Scopus İndeksli Yayınlar Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/395

Browse

Now showing 1 - 20 of 533

Citation - Scopus: 2
Future of Clean Cooking Energy Access in Emerging Economies by 2030
(Springer International Publishing, 2025) Çakır, Mehmet Ali; Ünlü, Ramazan; Çakir, Sümeyra Çay; Xanthopoulos, Petros
This study assesses the future of clean energy and technology access for cooking in emerging economic blocs—BRICS, MINT, ASEAN, and MENA—through 2030. Cooking contributes 3% of global greenhouse gas emissions, with over half of household emissions coming from cooking. Therefore, clean cooking energy is critical for sustainability and human health. The study aims to evaluate the likelihood of achieving the UN Sustainable Development Goal of universal clean cooking energy access by 2030 and the 2050 net-zero emissions target. Machine learning techniques, such as support vector regression, gradient boosting, and linear regression, alongside an ensemble approach, provide forecasts for these regions. The findings show a varied outlook. Within ASEAN, two countries are expected to reach 100% clean energy access for cooking by 2030, while two are likely to experience a decline. The MENA region shows stronger progress, with eight countries expected to meet the 2030 target. Among BRICS countries, only India is projected to reach full accessibility, while Russia faces a decline. The MINT countries face challenges, with none expected to meet the target, and Nigeria is projected to experience a decrease in clean energy access. The study concludes that the current trajectory makes achieving the 2030 Sustainable Development Goals and the 2050 net-zero emissions target unlikely for these regions. Policymakers must reassess their strategies and learn from successful countries to improve outcomes. © 2025 Elsevier B.V., All rights reserved.
Quasi-Static Operation of 2-Axis Microscanners With AlN Piezoelectric Quad-Actuators
(Institute of Electrical and Electronics Engineers Inc., 2021) Hah, D.
Aluminum nitride (AlN) started to draw attentions as a material for piezoelectric actuation owing to its CMOS process compatibility and safeness for biomedical applications. Due to its relatively low piezoelectric coefficients, AlN-based piezoelectric actuators have been mostly operated in resonance modes, especially in optical scanning. This paper presents a novel design of a 2-axis-tilt microscanner with AlN piezoelectric quad-actuators and meander-shaped hinges for reasonable quasi-static operation. Through finite-element-method simulation, it is shown that the proposed device can have about 9 degree of optical scan angle in two dimensions with the voltage amplitude of 50 V. Lissajous scanning operation of the device is demonstrated as well via simulation. © 2021 Elsevier B.V., All rights reserved.
Citation - Scopus: 19
A Novel Feature Design and Stacking Approach for Non-Technical Electricity Loss Detection
(Institute of Electrical and Electronics Engineers Inc., 2018) Aydin, Zafer; Güngör, Vehbi Çağrı
Non-technical electricity losses continue to jeopardize economic and social well-being of many countries. In this work, we develop machine learning classifiers that can identify anomalous electricity consumption in Turkey. Starting from weekly electricity usage data, we develop new features that capture statistical and frequency domain characteristics of the customers and their consumption patterns. We analyze the effect of reducing number of feature descriptors through dimensionality reduction and feature selection techniques. To overcome the class imbalance problem, we implement several ensemble methods and compare their prediction accuracy to those of the standard classifiers. The proposed features and combining strengths of different classifiers bring significant improvements on performance metrics, which is demonstrated through detailed simulations on shopping mall sector. We anticipate that advances in this field will contribute to the economies considerably. © 2018 Elsevier B.V., All rights reserved.
Citation - Scopus: 3
Solving Optimization Problem With Particle Swarm Optimization: Solving Hybrid Flow Shop Scheduling Problem With Particle Swarm Optimization Algorithm
(Springer, 2021) Madenoğlu, Fatma Selen
The flow shop scheduling problem is widely discussed in the literature since it is frequently applied in real industry. This paper presents a variant of flow shop scheduling problem with parallel machines. The proposed problem includes multistage and identical parallel machines at each stage, and the sequence-dependent setup time and transportation time are considered. The objective function is minimization of makespan. The particle swarm optimization algorithm (PSO) is addressed to solve the problem and compared with genetic algorithm and heuristics. The benchmark instances are generated to demonstrate the performance of the PSO. The numerical results show that the PSO significantly outperforms the comparison set. © 2021 Elsevier B.V., All rights reserved.
Citation - Scopus: 5
Emotion Detection Using Multivariate Synchrosqueezing Transform via 2D Circumplex Model
(Institute of Electrical and Electronics Engineers Inc., 2018) Ozel, Pinar; Akan, Aydin; Yilmaz, Bulent; Özel, Pınar; Akan, Aydin I.; Yilmaz, Bulent
Emotion detection by utilizing signal processing methods is a challenging area. An open issue in emotional modeling is to obtain an optimum feature set to use for the classification process. This study proposes an approach for emotional state classification by the investigation of EEG signals via multivariate synchrosqueezing transform (MSST). MSST is a post-processing technique to compose a localized time-frequency representation yielding multivariate syncyrosqueezing coefficients. After obtaining these coefficients from EEG signals for 18 subjects from DEAP dataset, coefficients and self-assessment-mannequins (SAM) labels of those subjects are used for emotional state classification by using support vector machines (SVM) nearest neighbor, decision tree, and ensemble methods. The accuracy rate is 70.6% for high valence high arousal (HVHA), 75.4% for low valence high arousal (LVHA), 77.8% for high valence low arousal (HVLA), and 77.2% for low valence low arousal (LVLA) cases using SVM. © 2019 Elsevier B.V., All rights reserved.
Citation - Scopus: 1
Detection of Epileptic Seizures With Tangent Space Mapping Features of EEG Signals
(IEEE, 2021) Altindis, Fatih; Yilmaz, Bulent
Detection of epileptic seizures from EEG signals is well-studied topic for the last couple of decades. Lately, automated signal processing and machine learning methods were developed to detect epileptic seizures. However, most of the methods are tailored to subjects and require fine tuning of many parameters. In this study, we proposed to use Riemannian geometry-based signal processing method that already showed superior performance on brain-computer interface problems, to extract features. We showed that tangent space mapping features of EEG signals can be used to detect seizures with high accuracy and precision.
Citation - Scopus: 7
A Comparative Analysis on Medical Article Classification Using Text Mining & Machine Learning Algorithms
(Institute of Electrical and Electronics Engineers Inc., 2021) Kolukisa, Burak; Dedeturk, Bilge Kagan; Dedeturk, Beyhan Adanur; Gulsen, Abdulkadir; Bakal, Gokhan
The document classification task is one of the widely studied research fields on multiple domains. The core motivation of the classification task is that the manual classification efforts are impractical due to the exponentially growing document volumes. Thus, we densely need to exploit automated computational approaches, such as machine learning models along with data & text mining techniques. In this study, we concentrated on the classification of medical articles specifically on common cancer types, due to the significance of the field and the decent number of available documents of interest. We deliberately targeted MEDLINE articles about common cancer types because most cancer types share a similar literature composition. Therefore, this situation makes the classification effort relatively more complicated. To this end, we built multiple machine learning models, including both traditional and deep learning architectures. We achieved the best performance (R¿82% F score) by the LSTM model. Overall, our results demonstrate a strong effect of exploiting both text mining and machine learning methods to distinguish medical articles on common cancer types. © 2022 Elsevier B.V., All rights reserved.
Citation - Scopus: 2
Investigation of the Beneficiation of Low Grade Manganese Ores
(Chamber of Mining Engineers of Turkey maden@maden.org.tr, 2013) Bayat, Oktay; Altiner, Mahmut; Top, S.
In this study, beneficiation of low grade manganese ores was investigated by applying high intensity dry magnetic separation, MGS (Multi Gravity Separator) and flotation methods. Manganese grades of the ores were 25.65% Mn and 13.96% Mn taken from Antalya and Kayseri regions, respectively. Flotation and magnetic separation recoveries of both tested samples were low and the grades of the concentrates were less than 45% Mn. Similar results were also observed using a lab-type MGS but a concentrate could be obtained with 41.24% Mn and 78.71% recovery for manganese ores taken from Antalya region. © 2014 Elsevier B.V., All rights reserved.
Stimuli-Responsive and Self-Assembled Sericin Materials for Various Applications
(Elsevier, 2025) Arabaci, N.; Demirbas, A.; Dadi, S.; Dogan, F.; Öçsoy, I.
The silkworm cocoon's structural integrity is maintained by sericin, which acts as a sticky binding layer that envelops the fibroin fibers, effectively holding them together. In the silk industry, sericin is removed from the structure of fibroin during the degumming process in order to provide the silk's whiteness, softness, and smoothness and also to make it dyeable. Sericin, which is separated from the fibroin of the cocoon by the degumming process in the textile industry in the production of silk fabric, is discarded as waste material. This waste helps cell attachment, proliferation, and differentiation in sericin-based materials, owing to its biocompatibility, biodegradability, and bioactivity features. Due to all these specific features, sericin protein is involved in the production of various biomaterials such as films, hydrogels, scaffolds, conduits, fibers, and devices used in tissue engineering and regenerative medicine. © 2025 Elsevier B.V., All rights reserved.
Citation - Scopus: 4
A QoS Provisioning Architecture of Fiber Wireless Network Based on XGPON and IEEE 802.11ac
(Walter de Gruyter GmbH, 2023) Mohammadani, Khalid Hussain; Butt, Rizwan Aslam; Ali, Kamran Ali; Pirzado, Azhar Ali Ayaz; Faheem, Muhammed Yasir; Abro, Adeel; Ain, Noor Ul
The integration of the XGPON network with the 5G WLAN network is a suitable solution for next-generation high-speed access Internet service. We demonstrated the integration of two different standards via the QoS concept. Further, this work also presents a proper mapping scheme of QoS traffic between XG-PON and fifth-generation Wi-Fi standards known as IEEE 802.11ac. The analysis assessment compares the behavior of different IEEE 802.11ac standards with XGPON with-respect-to multimedia traffic in the FiWi network. To assess the performance of the FiWi network, the OMNET++ and INET framework are used to carrying out a comparative analysis in terms of upstream (US) delay and fairness index. The study concludes that the EDCA Wi-Fi module has better performance than the DCF Wi-Fi module with the integrated XGPON system for the FiWi access network. © 2024 Elsevier B.V., All rights reserved.
Text Classification Experiments on Contextual Graphs Built by N-Gram Series
(Springer International Publishing AG, 2025) Sen, Tarik Uveys; Yakit, Mehmet Can; Gumus, Mehmet Semih; Abar, Orhan; Bakal, Gokhan
Traditional n-gram textual features, commonly employed in conventional machine learning models, offer lower performance rates on high-volume datasets compared to modern deep learning algorithms, which have been intensively studied for the past decade. The main reason for this performance disparity is that deep learning approaches handle textual data through the word vector space representation by catching the contextually hidden information in a better way. Nonetheless, the potential of the n-gram feature set to reflect the context is open to further investigation. In this sense, creating graphs using discriminative ngram series with high classification power has never been fully exploited by researchers. Hence, the main goal of this study is to contribute to the classification power by including the long-range neighborhood relationships for each word in the word embedding representations. To achieve this goal, we transformed the textual data by employing n-gram series into a graph structure and then trained a graph convolution network model. Consequently, we obtained contextually enriched word embeddings and observed F1-score performance improvements from 0.78 to 0.80 when we integrated those convolution-based word embeddings into an LSTM model. This research contributes to improving classification capabilities by leveraging graph structures derived from discriminative n-gram series.
Citation - WoS: 50
Citation - Scopus: 149
An Investigation on the Determinants of Carbon Emissions for OECD Countries: Empirical Evidence From Panel Models Robust to Heterogeneity and Cross-Sectional Dependence
(Springer Heidelberg, 2016) Dogan, Eyup; Seker, Fahri
This empirical study analyzes the impacts of real income, energy consumption, financial development and trade openness on CO2 emissions for the OECD countries in the Environmental Kuznets Curve (EKC) model by using panel econometric approaches that consider issues of heterogeneity and cross-sectional dependence. Results from the Pesaran CD test, the Pesaran-Yamagata's homogeneity test, the CADF and the CIPS unit root tests, the LM bootstrap cointegration test, the DSUR estimator, and the Emirmahmutoglu-Kose Granger causality test indicate that (i) the panel time-series data are heterogeneous and cross-sectionally dependent; (ii) CO2 emissions, real income, the quadratic income, energy consumption, financial development and openness are integrated of order one; (iii) the analyzed data are cointegrated; (iv) the EKC hypothesis is validated for the OECD countries; (v) increases in openness and financial development mitigate the level of emissions whereas energy consumption contributes to carbon emissions; (vi) a variety of Granger causal relationship is detected among the analyzed variables; and (vii) empirical results and policy recommendations are accurate and efficient since panel econometric models used in this study account for heterogeneity and cross-sectional dependence in their estimation procedures.
Citation - Scopus: 12
CoviDetector: A Transfer Learning-Based Semi Supervised Approach to Detect COVID-19 Using CXR Images
(Elsevier B.V., 2023) Chowdhury, Deepraj; Das, Anik; Dey, Ajoy; Banerjee, Soham; Golec, Muhammed; Kollias, Dimitrios; Arya, Rajesh Chand
COVID-19 was one of the deadliest and most infectious illnesses of this century. Research has been done to decrease pandemic deaths and slow down its spread. COVID-19 detection investigations have utilised Chest X-ray (CXR) images with deep learning techniques with its sensitivity in identifying pneumonic alterations. However, CXR images are not publicly available due to users’ privacy concerns, resulting in a challenge to train a highly accurate deep learning model from scratch. Therefore, we proposed CoviDetector, a new semi-supervised approach based on transfer learning and clustering, which displays improved performance and requires less training data. CXR images are given as input to this model, and individuals are categorised into three classes: (1) COVID-19 positive; (2) Viral pneumonia; and (3) Normal. The performance of CoviDetector has been evaluated on four different datasets, achieving over 99% accuracy on them. Additionally, we generate heatmaps utilising Grad-CAM and overlay them on the CXR images to present the highlighted areas that were deciding factors in detecting COVID-19. Finally, we developed an Android app to offer a user-friendly interface. We release the code, datasets and results’ scripts of CoviDetector for reproducibility purposes; they are available at: https://github.com/dasanik2001/CoviDetector © 2024 Elsevier B.V., All rights reserved.
Evaluating the Impact of Sentiment Analysis on Deep Reinforcement Learning-Based Trading Strategies
(Institute of Electrical and Electronics Engineers Inc., 2024) Etcil, Mustafa; Kolukisa, Burak; Bakir-Güngör, Burcu
Portfolio optimization is a form of investment management that aims to maximize returns while minimizing risks. However, the inherent complexity and unpredictability of financial markets pose a challenge. Recent advancements in machine learning, particularly in deep reinforcement learning (DRL), offer promising solutions by enabling dynamic and adaptive trading strategies. This paper presents a comprehensive evaluation of three actor-critic-based DRL algorithms-Advantage Actor-Critic (A2C), Deep Deterministic Policy Gradient (DDPG), and Proximal Policy Optimization (PPO)-applied to portfolio optimization. These strategies were implemented in both sentiment-aware and non-sentiment-aware versions, allowing for a direct comparison of their performance. The sentiment-aware models incorporated sentiment analysis using FinBERT and knowledge graphs to measure market sentiment from financial news, while the non-sentiment-aware models relied solely on stock prices and technical indicators. Our comparative study demonstrates that incorporating sentiment analysis resulted in consistently superior risk-adjusted returns and portfolio resilience during market fluctuations compared to non-sentiment-aware strategies. © 2025 Elsevier B.V., All rights reserved.
Gain Enhancement of a mmWave Patch Antenna Array Having Limited Number of Input Ports
(Institute of Electrical and Electronics Engineers Inc., 2024) Keskin, Mehmet Ziya; Yentur, Abdulkadir; Ozdur, Ibrahim T.; Kiliç, Veli Tayfun
mmWave sensors are rapidly being used in various fields due to their low power consumption, compact size, and cost-effectiveness, particularly for applications like target detection and tracking. This study investigates the gain enhancement of a patch antenna array operating in the mmWave frequency band of 76 GHz - 81 GHz, where commercial single-chip integrated circuits are available. We analyze the S-parameters and radiation patterns of a reference antenna in detail, comparing simulation results with experimental measurements to ensure accuracy. Acknowledging the challenges posed by mmWave patch antennas, we propose a straightforward method to enhance peak gain while preserving the capabilities of the commercial patch structure. Specifically, by twinning one of the input port signals using a power divider, we increase the number of elements in the array without altering the number of input ports. Our findings suggest that this technique can increase the peak gain by 1.3 dB and narrow the beam by 4°, resulting in practical benefits such as enhanced target detection range and accuracy in radar applications while mostly preserving the functioning of the system. © 2025 Elsevier B.V., All rights reserved.
Citation - WoS: 1
Citation - Scopus: 2
Vision-Based Autonomous Aerial Refueling
(Amer Inst Aeronautics & Astronautics, 2022) Erkin, Tevfik; Abdo, Omer; Sanli, Yilmaz; Celik, Harun; Isci, Hasan
Aerial refueling tasks are very challenging due to the high risk of aircraft close proximity. Currently, within the drogue-probe method, the receiver aircraft pilot manages the refueling task in accordance with the tanker aircraft pilot. Therefore, autonomous aerial refueling is still an unaccomplished task for aircrafts. In this paper, a fully automated aerial refueling procedure based on digital visual inspection is proposed. A nonlinear dynamic model of receiver aircraft is derived to track the motion of drogue. In order to control the receiver aircraft affected by tanker aircraft vortex during approach, and ensure the receiver aircraft to automatically track and dock the tanker aircraft, an autopilot system that considers visual sensing of drogue motion is designed. The receiver aircraft is controlled by the autopilot system via translational motion of tanker aircraft projected by a cameramounted on the receiver aircraft. Thanks to this vision-based controllers, the need of tanker aircraft positioning is denied since camera projection has the capability of perception of three-dimensional direction of tanker aircraft. In order to test the autopilots include vision-based controllers and algorithms, the vision-based autonomous aerial refueling is operated under presence of turbulence and vortex. Finally, the simulation results demonstrate that the proposed guidance-navigation-control system achieve aerial refueling autonomously, and make it feasible and realizable for aircrafts.
Citation - WoS: 3
Citation - Scopus: 3
Template Scoring Methods for Protein Torsion Angle Prediction
(Springer-Verlag Berlin, 2015) Aydin, Zafer; Baker, David; Noble, William Stafford
Prediction of backbone torsion angles provides important constraints about the 3D structure of a protein and is receiving a growing interest in the structure prediction community. In this paper, we introduce a three-stage machine learning classifier to predict the 7-state torsion angles of a protein. The first two stages employ dynamic Bayesian and neural networks to produce an ab-initio prediction of torsion angle states starting from sequence profiles. The third stage is a committee classifier, which combines the ab-initio prediction with a structural frequency profile derived from templates obtained by HHsearch. We develop several structural profile models and obtain significant improvements over the Laplacian scoring technique through: (1) scaling templates by integer powers of sequence identity score, (2) incorporating other alignment scores as multiplicative factors (3) adjusting or optimizing parameters of the profile models with respect to the similarity interval of the target. We also demonstrate that the torsion angle prediction accuracy improves at all levels of target-template similarity even when templates are distant from the target. The improvement is at significantly higher rates as template structures gradually get closer to target.
Citation - Scopus: 5
Development of Knowledge Based Response Correction for a Reconfigurable N-Shaped Microstrip Antenna Design
(Institute of Electrical and Electronics Engineers Inc., 2015) Aoad, Ashrf; Simsek, Murat; Aydin, Zafer
This study presents the use of prior knowledge of inverse artificial neural network (ANN) to model and optimize a reconfigurable N-shaped microstrip antenna. Three accurate prior knowledge inverse ANNs with large amount training data are proposed where the frequency information is incorporated into the structure of ANN. The complexity of the input/output relationship is reduced by using prior knowledge. Three separate methods of incorporating knowledge in the second step of the training process with a multilayer perceptron (MLP) in the first step are demonstrated and their results are compared to EM simulation. © 2023 Elsevier B.V., All rights reserved.
Range-Based Wireless Sensor Network Localization by a Circumnavigating Mobile Anchor Without Position Information
(IEEE, 2024) Guler, Samet
Typical range-based wireless sensor network (WSN) localization approaches aim at estimating the sensor node positions by using a set of anchors with known positions. In some applications, assuming the knowledge of the anchors' positions may be impractical, and estimation of the sensors' positions in an arbitrary fixed frame may be sufficient. Considering such scenarios, we propose a WSN localization algorithm by single mobile anchor without self location information. The mobile anchor obtains distance measurements from the sensors while tracking a custom trajectory which is shown to improve the localization performance over time for high signal-to-noise ratio cases. By utilizing two stationary reference nodes within the WSN, the proposed framework generates sensor node position estimation up to translation and rotation with sufficient precision in the absence of global positioning aids. We foresee that the proposed framework can demonstrate benefits in several WSN applications ranging from internet-of-things to service robotics.
Citation - Scopus: 13
Staging of the Liver Fibrosis From CT Images Using Texture Features
(2012) Kayaaltı, Ömer; Aksebzeci, Bekir Hakan; Karahan, Ökkeş Ibrahim; Deniz, Kemal; Öztürk, Menmet; Yilmaz, Bulent; Asyali, Musa Hakan
Even though liver biopsy is critical for evaluating chronic hepatitis and fibrosis, it is an invasive, costly, and difficult to standardize approach. The developments in medical image processing and artificial intelligence methods have advanced the potential of using computer-aided diagnosis techniques in the classification of liver tissues. The aim of this study was to develop a non-invasive, cost-effective, and fast approach to specify fibrosis stage using the texture properties of computed tomography images of liver. Gray level co-occurrence matrix, discrete wavelet transform, and discrete Fourier transform were the image analysis tools in the feature extraction phase. Following dimension reduction of the texture features support vector machines and k-nearest neighbor methods were used in the classification phase of this study. Our results showed that our approach is feasible in fibrosis staging especially in pairwise stage comparisons with success rate of approximately 90%. © 2012 IEEE. © 2012 Elsevier B.V., All rights reserved.

Browse

Browsing Scopus İndeksli Yayınlar Koleksiyonu by WoS Q "N/A"