{"id":{"repo_id":"msu","oai_identifier":"oai:d.lib.msu.edu:etd_53205"},"canonical_url":"https://search.ndltd.org/etd/msu/oai:d.lib.msu.edu:etd_53205","repository":{"repo_id":"msu","name":"Michigan State University","base_url":"https://d.lib.msu.edu/oai"},"display":{"title":"A LOSSY COMPRESSION TECHNIQUE USING DISJOINT AUTOENCODERS FOR LORA COMMUNICATION","abstract":"Thesis (M.S.)--Michigan State University. Electrical and Computer Engineering - Master of Science, 2026","abstract_html":"Thesis (M.S.)--Michigan State University. Electrical and Computer Engineering - Master of Science, 2026","abstract_has_math":false,"creators":["Manoharan, Santhosh"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Biswas, Subir","Srivastava, Vaibhav","Traganitis, Panagiotis"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-11-18T18:59:44Z","subjects":["Electrical engineering","Computer engineering"],"languages":["eng"],"rights":["In Copyright"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:53205","local:Manoharan_grad.msu_0128N_22227"],"render_values":[{"text":"etd:53205","href":null,"code":true},{"text":"local:Manoharan_grad.msu_0128N_22227","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/doi:10.25335/trrp-rb67","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/doi:10.25335/trrp-rb67","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://d.lib.msu.edu/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Ad.lib.msu.edu%3Aetd_53205","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Biswas, Subir","Srivastava, Vaibhav","Traganitis, Panagiotis"]},{"key":"dc:creator","label":"Author","values":["Manoharan, Santhosh"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026"]},{"key":"dc:relation","label":"Dc Relation","values":["Electronic Theses & Dissertations"]},{"key":"dc:type","label":"Dc Type","values":["text","Electronic dissertations"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical engineering","Computer engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:53205","local:Manoharan_grad.msu_0128N_22227","https://doi.org/doi:10.25335/trrp-rb67"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (M.S.)--Michigan State University. Electrical and Computer Engineering - Master of Science, 2026","The increasing need for efficient and robust data transmission in IoT-based sensor networks over long-range, low-power wireless links motivates the development of lightweight, channel-aware compression frameworks deployable on resource-constrained edge devices. Advances in deep learning and differentiable channel modeling enable compression schemes that simultaneously reduce bandwidth usage and withstand real-world channel impairments. However, existing methods fail to achieve the desired combination of both within the computational constraints of edge devices. Therefore, a disjoint autoencoder framework integrated with a learnable LoRa channel module, jointly trained end-to-end and independently deployed at the transmitter and receiver, is proposed to address this gap.The proposed framework employs a CNN-based encoder-decoder pair trained through a two-stage procedure. A differentiable LoRa channel module approximating chirp spread spectrum modulation, wireless channel impairments, and spectral demodulation is incorporated during fine-tuning, enabling the learned latent representations to withstand real-world LoRa transmission conditions. A comprehensive evaluation is conducted across various architectural configurations on the Raspberry Pi Zero 2W platform, profiling reconstruction quality, bandwidth reduction, computational complexity, processing time, and power consumption under real outdoor line-of-sight conditions over distances up to 100 meters. The proposed framework provides a practical, deployable solution for bandwidth-efficient and channel-robust data transmission in LoRa-based IoT sensor networks, with a systematic design methodology applicable to a broad range of resource-constrained edge deployments.","Description based on online resource. Title from PDF t.p. (Michigan State University Fedora Repository, viewed ).","Includes bibliographical references."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf","1 online resource (114 p.) : ill."]},{"key":"dc:title","label":"Title","values":["A LOSSY COMPRESSION TECHNIQUE USING DISJOINT AUTOENCODERS FOR LORA COMMUNICATION"]}]}],"canonical_facts":{"dc:contributor":["Biswas, Subir","Srivastava, Vaibhav","Traganitis, Panagiotis"],"dc:creator":["Manoharan, Santhosh"],"dc:date":["2026"],"dc:description":["Thesis (M.S.)--Michigan State University. Electrical and Computer Engineering - Master of Science, 2026","The increasing need for efficient and robust data transmission in IoT-based sensor networks over long-range, low-power wireless links motivates the development of lightweight, channel-aware compression frameworks deployable on resource-constrained edge devices. Advances in deep learning and differentiable channel modeling enable compression schemes that simultaneously reduce bandwidth usage and withstand real-world channel impairments. However, existing methods fail to achieve the desired combination of both within the computational constraints of edge devices. Therefore, a disjoint autoencoder framework integrated with a learnable LoRa channel module, jointly trained end-to-end and independently deployed at the transmitter and receiver, is proposed to address this gap.The proposed framework employs a CNN-based encoder-decoder pair trained through a two-stage procedure. A differentiable LoRa channel module approximating chirp spread spectrum modulation, wireless channel impairments, and spectral demodulation is incorporated during fine-tuning, enabling the learned latent representations to withstand real-world LoRa transmission conditions. A comprehensive evaluation is conducted across various architectural configurations on the Raspberry Pi Zero 2W platform, profiling reconstruction quality, bandwidth reduction, computational complexity, processing time, and power consumption under real outdoor line-of-sight conditions over distances up to 100 meters. The proposed framework provides a practical, deployable solution for bandwidth-efficient and channel-robust data transmission in LoRa-based IoT sensor networks, with a systematic design methodology applicable to a broad range of resource-constrained edge deployments.","Description based on online resource. Title from PDF t.p. (Michigan State University Fedora Repository, viewed ).","Includes bibliographical references."],"dc:format":["application/pdf","1 online resource (114 p.) : ill."],"dc:identifier":["etd:53205","local:Manoharan_grad.msu_0128N_22227","https://doi.org/doi:10.25335/trrp-rb67"],"dc:language":["eng"],"dc:relation":["Electronic Theses & Dissertations"],"dc:rights":["In Copyright"],"dc:subject":["Electrical engineering","Computer engineering"],"dc:title":["A LOSSY COMPRESSION TECHNIQUE USING DISJOINT AUTOENCODERS FOR LORA COMMUNICATION"],"dc:type":["text","Electronic dissertations"]},"updated_at":"2026-11-18T18:59:44Z"}