Integrated Sensing and Communication (ISAC) technology provides robust support for the development of the Internet of Things (IoT) by leveraging its powerful sensing and communication capabilities. Sensing-assisted beam prediction techniques effectively enhance the communication quality and efficiency of ISAC systems, which is crucial for achieving high-speed and stable communication among IoT devices. However, ensuring high accuracy in beam prediction typically relies on traditional centralized architectures, which intrinsically pose risks to privacy and security when the central server is compromised. Therefore, this inherent trade-off between high prediction accuracy and data security poses significant challenges in privacy-sensitive IoT deployments. To resolve this fundamental contradiction, we propose a federated CNN-Transformer method for distributed sensing-assisted beam prediction in ISAC systems. Specifically, We propose an improved federated learning (FL) framework where clients transmit not only gradients but also nonlinear features to the server for subsequent computations through task offloading while enforcing client data privacy security. Addressing this problem is particularly challenging due to scattering and noise issues in the propagation of radar sensing signals. To address this, we design a hybrid model that integrates CNN and Transformer for the client side, which effectively captures both local and global features of the sensing signals, thereby improving prediction accuracy. Experimental results demonstrate that, compared to traditional centralized methods, our proposed method not only achieves significant improvements in prediction accuracy but also offers unique advantages in terms of data privacy and security, mitigating the risk of data leakage.

The widespread application of cloud services make users pay more attention to Quality of Service (QoS). Generally, the user cannot call all services simultaneously to obtain corresponding QoS data and can only choose a service from a few known data, thus it’s critical to predict unknown QoS values. A third-order tensor can model temporal patterns of QoS data, and studies indicate that the tensor latent factor analysis models based on Canonical Polyadic (CP) decomposition can effectively capture temporal patterns to predict unknown data in QoS. However, the existing CP decomposition-based models limit their learning ability since rank-one tensors contain less structure information, which results in low prediction accuracy. Therefore, this paper proposes a Biased Block Term Tensor Decomposition (BBTTD) model to achieve high accuracy for temporal pattern-aware QoS prediction. It mainly adopts the following three-fold ideas: (a) implementing a tensor learning model by adopting the block term decomposition in rank-([Formula: see text], [Formula: see text], 1) terms; (b) proposing the bias block term tensors to enhance the model’s prediction accuracy; (c) designing a nonnegative multiplication update algorithm to learning model parameters. Extensive experiments on two public dynamic QoS datasets demonstrate that BBTTD has higher prediction accuracy compared with several QoS prediction models.

The digitization and intellectualization have been envisioned as the fundamental basis for future Industrial Internet of things, which integrates sensor technology, industrial control technology, communication technology, and artificial intelligence (AI). Specifically, the collaboration among these above techniques is crucial for the successful implementation of intelligent applications. This article develops an end-to-end visual control framework to accomplish multi-crane collaborative sorting in wireless time sensitive networking (TSN) networks. The design primarily incorporates field devices, data transmission, artificial intelligence (AI), and industrial control. An advanced binocular stereo visual recognition model based on deep learning is investigated to accurately obtain the world coordinates and types. A cooperative control scheduling model that combines a scheduling strategy with an anti-collision strategy is presented to effectively control multiple cranes for sorting tasks. The device data and commands are transmitted through industrial 5G-TSN integrated network for ultra-reliable, low-latency, and deterministic transmission. The proposed visual sorting system is further validated through the establishment of an experimental prototype, demonstrating its exceptional real-time performance while enabling flexible intelligent manufacturing.

A dynamic directed graph (DDG) can describe complex dynamic interactions among massive entities, for example, traffic transmissions in a metropolitan area network (MAN), in a natural way. Due to the rapid expansion of a network, it is impossible to capture all the interactions at each time slot, making a resultant DDG be high-dimensional and incomplete (HDI). A nonnegative latent factorization of tensors (NLFT) model has proven to be highly efficient in extracting desired knowledge from an HDI DDG. Nevertheless, an existing NLFT model attempts to be easily affected by the instantaneous data fluctuations. Motivated by this discovery, this article innovatively proposes a convolution bias-incorporated NLFT (CB-NLFT) model with threefold ideas: 1) utilizing the Tucker decomposition framework for accurately representing the complex patterns hidden in an HDI DDG; 2) establishing a novel convolution bias scheme for precisely depicting the instantaneous data fluctuations; and 3) theoretically proving the CB-NLFT model’s convergence. Extensively empirical studies on six real-world datasets illustrate that the proposed CB-NLFT achieves significantly higher accuracy and computational efficiency when addressing the representation learning to a DDG in comparison with state-of-the-art models.

A Dynamically Weighted Directed Network (DWDN) is usually used to describe a complex interaction system, such as the Internet of Things, where a weighted directed link denotes a specific interaction between a pair of entities. Typically, there are numerous missing links in a DWDN due to practical limitations. A Latent Factorization of Tensors (LFT)-based link prediction method proves to be effective in predicting weighted directed links. However, current LFT-based predictor is often built based on the Canonical Polyadic (CP) decomposition, its prediction ability is limited due to its small latent feature space. To address this issue, this work proposes a Tensor Ring decomposition-based Biased Latent-factorization-of-tensors (TRBL) model with three interesting ideas: 1) adopting tensor ring decomposition to build an LFT model for obtaining a larger latent feature space; 2) utilizing linear biases to model data fluctuations for boosting prediction accuracy; and 3) introducing the single latent factor-dependent, nonnegative and multiplicative update on tensor algorithm for achieving fast convergence. Experimental studies on four real DWDNs demonstrate that compared with state-of-the-art models, the proposed TRBL model achieves higher accuracy and competitive convergence rate on predicting the missing weighted directed links of a DWDN.

Dynamic community detection is crucial for elucidating the temporal evolution of social structures, information dissemination, and interactive behaviors within complex networks. Nonnegative matrix factorization provides an efficient framework for identifying communities in static networks but fall short in depicting temporal variations in community affiliations. To solve this problem, this paper proposes a Modularity maximization-incorporated Nonnegative Tensor RESCAL Decomposition (MNTD) model for dynamic community detection. This method serves two primary functions: a) Nonnegative tensor RESCAL decomposition extracts latent community structures in different time slots, highlighting the persistence and transformation of communities; and b) Incorporating an initial community structure into the modularity maximization algorithm, facilitating more precise community segmentations. Comparative analysis of real-world datasets shows that the MNTD is superior to state-of-the-art dynamic community detection methods in the accuracy of community detection.

In the context of the Internet of Things, utilizing the inherent inertial sensors in smartphones for human activity recognition (HAR) has garnered considerable attention owing to its wide-ranging applications. However, prevailing HAR approaches primarily treat activity identification as a single-label classification task, focusing solely on discerning pedestrian motion modes or device usage modes, while disregarding their interrelatedness. Additionally, HAR methods employing sliding windows encounter challenges associated with the multiclass window problem, wherein certain sample labels differ from the label assigned to the window. This paper aims to address these issues. This paper presents a novel approach for simultaneously recognizing pedestrian motion and device usage modes by utilizing the segmentation transformer. The proposed joint recognition framework effectively annotates sensor data at each timestamp and achieves dense prediction of time-series data through the encoding and decoding of the annotated data. To optimize the utilization of information extracted from each Transformer layer, a global up-sampling decoder based on the pyramid attention module is introduced, enabling dense decoding of features obtained from each Transformer layer. We performed experiments on two publicly available datasets to comprehensively assess the effectiveness of the proposed methodology. The results demonstrate that our approach achieves an accuracy of 99.79% and a weighted F-score of 99.77%, surpassing the performance of existing state-of-the-art methods. Furthermore, we constructed heterogeneous datasets to validate the robustness of our method. The extensive experimental findings indicate that the joint recognition framework effectively uncovers the inherent correlations between pedestrian motion and device usage modes, leading to enhanced accuracy in recognition and addressing the challenges posed by the multiclass window problem.

Location-based service (LBS) is the core of internet of things (IoTs), which serves tracking, navigation and monitoring. The ubiquitous magnetic signals are temporally stable and spatially distinguishable, and can achieve high-precision and ubiquitous positioning results without additional infrastructure, which is favored by researchers and has become a major research hotspot. Although there has been extensive research in the field of indoor magnetic positioning, there is still room for optimization in terms of positioning accuracy and robustness. Aiming at the problem that the magnetometer is offset and susceptible to environmental interference, we propose an online magnetometer calibration algorithm without user perception. Aiming at the inconsistency of magnetic data spatial scale problem caused by differences in device sampling frequency and user walking speed, we leverage different scales to segment the magnetic data, extract the magnetic sequence features of the corresponding scales through Transformer, utilize the attention mechanism to score the weights of the different scale features, and finally fuse the multiple scale features for positioning. We conduct extensive and well-designed experiments on public datasets and self-collected datasets. The experimental results indicate that the proposed method effectively solves the magnetic spatial scale problem and improves indoor magnetic positioning accuracy.

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.

Abstract 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.

With the explosive development of pervasive computing and the Internet of Things (IoT), indoor positioning and navigation have attracted immense attention over recent years. Pedestrian dead reckoning (PDR) is a potential autonomous localization technology that obtains position estimation employing built-in sensors. However, most existing PDR methods assume that the smartphone is held horizontally and points to the walking direction. To solve reckoning errors caused by inconsistency of headings between walking heading and pointing of smartphone, we design an accurate and robust PDR method based on walking patterns, which is identified by multihead convolutional neural networks. In addition to adaptively adjust the threshold of step detection and select the most suitable step length model according to the results of walking pattern recognition, a novel heading estimation approach independent of device orientation is proposed. To mitigate accumulative errors, we proposed an online trajectory calibration method based on forward and backward magnetic fingerprint trajectory matching. We conduct extensive and well-designed experiments in typical scenarios, and the experimental results indicate that the 75th percentile localization accuracy of the three scenarios is 1.06, 1.08, and 1.22 m, respectively, using the commercial smartphone embedded sensor without any dedicated infrastructures or training data. Despite the intricate pedestrian locomotion, the proposed PDR method has great potential in pedestrian positioning.

Existing power trace extractors consider the case where the number of power traces available to the attacker is sufficient to guarantee successful attacks, and the goal of power trace extraction is to extract a small part of traces with high signal-to-noise ratio (SNR) to reduce the complexity of attacks rather than to increase the success rates. Although strict theoretical proofs are given, the existing power trace extractors are too simple and leakage characteristics of Points-of-Interest (POIs) have not been thoroughly analyzed. They only maximize the variance of the data-dependent power consumption component and ignore the noise component, which results in very limited SNR that hampers the performance of extractors. In this article, we provide a rigorous theoretical analysis of SNR of power traces, and propose a simple yet efficient SNR-centric extractor, named shortest distance first (SDF), to extract power traces with the smallest estimated noise by taking advantage of known plaintexts. In addition, to maximize the variance of the exploitable component while minimizing the noise, we refer to the SNR estimation model and propose another novel extractor named maximizing estimated SNR first (MESF). Finally, we further propose an advanced extractor called mean-optimized MESF (MMESF) that exploits the mean power consumption of each plaintext byte value to more accurately and reasonably estimate the data-dependent power consumption of the corresponding samples. Experiments on both simulated power traces and measurements from an ATmega328p micro-controller demonstrate the superiority of our new extractors.

The ability to accurately estimate a user's stride length plays a great important role in various applications. For a new target pedestrian or device, their heterogeneity dramatically reduces the performance of the current stride-length estimation (SLE) methods. To address the issue of heterogeneity, in this article, we propose an SLE method based on a long short-term memory (LSTM) network and denoising autoencoders (DAEs). The LSTM network is used to mine temporal dependencies and extract significant eigenvectors from the corrupted inertial sensor observations. Then, DAEs are adopted to automatically eliminate the inherent noise in eigenvectors and obtain denoised eigenvectors. Finally, a regression module maps the denoised eigenvectors to the resulting stride length. To mitigate the heterogeneity, we propose an unperceived model updating framework based on active online learning to establish a personalized model for a given target pedestrian or device. The proposed framework utilizes a magnetism-aided map-matching approach to automatically generate personalized training data and utilizes online learning technologies to evolve the stride-length model. The extensive experimental results demonstrate that the proposed method outperforms other state-of-the-art algorithms and achieves a promising accuracy with a stride-length error rate of 4.59% at a confidence level of 80%.

An electro-mechanical actuator (EMA) consists of an electric motor and a mechanical transmission (reducer). As the applications of EMA in the actuators of flight control are increased, the demand for an accurate and reliable fault diagnostic method for its transmission becomes an important issue. In view of the traditional vibration-based diagnostics need extra hardware devices, this paper proposes a fault extraction method for the EMA, composed of spiral bevel gears, harmonic-drive transmission and Brushless DC motor (BLDC), by monitoring motor stator current. The BLDC, drives with speed control and current hysteresis control, is modeled using Simscape language in Matlab. Periodic impulsive loads simulating transmission faults are added to the model, and BLDC stator electric currents, as the output, are captured under constant motor speed. The fault features, hided in current signal, are exposed in time-domain after Gaussian filter and time-domain synchronous averaging, and the spectrum of current signal is calculated. The simulation and analysis show that transmission faults can generate special peaks in stator current and create unique spectral components in the spectrum. These facts can be used to the fault diagnosis of the mechanical transmission of EMA.

With the rapid increase of location based services, various indoor positioning technologies have emerged. The existing indoor positioning technologies have different characteristics in localization accuracy, real-time performance, coverage and cost. To meet the requirements of high accuracy, low cost, and broad coverage in complex indoor scenes, we design an indoor localization system WiMag: Multimode Fusion Localization System based on Magnetic/WiFi/PDR. Based on the particle filter framework, the system optimally selects the fusion strategy to combine the location results according to the identified smartphone status. The experimental results demonstrate that the proposed WiMag outperforms all single indoor positioning technologies with higher accuracy (1.6m average localization error), wider localization coverage and better robustness.

Personal dead reckoning (PDR) localization technology can provide effective and critical assistance for public security, such as emergency rescue or anti-terror training in the indoor or underground environment without the need of deploying additional positioning infrastructure. However, the PDR suffers from the severe position error accumulation with time due to the inaccurate step length and moving direction estimation. To improve the self-positioning accuracy, this paper proposed a novel indoor self-localization algorithm using two kinds of automatic calibration methods, i.e., opportunistic magnetic trajectory matching and indoor landmark identification. Extensive experiments performed in two representative indoor environments, including an office building and a supermarket, demonstrate that the proposed self-localization algorithm can obtain an 80 percentile localization accuracy of 1.4m and 2m in the two representative indoor environments, respectively, which outperforms the art-of-the-state PDR algorithms.