Mudanya University Institutional Academic Archive System
Mudanya University's Dspace system is a platform that digitally stores and opens academic studies. Academic content such as articles, presentations, theses, books, and reports are included here. Dspace@Mudanya provides easy access, making it a valuable resource for researchers and students. It serves as a digital archive for Mudanya University's academic outputs, facilitates access to scientific information and supports its sharing. For more information and assistance, please contact us.
Communities in DSpace
Select a community to browse its collections.
Now showing 1 - 3 of 3
Recent Submissions
Item
An explainable ensemble machine learning model using baseline blood transcriptomics to predict Parkinson’s disease motor progression
(FRONTIERS MEDIA SA, 2026-02) Fırat, Yelda; 41749
Introduction: Predicting Parkinson's disease (PD) motor progression remains challenging despite advances in neuroimaging. Blood-based transcriptomic profiling offers a more accessible and cost-effective alternative. This study aimed to develop and validate a machine learning approach using blood-based transcriptomic data to predict 12-month motor severity in PD and to identify the transcriptomic features and biological pathways most strongly associated with progression. Methods: A Stacking Regressor ensemble model combining three gradient boosting algorithms (XGBoost, LightGBM, CatBoost) was developed using baseline Parkinson's Progression Markers Initiative (PPMI) data (n = 390), integrating blood RNA sequencing (RNA-seq) and clinical features to predict 12-month UPDRS Part III scores. SHapley Additive exPlanations (SHAP) analysis was applied to identify key prognostic features, evaluating seven PD risk genes (SNCA, LRRK2, GBA, PRKN, PINK1, PARK7, VPS35) and pathway scores for mitochondrial dysfunction, neuroinflammation, and autophagy. Results: On an independent test set (n = 78), the model achieved a Coefficient of Determination (R & sup2;) of 0.551 and Mean Absolute Error (MAE) of 6.01. SHAP analysis identified the baseline UPDRS & times; PINK1 interaction (UPDRS_BL & times; PINK1) as the most influential feature (mean |SHAP| = 0.283). Among transcriptomic features, VPS35 (mean |SHAP| = 0.010), GBA, and LRRK2 were most prominent. Mitochondrial dysfunction showed the highest pathway contribution (mean |SHAP| = 0.008). Discussion: The study establishes that machine learning integrating blood transcriptomics and clinical data effectively predicts motor progression in PD. Crucially, the interplay between initial clinical state and specific genetic backgrounds-particularly PINK1-is a more powerful prognostic indicator than any factor alone. This study provides systematic evidence that mitochondrial dysfunction is a dominant prognostic signal for disease progression, nominating key genes and pathways for future mechanistic and therapeutic investigation.
Item
The Mixed-Up Birthday Party
(SP-Kindle, 2026-05) Mustafa, Esma; 392828
The Mixed-Up Birthday Party is a funny children’s drama about a birthday celebration that turns into complete chaos. Emma excitedly prepares for her birthday party with her friends Leo, Mia, and Tom. However, the party becomes strange and hilarious when Tom brings a disgusting “special sandwich” made of bananas, pickles, onions, and sardines. Later, the silly entertainer Clown Cookie arrives carrying mysterious boxes filled with random objects like carrots, socks, and rubber chickens. During party games, accidents and misunderstandings create more laughter and confusion. Finally, Clown Cookie accidentally drops his hat into the birthday cake, making the party even funnier. Despite all the disasters, Emma realizes that friendship, laughter, and fun are what make a birthday truly special.
Item
The Role of Forest Areas as Carbon Sinks in Türkiye: The Impact of Industrialization and Energy Consumption on Greenhouse Gas Emissions
(KASTAMONU UNIV, 2026-04) Şengül, Serkan; 355807
Aim of study: This study examines the impact of forest area expansion on greenhouse gas (GHG) emissions in T & uuml;rkiye, focusing on the roles of industrial production, energy consumption, and economic growth. Area of study: The analysis covers T & uuml;rkiye using annual data for the period 1990-2021. Data on GHG emissions, forest areas, industrial production, energy consumption, and economic growth were obtained from the Turkish Statistical Institute (TurkStat) and other official sources. Material and method: The study employs the autoregressive distributed lag (ARDL) model and Johansen cointegration approach to analyze the long-run relationships among the variables. Unit root tests were conducted to examine the stationarity properties of the series. Main results: The findings indicate that forest area expansion significantly reduces GHG emissions in the long run, highlighting the role of forests as carbon sinks. In contrast, industrial production, energy consumption, and GDP per capita exert statistically significant positive effects on emissions. The Johansen cointegration results confirm a stable long-run equilibrium relationship among the variables. Research highlights: Achieving T & uuml;rkiye's emission reduction targets requires strengthening forest management policies and aligning industrial production and energy consumption with environmental sustainability.
Item
SHAP-based explainable AI framework for autism severity classification using 3D motor biomarkers
(FRONTIERS MEDIA SA, 2026-03) Fırat, Yelda; 41749
Introduction Early Autism spectrum disorder (ASD) diagnosis is critical for intervention, yet current methods rely on subjective clinical observations. This study develops objective tools to classify ASD severity using 3D motor movement analysis, addressing motor abnormalities as core diagnostic features.Methods A Random Forest (RF) model classified three severity levels using 463 motor features from 25 Kinect V2 joint points. Data from 109 children (50 typical, 50 moderate ASD, 9 severe ASD) were validated via 5-fold cross-validation and two held-out test sets (20% each). Shapley Additive Explanations (SHAP) analysis identified critical motor biomarkers.Results The model achieved 84.6 +/- 10.9% accuracy (5-fold cross-validation) and 86.4% accuracy (internal and held-out test sets). For severe ASD, the model achieved 100% classification accuracy on synthetic test data (4/4 cases; 95% CI: 39.8%-100.0%). However, this result represents a methodological proof-of-concept rather than clinical validation, as severe ASD features were synthetically generated from moderate ASD data and the model has not been validated on real Kinect-derived severe ASD motor data. SHAP analysis identified wrist movements, knee trajectories, and elbow-to-foot distances as key motor biomarkers for severity classification.Discussion This Kinect-based approach with RF and SHAP offers effective, interpretable ASD severity assessment for typical and moderate ASD classes, with promising methodological foundations for severe ASD pending validation on real data.
Item
A study of the reliability and validity of the Mindfulness Parenting Scale in Infancy and the examination of Mothers' Mindfulness in Pareting in Turkish samples
(UNIV POLITECNICA VALENCIA, EDITORIAL UPV, 2025-10) Sezgin, Elif; 157389
The research aims to assess the reliability and validity of the Mindful Parenting in Infancy Scale (MPIS) for mothers with infants aged 0-24 months and to analyze their mindfulness levels across various variables. The study included 353 mothers from Bursa's Nil & uuml;fer and Osmangazi districts, with data collected in private nurseries and daycare homes between December 2023 and March 2024. Teachers distributed the data collection tools, which included the "Mother and Baby Information Form" and the MPIS, developed by Gartstein (2021). Adaptation permissions were secured, and the scale's language, content, and structure were validated. Reliability was measured using the Cronbach Alpha internal consistency coefficient and item-total correlations. Statistical analyses included independent samples t-test and One-way ANOVA to explore MPIS scores across demographic variables. The Levene test assessed homogeneity, while kurtosis and skewness evaluated normal distribution. The internal consistency coefficient was 0.74, with item-total correlations ranging from 0.35 to 0.49. The findings indicated no significant differences in mindfulness based on mothers' age, education, or family type, but highlighted variations based on the birth order of the baby.
