Ana Almeida
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
Ana Almeida has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Susana Sargento
University of Aveiro
9 shared publications - Susana Brás
IEETA, DETI, LASI, Universidade de Aveiro, Aveiro, Portugal
8 shared publications - Filipe Cabral Pinto
Altice Labs, 3810-106 Aveiro, Portugal
5 shared publications - Ilídio Oliveira
Universidade de Aveiro
3 shared publications - Pedro Rito
University of Aveiro
3 shared publications Carlos Costa
University of Aveiro, Aveiro, Portugal
1 shared publication
Latest Publications
- Open Access
- 1 January 2025
- Published by Elsevier in Computer Networks
- Vol. 258
Exploring the dynamic symbiosis of urban mobility and 5G networks
- 1 January 2025
- Published by Elsevier in Computer Networks
- Vol. 258
Open AccessExploring the dynamic symbiosis of urban mobility and 5G networks
- Open Access
- 21 October 2024
- Published by Elsevier in Computer Communications
- Vol. 228
A machine learning approach to forecast 5G metrics in a commercial and operational 5G platform: 5G and mobility
- 21 October 2024
- Published by Elsevier in Computer Communications
- Vol. 228
Open AccessA machine learning approach to forecast 5G metrics in a commercial and operational 5G platform: 5G and mobility
- Open Access
- 7 April 2024
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 27 (2) , 1-12
Focalize K-NN: an imputation algorithm for time series datasets
The effective use of time series data is crucial in business decision-making. Temporal data reveals temporal trends and patterns, enabling decision-makers to make informed decisions and prevent potential problems. However, missing values in time series data can interfere with the analysis and lead to inaccurate conclusions. Thus, our work proposes a Focalize K-NN method that leverages time series properties to perform missing data imputation. This approach shows the benefits of taking advantage of correlated features and temporal lags to improve the performance of the traditional K-NN imputer. A similar approach could be employed in other methods. We tested this approach with two datasets, various parameter and feature combinations, and observed that it is beneficial in scenarios with disjoint missing patterns. Our findings demonstrate the effectiveness of Focalize K-NN for imputing missing values in time series data. The more noticeable benefits of our methods occur when there is a high percentage of missing data. However, as the amount of missing data increases, so does the error.
- 7 April 2024
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 27 (2) , 1-12
Open AccessFocalize K-NN: an imputation algorithm for time series datasets
The effective use of time series data is crucial in business decision-making. Temporal data reveals temporal trends and patterns, enabling decision-makers to make informed decisions and prevent potential problems. However, missing values in time series data can interfere with the analysis and lead to inaccurate conclusions. Thus, our work proposes a Focalize K-NN method that leverages time series properties to perform missing data imputation. This approach shows the benefits of taking advantage of correlated features and temporal lags to improve the performance of the traditional K-NN imputer. A similar approach could be employed in other methods. We tested this approach with two datasets, various parameter and feature combinations, and observed that it is beneficial in scenarios with disjoint missing patterns. Our findings demonstrate the effectiveness of Focalize K-NN for imputing missing values in time series data. The more noticeable benefits of our methods occur when there is a high percentage of missing data. However, as the amount of missing data increases, so does the error.
- Open Access
- 11 October 2023
- Published by Elsevier in Journal of Urban Mobility
- Vol. 4
Exploring bus tracking data to characterize urban traffic congestion
- 11 October 2023
- Published by Elsevier in Journal of Urban Mobility
- Vol. 4
Open AccessExploring bus tracking data to characterize urban traffic congestion
- Top Cited PapersOpen Access
- 28 May 2023
- Published by Springer Nature in Journal of Big Data
- Vol. 10 (1) , 1-32
Time series big data: a survey on data stream frameworks, analysis and algorithms
Big data has a substantial role nowadays, and its importance has significantly increased over the last decade. Big data’s biggest advantages are providing knowledge, supporting the decision-making process, and improving the use of resources, services, and infrastructures. The potential of big data increases when we apply it in real-time by providing real-time analysis, predictions, and forecasts, among many other applications. Our goal with this article is to provide a viewpoint on how to build a system capable of processing big data in real-time, performing analysis, and applying algorithms. A system should be designed to handle vast amounts of data and provide valuable knowledge through analysis and algorithms. This article explores the current approaches and how they can be used for the real-time operations and predictions.
- 28 May 2023
- Published by Springer Nature in Journal of Big Data
- Vol. 10 (1) , 1-32
Top Cited PapersOpen AccessTime series big data: a survey on data stream frameworks, analysis and algorithms
Big data has a substantial role nowadays, and its importance has significantly increased over the last decade. Big data’s biggest advantages are providing knowledge, supporting the decision-making process, and improving the use of resources, services, and infrastructures. The potential of big data increases when we apply it in real-time by providing real-time analysis, predictions, and forecasts, among many other applications. Our goal with this article is to provide a viewpoint on how to build a system capable of processing big data in real-time, performing analysis, and applying algorithms. A system should be designed to handle vast amounts of data and provide valuable knowledge through analysis and algorithms. This article explores the current approaches and how they can be used for the real-time operations and predictions.
- Open Access
- 7 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 211-218
Safe Roads: an Integration between Twitter and City Sensing
With the increasing growth of devices connected to the Internet and the evolution of Internet of Things (IoT), the concept of a modern interconnected city is gaining popularity. On the other side, social media is providing citizens and authorities with information near real-time about incidents or events in the city. Therefore, the monitoring of the city and its roads through smart sensing can be coupled with social media to integrate different sources of information and provide better decisions. While some existing works make use of either social media or conveniently located sensors in key spots in a city, our work focuses on creating a platform that analyzes the data from two types of sources - sensors, such as radars and video cameras, and social networks, like Twitter, to find instances of road safety and provide alerts to authorities and the community. This approach is implemented and tested in a real city platform, and results show the different types of alerts received with the integrated platform.
- 7 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 211-218
Open AccessSafe Roads: an Integration between Twitter and City Sensing
With the increasing growth of devices connected to the Internet and the evolution of Internet of Things (IoT), the concept of a modern interconnected city is gaining popularity. On the other side, social media is providing citizens and authorities with information near real-time about incidents or events in the city. Therefore, the monitoring of the city and its roads through smart sensing can be coupled with social media to integrate different sources of information and provide better decisions. While some existing works make use of either social media or conveniently located sensors in key spots in a city, our work focuses on creating a platform that analyzes the data from two types of sources - sensors, such as radars and video cameras, and social networks, like Twitter, to find instances of road safety and provide alerts to authorities and the community. This approach is implemented and tested in a real city platform, and results show the different types of alerts received with the integrated platform.
- 26 April 2022
- Published by Springer Nature
- p. 667-679
Using Bus Tracking Data to Detect Potential Hazard Driving Zones
- 26 April 2022
- Published by Springer Nature
- p. 667-679
Using Bus Tracking Data to Detect Potential Hazard Driving Zones
- 1 March 2022
- Published by Elsevier in Future Generation Computer Systems
- Vol. 128, 429-442
Vehicular traffic flow prediction using deployed traffic counters in a city
- 1 March 2022
- Published by Elsevier in Future Generation Computer Systems
- Vol. 128, 429-442
Vehicular traffic flow prediction using deployed traffic counters in a city
- 16 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1882-1885
NoSQL distributed database for DICOM objects
Every year, the amount of data produced in health-care institutions in the field of medical imaging is increasing. The easy accessibility to digital modalities and the proliferation of diagnosis centers working in network of services, creates the need for very large repositories of data. Moreover, the institutions have redundant storage across the network and load balancing mechanism to improve access performance. NoSQL databases provide horizontal scalability which allows the system to grow easily and effortlessly. Document databases are particularly suitable to store the DICOM metadata and the JSON format is already supported by the standard. This paper, we discuss the use of document database model in the medical imaging field, trying to focus on both clinical and research environments. Moreover, we focused on the proposal of an architecture based on MongoDB to distribute the load between multiple nodes. The proposal was integrated with an open-source PACS and validated by simulating multiple operations over data distributed across multiple virtual locations, and the results are promising.
- 16 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1882-1885
NoSQL distributed database for DICOM objects
Every year, the amount of data produced in health-care institutions in the field of medical imaging is increasing. The easy accessibility to digital modalities and the proliferation of diagnosis centers working in network of services, creates the need for very large repositories of data. Moreover, the institutions have redundant storage across the network and load balancing mechanism to improve access performance. NoSQL databases provide horizontal scalability which allows the system to grow easily and effortlessly. Document databases are particularly suitable to store the DICOM metadata and the JSON format is already supported by the standard. This paper, we discuss the use of document database model in the medical imaging field, trying to focus on both clinical and research environments. Moreover, we focused on the proposal of an architecture based on MongoDB to distribute the load between multiple nodes. The proposal was integrated with an open-source PACS and validated by simulating multiple operations over data distributed across multiple virtual locations, and the results are promising.