No abstract

No abstract

In order for the pre-coding technology to suppress the influence of pilot contamination, a hybrid pre-coding scheme is proposed in this paper by combining a full-digital pre-coding technology and an analog beamforming in the context of current massive MIMO. Simulation results show that the proposed pre-coding scheme effectively suppresses the pilot contamination while reducing the system structure complexity and ensuring the system’s basic performance, which is of important significance in practical communication applications.

In today's leaf disease detection, the accuracy of recognition has never been of such importance as it is now. In this aspect, leaf disease recognition method based on machine learning relies heavily on the size of the region of interest and the dispersion of lesions. Professional instrument for leaf disease detection remains a challenging task in accuracy and convenience. A new lightweight model based on advanced residual network and attention mechanism for extracting more accurate region of interest and the lesion, SE-VRNet, was proposed. The proposed SE-VRNet incorporated deep variant residual network (VRNet) and a squeeze-and-excitation (SE) module with attention mechanism, in order to solve the problem that the feature extraction was difficult due to the dispersed location of the leaf disease. The accuracy of top-1 and top-3 obtained by the model SE-VRNet on NewData is 99.73% and 99.98%, respectively, and the accuracy of top-1 and top-3 obtained by the model on SelfData is 95.71% and 99.89%, respectively. The experimental results on the datasets of PlantVillage, OriData, NewData and SelfData were better than other state-of-theart methods, demonstrating the effectiveness and feasibility of the proposed SE-VRNet in identifying leaf diseases with mobile devices.

An image encryption algorithm based on Kronecker inner product matrix over the finite field and adversarial neural network (ANN) is designed. The Kronecker inner product matrix transform and the ANN fulfil the tasks of confusion and diffusion simultaneously. In addition, the look-up table method is used to complete the addition and multiplication operations over GF(2 B ) finite fields, which can effectively improve the finite field computation speed while retaining its performance of non rounding errors. At the same time, relying on the secure hash function SHA-256 of the plain image to control the Logistic-Sine map greatly improves the diffusion and security of the encryption system. The simulation results verify that the proposed algorithm not only has high security and sufficient sensitivity, but also has a good resistance to various common attacks.