Genetic Algorithm Enhanced by Levy Flight for Dynamic Vehicle Routing Problem with Time Window in Home Healthcare

In the present modern Healthcare system, demands for Home Healthcare services have drastically increased, especially during pandemic outbreaks such as the covid-19 infections. Home Healthcare (HHC) system is meant to provide a flexible method of healthcare services at the patient's home. Since HHC has limited and multi-dimensional resources, its demand is extensively high. As a result, the allocation of resources is one of the most complex and critical tasks for the HHC operational team. The inclusion of dynamic resources in their scheduling and routing plans becomes even more challenging for the HHC team. Hence, we investigate the Dynamic Vehicle routing problem with time window (DVRPTW) using the constraints for adding new patients to the existing route plan based on their preferred timeslots. In order to solve this combinatorial problem, we used Genetic Algorithm (GA) enhanced by Levy Flight (LF) to minimize total travel and idle time and maximize new patient visits in every route plan. In this paper, we evaluated the efficiency of the proposed algorithm by comparing it to the well-known Nearest Neighborhood algorithm, and found that it outperforms well. Thus, by adopting GA along with LF in the HHC organizations can benefit from cost effective and time saving solutions. © 2023 American Institute of Physics Inc.. All rights reserved.

Coronavirus Mask Protection Algorithm: A New Bio-inspired Optimization Algorithm and Its Applications.

Nowadays, meta-heuristic algorithms are attracting widespread interest in solving high-dimensional nonlinear optimization problems. In this paper, a COVID-19 prevention-inspired bionic optimization algorithm, named Coronavirus Mask Protection Algorithm (CMPA), is proposed based on the virus transmission of COVID-19. The main inspiration for the CMPA originated from human self-protection behavior against COVID-19. In CMPA, the process of infection and immunity consists of three phases, including the infection stage, diffusion stage, and immune stage. Notably, wearing masks correctly and safe social distancing are two essential factors for humans to protect themselves, which are similar to the exploration and exploitation in optimization algorithms. This study simulates the self-protection behavior mathematically and offers an optimization algorithm. The performance of the proposed CMPA is evaluated and compared to other state-of-the-art metaheuristic optimizers using benchmark functions, CEC2020 suite problems, and three truss design problems. The statistical results demonstrate that the CMPA is more competitive among these state-of-the-art algorithms. Further, the CMPA is performed to identify the parameters of the main girder of a gantry crane. Results show that the mass and deflection of the main girder can be improved by 16.44% and 7.49%, respectively.

Adjusting non-pharmaceutical interventions based on hospital bed capacity using a multi-operator differential evolution

Without vaccines and medicine, non-pharmaceutical interventions (NPIs) such as social distancing, have been the main strategy in controlling the spread of COVID-19. Strict social distancing policies may lead to heavy economic losses, while relaxed social distancing policies can threaten public health systems. We formulate optimization problems that minimize the stringency of NPIs during the prevaccination and vaccination phases and guarantee that cases requiring hospitalization will not exceed the number of available hospital beds. The approach utilizes an SEIQR model that separates mild from severe cases and includes a parameter µ that quantifies NPIs. Payoff constraints ensure that daily cases are decreasing at the end of the prevaccination phase and cases are minimal at the end of the vaccination phase. Using a penalty method, the constrained minimization is transformed into a non-convex, multi-modal unconstrained optimization problem. We solve this problem using the improved multi-operator differential evolution, which fared well when compared with other optimization algorithms. We apply the framework to determine optimal social distancing strategies in the Republic of Korea given different amounts and types of antiviral drugs. The model considers variants, booster shots, and waning of immunity. The optimal µ values show that fast administration of vaccines is as important as using highly effective vaccines. The initial number of infections and daily imported cases should be kept minimum especially if the bed capacity is low. In Korea, a gradual easing of NPIs without exceeding the bed capacity is possible if there are at least seven million antiviral drugs and the effectiveness of the drug in reducing severity is at least 86%. Model parameters can be adapted to a specific region or country, or other infectious diseases. The framework can be used as a decision support tool in planning economic policies, especially in countries with limited healthcare resources. © 2022 the Author(s).

A Hybrid Metaheuristic Algorithm for the Multi-Objective Location-Routing Problem in the Early Post-Disaster Stage

Disasters such as earthquakes, typhoons, floods and COVID-19 continue to threaten the lives of people in all countries. In order to cover the basic needs of the victims, emergency logistics should be implemented in time. Location-routing problem (LRP) tackles facility location problem and vehicle routing problem simultaneously to obtain the overall optimization. In response to the shortage of relief materials in the early post-disaster stage, a multi-objective model for the LRP considering fairness is constructed by eval-uating the urgency coefficients of all demand points. The objectives are the lowest cost, delivery time and degree of dissatisfaction. Since LRP is a NP-hard problem, a hybrid metaheuristic algorithm of Discrete Particle Swarm Opti-mization (DPSO) and Harris Hawks Optimization (HHO) is designed to solve the model. In addition, three improvement strategies, namely elite-opposition learning, nonlinear escaping energy, multi-probability random walk, are intro-duced to enhance its execution efficiency. Finally, the effectiveness and perfor-mance of the LRP model and the hybrid metaheuristic algorithm are verified by a case study of COVID-19 in Wuhan. It demonstrates that the hybrid meta-heuristic algorithm is more competitive with higher accuracy and the ability to jump out of the local optimum than other metaheuristic algorithms.

A Comprehensive Comparison of the Performance of Metaheuristic Algorithms in Neural Network Training for Nonlinear System Identification

Many problems in daily life exhibit nonlinear behavior. Therefore, it is important to solve nonlinear problems. These problems are complex and difficult due to their nonlinear nature. It is seen in the literature that different artificial intelligence techniques are used to solve these problems. One of the most important of these techniques is artificial neural networks. Obtaining successful results with an artificial neural network depends on its training process. In other words, it should be trained with a good training algorithm. Especially, metaheuristic algorithms are frequently used in artificial neural network training due to their advantages. In this study, for the first time, the performance of sixteen metaheuristic algorithms in artificial neural network training for the identification of nonlinear systems is analyzed. It is aimed to determine the most effective metaheuristic neural network training algorithms. The metaheuristic algorithms are examined in terms of solution quality and convergence speed. In the applications, six nonlinear systems are used. The mean-squared error (MSE) is utilized as the error metric. The best mean training error values obtained for six nonlinear systems were 3.5×10−4, 4.7×10−4, 5.6×10−5, 4.8×10−4, 5.2×10−4, and 2.4×10−3, respectively. In addition, the best mean test error values found for all systems were successful. When the results were examined, it was observed that biogeography-based optimization, moth–flame optimization, the artificial bee colony algorithm, teaching–learning-based optimization, and the multi-verse optimizer were generally more effective than other metaheuristic algorithms in the identification of nonlinear systems.

A novel hybrid DMHS-GMDH algorithm to predict COVID-19 pandemic time series

In this paper, a novel hybrid method called DMHS-GMDH is presented to predict the time series of COVID-19 outbreaks. In this way, a new version of Harmony Search (HS) algorithm, named Double Memory HS (DMHS), is designed to optimize the structure of a Group Method of Data Handling (GMDH) type neural network. We conduct a series of experiments by applying proposed method on real COVID-19 dataset to forecast new cases and deaths of COVID-19. The statistical analysis indicates that the DMHS-GMDH algorithm on average provides better results than other competitors and the results demonstrate how our approach at least improves coefficient of determination and RMSE by 21% and 45%, respectively. © 2021 IEEE.

Grasshopper KUWAHARA and Gradient Boosting Tree for Optimal Features Classifications

This paper aims to design an optimizer followed by a Kawahara filter for optimal classification and prediction of employees’ performance. The algorithm starts by processing data by a modified K-means technique as a hierarchical clustering method to quickly obtain the best features of employees to reach their best performance. The work of this paper consists of two parts. The first part is based on collecting data of employees to calculate and illustrate the performance of each employee. The second part is based on the classification and prediction techniques of the employee performance. This model is designed to help companies in their decisions about the employees’ performance. The classification and prediction algorithms use the Gradient Boosting Tree classifier to classify and predict the features. Results of the paper give the percentage of employees which are expected to leave the company after predicting their performance for the coming years. Results also show that the Grasshopper Optimization, followed by “KF” with the Gradient Boosting Tree as classifier and predictor, is characterized by a high accuracy. The proposed algorithm is compared with other known techniques where our results are fund to be superior.

Effective forecasting of stock market price by using extreme learning machine optimized by PSO-based group oriented crow search algorithm.

Stock index price forecasting is the influential indicator for investors and financial investigators by which decision making capability to achieve maximum benefit with minimum risk can be improved. So, a robust engine with capability to administer useful information is desired to achieve the success. The forecasting effectiveness of stock market is improved in this paper by integrating a modified crow search algorithm (CSA) and extreme learning machine (ELM). The effectiveness of proposed modified CSA entitled as Particle Swarm Optimization (PSO)-based Group oriented CSA (PGCSA) to outperform other existing algorithms is observed by solving 12 benchmark problems. PGCSA algorithm is used to achieve relevant weights and biases of ELM to improve the effectiveness of conventional ELM. The impact of hybrid PGCSA ELM model to predict next day closing price of seven different stock indices is observed by using performance measures, technical indicators and hypothesis test (paired t-test). The seven stock indices are considered by incorporating data during COVID-19 outbreak. This model is tested by comparing with existing techniques proposed in published works. The simulation results provide that PGCSA ELM model can be considered as a suitable tool to predict next day closing price.

A new clustering method for the diagnosis of CoVID19 using medical images.

With the spread of COVID-19, there is an urgent need for a fast and reliable diagnostic aid. For the same, literature has witnessed that medical imaging plays a vital role, and tools using supervised methods have promising results. However, the limited size of medical images for diagnosis of CoVID19 may impact the generalization of such supervised methods. To alleviate this, a new clustering method is presented. In this method, a novel variant of a gravitational search algorithm is employed for obtaining optimal clusters. To validate the performance of the proposed variant, a comparative analysis among recent metaheuristic algorithms is conducted. The experimental study includes two sets of benchmark functions, namely standard functions and CEC2013 functions, belonging to different categories such as unimodal, multimodal, and unconstrained optimization functions. The performance comparison is evaluated and statistically validated in terms of mean fitness value, Friedman test, and box-plot. Further, the presented clustering method tested against three different types of publicly available CoVID19 medical images, namely X-ray, CT scan, and Ultrasound images. Experiments demonstrate that the proposed method is comparatively outperforming in terms of accuracy, precision, sensitivity, specificity, and F1-score.