Highly Accurate Adaptive Federated Forests Based on Resistance to Adversarial Attacks in Wireless Traffic Prediction DOI Creative Commons
Lingyao Wang, Chenyue Pan, Haitao Zhao

et al.

Sensors, Journal Year: 2025, Volume and Issue: 25(5), P. 1590 - 1590

Published: March 5, 2025

Current 5G communication services have limitations, prompting the development of Beyond (B5G) network. B5G aims to extend scope encompass land, sea, air, and space while enhancing intelligence evolving into an omnipresent converged information This expansion demands higher standards for rates intelligent processing across multiple devices. Furthermore, traffic prediction is crucial efficient planning management networks, optimizing resource allocation, network performance speeds important part B5G's performance. Federated learning addresses privacy transmission cost issues in model training, making it widely applicable prediction. However, traditional federated models are susceptible adversarial attacks that can compromise outcomes. To safeguard from such ensure reliability system, this paper introduces Adaptive Threshold Modified Forest (ATMFF). ATMFF employs adaptive threshold modification, utilizing a confusion matrix rate-based screening-weighted aggregation weak classifiers adjust decision threshold. approach enhances accuracy recognizing samples, thereby ensuring model. Our experiments, based on real data, demonstrate ATMFF's sample recognition surpasses multiboost without modified. improvement bolsters security classification services.

Language: Английский

A Survey on Heterogeneity Taxonomy, Security and Privacy Preservation in the Integration of IoT, Wireless Sensor Networks and Federated Learning DOI Creative Commons
Tesfahunegn Minwuyelet Mengistu, Taewoon Kim, Jenn-Wei Lin

et al.

Sensors, Journal Year: 2024, Volume and Issue: 24(3), P. 968 - 968

Published: Feb. 1, 2024

Federated learning (FL) is a machine (ML) technique that enables collaborative model training without sharing raw data, making it ideal for Internet of Things (IoT) applications where data are distributed across devices and privacy concern. Wireless Sensor Networks (WSNs) play crucial role in IoT systems by collecting from the physical environment. This paper presents comprehensive survey integration FL, IoT, WSNs. It covers FL basics, strategies, types discusses WSNs various domains. The addresses challenges related to heterogeneity summarizes state-of-the-art research this area. also explores security considerations performance evaluation methodologies. outlines latest achievements potential directions emphasizes significance surveyed topics within context current technological advancements.

Language: Английский

Citations

16
Pancreatic Ductal Adenocarcinoma (PDAC): A Review of Recent Advancements Enabled by Artificial Intelligence DOI Open Access

Ashwin Mukund,

Muhammad Ali Afridi, Aleksandra Karolak

et al.

Cancers, Journal Year: 2024, Volume and Issue: 16(12), P. 2240 - 2240

Published: June 17, 2024

Pancreatic Ductal Adenocarcinoma (PDAC) remains one of the most formidable challenges in oncology, characterized by its late detection and poor prognosis. Artificial intelligence (AI) machine learning (ML) are emerging as pivotal tools revolutionizing PDAC care across various dimensions. Consequently, many studies have focused on using AI to improve standard care. This review article attempts consolidate literature from past five years identify high-impact, novel, meaningful focusing their transformative potential management. Our analysis spans a broad spectrum applications, including but not limited patient risk stratification, early detection, prediction treatment outcomes, thereby highlighting AI’s role enhancing quality precision By categorizing into discrete sections reflective patient’s journey screening diagnosis through survivorship, this offers comprehensive examination AI-driven methodologies addressing multifaceted PDAC. Each study is summarized explaining dataset, ML model, evaluation metrics, impact has improving PDAC-related outcomes. We also discuss prevailing obstacles limitations inherent application within context, offering insightful perspectives future directions innovations.

Language: Английский

Citations

10
Edge and Cloud Computing in Smart Cities DOI Creative Commons
Μαρία Τρίγκα, Ηλίας Δρίτσας

Future Internet, Journal Year: 2025, Volume and Issue: 17(3), P. 118 - 118

Published: March 6, 2025

The evolution of smart cities is intrinsically linked to advancements in computing paradigms that support real-time data processing, intelligent decision-making, and efficient resource utilization. Edge cloud have emerged as fundamental pillars enable scalable, distributed, latency-aware services urban environments. Cloud provides extensive computational capabilities centralized storage, whereas edge ensures localized processing mitigate network congestion latency. This survey presents an in-depth analysis the integration cities, highlighting architectural frameworks, enabling technologies, application domains, key research challenges. study examines allocation strategies, analytics, security considerations, emphasizing synergies trade-offs between paradigms. present also notes future directions address critical challenges, paving way for sustainable development.

Language: Английский

Citations

1
A dynamic barycenter bridging network for federated transfer fault diagnosis in machine groups DOI
Bin Yang, Yaguo Lei, Xiang Li

et al.

Mechanical Systems and Signal Processing, Journal Year: 2025, Volume and Issue: 230, P. 112605 - 112605

Published: March 30, 2025

Language: Английский

Citations

1
Multi-organ segmentation: a progressive exploration of learning paradigms under scarce annotation DOI
Shiman Li, Haoran Wang,

Yucong Meng

et al.

Physics in Medicine and Biology, Journal Year: 2024, Volume and Issue: 69(11), P. 11TR01 - 11TR01

Published: March 13, 2024

Abstract Precise delineation of multiple organs or abnormal regions in the human body from medical images plays an essential role computer-aided diagnosis, surgical simulation, image-guided interventions, and especially radiotherapy treatment planning. Thus, it is great significance to explore automatic segmentation approaches, among which deep learning-based approaches have evolved rapidly witnessed remarkable progress multi-organ segmentation. However, obtaining appropriately sized fine-grained annotated dataset extremely hard expensive. Such scarce annotation limits development high-performance models but promotes many annotation-efficient learning paradigms. Among these, studies on transfer leveraging external datasets, semi-supervised including unannotated datasets partially-supervised integrating partially-labeled led dominant way break such dilemmas We first review fully supervised method, then present a comprehensive systematic elaboration 3 abovementioned paradigms context both technical methodological perspectives, finally summarize their challenges future trends.

Language: Английский

Citations

5
A Comprehensive Survey on Federated Learning in the Healthcare Area: Concept and Applications DOI Open Access

Deepak Upreti,

Eunmok Yang, Hyunil Kim

et al.

Computer Modeling in Engineering & Sciences, Journal Year: 2024, Volume and Issue: 140(3), P. 2239 - 2274

Published: Jan. 1, 2024

Federated learning is an innovative machine technique that deals with centralized data storage issues while maintaining privacy and security.It involves constructing models using datasets spread across several centers, including medical facilities, clinical research Internet of Things devices, even mobile devices.The main goal federated to improve robust benefit from the collective knowledge these disparate without centralizing sensitive information, reducing risk loss, breaches, or exposure.The application in healthcare industry holds significant promise due wealth generated various sources, such as patient records, imaging, wearable surveys.This conducts a systematic evaluation highlights essential for selection implementation approaches healthcare.It evaluates effectiveness strategies field offers analysis domain, encompassing metrics employed.In addition, this study increasing interest applications among scholars provides foundations further studies.

Language: Английский

Citations

5
SelfFed: Self-supervised federated learning for data heterogeneity and label scarcity in medical images DOI
Sunder Ali Khowaja, Kapal Dev, Syed Muhammad Anwar

et al.

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: unknown, P. 125493 - 125493

Published: Oct. 1, 2024

Language: Английский

Citations

5
Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration DOI Open Access
Shabbar Abbas, Zeeshan Abbas,

Arifa Zahir

et al.

Healthcare, Journal Year: 2024, Volume and Issue: 12(24), P. 2587 - 2587

Published: Dec. 22, 2024

Federated learning (FL) is revolutionizing healthcare by enabling collaborative machine across institutions while preserving patient privacy and meeting regulatory standards. This review delves into FL's applications within smart health systems, particularly its integration with IoT devices, wearables, remote monitoring, which empower real-time, decentralized data processing for predictive analytics personalized care. It addresses key challenges, including security risks like adversarial attacks, poisoning, model inversion. Additionally, it covers issues related to heterogeneity, scalability, system interoperability. Alongside these, the highlights emerging privacy-preserving solutions, such as differential secure multiparty computation, critical overcoming limitations. Successfully addressing these hurdles essential enhancing efficiency, accuracy, broader adoption in healthcare. Ultimately, FL offers transformative potential secure, data-driven promising improved outcomes, operational sovereignty ecosystem.

Language: Английский

Citations

5
Federated Learning Lifecycle Management for Distributed Medical Artificial Intelligence Applications: A Case Study on Post-Transcatheter Aortic Valve Replacement Complication Prediction Solution DOI Creative Commons

Mette Holme Jung,

In‐Ho Song,

Kang Yoon Lee

et al.

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(1), P. 378 - 378

Published: Jan. 3, 2025

The evolution of artificial intelligence (AI) has unveiled considerable prospects for delivering efficacious solutions in the medical domain. Nevertheless, existing legal frameworks and concerns regarding data privacy associated with information impose substantial constraints on implementing AI this Federated learning is a paradigm that enables training machine models decentralized manner without transferring to central repository, allowing model development while preserving across other industries. This study provided comprehensive framework applying federated It advocates sustainable ecosystem by overseeing servers clients evaluating performance managing lifecycle. To enhance its practical relevance, includes detailed process continuous lifecycle management, involving deployment, aggregation, testing, evaluation, versioning, real-time monitoring through FedOps platform, supporting solution. In study, feasibility proposed methodology was verified using post-transcatheter aortic valve replacement (TAVR) complication–prediction framework. solution after transitioning approach compared an centralized findings indicated no statistically significant difference between two methodologies. implies can augment usability facilitate integration technologies into domain, where preservation critically important.

Language: Английский

Citations

0
Fvcm-Net: Interpretable Privacy-Preserved Attention Driven Lung Cancer Detection from Ct Scan Images with Explainable Hires-Cam Attribution Map and Ensemble Learning DOI
Abu Sayem Md. Siam, Md. Mehedi Hasan, Yeasir Arafat

et al.

Published: Jan. 1, 2025

Lung cancer is a predominant cause of related deaths globally, with early detection for improving patient prognosis being essential. Deep learning models, particularly those attention mechanisms, have shown promising accuracy in detecting lung from medical imaging data. However, privacy concerns and data scarcity present significant challenges developing robust generalizable models. This paper proposes novel approach utilizing federated mechanisms ensemble to address these challenges. Federated employed train the model across multiple decentralized institutions, allowing collaborative development without sharing sensitive minimizes risk information exposed or misused, making it ideal applications involving health records. Furthermore, this enables more accurate generalized models by leveraging diverse datasets sources. To improve robustness diagnosis we employ produce predictions than single model, interpretability identification (FVCM-Net), XAI (Explainable Artificial Intelligence) techniques instance SHAP (SHapley Additive exPlanations) HiResCAM (High-Resolution Class Activation Mapping). These help us understand how makes it's decisions explains its predictions. Experimental results showed that proposed method achieved higher performance 98.26% 97.37% F-1 score. The high FVCM-Net has potential significantly impact imaging, helping radiologists make better clinical decisions.

Language: Английский

Citations

0