An approach to forecast impact of Covid‐19 using supervised machine learning model

Software Practice and Experience, Journal Year: 2021, Volume and Issue: 52(4), P. 824 - 840

Published: April 1, 2021

Abstract The Covid‐19 pandemic has emerged as one of the most disquieting worldwide public health emergencies 21st century and thrown into sharp relief, among other factors, dire need for robust forecasting techniques disease detection, alleviation well prevention. Forecasting been powerful statistical methods employed world over in various disciplines detecting analyzing trends predicting future outcomes based on which timely mitigating actions can be undertaken. To that end, several machine learning have harnessed depending upon analysis desired availability data. Historically speaking, predictions thus arrived at short term country‐specific nature. In this work, multimodel technique is called EAMA related parameters long‐term both within India a global scale proposed. This proposed hybrid model well‐suited to past present For study, two datasets from Ministry Health & Family Welfare Worldometers, respectively, exploited. Using these datasets, data outlined, observed predicted being very similar real‐time values. experiment also conducted statewise countrywise across it included Appendix.

Language: Английский

---

Utilizing CNN-LSTM techniques for the enhancement of medical systems

Alexandria Engineering Journal, Journal Year: 2023, Volume and Issue: 72, P. 323 - 338

Published: April 15, 2023

Language: Английский

---

The economics of deep and machine learning-based algorithms for COVID-19 prediction, detection, and diagnosis shaping the organizational management of hospitals

Oeconomia Copernicana, Journal Year: 2024, Volume and Issue: 15(1), P. 27 - 58

Published: March 30, 2024

Research background: Deep and machine learning-based algorithms can assist in COVID-19 image-based medical diagnosis symptom tracing, optimize intensive care unit admission, use clinical data to determine patient prioritization mortality risk, being pivotal qualitative provision, reducing errors, increasing survival rates, thus diminishing the massive healthcare system burden relation severe inpatient stay duration, while operational costs throughout organizational management of hospitals. Data-driven financial scenario-based contingency planning, predictive modelling tools, risk pooling mechanisms should be deployed for additional equipment unforeseen demand expenses. Purpose article: We show that deep decision making systems likelihood treatment outcomes with regard susceptible, infected, recovered individuals, performing accurate analyses by modeling based on vital signs, surveillance data, infection-related biomarkers, furthering hospital facility optimization terms bed allocation. Methods: The review software employed article screening quality evaluation were: AMSTAR, AXIS, DistillerSR, Eppi-Reviewer, MMAT, PICO Portal, Rayyan, ROBIS, SRDR. Findings & value added: support tools forecast spread, confirmed cases, infection rates data-driven appropriate resource allocations effective therapeutic protocol development, determining suitable measures regulations using symptoms comorbidities, laboratory records across units, impacting financing infrastructure. As a result heightened personal protective equipment, pharmacy medication, outpatient treatment, supplies, revenue loss vulnerability occur, also due expenses related hiring staff critical expenditures. Hospital care, screening, capacity expansion, lead further losses affecting frontline workers patients.

Language: Английский

---

A Contemporary Review on Drought Modeling Using Machine Learning Approaches

Computer Modeling in Engineering & Sciences, Journal Year: 2021, Volume and Issue: 128(2), P. 447 - 487

Published: Jan. 1, 2021

Drought is the least understood natural disaster due to complex relationship of multiple contributory factors. Its beginning and end are hard gauge, they can last for months or even years. India has faced many droughts in few decades. Predicting future vital framing drought management plans sustain resources. The data-driven modelling forecasting metrological time series prediction becoming more powerful flexible with computational intelligence techniques. Machine learning (ML) techniques have demonstrated success process popular predict weather, especially minimum temperature using backpropagation algorithms. favourite ML weather include support vector machines (SVM), regression, random forest, decision tree, logistic Naive Bayes, linear gradient boosting k-nearest neighbours (KNN), adaptive neuro-fuzzy inference system, feed-forward neural networks, Markovian chain, Bayesian network, hidden Markov models, autoregressive moving averages, evolutionary algorithms, deep more. This paper presents a recent review literature prediction, indices, dataset, performance metrics.

Language: Английский

---

Deep learning for Covid-19 forecasting: State-of-the-art review.

Neurocomputing, Journal Year: 2022, Volume and Issue: 511, P. 142 - 154

Published: Sept. 8, 2022

Language: Английский

---

Fiber Bragg grating sensor-based temperature monitoring of solar photovoltaic panels using machine learning algorithms

Optical Fiber Technology, Journal Year: 2022, Volume and Issue: 69, P. 102831 - 102831

Published: Feb. 3, 2022

Language: Английский

---

Proposing a hybrid technique of feature fusion and convolutional neural network for melanoma skin cancer detection

Journal of Pathology Informatics, Journal Year: 2023, Volume and Issue: 14, P. 100341 - 100341

Published: Jan. 1, 2023

Skin cancer is among the most common types worldwide. Automatic identification of skin complicated because poor contrast and apparent resemblance between lesions. The rate human death can be significantly reduced if melanoma could detected quickly using dermoscopy images. This research uses an anisotropic diffusion filtering method on images to remove multiplicative speckle noise. To do this, fast-bounding box (FBB) applied here segment region. We also employ 2 feature extractors represent first one Hybrid Feature Extractor (HFE), second convolutional neural network VGG19-based CNN. HFE combines 3 extraction approaches namely, Histogram-Oriented Gradient (HOG), Local Binary Pattern (LBP), Speed Up Robust (SURF) into a single fused vector. CNN used extract additional features from test training datasets. 2-feature vector then design classification model. proposed employed datasets ISIC 2017 academic torrents dataset. Our achieves 99.85%, 91.65%, 95.70% in terms accuracy, sensitivity, specificity, respectively, making it more successful than previously machine learning algorithms.

Language: Английский

---

Advanced data integration in banking, financial, and insurance software in the age of COVID‐19

Software Practice and Experience, Journal Year: 2021, Volume and Issue: 52(4), P. 887 - 903

Published: Aug. 15, 2021

This study contributes to our understanding of how the emergence COVID-19 pandemic changes global Banking Financial Services and Insurance (BFSI) landscape. Before pandemic, BFSIs corporate strategy was solely aligned quest for operational efficiency. However, during ongoing are forced adopt digital transformation in their operations due a rise transaction volumes. The already triggers holistic innovations concerning BFSI's product, process, concept, trend, or idea. Thus, BFSI cannot survive without efficient innovative system software operations. plots hype cycle identify relevant technologies deal with real-world business problems. indicates that need advanced data integration is growing has triggered it. argues incorporation might be challenging initially but eventually it may result an model handle these types unexpected circumstances.

Language: Английский

---

FCMCPS-COVID: AI propelled fog–cloud inspired scalable medical cyber-physical system, specific to coronavirus disease

Internet of Things, Journal Year: 2023, Volume and Issue: 23, P. 100828 - 100828

Published: May 26, 2023

Language: Английский

---

Using Machine Learning Methods to Predict Bone Metastases in Breast Infiltrating Ductal Carcinoma Patients

Frontiers in Public Health, Journal Year: 2022, Volume and Issue: 10

Published: July 6, 2022

Breast cancer (BC) was the most common malignant tumor in women, and breast infiltrating ductal carcinoma (IDC) accounted for about 80% of all BC cases. patients who had bone metastases (BM) were more likely to have poor prognosis bad quality life, earlier attention at a high risk BM important. This study aimed develop predictive model based on machine learning predict with IDC. Six different algorithms, including Logistic regression (LR), Naive Bayes classifiers (NBC), Decision tree (DT), Random Forest (RF), Gradient Boosting Machine (GBM), Extreme gradient boosting (XGB), used build prediction models. The XGB offered best performance among these 6 models internal external validation sets (AUC: 0.888, accuracy: 0.803, sensitivity: 0.801, specificity: 0.837). Finally, an model-based web predictor developed IDC patients, which may help physicians make personalized clinical decisions treatment plans patients.

Language: Английский

---