In this paper, a new wireless sensor network architecture is introduced for underwater surveillance systems where sensors lie in surface buoys when nodes are first deployed. After deployment, sensors are lowered to various depths selected by our scheme such that the maximum coverage of the three dimensional sensor space is maintained. Each node has multiple microsensors of various types; acoustic, magnetic, radiation and mechanical. A classification based data mining scheme based on the readings of these sensor types detects and classifies submarines, small delivery vehicles, mines and divers.

Wireless sensor networks for underwater survelliance systems

The stationarity requirement for the process generating the data is a common assumption in classifiers' design. When such hypothesis does not hold, e.g., in applications affected by aging effects, drifts, deviations, and faults, classifiers must react just in time, i.e., exactly when needed, to track the process evolution. The first step in designing effective just-in-time classifiers requires detection of the temporal instant associated with the process change, and the second one needs an update of the knowledge base used by the classification system to track the process evolution. This paper addresses the change detection aspect leaving the design of just-in-time adaptive classification systems to a companion paper. Two completely automatic tests for detecting nonstationarity phenomena are suggested, which neither require a priori information nor assumptions about the process generating the data. In particular, an effective computational intelligence-inspired test is provided to deal with multidimensional situations, a scenario where traditional change detection methods are generally not applicable or scarcely effective.

Just-in-Time Adaptive Classifiers—Part I: Detecting Nonstationary Changes

Wavelet networks (WNs) are an efficient model of nonlinear signal processing developed in recent years. This paper presents a comparative study of WN efficiency for the detection of incipient faults of power transformers. After 700 groups of training and testing gases-in-oil samples are processed by fuzzy technology, we compare and analyze the network training process and simulation results of five WNs which include two types of WNs with two different activation functions and evolving WN. A lot of diagnostic examples show that the diagnostic accuracy and efficiency of the proposed five WN approaches prevail those of the conventional back-propagation neural-network method and are suitable for faults diagnosis of power transformers, especially with the evolving WN achieving superior performance.

Wavelet Networks in Power Transformers Diagnosis Using Dissolved Gas Analysis

Robust underwater noise targets classification using auditory inspired time–frequency analysis

Aging effects, environmental changes, thermal drifts, and soft and hard faults affect physical systems by changing their nature and behavior over time. To cope with a process evolution adaptive solutions must be envisaged to track its dynamics; in this direction, adaptive classifiers are generally designed by assuming the stationary hypothesis for the process generating the data with very few results addressing nonstationary environments. This paper proposes a methodology based on $k$ -nearest neighbor (NN) classifiers for designing adaptive classification systems able to react to changing conditions just-in-time (JIT), i.e., exactly when it is needed. $k$ -NN classifiers have been selected for their computational-free training phase, the possibility to easily estimate the model complexity $k$ and keep under control the computational complexity of the classifier through suitable data reduction mechanisms. A JIT classifier requires a temporal detection of a (possible) process deviation (aspect tackled in a companion paper) followed by an adaptive management of the knowledge base (KB) of the classifier to cope with the process change. The novelty of the proposed approach resides in the general framework supporting the real-time update of the KB of the classification system in response to novel information coming from the process both in stationary conditions (accuracy improvement) and in nonstationary ones (process tracking) and in providing a suitable estimate of $k$ . It is shown that the classification system grants consistency once the change targets the process generating the data in a new stationary state, as it is the case in many real applications.

Just-in-Time Adaptive Classifiers—Part II: Designing the Classifier

In this paper, a new subband-based classification scheme is developed for classifying underwater mines and mine-like targets from the acoustic backscattered signals. The system consists of a feature extractor using wavelet packets in conjunction with linear predictive coding (LPC), a feature selection scheme, and a backpropagation neural-network classifier. The data set used for this study consists of the backscattered signals from six different objects: two mine-like targets and four nontargets for several aspect angles. Simulation results on ten different noisy realizations and for signal-to-noise ratio (SNR) of 12 dB are presented. The receiver operating characteristic (ROC) curve of the classifier generated based on these results demonstrated excellent classification performance of the system. The generalization ability of the trained network was demonstrated by computing the error and classification rate statistics on a large data set. A multiaspect fusion scheme was also adopted in order to further improve the classification performance.

Underwater target classification using wavelet packets and neural networks

A new adaptive underwater target classification system to cope with environmental changes in acoustic backscattered data from targets and nontargets is introduced. The core of the system is the adaptive feature mapping that minimizes the classification error rate of the classifier. The goal is to map the feature vector in such a way that the mapped version remains invariant to the environmental changes. A K-nearest neighbor (K-NN) system is used as a memory to provide the closest matches of an unknown pattern in the feature space. The classification decision is done by a backpropagation neural network (BPNN). Two different cost functions for adaptation are defined. These two cost functions are then combined together to improve the classification performance. The test results on a 40-kHz linear FM acoustic backscattered data set collected from six different objects are presented. These results demonstrate the effectiveness of the adaptive system versus nonadaptive system when the signal-to-reverberation ratio (SRR) in the environment is varying.

https://www.engr.colostate.edu/ece///faculty/azimi/pdf/journals/ECEmra00012.pdf

Underwater target classification in changing environments using an adaptive feature mapping

The problem of classifying underwater targets is addressed in this paper. The proposed classification system consists of several subsystems including preprocessing, subband decomposition using wavelet packets, linear predictive coding, feature selection and neural network classifier. A multi-aspect fusion system is introduced to further improve the classification accuracy. The classification performance of the overall system is demonstrated and benchmarked on two different acoustic backscattered data sets with 40- and 80-kHz bandwidth. A comprehensive study is then carried out to compare the classification performance using these data sets in terms of the receiver operating curves, error locations, and generalization and robustness on a large set of noisy data. Additionally, the importance of different frequency bands for the wideband 80-kHz data is also investigated. For the wideband data, a subband fusion mechanism is introduced which offers very promising results.

A study of effects of sonar bandwidth for underwater target classification

Study of effects of sonar bandwidth for underwater target classification, A

In this paper, a new feature mapping scheme is presented to cope with environmental and target signature changes for underwater target classification. A wavelet packet-based feature extraction scheme is used in conjunction with the linear prediction coding (LPC) scheme as the front-end processor. The core of the system is the adaptive feature mapping subsystem that minimizes the classification error of the classifier. The extracted feature vector is mapped by the resultant transformation matrix in such a way that the mapped version remains invariant to the environmental and sensory changes. The feedback to the adaptation mechanism is provided by a k-nearest neighbor classifier. The test results on 40 kHz linear FM acoustic backscattered data collected for six different objects are presented The effectiveness of the adaptive system vs. nonadaptive one is demonstrated for several signal-to-noise ratio (SNR) conditions.

De Yao

Papers

Underwater target classification using wavelet packets and neural networks

Underwater target classification in changing environments using an adaptive feature mapping

A study of effects of sonar bandwidth for underwater target classification

Study of effects of sonar bandwidth for underwater target classification, A

Adaptive feature mapping for underwater target classification