Persona:
Pérez Cabello de Alba, María Beatriz

Foto de perfil
Dirección de correo electrónico
ORCID
0000-0003-0477-6917
Fecha de nacimiento
Proyectos de investigación
Unidades organizativas
Puesto de trabajo
Apellidos
Pérez Cabello de Alba
Nombre de pila
María Beatriz
Nombre

Filtros

2023 - 20242
Restablecer filtros

Ajustes

Autor: Panesar, Kulvinder × search.filters.applied.f.itemDepartamento: Filologías Extranjeras y sus Lingüísticas ×

Resultados de la búsqueda

Mostrando 1 - 2 de 2
  • Miniatura
    Publicación
    A hybrid conceptual model using statistical and linguistic methods for pre-screening memory through language and cognition
    (Comares, 2024-11-09) Panesar, Kulvinder; Pérez Cabello de Alba, María Beatriz
    This work is multidisciplinary (informatics, Artificial Intelligence, linguistics, and cognitive psychology) and transversal (health needs of a social nature inspired by technology), and its objective is the pre-diagnosis of people with memory problems. Language and cognitive assessment will be carried out via language production and comprehension of speech as a pre-diagnosis of dementia. Dementia and associated conditions are a global health problem supported by diverse expert groups, communities, research, and innovation (Alzheimer 2018, 2021, 2022). To take a small step in proactive early detection, we will employ a language and cognition assessment model supported by the DementiaBank multimedia database. This will provide results in terms of indicators of any potential problems with language production and cognition, as well as recommendations for the participant and carer, and as a precursor to other clinical tests for the diagnosis of dementia. The intervention will help to understand the person’s cognitive status and the early onset dementia and support the planning of healthcare provision. We will create a hybrid solution that contributes to research related to Natural Language Understanding, AI healthcare applications, and insights into cognitive impairment assessment. In this paper we present a schematic visual representation of a hybrid modular conceptual framework of a conversational agent.
  • Miniatura
    Publicación
    Natural language processing-driven framework for the early detection of language and cognitive decline
    (Elsevier, 2023-12) Panesar, Kulvinder; Pérez Cabello de Alba, María Beatriz
    Natural Language Processing (NLP) technology has the potential to provide a non-invasive, cost-effective method using a timely intervention for detecting early-stage language and cognitive decline in individuals concerned about their memory. The proposed pre-screening language and cognition assessment model (PST-LCAM) is based on the functional linguistic model Role and Reference Grammar (RRG) to analyse and represent the structure and meaning of utterances, via a set of language production and cognition parameters. The model is trained on a Dementia TalkBank dataset with markers of cognitive decline aligned to the global deterioration scale (GDS). A hybrid approach of qualitative linguistic analysis and assessment is applied, which includes the mapping of participants´ tasks of speech utterances and words to RRG phenomena. It uses a metric-based scoring with resulting quantitative scores and qualitative indicators as pre-screening results. This model is to be deployed in a user-centred conversational assessment platform.