International audienceThis paper presents a method aimed at recognizing environmental sounds for surveillance and security applications. We propose to apply one-class support vector machines (1-SVMs) together with a sophisticated dissimilarity measure in order to address audio classification, and more specifically, sound recognition. We illustrate the performance of this method on an audio database, which consists of 1015 sounds belonging to nine classes. The database used presents high intraclass diversity in temps of signal properties and some kind of interclass similarities. A large discrepancy in the number of items in each class implies nonuniform probability of sound appearances. The method proceeds as follows: first, the use of a set of state-of-the-art audio features is studied. Then, we introduce a set of novel features obtained by combining elementary features. Experiments conducted on a nine-class classification problem show the superiority of this novel sound recognition method. The best recognition accuracy (96.89%) is obtained when combining wavelet-based features, MFCCs, and individual temporal and frequency features. Our 1-SVM-based multiclass classification approach overperforms the conventional hidden Markov model-based system in the experiments conducted, the improvement in the error rate can reach 50%. Besides, we provide empirical results showing that the single-class SVM outperforms a combination of binary SVMs. Additional experiments demonstrate our method is robust to environmental noise

This paper proposes to apply optimized

Abstract-a Fourier Transform Technique has been used to enhance the genome periodicities when analyzing the distributions of independent nucleotides and dinucleotides. These periodicities are varying from 2 to 500bp. In this paper we focus on the 3 and 10.5 periodicities. The 3-base periodicity is characteristic for the protein-coding sequences only. The source of the approximately 10.5-base sequence period is related to the deformability of DNA. In fact, DNA folding in chromatin is facilitated by periodical positioning of some dinucleotides along the sequences, with the period close to 10.5 bases. When the DNA sequence is encoded for the signal 'AA' or 'TT' or 'TA' the peak at 10.5 is locally strengthened. For the Caenorhabditis elegans (C. Elegans) genome, this peak becomes the dominant feature in the transform. Studying one organism's genome requires three steps. First, the DNA coding method: the DNA's string data are transformed into numerical signal. Second, periodicities are detected by spectral analysis. Third, a 3D graphical representation allows following the evolution of this periodicity along the genome and facilitating the specific regions location.

No abstract

Support vector machines (SVMs) have gained great attention and have been used extensively and successfully in the field of sounds (events) recognition. However, the extension of SVMs to real-world signal processing applications is still an ongoing research topic. Our work consists of illustrating the potential of SVMs on recognizing impulsive audio signals belonging to a complex realworld dataset. We propose to apply optimized one-class support vector machines (1-SVMs) to tackle both sound detection and classification tasks in the sound recognition process. First, we propose an efficient and accurate approach for detecting events in a continuous audio stream. The proposed unsupervised sound detection method which does not require any pretrained models is based on the use of the exponential family model and 1-SVMs to approximate the generalized likelihood ratio. Then, we apply novel discriminative algorithms based on 1-SVMs with new dissimilarity measure in order to address a supervised sound-classification task. We compare the novel sound detection and classification methods with other popular approaches. The remarkable sound recognition results achieved in our experiments illustrate the potential of these methods and indicate that 1-SVMs are well suited for event-recognition tasks.

No abstract

No abstract

No abstract