functions at one-loop order in lattice perturbation theory, in order to extract the multiplicative renormalization factors and the critical gluino mass. By analyzing lattice discretization effects on the axial current and their dependence on the stout-smearing and clover parameters, we identify a value of the smearing parameter that ensures axial-current conservation at one loop. The results presented in this work provide practical guidance for the fine-tuning procedures required to set up and calibrate lattice simulations of SYM. - Open Access
- 10 February 2025
- Published by CERN in Open Research Europe
- Vol. 5, 49
A Multiple Compression Approach using Attribute-based Signatures
Background With the increasing volume of data collected for advanced analytical and AI applications, data storage remains a significant challenge. Despite advancements in storage technologies, the cost of maintaining vast datasets continues to grow. Compression techniques have been widely used to address this issue, but existing systems primarily rely on a single, typically lossless method, which limits adaptability to varying data characteristics. Methods This paper introduces COMPASS, a multiple compression approach that applies different compression techniques to different subsets of data within a database. COMPASS partitions relational data into rows or columns and selects the most suitable compression scheme for individual columns or column groups. Two versions of COMPASS are proposed: (i) COMPASS-D, which utilizes K-Means clustering based on data values; and (ii) COMPASS-E, which employs K-Means clustering based on column entropy to group similar columns efficiently. The effectiveness of COMPASS is evaluated using the Envmon dataset, a real-world environmental monitoring database, and compared against monolithic compression methods. Results Experimental results demonstrate that COMPASS significantly reduces disk space usage compared to traditional compression techniques. COMPASS-E achieves superior performance in terms of compression time and proximity to the optimal compression ratio, outperforming COMPASS-D. In worst-case scenarios, COMPASS methods offer 22% more savings compared to baseline techniques, with best-case savings reaching 56% (~2× improvement). Conclusion The proposed COMPASS framework offers a flexible and adaptive approach to database compression by leveraging multiple schemes tailored to different data subsets. This results in improved storage efficiency and reduced computational overhead. Future work will explore additional data characteristics and clustering methods to further enhance COMPASS’s adaptability and efficiency.
- 10 February 2025
- Published by CERN in Open Research Europe
- Vol. 5, 49
Open AccessA Multiple Compression Approach using Attribute-based Signatures
Background With the increasing volume of data collected for advanced analytical and AI applications, data storage remains a significant challenge. Despite advancements in storage technologies, the cost of maintaining vast datasets continues to grow. Compression techniques have been widely used to address this issue, but existing systems primarily rely on a single, typically lossless method, which limits adaptability to varying data characteristics. Methods This paper introduces COMPASS, a multiple compression approach that applies different compression techniques to different subsets of data within a database. COMPASS partitions relational data into rows or columns and selects the most suitable compression scheme for individual columns or column groups. Two versions of COMPASS are proposed: (i) COMPASS-D, which utilizes K-Means clustering based on data values; and (ii) COMPASS-E, which employs K-Means clustering based on column entropy to group similar columns efficiently. The effectiveness of COMPASS is evaluated using the Envmon dataset, a real-world environmental monitoring database, and compared against monolithic compression methods. Results Experimental results demonstrate that COMPASS significantly reduces disk space usage compared to traditional compression techniques. COMPASS-E achieves superior performance in terms of compression time and proximity to the optimal compression ratio, outperforming COMPASS-D. In worst-case scenarios, COMPASS methods offer 22% more savings compared to baseline techniques, with best-case savings reaching 56% (~2× improvement). Conclusion The proposed COMPASS framework offers a flexible and adaptive approach to database compression by leveraging multiple schemes tailored to different data subsets. This results in improved storage efficiency and reduced computational overhead. Future work will explore additional data characteristics and clustering methods to further enhance COMPASS’s adaptability and efficiency.
- 10 May 2024
- Published by Springer Nature in Distributed and Parallel Databases
- Vol. 42 (3) , 403-445
A blockchain datastore for scalable IoT workloads using data decaying
- 10 May 2024
- Published by Springer Nature in Distributed and Parallel Databases
- Vol. 42 (3) , 403-445
A blockchain datastore for scalable IoT workloads using data decaying
- 2 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Sustainable Computing
- Vol. 10 (1) , 70-81
A Sustainable Energy Management Framework for Smart Homes
The escalating global energy crisis and the increasing CO 2 emissions have necessitated the optimization of energy efficiency. The proliferation of Internet of Things (IoT) devices, expected to reach 100 billion by 2030, contributed to this energy crisis and subsequently to the global CO 2 emissions increase. Concomitantly, climate and energy targets have paved the way for an escalating adoption of solar photovoltaic power generation in residences. The IoT integration into home energy management systems holds the potential to yield energy and peak demand savings. Optimizing device planning to mitigate CO 2 emissions poses significant challenges due to the complexity of user-defined preferences and consumption patterns. In this paper, we propose an innovative IoT data platform, coined Sustainable Energy Management Framework (SEMF) , which aims to balance the trade-off between the imported energy from the grid, users' comfort, and CO 2 emissions. SEMF incorporates a Green Planning evolutionary algorithm, coined GreenCap$^+$ , to facilitate load shifting of IoT-enabled devices, taking into consideration the integration of renewable energy sources, multiple constraints, peak-demand times, and dynamic pricing. Based on our experimental evaluation utilizing real-world data, our prototype system has outperformed the state-of-the-art approach by up to$\approx$ 29% reduction in imported energy,$\approx$ 35% increase in self-consumption of renewable energy, and$\approx$ 34% decrease in CO 2 emissions, while maintaining a high level of user comfort$\approx$ 94%-99%.- 2 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Sustainable Computing
- Vol. 10 (1) , 70-81
A Sustainable Energy Management Framework for Smart Homes
The escalating global energy crisis and the increasing CO 2 emissions have necessitated the optimization of energy efficiency. The proliferation of Internet of Things (IoT) devices, expected to reach 100 billion by 2030, contributed to this energy crisis and subsequently to the global CO 2 emissions increase. Concomitantly, climate and energy targets have paved the way for an escalating adoption of solar photovoltaic power generation in residences. The IoT integration into home energy management systems holds the potential to yield energy and peak demand savings. Optimizing device planning to mitigate CO 2 emissions poses significant challenges due to the complexity of user-defined preferences and consumption patterns. In this paper, we propose an innovative IoT data platform, coined Sustainable Energy Management Framework (SEMF) , which aims to balance the trade-off between the imported energy from the grid, users' comfort, and CO 2 emissions. SEMF incorporates a Green Planning evolutionary algorithm, coined GreenCap$^+$ , to facilitate load shifting of IoT-enabled devices, taking into consideration the integration of renewable energy sources, multiple constraints, peak-demand times, and dynamic pricing. Based on our experimental evaluation utilizing real-world data, our prototype system has outperformed the state-of-the-art approach by up to$\approx$ 29% reduction in imported energy,$\approx$ 35% increase in self-consumption of renewable energy, and$\approx$ 34% decrease in CO 2 emissions, while maintaining a high level of user comfort$\approx$ 94%-99%.- Open Access
- 23 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 121-130
Recommending the Least Congested Indoor-Outdoor Paths without Ignoring Time
The exposure to viral airborne diseases is higher in crowded and congested spaces, the COVID-19 pandemic has revealed the need of pedestrian recommendation systems that can recommend less congested paths which minimize exposure to infectious crowd diseases in general. In this paper, we introduce ASTRO-C, an extension of previous work ASTRO, which optimizes for minimum congestion. To our knowledge, ASTRO-C is the only solution to this problem of constraint-satisfying, indoor-outdoor, congestion-based path finding. Our experimental evaluation using randomly generated Indoor-Outdoor graphs with varying constraints matching various real-world scenarios, show that ASTRO-C is able to recommend paths with, on average a 0.62X reduction in average congestion, while on average, total travel time increases by 1.06X and never exceeds 1.10X compared to ASTRO.
- 23 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 121-130
Open AccessRecommending the Least Congested Indoor-Outdoor Paths without Ignoring Time
The exposure to viral airborne diseases is higher in crowded and congested spaces, the COVID-19 pandemic has revealed the need of pedestrian recommendation systems that can recommend less congested paths which minimize exposure to infectious crowd diseases in general. In this paper, we introduce ASTRO-C, an extension of previous work ASTRO, which optimizes for minimum congestion. To our knowledge, ASTRO-C is the only solution to this problem of constraint-satisfying, indoor-outdoor, congestion-based path finding. Our experimental evaluation using randomly generated Indoor-Outdoor graphs with varying constraints matching various real-world scenarios, show that ASTRO-C is able to recommend paths with, on average a 0.62X reduction in average congestion, while on average, total travel time increases by 1.06X and never exceeds 1.10X compared to ASTRO.
- Open Access
- 3 June 2023
- Published by Springer Nature in Distributed and Parallel Databases
- Vol. 41 (3) , 267-271
Introduction to the special issue on self‑managing and hardware‑optimized database systems 2022
- 3 June 2023
- Published by Springer Nature in Distributed and Parallel Databases
- Vol. 41 (3) , 267-271
Open AccessIntroduction to the special issue on self‑managing and hardware‑optimized database systems 2022
- 1 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 310-313
Efficient Detection of COVID-19 Exposure Risk
In this demo paper, we present the new module of our HealthDist system that performs contact tracing in a privacy-preserving manner and considers the COVID-19 exposure risk. This is achieved by answering a new spatio-temporal query, dubbed ST-Aggregate Join, which calculates the COVID-19 exposure risk of an individual on their devices. It utilizes a special-purpose access structure to record the trajectories of users on their devices and optimize the ST-Aggregate Join processing. We demonstrate interactively using a smartphone application how our system can provide effective contact tracing within a university campus. We also illustrate how our new module is working through an intuitive web interface that shows the exposure risk of a person by coloring the trajectory of the infected person and the person(s) in high risk in a preloaded real dataset.
- 1 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 310-313
Efficient Detection of COVID-19 Exposure Risk
In this demo paper, we present the new module of our HealthDist system that performs contact tracing in a privacy-preserving manner and considers the COVID-19 exposure risk. This is achieved by answering a new spatio-temporal query, dubbed ST-Aggregate Join, which calculates the COVID-19 exposure risk of an individual on their devices. It utilizes a special-purpose access structure to record the trajectories of users on their devices and optimize the ST-Aggregate Join processing. We demonstrate interactively using a smartphone application how our system can provide effective contact tracing within a university campus. We also illustrate how our new module is working through an intuitive web interface that shows the exposure risk of a person by coloring the trajectory of the infected person and the person(s) in high risk in a preloaded real dataset.
- Open Access
- 30 December 2021
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Spatial Algorithms and Systems
- Vol. 8 (2) , 1-31
ASTRO: Reducing COVID-19 Exposure through Contact Prediction and Avoidance
The fight against the COVID-19 pandemic has highlighted the importance and benefits of recommending paths that reduce the exposure to and the spread of the SARS-CoV-2 coronavirus by avoiding crowded indoor or outdoor areas. Existing path discovery techniques are inadequate for coping with such dynamic and heterogeneous (indoor and outdoor) environments—they typically find an optimal path assuming a homogeneous and/or static graph, and hence they cannot be used to support contact avoidance. In this article, we pose the need for Mobile Contact Avoidance Navigation and propose ASTRO ( A ccessible S patio- T emporal R oute O ptimization), a novel graph-based path discovering algorithm that can reduce the risk of COVID-19 exposure by taking into consideration the congestion in indoor spaces. ASTRO operates in an A * manner to find the most promising path for safe movement within and across multiple buildings without constructing the full graph. For its path finding, ASTRO requires predicting congestion in corridors and hallways. Consequently, we propose a new grid-based partitioning scheme combined with a hash-based two-level structure to store congestion models, called CM-Structure , which enables on-the-fly forecasting of congestion in corridors and hallways. We demonstrate the effectiveness of ASTRO and the accuracy of CM-Structure ’s congestion models empirically with realistic datasets, showing up to one order of magnitude reduction in COVID-19 exposure.
- 30 December 2021
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Spatial Algorithms and Systems
- Vol. 8 (2) , 1-31
Open AccessASTRO: Reducing COVID-19 Exposure through Contact Prediction and Avoidance
The fight against the COVID-19 pandemic has highlighted the importance and benefits of recommending paths that reduce the exposure to and the spread of the SARS-CoV-2 coronavirus by avoiding crowded indoor or outdoor areas. Existing path discovery techniques are inadequate for coping with such dynamic and heterogeneous (indoor and outdoor) environments—they typically find an optimal path assuming a homogeneous and/or static graph, and hence they cannot be used to support contact avoidance. In this article, we pose the need for Mobile Contact Avoidance Navigation and propose ASTRO ( A ccessible S patio- T emporal R oute O ptimization), a novel graph-based path discovering algorithm that can reduce the risk of COVID-19 exposure by taking into consideration the congestion in indoor spaces. ASTRO operates in an A * manner to find the most promising path for safe movement within and across multiple buildings without constructing the full graph. For its path finding, ASTRO requires predicting congestion in corridors and hallways. Consequently, we propose a new grid-based partitioning scheme combined with a hash-based two-level structure to store congestion models, called CM-Structure , which enables on-the-fly forecasting of congestion in corridors and hallways. We demonstrate the effectiveness of ASTRO and the accuracy of CM-Structure ’s congestion models empirically with realistic datasets, showing up to one order of magnitude reduction in COVID-19 exposure.
- 1 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 217-224
A Context, Location and Preference-Aware System for Safe Pedestrian Mobility
The COVID-19 pandemic poses new challenges in providing safe pedestrian navigation information that helps to reduce the risk of severe illness due to the highly contagious nature of the virus. In this paper, we present an innovative system, dubbed HealthDist, which utilizes the context (e.g., weather conditions), location (e.g., crowded areas) and user’s preferences to support safe mobility. It consists of four modules that allow efficient contact tracing, social distancing, and isolation. HealthDist’s modular design reduces the time and resources needed to provide accurate localization for measuring density in common spaces and measuring potential infection exposure, and recommend outdoor and indoor paths satisfying the user’s preferences. HealthDist’s initial deployment within a university campus demonstrated its capability to provide real time navigation information that reduces the COVID-19 exposure risk while at the same time satisfying the constraints defined by the user.
- 1 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 217-224
A Context, Location and Preference-Aware System for Safe Pedestrian Mobility
The COVID-19 pandemic poses new challenges in providing safe pedestrian navigation information that helps to reduce the risk of severe illness due to the highly contagious nature of the virus. In this paper, we present an innovative system, dubbed HealthDist, which utilizes the context (e.g., weather conditions), location (e.g., crowded areas) and user’s preferences to support safe mobility. It consists of four modules that allow efficient contact tracing, social distancing, and isolation. HealthDist’s modular design reduces the time and resources needed to provide accurate localization for measuring density in common spaces and measuring potential infection exposure, and recommend outdoor and indoor paths satisfying the user’s preferences. HealthDist’s initial deployment within a university campus demonstrated its capability to provide real time navigation information that reduces the COVID-19 exposure risk while at the same time satisfying the constraints defined by the user.