Search

In recent years, the application of speech emotion recognition (SER) in the supervision of Internet public opinion has received increasing attention. This study proposes a new SER algorithm to analyze the public opinion information of network platforms. Firstly, we extract different spectrum features from speech signals and combine them into frame level speech features. Then, we select conditional deep confidence network (CDBN) which has the ability to learn sequential features as the final classification model. We apply particle swarm optimization (PSO) and genetic algorithm (GA) during the fine-tuning stage of the CDBN to obtain more suitable optimal weights of the whole network, and propose the PSO-GA-CDBN (PGCDBN) model. Compare with the traditional back propagation (BP) algorithm, our training method accelerates the convergence speed of the network and improves the robustness and recognition performance of the network. In our experiment, we used the Chinese Academy of Sciences’ Institute of automation (CASIA) Chinese emotional corpus and self-collected Chinese speech datasets, which were collected from Sina Weibo, Tik tok and other online social media platforms. Compare with the popular emotion classifiers such as support vector machine (SVM), deep residual network (ResNet), long short-term memory (LSTM) neural network, DBN, our proposed PGCDBN achieves the best recognition results from both datasets. In addition, we use bidirectional LSTM before PGCDBN to further process the extracted speech features, and the result of bidirectional LSTM has stronger speech signal expression ability. The average recognition accuracy of this new hybrid deep learning model algorithm in two datasets is 98.67%, which can be used for the supervision of netizens’ opinions.

With the development of the wireless network techniques, the number of cyber-attack increases significantly, which has seriously threat the security of Wireless Local Area Network (WLAN). The traditional intrusion detection technology is a prevalent area of study for numerous years, but it may not have a good detection performance in a real-time way. Therefore, it is urgent to design a detection mechanism to detect the attacks timely. In this paper, we exploit a CDBN (Conditional Deep Belief Network)-based intrusion detection mechanism to recognize the attack features and perform the wireless network intrusion detection in real time. To avoid the impact of the imbalanced dataset and the data redundancy on the detection accuracy, a window-based instance selection algorithm “SamSelect” is adopted to undersample the majority class data samples, and a Stacked Contractive Auto-Encoder (SCAE) algorithm is proposed to reduce the dimension of the data samples. By doing so, our proposed mechanism can effectively detect the potential attack and achieve high accuracy. The experiment results show that CDBN can be effectively combined with “SamSelect” and SCAE, and the proposed mechanism has a high detection speed and accuracy, with the average detection time 1.14 ms and the detection accuracy 0.974.

A smart grid improves power grid efficiency by using modern information and communication technologies. However, at the same time, due to the dependence on information technology and the deep integration of electrical components and computing information in cyber space, the system might become increasingly vulnerable to cyber-attacks. Among various emerging security problems, a false data injection attack (FDIA) is a new type of attack against the state estimation. In this article, a deep learning-based identification scheme is developed to detect and mitigate information corruption. The scheme implements a conditional deep belief network (CDBN) to analyze time-series input data and leverages captured features to detect the FDIA. The performance of our detection mechanism is validated by using the IEEE 14-bus test system for simulation. Different attack scenarios and parameters are set to demonstrate the feasibility and effectiveness of the developed scheme. Compared with the artificial neural network (ANN) and the support vector machine (SVM), the experimental analyses indicate that the results of our detection mechanism are better than those of the other two in terms of FDIA detection accuracy and robustness. [ABSTRACT FROM AUTHOR]