An Improved Soft Subspace Clustering Algorithm for Brain MR Image Segmentation

In recent years, the soft subspace clustering algorithm has shown good results for high-dimensional data, which can assign different weights to each cluster class and use weights to measure the contribution of each dimension in various features. The enhanced soft subspace clustering algorithm combines interclass separation and intraclass tightness information, which has strong results for image segmentation, but the clustering algorithm is vulnerable to noisy data and dependence on the initialized clustering center. However, the clustering algorithm is susceptible to the influence of noisy data and reliance on initialized clustering centers and falls into a local optimum;the clustering effect is poor for brain MR images with unclear boundaries and noise effects. To address these problems, a soft subspace clustering algorithm for brain MR images based on genetic algorithm optimization is proposed, which combines the generalized noise technique, relaxes the equational weight constraint in the objective function as the boundary constraint, and uses a genetic algorithm as a method to optimize the initialized clustering center. The genetic algorithm finds the best clustering center and reduces the algorithm's dependence on the initial clustering center. The experiment verifies the robustness of the algorithm, as well as the noise immunity in various ways and shows good results on the common dataset and the brain MR images provided by the Changshu First People's Hospital with specific high accuracy for clinical medicine.

Using Social Network Sentiment Analysis and Genetic Algorithm to Improve the Stock Prediction Accuracy of the Deep Learning-Based Approach

Traditionally, most investment tools used to predict stocks are based on quantitative variables, such as finance and capital flow. With the widespread impact of the Internet, investors and investment institutions designing investment strategies are also referring to online comments and discussions. However, multiple information sources, along with uncertainties accompanying international political and economic events and the recent pandemic, have left investors concerned about information interpretation approaches that could aid investment decision-making. To this end, this study proposes a method that combines social media sentiment, genetic algorithm (GA), and deep learning to predict changes in stock prices. First, it employs a hybrid genetic algorithm (HGA) combined with machine learning to identify chip-based indicators closely related to fluctuations in stock prices and then uses them as input for long short-term memory (LSTM) to establish a prediction model. Next, this study proposes five sentiment variables to analyze PTT social media on TSMC's stock price and performs a grey relational analysis (GRA) to identify the sentiment variables most closely related to stock price fluctuations. The sentiment variables are then combined with the selected chip-based indicators as input to build the LSTM prediction model. To improve the efficiency of the LSTM analysis, this study applies the Taguchi method to optimize the hyper-parameters. The results show that the proposed method of using HGA-screened chip-based variables and social media sentiment variables as input to establish an LSTM prediction model can effectively improve the prediction accuracy of stock price fluctuations.

Electrostatic Precipitator Design Optimization for the Removal of Aerosol and Airborne Viruses

In the midst of the COVID-19 pandemic, new requirements for clean air supply are introduced for heating, ventilation, and air conditioning (HVAC) systems. One way for HVAC systems to efficiently remove airborne viruses is by filtering them. Unlike disposable filters that require repeated purchases of consumables, the electrostatic precipitator (ESP) is an alternative option without the drawback of reduced dust collection efficiency in high-efficiency particulate air (HEPA) filters due to dust buildup. The majority of viruses have a diameter ranging from 0.1 μm to 5 μm. This study proposed a two-stage ESP, which charged airborne viruses and particles via positive electrode ionization wire and collected them on a collecting plate with high voltage. Numerical simulations were conducted and revealed a continuous decrease in collection efficiencies between 0.1 μm and 0.5 μm, followed by a consistent increase from 0.5 μm to 1 μm. For particles larger than 1 μm, collection efficiencies exceeding 90% were easily achieved with the equipment used in this study. Previous studies have demonstrated that the collection efficiency of suspended particles is influenced by both the ESP voltage and turbulent flow at this stage. To improve the collection efficiency of aerosols ranging from 0.1 μm to 1 μm, this study used a multi-objective genetic algorithm (MOGA) in combination with numerical simulations to obtain the optimal parameter combination of ionization voltage and flow speed. The particle collection performance of the ESP was examined under the Japan Electrical Manufacturers' Association (JEMA) standards and showed consistent collection performance throughout the experiment. Moreover, after its design was optimized, the precipitator collected aerosols ranging from 0.1 μm to 3 μm, demonstrating an efficiency of over 95%. With such high collection efficiency, the proposed ESP can effectively filter airborne particles as efficiently as an N95 respirator, eliminating the need to wear a mask in a building and preventing the spread of droplet infectious diseases such as COVID-19 (0.08 μm–0.16 μm). © 2023 by the authors.

Determination of households benefits from subsidies by using data mining approaches

Poverty, known as a widespread economic and political challenge (specifically at the times of crisis, like COVID-19), is a very complicated problem, which many countries have been trying for a long time to eradicate. Cash-subsidy allocation procedure using traditional statistical vision is the famous approach, which articles have targeted. Inefficiency of these solutions besides the fact that a pair of households with exact same situation will not be existing leads us to inadequacy and inaccuracy of these methods. This study, by putting data mining and machine learning (as well-known majors in IT and computer Science) visions together, draws a path to overcome this challenge. For this aim, the social, income and expenditure dimensions of a dataset are surveyed from 18885 households considered to measure the population poverty ratio (a fuzzy look at on their eligibility). In respect to the different experimental mode, the effective features are being filtered to use in FCM algorithm in order to determine to what extend the households in the poor or wealthy. Moreover, Genetic Algorithm displays its efficiency in the role of optimizer. Finally, the evaluation results show more accurate outcomes from the feature selection technique (on normalized data) and get the optimized clusters. [ FROM AUTHOR] Copyright of Journal of Information Technology & Politics is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)

Optimization of multistage timeliness transit consolidation problem using adaptive-weighted genetic algorithm.

Cargo consolidation is becoming a crucial part of international transportation and changing the customer consumption patterns of the international community. Poor connections between different operations and the delay of international express have motivated sellers and logistics organizers to put timeliness first in international multimodal transport, especially during the COVID-19 epidemic. However, for cargo with small quality and multiple batches, designing an efficient consolidation network presents a set of unique challenges, including the coupling of multiple origins and destinations (ODs), and fully utilizing the capacity of the container. We defined a multistage timeliness transit consolidation problem to decouple the multiple ODs of the logistics resource. By solving this problem, we can increase the connectivity between different phases and make full use of the container. To make this systematic multistage transit consolidation more flexible, we proposed a two-stage adaptive-weighted genetic algorithm that mainly focuses on the edge area of the Pareto front space and the diversity of the population. Computational experiments indicate that the correlation between parameters has certain regular trends, and appropriate parameter settings can lead to more satisfactory results. We also confirm that the pandemic has a giant influence on the market share of different transportation modes. Moreover, the comparison with other approaches demonstrates the feasibility and effectiveness of the proposed method.

Optimisation-based integrated decision model for ambulance routing in response to pandemic outbreaks

Pandemics and sudden disease outbreaks place considerable stress on hospital resources. Their increasing numbers in recent years has necessitated investment in disaster risk management strategies, particularly in the healthcare sector. The sudden surge of patients, particularly in requesting ambulance services, overwhelms hospital systems and compromises health service delivery. Failure of health planners to respond immediately to a sudden disease outbreak can result in insufficient distribution of healthcare services and can thereby exacerbate the death toll dramatically. The current research aims to develop an optimisation-based integrated decision model to assist healthcare decision-makers with immediate and effective planning for ambulances to move critical patients from their residences to hospitals, considering the available capacities of each hospital. Several lemmas for the problem are proposed, and based on these;several local search methods are developed to improve the performance of the proposed optimisation method. To confirm the efficacy of the proposed approach, a comprehensive comparison is conducted. In conclusion, sensitivity analyses are performed to discuss some practical insights. The proposed models can be adopted to develop decision tools that enable hospital system managers to optimize their resources to changing healthcare needs in disease outbreaks.

The logistic growth regression model with the genetic algorithm for predicting the third wave of the COVID-19 epidemic in Thailand

The world is currently facing the novel coronavirus 2019 (COVID-19). Thailand, with a high basic reproduction number (2.27), the situation remains serious as the disease spreads throughout the country. Applying various control measures to contain the outbreak has increased the need for policymakers to assess the scale of the epidemic. In this study, a logistic growth regression (LGR) model is implemented to characterize the trends and estimate the final size of the third wave of the epidemic in Thailand at both the provincial and national levels. The parameters of the LGR are fine-tuned through the genetic algorithm assisted by the Gauss-Newton algorithm (GA/GNA). The outbreak data from the previous two waves of infection is used to validate the model performance. As a result, the LGR-GA/GNA model provides goodness-of-fit with a low RMSE, high R2, and highly significant parameters. Furthermore, when compared to the LGR model parameterized by particle swarm optimization and ant colony optimization, the proposed model outperforms the rest. In addition, to verify the prediction performance by comparing with the Susceptible-Infectious-Recovered (SIR) model, the proposed model improves the prediction accuracy better than the other. As the work was completed on May 6, 2021, the study found a possible increasing trend of COVID-19 for some vulnerable provinces and the whole country and an estimated final and peak size of the epidemic and their occurrences. The study concluded that the epidemic size of the third wave of COVID-19 in Thailand was about 190,000 by mid-July 2021. © 2023, Khon Kaen University,Research and Technology Transfer Affairs Division. All rights reserved.

Research on Location Selection of Dairy Cold Chain Logistics Distribution Center

With the development of economy and the gradual improvement of material living standards, people's demand for nutritious and fresh products such as fresh, dairy products, fruits and vegetables is also increasing. Under the influence of the COVID-19, people put forward higher requirements for the distribution timeliness and radiation radius of cold chain logistics enterprises. Based on the existing research, this paper conducts an optimization study on the location selection of the distribution center of cold chain logistics for large-scale enterprises with self-operated operation mode. Moreover, a location model based on cluster analysis is proposed. The clustering results are corrected by gravity center method. Secondly, the optimization model of cycle picking is used to consider transportation cost, cooling cost, time constraint and so on. A better distribution center node is selected from the alternative points. Finally, the validity of the model is verified by case analysis. © 2023 SPIE.

Machine Learning Model to Study the Genetic Susceptibility of Patients with Sever Coronavirus Symptoms

COVID 19 is constantly changing properties because of its contagious as an urgent global challenge, and there are no vaccines or effective drugs. Smart model used to measure and prevent the spread of COVID 19 continues to provide health care services is an urgent need. Previous methods to identify severe symptoms of coronavirus in the early stages, but they have failed to predict the symptoms of coronavirus in an accurate way and also take more time. To overcome these issues the effective severe coronavirus symptoms techniques are proposed. Initially, Gradient Conventional Recursive Neural Classifier based classification and Linear Discriminant Genetic Algorithm used feature selection, mutation, and cross-analysis of features of coronary symptoms. These methods are used to select optimized features and selected features, and then classified by neural network. This Gradient Conventional Recursive Neural Classifier selects features based on the correlation between features that reduce irrelevant features involved in the identification process of coronary symptoms. Gradient Conventional Recursive Neural Classifier based on each function, helping to maximize the correlation between the prediction accuracy of coronavirus symptoms. For this reason, it has always been recommended in an effort to increase the accuracy and reliability of diagnostics to use machine learning to design different classification models. © 2023 IEEE.

Application of embedded computer and improved genetic algorithm in the strategy of community of human destiny: the development of artificial intelligence in the context of Covid-19.

Through the COVID-19 epidemic in 2020, the society has deeply realized the inevitability and necessity of building a community that shares the future of mankind. In the face of severely complex international trends and domestic and international economic conditions, artificial intelligence plays an important auxiliary role in the regular prevention and management of COVID-19. In order to effectively correspond to the formalized extensional prevention and control theory, it is essential to use coordination models, rule systems, prevention and control mechanisms, and governance landscapes to build artificial intelligence corresponding systems. This article uses a basic genetic algorithm to realize the robot path plan. This mainly includes the establishment of environmental models, the discovery of chromosomes and the determination of coding methods, the selection and design of fitness functions, and related designs. This paper proposes a new adaptive adjustment mode based on the basic genetic algorithm, which improves the selection and mutation operation, and improves the optimization efficiency of the genetic algorithm. Building an artificial intelligence response system may face various technical risks and governance dilemmas. Only by improving the rule system of artificial intelligence, creating an epidemic prevention and control ecology, conserving the public spirit of the whole people, strengthening the governance of the source of crisis, and further improving the new momentum of economic and social development and public safety. The modernization of governance capabilities can better respond to the current complex situation.

Vaccination and isolation based control design of the COVID-19 pandemic based on adaptive neuro fuzzy inference system optimized with the genetic algorithm.

The study of the COVID-19 pandemic is of pivotal importance due to its tremendous global impacts. This paper aims to control this disease using an optimal strategy comprising two methods: isolation and vaccination. In this regard, an optimized Adaptive Neuro-Fuzzy Inference System (ANFIS) is developed using the Genetic Algorithm (GA) to control the dynamic model of the COVID-19 termed SIDARTHE (Susceptible, Infected, Diagnosed, Ailing, Recognized, Threatened, Healed, and Extinct). The number of diagnosed and recognized people is reduced by isolation, and the number of susceptible people is reduced by vaccination. The GA generates optimal control efforts related to the random initial number of each chosen group as the input data for ANFIS to train Takagi-Sugeno (T-S) fuzzy structure coefficients. Also, three theorems are presented to indicate the positivity, boundedness, and existence of the solutions in the presence of the controller. The performance of the proposed system is evaluated through the mean squared error (MSE) and the root-mean-square error (RMSE). The simulation results show a significant decrease in the number of diagnosed, recognized, and susceptible individuals by employing the proposed controller, even with a 70% increase in transmissibility caused by various variants.

Artificial Bee Colony for Logic Mining in Credit Scoring

During the SARS-CoV-2 (Covid-19) pandemic, credit applications skyrocketed unimaginably. Thus, creditors or financial entities were burdened with information overload to ensure they provided the proper credit to the right person. The existing methods employed by financial entities were prone to overfitting and did not provide any information regarding the behavior of the creditor. However, the outcome did not consider the attribute of the creditor that led to the default outcome. In this paper, a swarm intelligence-based algorithm named Artificial Bee Colony has been implemented to optimize the learning phase of the Hopfield Neural Network with 2 Satisfiability-based Reverse Analysis Methods. The proposed hybrid model will be used to extract logical information in the credit data with more than 80% accuracy compared to the existing method. The effectiveness of the proposed hybrid model was evaluated and showed superior results compared to other models.

Performance optimization of water cycle algorithm for multilevel lupus nephritis image segmentation

Lupus nephritis (LN) is one of the most common and serious clinical manifestations of systemic lupus erythe-matosus (SLE), which causes serious damage to the kidneys of patients. To effectively assist the pathological diagnosis of LN, many researchers utilize a scheme combining multi-threshold image segmentation (MIS) with metaheuristic algorithms (MAs) to classify LN. However, traditional MAs-based MIS methods tend to fall into local optima in the segmentation process and find it difficult to obtain the optimal threshold set. Aiming at this problem, this paper proposes an improved water cycle algorithm (SCWCA) and applies it to the MIS method to generate an SCWCA-based MIS method. Besides, this MIS method uses a non-local means 2D histogram to represent the image information and utilizes Renyi's entropy as the fitness function. First, SCWCA adds a sine initialization mechanism (SS) in the initial stage of the original WCA to generate the initial solution to improve the population quality. Second, the covariance matrix adaptation evolution strategy (CMA-ES) is applied in the population location update stage of WCA to mine high-quality population information. To validate the excellent performance of the SCWCA-based MIS method, the comparative experiment between some peers and SCWCA was carried out first. The experimental results show that the solution of SCWCA was closer to the global optimal solution and can effectively deal with the local optimal problems. In addition, the segmentation experiments of the SCWCA-based MIS method and other equivalent methods on LN images showed that the former can obtain higher-quality segmented LN images.

Neural network inspired differential evolution based task scheduling for cloud infrastructure

In recent years, cloud computing has become an essential technology for businesses and individuals alike. Task scheduling is a critical aspect of cloud computing that affects the performance and efficiency of cloud infrastructure. During this pandemic where most of the healthcare services like COVID-19 sampling, vaccination process, patient management and other services are dependent on cloud infrastructure. These services come with huge clients and server load in a small instance of time. These task loads can only be managed at cloud infrastructure where an efficient resource management algorithm plays an important role. The optimal utilization of cloud infrastructure and optimization algorithms plays a vital role. The cloud resources rely on the allocation policy of the tasks on cloud resources. Simple static, dynamic, and meta-heuristic techniques provide a solution but not the optimal solution. In such a scenario machine learning and evolutionary algorithms are only the solution. In this work, a hybrid model based on meta-heuristic technique and neural network is proposed. The presented neural network inspired differential evolution hybrid technique provides an optimal assignment of the tasks on cloud infrastructure. The performance of the DE-ANN hybrid approach is performed using performance metrics, average start time(ms), average finish time(ms), average execution time(ms), total completion time(ms), simulation time(ms), and average resource utilization respectively. The proposed DE-ANN approach is validated against BB-BC, and Genetic approaches. It outperforms the existing meta-heuristic techniques i.e. Genetic approach, and Big-Bang Big-Crunch. The performance is evaluated using two configuration scenarios using 5 virtual machines and 10 virtual machines with varying tasks from 1000 to 4500. Experimental results show that the DE-ANN technique significantly improves task scheduling performance compared to other traditional techniques. The technique achieves an average improvement of 19.15% in total completion time(ms), 32.23% in average finish time(ms), 51.95% in average execution time(ms), and 33.24% in average resource utilization respectively. The DE-ANN technique is also effective in handling dynamic and uncertain environments, making it suitable for real-world cloud infrastructures.

Evolutionary Optimization of COVID-19 Vaccine Distribution With Evolutionary Demands

Vaccination uptake has become the key factor that will determine our success in containing the coronavirus pneumonia (COVID-19) pandemic. Efficient distribution of vaccines to inoculation spots is crucial to curtailing the spread of the novel COVID-19 pandemic. Normally, in a big city, a huge number of vaccines need to be transported from central depot(s) through a set of satellites to widely scattered inoculation spots by special-purpose vehicles every day. Such a large two-echelon vehicle routing problem is computationally difficult. Moreover, the demands for vaccines evolve with the epidemic spread over time, and the actual demands are hard to determine early and exactly, which not only increases the problem difficulty but also prolongs the distribution time. Based on our practical experience of COVID-19 vaccine distribution in China, we present a hybrid machine learning and evolutionary computation method, which first uses a fuzzy deep learning model to forecast the demands for vaccines for each next day, such that we can predistribute the forecasted number of vaccines to the satellites in advance;after obtaining the actual demands, it uses an evolutionary algorithm (EA) to route vehicles to distribute vaccines from the satellites/depots to the inoculation spots on each day. The EA saves historical problem instances and their high-quality solutions in a knowledge base, so as to capture inherent relationship between evolving problem inputs to solutions;when solving a new problem instance on each day, the EA utilizes historical solutions that perform well on the similar instances to improve initial solution quality and, hence, accelerate convergence. Computational results on real-world instances of vaccine distribution demonstrate that the proposed method can produce solutions with significantly shorter distribution time compared to state-of-the-arts and, hence, contribute to accelerating the achievement of herd immunity.

Pricing Strategy in an Interval-Valued Production Inventory Model for High-Tech Products under Demand Disruption and Price Revision

Due to continuous development in technology, new and updated products are launching in the market more frequently in the area of some high-tech products such as smartphones, laptops, etc. It is noticed that after a certain period of releasing a new product by a particular company some other company develops a similar type of product at a lesser selling price. Customers generally become attracted to buy that updated product causing a sudden disruption in the demand for the first product. The demand for a normal product may also suddenly vanish as we have experienced during the COVID-19 lock down period. The manufacturer is then compelled to reduce the selling price to sell the remaining products. This paper aims at developing a single period production inventory model addressing this particular market condition. This paper also considers carbon emissions from different inventory processes and examines the optimal inventory policies under the cap and trade regulatory policy. Again, in a real-life production system, the various inventory cost components and the carbon emission rates from different inventory processes are not fixed always. To incorporate this issue, the proposed model considers these quantities as interval numbers. The resulting optimization problem is thus also interval-valued and has been solved by using the quantum-behaved particle swarm optimization technique. A numerical illustration is provided to validate the proposed model. Finally, a sensitivity analysis with respect to key inventory parameters is performed to derive some key managerial implications. It is found that the frequency of launching new products is inversely proportional to the optimum profit of the manufacturer. Also, a higher carbon tax rate is found to be beneficial from an environmental point of view.

Towards Exploring Large Molecular Space: An Efficient Chemical Genetic Algorithm.

Generating molecules with desired properties is an important task in chemistry and pharmacy. An efficient method may have a positive impact on finding drugs to treat diseases like COVID-19. Data mining and artificial intelligence may be good ways to find an efficient method. Recently, both the generative models based on deep learning and the work based on genetic algorithms have made some progress in generating molecules and optimizing the molecule's properties. However, existing methods need to be improved in efficiency and performance. To solve these problems, we propose a method named the Chemical Genetic Algorithm for Large Molecular Space (CALM). Specifically, CALM employs a scalable and efficient molecular representation called molecular matrix. Then, we design corresponding crossover, mutation, and mask operators inspired by domain knowledge and previous studies. We apply our genetic algorithm to several tasks related to molecular property optimization and constraint molecular optimization. The results of these tasks show that our approach outperforms the other state-of-the-art deep learning and genetic algorithm methods, where the z tests performed on the results of several experiments show that our method is more than 99% likely to be significant. At the same time, based on the experimental results, we point out the insufficiency in the experimental evaluation standard which affects the fair evaluation of previous work. Supplementary Information: The online version contains supplementary material available at 10.1007/s11390-021-0970-3.

Trajectory Tracking Analysis of Fractional-Order Nonlinear PID Controller for Single Link Robotic Manipulator System

Increasing demand for automation is being observed especially during the recent scenarios like the Covid-19 pandemic, wherein direct contact of the healthcare workers with the patients can be life-threatening. The use of robotic manipulators facilitates in minimizing such risky interactions and thereby providing a safe environment. In this research work, a single link robotic manipulator (SLRM) system is taken, which is a nonlinear multi–input–multi–output system. In order to address the limitations like heavy object movements, uncontrolled oscillations in positional movement, and improper link variations, an adaptive fractional-order nonlinear proportional, integral, and derivative (FONPID) controller has been suggested. This aids in the effective trajectory tracking of the performance of the SLRM system under step input response. Further, by tuning the controller gains using genetic algorithm optimization (GA) based on the minimum objective function (JIAE ) of the integral of absolute error (IAE) index, the suggested controller has been made more robust for trajectory tracking performance. Finally, the comparative analysis of the simulation results of proportional & integral (PI), proportional, integral, & derivative (PID), fractional-order proportional, integral, & derivative (FOPID), and the suggested FONPID controllers validated that the FONPID controller has performed better in terms of minimum JIAE and lower oscillation amplitude in trajectory tracking of positional movement of SLRM system. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

A decision support system for selecting the most suitable machine learning in healthcare using user parameters and requirements

The application of machine learning in the medical field is still limited. The main reason behind the lack of use is the unavailability of an easy-to-use machine learning system that targets non-technical users. The objective of this paper is to propose an automated machine learning system to aid non-technical users. The proposed system provides the user with simple choices to provide suggestions to the system. The system uses the combination of the user's choices and performance evaluation to select the most suited model from available options. In this study, we employed the system on a Parkinson's disease dataset. The templates for support vector machine and random forest algorithms are provided to the system. Support vector machines and random forests were able to produce 80% and 75% accuracy, respectively. The system used performance parameters of the system and user choices to select the most suited models for each test case. The support vector machine was selected as the most suited model in three test cases, while random forest was selected as the most suited for one test case. The test cases also showed that the weighted time parameter impacted the results heavily.Copyright © 2022 The Author(s)