A memetic algorithm using emperor penguin and social engineering optimization for medical data classification

Application and planning of an energy-oriented stochastic disassembly line balancing problem

End-of-life (EOL) products are getting more and more attention as a result of the rapid decline in environmental resources and the dramatic rise in population at the moment. Disassembly is a crucial step in the reuse of EOL products. However, the disassembly process for EOL products is highly uncertain, and the disassembly planning method may not produce the anticipated outcomes in actual implementation. Based on the physical nature of the product disassembly process with multiple uncertain variables, certainty disassembly cannot adequately characterize the uncertain variables effectively. Uncertainty disassembly takes into account the changes in parts caused by product use, such as wear and corrosion, which can better coordinate the arrangement of disassembly tasks and better match the actual remanufacturing process. After analysis, it was found that most of studies on uncertain disassembly focus on the economic efficiency perspective and lack of energy consumption considerations. For the gaps in the current study, this paper proposes a stochastic energy consumption disassembly line balance problem (SEDLBP) and constructs a mathematical model of SEDLBP based on the disassembly of spatial interference matrix, In this model, the energy consumption generated by the disassembly operation and workstation standby is not a constant value but is generated stochastically in a uniformly distributed interval. In addition, an improved social engineering optimization algorithm that incorporates stochastic simulation (SSEO) is proposed in this paper to effectively address the issue. The incorporation of swap operators and swap sequences in SSEO makes it possible to solve discrete optimization problems efficiently. A comparison of a case study with some well-tested intelligent algorithms demonstrates the efficacy of the solutions produced by the proposed SSEO.

A novel firefly algorithm approach for efficient feature selection with COVID-19 dataset

Feature selection is one of the most important challenges in machine learning and data science. This process is usually performed in the data preprocessing phase, where the data is transformed to a proper format for further operations by machine learning algorithm. Many real-world datasets are highly dimensional with many irrelevant, even redundant features. These kinds of features do not improve classification accuracy and can even shrink down performance of a classifier. The goal of feature selection is to find optimal (or sub-optimal) subset of features that contain relevant information about the dataset from which machine learning algorithms can derive useful conclusions. In this manuscript, a novel version of firefly algorithm (FA) is proposed and adapted for feature selection challenge. Proposed method significantly improves performance of the basic FA, and also outperforms other state-of-the-art metaheuristics for both, benchmark bound-constrained and practical feature selection tasks. Method was first validated on standard unconstrained benchmarks and later it was applied for feature selection by using 21 standard University of California, Irvine (UCL) datasets. Moreover, presented approach was also tested for relatively novel COVID-19 dataset for predicting patients health, and one microcontroller microarray dataset. Results obtained in all practical simulations attest robustness and efficiency of proposed algorithm in terms of convergence, solutions' quality and classification accuracy. More precisely, the proposed approach obtained the best classification accuracy on 13 out of 21 total datasets, significantly outperforming other competitor methods.

Modeling a sustainable vaccine supply chain for a healthcare system

This study develops a vaccine supply chain (VSC) to ensure sustainable distribution during a global crisis in a developing economy. In this study, a multi-objective mixed-integer programming (MIP) model is formulated to develop the VSC, ensuring the entire network's economic performance. This is achieved by minimizing the overall cost of vaccine distribution and ensuring environmental and social sustainability by minimizing greenhouse gas (GHG) emissions and maximizing job opportunities in the entire network. The shelf-life of vaccines and the uncertainty associated with demand and supply chain (SC) parameters are also considered in this study to ensure the robustness of the model. To solve the model, two recently developed metaheuristics-namely, the multi-objective social engineering optimizer (MOSEO) and multi-objective feasibility enhanced particle swarm optimization (MOFEPSO) methods-are used, and their results are compared. Further, the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) model has been integrated into the optimization model to determine the best solution from a set of non-dominated solutions (NDSs) that prioritize environmental sustainability. The results are analyzed in the context of the Bangladeshi coronavirus disease (COVID-19) vaccine distribution systems. Numerical illustrations reveal that the MOSEO-TOPSIS model performs substantially better in designing the network than the MOFEPSO-TOPSIS model. Furthermore, the solution from MOSEO results in achieving better environmental sustainability than MOFEPSO with the same resources. Results also reflect that the proposed MOSEO-TOPSIS can help policymakers establish a VSC during a global crisis with enhanced economic, environmental, and social sustainability within the healthcare system.

Human-Inspired Optimization Algorithms: Theoretical Foundations, Algorithms, Open-Research Issues and Application for Multi-Level Thresholding

Humans take immense pride in their ability to be unpredictably intelligent and despite huge advances in science over the past century; our understanding about human brain is still far from complete. In general, human being acquire the high echelon of intelligence with the ability to understand, reason, recognize, learn, innovate, retain information, make decision, communicate and further solve problem. Thereby, integrating the intelligence of human to develop the optimization technique using the human problem-solving ability would definitely take the scenario to next level thus promising an affluent solution to the real world optimization issues. However, human behavior and evolution empowers human to progress or acclimatize with their environments at rates that exceed that of other nature based evolution namely swarm, bio-inspired, plant-based or physics-chemistry based thus commencing yet additional detachment of Nature-Inspired Optimization Algorithm (NIOA) i.e. Human-Inspired Optimization Algorithms (HIOAs). Announcing new meta-heuristic optimization algorithms are at all times a welcome step in the research field provided it intends to address problems effectively and quickly. The family of HIOA is expanding rapidly making it difficult for the researcher to select the appropriate HIOA; moreover, in order to map the problems alongside HIOA, it requires proper understanding of the theoretical fundamental, major rules governing HIOAs as well as common structure of HIOAs. Common challenges and open research issues are yet another important concern in HIOA that needs to be addressed carefully. With this in mind, our work distinguishes HIOAs on the basis of a range of criteria and discusses the building blocks of various algorithms to achieve aforementioned objectives. Further, this paper intends to deliver an acquainted survey and analysis associated with modern compartment of NIOA engineered upon the perception of human behavior and intelligence i.e. Human-Inspired Optimization Algorithms (HIOAs) stressing on its theoretical foundations, applications, open research issues and their implications on color satellite image segmentation to further develop Multi-Level Thresholding (MLT) models utilizing Tsallis and t-entropy as objective functions to judge their efficacy.

Machine learning based accident prediction in secure IoT enable transportation system

Smart city has come a long way since the development of emerging technology like Information and communications technology (ICT), Internet of Things (IoT), Machine Learning (ML), Block chain and Artificial Intelligence. The Intelligent Transportation System (ITS) is an important application in a rapidly growing smart city. Prediction of the automotive accident severity plays a very crucial role in the smart transportation system. The main motive behind this research is to determine the specific features which could affect vehicle accident severity. In this paper, some of the classification models, specifically Logistic Regression, Artificial Neural network, Decision Tree, K-Nearest Neighbors, and Random Forest have been implemented for predicting the accident severity. All the models have been verified, and the experimental results prove that these classification models have attained considerable accuracy. The paper also explained a secure communication architecture model for secure information exchange among all the components associated with the ITS. Finally paper implemented web base Message alert system which will be used for alert the users through smart IoT devices.

A Fine-tuned deep convolutional neural network for chest radiography image classification on COVID-19 cases

The outbreak of coronavirus disease 2019 (COVID-19) continues to have a catastrophic impact on the living standard of people worldwide. To fight against COVID-19, many countries are using a combination of containment and mitigation activities. Effective screening of contaminated patients is a critical step in the battle against COVID-19. During the early medical examination, it was observed that patient having abnormalities in chest radiography images shows the symptoms of COVID-19 infection. Motivated by this, in this article, we proposed a unique framework to diagnose the COVID-19 infection. Here, we removed the fully connected layers of an already proven model VGG-16 and placed a new simplified fully connected layer set that is initialized with some random weights on top of this deep convolutional neural network, which has already learned discriminative features, namely, edges, colors, geometric changes,shapes, and objects. To avoid the risk of destroying the rich features, we warm up our FC head by seizing all layers in the body of our network and then unfreeze all the layers in the network body to be fine-tuned.The suggested classification model achieved an accuracy of 97.12% with 99.2% sensitivity and 99.6% specificity for COVID-19 identification. This classification model is superior to the other classification model used to classify COVID-19 infected patients.

Review of Metaheuristics Inspired from the Animal Kingdom

The search for powerful optimizers has led to the development of a multitude of metaheuristic algorithms inspired from all areas. This work focuses on the animal kingdom as a source of inspiration and performs an extensive, yet not exhaustive, review of the animal inspired metaheuristics proposed in the 2006–2021 period. The review is organized considering the biological classification of living things, with a breakdown of the simulated behavior mechanisms. The centralized data indicated that 61.6% of the animal-based algorithms are inspired from vertebrates and 38.4% from invertebrates. In addition, an analysis of the mechanisms used to ensure diversity was performed. The results obtained showed that the most frequently used mechanisms belong to the niching category.

Improved barnacles mating optimizer algorithm for feature selection and support vector machine optimization

With the rapid development of computer technology, data collection becomes easier, and data object presents more complex. Data analysis method based on machine learning is an important, active, and multi-disciplinarily research field. Support vector machine (SVM) is one of the most powerful and fast classification models. The main challenges SVM faces are the selection of feature subset and the setting of kernel parameters. To improve the performance of SVM, a metaheuristic algorithm is used to optimize them simultaneously. This paper first proposes a novel classification model called IBMO-SVM, which hybridizes an improved barnacle mating optimizer (IBMO) with SVM. Three strategies, including Gaussian mutation, logistic model, and refraction-learning, are used to improve the performance of BMO from different perspectives. Through 23 classical benchmark functions, the impact of control parameters and the effectiveness of introduced strategies are analyzed. The convergence accuracy and stability are the main gains, and exploration and exploitation phases are more properly balanced. We apply IBMO-SVM to 20 real-world datasets, including 4 extremely high-dimensional datasets. Experimental results are compared with 6 state-of-the-art methods in the literature. The final statistical results show that the proposed IBMO-SVM achieves a better performance than the standard BMO-SVM and other compared methods, especially on high-dimensional datasets. In addition, the proposed model also shows significant superiority compared with 4 other classifiers.

Heart disease prediction using hybrid fuzzy K-medoids attribute weighting method with DBN-KELM based regression model

Automated prediction can be offered for further treatment to make effective and relieve the difficulties in the diagnosis of heart condition of patient. In this paper, a hybrid method is proposed combining FKMAW and DBNKELM based ensemble method to enhance medical diagnosis process. Firstly, the input attributes are weighed using a fuzzy k-medoids clustering based attribute weighting (FKMAW) method. Subsequently, the medical data classification performance is improved by applying the weighing method and the linearly separable dataset is obtained with the transformation of non-linearly separable dataset. With the weighted attributes, a regression model based heart disease prediction scheme is proposed combining Deep belief Network and Extreme learning machine (DBNKELM), in which Extreme learning machine is the top layer of the deep belief network to work as a regression model. The results demonstrate that FKMAW + DBNKELM achieved good performance in rectifying the problems in medical data classification for all the six datasets.

Analysis of high-dimensional genomic data using MapReduce based probabilistic neural network

BACKGROUND

The size of genomics data has been growing rapidly over the last decade. However, the conventional data analysis techniques are incapable of processing this huge amount of data. For the efficient processing of high dimensional datasets, it is essential to develop some new parallel methods.

METHODS

In this work, a novel distributed method is presented using Map-Reduce (MR)-based approach. The proposed algorithm consists of MR-based Fisher score (mrFScore), MR-based ReliefF (mrRefiefF), and MR-based probabilistic neural network (mrPNN) using a weighted chaotic grey wolf optimization technique (WCGWO). Here, mrFScore, and mrRefiefF methods are introduced for feature selection (FS), and mrPNN is implemented as an effective method for microarray classification. The proper choice of smoothing parameter (σ) plays a major role in the prediction ability of the PNN which is addressed using a novel technique namely, WCGWO. The WCGWO algorithm is used to select the optimal value of σ in PNN.

RESULTS

These algorithms have been successfully implemented using the Hadoop framework. The proposed model is tested by using three large and one small microarray datasets, and a comparative analysis is carried out with the existing FS and classification techniques. The results suggest that WCGWO-mrPNN can outperform other methods for high dimensional microarray classification.

CONCLUSION

The effectiveness of the proposed methods are compared with other existing schemes. Experimental results reveal that the proposed scheme is accurate and robust. Hence, the suggested scheme is considered to be a reliable framework for microarray data analysis.

SIGNIFICANCE

Such a method promotes the application of parallel programming using Hadoop cluster for the analysis of large-scale genomics data, particularly when the dataset is of high dimension.

A bi-objective home healthcare routing and scheduling problem considering patients' satisfaction in a fuzzy environment

Home care services are an alternative answer to hospitalization, and play an important role in reducing the healthcare costs for governments and healthcare practitioners. To find a valid plan for these services, an optimization problem called the home healthcare routing and scheduling problem is motivated to perform the logistics of the home care services. Although most studies mainly focus on minimizing the total cost of logistics activities, no study, as far as we know, has treated the patients' satisfaction as an objective function under uncertainty. To make this problem more practical, this study proposes a bi-objective optimization methodology to model a multi-period and multi-depot home healthcare routing and scheduling problem in a fuzzy environment. With regards to a group of uncertain parameters such as the time of travel and services as well as patients' satisfaction, a fuzzy approach named as the Jimenez's method, is also utilized. To address the proposed home healthcare problem, new and well-established metaheuristics are obtained. Although the social engineering optimizer (SEO) has been applied to several optimization problems, it has not yet been applied in the healthcare routing and scheduling area. Another innovation is to develop a new modified multi-objective version of SEO by using an adaptive memory strategy, so-called AMSEO. Finally, a comprehensive discussion is provided by comparing the algorithms based on multi-objective metrics and sensitivity analyses. The practicality and efficiency of the AMSEO in this context lends weight to the development and application of the approach more broadly.