This page has only limited features, please log in for full access.
Deep learning has been applied in the field of network intrusion detection and has yielded good results. In malicious network traffic classification tasks, many studies have achieved good performance with respect to the accuracy and recall rate of classification through self-designed models. In deep learning, the design of the model architecture greatly influences the results. However, the design of the network model architecture usually requires substantial professional knowledge. At present, the focus of research in the field of traffic monitoring is often directed elsewhere. Therefore, in the classification task of the network intrusion detection field, there is much room for improvement in the design and optimization of the model architecture. A neural architecture search (NAS) can automatically search the architecture of the model under the premise of a given optimization goal. For this reason, we propose a model that can perform NAS in the field of network traffic classification and search for the optimal architecture suitable for traffic detection based on the network traffic dataset. Each layer of our depth model is constructed according to the principle of maximum coding rate attenuation, which has strong consistency and symmetry in structure. Compared with some manually designed network architectures, classification indicators, such as Top-1 accuracy and F1 score, are also greatly improved while ensuring the lightweight nature of the model. In addition, we introduce a surrogate model in the search task. Compared to using the traditional NAS model to search the network traffic classification model, our NAS model greatly improves the search efficiency under the premise of ensuring that the results are not substantially different. We also manually adjust some operations in the search space of the architecture search to find a set of model operations that are more suitable for traffic classification. Finally, we apply the searched model to other traffic datasets to verify the universality of the model. Compared with several common network models in the traffic field, the searched model (NAS-Net) performs better, and the classification effect is more accurate.
Renjian Lyu; Mingshu He; Yu Zhang; Lei Jin; Xinlei Wang. Network Intrusion Detection Based on an Efficient Neural Architecture Search. Symmetry 2021, 13, 1453 .
AMA StyleRenjian Lyu, Mingshu He, Yu Zhang, Lei Jin, Xinlei Wang. Network Intrusion Detection Based on an Efficient Neural Architecture Search. Symmetry. 2021; 13 (8):1453.
Chicago/Turabian StyleRenjian Lyu; Mingshu He; Yu Zhang; Lei Jin; Xinlei Wang. 2021. "Network Intrusion Detection Based on an Efficient Neural Architecture Search." Symmetry 13, no. 8: 1453.
With the increasing number of people accessing the Internet, attacks against users or web servers have become a serious threat to network security. Network traffic can record network behavior, which is an important data source for analyzing network behavior. Using machine learning algorithm to analyze network behavior is one of the effective methods. However, these methods always put the data into black boxes, which is not enough for business understanding and result reliability display. In this paper, we propose an interpretability framework of network security traffic classification and apply it on a network traffic dataset. In this work, we apply some interpretable models, including model structure-based and feature importance-based. We verify that the methods can help researchers better explain the business features of network security traffic and optimize the classification model in algorithm selection and feature selection. We also study the interpretability of network traffic on neural network and make some progress.
Mingshu He; Lei Jin; Mei Song. Interpretability Framework of Network Security Traffic Classification Based on Machine Learning. Algorithms and Data Structures 2021, 305 -320.
AMA StyleMingshu He, Lei Jin, Mei Song. Interpretability Framework of Network Security Traffic Classification Based on Machine Learning. Algorithms and Data Structures. 2021; ():305-320.
Chicago/Turabian StyleMingshu He; Lei Jin; Mei Song. 2021. "Interpretability Framework of Network Security Traffic Classification Based on Machine Learning." Algorithms and Data Structures , no. : 305-320.
Various attacks have become the main threat in the Internet world. Traffic classification is the first step in network exception detection or network-based intrusion detection systems, and plays an important role in the field of network security. With the development of Internet technology, the source and complexity of network attacks are getting higher and higher, making it difficult for traditional anomaly detection systems to effectively analyze and identify malicious traffic. In recent years, the method of deep learning has been widely used in the field of traffic recognition, and the characteristics of traffic data can be automatically identified. Because of the size limit of the input data of the neural network, the flow data needs to be trimmed to feed into the network for learning, so the neural network cannot learn the characteristics of the traffic data well. In this paper, we propose an N-gram-based data processing method to convert the raw traffic data into N-gram features to represent more information. Then our method uses a detector based on convolutional neural network (CNN) to classify and detect data. Our experiments show that the detection accuracy of using N-gram feature data is better than the method using raw traffic. This method can more effectively detect malicious traffic data.
Wang Xiaojuan; Kaiwenlv Kacuila; He Mingshu. An N-gram Based Deep Learning Method for Network Traffic Classification. Algorithms and Data Structures 2021, 289 -304.
AMA StyleWang Xiaojuan, Kaiwenlv Kacuila, He Mingshu. An N-gram Based Deep Learning Method for Network Traffic Classification. Algorithms and Data Structures. 2021; ():289-304.
Chicago/Turabian StyleWang Xiaojuan; Kaiwenlv Kacuila; He Mingshu. 2021. "An N-gram Based Deep Learning Method for Network Traffic Classification." Algorithms and Data Structures , no. : 289-304.
Text, voice, images and videos can express some intentions and facts in daily life. By understanding these contents, people can identify and analyze some behaviors. This paper focuses on the commodity trade declaration process and identifies the commodity categories based on text information on customs declarations. Although the technology of text recognition is mature in many application fields, there are few studies on the classification and recognition of customs declaration goods. In this paper, we proposed a classification framework based on machine learning (ML) models for commodity trade declaration that reaches a high rate of accuracy. This paper also proposed a symmetrical decision fusion method for this task based on convolutional neural network (CNN) and transformer. The experimental results show that the fusion model can make up for the shortcomings of the two original models and some improvements have been made. In the two datasets used in this paper, the accuracy can reach 88% and 99%, respectively. To promote the development of study of customs declaration business and Chinese text recognition, we also exposed the proprietary datasets used in this study.
Mingshu He; Xiaojuan Wang; Chundong Zou; Bingying Dai; Lei Jin. A Commodity Classification Framework Based on Machine Learning for Analysis of Trade Declaration. Symmetry 2021, 13, 964 .
AMA StyleMingshu He, Xiaojuan Wang, Chundong Zou, Bingying Dai, Lei Jin. A Commodity Classification Framework Based on Machine Learning for Analysis of Trade Declaration. Symmetry. 2021; 13 (6):964.
Chicago/Turabian StyleMingshu He; Xiaojuan Wang; Chundong Zou; Bingying Dai; Lei Jin. 2021. "A Commodity Classification Framework Based on Machine Learning for Analysis of Trade Declaration." Symmetry 13, no. 6: 964.
Machine learning (ML)-based methods are increasingly used in different fields of business to improve the quality and efficiency of services. The increasing amount of data and the development of artificial intelligence algorithms have improved the services provided to customers in shopping malls. Most new services are based on customers’ precise positioning in shopping malls, especially customer positioning within shops. We propose a novel method to accurately predict the specific shops in which customers are located in shopping malls. We use global positioning system (GPS) information provided by customers’ mobile terminals and WiFi information that completely covers the shopping mall. According to the prediction results, we learn some of the behavior preferences of users. We use these predicted customer locations to provide customers with more accurate services. Our training dataset is built using feature extraction and screening from some real customers’ transaction records in shopping malls. In order to prove the validity of the model, we also cross-check our algorithm with a variety of machine learning algorithms. Our method achieves the best speed–accuracy trade-off and can accurately locate the shops in which customers are located in shopping malls in real time. Compared to other algorithms, the proposed model is more accurate. User preference behaviors can be used in applications to efficiently provide more tailored services.
Haiyang Jiang; Mingshu He; Yuanyuan Xi; Jianqiu Zeng. Machine-Learning-Based User Position Prediction and Behavior Analysis for Location Services. Information 2021, 12, 180 .
AMA StyleHaiyang Jiang, Mingshu He, Yuanyuan Xi, Jianqiu Zeng. Machine-Learning-Based User Position Prediction and Behavior Analysis for Location Services. Information. 2021; 12 (5):180.
Chicago/Turabian StyleHaiyang Jiang; Mingshu He; Yuanyuan Xi; Jianqiu Zeng. 2021. "Machine-Learning-Based User Position Prediction and Behavior Analysis for Location Services." Information 12, no. 5: 180.
With the increase of Internet visits and connections, it is becoming essential and arduous to protect the networks and different devices of the Internet of Things (IoT) from malicious attacks. The intrusion detection systems (IDSs) based on supervised machine learning (ML) methods require a large number of labeled samples. However, the number of abnormal behaviors is far less than that of normal behaviors, let alone that the shots of malicious behavior samples which can be intercepted as training dataset are actually limited. Consequently, it is a key research topic to conduct the anomaly detection for the small number of abnormal behavior samples. This paper proposes an anomaly detection model with a few abnormal samples to solve the problem in few-shot detection based on convolutional neural networks (CNN) and autoencoder (AE). This model mainly consists of the CNN-based supervised pretraining module and the AE-based data reconstruction module. Only a few abnormal samples are utilized to the pretrain module to build the structure of extracting deep features. The data reconstruction module simply chooses the deep features of normal samples as training data. There also exist some effective attention mechanisms in the pretraining module. Through the pretraining of small samples, the accuracy of abnormal detection is improved compared with merely training normal samples with AE. The simulation results prove that this solution can solve the above problems occurring in network behavior anomaly detection. In comparison to the original AE model and other clustering methods, the proposed model advances the detection results in a visible way.
Mingshu He; Xiaojuan Wang; Junhua Zhou; Yuanyuan Xi; Lei Jin; Xinlei Wang. Deep-Feature-Based Autoencoder Network for Few-Shot Malicious Traffic Detection. Security and Communication Networks 2021, 2021, 1 -13.
AMA StyleMingshu He, Xiaojuan Wang, Junhua Zhou, Yuanyuan Xi, Lei Jin, Xinlei Wang. Deep-Feature-Based Autoencoder Network for Few-Shot Malicious Traffic Detection. Security and Communication Networks. 2021; 2021 ():1-13.
Chicago/Turabian StyleMingshu He; Xiaojuan Wang; Junhua Zhou; Yuanyuan Xi; Lei Jin; Xinlei Wang. 2021. "Deep-Feature-Based Autoencoder Network for Few-Shot Malicious Traffic Detection." Security and Communication Networks 2021, no. : 1-13.
Network traffic classification technology plays an important role in network security management. However, the inherent limitations of traditional methods have become increasingly obvious, and they cannot address existing traffic classification tasks. Very recently, neural architecture search (NAS) has aroused widespread interest as a tool to automate the manual architecture construction process. To this end, this paper proposes NAS based on multiobjective evolutionary algorithms (MOEAs) to classify malicious network traffic. The main purpose is to simplify the search space by reducing the spatial ratio and number of channels of the model. In addition, the search strategy is changed in the effective search space, and the utilized strategies include EAs with the nondominated sorting genetic algorithm with the elite retention strategy (NSGA-II), strength Pareto evolutionary algorithm (SPEA-II) and multiobjective particle swarm optimization (MOPSO) to solve the formulated multiobjective NAS. Through comprehensive comparison of the population convergence times, model accuracies, Pareto optimality sets, model complexities and running speeds of the strategies, it is concluded that the model based on NSGA-II search has the best performance. The experimental results of the current machine learning algorithms and artificial learning methods based on the network are compared, showing that our method achieved better classification performance on two public datasets with a lower computational complexity, as mainly measured by FLOPs. Our approach is able to achieve 99.806% and 99.369% F1-score with 11.501 MB and 4.718 MB FLOPs on both IDS2012 and ISCX VPN dataset respectively.
Xiaojuan Wang; Xinlei Wang; Lei Jin; Renjian Lv; Bingying Dai; Mingshu He; Tianqi Lv. Evolutionary Algorithm-Based and Network Architecture Search-Enabled Multiobjective Traffic Classification. IEEE Access 2021, 9, 52310 -52325.
AMA StyleXiaojuan Wang, Xinlei Wang, Lei Jin, Renjian Lv, Bingying Dai, Mingshu He, Tianqi Lv. Evolutionary Algorithm-Based and Network Architecture Search-Enabled Multiobjective Traffic Classification. IEEE Access. 2021; 9 (99):52310-52325.
Chicago/Turabian StyleXiaojuan Wang; Xinlei Wang; Lei Jin; Renjian Lv; Bingying Dai; Mingshu He; Tianqi Lv. 2021. "Evolutionary Algorithm-Based and Network Architecture Search-Enabled Multiobjective Traffic Classification." IEEE Access 9, no. 99: 52310-52325.
This paper focuses on 6Dof object pose estimation from a single RGB image. We tackle this challenging problem with a two-stage optimization framework. More specifically, we first introduce a translation estimation module to provide an initial translation based on an estimated depth map. Then, a pose regression module combines the ROI (Region of Interest) and the original image to predict the rotation and refine the translation. Compared with previous end-to-end methods that directly predict rotations and translations, our method can utilize depth information as weak guidance and significantly reduce the searching space for the subsequent module. Furthermore, we design a new loss function function for symmetric objects, an approach that has handled such exceptionally difficult cases in prior works. Experiments show that our model achieves state-of-the-art object pose estimation for the YCB- video dataset (Yale-CMU-Berkeley).
Lei Jin; Xiaojuan Wang; Mingshu He; Jingyue Wang. DRNet: A Depth-Based Regression Network for 6D Object Pose Estimation. Sensors 2021, 21, 1692 .
AMA StyleLei Jin, Xiaojuan Wang, Mingshu He, Jingyue Wang. DRNet: A Depth-Based Regression Network for 6D Object Pose Estimation. Sensors. 2021; 21 (5):1692.
Chicago/Turabian StyleLei Jin; Xiaojuan Wang; Mingshu He; Jingyue Wang. 2021. "DRNet: A Depth-Based Regression Network for 6D Object Pose Estimation." Sensors 21, no. 5: 1692.
Mingdao Lu; Peng Wei; Mingshu He; Yinglei Teng. Flight Delay Prediction Using Gradient Boosting Machine Learning Classifiers. Journal of Quantum Computing 2021, 3, 1 -12.
AMA StyleMingdao Lu, Peng Wei, Mingshu He, Yinglei Teng. Flight Delay Prediction Using Gradient Boosting Machine Learning Classifiers. Journal of Quantum Computing. 2021; 3 (1):1-12.
Chicago/Turabian StyleMingdao Lu; Peng Wei; Mingshu He; Yinglei Teng. 2021. "Flight Delay Prediction Using Gradient Boosting Machine Learning Classifiers." Journal of Quantum Computing 3, no. 1: 1-12.
With the development of computer science, the era of big data has arrived. Facing the new era and new challenges, the traditional analytical methods of problems in various fields have been unable to meet the needs. Data visualization is a rapidly developing discipline, it has significant advantages in analyzing problems, so data visualization shines in the era of big data. As people are very concerned about the fields of energy and environment, we choose to conduct data visualization studies in two areas, energy and the environment. According to the different characteristics of data in different fields, we propose targeted data visualization processes and design data visualization solutions. For energy data, we follow the process of data processing, visualization design, and data visualization. Based on the principle of high efficiency and intuitiveness, we add timeline and a combination of various charts to our design, and finally show a dynamic effect. We also propose a multi-dimensional visual mapping visualization scheme. The scheme can refine and enrich the visual results. For environmental data, we follow the process of goal analysis, data processing, visualization and analysis, the work shows the importance of visualization in information analysis and decision-making.
Xin Guo; Mingshu He; Mo Chen; Xiaojie Zhao; Ye Tian. Research on Data Visualization in Different Scenarios. Computer Vision 2019, 232 -243.
AMA StyleXin Guo, Mingshu He, Mo Chen, Xiaojie Zhao, Ye Tian. Research on Data Visualization in Different Scenarios. Computer Vision. 2019; ():232-243.
Chicago/Turabian StyleXin Guo; Mingshu He; Mo Chen; Xiaojie Zhao; Ye Tian. 2019. "Research on Data Visualization in Different Scenarios." Computer Vision , no. : 232-243.
Network attack can invalidate the connectivity of the resource network topology composed of routers, switches and other resources. This type of structural vulnerability which is caused by increasing scale of nodes in the network is a hotspot of current researches. In order to integrate the random attack and the targeted attack, we proposed an asymmetric information attack model which is closer to reality. In this attack model, we use the attack range and the node detection degree to adjust the attack mode and these two parameters extend the attack mode more than the random attack and the targeted attack. In this paper, we apply our attack model to attack BA network, ER network and Router network under different parameters. Then we find the random attack is better than other attack modes with nonzero node detection degree in ER network. And BA network is fragile to nonzero node detection degree attack mode. In addition, we also notice that although the distribution of Router network and BA network both satisfy the power law distribution, they show different structural vulnerability. The random attack has a better effect than the asymmetric information attack with nonzero node detection degree and attack range. Router network has the same structural vulnerability with ER network, which means Router network also has randomness.
Mingshu He; Xiaojuan Wang; Jingwen You; Zhen Wang. Analysis on Structural Vulnerability Under the Asymmetric Information. Computer Vision 2018, 503 -515.
AMA StyleMingshu He, Xiaojuan Wang, Jingwen You, Zhen Wang. Analysis on Structural Vulnerability Under the Asymmetric Information. Computer Vision. 2018; ():503-515.
Chicago/Turabian StyleMingshu He; Xiaojuan Wang; Jingwen You; Zhen Wang. 2018. "Analysis on Structural Vulnerability Under the Asymmetric Information." Computer Vision , no. : 503-515.