The Machine Learning Ensemble for Analyzing Internet of Things Networks:Botnet Detection and Device Identification

The rapid proliferation of Internet of Things(IoT)technology has facilitated automation across various sectors.Nevertheless,this advancement has also resulted in a notable surge in cyberattacks,notably botnets.As a result,research on network analysis has become vital.Machine learning-based techniques for network analysis provide a more extensive and adaptable approach in comparison to traditional rule-based methods.In this paper,we propose a framework for analyzing communications between IoT devices using supervised learning and ensemble techniques and present experimental results that validate the efficacy of the proposed framework.The results indicate that using the proposed ensemble techniques improves accuracy by up to 1.7%compared to singlealgorithm approaches.These results also suggest that the proposed framework can flexibly adapt to general IoT network analysis scenarios.Unlike existing frameworks,which only exhibit high performance in specific situations,the proposed framework can serve as a fundamental approach for addressing a wide range of issues.

An accurate identification method for network devices based on spatial attention mechanism

With the metaverse being the development direction of the next generation Internet,the popularity of intelligent devices,and the maturity of various emerging technologies,more and more intelligent devices try to connect to the Internet,which poses a major threat to the management and security protection of network equipment.At present,the mainstream method of network equipment identification in the metaverse is to obtain the network traffic data generated in the process of device communication,extract the device features through analysis and processing,and identify the device based on a variety of learning algorithms.Such methods often require manual participation,and it is difficult to capture the small differences between similar devices,leading to identification errors.Therefore,we propose a deep learning device recognition method based on a spatial attention mechanism.Firstly,we extract the required feature fields from the acquired network traffic data.Then,we normalize the data and convert it into grayscale images.After that,we add a spatial attention mechanism to CNN and MLP respectively to increase the difference between similar network devices and further improve the recognition accuracy.Finally,we identify devices based on the deep learning model.A large number of experiments were carried out on 31 types of network devices such as web cameras,wireless routers,and smartwatches.The results show that the accuracy of the proposed recognition method based on the spatial attention mechanism is increased by 0.8%and 2.0%,respectively,compared with the recognition method based only on the deep learning model under the CNN and MLP models.The method proposed in this paper is significantly superior to the existing method of device-type recognition based only on a deep learning model.

RFID Based e-quality Tracking in Service-oriented Manufacturing Execution System

The method of acquiring the real-time data has influenced the implementation of the manufacturing execution system （MES）. Accompanied with turning the MES into service-oriented manufacturing execution system （so-MES）, real-time e-quality tracking （e-QT）, in which real-time data are computed, has played more and more important roles in manufacturing. This paper presents an e-QT model through the study of real-time status data tracking and quality data collecting. An implementing architecture of the e-QT model is constructed on the basis of radio frequency identification devices （RFID） data-tracking network. In order to develop the e-QT system, some key enabling technologies, such as configuration, data collection, and data processing, etc, are studied. The relation schema between hardware is built for the RFID data-tracking network based on the configuration technique. Real-time data are sampled by using data collecting technique. Furthermore, real-time status and quality data in a shop-floor can be acquired in terms of using the real-time data computing method. Finally, a prototype system is developed and a running example is given so as to verify the feasibility of methods proposed in this paper. The proposed research provides effective e-quality tracking theoretical foundation through the use of RFID technology for the discrete manufacturing.

Power Grid Fault Diagnosis Based on Deep Pyramid Convolutional Neural Network

Existing power grid fault diagnosis methods relyon manual experience to design diagnosis models, lack theability to extract fault knowledge, and are difficult to adaptto complex and changeable engineering sites. Considering thissituation, this paper proposes a power grid fault diagnosismethod based on a deep pyramid convolutional neural networkfor the alarm information set. This approach uses the deepfeature extraction ability of the network to extract fault featureknowledge from alarm information texts and achieve end-to-endfault classification and fault device identification. First, a deeppyramid convolutional neural network model for extracting theoverall characteristics of fault events is constructed to identifyfault types. Second, a deep pyramidal convolutional neuralnetwork model for alarm information text is constructed, thetext description characteristics associated with alarm informationtexts are extracted, the key information corresponding to faultsin the alarm information set is identified, and suspicious faultydevices are selected. Then, a fault device identification strategythat integrates fault-type and time sequence priorities is proposedto identify faulty devices. Finally, the actual fault cases and thefault cases generated by the simulation are studied, and theresults verify the effectiveness and practicability of the methodpresented in this paper.