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

英文中文

PIM-IoT: Enabling hierarchical, heterogeneous, and agile Processing-in-Memory in IoT systems

IF 6.2 2区计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS

Future Generation Computer Systems-The International Journal of Escience

Pub Date : 2025-02-28 DOI: 10.1016/j.future.2025.107782

Kan Zhong , Qiao Li , Ao Ren , Yujuan Tan , Xianzhang Chen , Linbo Long , Duo Liu

The Internet of Things (IoT) is an emerging concept that senses the physical world by connecting various “things” and objects to the Internet. Conventional cloud-based IoT systems are unlikely to keep up with the diverse needs of IoT applications and have some issues, such as privacy and latency. Edge computing based IoT systems solve these issues by placing data processing and inference tasks near the data source. However, due to the increasing complexity of IoT applications, performing data processing and inference tasks in edge computing based IoT systems can lead to high energy consumption and latency.

Processing-in-Memory (PIM) is a promising solution to reduce the energy consumption of data processing and inference tasks by closely integrating computational logics with memory device. Therefore, in this paper, we propose PIM-IoT, a PIM architectures enabled IoT system to reduce the energy consumption. To accommodate various data processing tasks, we architect PIM-IoT as a hierarchical system that consists of 3 tiers: sensing tier, gateway tier, and edge computing tier. We first analyze the dataflow of typical IoT applications and map tasks to different tiers. To handle the data processing and inference tasks effectively in each tier, we then propose hierarchical, heterogeneous, and collaborative PIM architectures for each tier. Finally, we show how multi-tier can be co-optimized under latency and power constraints. To our knowledge, this is the first work to explore novel PIM architectures in IoT systems. Detailed analysis and experimental results show that PIM-IoT can achieve 5.6x performance improvement and 6x energy consumption reduction for IoT applications.

{"title":"PIM-IoT: Enabling hierarchical, heterogeneous, and agile Processing-in-Memory in IoT systems","authors":"Kan Zhong , Qiao Li , Ao Ren , Yujuan Tan , Xianzhang Chen , Linbo Long , Duo Liu","doi":"10.1016/j.future.2025.107782","DOIUrl":"10.1016/j.future.2025.107782","url":null,"abstract":"<div><div>The Internet of Things (IoT) is an emerging concept that senses the physical world by connecting various “things” and objects to the Internet. Conventional cloud-based IoT systems are unlikely to keep up with the diverse needs of IoT applications and have some issues, such as privacy and latency. Edge computing based IoT systems solve these issues by placing data processing and inference tasks near the data source. However, due to the increasing complexity of IoT applications, performing data processing and inference tasks in edge computing based IoT systems can lead to high energy consumption and latency.</div><div>Processing-in-Memory (PIM) is a promising solution to reduce the energy consumption of data processing and inference tasks by closely integrating computational logics with memory device. Therefore, in this paper, we propose <strong>PIM-IoT</strong>, a PIM architectures enabled IoT system to reduce the energy consumption. To accommodate various data processing tasks, we architect PIM-IoT as a hierarchical system that consists of 3 tiers: <em>sensing tier</em>, <em>gateway tier</em>, and <em>edge computing tier</em>. We first analyze the dataflow of typical IoT applications and map tasks to different tiers. To handle the data processing and inference tasks effectively in each tier, we then propose hierarchical, heterogeneous, and collaborative PIM architectures for each tier. Finally, we show how multi-tier can be co-optimized under latency and power constraints. To our knowledge, this is the first work to explore novel PIM architectures in IoT systems. Detailed analysis and experimental results show that PIM-IoT can achieve 5.6x performance improvement and 6x energy consumption reduction for IoT applications.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"169 ","pages":"Article 107782"},"PeriodicalIF":6.2,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143563729","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 workload-aware quantized framework for secure learning in data-sensitive applications

IF 6.2 2区计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS

Future Generation Computer Systems-The International Journal of Escience

Pub Date : 2025-02-28 DOI: 10.1016/j.future.2025.107772

Manu Narula , Jasraj Meena , Dinesh Kumar Vishwakarma

Federated Learning (FL) emerged as a leading secure, distributed learning technology based on sharing insights instead of data. The privacy-ensuring capability of FL has enabled its extensive use in Data-Sensitive Applications like healthcare and finance. However, the transmitted insights are at risk of leakage as the security of the medium cannot be guaranteed and can lead to the inference of the user data. Quantization is sometimes used to change these transmitted values to provide security but at the cost of accuracy loss in global models. Coupled with client dropouts, this increases performance loss. In this paper, we propose a Federated Workload-Aware Framework with Linear Quantization (Fed-WALQ), which layers the quantization process with an active client-selection technique based on the sustainable workload of the clients. The framework minimizes the dropout rates and compensates for the loss due to quantization. Through numerical experiments compared against traditional FL and Quantization-enabled FL over multiple datasets, the Fed-WALQ shows improvements in security over the former and accuracy over the latter. The accuracy improvement varies with the complexities of the involved datasets, while a substantial drop in straggler node percentages is seen in all cases (up to 91.8% drop).

{"title":"Federated workload-aware quantized framework for secure learning in data-sensitive applications","authors":"Manu Narula , Jasraj Meena , Dinesh Kumar Vishwakarma","doi":"10.1016/j.future.2025.107772","DOIUrl":"10.1016/j.future.2025.107772","url":null,"abstract":"<div><div>Federated Learning (FL) emerged as a leading secure, distributed learning technology based on sharing insights instead of data. The privacy-ensuring capability of FL has enabled its extensive use in Data-Sensitive Applications like healthcare and finance. However, the transmitted insights are at risk of leakage as the security of the medium cannot be guaranteed and can lead to the inference of the user data. Quantization is sometimes used to change these transmitted values to provide security but at the cost of accuracy loss in global models. Coupled with client dropouts, this increases performance loss. In this paper, we propose a Federated Workload-Aware Framework with Linear Quantization (Fed-WALQ), which layers the quantization process with an active client-selection technique based on the sustainable workload of the clients. The framework minimizes the dropout rates and compensates for the loss due to quantization. Through numerical experiments compared against traditional FL and Quantization-enabled FL over multiple datasets, the Fed-WALQ shows improvements in security over the former and accuracy over the latter. The accuracy improvement varies with the complexities of the involved datasets, while a substantial drop in straggler node percentages is seen in all cases (up to 91.8% drop).</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"168 ","pages":"Article 107772"},"PeriodicalIF":6.2,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143548538","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

VeriTrac: Verifiable and traceable cross-silo federated learning

IF 6.2 2区计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS

Future Generation Computer Systems-The International Journal of Escience

Pub Date : 2025-02-27 DOI: 10.1016/j.future.2025.107780

Yanxin Xu , Hua Zhang , Zhenyan Liu , Fei Gao , Lei Qiao

Cross-silo federated learning enables many clients to train a machine learning model collaboratively, while keeping the raw training data locally. It faces the risks of privacy leakage and malicious participants. In this paper, we introduce a new security risk that malicious clients may disrupt the training process of cross-silo federated learning by falsifying the verification evidences. The verification failure caused by this malicious behavior is not easily distinguishable from that caused by the malicious server falsifying the aggregated model. To address this issue, we design VeriTrac, the first privacy-preserving cross-silo federated learning scheme that supports verifiability and traceability. Before performing the aggregation, the server can utilize the non-private information of clients to verify messages submitted by them to avoid being framed. When the proportion of malicious clients is less than 50%, malicious participants causing the verification error can be traced. In addition, to verify the correctness of the aggregated models, a model vector with a verification factor is constructed and encrypted. The vector is confidential for the server, and the factor is part of the verification evidence and recoverable for clients. Security analysis shows that VeriTrac can guarantee the tracing of malicious participants and the data security of clients. Experimental evaluation shows that computation efficiency and communication efficiency of VeriTrac are acceptable.

{"title":"VeriTrac: Verifiable and traceable cross-silo federated learning","authors":"Yanxin Xu , Hua Zhang , Zhenyan Liu , Fei Gao , Lei Qiao","doi":"10.1016/j.future.2025.107780","DOIUrl":"10.1016/j.future.2025.107780","url":null,"abstract":"<div><div>Cross-silo federated learning enables many clients to train a machine learning model collaboratively, while keeping the raw training data locally. It faces the risks of privacy leakage and malicious participants. In this paper, we introduce a new security risk that malicious clients may disrupt the training process of cross-silo federated learning by falsifying the verification evidences. The verification failure caused by this malicious behavior is not easily distinguishable from that caused by the malicious server falsifying the aggregated model. To address this issue, we design VeriTrac, the first privacy-preserving cross-silo federated learning scheme that supports verifiability and traceability. Before performing the aggregation, the server can utilize the non-private information of clients to verify messages submitted by them to avoid being framed. When the proportion of malicious clients is less than 50%, malicious participants causing the verification error can be traced. In addition, to verify the correctness of the aggregated models, a model vector with a verification factor is constructed and encrypted. The vector is confidential for the server, and the factor is part of the verification evidence and recoverable for clients. Security analysis shows that VeriTrac can guarantee the tracing of malicious participants and the data security of clients. Experimental evaluation shows that computation efficiency and communication efficiency of VeriTrac are acceptable.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"168 ","pages":"Article 107780"},"PeriodicalIF":6.2,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143548536","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

Alleviating straggler impacts for data parallel deep learning with hybrid parameter update

IF 6.2 2区计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS

Future Generation Computer Systems-The International Journal of Escience

Pub Date : 2025-02-27 DOI: 10.1016/j.future.2025.107775

Hongliang Li , Qi Tian , Dong Xu , Hairui Zhao , Zhewen Xu

Data parallelism in distributed clusters faces challenges due to costly global parameter updates and performance imbalances, leading to stragglers that negatively impact training speed and accuracy. This paper proposes Cooperate Grouping Parallel (CGP), a hybrid parameter update scheme to alleviate the problem. CGP supports dynamic grouping among parallel workers and utilizes both intra-group synchronous update and inter-group asynchronous update. CGP treats straggler as an opportunity for worker groups to cooperatively reduce the global parameter update cost. We give the theoretical upper bound of model accuracy deviation caused by inter-group asynchronous updates, which proves the convergence property of the proposed CGP. Extensive testbed experiments on different workloads shows that CGP achieves 1.94

\times

speedup compared to the other methods on average in different scenarios, and CGP improves accuracy by 16.8% over the asynchronous methods.

引用次数: 0

Entropy-based genetic feature engineering and multi-classifier fusion for anomaly detection in vehicle controller area networks

IF 6.2 2区计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS

Future Generation Computer Systems-The International Journal of Escience

Pub Date : 2025-02-27 DOI: 10.1016/j.future.2025.107779

Mohammad Fatahi , Danial Sadrian Zadeh , Behzad Moshiri , Otman Basir

Technological advances in mobile computing, wireless communications, and remote sensing have provided the foundation for expanding and improving intelligent transportation systems (ITS), making modern vehicles susceptible to cyberattacks due to their evolved functionality and connectivity. In-vehicle networks, such as controller area networks (CAN), are highly vulnerable to attacks due to the lack of security architecture. Considering the temporal and spatial aspects of attacks and the need to develop lightweight models, this study develops a flexible and lightweight anomaly detection model for CAN bus with normal and sensitive duty cycles. To achieve optimal performance and consider spatio-temporal information, the feature space is optimized by extracting new features based on a two-parameter genetic algorithm (2P-GA) and Shannon entropy. Next, a synergistic combination of different supervised machine learning classifiers based on the ordered weighted averaging (OWA) operators is leveraged to optimize the results and achieve better performance. Also, to show the effectiveness of the proposed method in the present study, a comprehensive and unique comparative analysis with previous works and state-of-the-art models is presented. The results show that the proposed framework achieves the highest performance in terms of accuracy and F1-score and the lowest computational cost compared with previous works.

{"title":"Entropy-based genetic feature engineering and multi-classifier fusion for anomaly detection in vehicle controller area networks","authors":"Mohammad Fatahi , Danial Sadrian Zadeh , Behzad Moshiri , Otman Basir","doi":"10.1016/j.future.2025.107779","DOIUrl":"10.1016/j.future.2025.107779","url":null,"abstract":"<div><div>Technological advances in mobile computing, wireless communications, and remote sensing have provided the foundation for expanding and improving intelligent transportation systems (ITS), making modern vehicles susceptible to cyberattacks due to their evolved functionality and connectivity. In-vehicle networks, such as controller area networks (CAN), are highly vulnerable to attacks due to the lack of security architecture. Considering the temporal and spatial aspects of attacks and the need to develop lightweight models, this study develops a flexible and lightweight anomaly detection model for CAN bus with normal and sensitive duty cycles. To achieve optimal performance and consider spatio-temporal information, the feature space is optimized by extracting new features based on a two-parameter genetic algorithm (2P-GA) and Shannon entropy. Next, a synergistic combination of different supervised machine learning classifiers based on the ordered weighted averaging (OWA) operators is leveraged to optimize the results and achieve better performance. Also, to show the effectiveness of the proposed method in the present study, a comprehensive and unique comparative analysis with previous works and state-of-the-art models is presented. The results show that the proposed framework achieves the highest performance in terms of accuracy and F1-score and the lowest computational cost compared with previous works.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"169 ","pages":"Article 107779"},"PeriodicalIF":6.2,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143548635","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

Dynamic FPGA reconfiguration for scalable embedded artificial intelligence (AI): A co-design methodology for convolutional neural networks (CNN) acceleration

IF 6.2 2区计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS

Future Generation Computer Systems-The International Journal of Escience

Pub Date : 2025-02-26 DOI: 10.1016/j.future.2025.107777

Jalil Boudjadar , Saif Ul Islam , Rajkumar Buyya

In recent years, FPGA platforms have shown significant potential for accelerating artificial intelligence (AI) applications, particularly in Embedded AI. While various studies have explored adaptive AI deployment on FPGAs, there remains a gap in methodologies fully integrating software adaptability with FPGA hardware reconfigurability. This article presents a novel end-to-end co-design methodology for deploying adaptable and scalable Convolutional Neural Networks (CNNs) on FPGA platforms. The framework enhances computational performance and reduces latency by dynamically modifying hardware acceleration units by combining CNN architecture adaptability with dynamic partial reconfiguration of FPGA hardware. The proposed methodology enables automated synthesis and runtime customization of both hardware accelerators and CNN architectures, eliminating the need for iterative synthesis. This approach has been implemented and tested on a Xilinx XC7020 FPGA board for a CNN-based image classifier, achieving superior computation performance (0.68s/image) and accuracy (97%) compared to state-of-the-art alternatives.

{"title":"Dynamic FPGA reconfiguration for scalable embedded artificial intelligence (AI): A co-design methodology for convolutional neural networks (CNN) acceleration","authors":"Jalil Boudjadar , Saif Ul Islam , Rajkumar Buyya","doi":"10.1016/j.future.2025.107777","DOIUrl":"10.1016/j.future.2025.107777","url":null,"abstract":"<div><div>In recent years, FPGA platforms have shown significant potential for accelerating artificial intelligence (AI) applications, particularly in Embedded AI. While various studies have explored adaptive AI deployment on FPGAs, there remains a gap in methodologies fully integrating software adaptability with FPGA hardware reconfigurability. This article presents a novel end-to-end co-design methodology for deploying adaptable and scalable Convolutional Neural Networks (CNNs) on FPGA platforms. The framework enhances computational performance and reduces latency by dynamically modifying hardware acceleration units by combining CNN architecture adaptability with dynamic partial reconfiguration of FPGA hardware. The proposed methodology enables automated synthesis and runtime customization of both hardware accelerators and CNN architectures, eliminating the need for iterative synthesis. This approach has been implemented and tested on a Xilinx XC7020 FPGA board for a CNN-based image classifier, achieving superior computation performance (0.68s/image) and accuracy (97%) compared to state-of-the-art alternatives.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"169 ","pages":"Article 107777"},"PeriodicalIF":6.2,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143620559","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A distributed monitoring architecture for JointCloud computing

IF 6.2 2区计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS

Future Generation Computer Systems-The International Journal of Escience

Pub Date : 2025-02-26 DOI: 10.1016/j.future.2025.107773

Yadi Wu , Lina Wang , Rongwei Yu , Xiuwen Huang , Jiatong Liu

JointCloud computing supports large-scale resource consolidation and collaboration among multiple cloud service providers to provide users with powerful performance and adequate services. In the face of exponential scaling of resources, monitoring is an indispensable part of effective resource management. Monitoring provides methods for reviewing and managing the performance status of JointCloud resources and services to better characterize the overall operating status of JointCloud system. However, the collaboration between cloud service providers and the scale of resources in JointCloud are dynamically changing, and it is not easy to perform monitoring in a flexible and scalable way. In order to cover all aspects related to resource monitoring in JointCloud environments, we propose a distributed monitoring architecture for JointCloud computing. The architecture focuses on the ability to obtain information, organizes monitoring components in a modular way, and supports on-demand startup to provide dynamic monitoring capabilities. The proposed distributed monitoring approach provides load balancing and fault tolerance services to ensure reliability and performance of monitoring. The architecture also considers the JointCloud quality of service (QoS) and designs a virtual resource orchestration approach aimed at improving the efficiency of resource utilization. We have developed a prototype architecture and presented experimental results to evaluate our design. The prototype architecture can be easily deployed in public or private JointCloud infrastructures for flexible and scalable monitoring. The evaluation results show that our architecture is feasible in terms of performance and scalability.

{"title":"A distributed monitoring architecture for JointCloud computing","authors":"Yadi Wu , Lina Wang , Rongwei Yu , Xiuwen Huang , Jiatong Liu","doi":"10.1016/j.future.2025.107773","DOIUrl":"10.1016/j.future.2025.107773","url":null,"abstract":"<div><div>JointCloud computing supports large-scale resource consolidation and collaboration among multiple cloud service providers to provide users with powerful performance and adequate services. In the face of exponential scaling of resources, monitoring is an indispensable part of effective resource management. Monitoring provides methods for reviewing and managing the performance status of JointCloud resources and services to better characterize the overall operating status of JointCloud system. However, the collaboration between cloud service providers and the scale of resources in JointCloud are dynamically changing, and it is not easy to perform monitoring in a flexible and scalable way. In order to cover all aspects related to resource monitoring in JointCloud environments, we propose a distributed monitoring architecture for JointCloud computing. The architecture focuses on the ability to obtain information, organizes monitoring components in a modular way, and supports on-demand startup to provide dynamic monitoring capabilities. The proposed distributed monitoring approach provides load balancing and fault tolerance services to ensure reliability and performance of monitoring. The architecture also considers the JointCloud quality of service (QoS) and designs a virtual resource orchestration approach aimed at improving the efficiency of resource utilization. We have developed a prototype architecture and presented experimental results to evaluate our design. The prototype architecture can be easily deployed in public or private JointCloud infrastructures for flexible and scalable monitoring. The evaluation results show that our architecture is feasible in terms of performance and scalability.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"168 ","pages":"Article 107773"},"PeriodicalIF":6.2,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143527563","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

Solving online resource-constrained scheduling for follow-up observation in astronomy: A reinforcement learning approach

IF 6.2 2区计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS

Future Generation Computer Systems-The International Journal of Escience

Pub Date : 2025-02-26 DOI: 10.1016/j.future.2025.107781

Yajie Zhang, Ce Yu, Chao Sun, Jizeng Wei, Junhan Ju, Shanjiang Tang

In the astronomical observation field, determining the allocation of observation resources of the telescope array and planning follow-up observations for targets of opportunity (ToOs) are indispensable components of astronomical scientific discovery. This problem is computationally challenging, given the online observation setting and the abundance of time-varying factors that can affect whether an observation can be conducted. This paper presents ROARS, a reinforcement learning approach for online astronomical resource-constrained scheduling. To capture the structure of the astronomical observation scheduling, we depict every schedule using a directed acyclic graph (DAG), illustrating the dependency of timing between different observation tasks within the schedule. Deep reinforcement learning is used to learn a policy that can improve the feasible solution by iteratively local rewriting until convergence. It can solve the challenge of obtaining a complete solution directly from scratch in astronomical observation scenarios, due to the high computational complexity resulting from numerous spatial and temporal constraints. A simulation environment is developed based on real-world scenarios for experiments, to evaluate the effectiveness of our proposed scheduling approach. The experimental results show that ROARS surpasses 5 popular heuristics, adapts to various observation scenarios and learns effective strategies with hindsight.

{"title":"Solving online resource-constrained scheduling for follow-up observation in astronomy: A reinforcement learning approach","authors":"Yajie Zhang, Ce Yu, Chao Sun, Jizeng Wei, Junhan Ju, Shanjiang Tang","doi":"10.1016/j.future.2025.107781","DOIUrl":"10.1016/j.future.2025.107781","url":null,"abstract":"<div><div>In the astronomical observation field, determining the allocation of observation resources of the telescope array and planning follow-up observations for targets of opportunity (ToOs) are indispensable components of astronomical scientific discovery. This problem is computationally challenging, given the online observation setting and the abundance of time-varying factors that can affect whether an observation can be conducted. This paper presents <span>ROARS</span>, a reinforcement learning approach for online astronomical resource-constrained scheduling. To capture the structure of the astronomical observation scheduling, we depict every schedule using a directed acyclic graph (DAG), illustrating the dependency of timing between different observation tasks within the schedule. Deep reinforcement learning is used to learn a policy that can improve the feasible solution by iteratively local rewriting until convergence. It can solve the challenge of obtaining a complete solution directly from scratch in astronomical observation scenarios, due to the high computational complexity resulting from numerous spatial and temporal constraints. A simulation environment is developed based on real-world scenarios for experiments, to evaluate the effectiveness of our proposed scheduling approach. The experimental results show that <span>ROARS</span> surpasses 5 popular heuristics, adapts to various observation scenarios and learns effective strategies with hindsight.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"169 ","pages":"Article 107781"},"PeriodicalIF":6.2,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143563730","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

An incomplete three-way consensus algorithm for unmanned aerial vehicle purchase using optimization-driven sentiment analysis

IF 6.2 2区计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS

Future Generation Computer Systems-The International Journal of Escience

Pub Date : 2025-02-19 DOI: 10.1016/j.future.2025.107761

Chao Zhang , Yating Wang , Arun Kumar Sangaiah , Mohammed J.F. Alenazi , Majed Aborokbah

As a novel productive force in the low-altitude economy, the unmanned aerial vehicle (UAV) industry has emerged as a crucial engine of the digital economy growth. However, high-dimensional online reviews, incomplete information systems (IISs), and coordination among numerous sellers may influence the purchasing decision for UAVs. To address these challenges, first, the sentiment analysis (SA) of UAV online reviews is conducted using BiLSTM and BiGRU models optimized by the hippopotamus optimization (HO) algorithm. Meanwhile, the K-nearest neighbor (KNN) algorithm that combines the Jensen–shannon (JS) divergence with the Hellinger distance is applied to construct a complete information system (CIS). Second, three-way clustering (TWC) is performed on sellers, followed by the calculation of seller weights and group weights using the full consistency method. Third, to closely align with the behavior of sellers, a two-stage consensus reaching process (CRP) model based on TWC and the dual fine-tuning (DFT) theory is proposed, referred to as TWC-DFT-CCRP. In the first stage, the behavior of sellers is adjusted based on the TWC result. In the second stage, optimization-based rules are used to reduce the conflict degree among sellers to reach consensus. Fourth, integrating the TWD process with prospect regret theory (P-RT) can reduce potential decision risks and identify the optimal solution. Finally, the model’s feasibility is demonstrated via a case study of UAV online reviews. In summary, the method not only addresses the challenge of handling high-dimensional data but also optimizes large-scale group decision-making (LSGDM), thereby providing effective decision support for purchasing UAVs.

{"title":"An incomplete three-way consensus algorithm for unmanned aerial vehicle purchase using optimization-driven sentiment analysis","authors":"Chao Zhang , Yating Wang , Arun Kumar Sangaiah , Mohammed J.F. Alenazi , Majed Aborokbah","doi":"10.1016/j.future.2025.107761","DOIUrl":"10.1016/j.future.2025.107761","url":null,"abstract":"<div><div>As a novel productive force in the low-altitude economy, the unmanned aerial vehicle (UAV) industry has emerged as a crucial engine of the digital economy growth. However, high-dimensional online reviews, incomplete information systems (IISs), and coordination among numerous sellers may influence the purchasing decision for UAVs. To address these challenges, first, the sentiment analysis (SA) of UAV online reviews is conducted using BiLSTM and BiGRU models optimized by the hippopotamus optimization (HO) algorithm. Meanwhile, the K-nearest neighbor (KNN) algorithm that combines the Jensen–shannon (JS) divergence with the Hellinger distance is applied to construct a complete information system (CIS). Second, three-way clustering (TWC) is performed on sellers, followed by the calculation of seller weights and group weights using the full consistency method. Third, to closely align with the behavior of sellers, a two-stage consensus reaching process (CRP) model based on TWC and the dual fine-tuning (DFT) theory is proposed, referred to as TWC-DFT-CCRP. In the first stage, the behavior of sellers is adjusted based on the TWC result. In the second stage, optimization-based rules are used to reduce the conflict degree among sellers to reach consensus. Fourth, integrating the TWD process with prospect regret theory (P-RT) can reduce potential decision risks and identify the optimal solution. Finally, the model’s feasibility is demonstrated via a case study of UAV online reviews. In summary, the method not only addresses the challenge of handling high-dimensional data but also optimizes large-scale group decision-making (LSGDM), thereby providing effective decision support for purchasing UAVs.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"168 ","pages":"Article 107761"},"PeriodicalIF":6.2,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143474372","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

Multigrain: Adaptive multilevel hot data identifier with a stack distance-based prefilter

IF 6.2 2区计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS

Future Generation Computer Systems-The International Journal of Escience

Pub Date : 2025-02-19 DOI: 10.1016/j.future.2025.107762

Hyerim Lee , Dongchul Park

Many computer system applications, such as data caching and Not AND (NAND) flash memory-based storage systems, employ a hot data identification scheme. However, regardless of the workload characteristics, most existing studies have adopted only a fine-grained (i.e., block-level) hot data decision policy, causing high computational overhead and error rates. Different workloads mandate different treatments to achieve effective hot data identification. Based on our comprehensive workload studies, this paper proposes Multigrain, an adaptive multilevel hot data identification scheme that dynamically selects a coarse-grained (i.e., subrequest-level) policy or coarser-grained (i.e., request-level) policy based on the workload. The proposed Multigrain employs multiple effective bloom filters to capture frequency and recency information. Moreover, it adopts a simple and smart prefilter mechanism leveraging workload stack distance information. To our knowledge, the proposed scheme is the first multilevel coarse-grained hot data identification scheme that judiciously selects an optimal hot data decision granularity to achieve effective and accurate identification. Our extensive experiments with many realistic workloads demonstrate that our adaptive multilevel scheme significantly reduces the execution time (by an average of up to 6.9

\times

) and error rate (by an average of up to 2.27

\times

) using the effective coarse-grained policies and a prefiltering mechanism.

{"title":"Multigrain: Adaptive multilevel hot data identifier with a stack distance-based prefilter","authors":"Hyerim Lee , Dongchul Park","doi":"10.1016/j.future.2025.107762","DOIUrl":"10.1016/j.future.2025.107762","url":null,"abstract":"<div><div>Many computer system applications, such as data caching and Not AND (NAND) flash memory-based storage systems, employ a hot data identification scheme. However, regardless of the workload characteristics, most existing studies have adopted only a fine-grained (i.e., block-level) hot data decision policy, causing high computational overhead and error rates. Different workloads mandate different treatments to achieve effective hot data identification. Based on our comprehensive workload studies, this paper proposes Multigrain, an <em>adaptive multilevel</em> hot data identification scheme that dynamically selects a coarse-grained (i.e., subrequest-level) policy or coarser-grained (i.e., request-level) policy based on the workload. The proposed Multigrain employs multiple effective bloom filters to capture frequency and recency information. Moreover, it adopts a simple and smart <em>prefilter mechanism</em> leveraging workload stack distance information. To our knowledge, the proposed scheme is the <em>first multilevel coarse-grained hot data identification scheme</em> that judiciously selects an optimal hot data decision granularity to achieve effective and accurate identification. Our extensive experiments with many realistic workloads demonstrate that our adaptive multilevel scheme significantly reduces the execution time (by an average of up to 6.9<span><math><mo>×</mo></math></span>) and error rate (by an average of up to 2.27<span><math><mo>×</mo></math></span>) using the effective coarse-grained policies and a prefiltering mechanism.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"167 ","pages":"Article 107762"},"PeriodicalIF":6.2,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143465148","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Future Generation Computer Systems-The International Journal of Escience

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀