Integrating Fifth Generation Communication Network (5G) with Time-Sensitive Networking (TSN) is essential for deterministic Industrial Internet of Things (IIoT). It is a challenge to provide ultra-reliable and deterministic services for time-triggered (TT) flow in the integrated TSN-5G network. In this paper, we propose PTFRS, a Proximal Policy Optimization (PPO)-based time–frequency resource scheduling approach that provides ultra-reliable and deterministic services for TT flow in 5G channel quality fluctuations. PTFRS applies a residual neural network (ResNet)-based convolutional neural network (CNN) (ResNet-based CNN) as a shared state encoder to extract high-dimensional features from the environment state. Then, based on these embeddings, the model jointly optimizes the allocation of sending time offsets, queue shifts, and resource blocks (RBs) using PPO. The auction expert algorithm serves as a guide in the PTFRS, helping the agent develop a more effective resource block allocation strategy for the UEs. The experimental results show that PTFRS reduces end-to-end delay by 26.16%, 14.17% over PPO-RB and DetTsch DRL algorithms and improves TT scheduling success by 20.3%, 53.4%, and 20.9% over PPO-Sym, PPO-RB, and DetTsch DRL algorithms, respectively. The PTFRS algorithm significantly reduces end-to-end delay and significantly enhances the scheduling success ratio and reliability performance. Our proposed PTFRS stabilizes and accelerates the model learning compared to the other existing deep reinforcement learning (DRL) algorithms. Consequently, the proposed PTFRS can provide ultra-reliable, low-latency, and deterministic services for TT flows in the integrated TSN-5G network.

Time-Sensitive Networking (TSN) supports mixed-criticality communication by integrating Time-Triggered (TT) and Audio Video Bridging (AVB) traffic within a unified network infrastructure. While TT flows benefit from deterministic scheduling through the Time-Aware Shaper (TAS), their presence can increase the worst-case delay (WCD) experienced by AVB traffic. However, many existing AVB-aware TT scheduling approaches incur high computational costs and lack a theoretical foundation for analyzing the impact of TT routing on AVB performance. To address these limitations, this article presents a unified routing and scheduling framework that jointly optimizes TT communication while systematically improving AVB performance. At the core of our method is a network calculus-based analysis that derives a theoretical lower bound on AVB WCD under TT interference. This bound is consistently leveraged in both the routing and scheduling stages: first, to define a flow-level metric called Impact on WCD (IoW) that guides AVB-aware routing decisions; and second, to introduce an AVB-Aware Idle Constraint that regulates TT offsets to shape residual bandwidth for AVB traffic. Extensive experiments across diverse topologies and traffic patterns demonstrate that the proposed framework significantly improves AVB schedulability and delay bounds while maintaining TT feasibility with low computational overhead. These results confirm the practicality and effectiveness of a tightly integrated approach to TSN configuration for mixed-criticality systems.

With the rapid evolution of 5G/6G networks, deterministic services such as the Industrial Internet, vehicular communications, and immersive applications impose stringent end-to-end (E2E) latency guarantees. Efficient resource allocation for E2E network slicing (NS) is therefore required to simultaneously satisfy strict latency constraints and improve overall resource efficiency. However, orchestrating cross-domain and multidimensional resources across the radio access network (RAN) and core network (CN) remains challenging due to strong coupling and scalability issues. To address this problem, this paper develops a profit-driven optimization framework for static E2E NS, which jointly accounts for deterministic service guarantees and system profitability. On the RAN side, a hybrid genetic algorithm (HGA) is developed to preserve the global exploration capability of genetic algorithms, while incorporating a gradientguided resource scaling (GGRS) operator to refine elite solutions and improve solution quality. On the CN side, we design a capacity-aware workload balancing algorithm (CA-WLB). For each candidate path, CA-WLB couples capacity adaptive virtual network function (VNF) placement with demand responsive CPU allocation to jointly optimize latency and resource consumption, and then selects the path that yields the maximum profit. Extensive simulations across a wide range of scenarios demonstrate that the proposed framework consistently outperforms conventional heuristic and meta-heuristic approaches, while achieving performance close to high-complexity optimization benchmarks with significantly reduced computational overhead.

Deep learning is widely used in many fields, but the emergence of adversarial examples threatens the application of deep learning. Various methods have been proposed to defend against adversarial attacks. However, existing defense methods either can only detect adversarial examples without restoring their original classes or merely focus on verifying the input category and attempting to recover the classes of adversarial examples while lacking awareness of whether the input has been perturbed. To develop defense approaches that simultaneously achieve both detection and correction capabilities, a heterogeneous model combinatorial defense framework (HMCDF) is proposed for adversarial attacks in this paper. In particular, we first summarize the fundamental operations, block structures, and compositional patterns that constitute the model, while analyzing how these factors influence both the functionality and robustness of the model. According to the differences in the structure of the models, the models can be divided into isomorphic models and heterogeneous models. Then, we combine heterogeneous models to construct a heterogeneous model defense framework. Within this framework, as long as a majority of models can detect adversarial examples and restore their original labels, the voting mechanism used in the framework can determine whether the input has been perturbed, ultimately outputting legitimate labels through collective decision‐making. To validate the performance, we conduct extensive experiments on three public datasets: CIFAR‐10, SVHN, and Mini‐ImageNet. After sufficient analysis of the simulation results, we find that our proposed method outperforms the others for the detection of adversarial attacks generated by the considered attack methods and can recover the classes of the adversarial examples.

Time-Sensitive Networking (TSN) is a new technology developed from Ethernet that guarantees deterministic transmission of various types of flows, such as Time-triggered (TT) flows and Audio-video-bridging (AVB) flows, in the same network. Currently, Time-aware Shaping (TAS) and Credit-based Shaping (CBS) are widely used for scheduling hybrid flows, where the credit value in CBS is directly linked to the logical bandwidth value idleSlope , which affects the real-time performance of AVB flows. However, as the network scale increases, existing bandwidth allocation methods result in higher computation times and lower allocation success rates. In this article, the aforementioned problem is addressed by two-step: first, we design a load-balanced routing heuristic (LBRH) to improve the allocation success rate; second, we accelerate the CBS bandwidth allocation by using unified bandwidth allocation scheme, which integrates LBRH and further improves the allocation success rate. Performance evaluation in multiple test cases shows that LBRH can improve the success rate of bandwidth allocation, and the unified bandwidth allocation scheme integrating LBRH significantly reduces the overall execution time while improving the success rate of bandwidth allocation, which is more suitable for large-scale TSN networks with complex routing.

Gaze-only input techniques in VR face the challenge of avoiding false triggering due to continuous eye tracking while maintaining interaction performance. In this paper, we proposed GazeDock, a technique for enabling fast and robust gaze-based menu selection in VR. GazeDock features a view-fixed peripheral menu layout that automatically triggers appearing and selection when the user’s gaze approaches and leaves the menu zone, thus facilitating interaction speed and minimizing the false triggering rate. We built a dataset of 12 participants’ natural gaze movements in typical VR applications. By analyzing their gaze movement patterns, we designed the menu UI personalization and optimized selection detection algorithm of GazeDock. We also examined users’ gaze selection precision for targets on the peripheral menu and found that 4–8 menu items yield the highest throughput when considering both speed and accuracy. Finally, we validated the usability of GazeDock in a VR navigation game that contains both scene exploration and menu selection. Results showed that GazeDock achieved an average selection time of 471ms and a false triggering rate of 3.6%. And it received higher user preference ratings compared with dwell-based and pursuit-based techniques.

Thanks to the great advancement of cognitive computing, artificial intelligence, big data, and the Internet of Things (IoT) technologies, the fusion of the physical and virtual worlds is changing people’s lifestyles. Although the research and deployment of cyber-physical systems (CPSs) are notably promoted by cognitive computing, the reliability and large-scale application of CPSs are still significantly challenged by some security issues. Therefore, it is meaningful to clarify and address the weaknesses of current intrusion detection methods for CPSs and enhance the ability to identify, analyze, and predict to improve the performance of intrusion detection. In this article, we first propose a novel self-learning spatial distribution algorithm, named Euclidean distance-based between-class learning (EBC learning), which improves between-class learning by calculating the Euclidean distance (ED) among$k$-nearest neighbors of different classes. In addition, a cognitive computing-based intrusion detection method named border-line SMOTE and EBC learning based on random forest (BSBC-RF) is also proposed based on the EBC learning for industrial CPSs. The experimental results over a real industrial traffic dataset show that the proposed EBC learning has strong spatial constraint capability and can improve the prediction and recognition performance. Compared with the eight state-of-the-art methods, the proposed method has an ACC exceeding 99.5%, false alarm rate (FAR) less than 0.06%, and$F1$close to 0.99, which is still superior to other ones.

Ray-casting, i.e., a ray cast from a hand-held controller to select targets, is widely used in 3D environments. Inspired by the bubble cursor [12] which dynamically resizes its selection range on 2D surfaces, we investigate a bubble mechanism for ray-casting in virtual reality. Bubble mechanism identifies the target nearest to the ray, with which users do not have to accurately shoot through the target. We first design the criterion of selection and the visual feedback of the bubble. We then conduct two experiments to evaluate ray-casting techniques with bubble mechanism in both simple and complicated 3D target acquisition tasks. Results show the bubble mechanism significantly improves ray-casting on both performance and preference, and our Bubble Ray technique with angular distance definition is competitive compared with other target acquisition techniques. We also discuss potential improvements to show more practical implementations of ray-casting with bubble mechanism.

Distributed Denial of Service (DDoS) attack is a stubborn network security problem. Various machine learning-based methods have been proposed to detect such attacks. According to our survey, the features used to characterize the attack are usually selected manually according to some personal understanding, and the detection model is expected to perform good generalization performance in practical detection all the time. Therefore, how to select the optimal features that perform the best performance is a critical problem for constructing an effective detector. Meanwhile, as network traffic gets increasingly complex and changeable, some original features may become incapable of characterizing current traffic, and detector failure could occur when traffic changes. In this paper, we chose the multilayer perceptrons (MLP) to demonstrate and solve the proposed problem. In our solution, we combined sequential feature selection with MLP to select the optimal features during the training phase and designed a feedback mechanism to reconstruct the detector when perceiving considerable detection errors dynamically. Finally, we validated the effectiveness of our method and compared it with some related works. The results showed that our method could yield comparable detection performance and correct the detector when it performed poorly.

Split keyboards are widely used on hand-held touchscreen devices (e.g., tablets). However, typing on a split keyboard often requires eye movement and attention switching between two halves of the keyboard, which slows users down and increases fatigue. We explore peripheral typing, a superior typing mode in which a user focuses her visual attention on the output text and keeps the split keyboard in peripheral vision. Our investigation showed that peripheral typing reduced attention switching, enhanced user experience and increased overall performance (27 WPM, 28% faster) over the typical eyes-on typing mode. This typing mode can be well supported by accounting the typing behavior in statistical decoding. Based on our study results, we have designed GlanceType, a text entry system that supported both peripheral and eyes-on typing modes for real typing scenario. Our evaluation showed that peripheral typing not only well co-existed with the existing eyes-on typing, but also substantially improved the text entry performance. Overall, peripheral typing is a promising typing mode and supporting it would significantly improve the text entry performance on a split keyboard.

The Neighbor Discovery Protocol (NDP) is one of the main protocols in the Internet Protocol version 6 (IPv6) suite, and it provides many basic functions for the normal operation of IPv6 in a local area network (LAN), such as address autoconfiguration and address resolution. However, it has many vulnerabilities that can be used by malicious nodes to launch attacks, because the NDP messages are easily spoofed without protection. Surrounding this problem, many solutions have been proposed for securing NDP, but these solutions either proposed new protocols that need to be supported by all nodes or built mechanisms that require the cooperation of all nodes, which is inevitable in the traditional distributed networks. Nevertheless, Software-Defined Networking (SDN) provides a new perspective to think about protecting NDP. In this paper, we proposed an SDN-based authentication mechanism to verify the identity of NDP packets transmitted in a LAN. Using the centralized control and programmability of SDN, it can effectively prevent the spoofing attacks and other derived attacks based on spoofing. In addition, this mechanism needs no additional protocol supporting or configuration at hosts and routers and does not introduce any dedicated devices.

This paper presents an approach for detecting and resolving feature interactions (FI) in telephone systems. In this approach, the basic telephone system (POTS) and the features are each represented as a temporal colored Petri net (TCP-net). When the POTS is enhanced with some features, their TCP-nets are integrated. The functionality of a feature is represented as a temporal formula and the behavior of the enhanced system is represented as the set of all firing sequences each of which realizes a transition-invariant of the TCP-net representing the feature. FI can be detected by inspecting whether or not the temporal formula is violated when executing some of these firing sequences. Three theorems are provided for finding realizing sequences and detecting FIs. Detailed examples are used to illustrate the specification of telephone features and the detection and resolution of FIs.

Proposes an approach to the synthesis and analysis of a FMS with a place/transition net. In this approach, a use case is represented as a firing sequence and is used to construct a net representing each working entity (e.g. a manufacturing machine) or the whole system, while invariance-preserving transformations are used to ensure place and transition invariants are preserved during synthesis and simplification. A detailed example is used for illustration.