With the development of recent years, the field of deep learning has made great progress. Compared with the traditional machine learning algorithm, deep learning can better find the rules in the data and achieve better fitting effect. In this paper, we propose a hybrid stock forecasting model based on Feature Selection, Convolutional Neural Network and Bidirectional Gated Recurrent Unit (FS-CNN-BGRU). Feature Selection (FS) can select the data with better performance for the results as the input data after data normalization. Convolutional Neural Network (CNN) is responsible for feature extraction. It can extract the local features of the data, pay attention to more local information, and reduce the amount of calculation. The Bidirectional Gated Recurrent Unit (BGRU) can process the data with time series, so that it can have better performance for the data with time series attributes. In the experiment, we used single CNN, LSTM and GRU models and mixed models CNN-LSTM, CNN-GRU and FS-CNN-BGRU (the model used in this manuscript). The results show that the performance of the hybrid model (FS-CNN-BGRU) is better than other single models, which has a certain reference value.

Digital image transmission plays a very significant role in information transmission, so it is very important to protect the security of image transmission. Based on the analysis of existing image encryption algorithms, this article proposes a new digital image encryption algorithm based on the splicing model and 1D secondary chaotic system. Step one is the algorithm of this article divides the plain image into four sub-parts by using quaternary coding, and these four sub-parts can be coded separately. Only by acquiring all the sub-parts at one time can the attacker recover the useful plain image. Therefore, the algorithm has high security. Additionally, the image encryption scheme in this article used a 1D quadratic chaotic system, which makes the key space big enough to resist exhaustive attacks. The experimental data show that the image encryption algorithm has high security and a good encryption effect.

To ensure the safe and reliable transmission of images on public channels, this paper proposes a dual-domain image encryption algorithm based on hyperchaos and dynamic wavelet decomposition. The combination of dynamic wavelet decomposition and scrambling and diffusion operations is adopted in our algorithm to realize the combination of spatial and frequency domain encryption. This not only ensures the security of the encryption algorithm, but also ensures the robustness and operating efficiency of the encryption, and at the same time reduces the risk of being attacked. First, divide the original image into blocks, use a random number sequence to control the block scrambling process, and generate a scrambling matrix; Then by calculating the Hamming distance related to the plaintext, dynamically selecting the wavelet type, performing wavelet decomposition, and generating a wavelet coefficient matrix; Re-input the plaintext image to the SHA-512 algorithm to generate the initial value of the hyperchaos. The chaotic system generates the chaotic key matrix through iteration; Then the scrambling matrix is dynamically rotated, and then the Zigzag transform is used to generate the key matrix; Finally, the wavelet coefficient matrix, the chaotic key matrix, and the key matrix are subjected to bitwise XOR operation to realize the diffusion of pixel values and obtain the final encrypted image. Simulation experiments and performance analysis experiments can show that this algorithm can effectively encrypt and decrypt images, and has good encryption and decryption quality, and the ability to resist various attacks.

Sparrow search algorithm (SSA) suffers from a tendency to fall into local optima, as well as a preference for zero locations. Therefore, to improve this drawback, we propose a non-uniform mutation sparrow search algorithm (NMSSA). In the initialization stage of the population, we introduce a tent chaos map and a generalized opposition-based learning strategy to improve the diversity of the population; We introduce adaptive weight to dynamically adjust the search range of the discoverer to improve the search efficiency of the algorithm; To prevent the algorithm from deviating from the target in the early stage, we adopt a non-uniform mutation strategy to improve the flexibility of the follower search to improve the convergence accuracy of the algorithm. Finally, we use the somersault strategy to reduce the probability of the algorithm falling into local optimum. In the test experiments with 10 benchmark functions and CEC2017 functions, we compare the experimental results of NMSSA with those of other algorithms, and the experimental results verify the effectiveness of NMSSA. In addition, we also applied NMSSA to engineering problems optimization and K-means image segmentation, and the experimental results show that NMSSA has good performance in practical applications.

In modern engineering construction, the compressive strength of concrete determines the safety of engineering structure. BP neural network (BPNN) tends to converge to different local minimum points, and the prediction accuracy is not high in the prediction of the compressive strength of concrete. Therefore, a prediction model based on the BPNN optimized by improved sparrow search algorithm (ISSA) and random forest (RF) is proposed to enhance the generalization ability and prediction accuracy of BPNN for compressive strength of concrete. In terms of algorithm improvement, three improvements are proposed for SSA: Latin hypercube sampling is introduced to initialize the location of sparrows and increase the diversity of sparrows; the somersault foraging strategy is used to enrich the optimal position of producers; and combining with the cyclone foraging mechanism, the position updating process of the scroungers is optimized to obtain a better foraging position. In terms of performance evaluation of the algorithm, the ablation experiment verifies that the three improved strategies have improved effects in SSA, and the performance of ISSA on the CEC2017 benchmark function is better than other peers. In terms of predictive index screening, the important features are selected as the input variables of the model by random forest. The prediction results show that compared with the RF-BPNN model and models optimized by other algorithms, RF-ISSA-BPNN model has the lowest prediction error, and the expected value fits the real value better.