Profiling Casualty Severity Levels of Road Accident Using Weighted Majority Voting

To determine the individual circumstances that account for a road traffic accident, it is crucial to consider the unplanned connections amongst various factors related to a crash that results in high casualty levels. Analysis of the road accident data concentrated mainly on categorizing accidents into different types using individually built classification methods which limit the prediction accuracy and fitness of the model. In this article, we proposed a multi-model hybrid framework of the weighted majority voting (WMV) scheme with parallel structure, which is designed by integrating individually implemented multinomial logistic regression (MLR) and multilayer perceptron (MLP) classifiers using three different accident datasets i.e., IRTAD, NCDB, and FARS. The proposed WMV hybrid scheme overtook individual classifiers in terms of modern evaluation measures like ROC, RMSE, Kappa rate, classification accuracy, and performs better than state-of-the-art approaches for the prediction of casualty severity level. Moreover, the proposed WMV hybrid scheme adds up to accident severity analysis through knowledge representation by revealing the role of different accident-related factors which expand the risk of casualty in a road crash. Critical aspects related to casualty severity recognized by the proposed WMV hybrid approach can surely support the traffic enforcement agencies to develop better road safety plans and ultimately save lives.     

Evaluating the Efficiency of CBAM-Resnet Using Malaysian Sign Language

The deaf-mutes population is constantly feeling helpless when others do not understand them and vice versa. To fill this gap, this study implements a CNN-based neural network, Convolutional Based Attention Module (CBAM), to recognise Malaysian Sign Language (MSL) in videos recognition. This study has created 2071 videos for 19 dynamic signs. Two different experiments were conducted for dynamic signs, using CBAM-3DResNet implementing ‘Within Blocks’ and ‘Before Classifier’ methods. Various metrics such as the accuracy, loss, precision, recall, F1-score, confusion matrix, and training time were recorded to evaluate the models’ efficiency. Results showed that CBAM-ResNet models had good performances in videos recognition tasks, with recognition rates of over 90% with little variations. CBAM-ResNet ‘Before Classifier’ is more efficient than ‘Within Blocks’ models of CBAM-ResNet. All experiment results indicated the CBAM-ResNet ‘Before Classifier’ efficiency in recognising Malaysian Sign Language and its worth of future research.     

An Optimized Neural Network with Bat Algorithm for DNA Sequence Classification

Recently, many researchers have used nature inspired metaheuristic algorithms due to their ability to perform optimally on complex problems. To solve problems in a simple way, in the recent era bat algorithm has become famous due to its high tendency towards convergence to the global optimum most of the time. But, still the standard bat with random walk has a problem of getting stuck in local minima. In order to solve this problem, this research proposed bat algorithm with levy flight random walk. Then, the proposed Bat with Levy flight algorithm is further hybridized with three different variants of ANN. The proposed BatLFBP is applied to the problem of insulin DNA sequence classification of healthy homosapien. For classification performance, the proposed models such as Bat levy flight Artificial Neural Network (BatLFANN) and Bat levy Flight Back Propagation (BatLFBP) are compared with the other state-of-the-art algorithms like Bat Artificial Neural Network (BatANN), Bat back propagation (BatBP), Bat Gaussian distribution Artificial Neural Network (BatGDANN). And Bat Gaussian distribution back propagation (BatGDBP), in-terms of means squared error (MSE) and accuracy. From the perspective of simulations results, it is show that the proposed BatLFANN achieved 99.88153% accuracy with MSE of 0.001185, and BatLFBP achieved 99.834185 accuracy with MSE of 0.001658 on WL5. While on WL10 the proposed BatLFANN achieved 99.89899% accuracy with MSE of 0.00101, and BatLFBP achieved 99.84473% accuracy with MSE of 0.004553. Similarly, on WL15 the proposed BatLFANN achieved 99.82853% accuracy with MSE of 0.001715, and BatLFBP achieved 99.3262% accuracy with MSE of 0.006738 which achieve better accuracy as compared to the other hybrid models.

     

Structure Preserving Algorithm for Fractional Order Mathematical Model of COVID-19

In this article, a brief biological structure and some basic properties of COVID-19 are described. A classical integer order model is modified and converted into a fractional order model with as order of the fractional derivative. Moreover, a valued structure preserving the numerical design, coined as Grunwald–Letnikov non-standard finite difference scheme, is developed for the fractional COVID-19 model. Taking into account the importance of the positivity and boundedness of the state variables, some productive results have been proved to ensure these essential features. Stability of the model at a corona free and a corona existing equilibrium points is investigated on the basis of Eigen values. The Routh–Hurwitz criterion is applied for the local stability analysis. An appropriate example with fitted and estimated set of parametric values is presented for the simulations. Graphical solutions are displayed for the chosen values of (fractional order of the derivatives). The role of quarantined policy is also determined gradually to highlight its significance and relevancy in controlling infectious diseases. In the end, outcomes of the study are presented.     

A New Hybrid SARFIMA-ANN Model for Tourism Forecasting

Many countries developed and increased greenery in their country sights to attract international tourists. This planning is now significantly contributing to their economy. The next task is to facilitate the tourists by sufficient arrangements and providing a green and clean environment; it is only possible if an upcoming number of tourists’ arrivals are accurately predicted. But accurate prediction is not easy as empirical evidence shows that the tourists’ arrival data often contains linear, nonlinear, and seasonal patterns. The traditional model, like the seasonal autoregressive fractional integrated moving average (SARFIMA), handles seasonal trends with seasonality. In contrast, the artificial neural network (ANN) model deals better with nonlinear time series. To get a better forecasting result, this study combines the merits of the SARFIMA and the ANN models and the purpose of the hybrid SARFIMA-ANN model. Then, we have used the proposed model to predict the tourists’ arrival in New Zealand, Australia, and London. Empirical results showed that the proposed hybrid model outperforms in predicting tourists’ arrival compared to the traditional SARFIMA and ANN models. Moreover, these results can be generalized to predict tourists’ arrival in any country or region with a complicated data pattern.     

Emotion Recognition from Occluded Facial Images Using Deep EnsembleModel

Facial expression recognition has been a hot topic for decades, but high intraclass variation makes it challenging. To overcome intraclass variation for visual recognition, we introduce a novel fusion methodology, in which the proposed model first extract features followed by feature fusion. Specifically, RestNet-50, VGG-19, and Inception-V3 is used to ensure feature learning followed by feature fusion. Finally, the three feature extraction models are utilized using Ensemble Learning techniques for final expression classification. The representation learnt by the proposed methodology is robust to occlusions and pose variations and offers promising accuracy. To evaluate the efficiency of the proposed model, we use two wild benchmark datasets Real-world Affective Faces Database (RAF-DB) and AffectNet for facial expression recognition. The proposed model classifies the emotions into seven different categories namely: happiness, anger, fear, disgust, sadness, surprise, and neutral. Furthermore, the performance of the proposed model is also compared with other algorithms focusing on the analysis of computational cost, convergence and accuracy based on a standard problem specific to classification applications.     

Soft chemistry synthesis of MxV2O5 + ε·nH2O (MCo, Ni, Cu, Zn) nanowires

Recently a simple method was used for preparing nanowires M_xV₂O_5 + ε·nH₂O (MMg, Mn). It consists of mixing a boiling solution of vanadium oxide with the corresponding metal nitrate. In the present paper, this method was explored for preparing other nanowires layered M_xV₂O_5 + ε·nH₂O compounds (MTi, Cr, Fe, Co, Ni, Cu, and Zn). The results obtained show that If the precipitates are formed immediately after mixing the two solutions, such in case of titanium, chromium and iron, the structure and particles shape of the products are different from the layered compound M_xV₂O_5 + ε·nH₂O. However, if the precipitates start to appear only after several minutes of stirring, such in case of cobalt, nickel, copper and zinc, the phases obtained are similar to layered nanowires M_xV₂O_5 + ε·nH₂O. The amount of the metal inserted “M” was found to be lower than 25 at.% in all as-prepared samples. Nickel containing sample shows the highest inserted amount.     

Biosynthesis of essential oils in aromatic plants: A review

In aromatic plants species, biosynthesis of essential oils occurs through two complex natural biochemical pathways involving different enzymatic reactions. Isopentenyl diphosphate (IPP) and its isomer dimethylallyl diphosphate (DMAPP) are the universal precursors of essential oil biosynthesis and are produced by the cytosolic enzymatic MVA (mevalonic acid) pathway or by plastidic and enzymatic 1-deoxy-d-xylolose-5-phosphate (DXP) pathway, also called the 2-C-methylerythritol-4-phosphate (MEP) pathway. In the particular plant cell part, prenyl diphosphate synthases condense isopentenyl diphosphate (IPP) and dimethylallyl diphosphate (DMAPP) further to form prenyl diphosphates, which are used as substrates for geranyl diphosphate (GPP; C₁₀) or for fernesyl diphosphate (FPP; C₁₅). Essential oils are final terpenoid products and are formed by a huge group of enzymes known as terpene synthases (TPS). Essential oils are important secondary metabolites of plants and have been used not only in different industries but also in ethnobotanical medicines for centuries. Hence, considerable research has been undertaken to understand the essential oil biosynthetic pathways. This review will be a valuable source of information in the field of natural products, as we give detailed insights about biosynthesis of essential oils in plants and thus indicate also new unexplored horizons for further research.     

Confinement-Induced Phonon Softening and Hardening in Sb2Te3 Thin Films

Scaling effects in Sesqui-chalcogenides are of major interest to understand and optimize their performance in heavily scaled applications, including topological insulators and phase-change devices. A combined experimental and theoretical study is presented for molecular beam epitaxy-grown films of antimony-telluride  (Sb₂Te₃). Structural,vibrational, optical, and bonding properties upon varying confinement are studied for thicknesses ranging from 1.3 to 56 nm. In ultrathin films, the low-frequency coherent phonons of A_1g¹ symmetry are softened compared to the bulk (64.5 cm⁻¹ at 1.3 nm compared to 68 cm⁻¹ at 55.8 nm). A concomitant increase of the high-frequency A_1g² Raman mode is seen. X-ray diffraction analyses unravel an accompanying out of plane stretch by 5%, mainly stemming from an increase in the Te-Te gap. This conclusion is supported by density functional theory slab models, which reveal a significant dependency of chemical bonding on film thickness. Changes in atomic arrangement, vibrational frequencies, and bonding extend over a thickness range much larger than observed for other material classes. The finding of these unexpectedly pronounced thickness-dependent effects in quasi-2D material Sb₂Te₃ allows tuning of the film properties with thickness. The results are discussed in the context of a novel bond-type, characterized by a competition between electron localization and delocalization.