The inherent computational complexity of validating and verifying concurrent systems implies a need to be able to exploit parallel and distributedcomputing architectures. We present a new distributed algorithm for st...
详细信息
ISBN:
(纸本)9781665401623
The inherent computational complexity of validating and verifying concurrent systems implies a need to be able to exploit parallel and distributedcomputing architectures. We present a new distributed algorithm for state space exploration of concurrent systems on computing clusters. Our algorithm relies on Remote Direct Memory Access (RDMA) for low-latency transfer of states between computing elements, and on state reconstruction trees for compact representation of states on the computing elements themselves. For the distribution of states between computing elements, we propose a concept of state stealing. We have implemented our proposed algorithm using the OpenSHMEM API for RDMA and experimentally evaluated it on the Grid'5000 testbed with a set of benchmark models. The experimental results show that our algorithm scales well with the number of available computing elements, and that our state stealing mechanism generally provides a balanced workload distribution.
Improving network performances to better support Cooperative Intelligent Transport systems (C-ITS) services has been the subject of renewed efforts by academia and industry. To this end, the availability of multiple i...
详细信息
ISBN:
(纸本)9781665467490
Improving network performances to better support Cooperative Intelligent Transport systems (C-ITS) services has been the subject of renewed efforts by academia and industry. To this end, the availability of multiple in-vehicle radio access technologies (RATs) has been exploited. In this paper, we propose a distributed and Context Aware Radio access Technology selection (DICART) framework for vehicular networks, formulated as Multi-Criteria Decision-Making (MCDM) problem. A validation methodology is then conducted based on OMNET++ full-stack network simulator to prove the effectiveness of DI CART. Results show the benefits of our proposal under low and high density network configurations, in enhancing network performance perceived by end-users while considering the needs and constraints of used services.
Military tactical scenarios have been shifting to more often consider combat situations in urban environments. Threats in these environments are generally more dynamic in nature, imposing new requirements on sensors a...
详细信息
ISBN:
(纸本)9798350342734
Military tactical scenarios have been shifting to more often consider combat situations in urban environments. Threats in these environments are generally more dynamic in nature, imposing new requirements on sensors and communications systems that support military operations. Wireless sensor networks (WSNs) with a large number of small and mobile computing nodes became the typical solution. However, WSNs demand additional complexity to dynamically manage their tasks, resource allocation, mobility, power consumption, and communication. This paper illustrates the integration of AI techniques into a Battle Management System (BMS) to support military operations in urban environments. The BMS is enhanced with an AI-based planner able to plan tasks, allocate resources, and monitor the WSN operation. The planner takes into consideration energy harvesting capabilities, secure data transfer, and authorization procedures. It generates plans using the information received from the sensors. In case new situations emerge, based on data fusion information, it automatically replans to adapt to the uncertainty in the environment. Finally, it takes into account the coverage between the different components to optimize the communications and better support WSN's operator(s) and their activities.
Federated learning (FL) has become a hot research domain due to its privacy protection for model collaboratively training in edge computingsystems. However, recent studies indicated that most FL algorithms have despe...
详细信息
ISBN:
(纸本)9781538674628
Federated learning (FL) has become a hot research domain due to its privacy protection for model collaboratively training in edge computingsystems. However, recent studies indicated that most FL algorithms have desperately suffered from backdoor attacks. Although many backdoor defence FL algorithms were proposed, their effects were highly related to the ratio of malicious clients (RMC) of all participated edge nodes. To be more specific, most of them only set RMC around 10% to 30% in their experiments, and their results also showed that the rate of successful backdoor defence seriously drops when RMC increases. In the paper, we propose a novel federated learning scheme with mode connectivity (FedMC) to defend against backdoor attacks, mitigating the sharp defence effect degradation as RMC increases. Conventional mode connectivity mainly focuses on training a connecting curve between two end models, which is inapplicable in distributed multiple clients FL situations. We extend the two-ends mode connectivity to multi-ends by introducing a scalable regularization term consisting of the edge clients' models to involve their knowledge in the connective model training. In each communication round, the FL-Server aggregates and absorbs the contribution of clients by training a connective model based on a small set of clean samples, which builds a pathway to accurately connect all edge clients' models and mitigates the backdoor triggers of models. Extensive experiments and results demonstrate that FedMC can effectively defend against backdoor attacks while maintaining the accuracy on untampered test data.
Mobile Crowd Sensing (MCS) is an innovative technology that ensuring data security and privacy is critical to encouraging user participation and maintaining system reliability. Zhu et al. proposed a privacy-preserving...
详细信息
In the aquaculture industry, maintaining optimal water quality is imperative for the health and productivity of aquatic species such as prawns and pearl spot fish. Wireless sensor Networks (WSNs) have emerged as a pro...
详细信息
In recent years, the rapid global climate change has resulted in frequent urban flooding disasters. The phenomenon of blocked drain covers in urban areas directly affects the passage of vehicles and pedestrians, causi...
详细信息
Wireless Rechargeable sensor Nodes (WRSNs) are widely used to sense, collect, and process data or signals transmitted among people, the environment, and computer systems. However, it faces severe threats such as conge...
详细信息
The global COVID-19 pandemic has put a strain on the healthcare system, further compounded by the aging population and the staffing shortage. As a result, the demand for healthcare exceeds the available offer, and hea...
详细信息
Indoor environmental comfort has become increasingly important, necessitating occupant-centric systems that provide personalized comfort. This trend is particularly notable in light of the increasing frequency of extr...
详细信息
ISBN:
(纸本)9783031600111;9783031600128
Indoor environmental comfort has become increasingly important, necessitating occupant-centric systems that provide personalized comfort. This trend is particularly notable in light of the increasing frequency of extreme weather events associated with global climate change. This paper proposes a novel framework integrating real-time occupant feedback, multi-sensor data fusion, online modeling, and intelligent sensor technologies to dynamically tailor indoor microenvironments. The framework collects diverse data on built environment and personal health using environmental sensors and wearable devices. It employs online machine learning algorithms to analyze the database and automatically adjust environmental conditions in real-time to match occupants' preferences. In implementing this framework, advanced encryption are utilized to enable swift, localized data processing while preserving privacy. Multi-sensor fusion techniques are leveraged to integrate heterogeneous sensor data into an accurate assessment of occupant comfort. The user interface facilitates occupant feedback to continuously refine the system's reinforcement learning model. By personalizing comfort in a responsive, privacy-aware manner, this framework is expected to enhance occupant well-being and satisfaction, potentially enabling significant energy savings by avoiding overcooling and overheating. The framework represents an innovative application of smart and computing technologies, including deep learning and data fusion, to advance beyond static environmental setpoints. In anticipation of testing, it shows promise in revolutionizing occupant-centric comfort, fostering the creation of more adaptive and resilient indoor spaces.
暂无评论