Sumaiya Suravee

Sumaiya Suravee

Auto-generated profile, based on publicly available information

Sumaiya Suravee

Universität Greifswald

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 August 2023 in ACM Computing Surveys
Verified
Journal Article
Open access
SZSamaneh Zolfaghari
Samaneh Zolfaghari
SSSumaiya Suravee
Sumaiya Suravee
Daniele RiboniDaniele Riboni
Daniele Riboni
Kristina YordanovaKristina Yordanova
Kristina Yordanova
Locomotion characteristics and movement patterns are reliable indicators of neurodegenerative diseases (NDDs). This survey provides a systematic literature review of locomotion data mining systems for supporting NDD diagnosis. We discuss techniques for discovering low-level locomotion indicators, sensor data acquisition and processing methods, and NDD detection algorithms. The survey presents a comprehensive discussion on the main challenges for this active area, including the addressed diseases, locomotion data types, duration of monitoring, employed algorithms, and experimental validation strategies. We also identify prominent open challenges and research directions regarding ethics and privacy issues, technological and usability aspects, and availability of public benchmarks.

1 January 2024
Verified
Conference Paper
Open access
PDF file
DYDipendra Yadav
Dipendra Yadav
SSSumaiya Suravee
Sumaiya Suravee
TSTobias Strauß
Tobias Strauß
Kristina YordanovaKristina Yordanova
Kristina Yordanova
Dipendra Yadav, Sumaiya Suravee, Tobias Strauß, Kristina Yordanova. Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024). 2024.

28 June 2024
Verified
Book Chapter
Closed access
PDF file
MBMaurice Boiting
Maurice Boiting
NTNiklas Tschorn
Niklas Tschorn
SSSumaiya Suravee
Sumaiya Suravee
Kristina YordanovaKristina Yordanova
Kristina Yordanova
MHMargareta Halek
Margareta Halek
ABAnja Burmann
Anja Burmann


1 May 2026 in Frontiers in Aging
Verified
Journal Article
Open access
PDF file
SSSumaiya Suravee
Sumaiya Suravee
CPChristiane Pinkert
Christiane Pinkert
IHIris Hochgraeber
Iris Hochgraeber
MHMargareta Halek
Margareta Halek
BHBernhard Holle
Bernhard Holle
KYKristina Yordanova
Kristina Yordanova
People with dementia (PwD) face cognitive decline, placing added stress on family caregivers. Challenging behaviour, such as agitation, is one of the prominent behaviours exhibited by PwD, and family caregivers are often faced with the challenge of finding an appropriate intervention strategy to cope with it. To address this problem, current research focuses on developing digital solutions for the support of unprofessional caregivers, allowing them to ease the stress factor while dealing with agitation. A major challenge in any digital solution is the required domain knowledge. This knowledge includes information about the types of agitated behaviour, living and socio-economic conditions of the PwD and non-pharmaceutical interventions, which the caregiver can apply. We refer to this structured knowledge as an ontology. This study focuses on the development of the eDEM-Connect Ontology: Ontology of Dementia-related Agitation and Relationship between Informal Caregivers and Persons with Dementia (EDEM-CONNECTONTO) as the formalised domain knowledge for providing adequate support to caregivers. The knowledge is elicited through a systematic literature review, analysis of existing ontologies, workshops with experts, and interviews with informal caregivers. EDEM-CONNECTONTO consists of 252 Concepts, 16 relations, and 241 individuals. The ontology is implemented in the Web Ontology Language (OWL) and validated with the Protégé ontology development software. The results from the evaluation show that it meets the standard for biomedical ontologies. Furthermore, EDEM-CONNECTONTO is applied in several tasks related to the development of digital support systems for caregivers of PwD, demonstrating its practical applicability within the domain. The proposed ontology provides a structured semantic foundation for ontology-guided data annotation, knowledge graph construction, and GraphRAG-based caregiver-support applications. By formally modelling types of agitation, causes, consequences, PwD-caregiver relations, and non-pharmacological interventions, EDEM-CONNECTONTO enables explainable digital tools that support informal caregivers in identifying agitation patterns and selecting appropriate care strategies, thereby contributing to improved caregiver support and reduced caregiving stress.