Tracking of unusual events in wireless sensor networks based on artificial neural-networks algorithms

@inproceedings{citeulike:1061473, abstract = {Some of the algorithms developed within the artificial neural-networks tradition can be easily adopted to wireless sensor network platforms and will meet the requirements for sensor networks like: simple parallel distributed computation, distributed storage and data robustness. As a result of the dimensionality reduction obtained simply from the outputs of the neural-networks clustering algorithms, lower communication costs and energy savings can also be obtained. In this paper we will present two possible implementations of the ART and FuzzyART neural-networks algorithms, which are unsupervised learning methods for categorization of the sensory inputs. They are tested on a data obtained from a set of several motes, equipped with several sensors each. Results from simulations of purposefully faulty sensors show the data robustness of these architectures. The proposed neural-networks classifiers have distributed short and long-term memory of the sensory inputs and can function as security alert when unusual sensor inputs are detected.}, author = {Kulakov, A. and Davcev, D. }, citeulike-article-id = {1061473}, journal = {Information Technology: Coding and Computing, 2005. ITCC 2005. International Conference on}, pages = {534--539 Vol. 2}, posted-at = {2007-07-16 02:47:25}, priority = {2}, title = {Tracking of unusual events in wireless sensor networks based on artificial neural-networks algorithms}, url = {http://ieeexplore.ieee.org/xpls/abs\_all.jsp?arnumber=1425198}, volume = {2}, year = {2005} }

TY - CONF ID - citeulike:1061473 L3 - citeulike-article-id:1061473 TI - Tracking of unusual events in wireless sensor networks based on artificial neural-networks algorithms JF - Information Technology: Coding and Computing, 2005. ITCC 2005. International Conference on VL - 2 SP - 534 EP - 539 Vol. 2 N2 - Some of the algorithms developed within the artificial neural-networks tradition can be easily adopted to wireless sensor network platforms and will meet the requirements for sensor networks like: simple parallel distributed computation, distributed storage and data robustness. As a result of the dimensionality reduction obtained simply from the outputs of the neural-networks clustering algorithms, lower communication costs and energy savings can also be obtained. In this paper we will present two possible implementations of the ART and FuzzyART neural-networks algorithms, which are unsupervised learning methods for categorization of the sensory inputs. They are tested on a data obtained from a set of several motes, equipped with several sensors each. Results from simulations of purposefully faulty sensors show the data robustness of these architectures. The proposed neural-networks classifiers have distributed short and long-term memory of the sensory inputs and can function as security alert when unusual sensor inputs are detected. AU - Kulakov, A AU - Davcev, D PY - 2005/// UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1425198 ER -