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...

Reinforcement Learning for Safe Robot Control using Control Lyapunov Barrier Functions

Reinforcement learning (RL) exhibits impressive performance when managing complicated control tasks for robots. However, its wide application to physical robots is limited by the absence of strong safety guarantees. To overcome this challenge, this paper explores the control Lyapunov barrier function (CLBF) to analyze the safety and reachability...

A Ring-Oscillator Sub-Sampling PLL With Hybrid Loop Using Generator-Based Design Flow

We present a ring-oscillator-based sub-sampling phase-locked loop (PLL) using a generator-based design flow. A hybrid loop with a delta-sigma ($\Delta \Sigma$) modulator is applied to reduce the loop filter (LF) area and the control ripple. The generator automatically produces the ring oscillator and PLL to meet the provided specifications. The...

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...

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...

The smart releasing behavior of a microcapsule based on chemical self-healing system caused by chemical trigger activation

A novel chemical self-healing system based on microcapsule technology for cementitious composites is established in Guangdong Key Laboratory of Durability for Coastal Civil Engineering, Shenzhen University. The key issue of this system is how to release the healing material and how to activate the healing mechanism. In this paper, the study is...

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...

A study on the steel corrosion protection of a microcapsule based self-healing cementitious system by means of electrochemical impedance spectroscopy

Based on microcapsule technology, a new type of self-healing system for cementitious composites is established. The performance of the system was characterized by means of electrochemical impedance spectroscopy of steel bars immersed in a simulated concrete environment. The results demonstrate strong inhibition of chloride-induced corrosion when...