With the rapid advancement of the Internet and the proliferation of Internet of Things (IoT) devices, the diversity of malicious URLs has increased. These changes are reflected not only in their increasing number but also in the escalating technological complexity, which poses significant security threats to IoT networks. Traditional detection methods relying on manual rules or specific patterns are insufficient to address these challenges. There is a pressing need for more sophisticated URL detection techniques to enhance the accuracy and comprehensiveness of malicious URL identification, especially in IoT environments. This study integrates the feature purification network FP-net into malicious URL classification and introduces the FCBA model utilizing CNN-BiLSTM-Attention as the feature extractor for FP-net. The model employs CNN for effective local feature extraction, BiLSTM for capturing sequence information, and incorporates the attention mechanism. Experimental findings indicate that the FCBA model achieves an accuracy of 94.66
In order to further study the development of autonomous cruise control vehicle systems and explore their applications in environmental perception, automatic obstacle avoidance, information processing and other aspects. The autonomous cruise control vehicle system based on Internet of Things technology is a highly integrated control system. The core technology lies in the application of the Internet of Things, which connects vehicles in real-time with the surrounding environment, other vehicles, and cloud platforms through wireless communication technology, It uses the vehicle system to construct a real-time map and uses visual recognition positioning technology to perceive the surrounding environment, there by achieving automatic recognition and avoidance of obstacles. The vehicle system makes corresponding instructions that comply with obstacles based on information algorithms, Plan a cruise path for the autonomous cruise control system in the established environmental map and together completes specific tasks such as mapping, obstacle avoidance navigation, QR code recognition and machine voice of the vehicle system.
The exponential growth in network users due to the rapid development of internet hardware and software has made Ethernet an integral part of the underlying links in today’s interconnected networks after two decades of evolution. This paper introduces a design for a dual-network redundant Ethernet controller based on FPGA, aimed at improving the reliability and robustness of network systems where physical layer devices are prone to errors. The controller is capable of real-time switching between two network channels, ensuring uninterrupted data flow even in the event of a default channel failure or data transmission error. Functional simulations have demonstrated the controller’s ability to switch to the redundant channel instantly when an error is detected, maintaining the integrity of data reception. The design principles, implementation techniques, and simulation results are discussed, highlighting the potential of this solution for enhancing network stability in critical applications. The paper also suggests directions for future research, including considerations for power consumption, heat dissipation, and scalability.
To accurate management the resource devices in optical communication networks that cannot automatically report their own information, this paper studies a digital twin system for intelligent management of dumb resources in optical communication networks. Firstly, the construction principles of digital twin system for dumb resource management in optical communication network are studied. Then the data capture methods of different dumb resources are analyzed to solve the problem in dumb resources. Finally, the analysis methods of dumb resource data are studied, and the isolated forest algorithm and the image detection algorithm YOLOv7 for dumb resource detection are applied to realize the analysis of dumb resource data. The application of optical communication dumb resource intelligent management digital twin system can realizes the effective management of dumb resources.
In recent years, human-computer interaction technology has become increasingly mature, and equipment based on human-computer interaction technology, such as mechanical exoskeletons, has also begun to be used in military, medical and sports rehabilitation fields. Among them, myoelectric signal is the cornerstone of controlling human-computer interaction devices, and its feature extraction and classification recognition quality are related to the performance of such devices. Nowadays, the EMG signal processing module still has shortcomings in signal preprocessing, feature extraction and classification recognition, in view of this problem, this thesis designs a surface electromyography signal (sEMG) classification recognition system, and innovatively improves the Ensemble Empirical Mode Decomposition method(EEMD) in the signal processing process. A two-layer ensemble classifier using the support vector machines (SVM) algorithm and the gradient boosting decision tree (GBDT) algorithm built by stacking fusion strategy is designed to improve the accuracy of human motion classification recognition based on myoelectric signals.
