Nickel is a vital strategic metal resource with commodity and financial attributes simultaneously, whose price fluctuation will affect the decision‐making of stakeholders. Therefore, an effective trend forecast of nickel price is of great reference for the risk management of the nickel market’s participants; yet, traditional forecast methods are defective in prediction accuracy and applicability. Therefore, a prediction model of nickel metal price is proposed based on improved particle swarm optimization algorithm (PSO) combined with long‐short‐term memory (LSTM) neural networks, for higher reliability. This article introduces a nonlinear decreasing assignment method and sine function to improve the inertia weight and learning factor of PSO, respectively, and then uses the improved PSO algorithm to optimize the parameters of LSTM. Nickel metal’s closing prices in London Metal Exchange are sampled for empirical analysis, and the improved PSO‐LSTM model is compared with the conventional LSTM and the integrated moving average autoregressive model (ARIMA). The results show that compared with the standard PSO, the improved PSO has a faster convergence rate and can improve the prediction accuracy of the LSTM model effectively. In addition, compared with the conventional LSTM model and the integrated moving average autoregressive (ARIMA) model, the prediction error of the LSTM model optimized by the improved PSO is reduced by 9% and 13%, respectively, which has high reliability and can provide valuable guidance for relevant managers.

Wind energy is a renewable energy source with great development potential, and a reliable and accurate prediction of wind speed is the basis for the effective utilization of wind energy. Aiming at hyperparameter optimization in a combined forecasting method, a wind speed prediction model based on the long short‐term memory (LSTM) neural network optimized by the firework algorithm (FWA) is proposed. Focusing on the real‐time sudden change and dependence of wind speed data, a wind speed prediction model based on LSTM is established, and FWA is used to optimize the hyperparameters of the model so that the model can set parameters adaptively. Then, the optimized model is compared with the wind speed prediction based on other deep neural architectures and regression models in experiments, and the results show that the wind speed model based on FWA‐improved LSTM reduces the prediction error when compared with other wind speed prediction‐based regression methods and obtains higher prediction accuracy than other deep neural architectures.

The advantages of cloud storage make more and more tenants outsource their data to the cloud. In the vehicular ad hoc networks, the sensors on the vehicle can collect road information being available for analyzing traffic conditions and their integrity must be guaranteed. Due to the limited storage capability, the vehicles tend to store the valid information have been collected on the cloud servers. However, unlike using local storage devices, the vehicles no longer have absolute control over the cloud data. Clearly, as the tenants of the cloud storage, the vehicles are most concerned about the data integrity. It is a pity that many existing integrity auditing schemes have some shortcomings, such as low efficiency in data dynamic updating, leakage of data privacy, and high auditing cost. To solve these problems, this paper proposes a dynamic data integrity auditing scheme supporting data privacy protection. First, build the hierarchical multiple branches tree data authentication structure in the initialization phase. Second, design a data integrity auditing scheme based on the bilinear pairing mapping technology and the Boneh-Lynn-Shacham digital signature mechanism, and describe the process of data dynamic updating in detail. Finally, security analysis and performance analysis are carried out in the evaluation of the scheme. The security analysis shows that the scheme can satisfy auditing correctness, support data privacy protection, resist forgery attack, and replay attack. The performance analysis shows that, compared with the existing scheme, the scheme reduces the time cost of data integrity auditing and dynamic updating.

Storing multi-copy of data file on multi-cloud may be useful in some practical contexts. How to ensure the integrity of a user’s multi-copy becomes very important in this case. In recent work, Li et al. proposed an efficient “identity-based” auditing protocol (LYZ-protocol, for short) to achieve this goal. The “identity-based” property guarantees that the resulting primitive does not rely on PKI to manage certificates. However, in this letter, we note that the performances of this protocol can be further improved. More precisely, by introducing a new hash function modeled as a random oracle, the communication costs of original LYZ-protocol can be greatly reduced. In addition, the building block of a traditional signature scheme used in this protocol results in the entire protocol not being completely identity-based, and thus it may still bear the burden of managing certificates. Therefore, by replacing this signature with an identity-based scheme, we can obtain a completely identity-based protocol. Finally, the performance analysis shows that the modified LYZ-protocol outperforms the original one.

The identification and classification of faults in chemical processes can provide decision basis for equipment maintenance personnel to ensure the safe operation of the production process. In this paper, we combine long short‐term memory neural network (LSTM) with convolutional neural network (CNN) and propose a new fault diagnosis method based on multichannel LSTM‐CNN (MCLSTM‐CNN). The primary methodology here includes three aspects. In the initial state, the fault data are input into the LSTM to obtain the output of the hidden layer, which stores the relevant temporal and spatial domain information. Due to the diversity of data features, convolutional kernels with different sizes are utilized to form multiple channels to extract the output characteristics of the hidden layer simultaneously. Finally, the fault data are classified by fully connected layers. The Tennessee Eastman (TE) chemical process is used for experimental analysis, and the MCLSTM‐CNN model is compared with the LSTM‐CNN, LSTM, CNN, RF and KPCA + SVM models. The experimental results show that the MCLSTM‐CNN model has higher diagnostic accuracy, and the fault classification results are superior to other models.

Semi-quantum cryptography communication stipulates that the quantum user has complete quantum capabilities, and the classical user has limited quantum capabilities, only being able to perform the following operations: (1) measuring and preparing qubits with a Z basis and (2) returning qubits without any processing. Secret sharing requires participants to work together to obtain complete secret information, which ensures the security of the secret information. In the semi-quantum secret sharing (SQSS) protocol, the quantum user Alice divides the secret information into two parts and gives them to two classical participants. Only when they cooperate can they obtain Alice’s original secret information. The quantum states with multiple degrees of freedom (DoFs) are defined as hyper-entangled states. Based on the hyper-entangled single-photon states, an efficient SQSS protocol is proposed. The security analysis proves that the protocol can effectively resist well-known attacks. Compared with the existing protocols, this protocol uses hyper-entangled states to expand the channel capacity. The transmission efficiency is 100% higher than that of single-degree-of-freedom (DoF) single-photon states, providing an innovative scheme for the design of the SQSS protocol in quantum communication networks. This research also provides a theoretical basis for the practical application of semi-quantum cryptography communication.