Güzin Kaya Aytutuldu

Güzin Kaya Aytutuldu

Auto-generated profile, based on publicly available information

Güzin Kaya Aytutuldu

Biruni Üniversitesi

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
5 November 2020 in International Journal of Occupational Safety and Ergonomics
Verified
Journal Article
Closed access
GAGuzin Kaya Aytutuldu
Guzin Kaya Aytutuldu
TBTansu Birinci
Tansu Birinci
ETEla Tarakcı
Ela Tarakcı
Purpose: Office workers are commonly exposed to work-related musculoskeletal pain. This study investigated the individual and work-related risk factors linked to musculoskeletal pain and pain-related disability among Turkish office workers who work using computers. Materials and Methods: One-hundred-fifty office workers were included. Data was collected using the online survey with a combination of the Nordic Musculoskeletal Questionnaire, Oswestry Disability Index (ODI), Neck Disability Index (NDI), Disabilities of the Arm, Shoulder, and Hand questionnaire short form (Q-DASH). The participants were divided into four subgroups: no pain (n=26), lower back pain (n=37), neck pain (n=49) and upper extremity pain (n=38). Results: There were differences between subgroups in terms of condition that feet touch the floor and condition that keyboard, mouse, and wrist are in the straight line (p=0.013 and p=0.025, respectively). The working year was correlated with the ODI score (ρ=0.802, p=0.041). There was also a significant correlation between the NDI score and working hours (ρ=0.415, p=0.003), while Q-DASH was correlated with body mass index and working years (ρ=0.406, p=0.014, and ρ=0.327, p=0.043, respectively). Conclusions: The pain-related disability was associated with various risk factors such as physical inactivity, body mass index, working hours, working years, and workplace ergonomics in the office workers. Trial registration: ClinicalTrials.gov identifier: NCT04160585..

18 April 2025 in arXiv
Verified
Preprint
Open access
PDF file
IAI. Aytutuldu
I. Aytutuldu
OYO. Yol
O. Yol
YAYusuf Sinan Akgül
Yusuf Sinan Akgül
This study explores the integration of Large Language Models (LLMs) into the grading and appeal resolution process in computer science education. We introduce AI-PAT, an AI-powered assessment tool that leverages LLMs to evaluate computer science exams, generate feedback, and address student appeals. AI-PAT was used to assess over 850 exam submissions and handle 185 appeal cases. Our multi-model comparison (ChatGPT, Gemini) reveals strong correlations between model outputs, though significant variability persists depending on configuration and prompt design. Human graders, while internally consistent, showed notable inter-rater disagreement, further highlighting subjectivity in manual evaluation. The appeal process led to grade changes in 74% of cases, indicating the need for continued refinement of AI evaluation strategies. While students appreciated the speed and detail of AI feedback, survey responses revealed trust and fairness concerns. We conclude that AI-PAT offers scalable benefits for formative assessment and feedback, but must be accompanied by transparent grading rubrics, human oversight, and appeal mechanisms to ensure equitable outcomes.

15 October 2025 in Archives of Physical Medicine and Rehabilitation
Verified
Journal Article
Closed access
GAGuzin Kaya Aytutuldu
Guzin Kaya Aytutuldu
DYDuygu Yalcınkaya
Duygu Yalcınkaya
BABuket Akıncı
Buket Akıncı
HUHikmet Ucgun
Hikmet Ucgun
RCRabia Gokcen Gozubatik Celik
Rabia Gokcen Gozubatik Celik
MTMesude Tutuncu
Mesude Tutuncu

28 February 2025 in Journal of Asthma
Verified
Journal Article
Closed access
HUHikmet Ucgun
Hikmet Ucgun
BABuket Akıncı
Buket Akıncı
STSena Teber
Sena Teber
GAGuzin Kaya Aytutuldu
Guzin Kaya Aytutuldu
ÖAÖmer Akçal
Ömer Akçal
The benefits of incorporating breathing exercises as an adjunct to medical treatment in the management of asthma are well established. Video game-based interventions are notable for the additional advantages they offer to children with chronic respiratory diseases; however, research specifically focusing on children with asthma remains limited. This study aimed to compare the effects of video game-based breathing exercises and conventional breathing exercises on pulmonary and extrapulmonary features in children with asthma. Thirty-four children with asthma aged 8-18 years were randomly divided into gamification group (GG) and control group (CG). The GG performed video game-based breathing exercises and the CG performed conventional breathing exercises 5 days a week for 8 weeks. Pulmonary function, respiratory and peripheral muscle strength, functional capacity, dyspnea, fatigue, asthma control, and quality of life were assessed at baseline and after 8 weeks of training. Pulmonary function, respiratory and peripheral muscle strength, functional capacity, and total and physical dimensions of both fatigue and quality of life improved in both GG and CG; however, the improvement in the GG was greater. Significant change in inspiratory capacity and improvement in dynamic hyperinflation were found only in the GG. Both methods were insufficient in improving dyspnea and asthma control. While breathing exercises are beneficial for children with asthma in improving pulmonary and extrapulmonary features, the video game-based method may provide further improvements. More importantly, the video game-based method is superior to the conventional method as it is also successful in improving dynamic hyperinflation.

7 October 2024 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
IAIlhan Aytutuldu
Ilhan Aytutuldu
YGYakup Genc
Yakup Genc
YAYusuf Sinan Akgül
Yusuf Sinan Akgül
This paper presents a phonetic segment classification method based on joint embeddings learned from processing Ultrasound Tongue Imaging (UTI) and audio data. For constructing the embeddings, we compiled an ultrasound image dataset synchronized with audio that encompasses common speech scenarios. The embeddings are obtained from artificial neural network models trained on this dataset. During testing, our model processes only audio data, making it practical for speech therapy as no ultrasound imaging is required. Experiments show that our method yields similar performance compared to methods that simultaneously use both audio and UTI data. However, it outperforms the methods utilizing solely audio or UTI data in real-time classification