Matches in SemOpenAlex for { <https://semopenalex.org/work/W3195847314> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W3195847314 abstract "The IoT is in a continuous evolution thanks to new technologies that openthe doors to various applications. While the structure of the IoT network remains the sameover the years, specifically composed of a server, gateways, and nodes, their tasks changeaccording to new challenges: the use of multimedia information and the large amount of datacreated by millions of devices forces the system to move from the cloud-centric approach to the thing-centric approach, wherenodes partially process the information. Computing at the sensor node level solveswell-known problems like scalability and privacy concerns. However, this study’s primaryfocus is on the impact that bringing the computation at the edge has on energy:continuous transmission of multimedia data drains the battery, and processing informationon the node reduces the amount of data transferred to event-based alerts. Nevertheless, mostof the foundational services for IoT applications are provided by AI. Dueto this class of algorithms’ complexity, they are always delegated to GPUs or devices withan energy budget that is orders of magnitude more than an IoT node, which shouldbe energy-neutral and powered only by energy harvesters. Enabling AI on IoT nodesis a challenging task. From the software side,this work explores the most recent compression techniques for NN,enabling the reduction of state-of-the-art networks to make them fit in microcontroller systems. From the hardware side, this thesis focuses on hardware selection. It compares the AI algorithms’ efficiency running on both well-established microcontrollers and state-of-the-art processors. An additional contribution towards energy-efficient AI is the exploration of hardware for acquisition and pre-processing of sound data, analyzing the data’s quality for further classification. Moreover, the combination of software andhardware co-design is the key point of this thesis to bring AI to the very edge of the IoT network." @default.
- W3195847314 created "2021-08-30" @default.
- W3195847314 creator A5061643938 @default.
- W3195847314 date "2021-04-13" @default.
- W3195847314 modified "2023-09-27" @default.
- W3195847314 title "Near Sensor Artificial Intelligence on IoT Devices for Smart Cities" @default.
- W3195847314 doi "https://doi.org/10.6092/unibo/amsdottorato/9658" @default.
- W3195847314 hasPublicationYear "2021" @default.
- W3195847314 type Work @default.
- W3195847314 sameAs 3195847314 @default.
- W3195847314 citedByCount "0" @default.
- W3195847314 crossrefType "dissertation" @default.
- W3195847314 hasAuthorship W3195847314A5061643938 @default.
- W3195847314 hasConcept C108037233 @default.
- W3195847314 hasConcept C111185680 @default.
- W3195847314 hasConcept C111919701 @default.
- W3195847314 hasConcept C120314980 @default.
- W3195847314 hasConcept C127413603 @default.
- W3195847314 hasConcept C138236772 @default.
- W3195847314 hasConcept C149635348 @default.
- W3195847314 hasConcept C154945302 @default.
- W3195847314 hasConcept C162307627 @default.
- W3195847314 hasConcept C173018170 @default.
- W3195847314 hasConcept C24590314 @default.
- W3195847314 hasConcept C2777904410 @default.
- W3195847314 hasConcept C2778456923 @default.
- W3195847314 hasConcept C31258907 @default.
- W3195847314 hasConcept C41008148 @default.
- W3195847314 hasConcept C41971633 @default.
- W3195847314 hasConcept C48044578 @default.
- W3195847314 hasConcept C555944384 @default.
- W3195847314 hasConcept C62611344 @default.
- W3195847314 hasConcept C66938386 @default.
- W3195847314 hasConcept C79974875 @default.
- W3195847314 hasConcept C81860439 @default.
- W3195847314 hasConcept C98045186 @default.
- W3195847314 hasConceptScore W3195847314C108037233 @default.
- W3195847314 hasConceptScore W3195847314C111185680 @default.
- W3195847314 hasConceptScore W3195847314C111919701 @default.
- W3195847314 hasConceptScore W3195847314C120314980 @default.
- W3195847314 hasConceptScore W3195847314C127413603 @default.
- W3195847314 hasConceptScore W3195847314C138236772 @default.
- W3195847314 hasConceptScore W3195847314C149635348 @default.
- W3195847314 hasConceptScore W3195847314C154945302 @default.
- W3195847314 hasConceptScore W3195847314C162307627 @default.
- W3195847314 hasConceptScore W3195847314C173018170 @default.
- W3195847314 hasConceptScore W3195847314C24590314 @default.
- W3195847314 hasConceptScore W3195847314C2777904410 @default.
- W3195847314 hasConceptScore W3195847314C2778456923 @default.
- W3195847314 hasConceptScore W3195847314C31258907 @default.
- W3195847314 hasConceptScore W3195847314C41008148 @default.
- W3195847314 hasConceptScore W3195847314C41971633 @default.
- W3195847314 hasConceptScore W3195847314C48044578 @default.
- W3195847314 hasConceptScore W3195847314C555944384 @default.
- W3195847314 hasConceptScore W3195847314C62611344 @default.
- W3195847314 hasConceptScore W3195847314C66938386 @default.
- W3195847314 hasConceptScore W3195847314C79974875 @default.
- W3195847314 hasConceptScore W3195847314C81860439 @default.
- W3195847314 hasConceptScore W3195847314C98045186 @default.
- W3195847314 hasLocation W31958473141 @default.
- W3195847314 hasOpenAccess W3195847314 @default.
- W3195847314 hasPrimaryLocation W31958473141 @default.
- W3195847314 hasRelatedWork W2007873860 @default.
- W3195847314 hasRelatedWork W2557408231 @default.
- W3195847314 hasRelatedWork W2746659798 @default.
- W3195847314 hasRelatedWork W2796552221 @default.
- W3195847314 hasRelatedWork W2873799763 @default.
- W3195847314 hasRelatedWork W2890294238 @default.
- W3195847314 hasRelatedWork W2890782911 @default.
- W3195847314 hasRelatedWork W2896952648 @default.
- W3195847314 hasRelatedWork W2898680432 @default.
- W3195847314 hasRelatedWork W2967514105 @default.
- W3195847314 hasRelatedWork W2975750829 @default.
- W3195847314 hasRelatedWork W3008723941 @default.
- W3195847314 hasRelatedWork W3019056961 @default.
- W3195847314 hasRelatedWork W3023353766 @default.
- W3195847314 hasRelatedWork W3042932518 @default.
- W3195847314 hasRelatedWork W3142495258 @default.
- W3195847314 hasRelatedWork W3157503767 @default.
- W3195847314 hasRelatedWork W3194271618 @default.
- W3195847314 hasRelatedWork W3211877398 @default.
- W3195847314 hasRelatedWork W2739891099 @default.
- W3195847314 isParatext "false" @default.
- W3195847314 isRetracted "false" @default.
- W3195847314 magId "3195847314" @default.
- W3195847314 workType "dissertation" @default.