Search

With the rapid development of the Internet of Things (IoT) technology, location-based services (LBSs) are gaining significant attention for their potential applications. Among the various LBS methods, angle of arrival (AOA) is attracting attention due to its simplicity and ease of implementation. However, in practical applications, the Bluetooth low-energy (BLE)-based 2-D antenna array encounters the problem of constant tone extension (CTE) frequency deviation (FD), which introduces phase impairments. Additionally, the support of periodical advertising (PA) event in Bluetooth poses a challenge for ensuring excellent angle estimation performance in periodic physical (PHY) channels, as the channel overlaps with the Wi-Fi frequency band. To address these challenges, we propose a hierarchical angle estimation (HAE) framework based on the phase difference of single reference antenna. The framework comprises three layers: the data acquisition layer, the phase restoration layer, and the multichannel estimation layer with angle collection solver. The HAE framework enables phase correction and accurate estimation over periodic PHY channels. We validate the proposed method on a real hardware system and demonstrate that it achieves a high level of precision and stability in the estimation of angles, which makes it suitable for practical LBSs applications in challenging environments.

With the development of cloud manufacturing, the automation of storage scheduling becomes popular in the steel industry. However, the high customization of steel plates makes the storage scheduling too complex to be optimized. To overcome this challenge, we propose to utilize the big data of steel plate orders and warehouse status to optimize the storage scheduling of steel plates. The agglomerative hierarchical clustering is first adopted to reduce the complexity of excessive steel plate specifications, then an optimization problem is defined to formulate the storage scheduling of steel plates with safety. A two-stage heuristic (TSH) algorithm is proposed to solve the optimization problem with low complexity. In TSH, steel plates are first assigned to multiple stacks, and then the arrangement of each stack is determined. Experiments are executed based on a cloud manufacturing platform for steel plates production and storage, and the results prove the effectiveness of the proposed works.

Dear Editor, This letter is concerned with wood crack detection which is important to guarantee the quality of wooden products. In the wood industry, the crack detection is one of the most challenging tasks in the wood defects detection, since the detection accuracy may be reduced due to the stains on the boards, the tiny cracks, and some cracks that are similar to the sound region. To overcome these challenges, we propose a data-driven semantic segmentation network based on U-Net, which is called WCU-Net, for wood crack detection. Specifically, a position attention mechanism is firstly proposed to exaggerate the wood crack positions, then the feature enhancement mechanism is designed to selectively derive more diluted information of tiny crack. Moreover, a residual block is adopted to obtain and fuse multi-scale receptive fields for finding more crack areas that are similar to the sound region. The experimental results show that WCU-Net can improve the accuracy of wood crack detection.

Dear Editor, This letter concerns the localization of three-core underwater cables which are widely deployed for offshore energy transmission. It is a non-trivial problem, since the external magnetic field of three-core underwater cables is variable which reduces the accuracy of localization. To solve this problem, in this letter, an approximate equation is firstly derived to formulate the external magnetic field of a three-core armored underwater cable by considering the seafloor environments and the structure of three-core cables. Then, a new underwater cable localization method is proposed based on dual three-axis magnetic sensor array and the beetle swarm optimization (BSO) algorithm. The method constructs a fitness function based on the magnetic flux density amplitude and replaces the existing analytical geometry method with an optimization algorithm to achieve underwater cable localization with higher accuracy.

The millimeter-wave (mmWave) radar technology has attracted significant attention because it is susceptible to environmental lighting, wall shielding, and privacy concern. This article proposes a novel noninvasive human activity recognition system using a mmWave radar. The proposed framework first transforms mmWave signals into point clouds. Generally speaking, it consists of four major components: denosing, enhanced voxelization, data augmentation, and dual-view machine learning to lead to accurate and efficient human activity recognition. The proposed new methodology considers the spatial–temporal point clouds in physical environments through a modified voxelization approach, enriches the sparse data based on the symmetry property of radar rotations, and learns the activity using a dual-view convolutional neural network. To evaluate the performance of the proposed learning models, a dataset involving seven different activities has been established using a mmWave radar platform. The experimental results have demonstrated that the proposed system can achieve 97.61% and 98% accuracies during the tests of fall detection and activity classification, respectively. In comparison, the proposed scheme greatly outperforms four other conventional machine learning schemes in terms of the overall accuracy.