This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

This paper presents a novel surveillance system aimed at the detection and classification of threats in the vicinity of a long gas pipeline. The sensing system is based on phase-sensitive optical time domain reflectometry (φ-OTDR) technology for signal acquisition and pattern recognition strategies for threat identification. The proposal incorporates contextual information at the feature level and applies a system combination strategy for pattern classification. The contextual information at the feature level is based on the tandem approach (using feature representations produced by discriminatively-trained multi-layer perceptrons) by employing feature vectors that spread different temporal contexts. The system combination strategy is based on a posterior combination of likelihoods computed from different pattern classification processes. The system operates in two different modes:(1) machine + activity identification, which recognizes the activity being carried out by a certain machine, and (2) threat detection, aimed at detecting threats no matter what the real activity being conducted is. In comparison with a previous system based on the same rigorous experimental setup, the results show that the system combination from the contextual feature information improves the results for each individual class in both operational modes, as well as the overall classification accuracy, with statistically-significant improvements.

No abstract

Abstract:There is an increasing interest in researchers and companies on the combination of Distributed Acoustic Sensing (DAS) and a Pattern Recognition System (PRS) to detect and classify potentially dangerous events that occur in areas above fiber optic cables deployed along active pipelines, aiming to construct pipeline surveillance systems. This paper presents a review of the literature in what respect to machine learning techniques applied to pipeline surveillance systems based on DAS+PRS (although its scope can also be extended to any other environment in which DAS+PRS strategies are to be used). To do so, we describe the fundamentals of the machine learning approaches when applied to DAS systems, and also do a detailed literature review of the main contributions on this topic. Additionally, this paper addresses the most common issues related to real field deployment and evaluation of DAS+PRS for pipeline threat monitoring, and intends to provide useful insights and recommendations in what respect to the design of such systems. The literature review concludes that a real field deployment of a PRS based on DAS technology is still a challenging area of research, far from being fully solved.

Deep neural networks (DNNs) have gained remarkable success in speech recognition, partially attributed to the flexibility of DNN models in learning complex patterns of speech signals. This flexibility, however, may lead to serious over-fitting and hence miserable performance degradation in adverse acoustic conditions such as those with high ambient noises. We propose a noisy training approach to tackle this problem: by injecting moderate noises into the training data intentionally and randomly, more generalizable DNN models can be learned. This 'noise injection' technique, although known to the neural computation community already, has not been studied with DNNs which involve a highly complex objective function. The experiments presented in this paper confirm that the noisy training approach works well for the DNN model and can provide substantial performance improvement for DNN-based speech recognition.

El acceso a la versión del editor puede requerir la suscripción del recurso Access to the published version may require subscription AbstractDiscriminative confidence based on multi-layer perceptrons (MLPs) and multiple features has shown significant advantage compared to the widely used lattice-based confidence in spoken term detection (STD). Although the MLP-based framework can handle any features derived from a multitude of sources, choosing all possible features may lead to over complex models and hence less generality. In this paper, we design an extensive set of features and analyze their contribution to STD individually and as a group. The main goal is to choose a small set of features that are sufficiently informative while keeping the model simple and generalizable. We employ two established models to conduct the analysis: one is linear regression which targets for the most relevant features and the other is logistic linear regression which targets for the most discriminative features. We find the most informative features are comprised of those derived from diverse sources (ASR decoding, duration and lexical properties) and the two models deliver highly consistent feature ranks. STD experiments on both English and Spanish data demonstrate significant performance gains with the proposed feature sets.

This paper presents an on-line augmented surveillance system that aims to real time monitoring of activities along a pipeline. The system is deployed in a fully realistic scenario and exposed to real activities carried out in unknown places at unknown times within a given test time interval (socalled blind field tests). We describe the system architecture that includes specific modules to deal with the fact that continuous on-line monitoring needs to be carried out, while addressing the need of limiting the false alarms at reasonable rates. To the best or our knowledge, this is the first published work in which a pipeline integrity threat detection system is deployed in a realistic scenario (using a fiber optic along an active gas pipeline) and is thoroughly and objectively evaluated in realistic blind conditions. The system integrates two operation modes: The machine+activity identification mode identifies the machine that is carrying out a certain activity along the pipeline, and the threat detection mode directly identifies if the activity along the pipeline is a threat or not. The blind field tests are carried out in two different pipeline sections: The first section corresponds to the case where the sensor is close to the sensed area, while the second one places the sensed area about 35 km far from the sensor. Results of the machine+activity identification mode showed an average machine+activity classification rate of 46.6%. For the threat detection mode, 8 out of 10 threats were correctly detected, with only 1 false alarm appearing in a 55.5-hour sensed period.

No abstract