{"id":{"repo_id":"umkc","oai_identifier":"oai:mospace.umsystem.edu:10355/87181"},"canonical_url":"https://search.dev.ndltd.org/etd/umkc/oai:mospace.umsystem.edu:10355/87181","repository":{"repo_id":"umkc","name":"University of Missouri - Kansas City","base_url":"https://mospace.umsystem.edu/oai/request"},"display":{"title":"AI-based Edge Computing System for Event Based Analytics","abstract":"In recent years, the Internet of Things (IoT) has received lots of attention due to its promising applications. Along with IoT evolution, we have witnessed advanced research for edge computing and its potential benefits of reducing latency, desirable availability, and privacy protection. However, cloud-based AI solutions are not readily deployable to the edge in IoT's data-driven world because of the difficulties of dealing with diverse sources, lack of availability, and network traffic congestion. We may need to move out to the edge of networks and move closer to the users. However, there are still significant challenges in deploying AI solutions to the edge of networks, but it becomes even more challenging when considering big real-time data. \\indent This dissertation hypothesizes that edge intelligence is required for event-driven analytics and actionable services demanded by the users. We have proposed a novel AI-based edge computing system, called AI-based edge computing system for event Analytics, based on the event-based approach for light-weighted data analytics and scalable multi-sensor fusion of complex real-time data. We have developed the prototype with low-cost IoT devices and sensors for edge intelligence with indoor and outdoor environment events, including air quality, noises, and in-home diagnostic. We have also evaluated event-driven analytics in terms of the scalability and flexibility of continuous signal streams or environmental sensing for noises, temperature, humidity, lighting, air quality sensing. Simulation and experimental results have validated that the deep learning models are better than the-state-of-art research with far less storage and computing resource requirements. Therefore, we have shown that the system has event-driven analytics capability, and it is suitable for real-time detection through diverse events with rapidly changing conditions.","abstract_html":"In recent years, the Internet of Things (IoT) has received lots of attention due to its promising applications. Along with IoT evolution, we have witnessed advanced research for edge computing and its potential benefits of reducing latency, desirable availability, and privacy protection. However, cloud-based AI solutions are not readily deployable to the edge in IoT's data-driven world because of the difficulties of dealing with diverse sources, lack of availability, and network traffic congestion. We may need to move out to the edge of networks and move closer to the users. However, there are still significant challenges in deploying AI solutions to the edge of networks, but it becomes even more challenging when considering big real-time data. \\indent This dissertation hypothesizes that edge intelligence is required for event-driven analytics and actionable services demanded by the users. We have proposed a novel AI-based edge computing system, called AI-based edge computing system for event Analytics, based on the event-based approach for light-weighted data analytics and scalable multi-sensor fusion of complex real-time data. We have developed the prototype with low-cost IoT devices and sensors for edge intelligence with indoor and outdoor environment events, including air quality, noises, and in-home diagnostic. We have also evaluated event-driven analytics in terms of the scalability and flexibility of continuous signal streams or environmental sensing for noises, temperature, humidity, lighting, air quality sensing. Simulation and experimental results have validated that the deep learning models are better than the-state-of-art research with far less storage and computing resource requirements. Therefore, we have shown that the system has event-driven analytics capability, and it is suitable for real-time detection through diverse events with rapidly changing conditions.","abstract_has_math":false,"creators":["Shah, Sayed Khushal"],"institution":"University of Missouri--Kansas City","degree_name":"Ph.D. (Doctor of Philosophy)","degree_level":"Doctoral","degree_discipline":"Computer Science (UMKC)","degree_department":null,"school":null,"contributors":[],"advisors":["Lee, Yugyung, 1960-"],"committee_chairs":[],"committee_members":[],"year":2021,"date_issued":"2021","date_published":"2021","updated_at":"2026-07-24T05:17:24Z","subjects":[],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10355/87181","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Lee, Yugyung, 1960-"]},{"key":"dc:creator","label":"Author","values":["Shah, Sayed Khushal"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2021-10-06T16:05:38Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2021-10-06T16:05:38Z"]},{"key":"dc:date.issued","label":"Date","values":["2021"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science (UMKC)","Computer Networking and Communication Systems (UMKC)"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Doctoral"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D. (Doctor of Philosophy)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Missouri--Kansas City"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10355/87181"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Title from PDF of title page viewed October 25, 2021","Dissertation advisor: Yugyung Lee","Vita","Includes bibliographical references (pages 162-175)","Thesis (PH.D.)--School of Computing and Engineering. University of Missouri--Kansas City, 2021"]},{"key":"dc:description.abstract","label":"Abstract","values":["In recent years, the Internet of Things (IoT) has received lots of attention due to its promising applications. Along with IoT evolution, we have witnessed advanced research for edge computing and its potential benefits of reducing latency, desirable availability, and privacy protection. However, cloud-based AI solutions are not readily deployable to the edge in IoT's data-driven world because of the difficulties of dealing with diverse sources, lack of availability, and network traffic congestion. We may need to move out to the edge of networks and move closer to the users. However, there are still significant challenges in deploying AI solutions to the edge of networks, but it becomes even more challenging when considering big real-time data. \\indent This dissertation hypothesizes that edge intelligence is required for event-driven analytics and actionable services demanded by the users. We have proposed a novel AI-based edge computing system, called AI-based edge computing system for event Analytics, based on the event-based approach for light-weighted data analytics and scalable multi-sensor fusion of complex real-time data. We have developed the prototype with low-cost IoT devices and sensors for edge intelligence with indoor and outdoor environment events, including air quality, noises, and in-home diagnostic. We have also evaluated event-driven analytics in terms of the scalability and flexibility of continuous signal streams or environmental sensing for noises, temperature, humidity, lighting, air quality sensing. Simulation and experimental results have validated that the deep learning models are better than the-state-of-art research with far less storage and computing resource requirements. Therefore, we have shown that the system has event-driven analytics capability, and it is suitable for real-time detection through diverse events with rapidly changing conditions."]},{"key":"dc:title","label":"Title","values":["AI-based Edge Computing System for Event Based Analytics"]}]}],"canonical_facts":{"dc:contributor.advisor":["Lee, Yugyung, 1960-"],"dc:creator":["Shah, Sayed Khushal"],"dc:date.accessioned":["2021-10-06T16:05:38Z"],"dc:date.available":["2021-10-06T16:05:38Z"],"dc:date.issued":["2021"],"dc:description":["Title from PDF of title page viewed October 25, 2021","Dissertation advisor: Yugyung Lee","Vita","Includes bibliographical references (pages 162-175)","Thesis (PH.D.)--School of Computing and Engineering. University of Missouri--Kansas City, 2021"],"dc:description.abstract":["In recent years, the Internet of Things (IoT) has received lots of attention due to its promising applications. Along with IoT evolution, we have witnessed advanced research for edge computing and its potential benefits of reducing latency, desirable availability, and privacy protection. However, cloud-based AI solutions are not readily deployable to the edge in IoT's data-driven world because of the difficulties of dealing with diverse sources, lack of availability, and network traffic congestion. We may need to move out to the edge of networks and move closer to the users. However, there are still significant challenges in deploying AI solutions to the edge of networks, but it becomes even more challenging when considering big real-time data. \\indent This dissertation hypothesizes that edge intelligence is required for event-driven analytics and actionable services demanded by the users. We have proposed a novel AI-based edge computing system, called AI-based edge computing system for event Analytics, based on the event-based approach for light-weighted data analytics and scalable multi-sensor fusion of complex real-time data. We have developed the prototype with low-cost IoT devices and sensors for edge intelligence with indoor and outdoor environment events, including air quality, noises, and in-home diagnostic. We have also evaluated event-driven analytics in terms of the scalability and flexibility of continuous signal streams or environmental sensing for noises, temperature, humidity, lighting, air quality sensing. Simulation and experimental results have validated that the deep learning models are better than the-state-of-art research with far less storage and computing resource requirements. Therefore, we have shown that the system has event-driven analytics capability, and it is suitable for real-time detection through diverse events with rapidly changing conditions."],"dc:identifier.uri":["https://hdl.handle.net/10355/87181"],"dc:title":["AI-based Edge Computing System for Event Based Analytics"],"thesis:degree_discipline":["Computer Science (UMKC)","Computer Networking and Communication Systems (UMKC)"],"thesis:degree_level":["Doctoral"],"thesis:degree_name":["Ph.D. (Doctor of Philosophy)"],"thesis:institution_name":["University of Missouri--Kansas City"]},"updated_at":"2026-07-24T05:17:24Z"}