A novel hybrid fuzzy time series model for prediction of COVID-19 infected cases and deaths in India

Abstract

World is facing stress due to unpredicted pandemic of novel COVID-19. Daily growing magnitude of confirmed cases of COVID-19 put the whole world humanity at high risk and it has made a pressure on health professionals to get rid of it as soon as possible. So, it becomes necessary to predict the number of upcoming cases in future for the preparation of future plan-of-action and medical set-ups. The present manuscript proposed a hybrid fuzzy time series model for the prediction of upcoming COVID-19 infected cases and deaths in India by using modified fuzzy C-means clustering technique. Proposed model has two phases. In phase-I, modified fuzzy C-means clustering technique is used to form basic intervals with the help of clusters centroid while in phase-II, these intervals are upgraded to form sub-intervals. The proposed model is tested against available COVID-19 data for the measurement of its performance based on mean square error, root mean square error and average forecasting error rate. The novelty of the proposed model lies in the prediction of COVID-19 infected cases and deaths for next coming 31 days. Beside of this, estimation for the approximate number of isolation beds and ICU required has been carried out. The projection of the present model is to provide a base for the decision makers for making protection plan during COVID-19 pandemic.

A novel explainable COVID-19 diagnosis method by integration of feature selection with random forest

“…Using an improved fuzzy clustering algorithm, a novel time series forecasting method is developed in Ref. [ 50 ] for the upcoming COVID-19 patients and deaths in India. Essentially, this technique consists of two steps.…”

“…and their symptoms Medium Medium Song et al [ 49 ] Time-dependent model parameters. forecasting the dynamic spread of COVID-19 Daily reported cases in China and the United States High Low Kumar and Kumar [ 50 ] Fuzzy clustering and time series model Prediction of COVID-19 infected cases and deaths Daily reported cases in India Medium Low Cobre et al [ 51 ] KNN, Neural Networks, Partial Least Squares Discriminant Analysis, etc. Diagnosis and prediction of COVID-19 severity Biochemical, hematological, and urinary biomarkers Medium Low Arvind et al [ 52 ] Sliding-window approach Prediction of intubation among hospitalized patients laboratory and vitals data COVID-19+ patients Medium Low Pahar et al [ 53 ] Residual neural networks Classification of COVID-19 cough Coughing sounds recorded during or after the acute phase of COVID-19 Medium Low Ebinger et al [ 54 ] Logistic regression, SVM, KNN, etc.…”

Analysis of Structured Data in Biomedicine Using Soft Computing Techniques and Computational Analysis

“…In reference [15], A similarity-based agglomerative clustering (SBAC) algorithm is used to cluster data by similarity to reach a cohesive hierarchical cluster. In reference [16], a modified FCM clustering technique with a hybrid fuzzy time series model is used to deal with disease interval information to predict the infected cases and deaths of COVID-19. Some authors put forward the Kullback-Leibler FCM algorithm to process Gauss-multinomial-distributed data sets (KL-FCM-GM) [17].…”

A Study for Plausible Third Wave of COVID-19 in India through Fuzzy Time Series Modelling Based on Particle Swarm Optimization and Fuzzy c-Means

“…(1) initialize the population of n particles, necessary components of PSOEFCM and a small positive number ∈ for stopping criteria (2) randomly generate the centroid and initial velocity of particles (3) stage I: formation of initial centroid using PSO algorithm (4) if the stopping criteria of PSO is not reached do (5) for particle k, (1 ≤ k ≤ c) do (6) evaluate fitness value of each particle according to (16) (7) select the gbest and pbest according to fitness value (8) update velocity vector of each particle by (17) (9) update the position of each cluster by using (18) (10) end for (11) end if (12) stage II: formation of intervals based on updated centroid using EFCM (13) again, by taking iteration number to 0, centroid obtained in step 4, assign them as initial centroid for EFCM algorithm (14) if the stopping criteria of EFCM is not reached do (15) for cluster k, (1 ≤ k ≤ c) do (16) obtained the membership value according to the (19) (17) update each cluster centroid by using (20) (18) end for (19) end if (20) calculate the intervals based on upgraded centroids, after arranging them in ascending order (21)…”