Rapid protocols to support COVID-19 clinical diagnosis based on hematological parameters

Purpose: In December 2019, the Covid-19 pandemic began in the world. To reduce mortality, in addiction to mass vaccination, it is necessary to massify and accelerate clinical diagnosis, as well as creating new ways of monitoring patients that can help in the construction of specific treatments for the disease. Objective: In this work, we propose rapid protocols for clinical diagnosis of COVID-19 through the automatic analysis of hematological parameters using evolutionary computing and machine learning. These hematological parameters are obtained from blood tests common in clinical practice. Method: We investigated the best classifier architectures. Then, we applied the particle swarm optimization algorithm (PSO) to select the most relevant attributes: serum glucose, troponin, partial thromboplastin time, ferritin, D-dimer, lactic dehydrogenase, and indirect bilirubin. Then, we assessed again the best classifier architectures, but now using the reduced set of features. Finally, we used decision trees to build four rapid protocols for Covid-19 clinical diagnosis by assessing the impact of each selected feature. The proposed system was used to support clinical diagnosis and assessment of disease severity in patients admitted to intensive and semi-intensive care units as a case study in the city of Paudalho, Brazil. Results: We developed a web system for Covid-19 diagnosis support. Using a 100-tree random forest, we obtained results for accuracy, sensitivity, and specificity superior to 99%. After feature selection, results were similar. The four empirical clinical protocols returned accuracies, sensitivities and specificities superior to 98%. Conclusion: By using a reduced set of hematological parameters common in clinical practice, it was possible to achieve results of accuracy, sensitivity, and specificity comparable to those obtained with RT-PCR. It was also possible to automatically generate clinical decision protocols, allowing relatively accurate clinical diagnosis even without the aid of the web decision support system. © 2023, The Author(s), under exclusive licence to The Brazilian Society of Biomedical Engineering.

Detecting Ransomware Attacks in Cloud Environment Using Machine Learning-Based Intelligence System in COVID-19 Chaos

2020-2022 provided nearly ideal circumstances for cybercriminals, with confusion and uncertainty dominating the planet due to COVID-19. Our way of life was altered by the COVID-19 pandemic, which also sparked a widespread shift to digital media. However, this change also increased people's susceptibility to cybercrime. As a result, taking advantage of the COVID-19 events' exceedingly unusual circumstances, cybercriminals launched widespread Phishing, Identity theft, Spyware, Trojan-horse, and Ransomware attacks. Attackers choose their victims with the intention of stealing their information, money, or both. Therefore, if we wish to safeguard people from these frauds at a time when millions have already fallen into poverty and the remaining are trying to survive, it is imperative that we put an end to these attacks and assailants. This manuscript proposes an intelligence system for identifying ransomware attacks using nature-inspired and machine-learning algorithms. To classify the network traffic in less time and with enhanced accuracy, Genetic Algorithm (GA) and Particle Swarm Optimization (PSO), two widely used algorithms are coupled in the proposed approach for Feature Selection (FS). Random Forest (RF) approach is used for classification. The system's effectiveness is assessed using the latest ransomware-oriented dataset of CIC-MalMem-2022. The performance is evaluated in terms of accuracy, model building, and testing time and it is found that the proposed method is a suitable solution to detect ransomware attacks. © 2022 IEEE.

COVID-19 Disease Prediction Utilizing Dilated Convolution Neural Network Based Levy Flight Tunicate Swarm Optimization.

The worldwide pandemic of COVID-19 illness has wreaked havoc on the health and lives of countless individuals in more than 200 countries. More than 44 million individuals have been afflicted by October 2020, with over 1,000,000 fatalities reported. This disease, which is classified as a pandemic, is still being researched for diagnosis and therapy. It is critical to diagnose this condition early in order to save a person's life. Diagnostic investigations based on deep learning are speeding up this procedure. As a result, in order to contribute to this sector, our research proposes a deep learning-based technique that may be employed for illness early detection. Based on this insight, gaussian filter is applied to the collected CT images and the filtered images are subjected to the proposed tunicate dilated convolutional neural network, whereas covid and non-covid disease are categorized to improve the accuracy requirement. The hyperparameters involved in the proposed deep learning techniques are optimally tuned using the proposed levy flight based tunicate behaviour. To validate the proposed methodology, evaluation metrics are tested and shows superiority of the proposed approach during COVID-19 diagnostic studies.

Integrating local and neighboring area influences into vulnerability modeling of infectious diseases in Singapore

Infectious disease spreading is a spatial interaction process. Assessing community vulnerability to infectious diseases thus requires not only information on local demographic and built environmental conditions, but also insights into human activity interactions with neighboring areas that can lead to the transition of vulnerability from locations to locations. This study presented an analytical framework based on the Particle Swarm Optimization model to estimate the weights of the factors for vulnerability modeling, and a local proportional parameter for use in the integration of the local and neighboring area risks. A country model and five cross-region validation models were developed for the case study of Singapore to assess the vulnerability to COVID-19. The results showed that the identified weights for the factors were robust throughout the optimization process and across various models. The local proportional parameter could be set slightly higher in between 0.6 and 0.8 (out of 1), signifying that the local effect was higher than the neighboring effect. Computation of the weights from the optimal solutions for the integrated vulnerability index showed that the factors of human activity intensity and accessibility to amenities had much higher weights, at 0.5 and 0.3, respectively. Conversely, the weights of population density, elderly population, social economic status and land use diversity were much lower. These findings underscored the importance of considering non-equal weights for factors and incorporating spatial interactions between local and neighboring areas for vulnerability modeling, to provide to a more comprehensive assessment of vulnerability to infectious diseases.

Dual-stage day-ahead optimized performance of renewable-based microgrids

In distributed networks, wind turbine generators (WTGs) are to be optimally sized and positioned for cost-effective and efficient network service. Various meta-heuristic algorithms have been proposed to allocate WTGs within microgrids. However, the ability of these optimizers might not be guaranteed with uncertainty loads and wind generations. This paper presents novel meta-heuristic optimizers to mitigate extreme voltage drops and the total costs associated with WTGs allocation within microgrids. Arithmetic optimization algorithm (AOA), coronavirus herd immunity optimizer, and chimp optimization algorithm (ChOA) are proposed to manipulate these aspects. The trialed optimizers are developed and analyzed via Matlab, and fair comparison with the grey wolf optimization, particle swarm optimization, and the mature genetic algorithm are introduced. Numerical results for a large-scale 295-bus system (composed of IEEE 141-bus, IEEE 85-bus, IEEE 69-bus subsystems) results illustrate the AOA and the ChOA outperform the other optimizers in terms of satisfying the objective functions, convergence, and execution time. The voltage profile is substantially improved at all buses with the penetration of the WTG with satisfactory power losses through the transmission lines. Day-ahead is considered generic and efficient in terms of total costs. The AOA records costs of 16.575M$/year with a reduction of 31% compared to particle swarm optimization. © 2023 The Authors. IET Renewable Power Generation published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.

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.

A Comprehensive Analysis of Clustering Public Utility Bus Passenger's Behavior during the COVID-19 Pandemic: Utilization of Machine Learning with Metaheuristic Algorithm

Public utility bus (PUB) systems and passenger behaviors drastically changed during the COVID-19 pandemic. This study assessed the clustered behavior of 505 PUB passengers using feature selection, K-means clustering, and particle swarm optimization (PSO). The wrapper method was seen to be the best among the six feature selection techniques through recursive feature selection with a 90% training set and a 10% testing set. It was revealed that this technique produced 26 optimal feature subsets. These features were then fed into K-means clustering and PSO to find PUB passengers' clusters. The algorithm was tested using 12 different parameter settings to find the best outcome. As a result, the optimal parameter combination produced 23 clusters. Utilizing the Pareto analysis, the study only considered the vital clusters. Specifically, five vital clusters were found to have comprehensive similarities in demographics and feature responses. The PUB stakeholders could use the cluster findings as a benchmark to improve the current system.

A modified binary version of aphid-ant mutualism for feature selection: a COVID-19 case study

The speedy development of intelligent technologies and gadgets has led to a drastic increment of dimensions within the datasets in recent years. Dimension reduction algorithms, such as feature selection methods, are crucial to resolving this obstacle. Currently, metaheuristic algorithms have been extensively used in feature selection tasks due to their acceptable computational cost and performance. In this article, a binary-modified version of aphid-ant mutualism (AAM) called binary aphid-ant mutualism (BAAM) is introduced to solve the feature selection problems. Like AAM, in BAAM, the intensification and diversification mechanisms are modeled via the intercommunication of aphids with other colonies' members, including aphids and ants. However, unlike AAM, the number of colonies' members can change in each iteration based on the attraction power of their leaders. Moreover, the second- and third-best individuals can take the place of the ringleader and lead the pioneer colony. Also, to maintain the population diversity, prevent premature convergence, and facilitate information sharing between individuals of colonies including aphids and ants, a random cross-over operator is utilized in BAAM. The proposed BAAM is compared with five other feature selection algorithms using several evaluation metrics. Twelve medical and nine non-medical benchmark datasets with different numbers of features, instances, and classes from the University of California, Irvine and Arizona State University repositories are considered for all the experiments. Moreover, a coronavirus disease (COVID-19) dataset is used to validate the effectiveness of the BAAM in real-world applications. Based on the acquired outcomes, the proposed BAAM outperformed other comparative methods in terms of classification accuracy using various classifiers, including K nearest neighbor, kernel-based extreme learning machine, and multi-class support vector machine, choosing the most informative features, the best and mean fitness values and convergence speed in most cases. As an instance, in the COVID-19 dataset, BAAM achieved 96.53% average accuracy and selected the most informative feature subset.

A global optimization feedback model with PSO for large scale group decision making in hesitant fuzzy linguistic environments

In an increasingly complex and uncertain decision-making environment, large-scale group decision-making (LSGDM) can offer a more efficient method, allowing a large number of decision-makers (DMs) to truly participate in the decision-making process. The consensus-reaching process (CRP) is an effective method for resolving conflicting opinions among large-scale DMs. However, in the existing CRP of LSGDM, the new consensus state and the adjustment cost borne by inconsistent DMs after implementing feedback suggestions are not taken into consideration. To address this issue, this paper proposes a global optimization feedback model with particle swarm optimization (PSO) for LSGDM in hesitant fuzzy linguistic environments. An improved density-based spatial clustering of applications with noise (DBSCAN) on hesitant fuzzy linguistic term sets (HFLTSs) is introduced to classify large-scale DMs into several clusters, and a weight determination method that combines cluster size and intra-cluster tightness is also presented. The consensus degree of clusters is calculated at two levels: intra-consensus and inter-consensus. To improve the global consensus level with minimum cost, a global optimization feedback model is established to generate recommendation advice for inconsistent DMs, and the model is solved by PSO. A numerical example related to "COVID-19” and some comparisons are provided to verify the feasibility and advantages of the proposed method.

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.

Covid-19 Forecasting Using CNN Approach With A Halbinomial Distribution And A Linear Decreasing Inertia Weight-Based Cat Swarm Optimization

In recent times, the COVID-19 epidemic has spread to over 170 nations. Authorities all around the world are feeling the strain of COVID-19 since the total of infected people is rising as well as they does not familiar to handle the problem. The majority of current research effort is thus being directed on the analysis of COVID-19 data within the framework of the machines learning method. Researchers looked the COVID 19 data to make predictions about who would be treated, who would die, and who would get infected in the future. This might prompt governments worldwide to develop strategies for protecting the health of the public. Previous systems rely on Long Short -Term Memory (LSTM) networks for predicting new instances of COVID-19. The LSTM network findings suggest that the pandemic might be over by June of 2020. However, LSTM may have an over-fitting issue, and it may fall short of expectations in terms of true positive. For this issue in COVID-19 forecasting, we suggest using two methods such as Cat Swarm Optimization (CSO) for reducing the inertia weight linearly and then artificial intelligence based binomial distribution is used. In this proposed study, we take the COVID-19 predicting database as an contribution and normalise it using the min-max approach. The accuracy of classification is improved with the use of the first method to choose the optimal features. In this method, inertia weight is added to the CSO optimization algorithm convergence. Death and confirmed cases are predicted for a certain time period throughout India using Convolutional Neural Network with Partial Binomial Distribution based on carefully chosen characteristics. The experimental findings validate that the suggested scheme performs better than the baseline system in terms of f-measure, recall, precision, and accuracy.

Online learning resource recommendation method based on multi-similarity metric optimization under the COVID-19 epidemic.

With the continuous COVID-19 pneumonia epidemic, online learning has become a normal choice for many learners. However, the problems of information overload and knowledge maze have been aggravated in the process of online learning. A learning resource recommendation method based on multi similarity measure optimization is proposed in this paper. We optimize the user score similarity by introducing information entropy, and use particle swarm optimization algorithm to determine the comprehensive similarity weight, and determine the nearest neighbor user with both score similarity and interest similarity through secondary screening in this method. The ultimate goal is to improve the accuracy of recommendation results, and help learners learn more effectively. We conduct experiments on public data sets. The experimental results show that the algorithm in this paper can significantly improve the recommendation accuracy on the basis of maintaining a stable recommendation coverage.

Design and Application of Vague Set Theory and Adaptive Grid Particle Swarm Optimization Algorithm in Resource Scheduling Optimization.

The purpose of resource scheduling is to deal with all kinds of unexpected events that may occur in life, such as fire, traffic jam, earthquake and other emergencies, and the scheduling algorithm is one of the key factors affecting the intelligent scheduling system. In the traditional resource scheduling system, because of the slow decision-making, it is difficult to meet the needs of the actual situation, especially in the face of emergencies, the traditional resource scheduling methods have great disadvantages. In order to solve the above problems, this paper takes emergency resource scheduling, a prominent scheduling problem, as an example. Based on Vague set theory and adaptive grid particle swarm optimization algorithm, a multi-objective emergency resource scheduling model is constructed under different conditions. This model can not only integrate the advantages of Vague set theory in dealing with uncertain problems, but also retain the advantages of adaptive grid particle swarm optimization that can solve multi-objective optimization problems and can quickly converge. The research results show that compared with the traditional resource scheduling optimization algorithm, the emergency resource scheduling model has higher resolution accuracy, more reasonable resource allocation, higher efficiency and faster speed in dealing with emergency events than the traditional resource scheduling model. Compared with the conventional fuzzy theory emergency resource scheduling model, its handling speed has increased by more than 3.82 times.

Study on site selection of emergency medical facilities for rural public health emergencies

In order to improve the scientificity of site selection decision⁃making of emergency medical facilities for rural public health emergencies, based on the characteristics of public health emergencies with rapid spread and strong harmfulness of corona virus disease 2019(COVID-19), according to the design standards of emergency medical facilities, taking into account the characteristics of small rural medical budget and rugged emergency roads, firstly, six influencing factors of engineering geological conditions, unit cost, infection rate, arrival time, site scale and service coverage area of alternative sites of facilities were selected. The Entropy value method(EVM) method and analytic hierarchy process(AHP) method were effectively combined to determine the weight of influencing factors. Secondly, a multi⁃objective location model considering the minimum sum of the distance from patients to emergency medical facilities and the optimal comprehensive evaluation value of the selected emergency medical facilities was established. Then, an IPSO algorithm was designed to solve the model and get the location decision. Finally, some villages in Tianmen city were selected for empirical analysis to verify the effectiveness of the model algorithm. The results show that infection rate and unit cost are the main influencing factors for the construction of emergency medical facilities. IPSO algorithm selects three emergency medical facilities, which can meet the treatment needs of patients in eight villages, and ensure that patients can seek medical treatment within 4-7 minutes,providing guarantee for efficient epidemic prevention and control activities. © 2023 China Safety Science Journal. All rights reserved.

In silico prediction of the inhibition of new molecules on SARS-CoV-2 3CL protease by using QSAR: PSOSVR approach

Continuous effort is dedicated to clinically and computationally discovering potential drugs for the novel coronavirus-2. Computer-Aided Drug Design CADD is the backbone of drug discovery, and shifting to computational approaches has become necessary. Quantitative Structure–Activity Relationship QSAR is a widely used approach in predicting the activity of potential molecules and is an early step in drug discovery. 3-chymotrypsin-like-proteinase 3CLpro is a highly conserved enzyme in the coronaviruses characterized by its role in the viral replication cycle. Despite the existence of various vaccines, the development of a new drug for SARS-CoV-2 is a necessity to provide cures to patients. In the pursuit of exploring new potential 3CLpro SARS-CoV-2 inhibitors and contributing to the existing literature, this work opted to build and compare three models of QSAR to correlate between the molecules' structure and their activity: IC50 through the application of Multiple Linear Regression(MLR), Support Vector Regression(SVR), and Particle Swarm Optimization-SVR algorithms (PSO-SVR). The database contains 71 novel derivatives of ML300which have proven nanomolar activity against the 3CLpro enzyme, and the GA algorithm obtained the representative descriptors. The built models were plotted and compared following various internal and external validation criteria, and applicability domains for each model were determined. The results demonstrated that the PSO-SVR model performed best in predictive ability and robustness, followed by SVR and MLR. These results also suggest that the branching degree 6 had a strong negative impact, while the moment of inertia X/Z ratio, the fraction of rotatable bonds, autocorrelation ATSm2, Keirshape2, and weighted path of length 2 positively impacted the activity. These outcomes prove that the PSO-SVR model is robust and concrete and paves the way for its prediction abilities for future screening of more significant inhibitors' datasets. © 2023, The Author(s) under exclusive licence to Associação Brasileira de Engenharia Química.

An optimal aggregation method for interval grey numbers using on Steiner-Weber point with application

Aiming at the problem of low accuracy of two-dimensional preference information aggregation, this paper takes two-dimensional interval grey numbers as an example to define its preference information mapping rules. This rule maps preference information to preference points on a two-dimensional plane. Based on the theory of plane Steiner-Weber point, we construct a two-dimensional optimal model, and prove the optimality of the model theoretically. Then, adopt plant growth simulation algorithm (PGSA) to solve the proposed model. The obtained optimal aggregation point that can represent the comprehensive opinions. Finally, by analyzing the selection problem of Fangcang shelter hospital and comparing it with the particle swarm optimization (PSO) method, we conclude that the sum of weighted Euclidean distance obtained by our method is minimal. The aggregation precision of our method is higher than that of other aggregation method to a certain extent. © 2023 Elsevier Ltd

Multi-objective Harris Hawks Optimization for Optimal Emergency Vehicle Dispatching During a Pandemic

Harris Hawks Optimization (HHO) is a Swarm Intelligence (SI) algorithm that is inspired by the cooperative behavior and hunting style of Harris Hawks in the nature. Researchers' interest in HHO is increasing day by day because it has global search capability, fast convergence speed and strong robustness. On the other hand, Emergency Vehicle Dispatching (EVD) is a complex task that requires exponential time to choose the right emergency vehicles to deploy, especially during pandemics like COVID-19. Therefore, in this work we propose to model the EVD problem as a multi-objective optimization problem where a potential solution is an allocation of patients to ambulances and the objective is to minimize the travelling cost while maximizing early treatment of critical patients. We also propose to use HHO to determine the best allocation within a reasonable amount of time. We evaluate our proposed HHO for EVD using 2 synthetic datasets. We compare the results of the proposed approach with those obtained using a modified version of Particle Swarm Optimization (PSO). The experimental analysis shows that the proposed multi-objective HHO for EVD is very competitive and gives a substantial improvement over the enhanced PSO algorithm in terms of performance. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Comparative Analysis of Swarm Algorithms to Classification of covid19 on X-Rays

The use of Chest radiograph (CXR) images in the examination and monitoring of different lung disorders like infiltration, tuberculosis, pneumonia, atelectasis, and hernia has long been known. The detection of COVID-19 can also be done with CXR images. COVID-19, a virus that results in an infection of the upper respiratory tract and lungs, was initially detected in late 2019 in China's Wuhan province and is considered to majorly damage the airway and, thus, the lungs of people afflicted. From that time, the virus has quickly spread over the world, with the number of mortalities and cases increasing daily. The COVID-19 effects on lung tissue can be monitored via CXR. As a result, This paper provides a comparison regarding k-nearest neighbors (KNN), Support-vector machine (SVM), and Extreme Gradient Boosting (XGboost) classification techniques depending on Harris Hawks optimization algorithm (HHO), Salp swarm optimization algorithm (SSA), Whale optimization algorithm (WOA), and Gray wolf optimizer (GWO) utilized in this domain and utilized for feature selection in the presented work. The dataset used in this analysis consists of 9000 2D X-ray images in Poster anterior chest view, which has been categorized by using valid tests into two categories: 5500 images of Normal lungs and 4044 images of COVID-19 patients. All of the image sizes were set to 200 × 200 pixels. this analysis used several quantitative evaluation metrics like precision, recall, and F1-score. © 2022 IEEE.

Design and Development of Polymer-Based Optical Fiber Sensor for GAIT Analysis

In the present scenario like COVID-19 pandemic, to maintain physical distance, the gait-based biometric is a must. Human gait identification is a very difficult process, but it is a suitable distance biometric that also gives good results at low resolution conditions even with face features that are not clear. This study describes the construction of a smart carpet that measures ground response force (GRF) and spatio-temporal gait parameters (STGP) using a polymer optical fiber sensor (POFS). The suggested carpet contains two light detection units for acquiring signals. Each unit obtains response from 10 nearby sensors. There are 20 intensity deviation sensors on a fiber. Light-emitting diodes (LED) are triggered successively, using the multiplexing approach that is being employed. Multiplexing is dependent on coupling among the LED and POFS sections. Results of walking experiments performed on the smart carpet suggested that certain parameters, including step length, stride length, cadence, and stance time, might be used to estimate the GRF and STGP. The results enable the detection of gait, including the swing phase, stance, stance length, and double supporting periods. The suggested carpet is dependable, reasonably priced equipment for gait acquisition in a variety of applications. Using the sensor data, gait recognition is performed using genetic algorithm (GA) and particle swarm optimization (PSO) technique. GA- and PSO-based gait template analyses are performed to extract the features with respect to the gait signals obtained from polymer optical gait sensors (POGS). The techniques used for classification of the obtained signals are random forest (RF) and support vector machine (SVM). The accuracy, sensitivity, and specificity results are obtained using SVM classifier and RF classifier. The results obtained using both classifiers are compared. © 2023 Mamidipaka Hema et al.

Medical Images Classification Using Hybrid Deep Learning CNN-PSO-GA

Convolutional Neural Network (CNN) has made outstanding achievements in image processing and detection. The recent research uses CNN to classify the medical images, but this performance depends on its hyperparameters chosen by the programmer. Choosing these parameters is a difficult process if done manually, so there is a need to find out alternative methods. To solve this problem, the researchers hybridized a CNN with particle swarm optimization (PSO) to find better values for these hyperparameters. PSO was hybridized using genetic algorithm to solve the retired particle problem. The purpose of this research is to take advantage of the achievements of deep learning in classifying medical images. The proposed model was tested with three datasets: malaria, COVID-19, and pneumonia. The model achieved 99.5%, 100%, and 99.7% accuracy for the above datasets respectively. These results were compared with the results of the standard CNN;the proposed model surpassed the standard CNN in overall performance. © 2022 IEEE.