{"id":"https://openalex.org/W7214076316","doi":"https://doi.org/10.64898/2026.09.17.752158","title":"Benchmarking Clustering Strategies for High-Dimensional Spike Time-Windows Data from Multi-Electrode Arrays","display_name":"Benchmarking Clustering Strategies for High-Dimensional Spike Time-Windows Data from Multi-Electrode Arrays","publication_year":2026,"publication_date":"2026-09-23","ids":{"openalex":"https://openalex.org/W7214076316","doi":"https://doi.org/10.64898/2026.09.17.752158"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.17.752158","doi":"https://doi.org/10.64898/2026.09.17.752158","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.17.752158","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/23/2026.09.17.752158.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/23/2026.09.17.752158.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062744502","display_name":"Lorenzo Sacchi","orcid":"https://orcid.org/0009-0007-7660-837X","observed_orcids":["https://orcid.org/0009-0007-7660-837X"]},"institutions":[{"id":"https://openalex.org/I83816512","display_name":"University of Genoa","ror":"https://ror.org/0107c5v14","country_code":"IT","type":"education","lineage":["https://openalex.org/I83816512"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lorenzo Sacchi","raw_affiliation_strings":["Dipartimento di Matematica, Universit\u00e0 di Genova, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Matematica, Universit\u00e0 di Genova, Italy","institution_ids":["https://openalex.org/I83816512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066610580","display_name":"Sara Sommariva","orcid":"https://orcid.org/0000-0003-1835-9399","observed_orcids":["https://orcid.org/0000-0003-1835-9399"]},"institutions":[{"id":"https://openalex.org/I83816512","display_name":"University of Genoa","ror":"https://ror.org/0107c5v14","country_code":"IT","type":"education","lineage":["https://openalex.org/I83816512"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Sara Sommariva","raw_affiliation_strings":["Dipartimento di Matematica, Universit\u00e0 di Genova, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Matematica, Universit\u00e0 di Genova, Italy","institution_ids":["https://openalex.org/I83816512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019701642","display_name":"Maurits Unkel","orcid":"https://orcid.org/0000-0003-1920-6001","observed_orcids":["https://orcid.org/0000-0003-1920-6001"]},"institutions":[{"id":"https://openalex.org/I2801952686","display_name":"Erasmus MC","ror":"https://ror.org/018906e22","country_code":"NL","type":"healthcare","lineage":["https://openalex.org/I2801952686"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Maurits Unkel","raw_affiliation_strings":["Department of Psychiatry, Erasmus MC University Medical Center, Rotterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Psychiatry, Erasmus MC University Medical Center, Rotterdam, The Netherlands","institution_ids":["https://openalex.org/I2801952686"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004639920","display_name":"Femke M. S. de Vrij","orcid":"https://orcid.org/0000-0003-0825-3806","observed_orcids":["https://orcid.org/0000-0003-0825-3806"]},"institutions":[{"id":"https://openalex.org/I2801952686","display_name":"Erasmus MC","ror":"https://ror.org/018906e22","country_code":"NL","type":"healthcare","lineage":["https://openalex.org/I2801952686"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Femke M.S. de Vrij","raw_affiliation_strings":["Department of Psychiatry, Erasmus MC University Medical Center, Rotterdam, The Netherlands","Erasmus MC Center of Expertise for Neurodevelopmental Disorders (ENCORE), Rotterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Psychiatry, Erasmus MC University Medical Center, Rotterdam, The Netherlands","institution_ids":["https://openalex.org/I2801952686"]},{"raw_affiliation_string":"Erasmus MC Center of Expertise for Neurodevelopmental Disorders (ENCORE), Rotterdam, The Netherlands","institution_ids":["https://openalex.org/I2801952686"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072706792","display_name":"Cristina Campi","orcid":"https://orcid.org/0000-0003-2105-8554","observed_orcids":["https://orcid.org/0000-0003-2105-8554"]},"institutions":[{"id":"https://openalex.org/I83816512","display_name":"University of Genoa","ror":"https://ror.org/0107c5v14","country_code":"IT","type":"education","lineage":["https://openalex.org/I83816512"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Cristina Campi","raw_affiliation_strings":["Dipartimento di Matematica, Universit\u00e0 di Genova, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Matematica, Universit\u00e0 di Genova, Italy","institution_ids":["https://openalex.org/I83816512"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5066610580"],"corresponding_institution_ids":["https://openalex.org/I83816512"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9253000020980835,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9253000020980835,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11601","display_name":"Neuroscience and Neural Engineering","score":0.01360000018030405,"subfield":{"id":"https://openalex.org/subfields/2804","display_name":"Cellular and Molecular Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.009499999694526196,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/microelectrode-arrays","display_name":"microelectrode arrays","score":0.9539999961853027},{"id":"https://openalex.org/keywords/unsupervised-clustering","display_name":"unsupervised clustering","score":0.7350000143051147},{"id":"https://openalex.org/keywords/high-dimensional-data","display_name":"high-dimensional data","score":0.7179999947547913},{"id":"https://openalex.org/keywords/nonstationary-time-series","display_name":"non-stationary time series","score":0.7990000247955322},{"id":"https://openalex.org/keywords/k-means-clustering","display_name":"K-means clustering","score":0.6430000066757202},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"hierarchical clustering","score":0.7839999794960022},{"id":"https://openalex.org/keywords/independent-component-analysis","display_name":"independent component analysis","score":0.8690000176429749},{"id":"https://openalex.org/keywords/kernel-pca","display_name":"kernel principal component analysis","score":0.9810000061988831},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"principal component analysis","score":0.9240000247955322},{"id":"https://openalex.org/keywords/distance-metrics","display_name":"distance measures","score":0.5820000171661377},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"noise reduction","score":0.6700000166893005}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.800599992275238},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6908000111579895},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6589000225067139},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.6528000235557556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5925999879837036},{"id":"https://openalex.org/C2781390188","wikidata":"https://www.wikidata.org/wiki/Q25203449","display_name":"Spike (software development)","level":2,"score":0.5637000203132629},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5552999973297119},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.51419997215271},{"id":"https://openalex.org/C58103923","wikidata":"https://www.wikidata.org/wiki/Q2286025","display_name":"Silhouette","level":2,"score":0.5072000026702881},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.49050000309944153},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4519999921321869},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.45159998536109924},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.4291999936103821},{"id":"https://openalex.org/C2777613131","wikidata":"https://www.wikidata.org/wiki/Q2003571","display_name":"Spike sorting","level":3,"score":0.4203999936580658},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4131999909877777},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4108000099658966},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.3919000029563904},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.3714999854564667},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.3407000005245209},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3327000141143799},{"id":"https://openalex.org/C186767784","wikidata":"https://www.wikidata.org/wiki/Q5162841","display_name":"Consensus clustering","level":5,"score":0.31439998745918274},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.3027999997138977},{"id":"https://openalex.org/C115328559","wikidata":"https://www.wikidata.org/wiki/Q4041956","display_name":"k-medians clustering","level":5,"score":0.3010999858379364},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.2897999882698059},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C2909946758","wikidata":"https://www.wikidata.org/wiki/Q194277","display_name":"Spike train","level":3,"score":0.27219998836517334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26669999957084656},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.26579999923706055},{"id":"https://openalex.org/C164660894","wikidata":"https://www.wikidata.org/wiki/Q2037833","display_name":"Piecewise","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C207968372","wikidata":"https://www.wikidata.org/wiki/Q310401","display_name":"k-means clustering","level":3,"score":0.2563999891281128},{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.17.752158","doi":"https://doi.org/10.64898/2026.09.17.752158","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.17.752158","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/23/2026.09.17.752158.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.17.752158","doi":"https://doi.org/10.64898/2026.09.17.752158","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.17.752158","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/23/2026.09.17.752158.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311030","display_name":"Istituto Nazionale di Alta Matematica \"Francesco Severi\"","ror":"https://ror.org/01vx64p53"},{"id":"https://openalex.org/F4320334079","display_name":"Gruppo Nazionale per il Calcolo Scientifico","ror":"https://ror.org/02rnys730"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214076316.pdf","grobid_xml":"https://content.openalex.org/works/W7214076316.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2794758172","https://openalex.org/W7171780833","https://openalex.org/W2678594852","https://openalex.org/W1977972180","https://openalex.org/W1985387745","https://openalex.org/W2889678141","https://openalex.org/W2146076516","https://openalex.org/W2153886236","https://openalex.org/W2000889718","https://openalex.org/W2132838253"],"abstract_inverted_index":{"Summary":[0],"From":[1],"a":[2,16,36,105,112],"statistical":[3],"point":[4],"of":[5,55,101,107,119,127,174],"view,":[6],"clustering":[7,20,61,86,180],"spike":[8,102,176],"time-windows":[9],"from":[10,111],"multi-electrode":[11],"arrays":[12],"(MEAs)":[13],"recordings":[14,110],"is":[15,30,39,151,161],"challenging":[17],"high-dimensional,":[18],"unsupervised":[19],"task":[21],"where":[22,148],"stationarity,":[23],"commonly":[24],"assumed":[25],"in":[26,125],"standard":[27,38],"time-series":[28],"analysis,":[29],"often":[31],"violated":[32],"and":[33,83,104,130,190],"for":[34,144],"which":[35],"gold":[37],"currently":[40],"unavailable.":[41],"Here":[42],"we":[43,91],"aim":[44],"at":[45],"providing":[46],"practical":[47],"guidance":[48],"on":[49],"how":[50],"to":[51,77],"cluster":[52],"this":[53],"type":[54],"data":[56,70,81],"by":[57,163],"systematically":[58],"comparing":[59],"108":[60],"pipelines":[62,122],"differing":[63],"along":[64],"three":[65],"main":[66],"dimensions:":[67],"(i)":[68],"the":[69,74,85,120,135,139,145,158,175,182],"feature":[71],"space;":[72],"(ii)":[73],"metrics":[75],"used":[76,92,143],"quantify":[78],"distance":[79,167],"between":[80],"points;":[82],"(iii)":[84],"algorithm.":[87],"For":[88],"our":[89,154],"benchmark":[90],"both":[93],"labeled":[94],"synthetic":[95,136],"data,":[96],"mimicking":[97],"four":[98],"physiologically-inspired":[99],"classes":[100],"time-windows,":[103],"set":[106],"real":[108,146],"MEAs":[109],"two-dimensional":[113],"in-vitro":[114],"neural":[115],"culture.":[116],"The":[117],"performance":[118],"competing":[121],"was":[123,142],"evaluated":[124],"terms":[126],"balanced":[128],"accuracy":[129],"computational":[131,184],"time":[132],"when":[133],"analyzing":[134],"datasets,":[137],"while":[138,186],"Silhouette":[140],"score":[141],"dataset,":[147],"no":[149],"ground-truth":[150],"available.":[152],"Overall,":[153],"analysis":[155],"shows":[156],"that":[157],"best":[159],"combination":[160],"formed":[162],"k-means":[164],"with":[165],"Euclidean":[166],"applied":[168],"after":[169],"Principal":[170],"Component":[171,188],"Analysis":[172,189],"(PCA)":[173],"time-windows.":[177],"Conversely,":[178],"hierarchical":[179],"showed":[181],"highest":[183],"burden,":[185],"Independent":[187],"kernel":[191],"PCA":[192],"provided":[193],"less":[194],"effective":[195],"noise":[196],"suppression.":[197]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-24T00:00:00"}