{"id":"https://openalex.org/W4320024090","doi":"https://doi.org/10.1109/bigdata55660.2022.10020541","title":"Enabling Real-Time Low-Cost Spectral Analysis on Edge Devices with Deep Neural Networks: a Robust Hybrid Approach","display_name":"Enabling Real-Time Low-Cost Spectral Analysis on Edge Devices with Deep Neural Networks: a Robust Hybrid Approach","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4320024090","doi":"https://doi.org/10.1109/bigdata55660.2022.10020541"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10020541","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata55660.2022.10020541","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063333627","display_name":"Xiang Xie","orcid":"https://orcid.org/0000-0002-4277-574X"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Xiang Xie","raw_affiliation_strings":["Karlsruhe Institute of Technology,Institute for Information Processing Technologies,Karlsruhe,Germany","Institute for Information Processing Technologies, Karlsruhe Institute of Technology, Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology,Institute for Information Processing Technologies,Karlsruhe,Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Institute for Information Processing Technologies, Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100736294","display_name":"Tiantian Chen","orcid":"https://orcid.org/0000-0002-8954-1430"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tiantian Chen","raw_affiliation_strings":["Karlsruhe Institute of Technology,Institute for Information Processing Technologies,Karlsruhe,Germany","Institute for Information Processing Technologies, Karlsruhe Institute of Technology, Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology,Institute for Information Processing Technologies,Karlsruhe,Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Institute for Information Processing Technologies, Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067846212","display_name":"Wilhelm Stork","orcid":"https://orcid.org/0000-0003-0579-4615"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wilhelm Stork","raw_affiliation_strings":["Karlsruhe Institute of Technology,Institute for Information Processing Technologies,Karlsruhe,Germany","Institute for Information Processing Technologies, Karlsruhe Institute of Technology, Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology,Institute for Information Processing Technologies,Karlsruhe,Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Institute for Information Processing Technologies, Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2431","last_page":"2436"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8474416732788086},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6141564846038818},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6047554612159729},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.5863732099533081},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.5109707117080688},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4946558177471161},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.47237446904182434},{"id":"https://openalex.org/keywords/network-architecture","display_name":"Network architecture","score":0.41680315136909485},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3502557873725891},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26208215951919556},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.15657207369804382},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.10825595259666443},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.08685129880905151}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8474416732788086},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6141564846038818},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6047554612159729},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.5863732099533081},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.5109707117080688},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4946558177471161},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.47237446904182434},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.41680315136909485},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3502557873725891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26208215951919556},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.15657207369804382},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.10825595259666443},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.08685129880905151},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10020541","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata55660.2022.10020541","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.4699999988079071,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2029505541","https://openalex.org/W2030819361","https://openalex.org/W2126981375","https://openalex.org/W2540786069","https://openalex.org/W2566523245","https://openalex.org/W2790034089","https://openalex.org/W2963446712","https://openalex.org/W2992742255","https://openalex.org/W3004366142","https://openalex.org/W3162485060","https://openalex.org/W4312513271","https://openalex.org/W4312696039","https://openalex.org/W4318147679","https://openalex.org/W6637373629","https://openalex.org/W6725739302"],"related_works":["https://openalex.org/W2178915921","https://openalex.org/W138634089","https://openalex.org/W4311454612","https://openalex.org/W4316042121","https://openalex.org/W2989221764","https://openalex.org/W4324368142","https://openalex.org/W3095393520","https://openalex.org/W3212680907","https://openalex.org/W3209017628","https://openalex.org/W4320024090"],"abstract_inverted_index":{"Recently,":[0],"neural-network-based":[1],"approaches":[2],"for":[3,123,197],"spectral":[4,58,195],"analysis":[5,59,196],"have":[6],"been":[7],"proposed":[8],"and":[9,39,62,84,142,156,182,199],"are":[10],"proven":[11],"to":[12,60,79,101,114,135,151],"be":[13,112],"successful.":[14],"However,":[15],"since":[16],"neural":[17,30,65,93],"networks":[18,31],"require":[19],"huge":[20],"computational":[21],"as":[22,24],"well":[23],"storage":[25,37],"resources,":[26],"the":[27,64,71,81,92,99,109,137],"application":[28],"of":[29,139],"may":[32],"face":[33],"latency,":[34],"memory":[35],"footprint,":[36],"size":[38,154,181],"power":[40],"consumption":[41],"issues,":[42],"especially":[43],"on":[44,130,187],"low-power":[45],"edge":[46,124],"devices.":[47,125],"In":[48],"this":[49],"paper,":[50],"we":[51,96,170],"propose":[52],"a":[53,103,116,167,173,177,188],"first":[54],"hybrid":[55],"approach":[56,147],"in":[57,163],"optimize":[61],"accelerate":[63],"network":[66,94,100,106,110],"execution":[67],"while":[68],"consistently":[69],"preserving":[70],"final":[72],"performance.":[73],"First,":[74],"feature":[75],"selection":[76],"is":[77],"performed":[78],"reduce":[80],"data":[82],"dimension":[83],"guarantee":[85],"an":[86],"efficient":[87],"input":[88],"throughput.":[89],"Then,":[90],"after":[91],"training,":[95],"further":[97],"prune":[98],"obtain":[102],"more":[104],"compact":[105],"architecture.":[107],"Finally,":[108],"will":[111],"quantized":[113],"reach":[115],"higher":[117],"compression":[118,155],"ratio":[119],"with":[120,159,175],"low-cost":[121],"operations":[122],"We":[126],"conduct":[127],"extensive":[128],"experiments":[129],"various":[131],"target":[132],"hardware":[133],"platforms":[134],"demonstrate":[136],"effectiveness":[138],"our":[140,146],"method,":[141],"results":[143],"show":[144],"that":[145],"can":[148],"achieve":[149],"up":[150],"52x":[152],"mode":[153],"600x":[157],"speedup":[158],"even":[160],"better":[161],"performance":[162],"most":[164],"cases.":[165],"As":[166],"representative":[168],"example,":[169],"successfully":[171],"deploy":[172],"DenseNet":[174],"only":[176],"0.1":[178],"MB":[179],"model":[180],"0.9":[183],"ms":[184],"inference":[185],"time":[186],"Raspberry":[189],"Pi,":[190],"which":[191],"enables":[192],"real-time":[193],"on-site":[194],"industrial":[198],"commercial":[200],"applications.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}