The increasing computational capabilities of Low Earth Orbit (LEO) constellations have significantly augmented their autonomy and operational flexibility. Complex onboard tasks such as observation, sensing, and situat...
详细信息
The increasing computational capabilities of Low Earth Orbit (LEO) constellations have significantly augmented their autonomy and operational flexibility. Complex onboard tasks such as observation, sensing, and situational awareness can be processed and executed directly on the Satellite Edge Computing (SEC) networks. to the time-varying characteristics of inter-satellite links and the uncertainty in the load of edge satellites, efficient offloading of on-board tasks presents significant challenges. We introduce an on-board distributed task offloading method for LEO satellite tasks in emergency to enhance service quality. We initially a dynamic offloading scheme, in which data-source satellites can transmit tasks to edge nodes. Then, formulate the multi-hop satellite network dynamic offloading (MSNDO) problem to minimize system and maximize success ratio of time-sensitive tasks under multiple constraints. Finally, we propose a distributed deep reinforcement learning algorithm that allows individual satellites to design offloading strategies knowing the decision-making patterns of other satellites. Simulation experiments show that the proposed algorithm can utilize the edge satellite processing capabilities more efficiently and significantly improve performance of the SEC system.
Wireless Sensor networks (WSNs) are constrained by the limited energy capacity of Sensor Nodes (SNs), which hinders their perpetual operation. The advent of Wireless Energy Transfer (WET) technology has emerged as a p...
详细信息
An important branch of artificial intelligence systems and architectures is Capsule networks (CapsNets) have been known extremely large amount of parameters and computation because of the complex capsule routing algor...
详细信息
We address the problem of enforcing global invariants, i.e., system-level properties, in Collective Adaptive systems, such as distributed and decentralized Internet of Things (IoT) solutions. In particular, we propose...
详细信息
ISBN:
(纸本)9783031751066;9783031751073
We address the problem of enforcing global invariants, i.e., system-level properties, in Collective Adaptive systems, such as distributed and decentralized Internet of Things (IoT) solutions. In particular, we propose a novel approach adopting Attribute-based memory Updates (AbU), a calculus modeling declarative, event-driven systems with attribute-based communication. Our methodology leverages a combination of precise node-level scheduling and local reasoning, with local invariants derived from the system-level property to guarantee. This distributed and decentralized approach promotes efficient enforcing while ensuring desired system-wide behavior, without the need for a central controlling authority.
As satellite network communication systems become an increasingly pivotal role in modern life, The routine maintenance of satellite networks is challenging due to limited resources and their susceptibility to interfer...
详细信息
This paper proposes enhancing urban traffic management by integrating traffic signals into the SCATS system and developing a distributed control algorithm. The expected benefits include reduced congestion, improved ro...
详细信息
ISBN:
(纸本)9783031809453;9783031809460
This paper proposes enhancing urban traffic management by integrating traffic signals into the SCATS system and developing a distributed control algorithm. The expected benefits include reduced congestion, improved road safety, and environmental sustainability. Scientifically, the research introduces innovative algorithms and integrates new features into existing systems, offering a scalable solution for urban traffic management. The study aims to optimise traffic flow and reduce travel times, ultimately improving quality of life in urban areas. The proposed approach promises efficient and sustainable urban mobility by dynamically adjusting to real-time traffic conditions. The system responds quickly to traffic conditions through collaborative coordination of traffic signals and autonomous decision-making, allowing effective urban traffic management. This research contributes to both practical applications and theoretical understanding, promising significant advances in urban traffic management practices.
Designing effective and user-friendly Human-Machine Interfaces for simulators can be a complex endeavor that requires adherence to guidelines established through decades of research. The inherent complexity of the sys...
详细信息
In the domain of image annotation, the involvement of human annotators presents a series of intricate challenges tied to the complexities of visual perception. The manual labeling process demands an understanding of c...
详细信息
ISBN:
(纸本)9783031809453;9783031809460
In the domain of image annotation, the involvement of human annotators presents a series of intricate challenges tied to the complexities of visual perception. The manual labeling process demands an understanding of context and visual intricacies, all susceptible to human subjectivity. Furthermore, the presence of visual distractions compromises annotation quality, not only impeding annotation precision but also escalating time expenditures as annotators navigate through visual noise to discern pertinent details. Traditional image annotation pipelines underscore these challenges in favor of automatic or semiautomatic annotation, emphasizing the critical necessity for innovative approaches in annotation tasks where the human annotator role is fundamental. Within this context, the Grounded SAM model, emerges as a potent tool for text-prompt-based panoptic segmentation. This paper proposes a novel annotation pipeline employing Grounded SAM and LaMa cleaner models to augment the indispensable role of human annotators by enhancing annotation efficiency through natural language-based attention mining for visual distractions elimination and preannotation techniques. The effectiveness of distraction elimination is demonstrated through an annotation task involving human annotators, with half of the images processed through our pipeline and the remaining unmodified. With our current approach and with the current data analyzed, image annotation times of 70% of the annotators were reduced by 15.88%, while global annotation time was reduced by a 6.93%.
Nowadays, energy buildings have a huge impact in society regarding the active role in the management of energy consumption. Hence, building owners are required to avoid energy losses and improve energy efficiency as h...
详细信息
ISBN:
(纸本)9783031820724;9783031820731
Nowadays, energy buildings have a huge impact in society regarding the active role in the management of energy consumption. Hence, building owners are required to avoid energy losses and improve energy efficiency as high as possible. Therefore, it is required to plan an optimization strategy to buy and sell energy in the market ahead of time. To formulate this optimization plan, building owners require the work of specialists responsible for processing, training, forecasting, and evaluation tasks regarding the prediction of energy consumption data from a building for a specific target of time. Therefore, a multiagent-system is needed to allow the cooperation of various agents including the building owner, forecast provider, data structurer and error analysis. Moreover, forecasting algorithms such as artificial neural networks should be taken into consideration in order to process large quantities of energy consumption data during the training and forecasting phases.
POSIT offers a wider dynamic range when compared to floating-point (FP) formats with lesser number of bits. Such data formats are required to address the need for low-bit high-precision hardware architectures for neur...
详细信息
ISBN:
(纸本)9798350330991;9798350331004
POSIT offers a wider dynamic range when compared to floating-point (FP) formats with lesser number of bits. Such data formats are required to address the need for low-bit high-precision hardware architectures for neural networks (NNs) on edge platforms. Activation functions (Af) which introduce non-linearity during the feature extraction process remain as a core component for realizing NN systems. CORDIC (COordinate Rotation Digital computer) architecture is a hardware efficient technique to realize complex non-linear functions and is deemed suitable to implement Afs. Hence, this work aims to investigate POSIT data formatted CORDIC architecture to realize Afs (Tanh, Sigmoid and Softmax) in different architectural styles. A benchmark evaluation for the proposed POSIT data formatted Afs with the improved CORDIC architecture over SOTA (IEEE 754 FP formats) based designs are presented. The noticeable improvement in hardware design space and error metrics makes the CORDIC architecture-based POSIT formatted Afs stand out over other methods. All the design files are made publicly available for easy adoption and further usage to the designers' and researchers' community.
暂无评论