With the continuous development of autonomous driving, real-time target detection has become increasingly critical in autonomous driving systems. However, traditional target detection algorithms usually require huge computational resources, limiting their application on embedded autonomous driving platforms. To address this challenge, a lightweight single-stage target detection algorithm is proposed YOLOdrive. The inverted residual structure, linear bottleneck layer, and depth-separable convolution in MobileNetv2 are utilized to improve the YOLOv8 backbone network, while the spatial channel reconstructed convolution is used to improve the C2f module of YOLOv8, and the convolution of YOLOv8 neck and detection head is replaced by the depth-separable convolution. Experimental results verify that the average accuracy of YOLOdrive algorithm on MS COCO2017 data set and VOC2007 data set is improved compared with the baseline model YOLOv8-Nano. The amount of model parameters has been reduced by more than 50%, and the amount of computation in the model has been reduced by more than 70%. The algorithm drastically reduces the amount of parameters and computational complexity of the network, improves the operational efficiency, saves the storage space of the network, and maintains a high-detection performance.

Aiming at the fact that the moving target defense game model fails to accurately portray attack and defense gains, resulting in bias in attack and defense games and the inability to select effective defense strategies, we construct the moving target three-way evolutionary game defense model (MTTEGDM). Firstly, the model is defined and analyzed theoretically under the premise of uncertainty and irrationality. Then, combined with the three-way decisions, the attack intention is introduced into the target network loss calculation, and a dynamic weight adjustment algorithm based on the three-way decisions is proposed to accurately characterize the attack and defense gains from a multi-attribute perspective. Finally, the evolutionary game model is used to analyze the evolution trend of the multi-stage defense strategy, so as to carry out feasible and effective defense behavior. The simulation results show that the model can accurately predict the optimal defense strategy of moving targets in different stages. Through a Monte Carlo simulation experiment, the proposed algorithm is compared with the traditional evolutionary game model, and the effectiveness and security of the proposed algorithm are verified.

The current unreasonable deployment mechanism of shared bikes makes it difficult to meet public demand. Accurate prediction of shared bikes demand can alleviate this problem, but current prediction models are limited by small data size and poor robustness, making them unable to provide sufficiently accurate prediction to be applied in real-life situations. In this work, we propose a generative adversarial networks (GAN)-based ensemble model (GANEM) for predicting the demand of shared bikes in 5G networks to solve the above problem. With the support of 5G networks, real-time transmission and storage of traffic data of shared bikes have become reality. We then use these data to train the GANEM model to have better generalization performance. The GANEM model first uses GAN to learn the data features of existing shared bikes demand to generate new training samples. We borrow the idea of ensemble learning, three benchmark predictors are integrated to fully exploit the association between explicit features, which can improve the robustness of the model. Excellent prediction results are achieved on two real datasets. The experimental results of our proposed GANEM model on two datasets are as follows, the values of MAE are 0.120 and 0.144, the values of MSE are 0.027 and 0.032, the values of RMSE are 0.164 and 0.181.

Consumer data in e-commerce platforms relies heavily on Internet of Things (IoT) devices, which bring forth numerous security threats. As an emerging proactive defense technology, IoT network security situation prediction has the capability to forecast the overall future network security conditions. However, the original network security situation sequences exhibit nonlinear and unstable characteristics, which diminish the direct predictive accuracy. In this paper, we propose a prediction model based on decomposition-fusion. Specifically, we propose a novel approach to compute situation values by integrating three key factors: IoT attack factors, IoT attack probabilities, and IoT threat factors. Then, we decompose the original sequence into more stable subsequences using Variational Mode Decomposition (VMD), and construct a Convolutional Neural Network (CNN)-Bidirectional Long Short-Term Memory (BiLSTM)-Attention architecture to predict these subsequences. Finally, we utilize BiLSTM to fuse the results from each subsequence calculation, generating the ultimate prediction. Experimental results underscore the significant advantages of this method in terms of stability and forecasting precision, with a fitting degree of 0.99. This method provides a more comprehensive security defense system for e-commerce platforms and IoT applications, thereby enhancing the overall security of consumer data. Furthermore, it presents a novel solution for the field of network security.

Credit risk assessment is an important process in bank financial risk management. Traditional machine-learning methods cannot solve the problem of data islands and the high error rate of two-way decisions, which is not conducive to banks’ accurate credit risk assessment of users. To this end, this paper establishes a federated three-way decision incremental naive Bayes bank user credit risk assessment model (FTwNB) that supports asymmetric encryption, uses federated learning to break down data barriers between banks, and uses asymmetric encryption to protect data security for federated processes. At the same time, the model combines the three-way decision methods to realize the three-way classification of user credit (good, bad and delayed judgment), so as to avoid the loss of bank interests caused by the forced division of uncertain users. In addition, the model also incorporates incremental learning steps to eliminate training samples with poor data quality to further improve the model performance. This paper takes German Credit data and Default of Credit Card Clients data as examples to conduct simulation experiments. The result shows that the performance of the FTwNB model has been greatly improved, which verifies that it has good credit risk assessment capabilities.

In recent years, some research results have been achieved in the field of image steganalysis. However, there are still problems of difficulty in extracting steganographic features from images with low embedding rates and unsatisfactory detection performance of steganalysis. In this paper, we propose an image steganalysis method based on the attention mechanism and transfer learning. The method constructs a network model based on a convolutional neural network, including a preprocessing layer, a transposed convolutional layer, an ordinary convolutional layer, and a fully connected layer. We introduce the efficient channel attention module after the ordinary convolutional layer to focus on the steganographic region of the image, capture the local cross-channel interaction information, realize the adaptive adjustment of feature weights, and enhance the ability to extract steganographic features. Meanwhile, we apply the transfer learning method to use the training model parameters of high embedding rate images as the initialization parameters of the training model of the low embedding rate to achieve feature migration and further improve the steganalysis performance of the low embedding rate. The experimental results show that compared to the typical Xu-Net and Yedroudj-Net models, the detection accuracy of the proposed method is improved by 16.36% to 30.66% and by 35.59 to 37.83% for the embedding rates of 0.05 bpp, 0.1 bpp, and 0.2 bpp, respectively. Compared to the state-of-the-art Shen-Net model with low embedding rates, the detection accuracy is improved by 3.43% to 6.41%. This demonstrates the higher detection performance of the proposed method for steganalysis of low embedding rate images.

In this paper, an improved Internet of Things (IoT) network security situation assessment model is designed to solve the problems arising from the existing IoT network security situation assessment approach regarding feature extraction, validity, and accuracy. Firstly, raw data are dimensionally reduced using independent component analysis (ICA), and the weights of all features are calculated and fused using the maximum relevance minimum redundancy (mRMR) algorithm, Spearman’s rank correlation coefficient, and extreme gradient boosting (XGBoost) feature importance method to filter out the optimal subset of features. Piecewise chaotic mapping and firefly perturbation strategies are then used to optimize the sparrow search algorithm (SSA) to achieve fast convergence and prevent getting trapped in local optima, and then the optimized algorithm is used to improve the light gradient boosting machine (LightGBM) algorithm. Finally, the improved LightGBM method is used for training to calculate situation values based on a threat impact to assess the IoT network security situation. The research findings reveal that the model attained an evaluation accuracy of 99.34%, sustained a mean square error at the 0.00001 level, and reached its optimum convergence value by the 45th iteration with the fastest convergence speed. This enables the model to more effectively evaluate the IoT network security status.

Aiming at the problems of the dynamic increase in data in real life and that the naive Bayes (NB) classifier only accepts or rejects the sample processing results, resulting in a high error rate when dealing with uncertain data, this paper combines three-way decision and incremental learning, and a new three-way incremental naive Bayes classifier (3WD-INB) is proposed. First, the NB classifier is established, and the distribution fitting is carried out according to the minimum residual sum of squares (RSS) for continuous data, so that 3WD-INB can process both discrete data and continuous data, then carry out an incremental learning operation, select the samples with higher data quality according to the confidence of the samples in the incremental training set for incremental learning, solve the problem of data dynamics and filter the poor samples. Then we construct the 3WD-INB classifier and determine the classification rules of the positive, negative and boundary domains of the 3WD-INB classifier, so that the three-way classification of samples can be realized and better decisions can be made when dealing with uncertain data. Finally, five discrete data and five continuous data are selected for comparative experimental analysis with traditional classification methods. The results show that 3WD-INB has high accuracy and recall rate on different types of datasets, and the classification performance is also relatively stable.

With the application and development of Internet technology, network traffic is growing rapidly, and the situation of network security is becoming more and more serious. As an important way to protect network security, abnormal traffic detection has been paid more and more attention. In this paper, the uncertainty of the samples in the abnormal traffic detection dataset is studied. Combining the three-way decision idea with the random forest algorithm, a three-way selection random forest optimization model for abnormal traffic detection is proposed. Firstly, the three-way decision idea is integrated into the random selection process of feature attributes, and the attribute importance based on decision boundary entropy is calculated. The feature attributes are divided into the normal domain, abnormal domain, and uncertain domain, and the three-way attribute random selection rules are designed to randomly select the feature attributes that conform to the rules from different domains. Secondly, the classifier evaluation function is constructed by combining pure accuracy and diversity, and the anomaly traffic detection base classifier with a high evaluation value is selected for integration to eliminate the unstable factors caused by randomness in the process of base classifier generation. Thirdly, the optimal node weight combination of the base classifier is obtained by iterative calculation of the gray wolf optimization algorithm to further improve the prediction effect and robustness of the model. Finally, the model is applied to the abnormal traffic detection dataset. The experimental results show that the prediction accuracy of the three-way selection random forest optimization model on CIC-IDS2017, KDDCUP99, and NSLKDD datasets is 96.1%, 95.2%, and 95.3%, respectively, which has a better detection effect than other machine learning algorithms.

With a large number of intrusion detection datasets and high feature dimensionality, the emergent nature of new attack types makes it impossible to collect network traffic data all at once. The modified three-way attribute reduction method is combined with a Self-Organizing Incremental learning Neural Network (SOINN) algorithm to propose a self-organizing incremental neural network intrusion detection model based on three-way attribute reduction. Attribute importance is used to perform attribute reduction, and the data after attribute reduction are fed into a self-organized incremental learning neural network algorithm, which generalizes the topology of the original data through self-organized competitive learning. When the streaming data are transferred into the model, the inter-class insertion or node fusion operation is performed by comparing the inter-node distance and similarity threshold to achieve incremental learning of the model streaming data. The inter-node distance value is introduced into the weight update formulation to replace the traditional learning rate and to optimize the topological structure adjustment operation. The experimental results show that T-SOINN achieves high precision and recall when processing intrusion detection data.

In recent years, deep learning models have been more and more widely used in various fields and have become a research hotspot for various tasks in artificial intelligence, but there are significant limitations in non-convex optimization problems. As a model training strategy for non-convex optimization, curriculum learning advocates that models learn in the order of easier to more difficult data, mimicking the basic idea of gradual human learning as they learn curriculum. This strategy has been widely used in the fields of computer vision, natural language processing, and reinforcement learning; it can effectively solve the non-convex optimization problem and improve the generalization ability and convergence speed of models. This paper first introduces the application of curriculum learning at three major levels: data, task, and model, and summarizes the evaluators designed using curriculum learning methods in various domains, including difficulty evaluators, training schedulers, and loss evaluators, which correspond to the three stages of difficulty evaluation, training schedule, and loss evaluation in the application of curriculum learning to model training. We also discuss how to choose an appropriate evaluation system and the differences between terms used in different types of research. Finally, we summarize five methods similar to curriculum learning in the field of machine learning and provide a summary and outlook of the curriculum learning evaluation system.

Traditional image steganography techniques complete the steganography process by embedding secret information into cover images, but steganalysis tools can easily detect detectable pixel changes that lead to the leakage of confidential information. The use of a generative adversarial network (GAN) makes it possible to embed information using a combination of information and noise in generating images to achieve steganography. However, this approach is usually accompanied by issues such as poor image quality and low steganography capacity. To address these challenges, we propose a steganography model based on a novel information-driven generative adversarial network (IDGAN), which fuses a GAN, attention mechanisms, and image interpolation techniques. We introduced an attention mechanism on top of the original GAN model to improve image accuracy. In the generation model, we replaced some transposed convolution operations with image interpolation for better quality of dense images. In contrast to traditional steganographic methods, the IDGAN generates images containing confidential information without using cover images and utilizes GANs for information embedding, thus having better anti-detection capability. Moreover, the IDGAN uses an attention mechanism to improve the image details and clarity and optimizes the steganography effect through an image interpolation algorithm. Experimental results demonstrate that the IDGAN achieves an accuracy of 99.4%, 95.4%, 93.2%, and 100% on the MNIST, Intel Image Classification, Flowers, and Face datasets, respectively, with an embedding rate of 0.17 bpp. The model effectively protects confidential information while maintaining high image quality.

With the spread of COVID-19 around the world, the education industry faces enormous challenges. Some colleges and universities have launched online teaching. Comprehensive online teaching and student health checkups help students complete the set teaching content and return to school as soon as possible. With the development of big data, combined with the epidemic risk we are facing, the rational use of big data and the internet for innovative online education has become a mainstream teaching method. Colleges and universities are not yet familiar with the development prospects and future of online education. Through the research of this paper, we can understand the combination of online education and the development of big data and promote its application in colleges and universities. Not only have innovative online education platforms such as MOOC and DingTalk been widely used, but innovative online education methods such as virtual classrooms also have been created. Based on the current epidemic background, this paper analyzes the development of online education, introduces the impact of the combination of online education and big data, and introduces innovative online education technologies and their effects. It helps online education under the influence of the new coronavirus epidemic, operating big data technology to analyze the current prospects and development of online education, showing the combination of big data technology and online education through the analysis of big data technology, and ending with more expectations on other aspects of the use of big data, which affects the online education industry as well as other industries. Finally, we summarize the combination of big data and innovative online education since the emergence of COVID-19 and introduce the concepts and methods of combining online education and big data technology in detail. The online education platform also makes a reasonable introduction. The thesis can be used to understand the problems and challenges faced by innovative online education in the context of the new coronavirus epidemic and look forward to the future on this basis.

With the rapid development of the field of artificial intelligence, China is paying more and more attention to the cultivation of professional talents related to artificial intelligence. As an emerging cross-cutting discipline, our university has built a curriculum system for the major of intelligent science and technology, which is a collaborative platform of "industry, science, education and innovation" for the training of talents for new industries and new engineering disciplines. It also provides reference and inspiration for other majors in our university to implement the new engineering construction.

A SEIARN compartment model with the asymptomatic infection and secondary infection is proposed to predict the trend of COVID-19 more accurately. The model is extended according to the propagation characteristics of the novel coronavirus, the concepts of the asymptomatic infected compartment and secondary infection are introduced, and the contact rate parameters of the improved model are updated in real time by using the LSTM trajectory, in order to make accurate predictions. This SEIARN model first builds on the traditional SEIR compartment model, taking into account the asymptomatic infection compartment and secondary infection. Secondly, it considers the disorder of the trajectory and uses the improved LSTM model to predict the future trajectory of the current patients and cross-track with the susceptible patients to obtain the contact rate. Then, we conduct real-time updating of exposure rates in the SEIARN model and simulation of epidemic trends in Tianjin, Xi'an, and Shijiazhuang. Finally, the comparison experiments show that the SEIARN model performs better in prediction accuracy, MSE, and RMSE.

Network intrusion detection system is an essential part of network security research. It detects intrusion behaviors through active defense technology and takes emergency measures such as alerting and terminating intrusions. With the rapid development of machine learning technology, more and more researchers apply machine learning algorithms to network intrusion detection to improve detection efficiency and accuracy. Due to the different principles of various algorithms, they also have their advantages and disadvantages. To construct the dominant algorithm model in the field of network intrusion detection and provide the accuracy value, this paper systematically combs the application literature of machine learning algorithms in intrusion detection in the past ten years. A review is made from three categories: traditional machine learning, ensemble learning, and deep learning. Then, this paper selects the KDD CUP99 and NSL-KDD datasets to conduct comparative experiments on decision trees, Naive Bayes, support vector machines, random forests, XGBoost, convolutional neural networks, and recurrent neural networks. The detection accuracy, F1, AUC, and other indicators of these algorithms on different data sets are compared. The experimental results show that the effect of the ensemble learning algorithm is generally better. The Naive Bayes algorithm has low accuracy in recognizing the learned data, but it has obvious advantages when facing new types of attacks, and the training speed is faster. The deep learning algorithm is not particularly prominent in this experiment, but its optimal results are affected by the structure, hyperparameters, and the number of training iterations, which need further in-depth study. Finally, the main challenges facing the current network intrusion detection field are summarized, and the future research directions have been prospected.

With increasing developments and progress, the status and influence of women in society have significantly improved, with more attention paid to women's health. According to relevant statistics, uterine cancer is a highly-incident malignant tumor in females and urges more research to improve the survival rate of uterine cancer patients. In this study, we established a prediction model to determine the location of uterine cancer recurrence by combining random forest and neural network algorithms. Data of uterine cancer patients were collected from major hospitals, and professional doctors evaluated and graded the patients' physical fitness indicators based on their experience, which were then used to construct the model and obtain the prediction results. Compared to traditional method, the proposed method of this paper showed that the model was more effective and accurate in predicting the location of uterine cancer recurrence, with a prediction accuracy rate of up to 88.63%.

Network intrusion detection has the problems of large amounts of data, numerous attributes, and different levels of importance for each attribute in detection. However, in random forests, the detection results have large deviations due to the random selection of attributes. Therefore, aiming at the current problems, considering increasing the probability of essential features being selected, a network intrusion detection model based on three-way selected random forest (IDTSRF) is proposed, which integrates three decision branches and random forest. Firstly, according to the characteristics of attributes, it is proposed to evaluate the importance of attributes by combining decision boundary entropy, and using three decision rules to divide attributes; secondly, to keep the randomness of attributes, three attribute random selection rules based on attribute randomness are established, and a certain number of attributes are randomly selected from three candidate fields according to conditions; finally, the training sample set is formed by using autonomous sampling method to select samples and combining three randomly selected attribute sets randomly, and multiple decision trees are trained to form a random forest. The experimental results show that the model has high precision and recall.

According to the logistics tasks and the interests relation between partners, partners selection of virtual enterprise only has two results: selection or elimination. This problem may cause some partners’ eliminations because of the temporary conflicts of interests, furthermore, influences the economic benefits of the logistics enterprises. Aiming at this problem, this paper proposes a dynamic method for partner selection of virtual logistics enterprises which based on threeway decision theory. And working with the cost function, the partners are selected from three aspects: selection, elimination and undetermined. Firstly, the basic idea of partner selection is derived, and the method of determining probability threshold is given. Secondly, the design of the computational model of conditional probability, the model and algorithm of partner selection is completed. Finally, comparing with the existing methods, experiments on different data sets are carried out. Experimental results show that the three-way decision method not only provides more selection objects in partner selection stage, but also improves the accuracy of partner selection.

The set is dynamic, including elements moving in and out. The two-direction PS-probabilistic rough set considers both the dynamic characteristics of the set and the rough set theory of statistical information in the knowledge base. Based on dynamic three way decisions making on PS-rough set, the corresponding dynamic algorithm is given. First, according to the moving in and out of objects, different cases are discussed, and relevant theorems, inferences and propositions are proved. Secondly, the corresponding algorithms for dynamic changes of the decision is given. Finally, a set of UCI data sets used for activity recognition data sets is selected as experimental data. Through the selection of different subsets, a good effect has been achieved in the experiment of one-direction moving in, one-direction moving out and two-direction moving in and out, and the feasibility of the algorithm is proved.