With the increasing customer demand on fabric variety in fashion markets, fabric texture becomes much more diverse, which brings great challenges to accurate fabric defect detection. In this paper, a fabric inspection model, consisting of image preprocessing, image restoration, and thresholding operation, is developed to address the woven fabric defect detection problem in the apparel industry, especially for fabric with complex texture and tiny defects. The image preprocessing first improves the image contrast in order to make the details of defects more salient. Based on the learned sub-dictionaries, a non-locally centralized sparse representation model is adopted to estimate the non-defective version of the input images, so that the possible defects can be easily segmented from the residual images of the estimated images and the inputs by thresholding operation. The performance of the proposed defect detection model was evaluated through extensive experiments with various types of real fabric samples. The proposed detection model was proved to be effective and robust, and superior to some representative detection models in terms of the detection accuracy and false alarms.

To achieve a green and sustainable wireless communication network, the reconfigurable intelligent surface (RIS) technology has emerged as an emerging technology. The RIS-assisted mmWave massive MIMO vehicle-to-everything (V2X) communications can support enhanced V2X applications for connected and automated vehicles. The design of RIS-assisted mmWave V2X communications is though not exempt of challenges as a result of fast time-varying propagation and highly dynamic vehicular networks and topologies. To address some of these challenges, we propose an attention-deep reinforcement learning jointly beamforming based on tensor decomposition for RIS-assisted mmWave massive MIMO system to improving the safety and traffic efficiency of cooperative automated driving. The received signal of the vehicle is decomposed into four-dimensional tensors and study the channel, frequency and time attention (CFTA) algorithm using the low order tensor characteristics of mmWave channels. This algorithm can extract the frequency and time characteristics of the channel, and obtain the millimeter wave characteristic channel between the corresponding base station (BS) and the vehicles. The problem of jointly optimization of beamforming matrix at the BS and the phase shift matrix on the RIS is constructed and solved using deep reinforcement learning (DRL). Unlike traditional alternating optimization methods, the integration of DRL techniques into the optimal design of the system enables the observation of immediate rewards, learning from the environment and improving it to obtain optimal solutions to high-dimensional jointly beamforming optimization problems ultimately. The simulation results show that the proposed algorithm has meaningful performance compared with other methods.

In the process of steel production, the defects on the surface of steel will adversely affect the subsequent processing of a product. Accurate detection of such defects is the key to improve production efficiency and economic benefits. In this paper, an end-to-end steel surface defect detection and size measurement system based on the YOLOv5 model is designed. Firstly, in consideration of the defect location and direction correlation in the production process, a coordinate attention mechanism is added at the head of YOLOv5 to strengthen the spatial correlation of the steel surface and an adaptive anchor box generation method based on defect shape difference feature is proposed, which realizes the detection of three main types of defects on the Pytorch deep learning framework. Secondly, BiFPN is used to strengthen the feature fusion and a transformer encoder is added to improve the performance of detecting small defects. Thirdly, calculate the conversion ratio between the pixel and the actual size according to the standard reference specimen and obtain the actual size through the pixel statistics of the defect area to achieve pixel level size measurement. Finally, the steel surface defect detection and size measurement system are designed in this paper, which consist of various hardware, related measurement, and detection algorithms. According to the experimental results, the comprehensive defect detection accuracy of this method reaches 93.6%, of which the scratch detection accuracy reaches 95.7%. The detection speed reaches 133 fps and the defect size measurement accuracy reaches 0.5 mm. Experimental result shows that the defect detection and size measurement system designed in this paper can accurately detect and measure various industrial production defects and can be applied to the actual production process.

Two-tier massive multiple-input multiple-output (MIMO) systems achieve high sum spectral efficiency by simultaneously serving large numbers of users. However, as the number of service antennas and users tend to infinity, the performance is limited by directed inter-cell and intra-cell interferences. Handling these interferences are challenging due to the large channel dimensionality and the high complexity associated with implementing large precoding/combining matrices. Moreover, two-tier massive MIMO is computationally demanding, as the high antenna count results in high-dimensional matrix operations when conventional MIMO hybrid precoding is applied. In this paper, a manifold learning two-tier beamforming (MLTB) scheme is proposed to enable efficient and low-complexity operation in large scale dimensional MIMO systems. Users of multi-cell are clustered into several regions of user groups by manifold learning. Most of the high-dimensional channels are embedded in the low-dimensional subspace by manifold learning, while retaining the potential spatial correlation of the high-dimensional channels. The nonlinearity of high-dimensional channel is transformed into local linearity to achieve dimensionality reduction. Through proper user clustering, the beamformers are split into outer beamformers and inner beamformers. The outer beamformers can minimize inter-cell interference and the inner beamformers can minimize multi-user interference of intra-groups. The high signal to interference plus noise ratio (SINR) is achieved and the computational complexity is reduced by avoiding the conventional schemes to deal with high-dimensional channel parameters. Performance evaluations show that the proposed MLTB scheme can obtain near-optimal sum-rate and considerably higher energy efficiency than the conventional schemes.

Reconfigurable intelligent surface (RIS)-assisted millimeter-wave (mmWave) communication systems relying on hybrid beamforming structures are capable of achieving high spectral efficiency at a low hardware complexity and with low power consumption. Tensor-based joint beamforming with low-cost ultrasonic and RIS-assisted Dual-Hop Hybrid free space optical (FSO) mm Wave massive Multiple Input Multiple Output (MIMO) of vehicle-to-everything (V2X) is proposed. To address the occlusion problem for high-speed mobility of the vehicle, an RIS-assisted mixed FSO-MIMO V2X system is proposed. The low-cost ultrasonic array signal model is developed to solve the accurate direction-of-arrival (DOA) estimation. The ultrasonic-assisted RIS phase shift matrix based on subspace self-organizing iterations is designed to track the beam direction between RIS and vehicle. Specifically, the associated bandwidth-efficiency maximization problem is transformed into a series of subproblems, where the subarray of phase shifters and RIS elements is jointly optimized to maximize each subarray’s rate. The vehicle motion state is transformed into a two-dimensional model for prior distribution to calculate the particle weights of the RIS phase. Multi-vehicle Tucker tensor decomposition is used to describe the high-dimensional beam space. We conceive a multi-vehicle joint optimization method for designing the hybrid beamforming matrix of the base station (BS) and the passive beamforming matrix of the RIS. A cascaded channel decomposition method based on Singular Value Decomposition (SVD) is used to obtain the combined matrix beamforming of BS and vehicle. Our simulation results demonstrate the superiority of the proposed method compared to its traditional counterparts.

Organoids hold significant potential and scientific value in areas such as disease modeling, drug screening, and regenerative medicine. During cultivation, researchers monitor the development of organoids through imaging and apply quantitative methods, such as cell counting, to assess key metrics like drug response. However, existing bright-field image processing techniques often struggle with challenges such as blurred boundaries, low contrast, and noise interference, particularly when organoids overlap. These limitations hinder the accurate segmentation of organoid structures. To address these issues, this paper proposes an innovative approach named OrganFit, which integrates a multi-scale convolutional model for segmenting organoid regions, followed by an optimized elliptical fitting principles to detect and screen junction points in overlapping areas. This method captures the features of organoids with varying sizes and shapes, enabling accurate contour fitting even under conditions of severe overlap and low image contrast. As a result, it effectively distinguishes overlapping organoids and significantly enhances the accuracy and reliability of organoid counting. Experimental results across multiple organoid datasets demonstrate that the proposed method maintains stable performance and robustness, showing adaptable generalization across diverse application scenarios.