Speech analysis for fatigue and sleepiness detection of a pilot

Página do item simplificado
dc.creatorCarla Aparecidade Vasconcelos
dc.creatorMaurílio Nunes Vieira
dc.creatorGöran Kecklund
dc.creatorHani Camille Yehia
dc.date.accessioned2025-05-22T13:14:01Z
dc.date.accessioned2025-09-09T01:33:01Z
dc.date.available2025-05-22T13:14:01Z
dc.date.issued2019
dc.identifier.doihttps://doi.org/10.3357/amhp.5134.2019
dc.identifier.issn2375-6314
dc.identifier.urihttps://hdl.handle.net/1843/82446
dc.languageeng
dc.publisherUniversidade Federal de Minas Gerais
dc.relation.ispartofAerospace Medicine and Human Performance
dc.rightsAcesso Restrito
dc.subjectSistemas de reconhecimento de padrões
dc.subject.otherAccidents related to sleepiness, An exploration of the utility of mathematical modeling predicting fatigue from sleep/wake history and circadian phase applied in accident analysis
dc.titleSpeech analysis for fatigue and sleepiness detection of a pilot
dc.typeArtigo de periódico
local.citation.epage418
local.citation.issue4
local.citation.spage415
local.citation.volume90
local.description.resumoBACKGROUND: Mental fatigue and sleepiness are well recognized determinants of human-error related accidents and incidents in aviation. In Brazil, according to the Center for Investigation and Prevention of Aeronautical Accidents (CENIPA), the rate of accidents in the aerial modal is 1 per 2 d. Human factors are present in 90% of these accidents.CASE REPORT: This paper describes a retrospective study of the communication between a pilot and an air traffic control tower just before a fatal accident. The objective was the detection of fatigue and sleepiness of a pilot, who complained of these signs and symptoms before the flight, by means of voice and speech analysis. The in-depth accident analysis performed by CENIPA indicated that sleepiness and fatigue most likely contributed to the accident. Speech samples were analyzed for two conditions: 1) nonsleepy data recorded 35 h before the air crash (control condition), which were compared with 2) data from samples collected about 1 h before the accident and also during the disaster (sleepy condition). Audio recording analyses provided objective measures of the temporal organization of speech, such as hesitations, silent pauses, prolongation of final syllables, and syllable articulation rate.DISCUSSION: The results showed that speech during the day of the accident had significantly low elocution and articulation rates compared to the preceding day, also indicating that the methodology adopted in this study is feasible for detection of fatigue and sleepiness through speech analysis.
local.publisher.countryBrasil
local.publisher.departmentENG - DEPARTAMENTO DE ENGENHARIA ELETRÔNICA
local.publisher.initialsUFMG
local.url.externahttps://asma.kglmeridian.com/view/journals/amhp/90/4/article-p415.xml

Arquivos

Licença do pacote

Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
License.txt
Tamanho:
1.99 KB
Formato:
Plain Text
Descrição:
Baixar

Coleções

Artigo de Periódico

Logo UFMG