Işık Üniversitesi Kurumsal Akademik Bellek
Işık Üniversitesi tarafından doğrudan ve dolaylı olarak yayınlanan; kitap, makale, tez, bildiri, rapor, araştırma verisi gibi tüm akademik kaynakları uluslararası standartlarda dijital ortamda depolar, Üniversitenin akademik performansını izlemeye aracılık eder, kaynakları uzun süreli saklar ve telif haklarına uygun olarak Açık Erişime sunar.
Güncel Gönderiler
Enhancing mechanical performance of FDM-printed ABS parts through annealing optimization
(John Wiley and Sons Inc, 2025-06-18) Kösemen, Elifnur; Bakkal, Mustafa; Kuzu, Ali Taner
This study examines the impact of annealing on the mechanical properties of acrylonitrile butadiene styrene (ABS) parts produced using fused deposition modeling (FDM). The research investigates how different annealing temperatures (90°C, 105°C, and 120°C), production orientations (upright, on edge, and flat), and infill patterns influence hardness, tensile strength, and impact resistance. Experiments were conducted using a Stratasys F370 printer, and samples were tested following ISO standards for mechanical performance. Results indicated that annealing at 90°C and 105°C generally improved hardness, tensile strength, and impact resistance, particularly for upright and on-edge orientations. However, annealing at 120°C led to a decrease in these properties, likely due to microstructural changes observed through scanning electron microscopy (SEM) and differential scanning calorimetry (DSC) analysis. The study highlights the importance of optimizing production parameters and annealing conditions to achieve desired mechanical properties in FDM-printed ABS parts. These findings may inform post-processing strategies for enhancing the reliability and performance of additive manufactured components, particularly for applications in industries utilizing ABS materials for customized and prototype parts.
Adaptive locally connected recurrent unit (ALCRU)
(Springer Science and Business Media Deutschland GmbH, 2025-07-03) Özçelik, Şuayb Talha; Tek, Faik Boray
Research has shown that adaptive locally connected neurons outperform their fully connected (dense) counterparts, motivating this study on the development of the Adaptive Locally Connected Recurrent Unit (ALCRU). ALCRU modifies the Simple Recurrent Neuron Model (SimpleRNN) by incorporating spatial coordinate spaces for input and hidden state vectors, facilitating the learning of parametric local receptive fields. These modifications add four trainable parameters per neuron, resulting in a minor increase in computational complexity. ALCRU is implemented using standard frameworks and trained with back-propagation-based optimizers. We evaluate the performance of ALCRU using diverse benchmark datasets, including IMDb for sentiment analysis, AdditionRNN for sequence modelling, and the Weather dataset for time-series forecasting. Results show that ALCRU achieves accuracy and loss metrics comparable to GRU and LSTM while consistently outperforming SimpleRNN. In particular, experiments with longer sequence lengths on AdditionRNN and increased input dimensions on IMDb highlight ALCRU’s superior scalability and efficiency in processing complex data sequences. In terms of computational efficiency, ALCRU demonstrates a considerable speed advantage over gated models like LSTM and GRU, though it is slower than SimpleRNN. These findings suggest that adaptive local connectivity enhances both the accuracy and efficiency of recurrent neural networks, offering a promising alternative to standard architectures.
ANN activation function estimators for homomorphic encrypted inference
(Institute of Electrical and Electronics Engineers Inc., 2025-06-13) Harb, Mhd Raja Abou; Çeliktaş, Barış
Homomorphic Encryption (HE) enables secure computations on encrypted data, facilitating machine learning inference in sensitive environments such as healthcare and finance. However, efficiently handling non-linear activation functions, specifically Sigmoid and Tanh, remains a significant computational challenge for encrypted inference using Artificial Neural Networks (ANNs). This study introduces a lightweight, ANN-based estimator designed to accurately approximate activation functions under homomorphic encryption. Unlike traditional polynomial and piecewise linear approximations, the proposed ANN estimators achieve superior accuracy with lower computational overhead associated with bootstrapping or high-degree polynomial techniques. These estimators are trained on plaintext data and seamlessly integrated into encrypted inference pipelines, significantly outperforming conventional methods. Experimental evaluations demonstrate notable improvements, with ANN estimators enhancing accuracy by approximately 2% for Sigmoid and up to 73% for Tanh functions, improving F1-scores by approximately 2% for Sigmoid and up to 88% for Tanh, and markedly reducing Mean Square Error (MSE) by up to 96% compared to polynomial approximations. The ANN estimator achieves an accuracy of 97.70% and an AUC of 0.9997 when integrated into a CNN architecture on the MNIST dataset, and an accuracy of 85.25% with an AUC of 0.9459 on the UCI Heart Disease dataset during ciphertext inference. These results underscore the estimator’s practical effectiveness and computational feasibility, making it suitable for secure and efficient ANN inference in encrypted environments.
The comparison of functional connectivity in Parkinson’s Disease patients with and without Parkin gene mutations
(Turkish Neuropsychiatric Society, 2025-06-19) Çebi, Merve; Ay, Ulaş; Kıçik, Ani; Erdoğdu, Emel; Tepgeç, Fatih; Uyguner, Zehra Oya; Tüfekçioğlu, Zeynep; Samancı, Bedia; Bilgiç, Başar; Emre, Murat; Demiralp, Tamer; Hanağası, Haşmet Ayhan
Introduction: Mapping the functional connectivity of brain regions became appealing in recent research in neurology. Accordingly, a growing body of evidence shows resting-state functional connectivity (rsFC) changes in neurodegenerative disorders including Parkinson’s Disease (PD). As characterised by extensive and progressive dopaminergic loss in the substantia nigra, PD emerges with serious motor and non-motor dysfunctions. In the literature, the minority of PD cases have been associated with certain genetic mutations. The aim of this study was to investigate the rsFC in a group of PD patients having Parkin gene mutation. Method: Twelve PD patients with Parkin mutation (PP-PD), 12 PD patients without Parkin mutation (PN-PD) and 12 healthy controls (HC) were included in the study. All participants underwent a resting-state functional magnetic resonance imaging as well as a neuropsychological assessment and clinical examination. Results: Results indicated that PP-PD had longer disease duration, a higher rate of dyskinesia and lower scores on complex visual perception tests. The resting state networks showed that all PD (consisting of PP-PD and PN-PD) and PP-PD groups had increased functional connectivity in the frontoparietal network as compared to the HC. In addition, the PP-PD group displayed decreased functional connectivity in the dorsal attention network compared to the PN-PD. Conclusion: In conclusion, our data suggests that PD with Parkin gene mutation might be emerging with distinct resting state functional connectivity changes in the brain.
Associations between cerebral perfusion pressure, hemodynamic parameters, and cognitive test values in normal-tension glaucoma patients, Alzheimer’s disease patients, and healthy controls
(Multidisciplinary Digital Publishing Institute (MDPI), 2025-05-24) Stoskuviene, Akvile; Chaleckas, Edvinas; Grusauskiene, Evelina; Bartusis, Laimonas; Çelikkaya, Güven; Januleviciene, Ingrida; Vaitkus, Antanas; Ragauskas, Arminas; Hamarat, Yasin
Background/Objectives: Glaucoma and Alzheimer’s disease (AD) are neurodegenerative conditions with vascular underpinnings. This study aimed to explore the relationship between blood pressure parameters such as mean arterial pressure (MAP), pulse pressure (PP), and cerebral perfusion pressure (CPP) and cognitive performance in patients with AD, normal-tension glaucoma (NTG), and healthy controls. We hypothesized that NTG patients, like those with mild cognitive impairment (MCI), may experience subtle cognitive changes related to vascular dysregulation. Methods: Ninety-eight participants (35 NTG, 17 AD, 46 controls) were assessed for CPP, MAP, OPP, and cognitive performance. Statistical analyses compared groups and examined correlations. Results: AD patients showed lower CPP and MAP (p < 0.001), indicating systemic vascular dysfunction, while NTG patients had higher ocular perfusion pressure (OPP) (p = 0.008), suggesting compensatory mechanisms. CPP correlated with visuospatial abilities in AD (r = 0.492, p = 0.045). MAP correlated with the Clock drawing test (CDT) scores in the NTG group (r = 0.378, p = 0.025). PP negatively correlated with cognition in AD (r = −0.527, p = 0.016 for CDT scores) and controls (r = −0.440, p = 0.002 for verbal fluency and r = −0.348, p = 0.019 for total ACE scores). Conclusions: The study highlights distinct hemodynamic profiles: systemic dysfunction in AD and localized dysregulation in NTG. These findings emphasize the role of vascular dysregulation in neurodegeneration, with implications for personalized treatment approaches targeting vascular health in neurodegenerative conditions.
