Echo state network (ESN) as a novel artificial neural network has drawn much attention from time series prediction in edge intelligence. ESN is slightly insufficient in long-term memory, thereby impacting the prediction performance. It suffers from a higher computational overhead when deploying on edge devices. We firstly introduce the knowledge distillation into the reservoir structure optimization, and then propose the echo state network based on improved knowledge distillation (ESN-IKD) for edge intelligence to improve the prediction performance and reduce the computational overhead. The model of ESN-IKD is constructed with the classic ESN as a student network, the long and short-term memory network as a teacher network, and the ESN with double loop reservoir structure as an assistant network. The student network learns the long-term memory capability of the teacher network with the help of the assistant network. The training algorithm of ESN-IKD is proposed to correct the learning direction through the assistant network and eliminate the redundant knowledge through the iterative pruning. It can solve the problems of error learning and redundant learning in the traditional knowledge distillation process. Extensive experimental simulation shows that ESN-IKD has a good time series prediction performance in both long-term and short-term memory, and achieves a lower computational overhead.
Payment Channel Network (PCN) provides the off-chain settlement of transactions. It is one of the most promising solutions to solve the scalability issue of the blockchain. Many routing techniques in PCN have been proposed. However, both incentive attack and privacy protection have not been considered in existing studies. In this paper, we present an auction-based system model for PCN routing using the Laplace differential privacy mechanism. We formulate the cost optimization problem to minimize the path cost under the constraints of the Hashed Time-Lock Contract (HTLC) tolerance and the channel capacity. We propose an approximation algorithm to find the top
We consider the extrema estimation problem in large-scale radio-frequency identification (RFID) systems, where there are thousands of tags and each tag contains a finite value. The objective is to design an extrema estimation protocol with the minimum execution time. Because the standard binary search protocol wastes much time due to interframe overhead, we propose a parameterized protocol and treat the number of slots in a frame as an unknown parameter. We formulate the problem and show how to find the best parameter to minimize the worst-case execution time. Finally, we propose two rules to further reduce the execution time. The first is to find and remove redundant frames. The second is to concatenate a frame from minimum value estimation with a frame from maximum value estimation to reduce the total number of frames. Simulations show that, in a typical scenario, the proposed protocol reduces execution time by 79% compared with the standard binary search protocol.