FedViT: Federated continual learning of vision transformer at edge

Deep Neural Networks (DNNs) have been ubiquitously adopted in internet of things and are becoming an integral part of our daily life. When tackling the evolving learning tasks in real world, such as classifying different types of objects, DNNs face the challenge to continually retrain themselves according to the tasks on different edge...

Integrating the flow regime and water quality effects into a niche-based metacommunity dynamics model for river ecosystems

Aquatic community dynamics are closely dominated by flow regime and water quality conditions, which are increasingly threatened by dam regulation, water diversion, and nutrition pollution. However, further understanding of the ecological impacts of flow regime and water quality conditions on aquatic multi-population dynamics has rarely been...

FedKNOW: Federated Continual Learning with Signature Task Knowledge Integration at Edge

Deep Neural Networks (DNNs) have been ubiquitously adopted in internet of things and are becoming an integral of our daily life. When tackling the evolving learning tasks in real world, such as classifying different types of objects, DNNs face the challenge to continually retrain themselves according to the tasks on different edge devices....

EdgeVisionBench: A Benchmark of Evolving Input Domains for Vision Applications at Edge

Vision applications powered by deep neural networks (DNNs) are widely deployed on edge devices and solve the learning tasks of incoming data streams whose class label and input feature continuously evolve, known as domain shift. Despite its prominent presence in real-world edge scenarios, existing benchmarks used by domain adaptation methods...

Inter-Vector Interference Self-Cancellation Scheme for Differential OSDM in Underwater Acoustic Communications

Differential orthogonal signal-division multiplexing (OSDM) is attractive for underwater acoustic (UWA) communications because it can eliminate channel estimation, resulting in a substantial reduction of complexity at the receiver. However, when the channel is time-varying, it may suffer from serious inter-vector interference (IVI), which is...

Lightweight and Accurate DNN-Based Anomaly Detection at Edge

Deep neural networks (DNNs) have been showing significant success in various anomaly detection applications such as smart surveillance and industrial quality control. It is increasingly important to detect anomalies directly on edge devices, because of high responsiveness requirements and tight latency constraints. The accuracy of DNN-based...

Determinants of villagers’ satisfaction with post-disaster reconstruction: Evidence from surveys ten years after the Wenchuan earthquake

Residents’ satisfaction with post-disaster reconstruction in earthquake-stricken areas directly affects their quality of life, which cannot be ignored in post-disaster reconstruction. More than 10 years after the Wenchuan earthquake, we took ten randomly selected villages in the five areas hardest-hit by the Wenchuan earthquake as research...

Temperature-sensing performance of polymer-derived SiAlCN ceramics up to 1000 °C

Temperature sensors that can operate in high-temperature and harsh environments are highly desired. However, this is a great challenge for sensing materials to operate under extreme working conditions because of oxidation and/or corrosion at high temperature. In this study, polymer-derived SiAlCN ceramics were prepared as sensing materials to...

Reinforcement learning control of constrained dynamic systems with uniformly ultimate boundedness stability guarantee

Reinforcement learning (RL) is promising for complicated stochastic nonlinear control problems. Without using a mathematical model, an optimal controller can be learned from data evaluated by certain performance criteria through trial-and-error. However, the data-based learning approach is notorious for not guaranteeing stability, which is...

New innovations in pavement materials and engineering: A review on pavement engineering research 2021

Sustainable and resilient pavement infrastructure is critical for current economic and environmental challenges. In the past 10 years, the pavement infrastructure strongly supports the rapid development of the global social economy. New theories, new methods, new technologies and new materials related to pavement engineering are emerging....

Knitting 4D garments with elasticity controlled for body motion

In this paper, we present a new computational pipeline for designing and fabricating 4D garments as knitwear that considers comfort during body movement. This is achieved by careful control of elasticity distribution to reduce uncomfortable pressure and unwanted sliding caused by body motion. We exploit the ability to knit patterns in...

Time-domain oversampled orthogonal signal-division multiplexing underwater acoustic communications

Orthogonal signal-division multiplexing (OSDM) is a recently emerging modulation scheme which, compared to conventional orthogonal frequency-division multiplexing, can effectively lower the peak-to-average power ratio and introduce intra-vector frequency diversity. In this paper, a time-domain oversampled OSDM system for underwater acoustic ...

Experimental Study on Cementitious Composites Embedded with Organic Microcapsules

The recovery behavior for strength and impermeability of cementitious composites embedded with organic microcapsules was investigated in this study. Mortar specimens were formed by mixing the organic microcapsules and a catalyst with cement and sand. The mechanical behaviors of flexural and compression strength were tested. The results showed...

Interaction between microcapsules and cementitious matrix after cracking in a self-healing system

A new type of self-healing cementitious composites by using organic microcapsules is designed in Guangdong Key Laboratory of Durability for Coastal Civil Engineering, Shenzhen University. For the organic microcapsules, the shell material is urea formoldehyde (UF), and the core healing agent is Epoxy. The effect of organic microcapsules on...

Design of microcapsule system used for self-healing cementitious material

For a microcapsule based self-healing system in the cementitious material, a fundamental issue is to find and facilitate a suitable microcapsule system, concerning either the material selection or design and manufacture process. In this study, urea formaldehyde resin is used for the shell of microcapsule, and bisphenol – an epoxy resin E-51...

Evaluation of a microcapsule based self-healing system for cementitious materials

An international cooperation research project has been financially supported by China Nature Science Foundation, which consists of three relatively independent, but strategically integrated research sub-programs, aiming at the formation of a selfhealing system based on the microcapsule principle for the cementitious composites. In this paper, a...

Evaluation of a microcapsule based self-healing system for cementitious materials

An international cooperation research project has been financially supported by China Nature Science Foundation, which consists of three relatively independent, but strategically integrated research sub-programs, aiming at the formation of a selfhealing system based on the microcapsule principle for the cementitious composites. In this paper, a...

Interaction between microcapsules and cementitious matrix after cracking in a self-healing system

A new type of self-healing cementitious composites by using organic microcapsules is designed in Guangdong Key Laboratory of Durability for Coastal Civil Engineering, Shenzhen University. For the organic microcapsules, the shell material is urea formoldehyde (UF), and the core healing agent is Epoxy. The effect of organic microcapsules on...