{"id":{"repo_id":"nps","oai_identifier":"oai:calhoun.nps.edu:10945/71009"},"canonical_url":"https://search.dev.ndltd.org/etd/nps/oai:calhoun.nps.edu:10945/71009","repository":{"repo_id":"nps","name":"Naval Postgraduate School","base_url":"https://calhoun.nps.edu/server/oai/request"},"display":{"title":"COGNITIVE RADIO CLUSTERING ALGORITHM FOR SWARMS USING NEURAL NETWORKS","abstract":"Spectral scarcity is a problem faced by many communications systems, in and outside the military. A cognitive radio network is an approach that opportunistically exploits the broadcasting spectrum. The basic concept includes classifying users into two types: primary and secondary. The primary users have priority in the resource allocation process, while the secondary users need to use the spectrum for communication. This thesis seeks to apply the cognitive radio concept to enable swarm communication in a high-traffic environment. Primary users may include prioritized friendly or adversary transmitters that cannot be controlled. This research employs cognitive radio concepts and machine learning algorithms to develop a dynamic clustering technique within the network that will optimize resource allocation. Three approaches are proposed to train a neural network to find an optimal spectrum allocation. Even though the proposed algorithm did not outperform the baseline heuristic, the existence of an optimal solution was shown to exist. It is recommended that this study be continued as the algorithms used can be further modified and applied in various ways.","abstract_html":"Spectral scarcity is a problem faced by many communications systems, in and outside the military. A cognitive radio network is an approach that opportunistically exploits the broadcasting spectrum. The basic concept includes classifying users into two types: primary and secondary. The primary users have priority in the resource allocation process, while the secondary users need to use the spectrum for communication. This thesis seeks to apply the cognitive radio concept to enable swarm communication in a high-traffic environment. Primary users may include prioritized friendly or adversary transmitters that cannot be controlled. This research employs cognitive radio concepts and machine learning algorithms to develop a dynamic clustering technique within the network that will optimize resource allocation. Three approaches are proposed to train a neural network to find an optimal spectrum allocation. Even though the proposed algorithm did not outperform the baseline heuristic, the existence of an optimal solution was shown to exist. It is recommended that this study be continued as the algorithms used can be further modified and applied in various ways.","abstract_has_math":false,"creators":["Frydman, Uriel D."],"institution":"Monterey, CA; Naval Postgraduate School","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Electrical and Computer Engineering (ECE)","school":null,"contributors":[],"advisors":["Thulasiraman, Preetha"],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-09","date_published":"2022-09","updated_at":"2026-07-27T20:25:31Z","subjects":[],"languages":[],"rights":["Copyright is reserved by the copyright owner."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10945/71009","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Thulasiraman, Preetha"]},{"key":"dc:contributor.department","label":"Department","values":["Electrical and Computer Engineering (ECE)"]},{"key":"dc:creator","label":"Author","values":["Frydman, Uriel D."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2022-11-17T20:54:38Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2022-11-17T20:54:38Z"]},{"key":"dc:date.issued","label":"Date","values":["2022-09"]},{"key":"dc:publisher","label":"Institution","values":["Monterey, CA; Naval Postgraduate School"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["Copyright is reserved by the copyright owner."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10945/71009"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Spectral scarcity is a problem faced by many communications systems, in and outside the military. A cognitive radio network is an approach that opportunistically exploits the broadcasting spectrum. The basic concept includes classifying users into two types: primary and secondary. The primary users have priority in the resource allocation process, while the secondary users need to use the spectrum for communication. This thesis seeks to apply the cognitive radio concept to enable swarm communication in a high-traffic environment. Primary users may include prioritized friendly or adversary transmitters that cannot be controlled. This research employs cognitive radio concepts and machine learning algorithms to develop a dynamic clustering technique within the network that will optimize resource allocation. Three approaches are proposed to train a neural network to find an optimal spectrum allocation. Even though the proposed algorithm did not outperform the baseline heuristic, the existence of an optimal solution was shown to exist. It is recommended that this study be continued as the algorithms used can be further modified and applied in various ways."]},{"key":"dc:title","label":"Title","values":["COGNITIVE RADIO CLUSTERING ALGORITHM FOR SWARMS USING NEURAL NETWORKS"]}]}],"canonical_facts":{"dc:contributor.advisor":["Thulasiraman, Preetha"],"dc:contributor.department":["Electrical and Computer Engineering (ECE)"],"dc:creator":["Frydman, Uriel D."],"dc:date.accessioned":["2022-11-17T20:54:38Z"],"dc:date.available":["2022-11-17T20:54:38Z"],"dc:date.issued":["2022-09"],"dc:description.abstract":["Spectral scarcity is a problem faced by many communications systems, in and outside the military. A cognitive radio network is an approach that opportunistically exploits the broadcasting spectrum. The basic concept includes classifying users into two types: primary and secondary. The primary users have priority in the resource allocation process, while the secondary users need to use the spectrum for communication. This thesis seeks to apply the cognitive radio concept to enable swarm communication in a high-traffic environment. Primary users may include prioritized friendly or adversary transmitters that cannot be controlled. This research employs cognitive radio concepts and machine learning algorithms to develop a dynamic clustering technique within the network that will optimize resource allocation. Three approaches are proposed to train a neural network to find an optimal spectrum allocation. Even though the proposed algorithm did not outperform the baseline heuristic, the existence of an optimal solution was shown to exist. It is recommended that this study be continued as the algorithms used can be further modified and applied in various ways."],"dc:identifier.uri":["https://hdl.handle.net/10945/71009"],"dc:publisher":["Monterey, CA; Naval Postgraduate School"],"dc:rights":["Copyright is reserved by the copyright owner."],"dc:title":["COGNITIVE RADIO CLUSTERING ALGORITHM FOR SWARMS USING NEURAL NETWORKS"],"dc:type":["Thesis"]},"updated_at":"2026-07-27T20:25:31Z"}