Gutiérrez-Portela, Fernando; Almenares-Mendoza, Florina; Calderón-Benavides, Liliana Evaluation of the performance of unsupervised learning algorithms for intrusion detection in unbalanced data environments Proceedings Article In: IEEE, 2024, ISSN: 2169-3536. Abstract | Links | BibTeX | Tags: anomaly detection, compromise, intrusion detection system, machine learning, metrics, Qursa, unsupervised models García-Rubio, Carlos; Campo, Celeste; Moure-Garrido, Marta Synthetic Generation of Electrical Consumption Traces in Smart Homes Conference Lecture Notes in Networks and Systems, vol. 594, Springer International Publishing, 2022, ISBN: 978-3-031-21332-8. Abstract | Links | BibTeX | Tags: anomaly detection, compromise, cynamon, Electricity consumption, magos, Smart home, Synthetic dataset generation Moure-Garrido, Marta; Campo-Vázquez, Celeste; García-Rubio, Carlos Entropy-Based Anomaly Detection in HouseholdElectricity Consumption Journal Article In: Energies, vol. 15, 2022, ISSN: 1996-1073. Abstract | Links | BibTeX | Tags: anomaly detection, behavior pattern, compromise, cynamon, entropy, household electricity consumption, load forecasting, magos García-Rubio, Carlos; Diaz-Redondo, Rebeca; Campo-Vázquez, Celeste; Fernandez-Vilas, Ana Using entropy of social media location data for the detection of crowd dynamics anomalies Journal Article In: Electronics, vol. 7, iss. 12, pp. 380, 2018, ISSN: 2079-9292. Abstract | Links | BibTeX | Tags: anomaly detection, city behavior, data mining algorithms, location-based social network2024
@inproceedings{almenarez019,
title = {Evaluation of the performance of unsupervised learning algorithms for intrusion detection in unbalanced data environments},
author = {Fernando Gutiérrez-Portela and Florina Almenares-Mendoza and Liliana Calderón-Benavides},
url = {https://ieeexplore.ieee.org/document/10794744},
doi = {10.1109/ACCESS.2024.3516615},
issn = {2169-3536},
year = {2024},
date = {2024-12-12},
urldate = {2024-12-12},
publisher = {IEEE},
abstract = {In this study, the performance of different unsupervised machine learning algorithms used for intrusion detection within unbalanced data environments were analyzed; these algorithms included the K-means++ algorithm, density-based spatial clustering of applications with noise (DBSCAN), local outlier factor (LOF), and isolation forest (I-forest) using the BoT–IoT dataset. Performance metrics such as purity, homogeneity_score, completeness_score, v_measure_score, and adjusted_mutual_info_score were used to evaluate the effectiveness of algorithms in detecting various types of attacks such as distributed denial of service (DDoS), denial of service (DoS), and reconnaissance. Similarly, different methods were used for the automatic selection of the optimal number of clusters such as the elbow method, silhouette coefficient, Calinski–Harabasz index, and Davies–Bouldin index. Moreover, principal component analysis (PCA) was used to explain data variance and the influence of variables on intrusion detection. Results revealed that the K-means algorithm achieved 95% purity as well as 95% and 99% prediction accuracies for normal and abnormal data, respectively. The I-forest algorithm achieved 95% purity as well as 99% and 90% prediction accuracies for normal and abnormal data in a balanced dataset, respectively. These findings indicated that I-forest exhibited a low central processing unit (CPU) consumption rate of 10% on balanced data, outperforming DBSCAN, K-Means++, and LOF, with 16% consumption rates.},
keywords = {anomaly detection, compromise, intrusion detection system, machine learning, metrics, Qursa, unsupervised models},
pubstate = {published},
tppubtype = {inproceedings}
}
2022
@conference{garciarubio008,
title = {Synthetic Generation of Electrical Consumption Traces in Smart Homes},
author = {Carlos García-Rubio and Celeste Campo and Marta Moure-Garrido },
url = {https://link.springer.com/chapter/10.1007/978-3-031-21333-5_68},
doi = {https://doi.org/10.1007/978-3-031-21333-5_68},
isbn = {978-3-031-21332-8},
year = {2022},
date = {2022-11-21},
urldate = {2022-11-21},
booktitle = { Lecture Notes in Networks and Systems},
volume = {594},
pages = {681-692},
publisher = {Springer International Publishing},
abstract = {With the introduction of the smart grid, smart meters and smart plugs, it is possible to know the energy consumption of a smart home, either per appliance or aggregate. Some recent works have used energy consumption traces to detect anomalies, either in the behavior of the inhabitants or in the operation of some device in the smart home. To train and test the algorithms that detect these anomalies, it is necessary to have extensive and well-annotated consumption traces. However, this type of traces is difficult to obtain. In this paper we describe a highly configurable synthetic electrical trace generator, with characteristics similar to real traces, that can be used in this type of study. In order to have a more realistic behavior, the traces are generated by adding the consumption of several simulated appliances, which precisely represent the consumption of different typical electrical devices. Following the behavior of the real traces, variations at different scales of time and anomalies are introduced to the aggregated smart home energy consumption.},
keywords = {anomaly detection, compromise, cynamon, Electricity consumption, magos, Smart home, Synthetic dataset generation},
pubstate = {published},
tppubtype = {conference}
}
@article{campo003,
title = {Entropy-Based Anomaly Detection in HouseholdElectricity Consumption},
author = {Marta Moure-Garrido and Celeste Campo-Vázquez and Carlos García-Rubio},
doi = {https://doi.org/10.3390/en15051837},
issn = {1996-1073},
year = {2022},
date = {2022-03-02},
urldate = {2022-03-02},
journal = {Energies},
volume = {15},
abstract = {Energy efficiency is one of the most important current challenges, and its impact at a global level is considerable. To solve current challenges, it is critical that consumers are able to control their energy consumption. In this paper, we propose using a time series of window-based entropy to detect anomalies in the electricity consumption of a household when the pattern of consumption behavior exhibits a change. We compare the accuracy of this approach with two machine learning approaches, random forest and neural networks, and with a statistical approach, the ARIMA model. We study whether these approaches detect the same anomalous periods. These different techniques have been evaluated using a real dataset obtained from different households with different consumption profiles from the Madrid Region. The entropy-based algorithm detects more days classified as anomalous according to context information compared to the other algorithms. This approach has the advantages that it does not require a training period and that it adapts dynamically to changes, except in vacation periods when consumption drops drastically and requires some time for adapting to the new situation.},
keywords = {anomaly detection, behavior pattern, compromise, cynamon, entropy, household electricity consumption, load forecasting, magos},
pubstate = {published},
tppubtype = {article}
}
2018
@article{campo006,
title = {Using entropy of social media location data for the detection of crowd dynamics anomalies},
author = {Carlos García-Rubio and Rebeca Diaz-Redondo and Celeste Campo-Vázquez and Ana Fernandez-Vilas },
url = {http://hdl.handle.net/10016/33760},
doi = {https://doi.org/10.3390/electronics7120380},
issn = {2079-9292},
year = {2018},
date = {2018-12-03},
urldate = {2018-12-03},
journal = {Electronics},
volume = {7},
issue = {12},
pages = {380},
abstract = {Evidence of something unusual happening in urban areas can be collected from different data sources, such as police officers, cameras, or specialized physical infrastructures. In this paper, we propose using geotagged posts on location-based social networks (LBSNs) to detect crowd dynamics anomalies automatically as evidence of a potential unusual event. To this end, we use the Instagram API media/search endpoint to collect the location of the pictures posted by Instagram users in a given area periodically. The collected locations are summarized by their centroid. The novelty of our work relies on using the entropy of the sequence of centroid locations in order to detect abnormal patterns in the city. The proposal is tested on a data set collected from Instagram during seven months in New York City and validated with another data set from Manchester. The results have also been compared with an alternative approach, a training phase plus a ranking of outliers. The main conclusion is that the entropy algorithm succeeds inn finding abnormal events without the need for a training phase, being able to dynamically adapt to changes in crowd behavior.},
keywords = {anomaly detection, city behavior, data mining algorithms, location-based social network},
pubstate = {published},
tppubtype = {article}
}
Publications
Evaluation of the performance of unsupervised learning algorithms for intrusion detection in unbalanced data environments Proceedings Article In: IEEE, 2024, ISSN: 2169-3536. Synthetic Generation of Electrical Consumption Traces in Smart Homes Conference Lecture Notes in Networks and Systems, vol. 594, Springer International Publishing, 2022, ISBN: 978-3-031-21332-8. Entropy-Based Anomaly Detection in HouseholdElectricity Consumption Journal Article In: Energies, vol. 15, 2022, ISSN: 1996-1073. Using entropy of social media location data for the detection of crowd dynamics anomalies Journal Article In: Electronics, vol. 7, iss. 12, pp. 380, 2018, ISSN: 2079-9292.2024
2022
2018