WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7150
Browse
11 results
Search Results
Article Citation - WoS: 16Citation - Scopus: 17Integrating Experimental and Machine Learning Approaches for Predictive Analysis of Photocatalytic Hydrogen Evolution Using Cu/G-c3n4(Pergamon-elsevier Science Ltd, 2024) Arabaci, Bahriyenur; Bakir, Rezan; Orak, Ceren; Yuksel, AsliThis study addresses environmental issues like global warming and wastewater generation by exploring waste-toenergy strategies that produce renewable hydrogen and treat wastewater simultaneously. Cu/g-C3N4 is used to evolve hydrogen from sucrose solution and the impact of reaction parameters such as pH (3, 5, and 7), Cu loading (5, 10, and 15 wt%), catalyst amount (0.1, 0.2, and 0.3 g/L), and oxidant (H2O2) concentration (0, 10, and 20 mM) on the evolved hydrogen amount is examined. Characterization study confirmed successful incorporation of Cu without significantly altering g-C3N4 properties. The highest hydrogen production (1979.25 mu mol g- 1 & sdot;h- 1) is achieved with 0.3 g/L catalyst, 20 mM H2O2, 5 % Cu loading, and pH 3. The experimental study concludes that Cu/g-C3N4 is an effective photocatalyst for renewable hydrogen production. In addition to the experimental investigations, various machine learning (ML) models, including Random Forest, Decision Tree, XGBoost, among others, are employed to analyze the impact of reaction parameters and forecast the quantities of produced hydrogen. Alongside these individual models, an ensemble approach is proposed and utilized. The R2 values of these ML models ranged from 0.9454 to 0.9955, indicating strong predictive performance across the board. Additionally, these models exhibited low error rates, further confirming their reliability in predicting hydrogen evolution.Article Citation - WoS: 52Citation - Scopus: 57Optimizing Hydrogen Evolution Prediction: a Unified Approach Using Random Forests, Lightgbm, and Bagging Regressor Ensemble Model(Elsevier Ltd, 2024) Bakır,R.; Orak,C.; Yüksel,A.Hydrogen, as a clean and versatile energy carrier, plays a pivotal role in addressing global energy challenges and transitioning towards sustainable energy systems. This study explores the convergence of machine learning (ML) for photocatalytic hydrogen evolution from sucrose solution using perovskite-type catalysts, namely LaFeO3 (LFO) and graphene-supported LaFeO3 (GLFO). This study pioneers the practical application of ML techniques, including Random Forests, LightGBM, and Bagging Regressor, to predict hydrogen yields in the presence of these photocatalysts. LFO and GLFO underwent a thorough characterization study to validate their successful preparation. Noteworthy, the highest hydrogen yield from the sucrose model solution was achieved using GLFO as 3.52 mmol/gcat. The optimum reaction conditions were experimentally found to be pH = 5.25, 0.15 g/L of catalyst amount, and 7.5 mM of HPC (hydrogen peroxide concentration). A pivotal contribution of this research lies in the practical application of ML models, culminating in the development of an ensemble model. This collaborative approach not only achieved an overall R2 of 0.92 but also demonstrated exceptional precision, as reflected in remarkably low error metrics. The mean squared logarithmic error (MSLE) was 0.0032, and the mean absolute error (MAE) was 0.049, underscoring the effectiveness of integrating diverse ML algorithms. This study advances both the understanding of photocatalytic hydrogen evolution and the practical implementation of ML in predicting intricate chemical reactions. © 2024 Hydrogen Energy Publications LLCArticle Citation - WoS: 5Citation - Scopus: 4Identifying Factors Controlling Cellular Uptake of Gold Nanoparticles by Machine Learning(TAYLOR & FRANCIS LTD, 2023) Bilgi, Eyüp; Winkler, David A.; Öksel Karakuş, CeydaThere is strong interest to improve the therapeutic potential of gold nanoparticles (GNPs) while ensuring their safe development. The utility of GNPs in medicine requires a molecular-level understanding of how GNPs interact with biological systems. Despite considerable research efforts devoted to monitoring the internalisation of GNPs, there is still insufficient understanding of the factors responsible for the variability in GNP uptake in different cell types. Data-driven models are useful for identifying the sources of this variability. Here, we trained multiple machine learning models on 2077 data points for 193 individual nanoparticles from 59 independent studies to predict cellular uptake level of GNPs and compared different algorithms for their efficacies of prediction. The five ensemble learners (Xgboost, random forest, bootstrap aggregation, gradient boosting, light gradient boosting machine) made the best predictions of GNP uptake, accounting for 80-90% of the variance in the test data. The models identified particle size, zeta potential, GNP concentration and exposure duration as the most important drivers of cellular uptake. We expect this proof-of-concept study will foster the more effective use of accumulated cellular uptake data for GNPs and minimise any methodological bias in individual studies that may lead to under- or over-estimation of cellular internalisation rates.Review Citation - WoS: 103Citation - Scopus: 136Digital Twin of Electric Vehicle Battery Systems: Comprehensive Review of the Use Cases, Requirements, and Platforms(Elsevier, 2023) Naseri, Farshid; Gil, S.; Barbu, C.; Jensen, A. C.; Larsen, P. G.; Gomes, Claudio; Çetkin, Erdal; Yarımca, GülşahTransportation electrification has been fueled by recent advancements in the technology and manufacturing of battery systems, but the industry yet is facing serious challenges that could be addressed using cutting-edge digital technologies. One such novel technology is based on the digital twining of battery systems. Digital twins (DTs) of batteries utilize advanced multi-layer models, artificial intelligence, advanced sensing units, Internet-of-Things technologies, and cloud computing techniques to provide a virtual live representation of the real battery system (the physical twin) to improve the performance, safety, and cost-effectiveness. Furthermore, they orchestrate the operation of the entire battery value chain offering great advantages, such as improving the economy of manufacturing, re-purposing, and recycling processes. In this context, various studies have been carried out discussing the DT applications and use cases from cloud-enabled battery management systems to the digitalization of battery testing. This work provides a comprehensive review of different possible use cases, key enabling technologies, and requirements for battery DTs. The review inclusively discusses the use cases, development/integration platforms, as well as hardware and software requirements for implementation of the battery DTs, including electrical topics related to the modeling and algorithmic approaches, software architec-tures, and digital platforms for DT development and integration. The existing challenges are identified and circumstances that will create enough value to justify these challenges, such as the added costs, are discussed.Article Citation - WoS: 40Citation - Scopus: 38Investigating the Local-Scale Fluctuations of Groundwater Storage by Using Downscaled Grace/Grace-fo Jpl Mascon Product Based on Machine Learning (ml) Algorithm(Springer, 2023) Khorrami, Behnam; Ali, Shoaib; Gündüz, OrhanGroundwater storage is of grave significance for humanity by sustaining the required water for agricultural irrigation, industry, and domestic use. Notwithstanding the impressive contribution of the state-of-the-art Gravity Recovery and Climate Experiment (GRACE) to detecting the groundwater storage anomaly (GWSA), its feasibility for the characterization of GWSA variation hotspots over small scales is still a major challenge due to its coarse resolution. In this study, a spatial water balance approach is proposed to enhance the spatial depiction of groundwater storage and depletion changes that can detect the hotspots of GWSA variation. In this study, Random Forest Machine Learning (RFML) model was utilized to simulate fine-resolution (10 km) groundwater storage based on the coarse resolution (50 km) of GRACE observations. To this end, parameters including soil moisture, snow water, evapotranspiration, precipitation, surface runoff, surface elevation, and GRACE data were integrated into the RFML model. The results show that with a correlation of above 0.98, the RFML model is very successful in simulating the fine-resolution groundwater storage over the Western Anatolian Basin (WAB), Turkiye. The results indicate an estimated annual depletion rate of 0.14 km(3)/year for the groundwater storage of the WAB, which is equivalent to about 2.57 km(3) of total groundwater depletion from 2003 to 2020. The findings also suggest that the downscaled GWSA is in harmony with the original GWSA in terms of temporal variations. The validation of the results demonstrates that the correlation is increased from 0.56 (for the GRACE-derived GWSA) to 0.60 (for the downscaled GWSA) over the WAB.Article Citation - WoS: 52Citation - Scopus: 60Applied Machine Learning for Prediction of Waste Plastic Pyrolysis Towards Valuable Fuel and Chemicals Production(Elsevier, 2023) Cheng, Yi; Yang, Yang; Coward, Brad; Wang, Jiawei; Yıldız, Güray; Ekici, Ecrin; Yıldız, GürayPyrolysis is a suitable conversion technology to address the severe ecological and environmental hurdles caused by waste plastics' ineffective pre- and/or post-user management and massive landfilling. By using machine learning (ML) algorithms, the present study developed models for predicting the products of continuous and non-catalytically processes for the pyrolysis of waste plastics. Along with different input datasets, four algorithms, including decision tree (DT), artificial neuron network (ANN), support vector machine (SVM), and Gaussian process (GP), were compared to select input variables for the most accurate models. Among these algorithms, the DT model exhibited generalisable and satisfactory accuracy (R2 > 0.99) with training data. The dataset with the elemental composition of waste plastics achieved better accuracy than that with the plastic-type for predicting liquid yields. These observations allow the predictions by the data from ultimate analysis when inaccessible to the plastic-type data in unknown plastic wastes. Besides, the combination of ultimate analysis input and the DT model also achieved excellent accuracy in liquid and gas composition predictions. © 2023 The AuthorsArticle Citation - WoS: 17Citation - Scopus: 19Prediction of Aspergillus Parasiticus Inhibition and Aflatoxin Mitigation in Red Pepper Flakes Treated by Pulsed Electric Field Treatment Using Machine Learning and Neural Networks(Elsevier, 2022) Akdemir Evrendilek, Gülsün; Bulut, Nurullah; Atmaca, Bahar; Uzuner, SibelPresence of aflatoxins in agricultural products is a worldwide problem. Because of their high heat stability and resistance to most of the food processing technologies, aflatoxin degradation is still a big challenge. Thus, efficacy of pulsed electric fields (PEF) by energies ranging from 0.97 to 17.28 J was tested to determine changes in quality properties in red pepper flakes, mitigation of aflatoxins, inactivation of aflatoxin producing Aspergillus parasiticus, reduction in aflatoxin mutagenity, and modelling of A. parasiticus inactivation in addition to aflatoxin mitigation. Maximum inactivation rate of 64.37 % with 17.28 J was encountered on the mean initial A. parasiticus count. A 99.88, 99.47, 97.75, and 99.58 % reductions were obtained on the mean initial AfG1, AfG2, AfB1, and AfB2 concentrations. PEF treated samples by 0.97, 1.36, 5.76, and 17.28 J at 1 μg/plate, 0.97, 1.92, 7.78, 10.80 J at 10 μg/plate, and 0.97, 1.92, 2.92, 4.08, 5.76, 4.86, 6.80, 9.60, 10.80, and 10.89 J at 100 μg/plate were not mutagenic. Modelling with gradient boosting regression tree (GBRT), random forest regression (RFR), and artificial neural network (ANN) provided the lowest RMSE and highest R2 value for GBRT model for the predicted inactivation of A. parasiticus, whereas ANN model provided the lowest RMSE and highest R2 for predicted mitigation of AfG1, AfB1, and AfB2. PEF treatment possess a viable alternative for aflatoxin degradation with reduced mutagenity and without adverse effect on quality properties of red pepper flakes.Article Citation - WoS: 40Citation - Scopus: 38Anisotropic and Outstanding Mechanical, Thermal Conduction, Optical, and Piezoelectric Responses in a Novel Semiconducting Bcn Monolayer Confirmed by First-Principles and Machine Learning(Elsevier, 2022) Mortazavi, Bohayra; Fazel Shojaei; Yağmurcukardeş, Mehmet; Alexander Shapeev; Xiaoying ZhuangGraphene-like nanomembranes made of the neighboring elements of boron, carbon and nitrogen elements, are well-known of showing outstanding physical properties. Herein, with the aid of density functional theory (DFT) calculations, various atomic configurations of the graphene-like BCN nanosheets are investigated. DFT results reveal that depending on the atomic arrangement, the BCN monolayers may display semimetallic Dirac cone or semiconducting electronic nature. BCN nanosheets are also found to exhibit high piezoelectricity and carrier mobilities with considerable in-plane anisotropy, depending on the atomic arrangement. For the predicted most stable BCN monolayer, thermal and mechanical properties are explored using machine learning interatomic potentials. The room temperature tensile strength and lattice thermal conductivity of the most stable BCN monolayer are estimated to be orientation-dependent and remarkably high, over 78 GPa and 290 W/m.K, respectively. In addition, the thermal expansion coefficient of the monolayer BCN at room temperature is estimated to be −3.2 × 10−6 K−1, which is close to that of the graphene. The piezoelectric response of the herein proposed BCN lattice is also predicted to be close to that of the h-BN monolayer. Presented results highlight outstanding physics of the BCN nanosheets.Article Citation - WoS: 3Citation - Scopus: 4Quasi-Supervised Strategies for Compound-Protein Interaction Prediction [article](Wiley-VCH Verlag, 2021) Çakı, Onur; Karaçalı, BilgeIn-silico compound-protein interaction prediction addresses prioritization of drug candidates for experimental biochemical validation because the wet-lab experiments are time-consuming, laborious and costly. Most machine learning methods proposed to that end approach this problem with supervised learning strategies in which known interactions are labeled as positive and the rest are labeled as negative. However, treating all unknown interactions as negative instances may lead to inaccuracies in real practice since some of the unknown interactions are bound to be positive interactions waiting to be identified as such. In this study, we propose to address this problem using the Quasi-Supervised Learning (QSL) algorithm. In this framework, potential interactions are predicted by estimating the overlap between a true positive dataset of compound-protein pairs with known interactions and an unknown dataset of all the remaining compound-protein pairs. The potential interactions are then identified as those in the unknown dataset that overlap with the interacting pairs in the true positive dataset in terms of the associated similarity structure. We also address the class-imbalance problem by modifying the conventional cost function of the QSL algorithm. Experimental results on GPCR and Nuclear Receptor datasets show that the proposed method can identify actual interactions from all possible combinations.Article Citation - WoS: 37Citation - Scopus: 45On the Performance of Pre-Microrna Detection Algorithms(Nature Publishing Group, 2017) Saçar Demirci, Müşerref Duygu; Baumbach, Jan; Allmer, JensMicroRNAs are crucial for post-transcriptional gene regulation, and their dysregulation has been associated with diseases like cancer and, therefore, their analysis has become popular. The experimental discovery of miRNAs is cumbersome and, thus, many computational tools have been proposed. Here we assess 13 ab initio pre-miRNA detection approaches using all relevant, published, and novel data sets while judging algorithm performance based on ten intrinsic performance measures. We present an extensible framework, izMiR, which allows for the unbiased comparison of existing algorithms, adding new ones, and combining multiple approaches into ensemble methods. In an exhaustive attempt, we condense the results of millions of computations and show that no method is clearly superior; however, we provide a guideline for biomedical researchers to select a tool. Finally, we demonstrate that combining all of the methods into one ensemble approach, for the first time, allows reliable purely computational pre-miRNA detection in large eukaryotic genomes.