A5075572639- Data Quality and Management
- Semantic Web and Ontologies
- Advanced Database Systems and Queries
- Data Mining Algorithms and Applications
- Traffic Prediction and Management Techniques
- E-Government and Public Services
- Explainable Artificial Intelligence (XAI)
- Anomaly Detection Techniques and Applications
- Social Media and Politics
- Service-Oriented Architecture and Web Services
- Energy Load and Power Forecasting
- Data Analysis with R
- Technology Adoption and User Behaviour
- Housing Market and Economics
- Transportation Planning and Optimization
- Hydrological Forecasting Using AI
- Big Data Technologies and Applications
- Topic Modeling
- Social Policy and Reform Studies
- Digital Marketing and Social Media
- Machine Learning in Healthcare
- Traffic control and management
- Geographic Information Systems Studies
- Insurance and Financial Risk Management
- Stock Market Forecasting Methods
University of Macedonia
2011-2024
Centre for Research and Technology Hellas
2021-2023
Traffic forecasting has been an important area of research for several decades, with significant implications urban traffic planning, management, and control. In recent years, deep-learning models, such as graph neural networks (GNN), have shown great promise in due to their ability capture complex spatio–temporal dependencies within networks. Additionally, public authorities around the world started providing real-time data open-government (OGD). This large volume dynamic high-value can...
Dynamic data (including environmental, traffic, and sensor data) were recently recognized as an important part of Open Government Data (OGD). Although these are vital importance in the development intelligence applications, such business applications that exploit traffic to predict demand, they prone quality errors produced by, e.g., failures sensors network faults. This paper explores Data. To end, a single case is studied using from official Greek OGD portal. The portal uses Application...
An important part of Open Data is a statistical nature and describes economic social indicators monitoring population size, inflation, trade, employment. Combining analyzing from multiple datasets sources enable the performance advanced data analytics scenarios that could result in valuable services products. However, it still difficult to discover combine Statistical reside different portals. Although Linked (LOSD) provide standards approaches facilitate combining statistics on Web, various...
Open Government Data (OGD), including statistical data, such as economic, environmental and social indicators, are data published by the public sector for free reuse. These have a huge potential when exploited using Machine Learning methods. Linked technologies facilitate retrieving integrated indicators defining executing SPARQL queries. However, available in different temporal spatial granularity levels well units of measurement. This article describes that were retrieved from official...
Large language models possess tremendous natural understanding and generation abilities. However, they often lack the ability to discern between fact fiction, leading factually incorrect responses. Open Government Data are repositories of, times linked, information that is freely available everyone. By combining these two technologies in a proof of concept designed application utilizing GPT3.5 OpenAI model Scottish open statistics portal, we show not only it possible augment large model's...
In the rapidly evolving field of real estate economics, prediction house prices continues to be a complex challenge, intricately tied multitude socio-economic factors. Traditional predictive models often overlook spatial interdependencies that significantly influence housing prices. The objective this study is leverage Graph Neural Networks (GNNs) on open statistics knowledge graphs model these dependencies and predict across Scotland’s 2011 data zones. methodology involves retrieving...
Large language models possess tremendous natural understanding and generation abilities. However, they often lack the ability to discern between fact fiction, leading factually incorrect responses. Open Government Data are repositories of, times linked, information that is freely available everyone. By combining these two technologies in a proof of concept designed application utilizing GPT3.5 OpenAI model Scottish open statistics portal, we show not only it possible augment large model's...
Dynamic data (including environmental, traffic, and sensor generated data) were, recently, recognised as an important part of the Open Government Data (OGD) movement. These are vital importance in development intelligence applications. For example, various business applications exploit traffic to predict, e.g., demand estimated time arrival. However, this type is inherently vulnerable quality errors produced by, failures sensors network faults. The objective paper explore for Towards end, we...
Open traffic data are sensor generated with real-time information about the movement of vehicles on roads and other transportation networks valuable for decisionmaking such as better management. One major challenge these datasets is imputation missing values, which can be addressed using methods that range from statistical to machine learning deep learning. This work investigates effectiveness three namely, self-attention SAITS, GAN-based USGAN, Transformer. Using open collected an...
In the rapidly evolving field of real estate economics, prediction house prices continues to be a complex challenge, intricately tied multitude socio-economic factors. However, traditional predictive models have often overlooked spatial interdependencies that play vital role in shaping housing prices. This study applies Graph Neural Networks (GNNs) on Open Statistics Knowledge Graphs model dependencies and predict across Scotland’s 2011 data zones. To this end, integrated statistical...
In the complex landscape of real estate market, accurately estimating house prices is paramount importance for a wide array stakeholders. While traditional statistical methods have been employed in past, machine learning and deep models are increasingly demonstrating their efficacy predicting by capturing intricate patterns relationships between features housing such as neighborhood characteristics geographical proximity to amenities. Recently, Graph Neural Networks shown great performance...