Heart disease is one of the most critical human diseases in world and affects life very badly. In heart disease, unable to push required amount blood other parts body. Accurate on time diagnosis important for failure prevention treatment. The through traditional medical history has been considered as not reliable many aspects. To classify healthy people with noninvasive-based methods such machine learning are efficient. proposed study, we developed a machine-learning-based system prediction...

Heart disease is one of the complex diseases and globally many people suffered from this disease. On time efficient identification heart plays a key role in healthcare, particularly field cardiology. In article, we proposed an accurate system to diagnosis based on machine learning techniques. The developed classification algorithms includes Support vector machine, Logistic regression, Artificial neural network, K-nearest neighbor, Naïve bays, Decision tree while standard features selection...

The patient of Parkinson's disease (PD) is facing a critical neurological disorder issue. Efficient and early prediction people having PD key issue to improve patient's quality life. diagnosis specifically in its initial stages extremely complex time-consuming. Thus, the accurate efficient has been significant challenge for medical experts practitioners. In order tackle this accurately PD, we proposed machine-learning-based system. development system, support vector machine (SVM) was used as...

With the increasing popularity of social media, people has changed way they access news. News online become major source information for people. However, much appearing on Internet is dubious and even intended to mislead. Some fake news are so similar real ones that it difficult human identify them. Therefore, automated detection tools like machine learning deep models have an essential requirement. In this paper, we evaluated performance five three two datasets different size with hold out...

Abstract The classification of brain tumors (BT) is significantly essential for the diagnosis Brian cancer (BC) in IoT-healthcare systems. Artificial intelligence (AI) techniques based on Computer aided diagnostic systems (CADS) are mostly used accurate detection cancer. However, due to inaccuracy artificial systems, medical professionals not effectively incorporating them into process Brain Cancer. In this research study, we proposed a robust tumor method using Deep Learning (DL) address...

Multimodal Large Language Models (MLLMs) are widely used for visual perception, understanding, and reasoning. However, long video processing precise moment retrieval remain challenging due to LLMs’ limited context size coarse frame extraction. We propose the Language-and-Vision Assistant Moment Retrieval (LLaVA-MR), which enables accurate contextual grounding in videos using MLLMs. LLaVA-MR combines Dense Frame Time Encoding (DFTE) spatial-temporal feature extraction, Informative Selection...

Significant attention has been paid to the accurate detection of diabetes. It is a big challenge for research community develop diagnosis system detect diabetes in successful way e-healthcare environment. Machine learning techniques have an emerging role healthcare services by delivering analyze medical data diseases. The existing systems some drawbacks, such as high computation time, and low prediction accuracy. To handle these issues, we proposed using machine methods method tested on set...

In recent years, blockchains have obtained so much attention from researchers, engineers, and institutions; the implementation of has started to revive a large number applications ranging e-finance, e-healthcare, smart home, Internet Things, social security, logistics forth. literature on blockchains, it is found that most articles focused their engineering implementation, while little been devoted exploration theoretical aspects system; however, existing work limited model mining process...

Support vector machine (SVM) is a learning method developed in the mid-1990s based on statistical theory. SVM classifier currently more popular classifier. This paper presents boundary detection technique for retaining potential support vector. Through seeking to structural risk minimization of SVM, it improves generalization ability and achieves empirical confidence range case small sample size can also obtain desired good law.

The accurate and efficient diagnosis of breast cancer is extremely necessary for recovery treatment in early stages IoT healthcare environment. Internet Things has witnessed the transition life last few years which provides a way to analyze both real-time data past by emerging role artificial intelligence mining techniques. current state-of-the-art method does not effectively diagnose stages, most ladies suffered from this dangerous disease. Thus, detection significantly poses great...

Abstract Brain tumor is a group of anomalous cells. The brain enclosed in more rigid skull. abnormal cell grows and initiates tumor. Detection complicated task due to irregular shape. proposed technique contains four phases, which are lesion enhancement, feature extraction selection for classification, localization, segmentation. magnetic resonance imaging (MRI) images noisy certain factors, such as image acquisition, fluctuation field coil. Therefore, homomorphic wavelet filer used noise...

Breast cancer is one the most critical disease and suffered many people around world. The efficient correct detection of breast still needed to ensure this medical issue although researchers world are proposed different diagnostic methods for disease, however these existing further improvement disease. In study, we a new identification method by using machine learning algorithms clinical data. supervised (Relief algorithm) unsupervised (Autoencoder, PCA algorithms) techniques have been used...

Accurate classification of brain tumors is vital for detecting cancer in the Medical Internet Things. Detecting at its early stages a tremendous medical problem, and many researchers have proposed various diagnostic systems; however, these systems still do not effectively detect cancer. To address this issue, we an automatic diagnosing framework that will assist experts ensuring proper treatment. In developing integrated framework, first Convolutional Neural Networks model to extract deep...

Breast tumor detection and classification on the Internet of Medical Things (IoMT) can be automated with potential Artificial Intelligence (AI). However, challenges arise when dealing sensitive data due to dependence large datasets. To address this issue, we propose an approach that combines different magnification factors histopathological images using a residual network information fusion in Federated Learning (FL). FL is employed preserve privacy patient data, while enabling creation...

Abstract This research explores the use of gated recurrent units (GRUs) for automated brain tumor detection using MRI data. The GRU model captures sequential patterns and considers spatial information within individual images temporal evolution lesion characteristics. proposed approach improves accuracy images. model’s performance is benchmarked against conventional CNNs other architectures. addresses interpretability concerns by employing attention mechanisms that highlight salient features...

The COVID-19 shows significant "catastrophe" characteristics. It has put tremendous pressure on various countries' government finances. A few studies have realized that insurance could be applied in the rescue of catastrophic epidemics to relieve and improve efficiency. However, most these are based qualitative analysis, with quantitative calculations prove whether it is feasible. Therefore, this article discusses insurability epidemic catastrophe proposes a novel methodology measures funds,...

Text classification is one of the most widely used natural language processing technologies. Common text applications include spam identification, news classification, information retrieval, emotion analysis, and intention judgment, etc. Traditional classifiers based on machine learning methods have defects such as data sparsity, dimension explosion poor generalization ability, while deep network greatly improve these defects, avoid cumbersome feature extraction process, strong ability...