Hand Gesture Recognition (HGR) using Frequency Modulated Continuous Wave (FMCW) radars is difficult because of the inherent variability and ambiguity caused by individual habits and environmental differences. This paper proposes a deformable dual-stream fusion network based on CNN-TCN (DDF-CT) to solve this problem. First, we extract range, Doppler, and angle information from radar signals with the Fast Fourier Transform to produce range-time (RT) and range-angle (RA) maps. Then, we reduce the noise of the feature map. Subsequently, the RAM sequence (RAMS) is generated by temporally organizing the RAMs, which captures a target’s range and velocity characteristics at each time point while preserving the temporal feature information. To improve the accuracy and consistency of gesture recognition, DDF-CT incorporates deformable convolution and inter-frame attention mechanisms, which enhance the extraction of spatial features and the learning of temporal relationships. The experimental results show that our method achieves an accuracy of 98.61%, and even when tested in a novel environment, it still achieves an accuracy of 97.22%. Due to its robust performance, our method is significantly superior to other existing HGR approaches.

Next‐generation 6G networks will fully drive the development of the industrial Internet of Things. Steel surface defect detection as an important application in industrial Internet of Things has recently received increasing attention from the military industry, the aviation industry and other fields, which is closely related to the quality of industrial production products. However, many typical convolutional neural networks‐based methods are insensitive to the problem of unclear boundaries. In this article, the authors develop a region‐based fully convolutional networks with deformable convolution and attention fusion to adaptively learn salient features for steel surface defect detection. Specifically, deformable convolution is applied into selectively replace the standard convolution in the backbone of the region‐based fully convolutional networks, which performs significantly in scenarios with unclear defect boundaries. Moreover, convolutional block attention module is utilised in region proposal network to further enhance detection accuracy. The proposed architecture is demonstrated on two popular steel defect detection benchmarks, including NEU‐DET and GC10‐DET, which can effectively present the performance of steel surface defect detection by abundant experiments. The mean average precision on two datasets reaches 80.9% and 66.2%. The average precision of defect crazing, inclusion, patches, pitted‐surface, rolled‐in scale and scratches on NEU‐DET is 58.2%, 82.3%, 95.7%, 85.6%, 75.9%, and 87.9% respectively.

We develop a deep-learning-based multicrane visual sorting system with virtualized programmable logic controllers (PLCs) in intelligent manufacturing, which enables the accurate location and suction of the materials on the conveyor belt. First, virtualized PLCs are deployed in the field and the cloud to break data islands for efficient communication between low-level devices. Second, artificial intelligence algorithms are integrated into the physical industrial control system in which cooperation between virtualized PLCs and the visual recognition model is developed to complete the industrial control closed loop. Third, we establish a visual recognition model in which object detection algorithms are used to process the original image and then obtain the position and type of the object in the pixel coordinate system. In addition, a new linear interpolation-based backpropagation neural network is presented to provide the transform relation between the pixel coordinate system and the world coordinate system that the crane needs to precisely suck the material. The whole system is applied in a time-sensitive network environment in a highly reliable and stable manner. The experimental prototype system demonstrates that high recognition accuracy can be achieved for the visual sorting system within an acceptable time frame. The accuracy of the sorting task reaches 96.5% and the average consumption time of each object is approximately 2.317 s when the speed of the conveyor belt is 5.2 m/min.

With the evolution of the 5th generation (5G) and the advent of the 6th generation (6G) mobile communication technologies, the consumer Internet of Things (CIoT) has emerged as a critical enabler for ubiquitous information exchange across diverse applications. The integration of sensing and communication (ISAC) offers significant potential to enhance communication performance by leveraging multimodal heterogeneous data collected through sensors in CIoT systems. This paper presents a comprehensive discussion on multimodal heterogeneous data-based environment sensing and its integration with communication in CIoT systems. We provide an overview of multimodal ISAC in CIoT, addressing the need for advanced environment understanding and optimization of network performance. Furthermore, we introduce a novel ISAC framework that integrates semantic environmental mapping, beam management, and resource allocation to improve communication efficiency. The concept of a semantic environment map (SEM) is proposed, which fuses multimodal sensing data for precise environment recognition and adaptive communication strategies. Additionally, we identify key future trends and challenges, including performance evaluation, multimodal data transmission, and security, and then propose a roadmap for future research. This paper aims to bridge the gap between multimodal sensing and communication in CIoT systems, offering insights into integrating advanced technologies such as artificial intelligence (AI) and 6G for smarter, more connected consumer applications.

This article investigates the joint scheduling of cross-channel traffic resources in 5G-time-sensitive networks (TSNs) and proposes an adaptive prediction method suitable for cross-domain channel state information (CSI). First, we analyze the 5G-TSN cross-domain data forwarding mechanism by leveraging the architecture of the 5G-TSN bridging network and combining the functions of 5G and TSN network elements. Second, we propose a representation method for the 5G-TSN cross-network wireless CSI, specifically the data transmission delay information, as a data set for channel quality prediction. This serves as a data foundation for subsequent intelligent prediction. Next, to make better use of the local information of channel state and achieve fast convergence, we employ an extreme learning machine autoencoder (ELM-AE) prediction logic based on deep extreme learning machine (DELM) and introduce the dung beetle optimizer (DBO) algorithm to improve the DELM regression prediction. We perform prediction and analysis of the 5G channel delay and TSN domain data transmission delay. Then, we use the 5G-TSN CSI, collected in practice, as the data source to train and test the wireless channel delay indicators, which helps form the 5G-TSN channel model. Finally, we build a laboratory transmission prototype test bed for 5G-TSN cross-network transmission and conduct end-to-end transmission delay testing based on the proposed offline-generated channel model. The results demonstrate that the channel prediction model enables the end-to-end delay to decrease to less than 5 ms, the cross-network time synchronization accuracy to reduce to less than 100 ns, and the relevant performance indicators to reach industry-leading levels.

Future environmental perception in the Industrial Internet of Things (IIoT) is expected to interconnect massive sensing objects, merge various intelligent technologies, and efficiently control devices to adapt a complex environment. It will optimize overall production value, including improving product quality, promoting multi-sensor collaboration, and decreasing energy consumption and costs. Current environmental perception (EP) perceives the industrial environmental information through industrial sensors that are controlled by traditional programmable logic controllers (PLCs), but the sensors are not capable of collaboration and intercommunication. Some sensors are difficult to deploy in the terminal and can easily be corrupted in a harsh environment. In addition, current EP lacks intelligent analysis of massive sensing data. Therefore, it is necessary to use the latest emerging techniques including knowledge graph, artificial intelligence (AI) algorithms, and cloud control, to create environmental intelligent perception (EIP) in the industry. In this article, an overview of challenges for EP in a complex industrial environment is provided, potential schemes for designing EIP architectures are given, and potential practical application scenarios are discussed. Finally, a case study analysis of a multi-crane visual sorting system is presented in the experiment, in which two mechanical arms operate cooperatively with the help of cloud PLCs and visual recognition algorithm.