999 results
Search Results
Now showing 1 - 10 of 999
Article Citation - WoS: 105Citation - Scopus: 163Cassava Disease Recognition From Low-Quality Images Using Enhanced Data Augmentation Model and Deep Learning(Wiley, 2021) Abayomi-Alli, Olusola Oluwakemi; Damasevicius, Robertas; Misra, Sanjay; Maskeliunas, RytisImprovement of deep learning algorithms in smart agriculture is important to support the early detection of plant diseases, thereby improving crop yields. Data acquisition for machine learning applications is an expensive task due to the requirements of expert knowledge and professional equipment. The usability of any application in a real-world setting is often limited by unskilled users and the limitations of devices used for acquiring images for classification. We aim to improve the accuracy of deep learning models on low-quality test images using data augmentation techniques for neural network training. We generate synthetic images with a modified colour value distribution to expand the trainable image colour space and to train the neural network to recognize important colour-based features, which are less sensitive to the deficiencies of low-quality images such as those affected by blurring or motion. This paper introduces a novel image colour histogram transformation technique for generating synthetic images for data augmentation in image classification tasks. The approach is based on the convolution of the Chebyshev orthogonal functions with the probability distribution functions of image colour histograms. To validate our proposed model, we used four methods (resolution down-sampling, Gaussian blurring, motion blur, and overexposure) for reducing image quality from the Cassava leaf disease dataset. The results based on the modified MobileNetV2 neural network showed a statistically significant improvement of cassava leaf disease recognition accuracy on lower-quality testing images when compared with the baseline network. The model can be easily deployed for recognizing and detecting cassava leaf diseases in lower quality images, which is a major factor in practical data acquisition.Editorial Citation - WoS: 2Citation - Scopus: 2Economic Growth and Health Expenditures Relationship Between Oecd Countries(Frontiers Media Sa, 2023) Tengilimoglu, Dilaver[No Abstract Available]Article Citation - WoS: 3Citation - Scopus: 4Intensive Parenting of Mothers in 11 Countries Differing in Individualism, Income Inequality, and Social Mobility(Pergamon-Elsevier Science Ltd, 2025) Lubiewska, Katarzyna; Zeglen, Marta; Lun, Vivian Miu-Chi; Park, Joonha; Runge, Ronja; Muller, Jacomien; van der Kaap-deeder, JoleneAlthough intensive parenting has been found to be mostly detrimental for both children and parents, less is known about the correlates and sources of this type of parenting. This study aimed to examine associations between mother's primary involvement in caregiving and intensive parenting, as well as their potential sources, thereby focusing on: family social status, characteristics of the national economy (income inequality and social mobility) and culture (individualism-collectivism) in 11 culturally diverse countries. Participants were 2535 mothers of children aged between 6 and 10. Mothers reported on their intensive parenting behaviors, entailing both supportive and undermining aspects of meeting their child's needs, as well as their level of involvement in daily caregiving tasks and the subjective family social status. Hypotheses were tested controlling for country level response style. Results revealed that: mothers who were more often the primary caregiver across daily tasks used more intensive parenting behaviors; high social status mothers were using less child need undermining yet more supportive intensive parenting behaviors, and less frequently served as the primary caregiver for daily tasks; the undermining intensive parenting behaviors related positively to country-level individualism and income inequality, whereas relations with social mobility were mixed.Article Citation - WoS: 9Citation - Scopus: 12Social Support and Help-Seeking Worldwide(Springer, 2024) Szkody, Erica; Spence, Anjolee; Ozdogru, Asil; Tushir, Bhawna; Chang, Fennie; Akkas, Handan; Cascalheira, Cory J.Social support has long been associated with positive physical, behavioral, and mental health outcomes. However, contextual factors such as subjective social status and an individual's cultural values, heavily influence social support behaviors (e.g., perceive available social support, accept support, seek support, provide support). We sought to determine the current state of social support behaviors and the association between these behaviors, cultural values, and subjective social support across regions of the world. Data from 6,366 participants were collected by collaborators from over 50 worldwide sites (67.4% or n = 4292, assigned female at birth; average age of 30.76). Our results show that individuals cultural values and subjective social status varied across world regions and were differentially associated with social support behaviors. For example, individuals with higher subjective social status were more likely to indicate more perceived and received social support and help-seeking behaviors; they also indicated more provision of social support to others than individuals with lower subjective social status. Further, horizontal, and vertical collectivism were related to higher help-seeking behavior, perceived support, received support, and provision of support, whereas horizontal individualism was associated with less perceived support and less help-seeking and vertical individualism was associated with less perceived and received support, but more help-seeking behavior. However, these effects were not consistently moderated by region. These findings highlight and advance the understanding of how cross-cultural complexities and contextual distinctions influence an individual's perception, processing, and practice of social support embedded in the changing social landscape.Article Citation - WoS: 1Citation - Scopus: 1How Do Visual, Auditory and Motor Dual-Tasking Each Affect Swallowing and Chewing Function?(Wiley, 2024) Begen, Sena Nur; Arslan, Selen Serel; Serel Arslan, SelenBackground: It can be challenging to perform a second task at the same time as swallowing. Objective(s)The study aimed to investigate the effect of visual, auditory and motor dual-tasking on swallowing and chewing function in healthy young adults. Method: Right-handed healthy adults without any psychological and cognitive problems were included in the study. Swallowing was evaluated based on the dysphagia limit in different liquid textures such as water and nectar consistencies, and chewing was evaluated by the Test of Masticating and Swallowing Solids. For the second task, visual and auditory performance was assessed using reaction time, and the motor performance was assessed using a bilateral tapping task. Assessments were performed in two steps: baseline and dual-task. For baseline, all evaluation methods were applied individually. After completing the baseline assessment, dual-task assessment were carried out the following day. For dual-task assessment, the swallowing and chewing tasks were performed simultaneously with visual, auditory and motor tasks. Results: Results showed a significant decrease in dysphagia limit in the nectar consistency, and significant increase in chewing time, visual reaction time and tapping rate (right-left) when compared to baseline and dual-task conditions (chi(2)(3) = 9.61, p = .02; chi(2)(3) = 9.02, p = .02; chi(2)(3) = 28.09, p < .001; chi(2)(3) = 28.97, p < .001; chi(2)(3) = 21.56, p < .001, respectively). However, there were no differences in dysphagia limit in the water and auditory reaction time compared to baseline and dual-task conditions (chi(2)(3) = 3.18, p = .36; chi(2)(3) = 2.56, p = .50, respectively). Conclusion: Results shedding light on how simultaneous dual tasks can influence swallowing and chewing. Dual-tasking cause a decrease in both swallowing/chewing and the visual/motor performances. These results may provide valuable information for designing interventions or strategies aimed at improving or maintaining optimal swallowing and chewing during in various populations during daily life.Article Citation - WoS: 23Citation - Scopus: 26Optimization Problems for a Parallel System With Multiple Types of Dependent Components(Elsevier Sci Ltd, 2020) Eryilmaz, Serkan; Ozkut, MuratThis paper is concerned with two optimization problems for a parallel system that consists of dependent components. First, the problem of finding the number of elements in the system that minimizes the mean cost rate of the system is considered. The second problem is concerned with the optimal replacement time of the system. Previous work assumes that the components are independent. We discuss the impact of dropping this assumption. In particular, we numerically examine how the dependence between the components affects the optimal number of units and replacement time for the system which minimize mean cost rates. We first consider the case when the components are exchangeable and dependent, i.e. the system consists of single type of dependent components. Subsequently, we consider a system that consists of multiple types of dependent components. Comparative numerical results are presented for particularly chosen dependence models.Article Citation - WoS: 4Citation - Scopus: 6Surgical Outcomes of Posterior Persistent Fetal Vasculature Syndrome: Cases With Tent-Shaped and Closed Funnel-Shaped Retinal Detachment(Springernature, 2023) Zeydanli, Ece Ozdemir; Ozdek, Sengul; Acar, Burak; Ozdemir, Huseyin Baran; Aktas, Zeynep; Gurelik, Gokhan; Atalay, Hatice Tuba; Ozdemir Zeydanli, EceBackground/objectives To determine the role of vitreoretinal surgery (VRS) for two different forms of posterior persistent fetal vasculature syndrome (PFVS); with tent-shaped tractional retinal detachment (TRD) and closed funnel-shaped TRD. Subjects/methods Retrospective, single surgeon, consecutive case series of 52 eyes of 44 patients with posterior PFVS who underwent VRS. Cases were divided into "tent-shaped TRD" and "funnel-shaped TRD" groups based on the preoperative TRD configuration. Associated anomalies, functional and anatomical outcomes were evaluated. The cosmetic appearance was defined as poor if there was phthisis bulbi, gross buphthalmos, or corneal opacification; acceptable if there was apparent leukocoria; and excellent if none were noted at the last follow-up. Results Thirty eyes of 29 patients presented with tent-shaped TRD; 70% of which obtained counting fingers or better vision and 90% showed significant reversal of tenting achieving retinal reattachment. The cosmetic appearance was excellent in 87%. Two eyes (7%) became phthisic. Twenty-two eyes of 15 patients presented with funnel-shaped TRD and leukocoria; 45% achieved LP vision and 70% of patients with bilateral pathology had LP in at least one eye. The cosmetic appearance was acceptable to excellent in 73%. Three eyes (14%) became phthisic, one (5%) of which required enucleation. The median follow-up time was 16 (6-71) months. Conclusions VRS often provides functional vision and anatomy in posterior PFVS with tent-shaped TRD morphology. In the funnel-shaped TRD morphology, where no treatment has historically been recommended, surgery may be considered with an aim of restoring light perception and globe preservation, particularly in bilateral cases.Article Citation - WoS: 31Citation - Scopus: 51Neural Network and Classification Approach in Identifying Customer Behavior in the Banking Sector: a Case Study of an International Bank(Wiley, 2015) Ogwueleka, Francisca Nonyelum; Misra, Sanjay; Colomo-Palacios, Ricardo; Fernandez, LuisThe customer relationship focus for banks is in development of main competencies and strategies of building strong profitable customer relationships through considering and managing the customer impression, influence on the culture of the bank, satisfactory treatment, and assessment of valued relationship building. Artificial neural networks (ANNs) are used after data segmentation and classification, where the designed model register records into two class sets, that is, the training and testing sets. ANN predicts new customer behavior from previously observed customer behavior after executing the process of learning from existing data. This article proposes an ANN model, which is developed using a six-step procedure. The back-propagation algorithm is used to train the ANN by adjusting its weights to minimize the difference between the current ANN output and the desired output. An evaluation process is conducted to determine whether the ANN has learned how to perform. The training process is halted periodically, and its performance is tested until an acceptable result is obtained. The principles underlying detection software are grounded in classical statistical decision theory.Article Citation - WoS: 55Citation - Scopus: 61Encoding the Future: Successful Processing of Intentions Engages Predictive Brain Networks(Academic Press inc Elsevier Science, 2010) Poppenk, J.; Moscovitch, M.; McIntosh, A. R.; Ozcelik, E.; Craik, F. I. M.Evidence from cognitive, patient and neuroimaging research indicates that "remembering to remember" intentions, i.e., prospective memory (PM) retrieval, requires both general memory systems involving the medial temporal lobes and an executive system involving rostral PFC (BA 10). However, it is not known how prospective memories are initially formed. Using fMRI, we investigated whether brain activity during encoding Of future intentions and present actions differentially predicted later memory for those same intentions (PM) and actions (retrospective memory). We identified two significant patterns of neural activity: a network linked to overall memory and another linked specifically to PM. While overall memory success was predicted by temporal lobe activations that included the hippocampus, PM success was also uniquely predicted by activations in additional regions, including left rostrolateral PFC and the right parahippocampal gyrus. This finding extends the role of these structures to the formation of individual intentions. It also provides the first evidence that PM encoding, like PM retrieval, is supported by both a common episodic memory network and an executive network specifically recruited by future-oriented processing. (C) 2009 Elsevier Inc. All rights reserved.Article Citation - WoS: 8Citation - Scopus: 10A New Approach To the Existence and Uniqueness of Solutions for A Class of Nonlinear Q-Fractional Boundary Value Problems(Institute of Applied Mathematics of Baku State University, 2025) Karapinar, E.; Sevinik-Adiguzel, R.; Aksoy, U.; Erhan, I. M.; Sevinik Adıgüzel, RezanThe object of this study is a boundary value problem associated with a q-difference equation of fractional order. The existence and uniqueness of a solution in the case of multi-point boundary conditions is studied from the viewpoint of fixed point theory. An integral equation equivalent to the boundary value problem is derived and the fixed points of the related integral operator are investigated by using a contractive condition involving a comparison function. The Ulam-Hyers stability of the problem is also discussed. Theoretical results are followed by a particular example.
