TY - GEN
T1 - Target detection and target type & motion classification
T2 - 2014 American Control Conference, ACC 2014
AU - Li, Yue
AU - Ray, Asok
AU - Wettergren, Thomas A.
PY - 2014
Y1 - 2014
N2 - This paper addresses sensor network-based surveillance of target detection and target type & motion classification. The performance of target detection and classification could be compromised (e.g., due to high rates of false alarm and misclassification), because of inadequacies of feature extraction from (possibly noisy) sensor data and subsequent pattern classification over the network. A feature extraction algorithm, called symbolic dynamic filtering (SDF), is investigated for solving the target detection & classification problem. In this paper, the performance of SDF is compared with two commonly used feature extractors, namely, Cepstrum and principal component analysis (PCA)). Each of these three feature extractors is executed in conjunction with three well-known pattern classifiers, namely, k-nearest neighbor (k-NN), support vector machine (SVM), and sparse representation classification (SRC). Results of numerical simulation are presented based on a dynamic model of target maneuvering and passive sonar sensing in the ocean environment. These results show that SDF has a consistently superior performance for all tasks - target detection and target type & motion classification.
AB - This paper addresses sensor network-based surveillance of target detection and target type & motion classification. The performance of target detection and classification could be compromised (e.g., due to high rates of false alarm and misclassification), because of inadequacies of feature extraction from (possibly noisy) sensor data and subsequent pattern classification over the network. A feature extraction algorithm, called symbolic dynamic filtering (SDF), is investigated for solving the target detection & classification problem. In this paper, the performance of SDF is compared with two commonly used feature extractors, namely, Cepstrum and principal component analysis (PCA)). Each of these three feature extractors is executed in conjunction with three well-known pattern classifiers, namely, k-nearest neighbor (k-NN), support vector machine (SVM), and sparse representation classification (SRC). Results of numerical simulation are presented based on a dynamic model of target maneuvering and passive sonar sensing in the ocean environment. These results show that SDF has a consistently superior performance for all tasks - target detection and target type & motion classification.
UR - http://www.scopus.com/inward/record.url?scp=84905682353&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84905682353&partnerID=8YFLogxK
U2 - 10.1109/ACC.2014.6858726
DO - 10.1109/ACC.2014.6858726
M3 - Conference contribution
AN - SCOPUS:84905682353
SN - 9781479932726
T3 - Proceedings of the American Control Conference
SP - 1132
EP - 1137
BT - 2014 American Control Conference, ACC 2014
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 4 June 2014 through 6 June 2014
ER -