Particle swarm optimization (PSO) is a well-known optimization algorithm that shows good performances in solving different optimization problems. However, the PSO usually suffers from slow convergence. In this article, a reinforcement-learning-based parameter adaptation method (RLAM) is developed to enhance the PSO convergence by designing a network to control the coefficients of the PSO. Moreover, based on the RLAM, a new reinforcement-learning-based PSO (RLPSO) algorithm is designed. To investigate the performance of the RLAM and RLPSO, experiments on 28 CEC 2013 benchmark functions were carried out to compare with other adaptation methods and PSO variants. The reported computational results showed that the proposed RLAM is efficient and effective and that the proposed RLPSO is superior to several state-of-the-art PSO variants.

Based on recent research in artificial neural networks, researchers have focused on topics from brain-like computing based on the Von Neumann architecture to brain-inspired computing based on the integration of storage and calculation due to the large energy dissipation. Inspired by biological neural networks, people use superconducting devices, which have nonlinear dynamic characteristics, to construct synapse and neuron circuits. However, it is challenging to build large-scale superconducting spiking neural networks due to fan-ins and fan-outs of superconducting devices. In this paper, we present a criterion to scale up the superconducting neural network. Then, we present a three-layer fully connected superconducting spiking neural network construction scheme. Inspired by the biological neural network, we present a new training method based on frequency coding. After only 100 training iterations with one grayscale image of a digit, the learned three-layer fully connected superconducting spiking neural network has a recognition accuracy rate of 86.1% on the digit class. Moreover, the power dissipation of one spiking event in a superconducting synapse is $23.2{\bm{\ zJ}}$ , which shows that the network has outstandingly high efficiency over existing biologically inspired neural networks.

Currently, integrated humidity sensors with fast-response time are widely needed. The most commonly used polyimide capacitive humidity sensor has a long response time, which is difficult to meet the need for a fast response. Most studies focusing on technology and materials have a high cost and are difficult to ensure compatability with the CMOS process. The dynamic compensation method can shorten the response time by only adding digital circuits or software processing. However, conventional compensation technology is not suitable for humidity sensors due to temperature coupling. This paper proposes a new dynamic compensation method for humidity sensors based on the decoupling of temperature factors by analyzing the coupling relationship between sensor dynamic characteristics and temperature. Simulations and experiments were used to verify the proposed method. The experimental results show that the proposed method reduces the humidity response time of the sensor by 85.6%. The proposed method can effectively shorten the response time of humidity sensors.

The limited computing resources on edge devices such as Unmanned Aerial Vehicles (UAVs) mean that lightweight object detection algorithms based on convolution neural networks require significant development. However, lightweight models are challenged by small targets with few available features. In this paper, we propose an LC-YOLO model that uses detailed information about small targets in each layer to improve detection performance. The model is improved from the one-stage detector, and contains two optimization modules: Laplace Bottleneck (LB) and Cross-Layer Attention Upsampling (CLAU). The LB module is proposed to enhance shallow features by integrating prior information into the convolutional neural network and maximizing knowledge sharing within the network. CLAU is designed for the pixel-level fusion of deep features and shallow features. Under the combined action of these two modules, the LC-YOLO model achieves better detection performance on the small object detection task. The LC-YOLO model with a parameter quantity of 7.30M achieves an mAP of 94.96% on the remote sensing dataset UCAS-AOD, surpassing the YOLOv5l model with a parameter quantity of 46.61M. The tiny version of LC-YOLO with 1.83M parameters achieves 94.17% mAP, which is close to YOLOv5l. Therefore, the LC-YOLO model can replace many heavyweight networks to complete the small target high-precision detection task under limited computing resources, as in the case of mobile edge-end chips such as UAV onboard chips.

In password guessing, the Markov model is still widely used due to its simple structure and fast inference speed. However, the Markov model based on random sampling to generate passwords has the problem of a high repetition rate, which leads to a low cover rate. The model based on enumeration has a lower cover rate for high-probability passwords, and it is a deterministic algorithm that always generates the same passwords in the same order, making it vulnerable to attack. We design a dynamic distribution mechanism based on the random sampling method. This mechanism enables the probability distribution of passwords to be dynamically adjusted and tend toward uniform distribution strictly during the generation process. We apply the dynamic distribution mechanism to the Markov model and propose a dynamic Markov model. Through comparative experiments on the RockYou dataset, we set the optimal adjustment degree $\alpha$. Compared with the Markov model without the dynamic distribution mechanism, the dynamic Markov model reduced the repetition rate from 75.88% to 66.50% and increased the cover rate from 37.65% to 43.49%. In addition, the dynamic Markov model had the highest cover rate for high-probability passwords. Finally, the model avoided the lack of a deterministic algorithm, and when it was run five times, it reached almost the same cover rate as OMEN.