A cross-sectional study of parental perspectives on children about COVID-19 and classification using machine learning models

Frontiers in Public Health, Journal Year: 2025, Volume and Issue: 12

Published: Jan. 15, 2025

This study delves into the parenting cognition perspectives on COVID-19 in children, exploring symptoms, transmission modes, and protective measures. It aims to correlate these with sociodemographic factors employ advanced machine-learning techniques for comprehensive analysis. Data collection involved a semi-structured questionnaire covering parental knowledge attitude transmission, measures, government satisfaction. The analysis utilised Generalised Linear Regression Model (GLM), K-Nearest Neighbours (KNN), Support Vector Machine (SVM), Random Forest (RF), Naive Bayes (NB), AdaBoost (AB). revealed an average score of 18.02 ± 2.9, 43.2 52.9% parents demonstrating excellent good knowledge, respectively. News channels (85%) emerged as primary information source. Commonly reported symptoms included cough (96.47%) fever (95.6%). GLM indicated lower awareness rural areas (β = -0.137, p < 0.001), scores males compared females -0.64, 0.025), correlation between socioeconomic status -0.048, 0.009). SVM classifier achieved highest performance (66.70%) classification tasks. offers valuable insights attitudes towards highlighting symptom recognition, awareness, preventive practices. Correlating underscores need tailored educational initiatives, particularly areas, addressing gender disparities. efficacy analytics, exemplified by classifier, potential informed decision-making public health communication targeted interventions, ultimately empowering safeguard their children's well-being amidst ongoing pandemic.

Language: Английский

---

Progress and trends in neurological disorders research based on deep learning

Computerized Medical Imaging and Graphics, Journal Year: 2024, Volume and Issue: 116, P. 102400 - 102400

Published: May 25, 2024

Language: Английский

---

Intelligent Internet of Medical Things for Depression: Current Advancements, Challenges, and Trends

International Journal of Intelligent Systems, Journal Year: 2025, Volume and Issue: 2025(1)

Published: Jan. 1, 2025

We investigated the fusion of Intelligent Internet Medical Things (IIoMT) with depression management, aiming to autonomously identify, monitor, and offer accurate advice without direct professional intervention. Addressing pivotal questions regarding IIoMT’s role in identification, its correlation stress anxiety, impact machine learning (ML) deep (DL) on depressive disorders, challenges potential prospects integrating management IIoMT, this research offers significant contributions. It integrates artificial intelligence (AI) (IoT) paradigms expand studies, highlighting data science modeling’s practical application for intelligent service delivery real‐world settings, emphasizing benefits within IoT. Furthermore, it outlines an IIoMT architecture gathering, analyzing, preempting employing advanced analytics enhance intelligence. The study also identifies current challenges, future trajectories, solutions domain, contributing scientific understanding management. evaluates 168 closely related articles from various databases, including Web Science (WoS) Google Scholar, after rejection repeated books. shows that there is 48% growth articles, mainly focusing symptoms, detection, classification. Similarly, most being conducted United States America, trend increasing other countries around globe. These results suggest essence automated monitoring, suggestions handling depression.

Language: Английский

---

Medical intelligence for anxiety research: Insights from genetics, hormones, implant science, and smart devices with future strategies

Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery, Journal Year: 2024, Volume and Issue: 14(6)

Published: Aug. 4, 2024

Abstract This comprehensive review article embarks on an extensive exploration of anxiety research, navigating a multifaceted landscape that incorporates various disciplines, such as molecular genetics, hormonal influences, implant science, regenerative engineering, and real‐time cardiac signal analysis, all while harnessing the transformative potential medical intelligence [medical + artificial (AI)]. By addressing fundamental research questions, this study investigated foundations underlying disorders, shedding light intricate interplay genetic factors contributing to etiology progression anxiety. Furthermore, delves into emerging implications biomaterials, defibrillators, state‐of‐the‐art devices for elucidating their roles in diagnosis, treatment, patient management. A pivotal contribution is development AI‐driven model analysis. innovative approach offers promising avenue enhancing precision timeliness diagnosis monitoring. Leveraging machine learning AI techniques enables accurate classification persons with based data, thereby ushering new era personalized data‐driven mental health care. Identifying themes knowledge gaps lays foundation future directions roadmap scholars practitioners navigate field. In conclusion, serves vital resource, consolidating diverse perspectives fostering deeper understanding disorders from biological, technological standpoints, ultimately advancing clinical practice. categorized under: Application Areas > Health Care Science Technology Technologies Classification

Language: Английский

---

An Intelligent COVID-19-Related Arabic Text Detection Framework Based on Transfer Learning Using Context Representation

International Journal of Intelligent Systems, Journal Year: 2024, Volume and Issue: 2024, P. 1 - 15

Published: May 22, 2024

The misleading information during the coronavirus disease 2019 (COVID-19) pandemic’s peak time is very sensitive and harmful in our community. Analyzing detecting COVID-19 on social media are a crucial task. Early detection of helpful minimizes risk psychological security which leads to inconvenience daily life. In this paper, deep ensemble transfer learning framework with an understanding context Arabic text proposed. This inspired spontaneously analyze recognize about COVID-19. ArCOVID-19Vac dataset has been used train test proposed model. A comprehensive experimental study for each scenario performed. For binary classification scenario, records better evaluation results 83.0%, 84.0%, 84.0% terms accuracy, precision, recall, F 1-score, respectively. second (three classes), overall performance recorded accuracy 82.0%, precision 80.0%, recall 1-score last ten classes, best 67.0%, 58.0%, 59.0%, addition, we have applied model get 64.0%, 66.0%, 65.0% show that through provides than all state-of-the-art methods.

Language: Английский

---

A machine learning-based analysis for the effectiveness of online teaching and learning in Pakistan during COVID-19 lockdown

Work, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 15, 2025

Background The COVID-19 pandemic has significantly disrupted daily life and education, prompting institutions to adopt online teaching. Objective This study delves into the effectiveness of these methods during lockdown in Pakistan, employing machine learning techniques for data analysis. Methods A cross-sectional survey was conducted with 300 respondents using a semi-structured questionnaire assess perceptions education. Artificial intelligence analyzed specificity, sensitivity, accuracy, precision collected data. Results Among participants, 42.3% expressed satisfaction learning, while 49.3% preferred Zoom. Convenience noted 72% favoring classes between 8 AM 12 PM. revealed 87.33% felt placement activities were negatively impacted, 85% reported effects on individual growth. Additionally, 90.33% stated that their routines, 84.66% citing adverse physical health. Decision Tree classifier achieved highest accuracy at 86%. Overall, preferences leaned toward traditional in-person teaching despite methods. Conclusions highlights significant challenges transitioning emphasizing disruptions routines overall well-being. Notably, age gender did not influence growth or Finally, collaborative efforts among educators, policymakers, stakeholders are crucial ensuring equitable access quality education future crises.

Language: Английский

---

Internet of Things in Healthcare Research: Trends, Innovations, Security Considerations, Challenges and Future Strategy

International Journal of Intelligent Systems, Journal Year: 2025, Volume and Issue: 2025(1)

Published: Jan. 1, 2025

The Internet of Things (IoT) has become a transformative force across various sectors, including healthcare, offering new opportunities for automation and enhanced service delivery. evolving architecture the IoT presents significant challenges in establishing comprehensive cyber‐physical framework. This paper reviews recent advancements IoT‐driven healthcare automation, focussing on integrating technologies such as cloud computing, augmented reality wearable devices. work examines network architectures platforms that support applications while addressing critical security privacy issues, specific threat models, attack classifications prerequisites relevant to sector. study highlights how emerging like distributed intelligence, big data analytics devices are incorporated into improve patient care streamline medical operations. findings reveal potential transform practices, particularly in‐patient monitoring, clinical decision‐making. However, concerns continue be substantial barrier. also explores implications global ehealth strategies their influence sustainable economic community growth. It proposes an innovative cooperative model mitigate risks IoT‐enabled systems. Finally, it identifies key unresolved future research IoT‐based healthcare.

Language: Английский

---

Progress and research trends in lumpy skin disease based on the scientometric assessment – a review

Annals of Animal Science, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 7, 2024

Abstract Background Lumpy skin disease (LSD) has been a significant concern in veterinary medicine since its discovery. Despite decades of research, understanding the full spectrum this remains challenge. To address gap, comprehensive analysis existing body knowledge on LSD is essential. Bibliometric offers systematic approach towards mapping research landscape, identifying key contributors, and uncovering emerging trends research. Objective This study aims to conduct thorough bibliometric spanning from 1947 till present date order map domain LSD. The objective gain insights into global trends, identify influential explore collaboration networks, predict future outlook Method Data extracted Scopus database was used perform analysis. 341 relevant documents were selected for indicators, including publication numbers, citation counts, h-index, utilized assess contributions nations, organizations, authors, source titles. Additionally, cooperation networks between countries, authors visualized using VOSviewer tool. Results revealed increase output LSD, with notable growth rate 19.26%. Since discovery Zambia 1929, grown steadily, an average annual 5.21%. University Pretoria Federal Centre Animal Health emerged as most active institutions organizations Journal Virology identified cited journal, reflecting impact field, strong international observed United Kingdom South Africa. Conclusion provides valuable landscape highlighting networks. By reviewing enhances our serves foundation endeavours. findings will aid researchers navigating vast literature ultimately contributing advancements management strategies.

Language: Английский

---

Evaluating CNN Architectures and Hyperparameter Tuning for Enhanced Lung Cancer Detection Using Transfer Learning

Journal of Electrical and Computer Engineering, Journal Year: 2024, Volume and Issue: 2024(1)

Published: Jan. 1, 2024

Accurate lung cancer detection is vital for timely diagnosis and treatment. This study evaluates the performance of six convolutional neural network (CNN) architectures, ResNet‐50, VGG‐16, ResNet‐101, VGG‐19, DenseNet‐201, EfficientNet‐B4, using LIDC‐IDRI dataset. Models were assessed both in their base forms with transfer learning. The dataset consisted 460 × 3 pixel images categorized into squamous cell carcinoma (SCC), normal benign, large (LCC), adenocarcinoma (ADC). Performance metrics computed, including accuracy (99.47% custom CNN), precision (99.50%), recall (98.37%), AUC (99.98%), F1‐score (98.98%) during training. However, overfitting was observed validation phases. Transfer learning models showed better generalization, DenseNet‐201 achieving a top 96.88% EfficientNet‐B4 96.53%. Hyperparameter tuning improved models’ generalization capabilities, maintaining high while reducing overfitting. highlights effectiveness learning, particularly enhancing automated systems. Future work will focus on expanding datasets exploring additional augmentation techniques to further refine model clinical settings.

Language: Английский

---

A comprehensive review of neurotransmitter modulation via artificial intelligence: A new frontier in personalized neurobiochemistry

Computers in Biology and Medicine, Journal Year: 2025, Volume and Issue: 189, P. 109984 - 109984

Published: March 14, 2025

Language: Английский

---