Land use/land cover (LULC) classification using deep-LSTM for hyperspectral images

The Egyptian Journal of Remote Sensing and Space Science, Год журнала: 2024, Номер 27(1), С. 52 - 68

Опубликована: Янв. 25, 2024

Land Use/Land Cover (LULC) classification using hyperspectral images in remote sensing is a leading technology. However, LULC difficult task and time-consuming process because it has fewer training samples. To overcome these issues, we proposed deep-Long Short-Term Memory (deep-LSTM) to classify the LULC. Before classifying LULC, extracting valuable features from an image needed, after features, selecting bands which are helpful for should be done. In this work, have auto-encoder model feature extraction, ranking-based band selection select bands, deep-LSTM classification. We used three publicly available benchmark datasets; they Pavia University (PU), Kennedy Space Centre (KSC), Indian Pines (IP). Average Accuracy (AA), Overall (OA), Kappa Coefficient (KC) measure accuracy. The suggested technique provided top outcomes compared other state-of-the-art methods.

Язык: Английский

---

Investigation into Application of AI and Telemedicine in Rural Communities: A Systematic Literature Review

Healthcare, Год журнала: 2025, Номер 13(3), С. 324 - 324

Опубликована: Фев. 4, 2025

Recent advances in artificial intelligence (AI) and telemedicine are transforming healthcare delivery, particularly rural underserved communities. Background/Objectives: The purpose of this systematic review is to explore the use AI-driven diagnostic tools platforms identify underlying themes (constructs) literature across multiple research studies. Method: team conducted an extensive studies articles using databases that aimed consistent patterns literature. Results: Five constructs were identified with regard utilization AI on patient diagnosis communities: (1) Challenges/benefits communities, (2) Integration monitoring, (3) Future considerations (4) Application for accurate early diseases through various digital tools, (5) Insights into future directions potential innovations specifically geared towards enhancing delivery Conclusions: While technologies offer enhanced capabilities by processing vast datasets medical records, imaging, histories, leading earlier more diagnoses, acts as a bridge between patients remote areas specialized providers, offering timely access consultations, follow-up care, chronic disease management. Therefore, integration allows real-time decision support, improving clinical outcomes providing data-driven insights during virtual consultations. However, challenges remain, including ensuring equitable these technologies, addressing literacy gaps, managing ethical implications decisions. Despite hurdles, hold significant promise reducing disparities advancing quality care settings, potentially improved long-term health populations.

Язык: Английский

---

Blockchain-Based Privacy-Enhancing Federated Learning in Smart Healthcare: A Survey

Blockchains, Год журнала: 2025, Номер 3(1), С. 1 - 1

Опубликована: Янв. 1, 2025

Federated learning (FL) has emerged as an efficient machine (ML) method with crucial privacy protection features. It is adapted for training models in Internet of Things (IoT)-related domains, including smart healthcare systems (SHSs), where the introduction IoT devices and technologies can arise various security concerns. However, FL cannot solely address all challenges, privacy-enhancing (PETs) blockchain are often integrated to enhance frameworks within SHSs. The critical questions remain regarding how these they contribute enhancing This survey addresses by investigating recent advancements on combination PETs healthcare. First, this emphasizes integration into context. Second, challenge integrating FL, it examines three main technical dimensions such blockchain-enabled model storage, aggregation, gradient upload frameworks. further explores collectively ensure integrity confidentiality data, highlighting their significance building a trustworthy SHS that safeguards sensitive patient information.

Язык: Английский

---

Detecting anomalies in smart wearables for hypertension: a deep learning mechanism

Frontiers in Public Health, Год журнала: 2025, Номер 12

Опубликована: Янв. 9, 2025

The growing demand for real-time, affordable, and accessible healthcare has underscored the need advanced technologies that can provide timely health monitoring. One such area is predicting arterial blood pressure (BP) using non-invasive methods, which crucial managing cardiovascular diseases. This research aims to address limitations of current systems, particularly in remote areas, by leveraging deep learning techniques Smart Health Monitoring (SHM). paper introduces a novel neural network architecture, ResNet-LSTM, predict BP from physiological signals as electrocardiogram (ECG) photoplethysmogram (PPG). combination ResNet's feature extraction capabilities LSTM's sequential data processing offers improved prediction accuracy. Comprehensive error analysis was conducted, model validated Leave-One-Out (LOO) cross-validation an additional dataset. ResNet-LSTM showed superior performance, with PPG data, achieving mean absolute (MAE) 6.2 mmHg root square (RMSE) 8.9 prediction. Despite higher computational cost (~4,375 FLOPs), accuracy generalization across datasets demonstrate model's robustness suitability continuous results confirm potential integrating into SHM accurate approach also highlights anomaly detection monitoring especially wearable devices. Future work will focus on enhancing cloud-based infrastructures real-time refining models improve patient outcomes.

Язык: Английский

---

Progression and Challenges of IoT in Healthcare: A Short Review

International Journal of Computer Applications, Год журнала: 2023, Номер 185(37), С. 9 - 15

Опубликована: Окт. 25, 2023

Smart healthcare, an integral element of connected living, plays a pivotal role in fulfilling fundamental human need.The burgeoning field smart healthcare is poised to generate substantial revenue the foreseeable future.Its multifaceted framework encompasses vital components such as Internet Things (IoT), medical sensors, artificial intelligence (AI), edge and cloud computing, well next-generation wireless communication technologies.Many research papers discuss more broadly.Numerous nations have strategically deployed Medical (IoMT) alongside other measures combat propagation COVID-19.This combined effort has not only enhanced safety frontline workers but also augmented overall efficacy managing pandemic, subsequently reducing its impact on lives mortality rates.Remarkable strides been made both applications technology within IoMT domain.However, it imperative acknowledge that this technological advancement introduced certain challenges, particularly realm security.The rapid extensive adoption worldwide magnified issues related security privacy.These encompass spectrum concerns, ranging from replay attacks, man-in-the-middle impersonation, privileged insider threats, remote hijacking, password guessing, denial service (DoS) malware incursions.In comprehensive review, we undertake comparative analysis existing strategies designed for detection prevention IoT environments.

Язык: Английский

---

Deep CNN based brain tumor detection in intelligent systems

International Journal of Intelligent Networks, Год журнала: 2024, Номер 5, С. 30 - 37

Опубликована: Янв. 1, 2024

The early detection of brain tumor is crucial for effective treatment and improved patient prognosis in Industrial Information Systems. This research introduces a novel computational model employing three-layer Convolutional Neural Network (CNN) the identification tumors Leveraging advanced techniques, this proposed can autonomously detect intricate patterns features from medical imaging data, resulting more accurate expedited diagnoses. With an impressive 90 % precision rate, our demonstrates potential to serve as valuable tool professionals working field neuroimaging. By presenting dependable precise model, study contributes advancement within domain imaging. We anticipate that methodology will aid healthcare providers making diagnoses, thereby leading enhanced outcomes. Potential avenues future encompass refining model's fundamental architecture exploring real-time therapeutic applications.

Язык: Английский

---

A fusion of machine learning algorithms and traditional statistical forecasting models for analyzing American healthcare expenditure

Healthcare Analytics, Год журнала: 2024, Номер 5, С. 100312 - 100312

Опубликована: Фев. 28, 2024

The American healthcare system allocates considerable resources compared to peer-developed nations. However, outcomes significantly trail behind, particularly in life expectancy. This study addresses questions about the enduring trends spending as a percentage of Gross Domestic Product (GDP), notable factors contributing this concerning trend, and timing apply an emergency brake curb accelerating trajectory. Advanced machine learning algorithms, such Random Forest Support Vector Regression (SVR), conjunction with traditional statistical forecasting methods, are used forecast future patterns. research underscores importance analytics unraveling intricacies system. findings highlight pressing need for effective policies confront mounting challenge.

Язык: Английский

---

Improved healthcare diagnosis accuracy through the application of deep learning techniques in medical transcription for disease identification

Alexandria Engineering Journal, Год журнала: 2025, Номер 123, С. 112 - 123

Опубликована: Март 23, 2025

Язык: Английский

---

SEMRAchain: A Secure Electronic Medical Record Based on Blockchain Technology

Electronics, Год журнала: 2022, Номер 11(21), С. 3617 - 3617

Опубликована: Ноя. 6, 2022

A medical record is an important part of a patient’s follow-up. It comprises healthcare professionals’ views, prescriptions, analyses, and all information about the patient. Several players, including patient, doctor, pharmacist, are involved in process sharing, managing this file. Any authorized individual can access electronic (EMR) from anywhere, data shared among various health service providers. Sharing EMR requires conditions, such as security confidentiality. However, existing systems may be exposed to system failure malicious intrusions, making it difficult deliver dependable services. Additionally, features these represent challenge for centralized control methods. This paper presents SEMRAchain based on Access (Role-Based Control (RBAC), Attribute-Based (ABAC)) smart contract approach. fusion enables decentralized, fine-grained, dynamic management management. Together, blockchain technology secure distributed ledger provides solution, providing stakeholders with not just visibility but also trustworthiness, credibility, immutability.

Язык: Английский

---

Fog-Based Smart Cardiovascular Disease Prediction System Powered by Modified Gated Recurrent Unit

Diagnostics, Год журнала: 2023, Номер 13(12), С. 2071 - 2071

Опубликована: Июнь 15, 2023

The ongoing fast-paced technology trend has brought forth ceaseless transformation. In this regard, cloud computing long proven to be the paramount deliverer of services such as power, software, networking, storage, and databases on a pay-per-use basis. is big proponent internet things (IoT), furnishing computation storage requisite address internet-of-things applications. With proliferating IoT devices triggering continual data upsurge, cloud-IoT interaction encounters latency, bandwidth, connectivity restraints. inclusion decentralized distributed fog layer amidst extends cloud's processing, networking close end users. This hierarchical edge-fog-cloud model distributes intelligence, yielding optimal solutions while tackling constraints like massive volume, delay, security vulnerability. healthcare domain, warranting time-critical functionalities, can reap benefits from cloud-fog-IoT interplay. research paper propounded fog-assisted smart system diagnose heart or cardiovascular disease. It combined fuzzy inference (FIS) with recurrent neural network model's variant gated unit (GRU) for pre-processing predictive analytics tasks. proposed showcases substantially improved performance results, classification accuracy at 99.125%. major processing happening layer, it observed that work reveals optimized results concerning delays in terms response time, jitter, compared cloud. Deep learning models are adept handling sophisticated tasks, particularly analytics. Time-critical applications deep learning's exclusive potential furnish near-perfect coupled merits model, revealed by experimental results.

Язык: Английский

---