Enumerating happiness index during COVID-19 lockdowns using artificial intelligence techniques

Happiness index is an all-inclusive methodology to assess well-being and happiness aspects of human resilience and sustainability. Pandemic like COVID-19 has brought deep level changes to human lifestyle and social behaviours. The world has been reshaped and life has more than likely changed permanently. This has led to calls for mental health, yet there is a dire need to introspect the mental state of health and behavioural changes. Happiness index is calculated based on factors such as GDP, freedom to make choice, health life expectancy and social support. These factors are analysed using datasets from social media with machine learning algorithms to map human response to the pandemic. This research focuses on use of artificial intelligence on the impact of lockdowns due to COVID-19 on the global happiness index.

Machine learning-based diffusion model for prediction of coronavirus-19 outbreak.

The coronavirus pandemic has been globally impacting the health and prosperity of people. A persistent increase in the number of positive cases has boost the stress among governments across the globe. There is a need of approach which gives more accurate predictions of outbreak. This paper presents a novel approach called diffusion prediction model for prediction of number of coronavirus cases in four countries: India, France, China and Nepal. Diffusion prediction model works on the diffusion process of the human contact. Model considers two forms of spread: when the spread takes time after infecting one person and when the spread is immediate after infecting one person. It makes the proposed model different over other state-of-the art models. It is giving more accurate results than other state-of-the art models. The proposed diffusion prediction model forecasts the number of new cases expected to occur in next 4 weeks. The model has predicted the number of confirmed cases, recovered cases, deaths and active cases. The model can facilitate government to be well prepared for any abrupt rise in this pandemic. The performance is evaluated in terms of accuracy and error rate and compared with the prediction results of support vector machine, logistic regression model and convolution neural network. The results prove the efficiency of the proposed model.

Forecasting major impacts of COVID-19 pandemic on country-driven sectors: challenges, lessons, and future roadmap.

The pandemic caused by the coronavirus disease 2019 (COVID-19) has produced a global health calamity that has a profound impact on the way of perceiving the world and everyday lives. This has appeared as the greatest threat of the time for the entire world in terms of its impact on human mortality rate and many other societal fronts or driving forces whose estimations are yet to be known. Therefore, this study focuses on the most crucial sectors that are severely impacted due to the COVID-19 pandemic, in particular reference to India. Considered based on their direct link to a country's overall economy, these sectors include economic and financial, educational, healthcare, industrial, power and energy, oil market, employment, and environment. Based on available data about the pandemic and the above-mentioned sectors, as well as forecasted data about COVID-19 spreading, four inclusive mathematical models, namely-exponential smoothing, linear regression, Holt, and Winters, are used to analyse the gravity of the impacts due to this COVID-19 outbreak which is also graphically visualized. All the models are tested using data such as COVID-19 infection rate, number of daily cases and deaths, GDP of India, and unemployment. Comparing the obtained results, the best prediction model is presented. This study aims to evaluate the impact of this pandemic on country-driven sectors and recommends some strategies to lessen these impacts on a country's economy.

On the existence and stability of fuzzy CF variable fractional differential equation for COVID-19 epidemic.

In this paper, we convert the recent COVID-19 model with the use of the most influential theories, such as variable fractional calculus and fuzzy theory. We propose the fuzzy variable fractional differential equation for the COVID-19 model in which the variable fractional-order derivative is described using the Caputo-Fabrizio in the Caputo sense. Furthermore, we provide the results on the existence and uniqueness using Lipschitz conditions. Also, discuss the stability analysis of the present new COVID-19 model by employing Hyers-Ulam stability.

A novel authentication protocol to ensure confidentiality among the Internet of Medical Things in covid-19 and future pandemic scenario.

Diagnosing the patients remotely, controlling the medical equipment, and monitoring the quarantined patients are some of the necessary and frequent activities in COVID-19. Internet of Medical Things (IoMT) makes this works easy and feasible. Sharing information from patients and sensors associated with the patients to doctors is always an integral part of IoMT. Unauthorized access to such information may invite adversaries to disturb patients financially and mentally; furthermore, leaks in its confidentiality will lead to dangerous health concerns for patients. While ensuring authentication and confidentiality, We must focus on the constraints of IoMT, such as low energy consumption, deficient memory, and the dynamic nature of devices. Numerous protocols have been proposed for authentication in healthcare systems such as IoMT and telemedicine. However, many of these protocols were neither computationally efficient nor provided confidentiality, anonymity, and resistance against several attacks. In the proposed protocol, we have considered the most common scenario of IoMT and tried to overcome the limitations of existing works. Describing the system module and security analysis proves it is a panacea for COVID-19 and future pandemics.

Intramuscular mRNA BNT162b2 vaccine against SARS-CoV-2 induces neutralizing salivary IgA.

Intramuscularly administered vaccines stimulate robust serum neutralizing antibodies, yet they are often less competent in eliciting sustainable "sterilizing immunity" at the mucosal level. Our study uncovers a strong temporary neutralizing mucosal component of immunity, emanating from intramuscular administration of an mRNA vaccine. We show that saliva of BNT162b2 vaccinees contains temporary IgA targeting the receptor-binding domain (RBD) of severe acute respiratory syndrome coronavirus-2 spike protein and demonstrate that these IgAs mediate neutralization. RBD-targeting IgAs were found to associate with the secretory component, indicating their bona fide transcytotic origin and their polymeric multivalent nature. The mechanistic understanding of the high neutralizing activity provided by mucosal IgA, acting at the first line of defense, will advance vaccination design and surveillance principles and may point to novel treatment approaches and new routes of vaccine administration and boosting.

Covid-19 and Obstructive Sleep Apnea: The Theatricals and Quality-of-Life Impact.

COVID-19 caused by SARS-CoV2 has reached pandemic proportions. The fear of Covid-19 has deterred many to abandon efforts for seeking timely medical help. In this setting, Obstructive sleep apnea (OSA)-like covid/non-covid cohorts have presented. Atypical pathologies can present like OSA and take the clinician unawares. With this series of misfits suffering silently, it would be unwise to underestimate its impact on quality-of-life (QOL). To determine the effect on quality-of-life by pathologies mimicking OSA and assess Covid-19 as a cause for delayed presentation. This was a prospective cross-sectional study. 127(N). Recent onset of symptoms of OSA. Study duration March 2020 to September 2021. Pittsburgh Sleep Quality Index (PSQI) screening done. Study criteria defined. Sleep parameters calculated. Primary surgical intervention given. Non-responders were put on CPAP therapy. QOL assessment done with sf-36 and SAQLI. Fear of Covid-19 scale (FCV-19S) quantified to study cause for temporal delay. Correlations computed. Level of Evidence-Level 3. 97 candidates completed study. Demographic and anthropometric details noted. Mean range was 43.85 ± 11.39 years. Male predominance. Overall AHI-19.73 ± 8.72. Moderate impact on QOL by sf-36/SAQLI. 78n Primary surgical candidates fared well. Polysomnography (PSG) and Continuous positive airway pressure (CPAP) titration/trial characteristics for 19n available. Statistically significant improvement in QOL after treatment completion. Correlations were meaningful. Body Mass Index (BMI) as a single factor was not influential on OSA-mimickers. Fear of Covid-19 significantly impacted emergency medical aid acquisition. OSA mimicking atypical airway pathologies may need emergent treatment not only from a surgical point-of-view but also from the QOL of the patient. On the contrary, these also unmask sub-clinical OSA, especially in patients with low/normal BMI. This category of recent onset OSA, if fortunately picked up at the earliest possible presentation, may hopefully not go through the significant QOL impact suffered by chronic OSA candidates.

Barbaloin: an amazing chemical from the 'wonder plant' with multidimensional pharmacological attributes.

Aloe vera (L.) Burm.f. is nicknamed the 'Miracle plant' or sometimes as the 'Wonder plant'. It is a plant that has been used since ancient times for the innumerable health benefits associated with it. It is one of the important plants that has its use in conventional medicinal treatments. It is a perennial succulent, drought-tolerant member of the family Asphodelaceae. There are scores of properties associated with the plant that help in curing various forms of human ailments. Extracts and gels obtained from plants have been shown to be wonderful healers of different conditions, mainly various skin problems. Also, this plant is popular in the cosmetics industry. The underlying properties of the plant are now mainly associated with the natural phytochemicals present in the plant. Diverse groups of phytoingredients are found in the plant, including various phenolics, amino acids, sugars, vitamins, and different other organic compounds, too. One of the primary ingredients found in the plant is the aloin molecule. It is an anthraquinone derivative and exists as an isomer of Aloin A and Aloin B. Barbaloin belonging to the first group is a glucoside of the aloe-emodin anthrone molecule. Various types of pharmacological properties exhibited by the plant can be attributed to this chemical. Few significant ones are antioxidant, anti-inflammatory, anti-diabetic, anti-cancer, anti-microbial, and anti-viral, along with their different immunity-boosting actions. Recently, molecular coupling studies have also found the role of these molecules as a potential cure against the ongoing COVID-19 disease. This study comprehensively focuses on the numerous pharmacological actions of the primary compound barbaloin obtained from the Aloe vera plant along with the mechanism of action and the potent application of these natural molecules under various conditions.

A COVID-19 X-ray image classification model based on an enhanced convolutional neural network and hill climbing algorithms.

The classification of medical images is significant among researchers and physicians for the early identification and clinical treatment of many disorders. Though, traditional classifiers require more time and effort for feature extraction and reduction from images. To overcome this problem, there is a need for a new deep learning method known as Convolution Neural Network (CNN), which shows the high performance and self-learning capabilities. In this paper,to classify whether a chest X-ray (CXR) image shows pneumonia (Normal) or COVID-19 illness, a test-bed analysis has been carried out between pre-trained CNN models like Visual Geometry Group (VGG-16), VGG-19, Inception version 3 (INV3), Caps Net, DenseNet121, Residual Neural Network with 50 deep layers (ResNet50), Mobile-Net and proposed CNN classifier. It has been observed that, in terms of accuracy, the proposed CNN model appears to be potentially superior to others. Additionally, in order to increase the performance of the CNN classifier, a nature-inspired optimization method known as Hill-Climbing Algorithm based CNN (CNN-HCA) model has been proposed to enhance the CNN model's parameters. The proposed CNN-HCA model performance is tested using a simulation study and contrasted to existing hybridized classifiers like as Particle Swarm Optimization (CNN-PSO) and CNN-Jaya. The proposed CNN-HCA model is compared with peer reviewed works in the same domain. The CXR dataset, which is freely available on the Kaggle repository, was used for all experimental validations. In terms of Receiver Operating Characteristic Curve (ROC), Area Under the ROC Curve (AUC), sensitivity, specificity, F-score, and accuracy, the simulation findings show that the CNN-HCA is possibly superior than existing hybrid approaches. Each method employs a k-fold stratified cross-validation strategy to reduce over-fitting.

Network Analysis Guided Designing of Multi-Targeted Anti-Fungal Agents: Synthesis and Biological Evaluation.

During the ongoing pandemic, there have been increasing reports of invasive fungal disease (IFD), particularly among immunocompromised populations. Candida albicans is one of the most common clinical pathogenic microorganisms which have become a serious health threat to population either infected with Covid-19 or on treatment with immunosuppressant's/broad-range antibiotics. Currently, benzothiazole is a well explored scaffold for anti-fungal activity, especially mercapto substituted benzothiazoles. It is reported that exploring the 2nd position of benzothiazoles yield improved anti-fungal molecules. Therefore, in the current study, lead optimization approach using bioisosteric replacement protocol was followed to improve the anti-fungal activity of an already reported benzothiazole derivative, N-(1,3-benzothiazole-2-yl)-2-(pyridine-3-ylformohydrazido) acetamide. To rationally identify the putative anti-candida targets of this derivative, network analysis was carried out. Complexes of designed compounds and identified putative targets were further analyzed for the docking interactions and their consequent retention after the completion of exhaustive MD simulations. Top seven designed compounds were synthesized and evaluated for in-vitro anti-fungal property against Candida, which indicated that compounds 1.2c and 1.2f possess improved and comparable anti-fungal activity to N-(1,3-benzothiazole-2-yl)-2-(pyridine-3-ylformohydrazido) acetamide and Nystatin, respectively.

Enhanced Framework for COVID-19 Prediction with Computed Tomography Scan Images using Dense Convolutional Neural Network and Novel Loss Function.

Recent studies have shown that computed tomography (CT) scan images can characterize COVID-19 disease in patients. Several deep learning (DL) methods have been proposed for diagnosis in the literature, including convolutional neural networks (CNN). But, with inefficient patient classification models, the number of 'False Negatives' can put lives at risk. The primary objective is to improve the model so that it does not reveal 'Covid' as 'Non-Covid'. This study uses Dense-CNN to categorize patients efficiently. A novel loss function based on cross-entropy has also been used to improve the CNN algorithm's convergence. The proposed model is built and tested on a recently published large dataset. Extensive study and comparison with well-known models reveal the effectiveness of the proposed method over known methods. The proposed model achieved a prediction accuracy of 93.78%, while false-negative is only 6.5%. This approach's significant advantage is accelerating the diagnosis and treatment of COVID-19.

Nitrogen dioxide as proxy indicator of air pollution from fossil fuel burning in New Delhi during lockdown phases of COVID-19 pandemic period: impact on weather as revealed by Sentinel-5 precursor (5p) spectrometer sensor.

There has been a long-lasting impact of the lockdown imposed due to COVID-19 on several fronts. One such front is climate which has seen several implications. The consequences of climate change owing to this lockdown need to be explored taking into consideration various climatic indicators. Further impact on a local and global level would help the policymakers in drafting effective rules for handling challenges of climate change. For in-depth understanding, a temporal study is being conducted in a phased manner in the New Delhi region taking NO2 concentration and utilizing statistical methods to elaborate the quality of air during the lockdown and compared with a pre-lockdown period. In situ mean values of the NO2 concentration were taken for four different dates, viz. 4th February, 4th March, 4th April, and 25th April 2020. These concentrations were then compared with the Sentinel (5p) data across 36 locations in New Delhi which are found to be promising. The results indicated that the air quality has been improved maximum in Eastern Delhi and the NO2 concentrations were reduced by one-fourth than the pre-lockdown period, and thus, reduced activities due to lockdown have had a significant impact. The result also indicates the preciseness of Sentinel (5p) for NO2 concentrations.

CriSNPr, a single interface for the curated and de novo design of gRNAs for CRISPR diagnostics using diverse Cas systems.

CRISPR-based diagnostics (CRISPRDx) have improved clinical decision-making, especially during the COVID-19 pandemic, by detecting nucleic acids and identifying variants. This has been accelerated by the discovery of new and engineered CRISPR effectors, which have expanded the portfolio of diagnostic applications to include a broad range of pathogenic and non-pathogenic conditions. However, each diagnostic CRISPR pipeline necessitates customized detection schemes based on the fundamental principles of the Cas protein used, its guide RNA (gRNA) design parameters, and the assay readout. This is especially relevant for variant detection, a low-cost alternative to sequencing-based approaches for which no in silico pipeline for the ready-to-use design of CRISPRDx currently exists. In this manuscript, we fill this lacuna using a unified web server, CriSNPr (CRISPR-based SNP recognition), which provides the user with the opportunity to de novo design gRNAs based on six CRISPRDx proteins of choice (Fn/enFnCas9, LwCas13a, LbCas12a, AaCas12b, and Cas14a) and query for ready-to-use oligonucleotide sequences for validation on relevant samples. Furthermore, we provide a database of curated pre-designed gRNAs as well as target/off-target for all human and SARS-CoV-2 variants reported thus far. CriSNPr has been validated on multiple Cas proteins, demonstrating its broad and immediate applicability across multiple detection platforms. CriSNPr can be found at http://crisnpr.igib.res.in/.

A comprehensive review on the production of alternative fuel through medical plastic waste

This paper aims to critically review the production of alternative fuels through medical plastic waste. In the recent past, medical plastic waste has been disposed of and incinerated in the dumping yards, which is the main cause of the threat of infection and environmental hazards.Adopting proper waste management and the appropriate technology like the 5R’s (refuse, reduce, reuse, repurpose, and recycle) may significantly improve the ecosystem. Moreover, the 5R’s is a comprehensive approach that can be applied, either awareness of stakeholders or enforcement mandate and regulation by the government. The current review suggested the possible route for converting medical-plastic waste into drop-in fuel and value-added products to minimize the waste through suitable technology. In this, the pyrolysis technique plays an important role which is more ecologically friendly, effective and produces minimal pollutants. It has been observed that using COVID medical waste management (CMWM) technology, 70–80 % plastic pyrolysis oil (PPO), 10–15% bio-char, and gaseous fuel can be extracted. As per the ASTM, the extracted PPO is a potential feedstock for the CI engine fuel. This review work provides a suitable solution for CMWM and improves the quality of medical infrastructure for sanitation in a sustainable mode.

Omicron BA.2 lineage predominance in severe acute respiratory syndrome coronavirus 2 positive cases during the third wave in North India.

Background: Recent studies on severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) reveal that Omicron variant BA.1 and sub-lineages have revived the concern over resistance to antiviral drugs and vaccine-induced immunity. The present study aims to analyze the clinical profile and genome characterization of the SARS-CoV-2 variant in eastern Uttar Pradesh (UP), North India. Methods: Whole-genome sequencing (WGS) was conducted for 146 SARS-CoV-2 samples obtained from individuals who tested coronavirus disease 2019 (COVID-19) positive between the period of 1 January 2022 and 24 February 2022, from three districts of eastern UP. The details regarding clinical and hospitalized status were captured through telephonic interviews after obtaining verbal informed consent. A maximum-likelihood phylogenetic tree was created for evolutionary analysis using MEGA7. Results: The mean age of study participants was 33.9 ± 13.1 years, with 73.5% accounting for male patients. Of the 98 cases contacted by telephone, 30 (30.6%) had a travel history (domestic/international), 16 (16.3%) reported having been infected with COVID-19 in past, 79 (80.6%) had symptoms, and seven had at least one comorbidity. Most of the sequences belonged to the Omicron variant, with BA.1 (6.2%), BA.1.1 (2.7%), BA.1.1.1 (0.7%), BA.1.1.7 (5.5%), BA.1.17.2 (0.7%), BA.1.18 (0.7%), BA.2 (30.8%), BA.2.10 (50.7%), BA.2.12 (0.7%), and B.1.617.2 (1.3%) lineages. BA.1 and BA.1.1 strains possess signature spike mutations S:A67V, S:T95I, S:R346K, S:S371L, S:G446S, S:G496S, S:T547K, S:N856K, and S:L981F, and BA.2 contains S:V213G, S:T376A, and S:D405N. Notably, ins214EPE (S1- N-Terminal domain) mutation was found in a significant number of Omicron BA.1 and sub-lineages. The overall Omicron BA.2 lineage was observed in 79.5% of women and 83.2% of men. Conclusion: The current study showed a predominance of the Omicron BA.2 variant outcompeting the BA.1 over a period in eastern UP. Most of the cases had a breakthrough infection following the recommended two doses of vaccine with four in five cases being symptomatic. There is a need to further explore the immune evasion properties of the Omicron variant.

Effectiveness of non-invasive respiratory support strategies in patients with COVID-19: A systematic review and meta analysis.

Background: BackgroundThe effectiveness of non-invasive respiratory strategies, namely CPAP and HFNO, in reducing the risk of mortality and tracheal intubation in patients with severe COVID-19 is not well established. Methods: A thorough literature search was conducted across 3 electronic databases (Medline, EMBASE and Cochrane Central) from inception through July 2022. Randomized controlled trials (RCTs) and observational studies assessing the impact of CPAP or HFNO on clinical outcomes in patients infected with COVID-19 were considered for inclusion. End-points included all-cause mortality and risk of tracheal intubation. Evaluations were reported as risk ratios (RRs) with 95% confidence intervals (CI) and analysis was performed using a random effects model. I2 index was used to assess heterogeneity. Results: From the 1041 articles retrieved from initial search, 7 potentially relevant studies (n = 2831 patients) were included in the final analysis. Compared to conventional oxygen therapy, non-invasive respiratory strategies reduced the risk of tracheal intubation (RR = 0.84, [95% CI 0.72, 0.98]; p = 0.02, I2 = 43%) and all-cause mortality (RR = 0.83, [95% CI 0.71-0.97]; p = 0.02, I2 = 0%) in patients infected with COVID-19 However, reduction in length of hospital stay was not significant between the non-invasive respiratory group and conventional oxygen therapy (MD = -0.60, [95% CI -2.17 - 0.98]; p = 0.46, I2 = 26%). Conclusion: This meta-analysis supports the application of non-invasive respiratory strategy is feasible as it can delay the start of tracheal intubation and reduce mortality rates among patients infected with COVID-19.

Prevalence and Quality of Endodontic Treatment in Patients with Cardiovascular Disease and Associated Risk Factors.

This study aimed to determine the prevalence and quality of endodontic treatment, by radiographically assessing the periapical periodontitis and endodontic treatment status in patients with cardiovascular disease (CVD) and cardiovascular risk (CVR) factors. Patients who visited the Out Patient Department of Institute of Dental Sciences and Department of Cardiology, Institute of Medical Sciences and SUM Hospital, Siksha 'O' Anusandhan University, Bhubaneswar, from August 2021 to February 2022, for a check-up or dental problem were considered as participants in this study. After obtaining informed consent, the participants were enrolled on the Oral Infections and Vascular Disease Epidemiology Study (INVEST) IDS, BHUBANESWAR. After testing negative for COVID-19, patients' demographic details, such as age and gender were recorded, followed by a panoramic radiographic examination (OPG). A total sample of 408 patients were divided into three groups: Group 1/control (without any cardiovascular manifestation) consisting of 102 samples, group 2 of 222 CVR patients, and group 3 of 84 CVD cases. The CVR and CVD groups had a preponderance of elderly age groups between 60 to 70 years, with a significantly higher proportion of males. Co-morbidities such as diabetes mellitus, hypertension, and dyslipidemia were significantly associated with the CVR and CVD groups. From OPG interpretation, it was observed that the periapical radiolucency was greater in the CVR and CVD groups than in the control group (p = 0.009). The prevalence of endodontically treated teeth was higher in CVR and CVD than in the control group (p = 0.028). A high prevalence of dental caries, about 70%, was reported in all three groups (p = 0.356). The presence of dental restoration among all the groups was low (p = 0.079). The proportion of periodontal bone loss in the control group was significantly lower than CVR and CVD (p = 0.000). There was a strong association between periapical radiolucency, endodontically treated teeth, and periodontal bone loss in CVR and CVD patients. Notably, the associations reported herein do not reflect a cause-effect relationship; however, individuals with endodontic pathologies may accumulate additional risk factors predisposing them to hypertension or other CVDs. The results emphasize that eliminating local infections may decrease the systemic infection burden.

Capturing nucleic acid variants with precision using CRISPR diagnostics.

CRISPR/Cas systems have the ability to precisely target nucleotide sequences and enable their rapid identification and modification. While nucleotide modification has enabled the therapeutic correction of diseases, the process of identifying the target DNA or RNA has greatly expanded the field of molecular diagnostics in recent times. CRISPR-based DNA/RNA detection through programmable nucleic acid binding or cleavage has been demonstrated for a large number of pathogenic and non-pathogenic targets. Combining CRISPR detection with nucleic acid amplification and a terminal signal readout step allowed the development of numerous rapid and robust nucleic acid platforms. Wherever the Cas effector can faithfully distinguish nucleobase variants in the target, the platform can also be extended for sequencing-free rapid variant detection. Some initial PAM disruption-based SNV detection reports were limited to finding or integrating mutated/mismatched nucleotides within the PAM sequences. In this review, we try to summarize the developments made in CRISPR diagnostics (CRISPRDx) to date emphasizing CRISPR-based SNV detection. We also discuss the applications where such diagnostic modalities can be put to use, covering various fields of clinical research, SNV screens, disease genotyping, primary surveillance during microbial infections, agriculture, food safety, and industrial biotechnology. The ease of rapid design and implementation of such multiplexable assays can potentially expand the applications of CRISPRDx in the domain of affinity-based target sequencing, with immense possibilities for low-cost, quick, and widespread usage. In the end, in combination with proximity assays and a suicidal gene approach, CRISPR-based in vivo SNV detection and cancer cell targeting can be formulated as personalized gene therapy.

A COVID-19 X-ray image classification model based on an enhanced convolutional neural network and hill climbing algorithms

The classification of medical images is significant among researchers and physicians for the early identification and clinical treatment of many disorders. Though, traditional classifiers require more time and effort for feature extraction and reduction from images. To overcome this problem, there is a need for a new deep learning method known as Convolution Neural Network (CNN), which shows the high performance and self-learning capabilities. In this paper,to classify whether a chest X-ray (CXR) image shows pneumonia (Normal) or COVID-19 illness, a test-bed analysis has been carried out between pre-trained CNN models like Visual Geometry Group (VGG-16), VGG-19, Inception version 3 (INV3), Caps Net, DenseNet121, Residual Neural Network with 50 deep layers (ResNet50), Mobile-Net and proposed CNN classifier. It has been observed that, in terms of accuracy, the proposed CNN model appears to be potentially superior to others. Additionally, in order to increase the performance of the CNN classifier, a nature-inspired optimization method known as Hill-Climbing Algorithm based CNN (CNN-HCA) model has been proposed to enhance the CNN model’s parameters. The proposed CNN-HCA model performance is tested using a simulation study and contrasted to existing hybridized classifiers like as Particle Swarm Optimization (CNN-PSO) and CNN-Jaya. The proposed CNN-HCA model is compared with peer reviewed works in the same domain. The CXR dataset, which is freely available on the Kaggle repository, was used for all experimental validations. In terms of Receiver Operating Characteristic Curve (ROC), Area Under the ROC Curve (AUC), sensitivity, specificity, F-score, and accuracy, the simulation findings show that the CNN-HCA is possibly superior than existing hybrid approaches. Each method employs a k-fold stratified cross-validation strategy to reduce over-fitting.

Ensemble multimodal deep learning for early diagnosis and accurate classification of COVID-19.

Over the past few years, the awful COVID-19 pandemic effect has become a lethal sickness. The processing of the gathered samples requires extra time due to the use of medical diagnostic equipment, methodologies, and clinical testing procedures for the early diagnosis of infected individuals. An innovative multimodal paradigm for the early diagnosis and precise categorization of COVID-19 is put up as a solution to this issue. To extract distinguishing features from the prepared chest X-ray picture and cough (audio) database, chest X-ray-based and cough-based model are used here. Other public chest X-ray image datasets, and the Coswara cough (audio) dataset containing 92 COVID-19 positive, and 1079 healthy subjects (people) using the deep Uniform-Net, and Convolutional Neural Network (CNN). The weighted sum-rule fusion method and ensemble deep learning algorithms are utilized to further combine the extracted features. For the early diagnosis of patients, the framework offers an accuracy of 98.67%.