Ioan Cosmin Radu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ioan Cosmin Radu has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Adela Bâra
Department of Economic Informatics and Cybernetics Bucharest University of Economic Studies Bucharest Romania
1 shared publication Andreea Buga
Christian-Doppler Laboratory for Client-Centric Cloud Computing, Johannes Kepler University of Linz, CDCC, Hagenberg, Austria
1 shared publicationAndrei Vasilateanu
Faculty of Engineering in Foreign Languages, University Politehnica Bucharest, Bucharest, Romania
1 shared publication- Florina Camelia Puican
Department of Economic Informatics and Cybernetics, Bucharest University of Economic Studies, Romana Square 6, 010374 Bucharest, Romania
1 shared publication - Simona-Vasilica Oprea
Department of Economic Informatics and Cybernetics Bucharest University of Economic Studies Bucharest Romania
1 shared publication
Latest Publications
- Open Access
- 2 October 2021
- Published by MDPI AG in Sustainability
- Vol. 13 (19) , 10963
Anomaly Detection with Machine Learning Algorithms and Big Data in Electricity Consumption
When analyzing smart metering data, both reading errors and frauds can be identified. The purpose of this analysis is to alert the utility companies to suspicious consumption behavior that could be further investigated with on-site inspections or other methods. The use of Machine Learning (ML) algorithms to analyze consumption readings can lead to the identification of malfunctions, cyberattacks interrupting measurements, or physical tampering with smart meters. Fraud detection is one of the classical anomaly detection examples, as it is not easy to label consumption or transactional data. Furthermore, frauds differ in nature, and learning is not always possible. In this paper, we analyze large datasets of readings provided by smart meters installed in a trial study in Ireland by applying a hybrid approach. More precisely, we propose an unsupervised ML technique to detect anomalous values in the time series, establish a threshold for the percentage of anomalous readings from the total readings, and then label that time series as suspicious or not. Initially, we propose two types of algorithms for anomaly detection for unlabeled data: Spectral Residual-Convolutional Neural Network (SR-CNN) and an anomaly trained model based on martingales for determining variations in time-series data streams. Then, the Two-Class Boosted Decision Tree and Fisher Linear Discriminant analysis are applied on the previously processed dataset. By training the model, we obtain the required capabilities of detecting suspicious consumers proved by an accuracy of 90%, precision score of 0.875, and F1 score of 0.894.
- 2 October 2021
- Published by MDPI AG in Sustainability
- Vol. 13 (19) , 10963
Open AccessAnomaly Detection with Machine Learning Algorithms and Big Data in Electricity Consumption
When analyzing smart metering data, both reading errors and frauds can be identified. The purpose of this analysis is to alert the utility companies to suspicious consumption behavior that could be further investigated with on-site inspections or other methods. The use of Machine Learning (ML) algorithms to analyze consumption readings can lead to the identification of malfunctions, cyberattacks interrupting measurements, or physical tampering with smart meters. Fraud detection is one of the classical anomaly detection examples, as it is not easy to label consumption or transactional data. Furthermore, frauds differ in nature, and learning is not always possible. In this paper, we analyze large datasets of readings provided by smart meters installed in a trial study in Ireland by applying a hybrid approach. More precisely, we propose an unsupervised ML technique to detect anomalous values in the time series, establish a threshold for the percentage of anomalous readings from the total readings, and then label that time series as suspicious or not. Initially, we propose two types of algorithms for anomaly detection for unlabeled data: Spectral Residual-Convolutional Neural Network (SR-CNN) and an anomaly trained model based on martingales for determining variations in time-series data streams. Then, the Two-Class Boosted Decision Tree and Fisher Linear Discriminant analysis are applied on the previously processed dataset. By training the model, we obtain the required capabilities of detecting suspicious consumers proved by an accuracy of 90%, precision score of 0.875, and F1 score of 0.894.
- 1 November 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Environment crowd-sensing for asthma management
Chronic diseases are the main cause of mortality in developed countries. Among them, asthma has an increasing prevalence in urban areas. We propose to use the crowd-sensing paradigm for monitoring the environment, especially the air quality parameters relevant for asthma patients. Asthma is a good candidate for participatory medicine approaches as current medical guidelines promote self-management of the disease by informed and ICT enabled patients. The paper continues our work for m-health applications for asthma patients and focuses on decentralized air quality monitoring by the patients themselves using affordable and available hardware platforms based on Arduino.
- 1 November 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Environment crowd-sensing for asthma management
Chronic diseases are the main cause of mortality in developed countries. Among them, asthma has an increasing prevalence in urban areas. We propose to use the crowd-sensing paradigm for monitoring the environment, especially the air quality parameters relevant for asthma patients. Asthma is a good candidate for participatory medicine approaches as current medical guidelines promote self-management of the disease by informed and ICT enabled patients. The paper continues our work for m-health applications for asthma patients and focuses on decentralized air quality monitoring by the patients themselves using affordable and available hardware platforms based on Arduino.