Network monitoring data generally consists of hundreds of counters periodically collected in the form of time-series, resulting in a complex-to-analyze multivariate time-series (MTS) process. Traditional time-series anomaly detection methods target univariate time-series analysis, which makes the MTS analysis cumbersome and prohibitively complex. We present DC-VAE (Dilated Convolutional -Variational Auto Encoder), a novel approach to anomaly detection in MTS data, leveraging convolutional neural networks (CNNs) and variational autoencoders (VAEs). DC-VAE detects anomalies in MTS data through a single model, exploiting temporal information without sacrificing computational and memory resources. In particular, instead of using recursive neural networks, large causal filters, or many layers, DC-VAE relies on Dilated Convolutions (DC) to capture long and short-term phenomena in the data. We evaluate DC-VAE on the detection of anomalies in the TELCO TELeCOmmunication-networks dataset, a large-scale, multi-dimensional network monitoring dataset collected at an operational mobile Internet Service Provider (ISP), where anomalous events were manually labeled by experts during seven months, at a five-minutes granularity. We benchmark DC-VAE against a broad set of traditional time-series anomaly detectors from the signal processing and machine learning domains. We also evaluate DC-VAE in open, publicly available datasets, comparing its performance against other multivariate anomaly detectors based on deep learning generative models. Results confirm the advantages of DC-VAE, both in terms of MTS data modeling, as well as for anomaly detection. For the sake of reproducibility and as an additional contribution, we make the TELCO dataset publicly available to the community and openly release the code implementing DC-VAE.

We present DC-VAE, an approach to network anomaly detection in multivariate time-series (MTS), using Variational Auto Encoders (VAEs) and Dilated Convolutional Neural Networks (CNN). DC-VAE detects anomalies in MTS data through a single model, exploiting temporal and spatial MTS information. We showcase DC-VAE in different MTS datasets, and portray its future application in a continual learning framework, exploiting the generative properties of the underlying generative model to deal with continuously evolving data, avoiding catastrophic forgetting. We showcase the functioning of DC-VAE in the event of concept drifts, and propose the application of a novel approach to generative-driven continual learning, introducing the Deep Generative Replay model.

The use of different evaluation measures for classification tasks have gained a significant amount of attention in the past decade, specially for those problems with multiple and imbalanced classes [1], [2]. However, the optimization of classifiers with respect to these measures is still heuristic, using ad-hoc rules with classical accuracy-optimized classifiers. We propose a classifier designed specifically to optimize one of the possible measures, namely, the so-called G-mean. Nevertheless, the technique is general, and it can be used to optimize generic evaluation measures. The optimization algorithm to train the classifier is described, and the numerical scheme is tested showing its usability and robustness. The code is publicly available, as well as the datasets used along this paper.

BACKGROUND: Beef quality measurement is a complex task with high economic impact. There is high interest in obtaining an automatic quality parameters estimation in live cattle or post mortem. In this paper we set out to obtain beef quality estimates from the analysis of ultrasound (in vivo) and color images (post mortem), with the measurement of various parameters related to tenderness and amount of meat: rib eye area, percentage of intramuscular fat and backfat thickness or subcutaneous fat. PROPOSAL: An algorithm based on curve evolution is implemented to calculate the rib eye area. The backfat thickness is estimated from the profile of distances between two curves that limit the steak and the rib eye, previously detected. A model base in Support Vector Regression (SVR) is trained to estimate the intramuscular fat percentage. A series of features extracted on a region of interest, previously detected in both ultrasound and color images, were proposed. In all cases, a complete evaluation was performed with different databases including: color and ultrasound images acquired by a beef industry expert, intramuscular fat estimation obtained by an expert using a commercial software, and chemical analysis. CONCLUSIONS: The proposed algorithms show good results to calculate the rib eye area and the backfat thickness measure and profile. They are also promising in predicting the percentage of intramuscular fat.

Face recognition systems (FRS) have been widely studied and the performances reported are very high in the standard databases used for comparison. In this work we present a FRS that achieves state of the art results in these databases and show its performance's variation when tested in a field trial using a citizen identification database. To accomplish this, a set of experiments are proposed. These include increasing the size of the database, using subsets that include a time difference of one to ten years between the query samples and those enrolled in the system and finally using different subsets of the same database. Discussion on these experiments and conclusions are presented.

In this work we will show that it is possible to perform three-dimensional (3D) analysis and extract features without performing a 3D surface reconstruction. We propose a novel approach that consists in acquiring the scene under the projection of structured light (plus the natural ambient illumination), which allows us to obtain the depth gradient map using a simple processing step with very low hardware requirements.

In this work we focused in the matching stage of a face recognition system. These systems are used to identify an unknown person or to validate a claimed identity. In the face recognition field it is very common to innovate in the extracted features of a face and use a simple threshold on the distance between samples in order to perform the validation of a claimed identity. In this work we present a novel strategy based in the a-contrario framework in order to improve the matching stage. This approach results in a validation threshold that is automatically adapted to the data and allows to predict the performance of the system in advance. We perform several experiments in order to validate this novel strategy using different databases and show its advantages over using a simple threshold over the distances.

Non-technical losses detection is a complex task, with high economic impact. The diversity and big number of consumption records, makes it very important to find an efficient automatic method for detect the largest number of frauds with the least amount of experts’ hours involved in preprocessing and inspections. This article analyzes the performance of a strategy based on learning from expert labeling: suspect/no-suspect, with one using inspection labels: fraud/no-fraud. Results show that the proposed framework, suitable for imbalance problems, improves performance in terms of the Fmeasure with inspection labels, avoiding hours of experts labeling.

Automatic ultrasound (US) image segmentation is a difficult task due to the quantity of noise present in the images and the lack of information in several zones produced by the acquisition conditions. In this paper, we propose a method that combines shape priors and image information to achieve this task. In particular, we introduce knowledge about the rib-eye shape using a set of images manually segmented by experts. A method is proposed for the automatic segmentation of new samples in which a closed curve is fitted taking into account both the US image information and the geodesic distance between the evolving curve and the estimated mean rib-eye shape in a shape space. This method can be used to solve similar problems that arise when dealing with US images in other fields. The method was successfully tested over a database composed of 610 US images, for which we have the manual segmentations of two experts.

A method is presented for segmentation of anatomical structures that incorporates prior information about shape. The method iteratively applies steps, which find object's border considering its properties independently from shape. The boundary is regularized taking in account the shape being extracted. Detection is not directly performed in the image but in a "shape space" referred to the shape in each step. The problem is reduced to work in this new coordinate system where the border is approximately a horizontal line. Shape information is introduced through a higher dimensional map similar to a distance map of a mean shape. Segmentation results are demonstrated on ultrasound imagery to measure meat quality of bovine and ovine livestock.