Ioannis Filippopoulos
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
Ioannis Filippopoulos has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
Georgios Stamoulis
4 shared publications- Yiannis Kiouvrekis
Mathematics, Computer Science and Artificial Intelligence Laboratory (MCSAI Lab), Department of Public and One Health, University of Thessaly, 43100 Karditsa, Greece
4 shared publications Mark Pearson
Maran Tankers Management Inc.,216-226, Doiranis Street, Kallithea,Greece,17674
3 shared publications- Sotiris Zikas
Mathematics, Computer Science and Artificial Intelligence Laboratory, Faculty of Public and One Health, University of Thessaly, 43100 Karditsa, Greece
3 shared publications - Theodor Panagiotakopoulos
Department of Management Science and Technology, University of Patras, 26504 Patras, Greece
3 shared publications Zoran Lajic
Maran Tankers Management Inc.,Fleet Performance Department,216-226, Doiranis Street, Kallithea,Greece,17674
3 shared publications
Latest Publications
- Open Access
- 24 June 2025
- Published by MDPI AG in Electronics
- Vol. 14 (13) , 2561
Explainable AI Models for IoT-Based Shaft Power Prediction and Comprehensive Performance Monitoring
This paper presents a comparative analysis of machine learning-based methods for predicting shaft power in ships, a key factor in optimizing ship performance. Accurate shaft power prediction facilitates efficient operations, reducing fuel consumption, emissions, and maintenance costs, aligning with environmental regulations and promoting sustainable maritime practices. The proposed approach evaluates three machine learning methods, analyzing 431 models to determine the most accurate and reliable option for VLCC tankers. XGBoost emerged as the top-performing model, delivering a 13% improvement in accuracy over traditional methods. Using the SHAP framework, key factors influencing shaft power predictions—such as GPS speed, draft, days from dry dock, and wave height—were identified, enhancing model transparency and decision-making clarity. This explainability fosters trust in the use of AI within marine engineering. The results demonstrate that machine learning can optimize maintenance scheduling by reducing unnecessary cleaning procedures, mitigating propulsion system wear, and improving reliability. By using predictive insights, ship operators can achieve better fuel efficiency, lower emissions, and cost savings. The study underscores the potential of explainable machine learning models as transformative tools for ship performance monitoring, supporting greener and more efficient maritime operations.
- 24 June 2025
- Published by MDPI AG in Electronics
- Vol. 14 (13) , 2561
Open AccessExplainable AI Models for IoT-Based Shaft Power Prediction and Comprehensive Performance Monitoring
This paper presents a comparative analysis of machine learning-based methods for predicting shaft power in ships, a key factor in optimizing ship performance. Accurate shaft power prediction facilitates efficient operations, reducing fuel consumption, emissions, and maintenance costs, aligning with environmental regulations and promoting sustainable maritime practices. The proposed approach evaluates three machine learning methods, analyzing 431 models to determine the most accurate and reliable option for VLCC tankers. XGBoost emerged as the top-performing model, delivering a 13% improvement in accuracy over traditional methods. Using the SHAP framework, key factors influencing shaft power predictions—such as GPS speed, draft, days from dry dock, and wave height—were identified, enhancing model transparency and decision-making clarity. This explainability fosters trust in the use of AI within marine engineering. The results demonstrate that machine learning can optimize maintenance scheduling by reducing unnecessary cleaning procedures, mitigating propulsion system wear, and improving reliability. By using predictive insights, ship operators can achieve better fuel efficiency, lower emissions, and cost savings. The study underscores the potential of explainable machine learning models as transformative tools for ship performance monitoring, supporting greener and more efficient maritime operations.
- Open Access
- 17 June 2025
- Published by MDPI AG in Future Internet
- Vol. 17 (6) , 264
An Explainable Machine Learning Approach for IoT-Supported Shaft Power Estimation and Performance Analysis for Marine Vessels
In the evolving landscape of green shipping, the accurate estimation of shaft power is critical for reducing fuel consumption and greenhouse gas emissions. This study presents an explainable machine learning framework for shaft power prediction, utilising real-world Internet of Things (IoT) sensor data collected from nine (9) Very Large Crude Carriers (VLCCs) over a 36-month period. A diverse set of models—ranging from traditional algorithms such as Decision Trees and Support Vector Machines to advanced ensemble methods like XGBoost and LightGBM—were developed and evaluated. Model performance was assessed using the coefficient of determination () and RMSE, with XGBoost achieving the highest accuracy (, RMSE 888) and LightGBM being close behind (, RMSE 902), with both substantially exceeding the industry baseline model (, RMSE 1500). Explainability was integrated through SHapley Additive exPlanations (SHAP), offering detailed insights into the influence of each input variable. Features such as draft, GPS speed, and time since last dry dock consistently emerged as key predictors. The results demonstrate the robustness and interpretability of tree-based methods, offering a data-driven alternative to traditional performance estimation techniques and supporting the maritime industry’s transition toward more efficient and sustainable operations.- 17 June 2025
- Published by MDPI AG in Future Internet
- Vol. 17 (6) , 264
Open AccessAn Explainable Machine Learning Approach for IoT-Supported Shaft Power Estimation and Performance Analysis for Marine Vessels
In the evolving landscape of green shipping, the accurate estimation of shaft power is critical for reducing fuel consumption and greenhouse gas emissions. This study presents an explainable machine learning framework for shaft power prediction, utilising real-world Internet of Things (IoT) sensor data collected from nine (9) Very Large Crude Carriers (VLCCs) over a 36-month period. A diverse set of models—ranging from traditional algorithms such as Decision Trees and Support Vector Machines to advanced ensemble methods like XGBoost and LightGBM—were developed and evaluated. Model performance was assessed using the coefficient of determination () and RMSE, with XGBoost achieving the highest accuracy (, RMSE 888) and LightGBM being close behind (, RMSE 902), with both substantially exceeding the industry baseline model (, RMSE 1500). Explainability was integrated through SHapley Additive exPlanations (SHAP), offering detailed insights into the influence of each input variable. Features such as draft, GPS speed, and time since last dry dock consistently emerged as key predictors. The results demonstrate the robustness and interpretability of tree-based methods, offering a data-driven alternative to traditional performance estimation techniques and supporting the maritime industry’s transition toward more efficient and sustainable operations. - Open Access
- 30 April 2025
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 13 (5) , 894
Digital Transformation in the Shipping Industry: A Network-Based Bibliometric Analysis
This paper presents a network-based bibliometric analysis of digital transformation in the shipping industry, a sector undergoing rapid change due to advancements in automation, artificial intelligence, blockchain, and Internet of Things. The study synthesizes existing knowledge to identify trends, challenges, and opportunities for industry stakeholders and researchers. Unlike previous literature reviews, this work adopts a graph theory approach applied to a large dataset of scientific publications, without predefined technological or industrial sub-domains. Data were collected from EBSCO, ProQuest, and IEEE eXplore, then refined using OpenAlex to comprise 2293 scientific publications. The analysis includes descriptive statistics, co-authorship network analysis, co-citation network analysis, and thematic analysis. The findings reveal a significant increase in publications since 2005, with exponential growth after 2015. They also suggest a potential inflection point after 2024. A small percentage of authors and institutions account for a disproportionate share of publications, suggesting a skewed distribution of research efforts and encouraging funding agencies to broaden maritime research worldwide. The co-authorship network exhibits a heavy-tail distribution and interconnected communities, indicating extensive national and international collaborations. The co-citation analysis identifies key research areas such as fuel consumption optimization, safety and risk management, and smart port development. Thematic analysis highlights the growing importance of artificial intelligence and cybersecurity.
- 30 April 2025
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 13 (5) , 894
Open AccessDigital Transformation in the Shipping Industry: A Network-Based Bibliometric Analysis
This paper presents a network-based bibliometric analysis of digital transformation in the shipping industry, a sector undergoing rapid change due to advancements in automation, artificial intelligence, blockchain, and Internet of Things. The study synthesizes existing knowledge to identify trends, challenges, and opportunities for industry stakeholders and researchers. Unlike previous literature reviews, this work adopts a graph theory approach applied to a large dataset of scientific publications, without predefined technological or industrial sub-domains. Data were collected from EBSCO, ProQuest, and IEEE eXplore, then refined using OpenAlex to comprise 2293 scientific publications. The analysis includes descriptive statistics, co-authorship network analysis, co-citation network analysis, and thematic analysis. The findings reveal a significant increase in publications since 2005, with exponential growth after 2015. They also suggest a potential inflection point after 2024. A small percentage of authors and institutions account for a disproportionate share of publications, suggesting a skewed distribution of research efforts and encouraging funding agencies to broaden maritime research worldwide. The co-authorship network exhibits a heavy-tail distribution and interconnected communities, indicating extensive national and international collaborations. The co-citation analysis identifies key research areas such as fuel consumption optimization, safety and risk management, and smart port development. Thematic analysis highlights the growing importance of artificial intelligence and cybersecurity.
- Open Access
- 28 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 75104-75122
Explainable Machine Learning for Radio Environment Mapping: An Intelligent System for Electric Field Strength Monitoring
The accurate characterization of signal propagation is critical for optimizing wireless network performance and supporting applications such as electromagnetic field (EMF) exposure assessment and the development of Radio Environmental Maps (REMs). This study proposes a novel, explainable machine learning system to predict electric field strength across diverse urban, semi-urban, and rural environments in Cyprus. The system is trained on a rich dataset comprising 6,543 EMF measurements collected in 2023 at mobile phone and digital TV stations, following CEPT/ECC/REC/(02)04 recommendations. The dataset includes geospatial and environmental features such as antenna distance, population density, urbanization level, and detailed built environment characteristics (e.g., volume, surface, and height). We evaluate multiple machine learning models—kNN, neural networks, decision trees, random forests, XGBoost, and LightGBM—using a two-semester split for training and assessment. Best performance was achieved with the Random Forest model, which yielded the lowest RMSE among all models. Gradient boosting models (XGBoost and LightGBM) also performed well, with RMSE values slightly higher than RF while offering flexible and scalable configurations. In contrast, k-NN and neural networks showed higher RMSE values, indicating they were less effective for this specific task. Across all models, confidence intervals were narrow, demonstrating stable and reliable predictions. Explainable AI techniques revealed that antenna distance, building volume, and population density are the most influential predictors of EMF intensity. Our approach outperforms traditional signal models by incorporating urban morphology and demographic context. As part of this system, we also create a Geographic Information System (GIS) that displays electromagnetic field strength maps derived from our explainable machine learning models. This contributes a scalable, interpretable framework for EMF exposure mapping to support regulatory monitoring, urban planning, and smart city initiatives.
- 28 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 75104-75122
Open AccessExplainable Machine Learning for Radio Environment Mapping: An Intelligent System for Electric Field Strength Monitoring
The accurate characterization of signal propagation is critical for optimizing wireless network performance and supporting applications such as electromagnetic field (EMF) exposure assessment and the development of Radio Environmental Maps (REMs). This study proposes a novel, explainable machine learning system to predict electric field strength across diverse urban, semi-urban, and rural environments in Cyprus. The system is trained on a rich dataset comprising 6,543 EMF measurements collected in 2023 at mobile phone and digital TV stations, following CEPT/ECC/REC/(02)04 recommendations. The dataset includes geospatial and environmental features such as antenna distance, population density, urbanization level, and detailed built environment characteristics (e.g., volume, surface, and height). We evaluate multiple machine learning models—kNN, neural networks, decision trees, random forests, XGBoost, and LightGBM—using a two-semester split for training and assessment. Best performance was achieved with the Random Forest model, which yielded the lowest RMSE among all models. Gradient boosting models (XGBoost and LightGBM) also performed well, with RMSE values slightly higher than RF while offering flexible and scalable configurations. In contrast, k-NN and neural networks showed higher RMSE values, indicating they were less effective for this specific task. Across all models, confidence intervals were narrow, demonstrating stable and reliable predictions. Explainable AI techniques revealed that antenna distance, building volume, and population density are the most influential predictors of EMF intensity. Our approach outperforms traditional signal models by incorporating urban morphology and demographic context. As part of this system, we also create a Geographic Information System (GIS) that displays electromagnetic field strength maps derived from our explainable machine learning models. This contributes a scalable, interpretable framework for EMF exposure mapping to support regulatory monitoring, urban planning, and smart city initiatives.
- Open Access
- 9 January 2025
- Published by MDPI AG in Electronics
- Vol. 14 (2) , 254
Explainable Machine Learning-Based Electric Field Strength Mapping for Urban Environmental Monitoring: A Case Study in Paris Integrating Geographical Features and Explainable AI
The objective of this study is to determine the optimal machine learning model for constructing electric field strength maps across urban areas, advancing the field of environmental monitoring. These models are unique because they use a detailed dataset that goes beyond electromagnetic readings, incorporating information like population density, urbanization levels, and building characteristics. This novel approach, combined with explainable AI, helps identify the key factors affecting electromagnetic exposure. The models enable the creation of highly detailed and dynamic maps of electromagnetic pollution. These maps are not just static snapshots, they can track changes over time, evaluate the success of mitigation efforts, and provide deeper insights into how electromagnetic fields are distributed in urban areas. To construct a detailed electric field strength map, we conducted an extensive analysis using 410 machine learning models across the urban area of Paris, incorporating three fundamental approaches: k-nearest neighbors, neural networks, and decision trees. This comprehensive exploration allowed us to evaluate and optimize various model configurations, ensuring robust and accurate predictions of electric field strength across diverse urban environments. The kNN model exhibited the most consistent performance, with an RMSE of and an SD of . The analysis indicates that kNN outperforms simple neural networks and decision trees in terms of both RMSE and performance stability. From the SHAP analysis, we conclude that the feature representing the total volume of buildings in the area around each antenna (V) is the most significant in predicting electromagnetic field strength in the kNN regression model, consistently showing a high impact across predictions. The population density feature (POP) also demonstrates considerable influence.- 9 January 2025
- Published by MDPI AG in Electronics
- Vol. 14 (2) , 254
Open AccessExplainable Machine Learning-Based Electric Field Strength Mapping for Urban Environmental Monitoring: A Case Study in Paris Integrating Geographical Features and Explainable AI
The objective of this study is to determine the optimal machine learning model for constructing electric field strength maps across urban areas, advancing the field of environmental monitoring. These models are unique because they use a detailed dataset that goes beyond electromagnetic readings, incorporating information like population density, urbanization levels, and building characteristics. This novel approach, combined with explainable AI, helps identify the key factors affecting electromagnetic exposure. The models enable the creation of highly detailed and dynamic maps of electromagnetic pollution. These maps are not just static snapshots, they can track changes over time, evaluate the success of mitigation efforts, and provide deeper insights into how electromagnetic fields are distributed in urban areas. To construct a detailed electric field strength map, we conducted an extensive analysis using 410 machine learning models across the urban area of Paris, incorporating three fundamental approaches: k-nearest neighbors, neural networks, and decision trees. This comprehensive exploration allowed us to evaluate and optimize various model configurations, ensuring robust and accurate predictions of electric field strength across diverse urban environments. The kNN model exhibited the most consistent performance, with an RMSE of and an SD of . The analysis indicates that kNN outperforms simple neural networks and decision trees in terms of both RMSE and performance stability. From the SHAP analysis, we conclude that the feature representing the total volume of buildings in the area around each antenna (V) is the most significant in predicting electromagnetic field strength in the kNN regression model, consistently showing a high impact across predictions. The population density feature (POP) also demonstrates considerable influence. - 1 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 331-338
Transformation of Vessel Performance System into Fault-tolerant Syste - Example of Fault Detection on Speed Log
In this paper fault diagnosis as the first step of system transformation into a fault-tolerant system has been presented. Fault diagnosis means that the existence of faults has to be detected and the faults have to be isolated. As an example, fault detection on the speed log (measurement of speed through the water) and GPS corrected speed (calculated speed through the water by combining the vectors of speed over ground and sea current) has been presented. Furthermore, the influence of hull fouling on the results has been discussed. In order to achieve the final goal, i.e. transformation of the system into a fault-tolerant system, the system must be redesigned. System re-design implies that the system has to be adapted to the faulty situation so that the overall system continues to satisfy its goal. The results of the fault detection from one VLCCs (Very Large Crude Carrier) and one SUEZMAX tanker, with clean and with fouled hull will be shown.
- 1 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 331-338
Transformation of Vessel Performance System into Fault-tolerant Syste - Example of Fault Detection on Speed Log
In this paper fault diagnosis as the first step of system transformation into a fault-tolerant system has been presented. Fault diagnosis means that the existence of faults has to be detected and the faults have to be isolated. As an example, fault detection on the speed log (measurement of speed through the water) and GPS corrected speed (calculated speed through the water by combining the vectors of speed over ground and sea current) has been presented. Furthermore, the influence of hull fouling on the results has been discussed. In order to achieve the final goal, i.e. transformation of the system into a fault-tolerant system, the system must be redesigned. System re-design implies that the system has to be adapted to the faulty situation so that the overall system continues to satisfy its goal. The results of the fault detection from one VLCCs (Very Large Crude Carrier) and one SUEZMAX tanker, with clean and with fouled hull will be shown.
- 1 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 35-40
Multi-Sensor Data Fusion for the Vessel Trim Analyzer and Optimization Platform
The purpose of this paper is to describe a platform and the multi-sensor Data Fusion., that is used to analyze the power consumed regarding the Vessel's trim during past Voyages and to provide decision making support about the trim for futures Voyages. Platform collects data from several resources., including live data from sensors, aggregates, and analyses them. Platform also provides simplified user interfaces and indicators to the maritime company's specialized personnel and the Vessel's Captain and Chief Engineer for best “trimming” selection. Maran Tankers Management Inc. is a maritime company that uses the described platform for more than forty (40) Tanker Vessels.
- 1 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 35-40
Multi-Sensor Data Fusion for the Vessel Trim Analyzer and Optimization Platform
The purpose of this paper is to describe a platform and the multi-sensor Data Fusion., that is used to analyze the power consumed regarding the Vessel's trim during past Voyages and to provide decision making support about the trim for futures Voyages. Platform collects data from several resources., including live data from sensors, aggregates, and analyses them. Platform also provides simplified user interfaces and indicators to the maritime company's specialized personnel and the Vessel's Captain and Chief Engineer for best “trimming” selection. Maran Tankers Management Inc. is a maritime company that uses the described platform for more than forty (40) Tanker Vessels.
- 1 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 280-288
Adaptive GLR Change Detector for Increasing Reliability of Vessel Performance System
In this paper a new adaptive GLR (generalized likelihood ratio) detector which is able to detect the stable periods of the operation of a vessel has been presented. To assess the performance of a vessel, the stable periods of navigation can be used only. Therefore, having only sensor measurements from the stable periods as the inputs to the system is crucial for proper functioning of an auto logged vessel performance monitoring system. Removing the “contaminated” signals by ship maneuvering, changes in the weather condition or vessel speed would lead to an increase of the reliability of the system. The results from two VLCCs (Very Large Crude Carrier) with high and low frequency data will be shown.
- 1 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 280-288
Adaptive GLR Change Detector for Increasing Reliability of Vessel Performance System
In this paper a new adaptive GLR (generalized likelihood ratio) detector which is able to detect the stable periods of the operation of a vessel has been presented. To assess the performance of a vessel, the stable periods of navigation can be used only. Therefore, having only sensor measurements from the stable periods as the inputs to the system is crucial for proper functioning of an auto logged vessel performance monitoring system. Removing the “contaminated” signals by ship maneuvering, changes in the weather condition or vessel speed would lead to an increase of the reliability of the system. The results from two VLCCs (Very Large Crude Carrier) with high and low frequency data will be shown.