Fake news detection has been a more urgent technical demand for operators of online social platforms, and the prevalence of deep learning well boosts its development. From the model structure, existing research works can be categorized into three types: convolution filtering-based neural network approaches, sequential analysis-based neural network approaches, and attention mechanism-based neural network approaches. However, almost all of them were developed oriented to scenes of a single language, without considering the context of mixed languages. To bridge such gap, this article extends to the basic pretraining language processing model transformer into the multiscale format and proposes a novel fake news detection model for the context of mixed languages through a multiscale transformer to fully capture the semantic information of the text. By extracting more fruitful feature levels of initial textual contents, it is expected to obtain more resilient feature spaces for the semantics characteristics of mixed languages. Finally, experiments are conducted on a postprocessed real-world dataset to illustrate the efficiency of the proposal by comparing performance with four baseline methods. The results obtained show that the proposed method has an accuracy of about 2%–10% higher than commonly used baseline models, indicating that the scheme has appropriate detection efficiency in mixed language scenarios.

The Finance-level Artificial Intelligence of Things (AIoT) is going to become a novel media in the 6G-driven digital society. Inside the financial AIoT environment, large-scale crowd credit assessment with the guarantee of low latency has been a general demand. Facing limited computational resources, there is still a lack of effective computation offloading methods for this purpose to ensure low latency. In order to deal with such an issue, this paper introduces edge computing mode and proposes a low-latency edge computation offloading scheme for trust evaluation in financial AIoT. With different elements involved in the assessment process being denoted via mathematical description, a multi-objective optimization problem with constraints is formulated. Then, the aforementioned optimization problem is solved by a specific search algorithm, so that optimal task offloading schemes can be found. To assess the performance of the proposal, some simulation experiments are conducted to verify the proposed task offloading method. And it can be reflected from numerical results that latency can be well reduced compared with baseline methods.

The unmanned aerial vehicle-assisted 6G supported intelligent transportation systems (UAV-assisted 6G-ITS) have great potential to make transportation systems efficient, smart, and sustainable. However, when connected and autonomous vehicles communicate with UAVs, it can lead to issues such as energy consumption and overlapping interference, which can affect system performance. Therefore, this paper proposes an interference tolerance-based energy harvesting (EH) resource allocation (IT-EHRA) strategy, aiming to improve the energy efficiency (EE) of UAV-assisted 6G-ITS and mitigate the overlapping interference. Firstly, we established an interference hypergraph model and analyzed the types and relationships of interference in the network. Based on this model, an interference tolerance method was designed to alleviate overlapping interference. Then, an EH optimization model with imperfect channel state information (CSI) is proposed based on the interference model, aiming to maximize the network EE and reduce energy consumption. Finally, we adopt the IT-EHRA algorithm to reduce the impact of imperfect CSI and use duality theory to obtain the optimal solution, thereby achieving maximum network EE. Simulation results show that the algorithm effectively ensures the EE requirements of the network, improves the throughput of the network, and promotes the sustainable development of the network.

Effective data management schemes have always been the major demand in universal industrial Internet of Things (IoT) systems, especially in resource-constrained scenarios. In realistic wastewater treatment process (WTP), only limited monitoring data resource can be available due to some digital constraint. Aiming at this practical issue, this work explores utilization of deep neural network to deal with such practical issue in the objective situation. Therefore, a deep learning-based data management scheme for intelligent control of WTP under resource-constrained IoT systems, is proposed in this paper. Firstly, a specific data encoding and preprocessing approach is developed for the objective business scenario. Then, the detailed workflow of a deep neural network structure is applied to predict key intermediate parameters which can further guide control decision. Finally, a comprehensive series of experiments are conducted on a real-world dataset which covers a range of one year. Both efficiency and robustness of the proposal are tested by introducing several performance metrics. The results show that it can have proper prediction effect in such resource-constrained environment, which can facilitate following intelligent control operations.

The urban sensing provides a fundamental computing environment for smart cities, in which ubiquitous vehicular networks are an important component. Due to the limitation of urban sensing resource, roadside units (RSU) are sparsely deployed in freeway-oriented vehicular networks. Thus, communication resources cannot cover all the vehicles everywhere and communication blind areas exist among RSUs. In urban sensing-based vehicular networks, the uncompleted content downloads of a vehicle within the current RSU range will be continued in the next RSU range. This will inevitably lead to some delay and influence user experience. To deal with such a challenge, this paper proposes a novel vehicle-road urban sensing framework, in order to realize collaborative content delivery in freeway-oriented vehicular networks. It utilizes the collaboration of vehicle-to-vehicle communication and vehicle-to-infrastructure communication, and set up a corresponding content delivery mechanism oriented to the same direction and opposite direction of the object vehicle. Specifically, the proposed urban sensing framework develops a node clustering strategy for vehicles cruising in the same direction and a cooperative download strategy for vehicles cruising in the opposite direction, respectively. On this basis, theoretical analysis towards the whole collaborative content delivery framework is carried out, in order to assess the performance of the proposal. The simulation results show that the proposal can have proper delivery ability under the guarantee of low latency.