Search

• Fairness-aware Collaborative Filtering (FCF). • Adaptive and Concise Empirical Wavelet Transform (ACEWT). • Attention Induced Multi-head Convolutional Neural Network with MobileNetv1. • Classifies the COVID-19, like Normal, COVID-19, SARS, Pneumocystis. • The proposed C19D-AIMCNN-MNet-JSOA model experimentally authenticated. In this research, Attention Induced Multi-head Convolutional Neural Network Organization using MobileNetv1 Transfer Learning and COVID-19 Diagnosis using Jellyfish Search Optimization Process on Chest X-ray Images (C19D-AIMCNN-MNet-JSOA) is proposed. Initially, the input images are taken from chest X-ray dataset. Fairness-aware Collaborative Filtering (FCF) is utilized for eliminating the noise and also improves the X-ray image quality. Next, these pre-processed images are given to Adaptive and Concise Empirical Wavelet Transform (ACEWT) for extracting Grayscale statistic and Haralick Texture features. The extracted features are given into the Attention Induced Multi-head Convolutional Neural Network with MobileNetv1 (AIMCNN-MNet) which classifies the COVID-19, like Normal, COVID-19, SARS, Pneumocystis. In general, AIMCNN-MNet does not show any optimization adaption techniques to determine the ideal parameter to provide precise COVID-19 categorization. The proposed C19D-AIMCNN-MNet-JSOA model experimentally authenticated utilizing chest X-ray dataset in MATLAB and performance metrics including sensitivity, precision, F-Score, specificity, accuracy, Kappa, computation time, error rate used to examine the efficiency of proposed method. The performance of the C19D-AIMCNN-MNet-JSOA approach attains 25.99%, 20.34%, 30%, 19% and 20.35% high Precision, 25.43%, 29.53%, 22%, 28% and 25.31% lower computation Time and 15.249%, 25.491%, 10%, 31% and 13.98% higher RoC comparing with existing methods like novel hand-crafted fusion model founded on deep learning features COVID-19 diagnosis and organization using X-ray pictures of the chest (C19D-CNN-MLP), Multi-modal fusion of deep transfer learning founded COVID-19 diagnosis and organization utilizing chest x-ray images (C19D-MMF-DTL), Recognition and organization of lung diseases for pneumonia and Covid-19 utilizing machine along deep learning methods (C19D-RNN-LSTM). [ABSTRACT FROM AUTHOR]

• To introduce a pre-processor using a cascaded Variable step size NLMS and Sparse Low-Rank filter (CVSS-NLMS-LRF) method to remove noise from ECG signals. • To perform Higher-order spectral energy distribution image (HSDI) method using two-dimensional Fourier transform of the third order cumulant function. • To classify cardiac arrhythmia detection using the multi-stage dual-swin transformer method with attention learning (MS-DSwin-AL). • To propose integrated average subtraction and standard deviation-based optimizer (IASSD) Method for hyperparameter optimization. • To compare the performances of the proposed model with the existing methods in terms of different performance metrics to prove the performance superiority of the proposed method. In this article, a new framework for arrhythmia identification using higher-order spectral distributions and deep learning approaches has been proposed. The input signal is first pre-processed using the Sparse Low-Rank filter (CVSS-NLMS-LRF) and Cascaded Variable step size-Normalized least mean square algorithm (CVSS-NLMS-LRF) techniques. This method eliminates various types of noise signals from the Electrocardiogram (ECG) signals, such as power line noise, baseline wander noise (BW), and high-frequency muscle artefacts. After pre-processing the signal, the features are selected using a Higher-order spectral energy distribution image (HSDI) obtained using a two-dimensional Fourier transform from the third-order cumulant process. Finally, the multi-stage dual swin transformer with attention learning (MS-DSwin-AL) is proposed to classify cardiac arrhythmias in the input ECG spectral. The Dual Swin Transformer, the Channel and Element-wise Attention Mechanism (CEAM) and the Transitional Module (TM) form the framework of the proposed classification. Additionally, the classification parameters are fine-tuned using an Integrated Average Subtraction and Standard Deviation based Optimizer (IASSD) algorithm. As a result, the proposed model is executed in the Python platform using the MIT-BIH dataset, and the performance is considered in terms of various evaluation metrics. Furthermore, the performance of a proposed model is compared with existing classifiers. The proposed model achieves an accuracy (96.01%), specificity (94%), recall (93.02%), and F1-score (89.14%) higher than the existing classifiers for cardiac arrhythmia classification. As a result, it can be said that the proposed model has a strong chance of identifying cardiac arrhythmias from the provided data. [ABSTRACT FROM AUTHOR]

• ECG records over a longer period of time. • Heart arrhythmia is a regular indication of cardiovascular arrhythmia. • It increase the computational time. • The input data is pre-processed using ADKF. • The proposed Deep CNN-Hyb (MPA-NPO)-AC method is implemented in python. Electrocardiogram (ECG) accounts are generally utilized for analyzing and figure cardiovascular arrhythmias for examining the heart ailment. In this situation, medical professionals may need to review the ECG records over a longer period of time to diagnose cardiac arrhythmias. Heart arrhythmia is a regular indication of cardiovascular arrhythmia. Several deep learning models have been suggested to classify the Cardiac Arrhythmia. But, the existing methods do not reach adequate efficiency and increase the computational time. To overcome these issues, deep convolutional neural network optimized with hybrid marine predators and nomadic people optimization for cardiac arrhythmia classification using electrocardiogram signals is proposed in this manuscript. The input data is pre-processed using anisotropic diffusion Kuwahara filtering (ADKF) for removing noise, error, blur and histogram noises. Then Term frequency-inverse document frequency (TF-IDF) based feature extraction is utilized for feature extraction. Afterward, the extracting features are given to the Weibull Distributive Generalized Multidimensional Scaling (WDGMS) feature selection for features selection. Thus, hybrid Marine Predator's Algorithm (MPA) and Nomadic people optimizer (NPO) is employed for optimizing the DCNN weight parameters. The proposed Deep CNN-Hyb (MPA-NPO)-AC method is implemented in python. Thus the proposed Deep CNN-Hyb(MPA-NPO)-AC method attains 14.03 %, 22.30 % and 16.35 % lower error rate; 3.32 %, 4.27 %, 5.39 % and 2.05 % greater AUC compared with existing methods, like time-series augmented signals with deep learning (SVM-CA-ECG), Linearly Adaptive Sine–Cosine Algorithm along application in Deep Neural Network for Feature Optimization in Arrhythmia Categorization utilizing ECG Signals (DNN-CA-ECG) and Categorization of normal sinus rhythm, abnormal arrhythmia and congestive heart fault ECG signals under LSTM with hybrid CNN-SVM deep neural network (CNN-CA-ECG) respectively. [ABSTRACT FROM AUTHOR]

• The role of operations and SCM in managing epidemics and pandemics is reviewed. • Five research areas are identified, providing an integrative view of the field. • Ten future research directions are developed. • A starting point for researchers to investigate this domain is provided. Epidemics have been posing significant challenges to health, existence, and continuity. From the emergence of an outbreak to its elimination, managing an epidemic/pandemic entails many operations and supply chain management decisions that can contribute to a lessening of its impact. With these decisions, epidemic-/pandemic-imposed challenges related to forecasting, planning, supply, manufacturing, storage, and transportation can be addressed in an effort to curtail and end the epidemic/pandemic. We have witnessed these disruptions first-hand during the COVID-19 pandemic, which has had a destructive effect on many well-established supply chains, threatening the existence of firms. The role of operations and supply chain management is thus pivotal for navigating epidemics/pandemics. Against this background, we present a systematic literature review on the role of operations and supply chain management during epidemics and pandemics, illustrating its potential and calling for future research. Leveraging bibliographic coupling analysis, we identify major research areas and contributions that serve as a foundation to propel these domains forward. We further critically review these research areas, identifying multiple themes of which many have been perennially relevant, while others have come to the fore only recently due to the COVID-19 pandemic. Our review provides an integrative view of the field, concurrently advancing theory, and offering ten distinct future research directions. Overall, this paper is meant to serve as a starting point for researchers in operations and supply chain management aiming to investigate this increasingly important domain. [ABSTRACT FROM AUTHOR]

Miri River is a tropical river in Borneo that drains on flat terrain and urbanised area and debauches into the South China Sea. This paper documents the environmental status of this river, and provides an insight into the provenance using bulk chemistry of the sediments, and brings out the geochemical mobility, bioavailability, and potential toxicity of some critical elements based on BCR sequential extraction. The sediments are intense to moderately weathered and recycled products of Neogene sedimentary rocks. The hydrodynamic characteristics of the river favoured an upstream section dominated by fine sand, while the downstream sediments are medium silt. Based on the bulk geochemistry, the Miri River sediments are moderate to considerably contaminated by Cu, Mo, and As in the upstream and by Sb, As and Cu in the downstream. The potential ecological risk values are low except Cu and a significant biological impact is expected in downstream due to Cu, As, Zn and Cr. The mobility, bioavailability and Risk Assessment Code values for Zn and Mn are higher and thus may pose moderate to very high risk to aquatic organisms. Though a high bulk concentration of Cu is observed, the association of Cu with the bioavailable fraction is low. [Display omitted] • Miri River sediments are recycled, moderately weathered and contaminated by Cu and As. • Grain size variations have a significant impact on the bulk composition of the sediments • Fe, Cr, Ni and Cd are mainly associated with residual fraction and thus less threat. • Mn and Zn show higher mobility and RAC values, which may pose a higher risk to aquatic organisms. [ABSTRACT FROM AUTHOR]

• The combination of AE-biLSTM for automated arrhythmia classification. • The input ECG signals are pre-processed by DTCWT for removing the baseline. • AE-biLSTM method contains an encoder that extracts higher level feature. • Decoder output reconstruct ECG signals from higher level features using biLSTM. • Finally classifies the 6 heartbeats such as N, AFIB, B, P, AFL, SBR. In this manuscript, the combination of Auto- Encoder and Bidirectional long short-term memory (AE-biLSTM) for automated arrhythmia classification is proposed to automatically classify the six kinds of Electrocardiogram (ECG) signals with low cost. Initially, the input Electrocardiogram signals are pre-processed by Dual tree complex wavelet transform (DTCWT) for removing the baseline. The pre-processed ECG signals are given to the combined network of AE-biLSTM. The proposed AE-biLSTM method contains an encoder that extracts higher level feature from the Electro cardiogram arrhythmias signals using bidirectional long short- term memory (biLSTM) network, then a decoder output reconstruct Electro cardiogram arrhythmias signals from higher level features using biLSTM network. Finally, the proposed method accurately classifies the 6 heartbeats types, such as normal (N) sinus beat, atrial fibrillation (AFIB), ventricular bigeminy (B), pacing beat (P), atrial flutter (AFL), sinus brady cardia (SBR). The simulating process is activated in MATLAB. Lastly, the AE-biLSTM method utilize 2 extra databases: (i) new N beat (ii) AFIB beat, which is self-determining of the network's training database. The proposed model attains the better performance of 97.15 % accuracy, 98.33% positive predictive value, 99.43% sensitivity, 96.22% specificity compared to the existing methods, such as Automated arrhythmia classification based convolutional neural networks with long short-term memory networks (CNN-LSTM), and automated arrhythmia classification based deep code features with long short-term memory networks (DCF-LSTM) respectively. [ABSTRACT FROM AUTHOR]

The Internet of Vehicles (IoV) ability to monitor the surrounding environment promotes autonomous activities like determining a trajectory and responding accordingly. Security and transportation are vital components of today's technology-driven society. In addition to search and rescue, it may also be used for planetary exploration and material management. So, the Internet of Vehicles must drive independently in various dynamic situations. Unlocking the potential of the IoV navigation process, a dynamic access control architecture-based autonomous navigation system is proposed. It can perform assigned tasks while also reacting quickly to unexpected situations. The efficiency of AI-based IoV navigation is compared and studied using autonomous decision control systems. [Display omitted] [ABSTRACT FROM AUTHOR]

• In this manuscript, MLGK-TDCNN is proposed for the detection of ECG arrhythmia. • Here, the input ECG signals are taken from two datasets: (i) AFDB (ii) MBDB. • These datasets are balanced using Improved fuzzy c-means method. • Moreover, the de-noised ECG signals are given to the MLGK. • Then, the MLGK features given to the TDCNN classifier for detecting AF and NSR. In this manuscript, Multiscale Laplacian graph kernel features combined with Tree Deep Convolutional Neural Network (MLGK-TDCNN) is proposed for the detection of Electrocardiogram (ECG) arrhythmia. Here, the input ECG signals are taken from two datasets: (i) MIT-BIH AF database (AFDB) (ii) MIT-BIH arrhythmia database (MBDB). These datasets are fully unbalanced dataset, and these datasets are balanced using Improved fuzzy c-means method for unbalanced dataset. Moreover, the de-noised ECG signals are given to the MLGK. The proposed MLGK is to combine the Multiscale kernel features from the Preprocessed ECG signals. The combined Multiscale kernel features given to the TDCNN classifier for the detection of AF with raw normal sinus rhythm (NSR). The proposed approach is activated in MATLAB platform, then the efficiency is analyzed with existing approaches. The experimental outcomes demonstrate that the proposed FFREWT-MLGK-TDCNN approach is compared with two databases. From the analysis, the accuracy of AFDB shows 9.40%, 16.44% and 23.20% better than the existing approaches, the accuracy of MBDB shows 14.67%, 21.42% and 7.54% better than the existing approaches, like novel intelligent approach depending on multi-scale convolution kernel (MCK) and Squeeze-and-Excitation network (SENet) for AF detection, automatic arrhythmia classification strategy using the optimization-based deep convolutional neural network (CNN-BaROA), deep learning method for classifying arrhythmia by using 2-second segments of 2D recurrence plot images of ECG signals (2D-CNN) respectively. [ABSTRACT FROM AUTHOR]

Among the various climate change causing agents, transportation alone is responsible for 19.2% of the carbon emissions. By proper implementation of various preventive measures, the impact of transportation on climate change can be drastically reduced. It is also necessary to determine the relationship between the transportation factors responsible for creating environmental degradation and causing climate change and to rank them based on the preventive measures impact to deal with them. In this paper, we have identified the transportation factors that affect climate change and the factors related to its preventive measures based on the 'environment', 'sociology' and 'modernity' elements of Ecological Modernization Theory (EMT). Given the context, this study focusses on development of an assessment framework that combines three techniques: Simple Additive Weighting (SAW), Interpretive Structural Modelling (ISM) and Interpretive Ranking Process (IRP). • We integrate SAW-ISM-IRP approach to understand the impact of transportation on climate change. • We have identified the factors based on Ecological Modernization Theory. • First, SAW has been used to reduce the number of factors in order to apply ISM and IRP easily. • We have collected data from 10 experts. [ABSTRACT FROM AUTHOR]

• We compare a seller's disaster payment period policies to boost demand. • We consider Advance, Cash, Credit or Disaster Grace Period (ACCD) payment options. • The trade-off between default/disaster risk and demand is investigated. • We identify the optimum replenishment cycle and payments period for a seller's profit. Sellers can offer various payment schemes for buyers to boost demand, with the advance, cash, and credit payment policies being popular approaches. To provide further insight into the dynamics of these policies, we consider them in addition to a Disaster Grace Period payment option, which has become increasingly prevalent. The seller's motivation for offering Advance, Cash, Credit or Disaster Grace Period (ACCD) payment options include the desire for a stronger relationship to the buyer, a smoother cash flow throughout the supply chain, and a potential increase in demand. In addition, the disaster grace period payment scheme can help in better navigating worldwide emergencies, such as pandemics, but also natural emergencies like severe storms, floods, tornadoes, and landslides, which have been happening with an increasing frequency over the last decades. However, the increase in the payment period increases the default/disaster risk, rendering a trade-off between risk and demand, making these crucial parameters in influencing the seller's profit. Within this context, we aim to find the optimum replenishment cycle and payments period for a seller to increase their total profit. To do so, we perform numerical analysis to examine the impact of the demand coefficient, interest rate, default risk, disaster risk, and the disaster demand coefficient on profit. The results offer managerial insights on which payment option to choose in a particular setting to maximize profit. We for example find that sellers should offer a disaster grace period when the disaster demand increases and the risk of a disaster decreases. [ABSTRACT FROM AUTHOR]

• Best strategies for a large-scale COVID-19 vaccine distribution are developed. • Storage and transportation requirements, as well as costs are considered. • An equitable distribution is considered due to limited vaccine availability. • Best location and allocation decisions for cold storage facilities are provided. • The model is evaluated in a real-world case study. While cold chain management has been part of healthcare systems, enabling the efficient administration of vaccines in both urban and rural areas, the COVID-19 virus has created entirely new challenges for vaccine distributions. With virtually every individual worldwide being impacted, strategies are needed to devise best vaccine distribution scenarios, ensuring proper storage, transportation and cost considerations. Current models do not consider the magnitude of distribution efforts needed in our current pandemic, in particular the objective that entire populations need to be vaccinated. We expand on existing models and devise an approach that considers the needed extensive distribution capabilities and special storage requirements of vaccines, while at the same time being cognizant of costs. As such, we provide decision support on how to distribute the vaccine to an entire population based on priority. We do so by conducting predictive analysis for three different scenarios and dividing the distribution chain into three phases. As the available vaccine doses are limited in quantity at first, we apply decision tree analysis to find the best vaccination scenario, followed by a synthetic control analysis to predict the impact of the vaccination programme to forecast future vaccine production. We then formulate a mixed-integer linear programming (MILP) model for locating and allocating cold storage facilities for bulk vaccine production, followed by the proposition of a heuristic algorithm to solve the associated objective functions. The application of the proposed model is evaluated by implementing it in a real-world case study. The optimized numerical results provide valuable decision support for healthcare authorities. [ABSTRACT FROM AUTHOR]

• We investigate a location-allocation problem for convalescent plasma banks. • Optimal locations are determined, then collection facilities are allocated. • A MILP model considering transportation time and cost is solved via CPLEX. • Results are validated by a comparison study using NSGA-II and NSGA-III. • The model is implemented within the context of India and results are presented. With convalescent plasma being recognized as an eminent treatment option for COVID-19, this paper addresses the location-allocation problem for convalescent plasma bank facilities. This is a critical topic, since limited supply and overtly increasing cases demand a well-established supply chain. We present a novel plasma supply chain model considering stochastic parameters affecting plasma demand and the unique features of the plasma supply chain. The primary objective is to first determine the optimal location of the plasma banks and to then allocate the plasma collection facilities so as to maintain proper plasma flow within the network. In addition, recognizing the perishable nature of plasma, we integrate a deteriorating rate with the objective that as little plasma as possible is lost. We formulate a robust mixed-integer linear programming (MILP) model by considering two conflicting objective functions, namely the minimization of overall plasma transportation time and total plasma supply chain network cost, with the latter also capturing inventory costs to reduce wastage. We then propose a CPLEX-based optimization approach for solving the MILP functions. The feasibility of our results is validated by a comparison study using the Non-Dominated Sorting Genetic Algorithm-II (NSGA-II) and a proposed modified NSGA-III. The application of the proposed model is evaluated by implementing it in a real-world case study within the context of India. The optimized numerical results, together with their sensitivity analysis, provide valuable decision support for policymakers. [ABSTRACT FROM AUTHOR]