No abstract

Detecting non-human activity in social networks has become an area of great interest for both industry and academia. In this context, obtaining a high detection accuracy is not the only desired quality; experts in the application domain would also like having an understandable model, with which one may explain a decision. An explanatory decision model may help experts to consider, for example, taking legal action against an account that has displayed offensive behavior, or forewarning an account holder about suspicious activity. In this paper, we shall use a pattern-based classification mechanism to social bot detection, specifically for Twitter. Furthermore, we shall introduce a new feature model for social bot detection, which extends (part of) an existing model with features out of Twitter account usage and tweet content sentiment analysis. From our experimental results, we shall see that our mechanism outperforms other, state-of-the-art classifiers, not based on patterns; and that our feature model yields better classification results than others reported on in the literature.

Latent fingerprint identification is attracting increasing interest because of its important role in law enforcement. Although the use of various fingerprint features might be required for successful latent fingerprint identification, methods based on minutiae are often readily applicable and commonly outperform other methods. However, as many fingerprint feature representations exist, we sought to determine if the selection of feature representation has an impact on the performance of automated fingerprint identification systems. In this paper, we review the most prominent fingerprint feature representations reported in the literature, identify trends in fingerprint feature representation, and observe that representations designed for verification are commonly used in latent fingerprint identification. We aim to evaluate the performance of the most popular fingerprint feature representations over a common latent fingerprint database. Therefore, we introduce and apply a protocol that evaluates minutia descriptors for latent fingerprint identification in terms of the identification rate plotted in the cumulative match characteristic (CMC) curve. From our experiments, we found that all the evaluated minutia descriptors obtained identification rates lower than 10% for Rank−1 and 24% for Rank−100 comparing the minutiae in the database NIST SD27, illustrating the need of new minutia descriptors for latent fingerprint identification.INDEX TERMS Latent fingerprint identification, minutia descriptor, fingerprint feature representation, minutia descriptor evaluation.

No abstract

This study introduces the One-Class K-means with Randomly-projected features Algorithm (OCKRA). OCKRA is an ensemble of one-class classifiers built over multiple projections of a dataset according to random feature subsets. Algorithms found in the literature spread over a wide range of applications where ensembles of one-class classifiers have been satisfactorily applied; however, none is oriented to the area under our study: personal risk detection. OCKRA has been designed with the aim of improving the detection performance in the problem posed by the Personal RIsk DEtection(PRIDE) dataset. PRIDE was built based on 23 test subjects, where the data for each user were captured using a set of sensors embedded in a wearable band. The performance of OCKRA was compared against support vector machine and three versions of the Parzen window classifier. On average, experimental results show that OCKRA outperformed the other classifiers for at least 0.53% of the area under the curve (AUC). In addition, OCKRA achieved an AUC above 90% for more than 57% of the users.

Pattern recognition methods are used in the final stage of a traffic sign detection and recognition system, where the main objective is to categorize a detected sign. Support vector machines have been reported as a good method to achieve this main target due to their ability to provide good accuracy as well as being sparse methods. Nevertheless, for complete data sets of traffic signs the number of operations needed in the test phase is still large, whereas the accuracy needs to be improved. The objectives of this work are to propose pre-processing methods and improvements in support vector machines to increase the accuracy achieved while the number of support vectors, and thus the number of operations needed in the test phase, is reduced. Results show that with the proposed methods the accuracy is increased 3-5% with a reduction in the number of support vectors of 50-70%.

No abstract

Reconstruction‐based one‐class classification has shown to be very effective in a number of domains. This approach works by attempting to capture the underlying structure of the normal class, typically, by means of clusters of objects. It has the main disadvantage, however, that one has to indicate the number of clusters in advance, for this yields an efficient way of computing a clustering. In this paper, we introduce a new algorithm, OCKRA++, which achieves a better performance, by enhancing a clustering‐based one‐class ensemble classifier (OCKRA) with a cluster validity index that is used to set the best number of clusters during the classifier's training process. We have thoroughly tested OCKRA++ in a particular domain, namely masquerade detection. For this purpose, we have used the Windows‐Users and ‐Intruder simulation Logs data set repository, which contains 70 different masquerade data sets. We have found that OCKRA++ is currently the algorithm that achieves the best area under the curve, with a significant difference, in masquerade detection using the file system navigation approach.