{"id":{"repo_id":"mtu","oai_identifier":"oai:digitalcommons.mtu.edu:etdr-1700"},"canonical_url":"https://search.ndltd.org/etd/mtu/oai:digitalcommons.mtu.edu:etdr-1700","repository":{"repo_id":"mtu","name":"Michigan Technological University","base_url":"https://digitalcommons.mtu.edu/do/oai/"},"display":{"title":"Resource Optimization in Wireless Sensor Networks for an Improved Field Coverage and Cooperative Target Tracking","abstract":"There are various challenges that face a wireless sensor network (WSN) that mainly originate from the limited resources a sensor node usually has. A sensor node often relies on a battery as a power supply which, due to its limited capacity, tends to shorten the life-time of the node and the network as a whole. Other challenges arise from the limited capabilities of the sensors/actuators a node is equipped with, leading to complication like a poor coverage of the event, or limited mobility in the environment. This dissertation deals with the coverage problem as well as the limited power and capabilities of a sensor node. In some environments, a controlled deployment of the WSN may not be attainable. In such case, the only viable option would be a random deployment over the region of interest (ROI), leading to a great deal of uncovered areas as well as many cutoff nodes. Three different scenarios are presented, each addressing the coverage problem for a distinct purpose. First, a multi-objective optimization is considered with the purpose of relocating the sensor nodes after the initial random deployment, through maximizing the field coverage while minimizing the cost of mobility. Simulations reveal the improvements in coverage, while maintaining the mobility cost to a minimum. In the second scenario, tracking a mobile target with a high level of accuracy is of interest. The relocation process was based on learning the spatial mobility trends of the targets. Results show the improvement in tracking accuracy in terms of mean square position error. The last scenario involves the use of inverse reinforcement learning (IRL) to predict the destination of a given target. This lay the ground for future exploration of the relocation problem to achieve improved prediction accuracy. Experiments investigated the interaction between prediction accuracy and terrain severity. The other WSN limitation is dealt with by introducing the concept of sparse sensing to schedule the measurements of sensor nodes. A hybrid WSN setup of low and high precision nodes is examined. Simulations showed that the greedy algorithm used for scheduling the nodes, realized a network that is more resilient to individual node failure. Moreover, the use of more affordable nodes stroke a better trade-off between deployment feasibility and precision.","abstract_html":"There are various challenges that face a wireless sensor network (WSN) that mainly originate from the limited resources a sensor node usually has. A sensor node often relies on a battery as a power supply which, due to its limited capacity, tends to shorten the life-time of the node and the network as a whole. Other challenges arise from the limited capabilities of the sensors/actuators a node is equipped with, leading to complication like a poor coverage of the event, or limited mobility in the environment. This dissertation deals with the coverage problem as well as the limited power and capabilities of a sensor node. In some environments, a controlled deployment of the WSN may not be attainable. In such case, the only viable option would be a random deployment over the region of interest (ROI), leading to a great deal of uncovered areas as well as many cutoff nodes. Three different scenarios are presented, each addressing the coverage problem for a distinct purpose. First, a multi-objective optimization is considered with the purpose of relocating the sensor nodes after the initial random deployment, through maximizing the field coverage while minimizing the cost of mobility. Simulations reveal the improvements in coverage, while maintaining the mobility cost to a minimum. In the second scenario, tracking a mobile target with a high level of accuracy is of interest. The relocation process was based on learning the spatial mobility trends of the targets. Results show the improvement in tracking accuracy in terms of mean square position error. The last scenario involves the use of inverse reinforcement learning (IRL) to predict the destination of a given target. This lay the ground for future exploration of the relocation problem to achieve improved prediction accuracy. Experiments investigated the interaction between prediction accuracy and terrain severity. The other WSN limitation is dealt with by introducing the concept of sparse sensing to schedule the measurements of sensor nodes. A hybrid WSN setup of low and high precision nodes is examined. Simulations showed that the greedy algorithm used for scheduling the nodes, realized a network that is more resilient to individual node failure. Moreover, the use of more affordable nodes stroke a better trade-off between deployment feasibility and precision.","abstract_has_math":false,"creators":["Sweidan, Husam"],"institution":null,"degree_name":"Doctor of Philosophy in Electrical Engineering (PhD)","degree_level":"Open Access Dissertation","degree_discipline":"Department of Electrical and Computer Engineering","degree_department":null,"school":null,"contributors":["Timothy C. Havens"],"advisors":[],"committee_chairs":[],"committee_members":["Aurenice M. Oliveira","Laura E. Brown","Zhaohui Wang"],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:17:16Z","subjects":["wireless sensor network","sparse sensing","Kalman filter","target tracking","evolutionary computation","artificial immune system algorithm","Artificial Intelligence and Robotics","Controls and Control Theory","Digital Communications and Networking","Robotics","Theory and Algorithms"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.mtu.edu/etdr/628"],"render_values":[{"text":"https://digitalcommons.mtu.edu/etdr/628","href":"https://digitalcommons.mtu.edu/etdr/628","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/10.37099/mtu.dc.etdr/628","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/10.37099/mtu.dc.etdr/628","record_label":"Repository record","record_kind":"doi","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.mtu.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.mtu.edu%3Aetdr-1700","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Timothy C. Havens"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Aurenice M. Oliveira","Laura E. Brown","Zhaohui Wang"]},{"key":"dc:creator","label":"Author","values":["Sweidan, Husam"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2019-04-13T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2018-01-01T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Department of Electrical and Computer Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Open Access Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy in Electrical Engineering (PhD)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["wireless sensor network","sparse sensing","Kalman filter","target tracking","evolutionary computation","artificial immune system algorithm","Artificial Intelligence and Robotics","Controls and Control Theory","Digital Communications and Networking","Robotics","Theory and Algorithms"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["10.37099/mtu.dc.etdr/628","https://digitalcommons.mtu.edu/etdr/628"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["There are various challenges that face a wireless sensor network (WSN) that mainly originate from the limited resources a sensor node usually has. A sensor node often relies on a battery as a power supply which, due to its limited capacity, tends to shorten the life-time of the node and the network as a whole. Other challenges arise from the limited capabilities of the sensors/actuators a node is equipped with, leading to complication like a poor coverage of the event, or limited mobility in the environment. This dissertation deals with the coverage problem as well as the limited power and capabilities of a sensor node. In some environments, a controlled deployment of the WSN may not be attainable. In such case, the only viable option would be a random deployment over the region of interest (ROI), leading to a great deal of uncovered areas as well as many cutoff nodes. Three different scenarios are presented, each addressing the coverage problem for a distinct purpose. First, a multi-objective optimization is considered with the purpose of relocating the sensor nodes after the initial random deployment, through maximizing the field coverage while minimizing the cost of mobility. Simulations reveal the improvements in coverage, while maintaining the mobility cost to a minimum. In the second scenario, tracking a mobile target with a high level of accuracy is of interest. The relocation process was based on learning the spatial mobility trends of the targets. Results show the improvement in tracking accuracy in terms of mean square position error. The last scenario involves the use of inverse reinforcement learning (IRL) to predict the destination of a given target. This lay the ground for future exploration of the relocation problem to achieve improved prediction accuracy. Experiments investigated the interaction between prediction accuracy and terrain severity. The other WSN limitation is dealt with by introducing the concept of sparse sensing to schedule the measurements of sensor nodes. A hybrid WSN setup of low and high precision nodes is examined. Simulations showed that the greedy algorithm used for scheduling the nodes, realized a network that is more resilient to individual node failure. Moreover, the use of more affordable nodes stroke a better trade-off between deployment feasibility and precision."]},{"key":"dc:title","label":"Title","values":["Resource Optimization in Wireless Sensor Networks for an Improved Field Coverage and Cooperative Target Tracking"]}]}],"canonical_facts":{"dc:contributor":["Timothy C. Havens"],"dc:contributor.committeemember":["Aurenice M. Oliveira","Laura E. Brown","Zhaohui Wang"],"dc:creator":["Sweidan, Husam"],"dc:date.available":["2019-04-13T07:00:00Z"],"dc:date.created":["2018-01-01T08:00:00Z"],"dc:description.abstract":["There are various challenges that face a wireless sensor network (WSN) that mainly originate from the limited resources a sensor node usually has. A sensor node often relies on a battery as a power supply which, due to its limited capacity, tends to shorten the life-time of the node and the network as a whole. Other challenges arise from the limited capabilities of the sensors/actuators a node is equipped with, leading to complication like a poor coverage of the event, or limited mobility in the environment. This dissertation deals with the coverage problem as well as the limited power and capabilities of a sensor node. In some environments, a controlled deployment of the WSN may not be attainable. In such case, the only viable option would be a random deployment over the region of interest (ROI), leading to a great deal of uncovered areas as well as many cutoff nodes. Three different scenarios are presented, each addressing the coverage problem for a distinct purpose. First, a multi-objective optimization is considered with the purpose of relocating the sensor nodes after the initial random deployment, through maximizing the field coverage while minimizing the cost of mobility. Simulations reveal the improvements in coverage, while maintaining the mobility cost to a minimum. In the second scenario, tracking a mobile target with a high level of accuracy is of interest. The relocation process was based on learning the spatial mobility trends of the targets. Results show the improvement in tracking accuracy in terms of mean square position error. The last scenario involves the use of inverse reinforcement learning (IRL) to predict the destination of a given target. This lay the ground for future exploration of the relocation problem to achieve improved prediction accuracy. Experiments investigated the interaction between prediction accuracy and terrain severity. The other WSN limitation is dealt with by introducing the concept of sparse sensing to schedule the measurements of sensor nodes. A hybrid WSN setup of low and high precision nodes is examined. Simulations showed that the greedy algorithm used for scheduling the nodes, realized a network that is more resilient to individual node failure. Moreover, the use of more affordable nodes stroke a better trade-off between deployment feasibility and precision."],"dc:identifier":["10.37099/mtu.dc.etdr/628","https://digitalcommons.mtu.edu/etdr/628"],"dc:subject":["wireless sensor network","sparse sensing","Kalman filter","target tracking","evolutionary computation","artificial immune system algorithm","Artificial Intelligence and Robotics","Controls and Control Theory","Digital Communications and Networking","Robotics","Theory and Algorithms"],"dc:title":["Resource Optimization in Wireless Sensor Networks for an Improved Field Coverage and Cooperative Target Tracking"],"thesis:degree_discipline":["Department of Electrical and Computer Engineering"],"thesis:degree_level":["Open Access Dissertation"],"thesis:degree_name":["Doctor of Philosophy in Electrical Engineering (PhD)"]},"updated_at":"2026-11-19T08:17:16Z"}