Fog Computing-Based Framework and Solutions for Intelligent Systems

Advances in computational intelligence and robotics book series, Journal Year: 2024, Volume and Issue: unknown, P. 330 - 356

Published: Feb. 27, 2024

The automotive industry is increasingly focusing on autonomous vehicles, leading to a need for intelligent systems that enable safe and efficient self-driving. Fog computing promising paradigm real-time data processing communication in vehicles. This chapter presents comprehensive framework solutions integrating fog into vehicle systems, enabling features, low-latency processing, reliable communication, enhanced decision-making capabilities. By offloading computational tasks nearby nodes, this optimizes resource utilization, reduces network congestion, enhances autonomy. discusses various use cases, architectures, protocols, security considerations within computing, ultimately contributing the evolution of

Language: Английский

---

FedHealthFog: A federated learning-enabled approach towards healthcare analytics over fog computing platform

Heliyon, Journal Year: 2024, Volume and Issue: 10(5), P. e26416 - e26416

Published: Feb. 16, 2024

The emergence of federated learning (FL) technique in fog-enabled healthcare system has leveraged enhanced privacy towards safeguarding sensitive patient information over heterogeneous computing platforms. In this paper, we introduce the FedHealthFog framework, which was meticulously developed to overcome difficulties distributed resource-constrained IoT-enabled systems, particularly those delays and energy efficiency. Conventional approaches face challenges stemming from substantial compute requirements significant communication costs. This is primarily due their reliance on a singular server for aggregation global data, results inefficient training models. We present transformational approach address these problems by elevating strategically placed fog nodes position local aggregators within architecture. A sophisticated greedy heuristic used optimize choice node as aggregator each cycle between edge devices cloud. notably accounts drop latency 87.01%, 26.90%, 71.74%, consumption 57.98%, 34.36%, 35.37% respectively, three benchmark algorithms analyzed study. effectiveness strongly supported outcomes our experiments compared cutting-edge alternatives while simultaneously reducing number cycles. These findings highlight FedHealthFog's potential transform IoT environments delay-sensitive applications.

Language: Английский

---

The Convergence of Cutting-Edge Technologies: Leveraging AI and Edge Computing to Transform the Internet of Medical Things (IoMT)

Published: July 6, 2023

This research used a wearable sensor to gather photoplethysmography (PPG) signals from 15 healthy subjects. The dataset includes 7,308 PPG segments, each containing 8 seconds of data and corresponding labels indicating the type physical activity subject performed. article proposes convolutional neural network (CNN) model classify signals. proposed several layers: batch normalization, convolutional, max-pooling, dropout, fully connected. output layer uses softmax activation function compute probabilities class. Regarding performance, suggested CNN outperforms conventional models like SVM with RBF kernel, Decision Tree, Random Forest. also suggests techniques optimize further, which can be beneficial for developing IoMT applications such as recognition vital signs monitoring.

Language: Английский

---

An SDN-enabled fog computing framework for wban applications in the healthcare sector

Internet of Things, Journal Year: 2024, Volume and Issue: 26, P. 101150 - 101150

Published: Feb. 28, 2024

Language: Английский

---

Shaping the Next Generation Smart City Ecosystem: An Investigation on the Requirements, Applications, Architecture, Security and Privacy, and Open Research Questions

S.M.A.R.T. environments, Journal Year: 2024, Volume and Issue: unknown, P. 3 - 52

Published: Jan. 1, 2024

Language: Английский

---

Machine Learning for Blockchain and IoT Systems in Smart City

Future Internet, Journal Year: 2025, Volume and Issue: 17(2), P. 80 - 80

Published: Feb. 11, 2025

Recent advancements in machine learning algorithms have facilitated the rapid use of blockchain technology and Internet Things design development smart cities [...]

Language: Английский

---

An end-to-end four tier remote healthcare monitoring framework using edge-cloud computing and redactable blockchain

Computers in Biology and Medicine, Journal Year: 2025, Volume and Issue: 189, P. 109987 - 109987

Published: March 12, 2025

Language: Английский

---

Advancing Ovarian Cancer Diagnosis Through Deep Learning and eXplainable AI: A Multiclassification Approach

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 116968 - 116986

Published: Jan. 1, 2024

Language: Английский

---

Sustainable Fog-Assisted Intelligent Monitoring Framework for Consumer Electronics in Industry 5.0 Applications

IEEE Transactions on Consumer Electronics, Journal Year: 2023, Volume and Issue: 70(1), P. 1501 - 1510

Published: Nov. 17, 2023

The fifth era of the industry (Industry 5.0) has been marked by reformation witnessed in consumer electronics sector bringing forth technology that could enhance efficiency, connectivity, and user experience. Industry 5.0 makes it possible to create intelligent products can interact, analyse data, instantly adjust preferences. Fog processing further enhances power closer end-user devices at network's edge. Traditional machine learning techniques are unsuitable for manufacturing use cases which demand high degree interoperability heterogeneity due unavailability private requires decentralized solutions. To address this, we designed a monitoring framework uses deep reinforcement predict effect mobile computing resources systems detect disruptions real time. Our is deployed level includes dynamic rescheduling module sustainably optimizes task assignment, improves execution accuracy, reduces delay, maximizes resource utilization. Numerical results demonstrate efficiency our scheme managing real-time disruption detection, depicting sustainable utilization available over considered benchmark algorithms.

Language: Английский

---

Toward Multi-Modal Deep Learning-Assisted Task Offloading for Consumer Electronic Devices Over an IoT-Fog Architecture

IEEE Transactions on Consumer Electronics, Journal Year: 2024, Volume and Issue: 70(1), P. 1656 - 1663

Published: Feb. 1, 2024

Internet of Things (IoT) devices along with associated software have proliferated at an unprecedented pace, presenting the challenge high energy use combined latency during complex, time-sensitive transactions. Fog computing, i.e., a distributed computing paradigm, may be potential remedy. However, despite these efforts, it is highly strenuous to regulate service and efficiency within fog layer for IoT centered consumer electronics. In our research, we propose algorithm called Dynamic Deep Reinforcement learning-based Task Offloading (DDTO). Therefore, in multi-modal IoT-Fog systems, intelligent distribution resources by DDTO considered on basis constraints timeliness completion tasks. We log-normal describe delay consumption so as make up varying modalities. Besides, task prioritization problem, which described integer programming that minimizes servers further described. yields better performance than conventional Q–learning respect long-term expected rewards since uses priority weights derived from statistical data. Experimental results demonstrate benefits reducing energy, when compared benchmark strategies, discussing issues multiple modalities systems.

Language: Английский

---