Abstract: Methods or systems for identifying seismic or acoustic signals of interest originating with moving motorized vehicles or footstep movement or stationary or moving machinery. A related system for monitoring an area includes a plurality of sensing devices each comprising a frame and a piezo-electric sensor element. A monitoring device is coupled to receive information from each of the sensing devices. One method includes providing a processing chain coupled to receive signal data from a sensor device which receives the signals, including a detection stage, a Joint Time Frequency (JTF) domain stage, and a classification stage. The detection stage identifies presence of signals that emerge from the background. The JTF domain stage estimates the state of the signals of interest over time. The classification stage assesses the previously derived information to form a decision about source identity. In one embodiment, the detector stage performs detections on a single cycle basis.

Abstract: Methods of making classifications. One method acquires groups of data, derives features of potential interest in a first data group, and analyzes features using a classification tree and a statistically based classification process to draw a classification conclusion on identity with an associated level of confidence. Features associated with a signal of potential interest may be derived with at least a second group of data. A statistical algorithm may perform linear discrimination analysis, or a quadratic discrimination analysis or a logistic regression classification analysis. A related method includes acquiring signal data with a sensor device comprising piezo-electric material and detecting a signal by performing detections on signal data from the sensor device. Determinations are provided when detections surpass defined thresholds of confidence.

Abstract: Methods of making classifications. One method acquires groups of data, derives features of potential interest in a first data group, and analyzes features using a classification tree and a statistically based classification process to draw a classification conclusion on identity with an associated level of confidence. Features associated with a signal of potential interest may be derived with at least a second group of data. A statistical algorithm may perform linear discrimination analysis, or a quadratic discrimination analysis or a logistic regression classification analysis. A related method includes acquiring signal data with a sensor device comprising piezo-electric material and detecting a signal by performing detections on signal data from the sensor device. Determinations are provided when detections surpass defined thresholds of confidence.

Abstract: Methods or systems for identifying seismic or acoustic signals of interest originating with moving motorized vehicles or footstep movement or stationary or moving machinery. A related system for monitoring an area includes a plurality of sensing devices each comprising a frame and a piezo-electric sensor element. A monitoring device is coupled to receive information from each of the sensing devices. One method includes providing a processing chain coupled to receive signal data from a sensor device which receives the signals, including a detection stage, a Joint Time Frequency (JTF) domain stage, and a classification stage. The detection stage identifies presence of signals that emerge from the background. The JTF domain stage estimates the state of the signals of interest over time. The classification stage assesses the previously derived information to form a decision about source identity. In one embodiment, the detector stage performs detections on a single cycle basis.