Average Precision Research Articles

Enhanced Swine Behavior Detection with YOLOs and a Mixed Efficient Layer Aggregation Network in Real Time

Effective livestock management has become essential owing to an aging workforce and the growth of large-scale farming operations in the agricultural industry. Conventional monitoring methods, primarily reliant on manual observation, are increasingly reaching their limits, necessitating the development of innovative automated solutions. This study developed a system, termed mixed-ELAN, for real-time sow and piglet behavior detection using an extended ELAN architecture with diverse kernel sizes. The standard convolution operations within the ELAN framework were replaced with MixConv using diverse kernel sizes to enhance feature learning capabilities. To ensure high reliability, a performance evaluation of all techniques was conducted using a k-fold cross-validation (k = 3). The proposed architecture was applied to YOLOv7 and YOLOv9, yielding improvements of 1.5% and 2%, with mean average precision scores of 0.805 and 0.796, respectively, compared with the original models. Both models demonstrated significant performance improvements in detecting behaviors critical for piglet growth and survival, such as crushing and lying down, highlighting the effectiveness of the proposed architecture. These advances highlight the potential of AI and computer vision in agriculture, as well as the system’s benefits for improving animal welfare and farm management efficiency. The proposed architecture enhances the real-time monitoring and understanding of livestock behavior, establishing improved benchmarks for smart farming technologies and enabling further innovation in livestock management.

ESL-YOLO: Small Object Detection with Effective Feature Enhancement and Spatial-Context-Guided Fusion Network for Remote Sensing

Improving the detection of small objects in remote sensing is essential for its extensive use in various applications. The diminutive size of these objects, coupled with the complex backgrounds in remote sensing images, complicates the detection process. Moreover, operations like downsampling during feature extraction can cause a significant loss of spatial information for small objects, adversely affecting detection accuracy. To tackle these issues, we propose ESL-YOLO, which incorporates feature enhancement, fusion, and a local attention pyramid. This model includes: (1) an innovative plug-and-play feature enhancement module that incorporates multi-scale local contextual information to bolster detection performance for small objects; (2) a spatial-context-guided multi-scale feature fusion framework that enables effective integration of shallow features, thereby minimizing spatial information loss; and (3) a local attention pyramid module aimed at mitigating background noise while highlighting small object characteristics. Evaluations on the publicly accessible remote sensing datasets AI-TOD and DOTAv1.5 indicate that ESL-YOLO significantly surpasses other contemporary object detection frameworks. In particular, ESL-YOLO enhances mean average precision mAP by 10% and 1.1% on the AI-TOD and DOTAv1.5 datasets, respectively, compared to YOLOv8s. This model is particularly adept at small object detection in remote sensing imagery and holds significant potential for practical applications.

Research on Deep Learning Model Enhancements for PCB Surface Defect Detection

With the miniaturization and increasing complexity of electronic devices, the accuracy and efficiency of printed circuit board (PCB) defect detection are crucial to ensuring product quality. To address the issues of small defect sizes and high missed detection rates in PCB surface inspection, this paper proposes an enhanced YOLOv8s model which not only improves detection performance but also achieves a lightweight design. Firstly, the Nexus Attention module is introduced, which organically integrates multiple attention mechanisms to further enhance feature extraction and fusion capabilities, improving the model’s learning and generalization performance. Secondly, an improved CGFPN network is designed to optimize multi-scale feature fusion, significantly boosting the detection of small objects. Additionally, the WaveletUnPool module is incorporated, leveraging wavelet transform technology to refine the upsampling process, accurately restoring detailed information and improving small-object detection in complex backgrounds. Lastly, the C2f-GDConv module replaces the traditional C2f module, reducing the number of model parameters and computational complexity while maintaining feature extraction efficiency. Comparative experiments on a public PCB dataset demonstrate that the enhanced model achieved a mean average precision (mAP) of 97.3% in PCB defect detection tasks, representing a 3.0% improvement over the original model, while reducing Giga Floating Point Operations (GFLOPs) by 26.8%. These enhancements make the model more practical and adaptable for industrial applications, providing a solid foundation for future research.

Optimizing the Accuracy and Precision of the Minimal Detectable Change Statistic: Secondary Analysis of Test-Retest Data from the NIH Toolbox Study.

The minimal detectable change (MDC) statistic is often used by clinicians to monitor change in patients. However, the way in which the MDC is traditionally calculated might be suboptimal in terms of accuracy and precision, potentially resulting in erroneous clinical decisions. This study compared the performance of the MDC statistic as traditionally calculated to that of 2 regression-based alternatives. This analysis used test-retest data from adults who participated in usual walking speed (n = 169) or grip strength (n = 178) assessments as part of the NIH Toolbox Study. Three approaches for MDC calculation were compared: the traditional approach (MDCTrad), simple linear regression (MDCSLR), and generalized additive models for location, scale, and shape (MDCGAMLSS). These approaches were compared in terms of accuracy and precision across all levels of measurement and separately for initial test values above and below the median. Each of the 3 approaches accurately modeled detectable change thresholds when performance was averaged across all test values. However, MDCTrad demonstrated inaccuracies when performance was considered separately for initial test values below or above the median. For walking speed, average precision improved by 12% with MDCSLR and 16% with MDCGAMLSS, compared to MDCTrad. For grip strength, average precision improved by 3% with MDCSLR and 21% with MDCGAMLSS, compared to MDCTrad. MDCSLR and MDCGAMLSS appeared to more accurately and precisely model detectable change thresholds, compared to MDCTRAD. In general, MDCGAMLSS demonstrated the best overall performance in this within-sample analysis. Improved precision and accuracy in detectable change thresholds for walking speed or grip strength might facilitate clinicians' ability to promptly detect a decline in function and intervene and to confidently detect improvements in function over time.

Stacking model framework reveals clinical biochemical data and dietary behavior features associated with type 2 diabetes: A retrospective cohort study.

Background: Type 2 diabetes mellitus (T2DM) is the most common type of diabetes, accounting for around 90% of all diabetes. Studies have found that dietary habits and biochemical metabolic changes are closely related to T2DM disease surveillance, but early surveillance tools are not specific and have lower accuracy. This paper aimed to provide a reliable artificial intelligence model with high accuracy for the clinical diagnosis of T2DM. Methods: A cross-sectional dataset comprising 8981 individuals from the First Affiliated Hospital of Guangxi Medical University was analyzed by a model fusion framework. The model includes four machine learning (ML) models, which used the stacking method. The ability to leverage the strengths of different algorithms to capture complex patterns in the data can effectively combine questionnaire data and blood test data to predict diabetes. Results: The experimental results show that the stacking model achieves significant prediction results in diabetes detection. Compared with the single machine learning algorithm, the stacking model has improved in the metrics of accuracy, recall, and F1-score. The test set accuracy is 0.90, and the precision, recall, F1-score, area under the curve, and average precision (AP) are 0.91, 0.90, 0.90, 0.90, and 0.85, respectively. Additionally, this study showed that HbA1c (P < 0.001,OR = 2.203), fasting blood glucose (FBG) (P < 0.001,OR = 1.586), Ph2BG (P < 0.001,OR = 1.190), age (P < 0.001,OR = 1.018), Han nationality (P < 0.001,OR = 1.484), and carbonate beverages (P = 0.001,OR = 1.347) were important predictors of T2DM. Conclusion: This study demonstrates that stacking models show great potential in diabetes detection, and by integrating multiple machine learning algorithms, stacking models can significantly improve the accuracy and stability of diabetes prediction and provide strong support for disease prevention, early diagnosis, and individualized treatment.

ViTGaze: gaze following with interaction features in vision transformers

Gaze following aims to interpret human-scene interactions by predicting the person’s focal point of gaze. Prevailing approaches often adopt a two-stage framework, whereby multi-modality information is extracted in the initial stage for gaze target prediction. Consequently, the efficacy of these methods highly depends on the precision of the previous modality extraction. Others use a single-modality approach with complex decoders, increasing network computational load. Inspired by the remarkable success of pre-trained plain vision transformers (ViTs), we introduce a novel single-modality gaze following framework called ViTGaze. In contrast to previous methods, it creates a novel gaze following framework based mainly on powerful encoders (relative decoder parameters less than 1%). Our principal insight is that the inter-token interactions within self-attention can be transferred to interactions between humans and scenes. Leveraging this presumption, we formulate a framework consisting of a 4D interaction encoder and a 2D spatial guidance module to extract human-scene interaction information from self-attention maps. Furthermore, our investigation reveals that ViT with self-supervised pre-training has an enhanced ability to extract correlation information. Many experiments have been conducted to demonstrate the performance of the proposed method. Our method achieves state-of-the-art performance among all single-modality methods (3.4% improvement in the area under curve score, 5.1% improvement in the average precision) and very comparable performance against multi-modality methods with 59% fewer parameters.

AQSFormer: Adaptive Query Selection Transformer for Real-Time Ship Detection from Visual Images

The Internet of Things (IoT) has emerged as a popular topic in both industrial and academic research. IoT devices are often equipped with rapid response capabilities to ensure seamless communication and interoperability, showing significant potential for IoT-based maritime traffic monitoring and navigation safety tasks. However, this also presents major challenges for maritime surveillance systems. The diversity of IoT devices and variability in collected data are substantial. Visual image ship detection is crucial for maritime tasks, yet it must contend with environmental challenges such as haze and waves that can obscure ship details. To address these challenges, we propose an adaptive query selection transformer (AQSFormer) that utilizes two-dimensional rotational position encoding for absolute positioning and integrates relative positions into the self-attention mechanism to overcome insensitivity to the position. Additionally, the introduced deformable attention module focuses on ship edges, enhancing the feature space resolution. The adaptive query selection module ensures a high recall rate and a high end-to-end processing efficiency. Our method improves the mean average precision to 0.779 and achieves a processing speed of 31.3 frames per second, significantly enhancing both the real-time capabilities and accuracy, proving its effectiveness in ship detection.

YOLOv8-GDCI: Research on the Phytophthora Blight Detection Method of Different Parts of Chili Based on Improved YOLOv8 Model

Smart farms are crucial in modern agriculture, but current object detection algorithms cannot detect chili Phytophthora blight accurately. To solve this, we introduced the YOLOv8-GDCI model, which can detect the disease on leaves, fruits, and stem bifurcations. The model uses RepGFPN for feature fusion, Dysample upsampling for accuracy, CA attention for feature capture, and Inner-MPDIoU loss for small object detection. In addition, we also created a dataset of chili Phytophthora blight on leaves, fruits, and stem bifurcations, and conducted comparative experiments. The results manifest that the YOLOv8-GDCI model demonstrates outstanding performance across a gamut of comprehensive indicators. In comparison with the YOLOv8n model, the YOLOv8-GDCI model demonstrates an improvement of 0.9% in precision, an increase of 1.8% in recall, and a remarkable enhancement of 1.7% in average precision. Although the FPS decreases slightly, it still exceeds the industry standard for real-time object detection (FPS &gt; 60), thus meeting the requirements for real-time detection.

AI-Driven Crack Detection for Remanufacturing Cylinder Heads Using Deep Learning and Engineering-Informed Data Augmentation

Detecting cracks in cylinder heads traditionally relies on manual inspection, which is time-consuming and susceptible to human error. As an alternative, automated object detection utilizing computer vision and machine learning models has been explored. However, these methods often face challenges due to a lack of sufficiently annotated training data, limited image diversity, and the inherently small size of cracks. Addressing these constraints, this paper introduces a novel automated crack-detection method that enhances data availability through a synthetic data generation technique. Unlike general data augmentation practices, our method involves copying cracks from one location to another, guided by both random and informed engineering decisions about likely crack formations due to cyclic thermomechanical loads. The innovative aspect of our approach lies in the integration of domain-specific engineering knowledge into the synthetic generation process, which substantially improves detection accuracy. We evaluate our method’s effectiveness using two metrics: the F2 score, which emphasizes recall to prioritize detecting all potential cracks, and mean average precision (MAP), a standard measure in object detection. Experimental results demonstrate that, without engineering insights, our method increases the F2 score from 0.40 to 0.65, while maintaining a stable MAP. Incorporating detailed engineering knowledge further enhances the F2 score to 0.70 and improves MAP to 0.57, representing increases of 63% and 43%, respectively. These results confirm that our approach not only mitigates the limitations of traditional data augmentation but also significantly advances the reliability and precision of crack detection in industrial settings.

YOLO-Ginseng: a detection method for ginseng fruit in natural agricultural environment

IntroductionThe accurate and rapid detection of ginseng fruits in natural environments is crucial for the development of intelligent harvesting equipment for ginseng fruits. Due to the complexity and density of the growth environment of ginseng fruits, some newer visual detection methods currently fail to meet the requirements for accurate and rapid detection of ginseng fruits. Therefore, this study proposes the YOLO-Ginseng detection method.MethodsFirstly, this detection method innovatively proposes a plug-and-play deep hierarchical perception feature extraction module called C3f-RN, which incorporates a sliding window mechanism. Its unique structure enables the interactive processing of cross-window feature information, expanding the deep perception field of the network while effectively preserving important weight information. This addresses the detection challenges caused by occlusion or overlapping of ginseng fruits, significantly reducing the overall missed detection rate and improving the long-distance detection performance of ginseng fruits; Secondly, in order to maintain the balance between YOLO-Ginseng detection precision and speed, this study employs a mature channel pruning algorithm to compress the model.ResultsThe experimental results demonstrate that the compressed YOLO-Ginseng achieves an average precision of 95.6%, which is a 2.4% improvement compared to YOLOv5s and only a 0.2% decrease compared to the uncompressed version. The inference time of the model reaches 7.4ms. The compressed model exhibits reductions of 76.4%, 79.3%, and 74.2% in terms of model weight size, parameter count, and computational load, respectively.DiscussionCompared to other models, YOLO-Ginseng demonstrates superior overall detection performance. During the model deployment experiments, YOLO-Ginseng successfully performs real-time detection of ginseng fruits on the Jetson Orin Nano computing device, exhibiting good detection results. The average detection speed reaches 24.9 fps. The above results verify the effectiveness and practicability of YOLO-Ginseng, which creates primary conditions for the development of intelligent ginseng fruit picking equipment.

Integrated Anti-Aliasing and Fully Shared Convolution for Small-Ship Detection in Synthetic Aperture Radar (SAR) Images

Synthetic Aperture Radar (SAR) imaging plays a vital role in maritime surveillance, yet the detection of small vessels poses a significant challenge when employing conventional Constant False Alarm Rate (CFAR) techniques, primarily due to the limitations in resolution and the presence of clutter. Deep learning (DL) offers a promising alternative, yet it still struggles with identifying small targets in complex SAR backgrounds because of feature ambiguity and noise. To address these challenges, our team has developed the AFSC network, which combines anti-aliasing techniques with fully shared convolutional layers to improve the detection of small targets in SAR imagery. The network is composed of three key components: the Backbone Feature Extraction Module (BFEM) for initial feature extraction, the Neck Feature Fusion Module (NFFM) for consolidating features, and the Head Detection Module (HDM) for final object detection. The BFEM serves as the principal feature extraction technique, with a primary emphasis on extracting features of small targets, The NFFM integrates an anti-aliasing element and is designed to accentuate the feature details of diminutive objects throughout the fusion procedure, HDM is the detection head module and adopts a new fully shared convolution strategy to make the model more lightweight. Our approach has shown better performance in terms of speed and accuracy for detecting small targets in SAR imagery, surpassing other leading methods on the SSDD dataset. It attained a mean Average Precision (AP) of 69.3% and a specific AP for small targets (APS) of 66.5%. Furthermore, the network’s robustness was confirmed using the HRSID dataset.

Two-stage ship detection at long distances based on deep learning and slicing technique.

Ship detection over long distances is crucial for the visual perception of intelligent ships. Since traditional image processing-based methods are not robust, deep learning-based image recognition methods can automatically obtain the features of small ships. However, due to the limited pixels of ships over long distances, accurate features of such ships are difficult to obtain. To address this, a two-stage object detection method that combines the advantages of traditional and deep-learning methods is proposed. In the first stage, an object detection model for the sea-sky line (SSL) region is trained to select a potential region of ships. In the second stage, another object detection model for ships is trained using sliced patches containing ships. When testing, the SSL region is first detected using the trained 8th version of You Only Look Once (YOLOv8). Then, the SSL region detected is divided into several overlapping patches using the slicing technique, and another trained YOLOv8 is applied to detect ships. The experimental results showed that our method achieved 85% average precision when the intersection over union is 0.5 (AP50), and a detection speed of 75 ms per image with a pixel size of 1080×640. The code is available at https://github.com/gongyanfeng/PaperCode.

Accuracy and Precision of Shallow-Water Photogrammetry from the Sea Surface

Mapping shallow-water bathymetry and morphology represents a technical challenge. In fact, acoustic surveys are limited by water depths reachable by boat, and airborne surveys have high costs. Photogrammetric approaches (either via drone or from the sea surface) have opened up the possibility to perform shallow-water surveys easily and at accessible costs. This work presents a simple, low-cost, and highly portable platform that allows gathering sequential photos and echosounder depth values of shallow-water sites (up to 5 m depth). The photos are then analysed in conjunction with photogrammetric techniques to obtain digital bathymetric models and orthomosaics of the seafloor. The workflow was tested on four repeated surveys of the same area in the Western Mediterranean and allowed obtaining digital bathymetric models with centimetric average accuracy and precision and root mean square errors within a few decimetres. The platform presented in this work can be employed to obtain first-order bathymetric products, enabling the contextual establishment of the depth accuracy of the final products.

Lightweight UAV Small Target Detection and Perception Based on Improved YOLOv8-E

Traditional unmanned aerial vehicle (UAV) detection methods struggle with multi-scale variations during flight, complex backgrounds, and low accuracy, whereas existing deep learning detection methods have high accuracy but high dependence on equipment, making it difficult to detect small UAV targets efficiently. To address the above challenges, this paper proposes an improved lightweight high-precision model, YOLOv8-E (Enhanced YOLOv8), for the fast and accurate detection and identification of small UAVs in complex environments. First, a Sobel filter is introduced to enhance the C2f module to form the C2f-ESCFFM (Edge-Sensitive Cross-Stage Feature Fusion Module) module, which achieves higher computational efficiency and feature representation capacity while preserving detection accuracy as much as possible by fusing the SobelConv branch for edge extraction and the convolution branch to extract spatial information. Second, the neck network is based on the HSFPN (High-level Screening-feature Pyramid Network) architecture, and the CAA (Context Anchor Attention) mechanism is introduced to enhance the semantic parsing of low-level features to form a new CAHS-FPN (Context-Augmented Hierarchical Scale Feature Pyramid Network) network, enabling the fusion of deep and shallow features. This improves the feature representation capability of the model, allowing it to detect targets of different sizes efficiently. Finally, the optimized detail-enhanced convolution (DEConv) technique is introduced into the head network, forming the LSCOD (Lightweight Shared Convolutional Object Detector Head) module, enhancing the generalization ability of the model by integrating a priori information and adopting the strategy of shared convolution. This ensures that the model enhances its localization and classification performance without increasing parameters or computational costs, thus effectively improving the detection performance of small UAV targets. The experimental results show that compared with the baseline model, the YOLOv8-E model achieved (mean average precision at IoU = 0.5) an mAP@0.5 improvement of 6.3%, reaching 98.4%, whereas the model parameter scale was reduced by more than 50%. Overall, YOLOv8-E significantly reduces the demand for computational resources while ensuring high-precision detection.

The urine formed element instance segmentation based on YOLOv5n

Accurate and efficient detection and segmentation of the urine formed element plays a vital role in the clinical diagnosis and treatment of many diseases, such as urinary system diseases, kidney diseases, and other diseases. However, artificial microscopy is subjective, and time- consuming. The mainstream detection and instance segmentation algorithms lack adequate accuracy and speed for the urine formed element due to small and dense targets. Therefore, this study proposes a quick one-stage urine formed element instance segmentation model based on YOLOv5n. The approach first employs a backbone architecture to extract features named shallow graphical features and semantic features from urine cells. Next, the neck network combines shallow graphical features with different deep semantic features, obtaining multi-scale, and multi-level features. Finally, according to these multi-level features, the head network of YOLOv5n integrates a small FCN network into the YOLOv5 detector. It obtains the location, classification, and segmentation results of the targets. To validate the superiority of this approach in terms of speed and accuracy, a special urine formed element dataset including 500 images was created. Experimental results show that the YOLOv5n method achieves a Mean Average Precision (mAP) at intersection over the union threshold of 0.5 (mAP50) with 91.8%, and Frames Per Second (FPS) of 63.3. Compared to Mask R-CNN and YOLOv8, its FPS increased by 62.6 and 60.9, respectively, resulting in nearly a hundred-fold speedup, and its mAP50 also increased by 3.6 and 1.4% points in accuracy, respectively. Additionally, the YOLOv5n obtains a superior balance of accuracy and speed in comparisons with SOLOv2, BoxInst, and ConvNeXt V2. This study developed a new automated analysis of urinary particles based on deep learning, and this method is expected to be used for the automated analysis and detection of the urine formed element. The experimental results also demonstrate that YOLOv5n can achieve more accurate and faster instance segmentation of urine formed element, providing technical support for clinical disease diagnosis.

Edge Computing-Driven Real-Time Drone Detection Using YOLOv9 and NVIDIA Jetson Nano

Drones, with their ability to vertically take off and land with their stable hovering performance, are becoming favorable in both civilian and military domains. However, this introduces risks of its misuse, which may include security threats to airports, institutes of national importance, VIP security, drug trafficking, privacy breaches, etc. To address these issues, automated drone detection systems are essential for preventing unauthorized drone activities. Real-time detection requires high-performance devices such as GPUs. For our experiments, we utilized the NVIDIA Jetson Nano to support YOLOv9-based drone detection. The performance evaluation of YOLOv9 to detect drones is based on metrics like mean average precision (mAP), frames per second (FPS), precision, recall, and F1-score. Experimental data revealed significant improvements over previous models, with a mAP of 95.7%, a precision of 0.946, a recall of 0.864, and an F1-score of 0.903, marking a 4.6% enhancement over YOLOv8. This paper utilizes YOLOv9, optimized with pre-trained weights and transfer learning, achieving significant accuracy in real-time drone detection. Integrated with the NVIDIA Jetson Nano, the system effectively identifies drones at altitudes ranging from 15 feet to 110 feet while adapting to various environmental conditions. The model’s precision and adaptability make it particularly suitable for deployment in security-sensitive areas, where quick and accurate detection is crucial. This research establishes a solid foundation for future counter-drone applications and shows great promise for enhancing situational awareness in critical, high-risk environments.

PLC-Fusion: Perspective-Based Hierarchical and Deep LiDAR Camera Fusion for 3D Object Detection in Autonomous Vehicles

Accurate 3D object detection is essential for autonomous driving, yet traditional LiDAR models often struggle with sparse point clouds. We propose perspective-aware hierarchical vision transformer-based LiDAR-camera fusion (PLC-Fusion) for 3D object detection to address this. This efficient, multi-modal 3D object detection framework integrates LiDAR and camera data for improved performance. First, our method enhances LiDAR data by projecting them onto a 2D plane, enabling the extraction of object perspective features from a probability map via the Object Perspective Sampling (OPS) module. It incorporates a lightweight perspective detector, consisting of interconnected 2D and monocular 3D sub-networks, to extract image features and generate object perspective proposals by predicting and refining top-scored 3D candidates. Second, it leverages two independent transformers—CamViT for 2D image features and LidViT for 3D point cloud features. These ViT-based representations are fused via the Cross-Fusion module for hierarchical and deep representation learning, improving performance and computational efficiency. These mechanisms enhance the utilization of semantic features in a region of interest (ROI) to obtain more representative point features, leading to a more effective fusion of information from both LiDAR and camera sources. PLC-Fusion outperforms existing methods, achieving a mean average precision (mAP) of 83.52% and 90.37% for 3D and BEV detection, respectively. Moreover, PLC-Fusion maintains a competitive inference time of 0.18 s. Our model addresses computational bottlenecks by eliminating the need for dense BEV searches and global attention mechanisms while improving detection range and precision.

Investigating the Surface Damage to Fuzhou’s Ancient Houses (Gu-Cuo) Using a Non-Destructive Testing Method Constructed via Machine Learning

As an important part of traditional Chinese architecture, Fuzhou’s ancient houses have unique cultural and historical value. However, over time, environmental factors such as efflorescence and plant growth have caused surface damage to their gray brick walls, leading to a decline in the quality of the buildings’ structure and even posing a threat to the buildings’ safety. Traditional damage detection methods mainly rely on manual labor, which is inefficient and consumes a lot of human resources. In addition, traditional non-destructive detection methods, such as infrared imaging and laser scanning, often face difficulty in accurately identifying specific types of damage, such as efflorescence and plant growth, on the surface of gray bricks and are easily hampered by diverse surface features. This study uses the YOLOv8 machine learning model for the automated detection of two common types of damage to the gray brick walls of Fuzhou’s ancient houses: efflorescence and plant growth. We establish an efficient gray brick surface damage detection model through dataset collection and annotation, experimental parameter optimization, model evaluation, and analysis. The research results reveal the following. (1) Reasonable hyperparameter settings and model-assisted annotation significantly improve the detection accuracy and stability. (2) The model’s average precision (AP) is improved from 0.30 to 0.90, demonstrating good robustness in detecting complex backgrounds and high-resolution real-life images. The F1 value of the model’s gray brick detection efficiency is improved (classification model performance index) from 0.22 to 0.77. (3) The model’s ability to recognize the damage details of gray bricks under high-resolution conditions is significantly enhanced, demonstrating its ability to cope with complex environments. (4) The simplified data enhancement strategy effectively reduces the feature extraction interference and enhances the model’s adaptability in different environments.

Decision model of public opinion risk in campus social network based on hybrid dynamic deletion and shortest path algorithm

Aiming at the problem that traditional network public opinion monitoring and searching are inefficient and can easily cause resource waste, the study firstly, through the dynamic deletion-shortest path algorithm to classify network text, and on this basis, innovatively constructs a text sentiment classification model based on the variant of convolutional neural network and recurrent neural network, and secondly, uses attention mechanism to classify the model. improvement of the classification model by using the attention mechanism. The research results show that the average precision rate, recall rate, and F-value of the dynamic deletion-shortest path algorithm are 97.30%, 79.55%, and 87.53%, and the classification speed is 397 KB/s, which is better than the traditional shortest path algorithm. In the classification effect measurement of long text, the accuracy and F-value of the recurrent neural network variant model are above 84%, and the accuracy of the text sentiment classification model with the introduction of the attention mechanism is improved by 3.89% compared to the pre-improvement period. In summary, the dynamic deletion-shortest path algorithm proposed in the study and the sentiment classification model with the introduction of the attention mechanism have superior performance and can provide certain application value for campus social network opinion risk decision-making.

DMFR-YOLO: an infrared small hotspot detection algorithm based on double multi-scale feature fusion

Abstract Hotspot automatic detection is an effective strategy to realize intelligent maintenance of photovoltaic (PV) modules. However, it is challenging to detect small hotspots accurately using deep learning-based object detection methods due to the weak information and small area of the target. This study presents a double multi-scale feature reconstruction (DMFR)-YOLO to detect small hotspots in PV modules. In the proposed DMFR-YOLO, the backbone of YOLOv8n is improved by eliminating redundant deep layers and introducing a shallow detection head to enhance its perception and recognition ability for small objects. Moreover, a weighted multi-layer feature reconstruction (MLFR) module is introduced to fuse the features of different depths and a multi-receptive field feature reconstruction (MRFR) module is designed to fuse the information of different receptive fields. Finally, ablation and comparison experiments are conducted to evaluate the performance of the proposed method. The model with both MLFR and MRFR can achieve a recall rate of 88.6%, with a mean average precision (mAP@0.5) of 93.3%. Experimental results demonstrate that the proposed DMFR-YOLO is able to achieve small hotspot detection in IR images with high accuracy.