Future Generation Computer Systems-The International Journal of Escience最新文献

A verifiable query scheme with rich query capabilities and low storage redundancy on blockchain

IF 6.2 2区计算机科学

Future Generation Computer Systems-The International Journal of Escience Pub Date : 2025-04-19 DOI: 10.1016/j.future.2025.107859

Linkun Sun , Luqi Wang , Wenbao Jiang, Yangnan Guo

{"title":"A verifiable query scheme with rich query capabilities and low storage redundancy on blockchain","authors":"Linkun Sun , Luqi Wang , Wenbao Jiang, Yangnan Guo","doi":"10.1016/j.future.2025.107859","DOIUrl":"10.1016/j.future.2025.107859","url":null,"abstract":"<div><div>In current blockchain verifiable query research, redundant storage of data to be indexed is often required to enable efficient and feature-rich query algorithms. However, most blockchains currently face the problem of rapid data growth, leading to significant storage resource consumption by nodes. To provide a high-efficiency and generic verifiable query capability while reducing the storage burden on nodes, we propose a cryptographic accumulator-based verifiable generic query scheme. By skilfully establishing a logical relationship between the cryptographic accumulation value and the proof of element members, our scheme effectively reduces the redundant design of data structures on the chain. Additionally, we design a filter aggregation algorithm, an inter-block indexing structure, and a range query method that transforms the numerical attribute comparison problem into a proof-of-existence problem for members in a collection based on this scheme. Security analysis and experimental analysis verify the robustness and practicality of the proposed techniques.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"171 ","pages":"Article 107859"},"PeriodicalIF":6.2,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143859486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Federated learning for heterogeneous neural networks with layer similarity relations in Cloud–Edge–End scenarios

IF 6.2 2区计算机科学

Future Generation Computer Systems-The International Journal of Escience Pub Date : 2025-04-19 DOI: 10.1016/j.future.2025.107856

Rao Fu, Yongqiang Gao, Zijian Qiao

{"title":"Federated learning for heterogeneous neural networks with layer similarity relations in Cloud–Edge–End scenarios","authors":"Rao Fu, Yongqiang Gao, Zijian Qiao","doi":"10.1016/j.future.2025.107856","DOIUrl":"10.1016/j.future.2025.107856","url":null,"abstract":"<div><div>Federated Learning (FL) aims to allow numerous clients to participate in collaborative training in an efficient communication manner without exchanging private data. Traditional FL assumes that all clients have sufficient local resources to train models with the same architecture, and does not consider the reality that clients may struggle to deploy the same model across devices with varying computational resources. To address this, we propose a heterogeneous FL method, HNN-LSFL, in which the edge server first aggregates the clients of the homogeneous model, and then the cloud server selectively aligns and aggregates the knowledge between the heterogeneous models according to the layer similarity. This Cloud–Edge–End tiered architecture effectively utilizes the powerful computing power of cloud servers, reduces the computational cost of multiple alignment and aggregation of heterogeneous models, and reduces the communication cost with the cloud, which is more suitable for large-scale client scenarios. By identifying layer similarities, the method finds commonalities between different models, enabling more valuable aggregations and reducing the transmission of unnecessary parameters. We also evaluated HNN-LSFL on heterogeneous datasets, demonstrating that it not only improves the utilization of local client resources but also optimizes FL performance. By transmitting fewer model parameters, it reduces the risk of privacy leaks and proves to be superior in FL tasks with heterogeneous models compared to current state-of-the-art heterogeneous FL algorithms.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"171 ","pages":"Article 107856"},"PeriodicalIF":6.2,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143874639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

HalfFedLearn: A secure federated learning with local data partitioning and homomorphic encryption HalfFedLearn：具有本地数据分区和同态加密功能的安全联合学习

IF 6.2 2区计算机科学

Future Generation Computer Systems-The International Journal of Escience Pub Date : 2025-04-18 DOI: 10.1016/j.future.2025.107858

Rojalini Tripathy, Jigyasa Meshram, Padmalochan Bera

{"title":"HalfFedLearn: A secure federated learning with local data partitioning and homomorphic encryption","authors":"Rojalini Tripathy, Jigyasa Meshram, Padmalochan Bera","doi":"10.1016/j.future.2025.107858","DOIUrl":"10.1016/j.future.2025.107858","url":null,"abstract":"<div><div>Federated Learning (FL) is an emerging technology in collaborative machine learning, where multiple data owners train a unified model by exchanging model parameters instead of private data. Despite providing data privacy and a wide range of applications, FL faces several challenges, such as slow convergence, high computation and communication costs, and security in parameter sharing. In this paper, we propose HalfFedLearn to address these challenges using Homomorphic Encryption (HE) and local horizontal data partitioning. We leverage the inherent distribution of the dataset to use horizontal data partitioning based on data sensitivity and enforce selective security on private data samples using HE. HalfFedLearn minimizes the data volume per client, which reduces local training time and computation. Also, the number of communication rounds decreases due to the reduction in local dataset size. We experimented on MNIST, CIFAR-10, and FMNIST datasets with varying clients and number of rounds. The results demonstrate that HalfFedLearn increases accuracy by 3%–6% and achieves an average reduction of 29.33% in training rounds, with a maximum training time reduction of 9.94% per round. Additionally, we performed a comparative analysis of the computation, communication cost, and security that shows the efficacy of HalfFedLearn.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"171 ","pages":"Article 107858"},"PeriodicalIF":6.2,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143864738","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fluid Computing & Digital Twins for intelligent interoperability in the IoT ecosystem

IF 6.2 2区计算机科学

Future Generation Computer Systems-The International Journal of Escience Pub Date : 2025-04-18 DOI: 10.1016/j.future.2025.107855

Luca Bedogni, Marco Mamei, Marco Picone, Marcello Pietri, Franco Zambonelli

{"title":"Fluid Computing & Digital Twins for intelligent interoperability in the IoT ecosystem","authors":"Luca Bedogni, Marco Mamei, Marco Picone, Marcello Pietri, Franco Zambonelli","doi":"10.1016/j.future.2025.107855","DOIUrl":"10.1016/j.future.2025.107855","url":null,"abstract":"<div><div>The integration of physical and digital systems is fundamental to enabling intelligent, adaptive, and scalable solutions in modern IoT environments. This paper explores Fluid Digital Twins (FDTs), a novel framework combining Fluid Computing (FC) principles with Digital Twin (DT) technology, to address challenges related to interoperability, dynamic functionality, and adaptability in IoT ecosystems. FC introduces a paradigm shift, enabling seamless data and computational task flow across heterogeneous environments, dynamically adjusting to resource availability and system needs. This paper focuses on embedding intelligence within FDTs to enhance interoperability and enable IoT applications to adapt to changes across both physical and digital domains. By integrating intelligent interoperability mechanisms, FDTs ensure smooth data alignment and compatibility across platforms, adapting to both physical and digital changes. The proposed framework has been implemented, prototyped, and evaluated in the Modena Automotive Smart Area (MASA), a smart city testbed. The evaluation demonstrates FDTs’ ability to enhance smart mobility, optimize transportation systems, and provide actionable insights, highlighting their transformative potential in dynamic, data-rich environments. The results emphasize the practical applicability of FDTs in addressing real-world challenges and advancing the capabilities of IoT-driven smart cities.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"171 ","pages":"Article 107855"},"PeriodicalIF":6.2,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143869449","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DFASCN:A distributed flocking approach for UAV swarm collective navigation

IF 6.2 2区计算机科学

Future Generation Computer Systems-The International Journal of Escience Pub Date : 2025-04-15 DOI: 10.1016/j.future.2025.107852

Yibing Li , Zitang Zhang , Yujie Huang , Zongyu He , Qian Sun , Qianhui Dong

{"title":"DFASCN:A distributed flocking approach for UAV swarm collective navigation","authors":"Yibing Li , Zitang Zhang , Yujie Huang , Zongyu He , Qian Sun , Qianhui Dong","doi":"10.1016/j.future.2025.107852","DOIUrl":"10.1016/j.future.2025.107852","url":null,"abstract":"<div><div>In recent years, the application domains of unmanned swarms have been continuously expanding. Existing swarm navigation methods predominantly rely on communication networks for frequently information exchange to achieve stable navigation behavior. However, this reliance presents challenges in achieving coordinated cooperative behavior in communication-restricted and obstacle-rich environments. To ensure the task efficiency of swarms in such mission settings, we propose a distributed flocking framework to guide unmanned aerial vehicle (UAV) swarms in navigating from a starting point to a target in unknown environments.Our approach begins by employing Boyd’s OODA loop (Observe, Orient, Decide, Act), combined with a locally limited perception model, to develop an interactive decision-making process between individual UAVs and their external environment. We classify the roles of different UAV platforms within the swarm, enhancing cooperative flight efficiency through the guiding behavior of critical nodes. Each UAV utilizes a dynamic adjustment mechanism for control parameters, allowing adaptive modifications based on local flight states. Additionally, each UAV is equipped with a model predictive control (MPC) controller, which provides feasible control inputs to ensure robust and reliable operation in complex and dynamic scenarios.To evaluate the adaptability of our method, we conducted simulations across various task environments with differing obstacle densities and numbers of UAVs. The results validate the algorithm’s effectiveness and scalability, highlighting its robustness and potential applicability to real-world scenarios.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"171 ","pages":"Article 107852"},"PeriodicalIF":6.2,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143838901","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Rethinking federated learning as a digital platform for dynamic and value-driven participation

IF 6.2 2区计算机科学

Future Generation Computer Systems-The International Journal of Escience Pub Date : 2025-04-12 DOI: 10.1016/j.future.2025.107847

Christoph Düsing, Philipp Cimiano

{"title":"Rethinking federated learning as a digital platform for dynamic and value-driven participation","authors":"Christoph Düsing, Philipp Cimiano","doi":"10.1016/j.future.2025.107847","DOIUrl":"10.1016/j.future.2025.107847","url":null,"abstract":"<div><div><em>Federated learning</em> (FL) has emerged as a powerful framework for privacy-preserving machine learning, especially relevant in fields like healthcare, finance, and mobile devices. Despite its success, traditional FL systems have a significant limitation: they rely on a static set of clients, forming a federation at the beginning of the training process, which remains fixed throughout the training cycle, thus limiting their scalability and adaptability in dynamic, data-rich settings. To address this, we introduce the concept of <em>federated learning platforms</em> (FLPs), which extend FL into a dynamic platform where client participation is continuously adapted based on their expected value and strategic incentives. In this paper, we envision FLPs as a natural extension of conventional FL that resemble dynamic, value-driven digital platforms where participants can join or leave the federation at any time. Given this dynamicity of client participation, FLPs are designed to gracefully handle changes in the client pool to uphold their value proposition. In this article, we propose a framework for implementing FLPs, outlining key components such as those for dynamic FLP governance, including client on- and offboarding as well as process monitoring. Furthermore, we demonstrate the practical viability of FLPs through a proof of concept for an exemplary use-case and discuss key challenges related to federation stability, data interoperability, as well as privacy, alongside potential solutions. Finally, we present a roadmap and future research directions, guiding the development of robust and scalable FLPs to drive innovation in FL and data interoperability.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"171 ","pages":"Article 107847"},"PeriodicalIF":6.2,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143838903","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Efficient profit maximization in reliability concerned static vehicular cloud system

IF 6.2 2区计算机科学

Future Generation Computer Systems-The International Journal of Escience Pub Date : 2025-04-12 DOI: 10.1016/j.future.2025.107850

Suvarthi Sarkar , Akshat Arun , Harshit Sureka , Aryabartta Sahu

{"title":"Efficient profit maximization in reliability concerned static vehicular cloud system","authors":"Suvarthi Sarkar , Akshat Arun , Harshit Sureka , Aryabartta Sahu","doi":"10.1016/j.future.2025.107850","DOIUrl":"10.1016/j.future.2025.107850","url":null,"abstract":"<div><div>Modern vehicles are equipped with high-performance compute systems. These compute resources mostly stay idle as most of the time vehicles get parked in the parking lots. In this work, we propose to utilize the unused compute resources of the vehicles efficiently to enhance the computing power of regular cloud systems, which is termed as vehicular cloud. Unlike in traditional cloud computing resources, the vehicles or vehicular compute resources move in or out of the parking lot, which introduces dynamic nature of the available compute resources. This makes it challenging for the vehicular cloud to ensure reliability of execution of the user-submitted tasks.</div><div>In this work, we propose an approach to maximize the profit of the vehicular cloud by ensuring the reliability of the vehicular cloud. We consider user-submitted tasks with execution time, deadline and revenue associated with it. Our approach classifies the tasks based on the deadline, and orders the tasks for task admission based on the expected profit of the task. We also perform the classification of available vehicular units based on the expected residency time of vehicles and use the same for allocating vehicular units for redundant execution of task to ensure higher reliability. As the task execution time has a direct impact on redundancy requirements to ensure higher reliability, we convert the longer tasks to a chain of shorter sub-tasks to reduce the redundancy requirement. Our experiments show that the proposed approach outperforms the state-of-the-art approach with a profit margin increasing up to 25 to 45 % in real-life scenarios.The codes and dataset for this work are available at our <span><span>https://github.com/SuvarthiSarkar/Efficient-profit-maximization-in-reliability-concerned-static-vehicular-cloud-system.git</span><svg><path></path></svg></span>GitHub repository.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"171 ","pages":"Article 107850"},"PeriodicalIF":6.2,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143847726","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Instant resonance: Dual strategy enhances the data consensus success rate of blockchain threshold signature oracles

IF 6.2 2区计算机科学

Future Generation Computer Systems-The International Journal of Escience Pub Date : 2025-04-11 DOI: 10.1016/j.future.2025.107846

Youquan Xian , Xueying Zeng , Chunpei Li, Dongcheng Li, Peng Wang, Peng Liu, Xianxian Li

{"title":"Instant resonance: Dual strategy enhances the data consensus success rate of blockchain threshold signature oracles","authors":"Youquan Xian , Xueying Zeng , Chunpei Li, Dongcheng Li, Peng Wang, Peng Liu, Xianxian Li","doi":"10.1016/j.future.2025.107846","DOIUrl":"10.1016/j.future.2025.107846","url":null,"abstract":"<div><div>With the rapid development of Decentralized Finance (DeFi) and Real-World Assets (RWA), the importance of blockchain oracles in real-time data acquisition has become increasingly prominent. Using cryptographic techniques, threshold signature oracles can achieve consensus on data from multiple nodes and provide corresponding proofs to ensure the credibility and security of the information. However, in real-time data acquisition, threshold signature methods face challenges such as data inconsistency and low success rates in heterogeneous environments, which limit their practical application potential. To address these issues, this paper proposes an AI-driven dual optimization strategy to enhance the data consensus success rate of blockchain threshold signature oracles. Firstly, we introduce the Representative-Enhanced Aggregation Strategy (REP-AG), which leverages a Bayesian game model to improve the representativeness of node-submitted data, ensuring consistency with other nodes and thereby enhancing the availability of threshold signatures. Additionally, we present a Timing Optimization Strategy (TIM-OPT) that dynamically adjusts the timing of nodes’ access to data sources to maximize consensus success rates. Experimental results indicate that REP-AG improves the consensus success rate by approximately 56.6% compared to the optimal baseline, while the implementation of TIM-OPT leads to an average increase of approximately 32.9% in consensus success rates across all scenarios.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"171 ","pages":"Article 107846"},"PeriodicalIF":6.2,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143838904","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

pFL-SBPM: A communication-efficient personalized federated learning framework for resource-limited edge clients pFL-SBPM：为资源有限的边缘客户提供通信效率高的个性化联合学习框架

IF 6.2 2区计算机科学

Future Generation Computer Systems-The International Journal of Escience Pub Date : 2025-04-10 DOI: 10.1016/j.future.2025.107849

Han Hu , Wenli Du , Yuqiang Li , Yue Wang

{"title":"pFL-SBPM: A communication-efficient personalized federated learning framework for resource-limited edge clients","authors":"Han Hu , Wenli Du , Yuqiang Li , Yue Wang","doi":"10.1016/j.future.2025.107849","DOIUrl":"10.1016/j.future.2025.107849","url":null,"abstract":"<div><div>Federated learning has attracted widespread attention due to its privacy-preserving characteristic. However, in real-world scenarios, the heterogeneity of decentralized data and the limited communication resources of clients pose great challenges to the deployment of federated training. Although existing works have made great strides in dealing with heterogeneous data or compressing communication, they struggle to strike a balance between model accuracy and communication cost. To address the above issues, this paper proposes a novel federated learning framework called pFL-SBPM, which achieves communication-efficient <strong>p</strong>ersonalized <strong>F</strong>ederated <strong>L</strong>earning through <strong>S</strong>tochastic <strong>B</strong>inary <strong>P</strong>robability <strong>M</strong>asks. Specifically, we utilize probability mask optimization instead of conventional weight training, where clients obtain personalized sparse subnetworks adapted to local task requirements by cooperative optimization of probability masks in a randomly weighted network. We develop an uplink communication strategy based on stochastic binary masks and a downlink communication strategy based on binary encoding and decoding, which achieves enhanced privacy protection while dramatically reducing the communication cost. Furthermore, to effectively handle heterogeneous data while mitigating the negative impact of the introduction of stochasticity on the stability of federated training, we carefully design a soft-threshold based selective updating strategy for probability masks. The experimental results show the significant superiority and competitiveness of pFL-SBPM compared to existing baseline and state-of-the-art methods in terms of inference accuracy, communication cost, computational cost and model size.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"171 ","pages":"Article 107849"},"PeriodicalIF":6.2,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143856017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The role of Large Language Models in addressing IoT challenges: A systematic literature review

IF 6.2 2区计算机科学

Future Generation Computer Systems-The International Journal of Escience Pub Date : 2025-04-10 DOI: 10.1016/j.future.2025.107829

Gabriele De Vito, Fabio Palomba, Filomena Ferrucci

{"title":"The role of Large Language Models in addressing IoT challenges: A systematic literature review","authors":"Gabriele De Vito, Fabio Palomba, Filomena Ferrucci","doi":"10.1016/j.future.2025.107829","DOIUrl":"10.1016/j.future.2025.107829","url":null,"abstract":"<div><div>The Internet of Things (IoT) has revolutionized various sectors by enabling devices to communicate and interact seamlessly. However, developing IoT applications has data management, security, and interoperability challenges. Large Language Models (LLMs) have shown promise in addressing these challenges due to their advanced language processing capabilities. This Systematic Literature Review assesses the role of LLMs in addressing IoT challenges, exploring the strategies, hardware, and software configurations used, and identifying directions for future research. We extensively searched databases like Scopus, IEEE Xplore, and ACM Digital Library, initially screening 1,419 studies and identifying an additional 1,167 through snowballing, ultimately focusing on 55 relevant papers. The findings reveal LLMs’ potential to address key IoT challenges such as security and scalability. However, they also highlight significant obstacles, including high computational demands and the complexities of training and tuning these models. Future research should aim to develop methods to reduce the computational requirements of LLMs, improve training datasets, simplify implementation processes, and explore the ethical and privacy implications of using LLMs in IoT applications.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"171 ","pages":"Article 107829"},"PeriodicalIF":6.2,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143838900","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0