Search

Cardiovascular disease (CVD) believes to be a major cause of transience and indisposition worldwide. Early diagnosis and timely intervention are critical in preventing the progression of CVD and improving patient outcomes. Machine learning (ML) algorithms have emerged as powerful tools in CVD recognition, with the potential to assist physicians in making accurate and efficient diagnoses. This research paper explores the combination of multiple ML algorithms for CVD recognition, utilizing diverse datasets such as the Cleveland, Hungarian, Switzerland, statlog, and VA Long Beach datasets. Additionally, a CVD dataset comprising 12 attributes and 70,000 records is employed, demonstrating improved results through the proposed and trained model compared to previous prediction techniques for CVD. The performance of various ML techniques, including support vector machines (SVM), naive Bayes (NB), K‐nearest neighbour (KNN), random forest (RF), and logistic regression (LR), is evaluated and compared. The impact of feature selection and feature scaling on the models' performance is also examined. An ensemble bagging technique is applied which is being embedded with other classifiers. LR classifier embedded with bagging techniques proved to be our proposed model. The findings reveal that the proposed Hybrid Linear Regression Bagging Model (HLRBM) outperforms other models. Furthermore, the study highlights the significance of data preprocessing techniques, such as data normalization and class balancing, which significantly enhance the performance of all models. To this end, standard scalar and synthetic minority over‐sampling technique (SMOTE) are employed. The study emphasizes the importance of selecting an appropriate ensemble technique in conjunction with various ML algorithms and preprocessing methods for CVD prediction. Overall, the research provides valuable insights into the potential of ML in improving CVD risk assessment. [ABSTRACT FROM AUTHOR]

Precipitation plays a critical role in the hydrological cycle and significantly influences the biodiversity of the Earth's ecosystems. It also regulates socioeconomic systems by impacting agricultural production and water resources. Analyzing climate-driven changes in precipitation patterns is essential for understanding the hydrological cycle's response to global warming. This study analyzed the projections of five general circulation models (GCMs) from the sixth phase of the Coupled Model Intercomparison Project (CMIP6) to evaluate variations in the seasonal and annual patterns of future precipitation over the northern highlands of Pakistan (NHP). The analysis focused on precipitation variations projected for the near future (2021–2050), in comparison to the historical climate (1985–2014), utilizing two combined scenarios from the Shared Socioeconomic Pathways and the Representative Concentration Pathways (SSP2-4.5 and SSP5-8.5). This study employed the multi-model ensemble (MME) approach, which demonstrated notable seasonal and annual variations in precipitation across the NHP. The average annual precipitation is expected to decrease in both scenarios, with SSP2-4.5 expecting a reduction of −21.42% and SSP5-8.5 expecting a decrease of −22.43%, compared to the historical average precipitation. In both scenarios, the seasonal precipitation patterns are similar. However, the changes are more noticeable in the spring and summer. Both SSPs predict a 15% decrease in summer precipitation, while SSP2-4.5 and SSP5-8.5 predict a 5% and 4% decrease in spring precipitation, respectively. These changes can result in more frequent and intense periods of drought, which might adversely impact agriculture, human health, the environment, hydropower generation, and the surrounding ecosystem. This study provides important insights into projected seasonal and annual precipitation changes over the NHP, which is particularly susceptible to the effects of climate change. Thus, it is crucial to understand these predicted changes in precipitation in order to develop strategies for adapting to the climate, assuring water security, and promoting sustainable agricultural practices in this area. [ABSTRACT FROM AUTHOR]

In video surveillance, anomaly detection requires training machine learning models on spatio-temporal video sequences. However, sometimes the video-only data is not sufficient to accurately detect all the abnormal activities. Therefore, we propose a novel audio-visual spatiotemporal autoencoder specifically designed to detect anomalies for video surveillance by utilizing audio data along with video data. This paper presents a competitive approach to a multi-modal recurrent neural network for anomaly detection that combines separate spatial and temporal autoencoders to leverage both spatial and temporal features in audio-visual data. The proposed model is trained to produce low reconstruction error for normal data and high error for abnormal data, effectively distinguishing between the two and assigning an anomaly score. Training is conducted on normal datasets, while testing is performed on both normal and anomalous datasets. The anomaly scores from the models are combined using a late fusion technique, and a deep dense layer model is trained to produce decisive scores indicating whether a sequence is normal or anomalous. The model's performance is evaluated on the University of California, San Diego Pedestrian 2 (UCSD PED 2), University of Minnesota (UMN), and Tampere University of Technology (TUT) Rare Sound Events datasets using six evaluation metrics. It is compared with state-of-the-art methods depicting a high Area Under Curve (AUC) and a low Equal Error Rate (EER), achieving an (AUC) of 93.1 and an (EER) of 8.1 for the (UCSD) dataset, and an (AUC) of 94.9 and an (EER) of 5.9 for the UMN dataset. The evaluations demonstrate that the joint results from the combined audio-visual model outperform those from separate models, highlighting the competitive advantage of the proposed multi-modal approach. [ABSTRACT FROM AUTHOR]

Fog's basic distributed nature and ability to process data in transit—that is, to make decisions in real time—make it a good fit for scenarios involving several distributed devices that need to communicate, provide real‐time data analysis, and carry out storage functions. The majority of fog computing applications are driven by the user's demands and/or their desire for functioning services, either neglecting or giving security considerations second attention. Fog computing security issues have not received enough attention. Fog computing could be exploitable due to the security difficulties associated with cloud computing. Due to its flexibility to function near the end user and independence from a centralized design, fog computing provides the dependability required by time‐sensitive smart healthcare systems. There is a need for enhanced security and privacy solutions for fog computing, where trust is essential, due to the importance of healthcare data. This research aims to develop a context‐based adaptive trust solution for the smart healthcare environment utilizing Bayesian approaches and similarity measures against bad mouthing and ballot stuffing, while context‐dependent trust solutions for fogs remain an unexplored area of study. The proposed trust model has been simulated in Contiki‐Cooja to evaluate our findings. In contrast to static weighting, adaptive weights are provided to direct and indirect trust using entropy values that ensure the least degree of trust bias, and context similarity calculations eliminate recommender nodes with malicious intent by leveraging server, colleague, and service similarities. The proposed model protects smart healthcare systems from attacks using similarity metrics, incorporates context, and also uses adaptive weighting for trust calculation. By eliminating trust bias and also detecting attacks, this solution enhances the trust calculation by 10% as compared to the previous solution. This paradigm is efficient due to its small trust computation overhead and linear complexity O(n). [ABSTRACT FROM AUTHOR]

Introduction: Nicotine is the principal alkaloid contained in tobacco and is produced by plants of nightshade family. Nicotine has relatively high toxicity with varied effects on our body. The liver of albino rats resembles human liver both microscopically as well as microscopically. Aims and objectives: The aim of study was to study gross and histopathological changes induced by administration of graded doses of nicotine hydrogen tartrate in albino rats over a period. Material & methods: A total of 36 male albino rats were included in our study and after a period of acclimatization, were divided in to three groups of 12 rats each with one group serving as control while as other two groups received nicotine in concentration of 5mg/10ml and 7.5mg/10ml.The rats were sacrificed later to study for changes in liver anatomy. Results and observation: The most common changes were progressive decrease in weight of albino rats and pentad of microscopic changes including central venous congestion, portal venous congestion, sinusoidal congestion, fatty changes of hepatocytes and inflammation of portal triads. Conclusion: The findings of our study clearly revealed that changes induced in microanatomy of liver in male albino rats were directly related with dosage and duration of nicotine administration and considering the similarity between human liver and liver of male albino rats, the therapeutic administration of nicotine in human population should be rigorously studied by more experimental studies. [ABSTRACT FROM AUTHOR]

The objective of this study is to examine the use of explainable artificial intelligence (XAI) for gathering and analyzing health-related data in medical services applications, particularly in predicting outcomes in mental health care. Artificial Intelligence (Al) is increasingly utilized in medical services and wearable technologies, such as Fitbits. Strategies in the field of explainable Al (XAI) aim to clarify the predictions made by Al systems, enhancing their application in health-related contexts. Data was collected from 970 individuals, incorporating clinical and sociodemographic information. The analysis focused on factors such as self-reported motivation, the type of reference (self vs. healthcare provider), and the Work Productivity and Activity Impairment Questionnaire. Additionally, pre-treatment scores from the Patient Health Questionnaire-9 and General Anxiety Disorder Screener-7 were evaluated. The study identified that self-reported motivation and the specified reference type significantly contributed to predictive outcomes. The irregular forest model achieved an accuracy of 0.71 for the test set, with a base rate of 0.67, an AUC of 0.60, and a p-value of 0.001. Adjusted accuracy was noted at 0.60, indicating a significant ability to predict reductions in anxiety and depressive symptoms. To improve the personalization and effectiveness of mental health care, it is essential to advance predictive models that accurately evaluate individual responses to therapeutic interventions. [ABSTRACT FROM AUTHOR]