Explore the vast range of titles available.

The increasing integration of the Internet of Things (IoT) in healthcare has led to massive, high-dimensional data streams, demanding advanced, adaptive learning models for timely and accurate clinical predictions, especially in sensitive domains such as palliative care. Existing models often suffer from high computational overhead, sensitivity to learning rate variations, and difficulties in handling non-stationary data, which impedes their ability to deliver accurate and prompt predictions in high-risk medical scenarios. To address these limitations, this study proposes a Hybrid Metaheuristic-Driven Deep Neural Architectures (HMDNA) that combines a Deep Neural Network (DNN) with Cuckoo Search Optimization (CSO) for sepsis detection and prognosis. The methodology follows a structured pipeline encompassing data preprocessing, model training, and optimization. Time-series ICU data were preprocessed using k-NN imputation and min–max scaling, followed by DNN training with CSO-based optimization applied at initialization, mid-training, and fine-tuning stages. Implemented using TensorFlow and trained on an NVIDIA Tesla V100 GPU, the model achieved an accuracy of 92.7%, precision of 91.8%, recall of 90.3%, and F1 score of 91.4%. These results significantly outperform baseline models including traditional DNN (85.3% accuracy), DNN + GA (88.5%), DNN + PSO (89.2%), and DNN + ACO (90.1%). The proposed model demonstrated faster convergence, better generalization, and robustness to real-time variability in healthcare data. By combining the strengths of deep learning and metaheuristic optimization, this approach ensures reliable performance in dynamic and unpredictable clinical environments. The study highlights the potential of adaptive, hybrid AI models in enhancing healthcare decision-making, particularly in critical care scenarios where prediction accuracy and model responsiveness are vital for improving patient outcomes.

Background: Early hospital presentation is critical in the management of acute ischemic stroke. The effectiveness of stroke treatment is highly dependent on the amount of time lapsed between onset of symptoms and treatment. This study was aimed to identify the factors associated with prehospital delay in patients with acute stroke. Material and Methods: A cross-sectional descriptive study was conducted in Sri Ramachandra University Hospital, India. A total of 210 patients hospitalized in the stroke unit were included. Patients' data were obtained by interviewing the patient and/or accompanying family member and by reviewing their medical records using a standard questionnaire. Associations were determined between prehospital delay (≥4.5 h) and variables of interest by using univariate and multivariate logistic regression analyses. Results: The prehospital delay was observed in 154 patients (73.3%) and the median prehospital delay was 11.30 h. The following are the factors significantly (P < 0.05) attributed for the delay in presenting to the hospital: contextual factors like using public transport (bus), taxi, time of onset of symptoms, 7 pm-3 am; family history of stroke, perceived cognitive and behavioral factors like, wishing or praying for the symptoms to subside on its own, hesitation to travel due to long distance, delay in arranging transport, and arranging money for admission and wasting time by shopping for general practitioners, nursing homes, and hospitals. The presence of stroke symptom, headache, significantly decreased the prehospital delay. Conclusions: Prehospital delay is high in South India and influenced by clinical, contextual, and cognitive/behavioral factors.

Digital advancements have made cloud computing and IoT essential for innovative environments such as healthcare and industry. Cloud platforms offer scalable compute and storage capabilities, whereas IoT devices generate real‐time data. However, there are significant challenges faced while integrating the IoT with cloud to achieve robust, scalable, and secure access control. Traditional centralized models, such as static rule‐based mechanisms and public key infrastructure (PKI), are prone to single points of failure and suffer from limited scalability and poor adaptability. To address these issues, this paper proposes a decentralized access control architecture that combines blockchain with a hybrid bidirectional graph convolutional network (Bi‐GCN). The framework integrates ciphertext policy‐attribute based encryption (CP‐ABE) with trusted platform module (TPM)–based pseudonymous identities and the blockchain smart contracts for fine‐ and hardware‐assisted access control. A generative adversarial network (GAN)‐assisted prevalidation layer filters sybil, tampering, and spoofing attempts before block inclusion, enhancing integrity and reducing overhead. Bi‐GCN supports real‐time anomaly detection, trust adaptation, and behavior profiling, while smart contracts enforce adaptive role‐attribute policies. Experimental results show that the proposed model outperforms existing methods across key metrics, including 0.97 accuracy, 0.98 F‐measure, and minimal security overhead of 0.7%. Although it introduces slight latency due to advanced processing, the benefits of secure and intelligent access management outweigh the trade‐off. The integration of blockchain ensures decentralized and immutable policy enforcement, while Bi‐GCN facilitates self‐adaptive security, making the architecture suitable for dynamic IoT–cloud ecosystems.

Background Early diagnosis of osteoporosis can potentially decrease the risk of fractures and improve the quality of life. Detection of thin inferior cortices of the mandible on dental panoramic radiographs could be useful for identifying postmenopausal women with low bone mineral density (BMD) or osteoporosis. The aim of our study was to assess the diagnostic efficacy of using kernel-based support vector machine (SVM) learning regarding the cortical width of the mandible on dental panoramic radiographs to identify postmenopausal women with low BMD. Methods We employed our newly adopted SVM method for continuous measurement of the cortical width of the mandible on dental panoramic radiographs to identify women with low BMD or osteoporosis. The original X-ray image was enhanced, cortical boundaries were determined, distances among the upper and lower boundaries were evaluated and discrimination was performed by a radial basis function. We evaluated the diagnostic efficacy of this newly developed method for identifying women with low BMD (BMD T-score of -1.0 or less) at the lumbar spine and femoral neck in 100 postmenopausal women (≥50 years old) with no previous diagnosis of osteoporosis. Sixty women were used for system training, and 40 were used in testing. Results The sensitivity and specificity using RBF kernel-SVM method for identifying women with low BMD were 90.9% [95% confidence interval (CI), 85.3-96.5] and 83.8% (95% CI, 76.6-91.0), respectively at the lumbar spine and 90.0% (95% CI, 84.1-95.9) and 69.1% (95% CI, 60.1-78.6), respectively at the femoral neck. The sensitivity and specificity for identifying women with low BMD at either the lumbar spine or femoral neck were 90.6% (95% CI, 92.0-100) and 80.9% (95% CI, 71.0-86.9), respectively. Conclusion Our results suggest that the newly developed system with the SVM method would be useful for identifying postmenopausal women with low skeletal BMD.

Parkinson’s disease (PD) is a progressive neurodegenerative disorder characterized by motor and motor impairments. However, the conventional diagnostic approaches often struggle to identify subtle abnormal movements at its early stages. To address this issue, a novel video-based PAVE-GAN framework is proposed for PD detection. The patient video sequences are processed using Multi-scale Retinex (MSR) algorithm to improve the visual quality and Improved Sobel edge detector (ISED) is used to extract precise body contours. The Generative adversarial network (GAN) structure is designed with Pose-Activity sampling modules for estimating different body poses with fine details. The estimated feature subsets are processed in the Deep belief network (DBN) to classify the subjects as PD or normal. The proposed PAVE-GAN is evaluated with specific network metrices such as precision, recall, specificity, accuracy, Matthews Correlation Coefficient and F1 score. The experimental results reveal that the proposed PAVE-GAN attains the accuracy of 98.23% for PD detection based on clinical video datasets. Moreover, the proposed PAVE-GAN framework increases an accuracy range by 12.74%, 6.51%, 3.42% and 2.69% better than 3D-CAM model, Random Forest, DNN architecture and Hybrid machine learning classifiers respectively.

When watching pictures or videos, the Human Visual System has the potential to concentrate on important locations. Saliency detection is a tool for detecting the abnormality and randomness of images or videos by replicating the human visual system. Video saliency detection has received a lot of attention in recent decades, but due to challenging temporal abstraction and fusion for spatial saliency, computational modelling of spatial perception for video sequences is still limited.Unlike methods for detection of salient objects in still images, one of the most difficult aspects of video saliency detection is figuring out how to isolate and integrate spatial and temporal features.Saliency detection, which is basically a tool to recognize areas in images and videos that catch the attention of the human visual system, may benefit multimedia applications such as video or image retrieval, copy detection, and so on. As the two crucial steps in trajectory-based video classification methods are feature point identification and local feature extraction. We suggest a new spatio-temporal saliency detection using an enhanced 3D Conventional neural network with an inclusion of histogram for optical and orient gradient in this paper.

As is eminent, lung cancer is one of the death frightening syndromes among people in present cases. The earlier diagnosis and treatment of lung cancer can increase the endurance rate of the affected people. But, the structure of the cancer cell makes the diagnosis process more challenging, in which the most of the cells are superimposed. By adopting the efficient image processing techniques, the diagnosis process can be made effective, earlier and accurate, where the time aspect is extremely decisive. With those considerations, the main objective of this work is to propose a region based Fuzzy C-Means Clustering (FCM) technique for segmenting the lung cancer region and the Support Vector Machine (SVM) based classification for diagnosing the cancer stage, which helps in clinical practice in significant way to increase the morality rate. Moreover, the proposed ECM-CSD (Efficient Classification Model for Cancer Stage Diagnosis) uses Computed Tomography (CT) lung images for processing, since it poses higher imaging sensitivity, resolution with good isotopic acquisition in lung nodule identification. With those images, the pre-processing has been made with Gaussian Filter for smoothing and Gabor Filter for enhancement. Following, based on the extracted image features, the effective segmentation of lung nodules is performed using the FCM based clustering. And, the stages of cancer are identified based on the SVM classification technique. Further, the model is analyzed with MATLAB tool by incorporating the LIDC-IDRI lung CT images clinical dataset. The comparative experiments show the efficiency of the proposed model in terms of the performance evaluation factors like increased accuracy and reduced error rate.

In the modern era, breast cancer (BC) is one of the most prevalent diseases affecting the lifespan of women. Single nucleotide polymorphism (SNP) elucidates an enormous proportion of the hazard in women with a solid family history. Different types of human disorders have been analyzed using Machine Learning methods to locate the vital SNP. The identification of an optimal feature set is the primary constraint in the existing methods owing to the ill effects of multidimensionality. Thus, a novel Bio-Inspired Ensemble Feature Selection (BIEFS) technique has been proposed in this paper to identify the most relevant SNP for accurate classification of BC. An initial feature subset is generated from each base feature selector such as Membership Weight Salp Swarm Algorithm (MWSSA), Crossover Horse Herd Optimization (CHHO), and Levy Mutation Manta-Ray Foraging Optimization (LMMRFO). Then the proposed BIEFS technique obtains the optimized weight of each feature subset through the mutation operator. Finally, the Self-Organizing Deep Auto-Encoder (SODAE) is employed for BC classification. A Gene Expression Omnibus (GEO) dataset is used to assess the proposed methodology. Simulation results validate that the proposed methodology attains a maximum accuracy of 98.75% as compared to the conventional techniques.

The cry of a premature infant is an attempt to connect with its mother or others. The newborns are communicated in different ways depending on the reason for their screams. In recent days, the preprocessing, feature extraction, and classification of audio signals require expert attention and a lot of effort. In this paper, a novel deep convolutional recurrent neural network (DCR net) has been proposed to classify the premature infant cry signal into different categories. The acquisition of the cry signal generally requires a lengthy observation period and several activity processes to obtain all the signals of the premature infant. The relevant multi-class frequency features are extracted by using the MFCC (Mel-frequency cepstral coefficient), BFCC (Bark-frequency cepstral coefficient), and LPCC (linear prediction cepstral coefficient) features, which are combined to create a fused feature matrix that is helpful in the classification of pathological crying. Based on these features, the DCR net is used to classify sounds in the premature infant cry. The sound of the target cry signal is classified into five categories: “neh” means hunger, “heh” means discomfort, “eh” means burping, “eair” means cramps, and “owh” means fatigue. The efficiency of the DCR net was estimated with some metrics such as specificity, precision, accuracy, recall, and F1 score. The experimental fallouts disclose that the proposed DCR net attains a better classification accuracy of 97.27% for identifying infant cry signals. The DCR net increases the overall performance range by 8.61%, 11.58%, 0.54%, and 17.03% better than SVM-RBF, MFCC-SVM, optimized deep learning model, and hidden Markov model, respectively.

INTRODUCTION: Medical images still need to be examined by medical personnel, which is a prolonged and vulnerable progression. The dataset used included 4 classes of 6400 training and test MRI images each and was collected from Kaggle such as cognitively normal (CN), Mild Cognitive Impairment stage (MCI), moderate cognitive impairment (Moderate MCI), and Severe stage of cognitive impairment (AD). OBJECTIVES: There was a glaring underrepresentation of the Alzheimer Disease (AD) class. The accuracy and effectiveness of diagnoses can be improved with the use of neural network models. METHODS: In order to establish which CNN-based algorithm performed the multi-class categorization of the AD patient's brain MRI images most accurately. Thus, examine the effectiveness of the popular CNN-based algorithms like Convolutional Neural Network (CNN), Region-based CNN (R-CNN), Fast R-CNN, and Faster R-CNN. RESULTS:  On the confusion matrix, R-CNN performed the best. CONCLUSION: R-CNN is quick and offers a high precision of 98.67% with a low erroneous measure of 0.0133, as shown in the research.