Zan Yang

Introduction: Cryptococcus spp. infection can lead to cryptococcal meningitis (called CM) and pulmonary cryptococcosis, and how to diagnose Cryptococcus spp. infection accurately and timely is an urgent need in clinical practice. However, the existing methods such as cerebrospinal fluid (CSF) ink staining smear microscopy and CSF Cryptococcus spp. culture only rely on manual counting to determine the number of Cryptococcus spp., resulting in low efficiency. Thus, how to identify Cryptococcus spp. in cerebrospinal fluid and achieve automated counting of Cryptococcus spp. is of great significance for helping clinical experts accurately and timely diagnose Cryptococcus spp. infections to reduce the risk of deterioration. Method: We propose a small target Cryptococcus spp. detection and counting method called CsDETC, where three important components are integrated, such as data augmentation, hypergraph computation empowered semantic collecting and scattering module called HGC-SCS, and attention-enhanced path aggregation network called AEPAN. The Cryptococcus spp. dataset has been expanded through multiple data augmentation techniques such as random cropping, horizontal flipping, and rotation before training the model. Subsequently, the Cryptococcus spp. morphological features have been enriched by data augmentation based on perspective transformation and vertical flipping in the training process, thereby improving the generalization ability. Then different morphological features can be adaptively detected by learning high-order relationships between visual features when adding HGC-SCS into the neck network. Eventually, the convolution block attention module (CBAM) is integrated into path aggregation network to generate attention maps along the channel and spatial dimensions, transmitting more detailed information contained in the shallow layer to the deep layers to enhance the perception ability of small targets. Results: The experimental results on private dataset show that CsDETC outperforms other advanced object detection models with excellent performance such as YOLOv10 and YOLO11, etc. Typically, compared to the baseline, CsDETC shows significant improvements in mAP50 (93.6% vs. 91.3%), APs (51.0% vs. 49.5%), and MAE (1.865 vs. 2.370), while only a 0.7 millisecond increase in the inference time. Discussion: CsDETC is a promising tool that has performed well in preliminary validation. After validation with larger and more diverse datasets from different medical centers in the future, CsDETC can help doctors accurately and timely identify Cryptococcus spp. and achieve automated counting of Cryptococcus spp., providing reference for treatment plans and improving the diagnostic efficiency.

Carbon fiber reinforced polymer (CFRP) components require precise curing process control to ensure quality, but traditional phenomenological cure kinetics models face limitations in handling nonlinearity and data diversity. This study addresses the challenges in modeling the cure kinetics of carbon fiber reinforced polymer (CFRP) composites, where traditional phenomenological models lack generalizability and neural networks suffer from robustness issues due to their numerous hyperparameters and data dependency. To overcome these limitations, a novel machine learning model called the angle information-enhanced radial basis function (RBF) model is proposed, which integrates both Euclidean distance and angular relationships between data points to improve prediction stability and accuracy. The performance of this machine learning approach is systematically compared against an autocatalytic model and a neural network using dynamic DSC data from T700/2626 epoxy resin at multiple heating rates. The angle-enhanced RBF model balances accuracy, efficiency, and robustness, offering a reliable data-driven alternative for CFRP cure kinetics prediction without requiring extensive data or complex hyperparameter optimization, thus facilitating better process control in manufacturing.

In the field of intelligent manufacturing, image anomaly detection plays a pivotal role in automated product quality inspection. Most existing anomaly detection methods are adept at capturing local features of images, achieving high detection accuracy for structural anomalies such as cracks and scratches. However, logical anomalies typically appear normal within local regions of an image and are difficult to represent well by the anomaly score map, requiring the model to possess the capability to extract global context features. To address this challenge while balancing the detection of both structural and logical anomalies, this paper proposes a lightweight anomaly detection framework built upon EfficientAD. This framework integrates the reconstruction difference constraint (RDC) and a logical anomaly detection module. Specifically, the original EfficientAD relies on the coarse-grained reconstruction difference between the student and the autoencoder to detect logical anomalies; but, false detection may be caused by the local fine-grained reconstruction difference between the two models. RDC can promote the consistency of the fine-grained reconstruction between the student and the autoencoder, thereby effectively alleviating this problem. Furthermore, in order to detect anomalies that are difficult to represent by feature maps more effectively, the proposed logical anomaly detection module extracts and aggregates the context features of the image, and combines the feature-based method to calculate the overall anomaly score. Extensive experiments demonstrate our method’s significant improvement in logical anomaly detection, achieving 94.2 AU-ROC on MVTec LOCO, while maintaining strong structural anomaly detection performance at 98.4 AU-ROC on MVTec AD. Compared to the baseline, like EfficientAD, our framework achieves a state-of-the-art balance between both anomaly types.

This paper presents a surrogate-assisted global and distributed local collaborative optimization (SGDLCO) algorithm for expensive constrained optimization problems where two surrogate optimization phases are executed collaboratively at each generation. As the complexity of optimization problems and the cost of solutions increase in practical applications, how to efficiently solve expensive constrained optimization problems with limited computational resources has become an important area of research. Traditional optimization algorithms often struggle to balance the efficiency of global and local searches, especially when dealing with high-dimensional and complex constraint conditions. For global surrogate-assisted collaborative evolution phase, the global candidate set is generated through classification collaborative mutation operations to alleviate the pre-screening pressure of the surrogate model. For local surrogate-assisted phase, a distributed central region local exploration is designed to achieve intensively search for promising distributed local areas which are located by affinity propagation clustering and mathematical modeling. More importantly, a three-layer adaptive selection strategy where the feasibility, diversity and convergence are balanced effectively is designed to identify promising solutions in global and local candidate sets. Therefore, the SGDLCO efficiently balances global and local search during the whole optimization process. Experimental studies on five classical test suites demonstrate that the SGDLCO provides excellent performance in solving expensive constrained optimization problems.