Within the last decade, e-commerce has increased at an extraordinary level. The widespread use of Unmanned Aerial Vehicles (VAVs) in the logistics sector can reduce traffic density, improve delivery time, and can prov...
详细信息
In traditional federated learning, a single global model cannot perform equally well for all clients. Therefore, the need to achieve the client-level fairness in federated system has been emphasized, which can be real...
In traditional federated learning, a single global model cannot perform equally well for all clients. Therefore, the need to achieve the client-level fairness in federated system has been emphasized, which can be realized by modifying the static aggregation scheme for updating the global model to an adaptive one, in response to the local signals of the participating clients. Our work reveals that existing fairness-aware aggregation strategies can be unified into an online convex optimization framework, in other words, a central server's sequential decision making process. To enhance the decision making capability, we propose simple and intuitive improvements for suboptimal designs within existing methods, presenting AAggFF. Considering practical requirements, we further subdivide our method tailored for the cross-device and the cross-silo settings, respectively. Theoretical analyses guarantee sublinear regret upper bounds for both settings: O(√T log K) for the cross-device setting, and O(K log T) for the cross-silo setting, with K clients and T federation rounds. Extensive experiments demonstrate that the federated system equipped with AAggFF achieves better degree of client-level fairness than existing methods in both practical settings. Code is available at https://***/vaseline555/AAggFF.
The manufacturing industry is undergoing a major transformation based on the emerging industry 4.0 technologies, such as cloud computing, big data, internet of things and cyber-physical systems. These novelty technolo...
详细信息
With the widespread application of 5G and artificial intelligence (AI) technology, the Internet of Things (IoT) has been expanding and integrated into various aspects of our daily lives. However, this also poses chall...
详细信息
Reliable classification of sleep stages is crucial in sleep medicine and neuroscience research for providing valuable insights, diagnoses, and understanding of brain states. The current gold standard method for sleep ...
详细信息
Supervised learning in function spaces is an emerging area of machine learning research with applications to the prediction of complex physical systems such as fluid flows, solid mechanics, and climate modeling. By di...
ISBN:
(纸本)9781713871088
Supervised learning in function spaces is an emerging area of machine learning research with applications to the prediction of complex physical systems such as fluid flows, solid mechanics, and climate modeling. By directly learning maps (operators) between infinite dimensional function spaces, these models are able to learn discretization invariant representations of target functions. A common approach is to represent such target functions as linear combinations of basis elements learned from data. However, there are simple scenarios where, even though the target functions form a low dimensional submanifold, a very large number of basis elements is needed for an accurate linear representation. Here we present NOMAD, a novel operator learning framework with a nonlinear decoder map capable of learning finite dimensional representations of nonlinear submanifolds in function spaces. We show this method is able to accurately learn low dimensional representations of solution manifolds to partial differential equations while outperforming linear models of larger size. Additionally, we compare to state-of-the-art operator learning methods on a complex fluid dynamics benchmark and achieve competitive performance with a significantly smaller model size and training cost.
Anion detection gain wide interest because anions play important roles in many fields. Microfluidic paper analytical devices (μPADs) are promising for monitoring anions due to their low cost, short time analysis, and...
详细信息
Enhancing disaster awareness and preparedness is crucial for building resilient societies. This study comprehensively assessed the levels of disaster awareness and preparedness among children and adults in Thailand th...
详细信息
ISBN:
(数字)9798350353952
ISBN:
(纸本)9798350353969
Enhancing disaster awareness and preparedness is crucial for building resilient societies. This study comprehensively assessed the levels of disaster awareness and preparedness among children and adults in Thailand through qualitative and quantitative surveys. Children strongly emphasized the importance of disaster education in school curricula, leveraging multimedia channels for risk communication, and implementing early warning systems. In contrast, adults exhibited a greater understanding of the significance of business continuity and disaster management technologies. These findings revealed disparities in disaster awareness across age groups. The insights from this study suggest age-specific engineering system approaches to information dissemination, contributing to the development of inclusive disaster preparedness strategies that incorporate diverse stakeholder perspectives. Children highlighted the need for practical training on survival skills, accessible disaster communication through SMS alerts, and monitoring systems for timely information dissemination. Adults, on the other hand, placed greater importance on business continuity planning and recognized the usefulness of technologies like satellite imagery for disaster management. By identifying these gaps and areas for improvement, this research provides valuable guidance for tailoring interventions, fostering a culture of preparedness, and harnessing technological solutions that resonate with the needs and concerns of different age cohorts within Thai society.
This study embarked on a rigorous examination of the factors driving user satisfaction and usage behavior in the context of telehealth applications. Utilizing a well- structured Google Form survey, distributed through...
This study embarked on a rigorous examination of the factors driving user satisfaction and usage behavior in the context of telehealth applications. Utilizing a well- structured Google Form survey, distributed through an array of social media platforms, including WhatsApp, Discord, Instagram, and Line, the research gathered 251 responses. The purposive sampling technique was employed to ensure that the data captured the experiences of individuals who had actively engaged with telehealth services. One hypothesis, relating to the influence of Online Reviews, was found to be unsupported. This surprising result suggests that, contrary to expectations, the opinions and reviews shared online do not significantly affect users’ satisfaction or their behavioral decisions in the context of telehealth applications. This finding highlights the need for a more nuanced understanding of the factors influencing user preferences and choices in this rapidly evolving sector. Conversely, other hypotheses examining factors such as Social Influence, Facilitating Conditions, Perceived Reliability, Price Value, and Purchase Intention were substantiated. The positive influence of these factors on customer usage behavior underscores their significance in shaping user experiences and satisfaction within the telehealth ecosystem. Furthermore, the study posits that facilitating conditions should be closely aligned with technological advancements, as this alignment is conducive to the development of enhanced application features. This insight suggests that telehealth providers should continuously innovate and integrate advanced technologies to ensure that the facilitating conditions meet the ever-evolving needs and expectations of users.
Atomic-layer-deposited (ALD) zinc-tin-oxide (ZTO) thin films offer promising electronic properties for many applications, but their development has been limited by their tendency to experience significant nucleation d...
详细信息
暂无评论