Search results

The purpose of this paper is to implement a micromechanical hybrid finite element approach in order to investigate the stress transfer behavior of composites reinforced with hexagonal boron nitride (h-BN) nanosheets.

For the analysis of the problem, a three-dimensional representative volume element, consisting of three phases, has been used. The reinforcement is modeled discretely using spring elements of specific stiffness while the matrix material is modeled as a continuum medium using solid finite elements. The third phase, the intermediate one, known as the interface, has been simulated by appropriate stiffness variations which define a heterogeneous region affecting the stress transfer characteristics of the nanocomposite.

The results show a good agreement with corresponding ones from the literature and also the effect of a number of factors is indicated in stress transfer efficiency.

This is the first time that such a modeling is employed in the stress transfer examination of h-BN nanocomposites.

This study aims to investigate the potential of the decorated boron nitride nanocage (BNNc) with transition metals for capturing carbon monoxide (CO) as a toxic gas in the air.

BNNc was modeled in the presence of doping atoms of titanium (Ti), vanadium (V), chromium (Cr), cobalt (Co), copper (Cu) and zinc (Zn) which can increase the gas sensing ability of BNNc. In this research, the calculations have been accomplished by CAM–B3LYP–D3/EPR–3, LANL2DZ level of theory. The trapping of CO molecules by (Ti, V, Cr, Co, Cu, Zn)–BNNc has been successfully incorporated because of binding formation consisting of C → Ti, C → V, C → Cr, C → Co, C → Cu, C → Zn.

Nuclear quadrupole resonance data has indicated that Cu-doped or Co-doped on pristine BNNc has high fluctuations between Bader charge versus electric potential, which can be appropriate options with the highest tendency for electron accepting in the gas adsorption process. Furthermore, nuclear magnetic resonance spectroscopy has explored that the yield of electron accepting for doping atoms on the (Ti, V, Cr, Co, Cu, Zn)–BNNc in CO molecules adsorption can be ordered as follows: Cu > Co >> Cr > Zn ˜ V> Ti that exhibits the strength of the covalent bond between Ti, V, Cr, Co, Cu, Zn and CO. In fact, the adsorption of CO gas molecules can introduce spin polarization on the (Ti, V, Cr, Co, Cu, Zn)–BNNc which specifies that these surfaces may be used as magnetic-scavenging surface as a gas detector. Gibbs free energy based on IR spectroscopy for adsorption of CO molecules adsorption on the (Ti, V, Cr, Co, Cu, Zn)–BNNc have exhibited that for a given number of carbon donor sites in CO, the stabilities of complexes owing to doping atoms of Ti, V, Cr, Co, Cu, Zn can be considered as: CO →Cu–BNNc >> CO → Co–BNNc > CO → Cr–BNNc > CO → V–BNNc > CO → Zn–BNNc > CO → Ti–BNNc.

This study by using materials modeling approaches and decorating of nanomaterials with transition metals is supposed to introduce new efficient nanosensors in applications for selective sensing of carbon monoxide.

This study aims to assess the predictive performance of various factors on Bitcoin returns, used for the development of a robust forecasting support decision model using machine learning techniques, before and during the COVID-19 pandemic. More specifically, the authors investigate the impact of the investor's sentiment on forecasting the Bitcoin returns.

This method uses feature selection techniques to assess the predictive performance of the different factors on the Bitcoin returns. Subsequently, the authors developed a forecasting model for the Bitcoin returns by evaluating the accuracy of three machine learning models, namely the one-dimensional convolutional neural network (1D-CNN), the bidirectional deep learning long short-term memory (BLSTM) neural networks and the support vector machine model.

The findings shed light on the importance of the investor's sentiment in enhancing the accuracy of the return forecasts. Furthermore, the investor's sentiment, the economic policy uncertainty (EPU), gold and the financial stress index (FSI) are the top best determinants before the COVID-19 outbreak. However, there was a significant decrease in the importance of financial uncertainty (FSI and EPU) during the COVID-19 pandemic, proving that investors attach much more importance to the sentimental side than to the traditional uncertainty factors. Regarding the forecasting model accuracy, the authors found that the 1D-CNN model showed the lowest prediction error before and during the COVID-19 and outperformed the other models. Therefore, it represents the best-performing algorithm among its tested counterparts, while the BLSTM is the least accurate model.

Moreover, this study contributes to a better understanding relevant for investors and policymakers to better forecast the returns based on a forecasting model, which can be used as a decision-making support tool. Therefore, the obtained results can drive the investors to uncover potential determinants, which forecast the Bitcoin returns. It actually gives more weight to the sentiment rather than financial uncertainties factors during the pandemic crisis.

To the authors’ knowledge, this is the first study to have attempted to construct a novel crypto sentiment measure and use it to develop a Bitcoin forecasting model. In fact, the development of a robust forecasting model, using machine learning techniques, offers a practical value as a decision-making support tool for investment strategies and policy formulation.

Bitcoin has indeed been universally acknowledged as an investment asset in recent decades, after the boom-and-bust of cryptocurrency values. Because of its extreme volatility, it requires accurate forecasts to build economic decisions. Although prior research has utilized machine learning to improve Bitcoin price prediction accuracy, few have looked into the plausibility of using multiple modeling approaches on datasets containing varying data types and volumetric attributes. Thus, this paper aims to propose a bitcoin price prediction model.

In this research work, a bitcoin price prediction model is introduced by following three major phases: Data collection, feature extraction and price prediction. Initially, the collected Bitcoin time-series data will be preprocessed and the original features will be extracted. To make this work good-fit with a high level of accuracy, we have been extracting the second order technical indicator based features like average true range (ATR), modified-exponential moving average (M-EMA), relative strength index and rate of change and proposed decomposed inter-day difference. Subsequently, these extracted features along with the original features will be subjected to prediction phase, where the prediction of bitcoin price value is attained precisely from the constructed two-level ensemble classifier. The two-level ensemble classifier will be the amalgamation of two fabulous classifiers: optimized convolutional neural network (CNN) and bidirectional long/short-term memory (BiLSTM). To cope up with the volatility characteristics of bitcoin prices, it is planned to fine-tune the weight parameter of CNN by a new hybrid optimization model. The proposed hybrid optimization model referred as black widow updated rain optimization (BWURO) model will be conceptual blended of rain optimization algorithm and black widow optimization algorithm.

The proposed work is compared over the existing models in terms of convergence, MAE, MAPE, MARE, MSE, MSPE, MRSE, Root Mean Square Error (RMSE), RMSPE and RMSRE, respectively. These evaluations have been conducted for both algorithmic performance as well as classifier performance. At LP = 50, the MAE of the proposed work is 0.023372, which is 59.8%, 72.2%, 62.14% and 64.08% better than BWURO + Bi-LSTM, CNN + BWURO, NN + BWURO and SVM + BWURO, respectively.

In this research work, a new modified EMA feature is extracted, which makes the bitcoin price prediction more efficient. In this research work, a two-level ensemble classifier is constructed in the price prediction phase by blending the Bi-LSTM and optimized CNN, respectively. To deal with the volatility of bitcoin values, a novel hybrid optimization model is used to fine-tune the weight parameter of CNN.

In the past decades, artificial intelligence (AI)-based hybrid methods have been increasingly applied in construction risk management practices. The purpose of this paper is to review and compile the current AI methods used for cost-risk assessment in the construction management domain in order to capture complexity and risk interdependencies under high uncertainty.

This paper makes a content analysis, based on a comprehensive literature review of articles published in high-quality journals from the years 2008 to 2018. Fuzzy hybrid methods, such as fuzzy-analytical network processing, fuzzy-artificial neural network and fuzzy-simulation, have been widely used and dominated in the literature due to their ability to measure the complexity and uncertainty of the system.

The findings of this review article suggest that due to the limitation of subjective risk data and complex computation, the applications of these AI methods are limited in order to address cost overrun issues under high uncertainty. It is suggested that a hybrid approach of fuzzy logic and extended form of Bayesian belief network (BBN) can be applied in cost-risk assessment to better capture complexity-risk interdependencies under uncertainty.

This study only focuses on the subjective risk assessment methods applied in construction management to overcome cost overrun problem. Therefore, future research can be extended to interpret the input data required to deal with uncertainties, rather than relying solely on subjective judgments in risk assessment analysis.

These results may assist in the management of cost overrun while addressing complexity and uncertainty to avoid chaos in a project. In addition, project managers, experts and practitioners should address the interrelationship between key complexity and risk factors in order to plan risk impact on project cost. The proposed hybrid method of fuzzy logic and BBN can better support the management implications in recent construction risk management practice.

This study addresses the applications of AI-based methods in complex construction projects. A proposed hybrid approach could better address the complexity-risk interdependencies which increase cost uncertainty in project.