Altınbaş University Institutional Repository
Not a member yet
5805 research outputs found
Sort by
Economic policy uncertainty and capital investment: Evidence from European tourism firms
No full textThis paper investigates the impact of economic policy uncertainty (EPU) on the capital investment behavior of tourism firms in Europe. Using firm-level data from 4874 firms in 11 European countries for the period 2012-2022, we conduct a dynamic panel data analysis that accounts for the different effects of domestic and global policy uncertainty on the tourism industry and its sub-industries. The results reveal that both domestic and global EPU slow down capital investment in the tourism industry. Notably, global EPU has a significant negative impact in all sub-industries, while domestic EPU mainly affects the hotel sub-industry. These findings remain robust when different firm- and country-specific factors are taken into account. Our study highlights the need for policymakers to reduce policy uncertainty to encourage greater investment. Tourism managers may also benefit from considering both domestic and global uncertainties along with industry-specific characteristics in their investment decisions
Smart Energy Management in Green Cloud Computing using Machine Learning Algorithms
No full textCloud computing has many advantages as well as some disadvantages. An internet connection is required to use Cloud Computing. In other words, it is not possible to access the data in cases without internet. Cloud Computing can provide infrastructure services, platform services and software services to individuals with any device connected to the internet. If the connection speed is low when there is internet, the data transmission is also slower. In this context, it may not be practical for individuals or institutions to benefit from Cloud Computing in places where internet connection is low, limited, or absent. A new technology was obtained in this study; this method depends on deep learning and machine learning techniques applied to detect the attacks in the cloud computing-based systems. The suggested method compared with many traditional machine learning techniques. © 2025, American Scientific Publishing Group (ASPG). All rights reserved
Enhancing Driving Control via Speech Recognition Utilizing Influential Parameters in Deep Learning Techniques
No full textArticle number; 496.This study investigates the enhancement of automated driving and command control through speech recognition using a Deep Neural Network (DNN). The method depends on some sequential stages such as noise removal, feature extraction from the audio file, and their classification using a neural network. In the proposed approach, the variables that affect the results in the hidden layers were extracted and stored in a vector to classify them and issue the most influential ones for feedback to the hidden layers in the neural network to increase the accuracy of the result. The result was 93% in terms of accuracy and with a very good response time of 0.75 s, with PSNR 78 dB. The proposed method is considered promising and is highly satisfactory to users. The results encouraged the use of more commands, more data processing, more future exploration, and the addition of sensors to increase the efficiency of the system and obtain more efficient and safe driving, which is the main goal of this research
A machine learning analysis to predict the stability driven structural correlations of selenium-based compounds as surface enhanced materials
No full textThe selenium-based compounds are gaining significance for their surface-enhanced properties. In order to accelerate their discovery, a machine learning (ML) approach has been employed to predict their structural correlations. For this a dataset of 618 compounds is collected from literature and is trained by using Support Vector Machine (SVM) with its Linear Kernal. Among ten ML evaluated models, three top-performing models are selected to make predictions for their stability energy. A Convex Hull Distribution (CHD) is constructed to elucidate the relationship for their stability and structural correlations. The main finding of this study reveals its strong correlation between stability and its related structural descriptors, particularly Bertz Branching Index" corrected for the number of Terminal atoms (BertzCT), Partial Equalization of Orbital Electronegativities-Van der Waals Surface Area with 14 bins (PEOE_VSA14), and First-Order Connectivity Index (chi 1). The analysis demon strates that the current ML models can effectively predict the stability of such materials to enable their rapid screening. Their calculations can provide a framework to understand their complex relationships between their material properties, structure, and stability.Funding agency : Taif University
Grant number : TU-DSPP-2024-7
Brushing motion caused no microcracks: a micro-computed tomography study
No full textObjective: We evaluated the effect of brushing motion on microcrack formation in round distal canals after using multi-file rotary(MFR), single-file rotary(SFR), and single-file reciprocation(SFRc) systems via micro-computed tomography(micro-CT).
Materials and methods: Thirty-six mandibular molars were used. Samples were allocated according to files and preparation patterns (n = 12); pecking (P) and brushing (B): Group-MFR-P, Group-MFR-B, Group-SFRc-P, Group-SFRc-B, Group-SFR-P, Group-SFR-B. MFR was ProTaper Next, SFR was TruNatomy, and SFRc was WaveOne Gold. Mesial and distal were prepared using pecking motion, and additional brushing motion. Brushing motions were performed after the pecking motions with 6 strokes. Pre-and-post-instrumentation scans were obtained. Wilcoxon, Krukal-Wallis, and Mann-Whitney-U were performed.
Results: No differences were between pre-and-post-instrumentation scans (p > 0.05). Post-instrumentation microcracks were not different in Group MFR-P and Group MFR-B, Group SFRc-P and Group SFRc-B, Group SFR-P and Group SFR-B (p > 0.05).
Conclusion: The brushing motion followed by the pecking motion did not cause microcracks. None of the file systems examined in the study induced microcracks
A secure smart monitoring network for hybrid energy systems using IoT, AI
No full textEnergy systems are now incorporating Internet of Things technology to make better monitoring and management of energy possible. This research study analyzes the design and implementation of a secure and smart monitoring network for hybrid energy systems using two of the most widely known Internet of Things protocols and AI, MQTT (Message Queuing Telemetry Transport) and CoAP (Constrained Application Protocol). Traditional energy monitoring has latency issues, low scalability. This paper discusses an enhancement over this with MQTT and CoAP, aiming at increasing overall performance and scalability within hybrid energy frameworks. Methodologies are developed to implement the application with IoT sensors and to collect data from MQTT and CoAP protocols for further processing in the Python programming language. To demonstrate these improvements in efficiency and reliability, the results are compared against those obtained from traditional systems. This work investigates how Internet of Things (IoT) and AI can be deployed in hybrid energy systems with advanced communication protocols to enhance observability as well as control. A total of many enhancements have been added to this system: latency by 35% has been minimized, data transmission efficiency of 96.87%, a reliability increase of 28%, 25% enhancement in scalability, and 20% reduction in energy consumption
Exploring structural basis of photovoltaic dye materials to tune power conversion efficiencies: A DFT and ML analysis of Violanthrone
No full textThis study employs a systematic approach to modify Violanthrone (V) structures and analyze their impact on photovoltaic (PV) properties. We use cheminformatics based Python library based RDKit tool to calculate their structural descriptors for to correlate them with their PV parameters. Our analysis reveals a positive correlation for their Open-Circuit Voltage (Voc) and Fill Factor (FF) for indicating that their higher voltage output is associated for their efficient charge carrier mobilities. We also predict their Power Conversion Efficiency (PCE) by drawing their their Scharber diagram which achieves their promising efficiency of up to 15 %. To further enhance the reliability our work, we conduct an extensive literature survey of such organic materials to predict their PCEs by their Machine Learning (ML) after utilizing various ML models. Among five tested ML models, it identifies the Random Forecast (RF) model and Gradient Boosting (GB) models as as the optimal one (R-squared value: 0.82). Their feature importance reveals that their FF is the most significant feature to impact their PCEs (importance value: 10.9). Furthermore, we observe a negative correlation between orbital interaction strength (E(2)) values and orbital energy differences E(j)-E(i) which indicates that their stronger orbital interactions are associated with their smaller energy differences. Our study provides valuable insights for their structural basis to PV material designs for enabling their design for efficient materials in energy conversion
OPTIMIZING ROAD SAFETY: THE ROLE OF GEOGRAPHIC INFORMATION SYSTEMS (GIS) IN TRAFFIC ACCIDENT ANALYSIS AND PREDICTION
No full textThis study investigates the application of Geographic Information Systems (GIS) in traffic accident analysis and prediction. By integrating GIS with deep learning techniques, the research highlights how spatial data management and analysis can enhance road safety. Key objectives include identifying accident hotspots, optimizing traffic control systems, and improving emergency response. The methodology involves a comprehensive review of existing literature, emphasizing GIS's role in data integration, spatial analysis, and predictive modeling. Findings demonstrate that GIS significantly contributes to understanding traffic patterns, predicting accidents, and formulating targeted safety interventions. Challenges such as data complexity, real-time processing, and model interpretability are addressed, offering future directions for leveraging GIS in road safety management. The study concludes that GIS, combined with advanced analytics, presents a powerful tool for reducing traffic accidents and enhancing overall traffic safety
A hybrid model using 1D-CNN with Bi-LSTM, GRU, and various ML regressors for forecasting the conception of electrical energy
No full textTo solve power consumption challenges by using the power of Artificial Intelligence (AI) techniques, this research presents an innovative hybrid time series forecasting approach. The suggested model combines GRU-BiLSTM with several regressors and is benchmarked against three other models to guarantee optimum reliability. It uses a specialized dataset from the Ministry of Electricity in Baghdad, Iraq. For every model architecture, three optimizers are tested: Adam, RMSprop and Nadam. Performance assessments show that the hybrid model is highly reliable, offering a practical option for model-based sequence applications that need fast computation and comprehensive context knowledge. Notably, the Adam optimizer works better than the others by promoting faster convergence and obstructing the establishment of local minima. Adam modifies the learning rate according to estimates of each parameter's first and second moments of the gradients separately. Furthermore, because of its tolerance for outliers and emphasis on fitting within a certain margin, the SVR regressor performs better than stepwise and polynomial regressors, obtaining a lower MSE of 0.008481 using the Adam optimizer. The SVR's regularization also reduces overfitting, especially when paired with Adam's flexible learning rates. The research concludes that the properties of the targeted dataset, processing demands and job complexity should all be considered when selecting a model and optimizer
From Trash to Treasure: Assessing Deep Learning Models for Plastic Waste Identification
No full textConference name: International Conference on Data Analytics and Management, ICDAM 2025.
Volume editors: Swaroop A., Virdee B., Correia S.D., Polkowski Z.The pervasive utilization of plastic bottles in our daily routines has escalated environmental predicaments, notably within marine ecosystems. A considerable volume of plastic bottles is carried ashore by waves, often ensnaring coastal regions. The deleterious ramifications of plastic waste, including bottles, on coastal ecology necessitate attention. Fortunately, artificial intelligence (AI) has pervaded various domains, including environmental endeavors, proffering promising resolutions to counter these ecological quandaries effectively. This study endeavors to classify plastic bottles through image data encompassing diverse scenarios. Employing distinct AI algorithms, we preprocess the dataset and conduct this classification. Remarkably, the CNN with the heuristic model attains the highest accuracy, an impressive 99%