\"Wireless sensor networks (WSNs) are networks of autonomous nodes that sense, compute and communicate in order to monitor an environment collectively. Ad hoc deployment, dynamic environment and resource constraints in nodes need to be considered while addressing WSN challenges such as deployment, localization, routing and scheduling. Adaptive mechanisms that exhibit intelligent behavior in complex and dynamic environments are desirable to address these challenges. The potential of computational intelligence ( CI) based approaches for addressing WSN challenges is investigated in this study. Contributions of this dissertation are in the following three areas: critical literature analysis, new architectures and approaches, and new solutions to WSN challenges.
Challenges in WSNs are discussed, paradigms of CI are introduced and a comprehensive survey of CI-based WSN applications is conducted with an emphasis on pros, cons and suitability of CI methods for WSN applications. A discussion on multidimensional optimization in WSNs and a survey of the applications of particle swarm optimization (PSO) in WSNs are presented.
An adaptive critic design (ACD) having a new combination of a PSO-based actor and a multilayer perceptron (MLP) critic is introduced for dynamic optimization. Its effectiveness is demonstrated through dynamic sleep scheduling of WSN nodes for wildlife monitoring. Compact generalized neuron (GN) is investigated as a resource-efficient alternative to MLPs for classification, nonlinear function approximation and time series prediction. A recurrent GN (RGN) structure is introduced. The performance of GN and RGN is shown to be comparable to that of MLPs having a larger number of trainable parameters.
Autonomous deployment of sensor nodes from an unmanned aerial vehicle and distributed iterative node localization are investigated. These tasks are formulated as multidimensional optimization problems, and addressed through PSO and bacterial foraging algorithm. Lastly, an adaptive critic is developed using two GNs for dynamic sleep scheduling of WSN nodes. Its performance is compared with the results of the ACD having a PSO actor and an MLP critic\"--Abstract, page iv.
","abstract_html":"<p>"Wireless sensor networks (WSNs) are networks of autonomous nodes that sense, compute and communicate in order to monitor an environment collectively. Ad hoc deployment, dynamic environment and resource constraints in nodes need to be considered while addressing WSN challenges such as deployment, localization, routing and scheduling. Adaptive mechanisms that exhibit intelligent behavior in complex and dynamic environments are desirable to address these challenges. The potential of computational intelligence ( CI) based approaches for addressing WSN challenges is investigated in this study. Contributions of this dissertation are in the following three areas: critical literature analysis, new architectures and approaches, and new solutions to WSN challenges.</p> <p>Challenges in WSNs are discussed, paradigms of CI are introduced and a comprehensive survey of CI-based WSN applications is conducted with an emphasis on pros, cons and suitability of CI methods for WSN applications. A discussion on multidimensional optimization in WSNs and a survey of the applications of particle swarm optimization (PSO) in WSNs are presented.</p> <p>An adaptive critic design (ACD) having a new combination of a PSO-based actor and a multilayer perceptron (MLP) critic is introduced for dynamic optimization. Its effectiveness is demonstrated through dynamic sleep scheduling of WSN nodes for wildlife monitoring. Compact generalized neuron (GN) is investigated as a resource-efficient alternative to MLPs for classification, nonlinear function approximation and time series prediction. A recurrent GN (RGN) structure is introduced. The performance of GN and RGN is shown to be comparable to that of MLPs having a larger number of trainable parameters.</p> <p>Autonomous deployment of sensor nodes from an unmanned aerial vehicle and distributed iterative node localization are investigated. These tasks are formulated as multidimensional optimization problems, and addressed through PSO and bacterial foraging algorithm. Lastly, an adaptive critic is developed using two GNs for dynamic sleep scheduling of WSN nodes. Its performance is compared with the results of the ACD having a PSO actor and an MLP critic"--Abstract, page iv.</p>","abstract_has_math":false,"creators":["Kulkarni, Raghavendra V."],"institution":"Missouri University of Science and Technology","degree_name":"Ph. D. in Electrical Engineering","degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2016,"date_issued":"2016-02-10T08:00:00Z","date_published":"2016-02-10T08:00:00Z","updated_at":"2026-07-24T03:19:54Z","subjects":["Electrical and Computer Engineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://scholarsmine.mst.edu/doctoral_dissertations/1787","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Kulkarni, Raghavendra V."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2016-02-10T08:00:00Z"]},{"key":"dc:type","label":"Dc Type","values":["Dissertation - Open Access"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph. D. in Electrical Engineering"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Missouri University of Science and Technology"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical and Computer Engineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://scholarsmine.mst.edu/doctoral_dissertations/1787"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["\"Wireless sensor networks (WSNs) are networks of autonomous nodes that sense, compute and communicate in order to monitor an environment collectively. Ad hoc deployment, dynamic environment and resource constraints in nodes need to be considered while addressing WSN challenges such as deployment, localization, routing and scheduling. Adaptive mechanisms that exhibit intelligent behavior in complex and dynamic environments are desirable to address these challenges. The potential of computational intelligence ( CI) based approaches for addressing WSN challenges is investigated in this study. Contributions of this dissertation are in the following three areas: critical literature analysis, new architectures and approaches, and new solutions to WSN challenges.
Challenges in WSNs are discussed, paradigms of CI are introduced and a comprehensive survey of CI-based WSN applications is conducted with an emphasis on pros, cons and suitability of CI methods for WSN applications. A discussion on multidimensional optimization in WSNs and a survey of the applications of particle swarm optimization (PSO) in WSNs are presented.
An adaptive critic design (ACD) having a new combination of a PSO-based actor and a multilayer perceptron (MLP) critic is introduced for dynamic optimization. Its effectiveness is demonstrated through dynamic sleep scheduling of WSN nodes for wildlife monitoring. Compact generalized neuron (GN) is investigated as a resource-efficient alternative to MLPs for classification, nonlinear function approximation and time series prediction. A recurrent GN (RGN) structure is introduced. The performance of GN and RGN is shown to be comparable to that of MLPs having a larger number of trainable parameters.
Autonomous deployment of sensor nodes from an unmanned aerial vehicle and distributed iterative node localization are investigated. These tasks are formulated as multidimensional optimization problems, and addressed through PSO and bacterial foraging algorithm. Lastly, an adaptive critic is developed using two GNs for dynamic sleep scheduling of WSN nodes. Its performance is compared with the results of the ACD having a PSO actor and an MLP critic\"--Abstract, page iv.
"]},{"key":"dc:title","label":"Title","values":["Computational intelligence methods in wireless sensor networks"]}]}],"canonical_facts":{"dc:creator":["Kulkarni, Raghavendra V."],"dc:date.available":["2016-02-10T08:00:00Z"],"dc:description.abstract":["\"Wireless sensor networks (WSNs) are networks of autonomous nodes that sense, compute and communicate in order to monitor an environment collectively. Ad hoc deployment, dynamic environment and resource constraints in nodes need to be considered while addressing WSN challenges such as deployment, localization, routing and scheduling. Adaptive mechanisms that exhibit intelligent behavior in complex and dynamic environments are desirable to address these challenges. The potential of computational intelligence ( CI) based approaches for addressing WSN challenges is investigated in this study. Contributions of this dissertation are in the following three areas: critical literature analysis, new architectures and approaches, and new solutions to WSN challenges.
Challenges in WSNs are discussed, paradigms of CI are introduced and a comprehensive survey of CI-based WSN applications is conducted with an emphasis on pros, cons and suitability of CI methods for WSN applications. A discussion on multidimensional optimization in WSNs and a survey of the applications of particle swarm optimization (PSO) in WSNs are presented.
An adaptive critic design (ACD) having a new combination of a PSO-based actor and a multilayer perceptron (MLP) critic is introduced for dynamic optimization. Its effectiveness is demonstrated through dynamic sleep scheduling of WSN nodes for wildlife monitoring. Compact generalized neuron (GN) is investigated as a resource-efficient alternative to MLPs for classification, nonlinear function approximation and time series prediction. A recurrent GN (RGN) structure is introduced. The performance of GN and RGN is shown to be comparable to that of MLPs having a larger number of trainable parameters.
Autonomous deployment of sensor nodes from an unmanned aerial vehicle and distributed iterative node localization are investigated. These tasks are formulated as multidimensional optimization problems, and addressed through PSO and bacterial foraging algorithm. Lastly, an adaptive critic is developed using two GNs for dynamic sleep scheduling of WSN nodes. Its performance is compared with the results of the ACD having a PSO actor and an MLP critic\"--Abstract, page iv.
"],"dc:identifier":["https://scholarsmine.mst.edu/doctoral_dissertations/1787"],"dc:subject":["Electrical and Computer Engineering"],"dc:title":["Computational intelligence methods in wireless sensor networks"],"dc:type":["Dissertation - Open Access"],"thesis:degree_name":["Ph. D. in Electrical Engineering"],"thesis:institution_name":["Missouri University of Science and Technology"]},"updated_at":"2026-07-24T03:19:54Z"}