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...

A Self Bias-flip Piezoelectric Energy Harvester Array without External Energy Reservoirs achieving 488% Improvement with 4-Ratio Switched-PEH DC-DC Converter

With the advent of the lnternet-of-Things (1oT) era, sensor nodes are required in almost all fields to achieve a better interaction between humans and the environment. Piezoelectric energy harvester (PEH), which exhibits an equivalent electrical model of an AC current source /P in parallel with the inherent capacitor CP, is a promising...

EdgeTuner: Fast Scheduling Algorithm Tuning for Dynamic Edge-Cloud Workloads and Resources

Edge-cloud jobs are rapidly prevailing in many application domains, posing the challenge of using both resource-strenuous edge devices and elastic cloud resources. Efficient resource allocation on such jobs via scheduling algorithms is essential to guarantee their performance, e.g. latency. Deep reinforcement learning (DRL) is increasingly...

Hydration behaviour of magnesium ammonium phosphate cement and stability analysis of its hydration products through thermodynamic modelling

Magnesium ammonium phosphate cement (MAPC) has been commonly applied in civil engineering. However, the analysis of hydration behavior and composition of solid assemblages still needs further exploration. From thermodynamic simulation, it is shown that the molar ratio between MgO and NH4H2PO4 (M/P ratio) determines the final composition of...