The ideal Hopfield network would be able to remember information and recover the missing information based on what has been remembered. It is expected to have applications in areas such as associative memory, pattern recognition, optimisation computation, parallel implementation of VLSI and optical devices, but the lack of memory capacity and the tendency to generate pseudo-attractors make the network capable of handling only a very small amount of data. In order to make the network more widely used, we propose a scheme to optimise and improve its memory and resilience by introducing quantum perceptrons instead of Hebbian rules to complete its weight matrix design. Compared with the classical Hopfield network, our scheme increases the threshold of each node in the network while training the weights, and the memory space of the Hopfield network changes from being composed of the weight matrix only to being composed of the weight matrix and the threshold matrix together, resulting in a dimensional increase in the memory capacity of the network, which greatly solves the problem of the Hopfield network’s memory The problem of insufficient memory capacity and the tendency to generate pseudo-attractors was solved to a great extent. To verify the feasibility of the proposed scheme, we compare it with the classical Hopfield network in four different dimensions, namely, non-orthogonal simple matrix recovery, incomplete data recovery, memory capacity and model convergence speed. These experiments demonstrate that the improved Hopfield network with quantum perceptron has significant advantages over the classical Hopfield network in terms of memory capacity and recovery ability, which provides a possibility for practical application of the network.

In order to solve the common problems of high leakage rate of urban water supply network and controlling water supply enterprises, a multi index system of leakage evaluation is proposed. The first step in leakage assessment is to recommend non profitable water volume, rather than just based on the percentage of leakage rate (the calculation mode of percentage is easily disturbed by the change of water volume); Advanced indicators also need to consider factors such as pipe network conditions, pressure and the number of user connections; If possible, it is recommended to calculate the leakage index (ILI) of water supply network in line with international standards, and through this index, determine the leakage classification of water supply system according to the target matrix provided by the world bank, so as to formulate corresponding leakage control countermeasures, and finally form a set of leakage performance evaluation system of urban water supply system combined with the actual situation of our country. Experiments have proved that among users with large caliber and large water volume, the promotion of electromagnetic remote transmission water meter should be strengthened to improve the metering capacity of water meter. Since 2014, non household meters above Dn40 in the company's new household installation project have adopted electromagnetic remote transmission water meters. At the same time, strengthen the remote monitoring and management of large-diameter water meters. Through remote transmission, we can grasp the changes of users' water use in real time, and realize the three-level early warning of sudden change of water volume through the mining of remote transmission data.

With the development of computer network technology, people's demand for information security is increasing. However, the classical encryption technology has the defects of small key space and easy to be cracked. The problems of image encryption technology in protecting image information security and private content need to be solved urgently. As a new type of quantum key generator, quantum random walk has a large key space. Compared with the classical random walk, the computing speed and security are significantly improved. This paper presents a three-dimensional image encryption algorithm based on quantum random walk and involving Lorenz and Rossler multidimensional chaos. Firstly, Gaussian pyramid is used to segment the image; Secondly, the Hamming distance of several sub images is calculated by using the random sequence generated by quantum random walk and the random sequence generated by Lorenz chaotic system in multi-dimensional chaos, and then synthesized, and the Euclidean distance between the three RGB channels of the image is calculated; Finally, the sequence value obtained from the remainder of Hamming distance and Euclidean distance is input as the initial value into the Rossler system in multi-dimensional chaos to generate a random sequence as the key to XOR the RGB channel of the image to obtain the encrypted image. The corresponding decryption scheme is the inverse process of encryption process. In addition, in terms of transmission security, this paper uses the blind watermark embedding algorithm based on DCT and SVD to embed the watermark information into the encrypted image, so that the receiver can extract the watermark and judge whether the image is damaged by attack in the process of transmission according to the integrity of the watermark information. If it is not attacked maliciously, decrypt the image. This operation further improves the protection of image information security.The experimental results show that the peak signal-to-noise ratio of the encrypted image is stable between 7-9 and the encryption effect is good, the GVD score is close to 1, the correlation of the encrypted image is uniformly distributed, and the correlation coefficient is close to 0, and the key space 2¹²⁸ and the encrypted histogram is evenly distributed, and has a high ability to resist statistical analysis attacks.

No abstract