Search

• Qualitative and quantitative detection of amine gases could be achieved by CSA. • A visible detection of beef freshness using the amine-responsive CSA was proposed. • ResNet34 had the best performance for beef freshness detection based on CSA. • T-SNE could further visualize and understand the classification process of DL. This study developed an innovative approach that combines a colourimetric sensor array (CSA) composed of twelve pH-response dyes with advanced algorithms, aiming to detect amine gases and assess the freshness of chilled beef. With the assistance of multivariate statistical analysis, the sensor array can effectively distinguish five amine gases and enable rapid quantification of trimethylamine vapour with a limit of detection (LOD) of 8.02 ppb and visually monitor the fresh levels of chilled beef. Moreover, the utilization of deep learning models (ResNet34, VGG16, and GoogleNet) for chilled beef freshness evaluation achieved an overall accuracy of 98.0 %. Furthermore, t -distributed stochastic neighbour embedding (t -SNE) visualized the feature extraction process and provided explanations to understand the classification process of deep learning. The results demonstrated that applying deep learning techniques in the process of pattern recognition of CSA can help in realizing the rapid, robust, and accurate assessment of chilled beef freshness. [ABSTRACT FROM AUTHOR]

Logistics parcel detection technology is critical for unmanned sorting. YOLOv5, the state-of-the-art (SOTA) object detection model, is a classic network widely used in engineering. However, on the premise of fast and accurate detection of logistics parcels, it confronts certain challenges of high computing load and parameter quantity. To address these issues, this paper proposes a two-scale lightweight deep learning model named SFYOLOv5. In this article, a lightweight feature extraction module called Pruned-Shuffle-Block (PSB) is proposed. Meanwhile, a double-layer pyramid structure for the medium and large target detection is created in accordance with the image size distribution of logistics parcels. With this structure, the Floating Point of Operations (FLOPs) and parameters in feature extraction were significantly reduced. In addition, a down sampling module named Focus for Downsampling (FFD) is designed and attention modules are introduced to extract high-level semantic information in logistics parcels. These modules not only compensate for the loss caused by down sampling but also improve the mean Average Precision (mAP). Finally, the comparison experiment is performed by using the self-built logistics parcel dataset. The results show that the mAP of the model reaches 99.1%, the number of model parameters decreased by 92.14%, and the FLOPs decreased by 89.57% compared with the existing SOTA model. This model can be used in logistics parcel intelligent sorting. [ABSTRACT FROM AUTHOR]

This paper addresses the common orthopedic trauma of spinal vertebral fractures and aims to enhance doctors' diagnostic efficiency. Therefore, a deep-learning-based automated diagnostic systemwithmulti-label segmentation is proposed to recognize the condition of vertebral fractures. The whole spine Computed Tomography (CT) image is segmented into the fracture, normal, and background using U-Net, and the fracture degree of each vertebra is evaluated (Genant semi-qualitative evaluation). The main work of this paper includes: First, based on the spatial configuration network (SCN) structure, U-Net is used instead of the SCN feature extraction network. The attention mechanismand the residual connection between the convolutional layers are added in the local network (LN) stage. Multiple filtering is added in the global network (GN) stage, and each layer of the LN decoder feature map is filtered separately using dot product, and the filtered features are re-convolved to obtain the GN output heatmap. Second, a network model with improved SCN (M-SCN) helps automatically localize the center-of-mass position of each vertebra, and the voxels around each localized vertebra were clipped, eliminating a large amount of redundant information (e.g., background and other interfering vertebrae) and keeping the vertebrae to be segmented in the center of the image. Multilabel segmentation of the clipped portion was subsequently performed using U-Net. This paper uses VerSe'19, VerSe'20 (using only data containing vertebral fractures), and private data (provided by Guizhou Orthopedic Hospital) for model training and evaluation. Compared with the original SCN network, the M-SCN reduced the prediction error rate by 1.09% and demonstrated the effectiveness of the improvement in ablation experiments. In the vertebral segmentation experiment, the Dice Similarity Coefficient (DSC) index reached 93.50% and the Maximum Symmetry Surface Distance (MSSD) index was 4.962 mm, with accuracy and recall of 95.82% and 91.73%, respectively. Fractured vertebrae were also marked as red and normal vertebrae were marked as white in the experiment, and the semi-qualitative assessment results of Genant were provided, as well as the results of spinal localization visualization and 3D reconstructed views of the spine to analyze the actual predictive ability of the model. It provides a promising tool for vertebral fracture detection. [ABSTRACT FROM AUTHOR]

High-quality agricultural multi-view stereo reconstruction technology is the key to precision and informatization in agriculture. Multi-view stereo reconstruction methods are an important part of 3D vision technology. In the multi-view stereo 3D reconstruction method based on deep learning, the effect of feature extraction directly affects the accuracy of reconstruction. Aiming at the actual problems in orchard fruit tree reconstruction, this paper designs an improved multi-view stereo structure based on the combination of remote sensing and artificial intelligence to realize the accurate reconstruction of jujube tree trunks. Firstly, an automatic key frame extraction method is proposed for the DSST target tracking algorithm to quickly recognize and extract high-quality data. Secondly, a composite U-Net feature extraction network is designed to enhance the reconstruction accuracy, while the DRE-Net feature extraction enhancement network improved by the parallel self-attention mechanism enhances the reconstruction completeness. Comparison tests show different levels of improvement on the Technical University of Denmark (DTU) dataset compared to other deep learning-based methods. Ablation test on the self-constructed dataset, the MVSNet + Co U-Net + DRE-Net_SA method proposed in this paper improves 20.4% in Accuracy, 12.8% in Completion, and 16.8% in Overall compared to the base model, which verifies the real effectiveness of the scheme. [ABSTRACT FROM AUTHOR]