Accuracy–latency trade-offs and absent embedded validation in deep learning driver drowsiness detection: a PRISMA systematic review
Introduction: Driver drowsiness is a leading cause of road traffic fatalities worldwide, and the convergence of computer vision and deep learning has transformed driver-state monitoring by enabling non-invasive detection within Advanced Driver Assistance Systems (ADAS). Methods: This systematic lite...
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Artículo de revisión |
| Lenguaje: | inglés |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | Enlace permanente (DOI o Handle) Ver en el sistema de origen |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1881700519008796672 |
|---|---|
| author | Christian Wilbert Salas Yupanqui Cristhian Edy Llanque Tipo Frank Diego Choquehuanca Huayhua Ángel Rosendo Condori-Coaquira David Mamani-Pari Milton Edward Humpiri Flores Esteban Tocto-Cano |
| author_browse | Christian Wilbert Salas Yupanqui Cristhian Edy Llanque Tipo David Mamani-Pari Esteban Tocto-Cano Frank Diego Choquehuanca Huayhua Milton Edward Humpiri Flores Ángel Rosendo Condori-Coaquira |
| author_facet | Christian Wilbert Salas Yupanqui Cristhian Edy Llanque Tipo Frank Diego Choquehuanca Huayhua Ángel Rosendo Condori-Coaquira David Mamani-Pari Milton Edward Humpiri Flores Esteban Tocto-Cano |
| author_sort | Christian Wilbert Salas Yupanqui |
| collection | Producción científica |
| description | Introduction: Driver drowsiness is a leading cause of road traffic fatalities worldwide, and the convergence of computer vision and deep learning has transformed driver-state monitoring by enabling non-invasive detection within Advanced Driver Assistance Systems (ADAS). Methods: This systematic literature review, conducted using the PRISMA 2020 methodology and the Kitchenham protocol, synthesizes findings from 33 peer-reviewed studies published between January 2021 and October 2025 to examine the architectures, biomarkers, performance benchmarks, and deployment barriers of deep-learning-based drowsiness detection. Results: The literature is dominated by convolutional single-pass designs; no reviewed model combines an accuracy above 99% with a latency below 100 ms, and none were evaluated on embedded or automotive-grade hardware. Discussion: This distribution highlights a persistent accuracy-latency trade-off and emphasizes the need for embedded hardware and cross-dataset evaluation. By synthesizing the available evidence, this review characterizes the current state of the art and proposes a prioritized framework for selecting deep learning architectures for embedded ADAS applications. |
| format | Review |
| id | openalex:W7204817613 |
| institution | UPeU |
| language | English |
| publishDate | 2026 |
| publishDateRange | 2026 |
| publishDateSort | 2026 |
| record_format | dspace |
| spelling | openalex:W7204817613Accuracy–latency trade-offs and absent embedded validation in deep learning driver drowsiness detection: a PRISMA systematic reviewChristian Wilbert Salas YupanquiCristhian Edy Llanque TipoFrank Diego Choquehuanca HuayhuaÁngel Rosendo Condori-CoaquiraDavid Mamani-PariMilton Edward Humpiri FloresEsteban Tocto-Canodriver drowsiness detectiondeep learningaccuracy-latency trade-offdriver assistance systemsdriver state monitoringconvolutional neural networkscross-dataset evaluationmodel selection frameworkroad safetySleep and Work-Related FatigueHuman-Automation Interaction and SafetyAdvanced Neural Network ApplicationsIntroduction: Driver drowsiness is a leading cause of road traffic fatalities worldwide, and the convergence of computer vision and deep learning has transformed driver-state monitoring by enabling non-invasive detection within Advanced Driver Assistance Systems (ADAS). Methods: This systematic literature review, conducted using the PRISMA 2020 methodology and the Kitchenham protocol, synthesizes findings from 33 peer-reviewed studies published between January 2021 and October 2025 to examine the architectures, biomarkers, performance benchmarks, and deployment barriers of deep-learning-based drowsiness detection. Results: The literature is dominated by convolutional single-pass designs; no reviewed model combines an accuracy above 99% with a latency below 100 ms, and none were evaluated on embedded or automotive-grade hardware. Discussion: This distribution highlights a persistent accuracy-latency trade-off and emphasizes the need for embedded hardware and cross-dataset evaluation. By synthesizing the available evidence, this review characterizes the current state of the art and proposes a prioritized framework for selecting deep learning architectures for embedded ADAS applications.Reviewhttps://doi.org/10.3389/frai.2026.1871926https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2026.1871926/pdfW7204817613enFrontiers in Artificial Intelligence2624-82122026-08-31 |
| spellingShingle | driver drowsiness detection deep learning accuracy-latency trade-off driver assistance systems driver state monitoring convolutional neural networks cross-dataset evaluation model selection framework road safety Sleep and Work-Related Fatigue Human-Automation Interaction and Safety Advanced Neural Network Applications Christian Wilbert Salas Yupanqui Cristhian Edy Llanque Tipo Frank Diego Choquehuanca Huayhua Ángel Rosendo Condori-Coaquira David Mamani-Pari Milton Edward Humpiri Flores Esteban Tocto-Cano Accuracy–latency trade-offs and absent embedded validation in deep learning driver drowsiness detection: a PRISMA systematic review |
| title | Accuracy–latency trade-offs and absent embedded validation in deep learning driver drowsiness detection: a PRISMA systematic review |
| title_full | Accuracy–latency trade-offs and absent embedded validation in deep learning driver drowsiness detection: a PRISMA systematic review |
| title_fullStr | Accuracy–latency trade-offs and absent embedded validation in deep learning driver drowsiness detection: a PRISMA systematic review |
| title_full_unstemmed | Accuracy–latency trade-offs and absent embedded validation in deep learning driver drowsiness detection: a PRISMA systematic review |
| title_short | Accuracy–latency trade-offs and absent embedded validation in deep learning driver drowsiness detection: a PRISMA systematic review |
| title_sort | accuracy latency trade offs and absent embedded validation in deep learning driver drowsiness detection a prisma systematic review |
| topic | driver drowsiness detection deep learning accuracy-latency trade-off driver assistance systems driver state monitoring convolutional neural networks cross-dataset evaluation model selection framework road safety Sleep and Work-Related Fatigue Human-Automation Interaction and Safety Advanced Neural Network Applications |
| topic_facet | driver drowsiness detection deep learning accuracy-latency trade-off driver assistance systems driver state monitoring convolutional neural networks cross-dataset evaluation model selection framework road safety Sleep and Work-Related Fatigue Human-Automation Interaction and Safety Advanced Neural Network Applications |
| url | https://doi.org/10.3389/frai.2026.1871926 https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2026.1871926/pdf |
| work_keys_str_mv | AT christianwilbertsalasyupanqui accuracylatencytradeoffsandabsentembeddedvalidationindeeplearningdriverdrowsinessdetectionaprismasystematicreview AT cristhianedyllanquetipo accuracylatencytradeoffsandabsentembeddedvalidationindeeplearningdriverdrowsinessdetectionaprismasystematicreview AT frankdiegochoquehuancahuayhua accuracylatencytradeoffsandabsentembeddedvalidationindeeplearningdriverdrowsinessdetectionaprismasystematicreview AT angelrosendocondoricoaquira accuracylatencytradeoffsandabsentembeddedvalidationindeeplearningdriverdrowsinessdetectionaprismasystematicreview AT davidmamanipari accuracylatencytradeoffsandabsentembeddedvalidationindeeplearningdriverdrowsinessdetectionaprismasystematicreview AT miltonedwardhumpiriflores accuracylatencytradeoffsandabsentembeddedvalidationindeeplearningdriverdrowsinessdetectionaprismasystematicreview AT estebantoctocano accuracylatencytradeoffsandabsentembeddedvalidationindeeplearningdriverdrowsinessdetectionaprismasystematicreview |