Intelligent Detection Model Research Articles

BS-YOLOV8: an intelligent detection model for bearing pin support-piece states of high-rise building machine

Abstract As the main support part of the working platform of a high-rise building machine, the bearing pin support (BPS) plays a crucial role in the safety and stability of the platform, the conventional method has the problems of low detection efficiency, low accuracy, and high cost. To improve the accuracy and robustness of the detection algorithm under weak light, this paper proposes an intelligent detection algorithm for the BPS-piece states of the BS-YOLOV8, to improve the feature map utilization and reduce the model leakage detection error detection rate, Swin transformer is used to improve the YOLOV8 backbone network. In addition, the BiFormer attention mechanism is used to weigh the feature map to solve the problem of feature information loss in different feature layers and weak lighting conditions, and then the Scylla-IOU loss function is used instead of the original localization loss function to guide the model to learn to generate a predicted bounding box closer to the real target bounding box. Finally, the BS-YOLOV8 algorithm is used to compare with its classical algorithm on the self-constructed dataset of this study, The results show that the mAP0.5, mAP0.5:0.95, and FPS values of the BS-YOLOV8 algorithm reach 97.9%, 96.3% and 40 under normal lighting. The mAP0.5 value reaches 87.6% under low light conditions, which effectively solves the problems of low detection efficiency and poor detection under low light conditions, and is superior compared to other algorithms.

YOLOv5-S-G-B: a lightweight intelligent detection model for cardboard surface defects

YOLOv5-S-G-B: a lightweight intelligent detection model for cardboard surface defects

Tri-Flow-YOLO: Counter helps to improve cross-domain object detection

The excellence of intelligent detection models has been widely recognized, but in terms of cross-domain scenes, they still face performance degradation and low accuracy. A multi-supervised Tri-Flow-YOLO model is proposed to improve the accuracy of objects with various scales under cross-domain conditions. Based on the full-supervised traditional detection branch of YOLOv5, another two mutually supporting task branches are designed intently. In brief, we add unsupervised adversarial classification training flow to the backend, to realize the feature alignment requirements and improve the cross-domain performance stability of the model. Meanwhile, a weakly-supervised object counting flow is proposed to improve the model's attention to all the objects and the detection ability is efficiently enforced. In addition, I-Mosaic and iCIOU are designed especially for small hard objects, enriching the positive samples during the training process. With the auxiliary of both improved strategies, the imbalance of positive and negative samples in the anchor-based model is relieved accordingly. The experimental results show that the improved Tri-Flow-YOLO model achieves 56.0 mAP in the Cityscapes→Foggy-Cityscapes task, and 49.8 mAP in the VOC→Clipart task.

SCB-YOLOv5: a lightweight intelligent detection model for athletes’ normative movements

Intelligent detection of athlete behavior is beneficial for guiding sports instruction. Existing mature target detection algorithms provide significant support for this task. However, large-scale target detection algorithms often encounter more challenges in practical application scenarios. We propose SCB-YOLOv5, to detect standardized movements of gymnasts. First, the movements of aerobics athletes were captured, labeled using the labelImg software, and utilized to establish the athlete normative behavior dataset, which was then enhanced by the dataset augmentation using Mosaic9. Then, we improved the YOLOv5 by (1) incorporating the structures of ShuffleNet V2 and convolutional block attention module to reconstruct the Backbone, effectively reducing the parameter size while maintaining network feature extraction capability; (2) adding a weighted bidirectional feature pyramid network into the multiscale feature fusion, to acquire precise channel and positional information through the global receptive field of feature maps. Finally, SCB-YOLOv5 was lighter by 56.9% than YOLOv5. The detection precision is 93.7%, with a recall of 99% and mAP value of 94.23%. This represents a 3.53% improvement compared to the original algorithm. Extensive experiments have verified that our method. SCB-YOLOv5 can meet the requirements for on-site athlete action detection. Our code and models are available at https://github.com/qingDu1/SCB-YOLOv5.

Intelligent Cotton Pest and Disease Detection: Edge Computing Solutions with Transformer Technology and Knowledge Graphs

In this study, a deep-learning-based intelligent detection model was designed and implemented to rapidly detect cotton pests and diseases. The model integrates cutting-edge Transformer technology and knowledge graphs, effectively enhancing pest and disease feature recognition precision. With the application of edge computing technology, efficient data processing and inference analysis on mobile platforms are facilitated. Experimental results indicate that the proposed method achieved an accuracy rate of 0.94, a mean average precision (mAP) of 0.95, and frames per second (FPS) of 49.7. Compared with existing advanced models such as YOLOv8 and RetinaNet, improvements in accuracy range from 3% to 13% and in mAP from 4% to 14%, and a significant increase in processing speed was noted, ensuring rapid response capability in practical applications. Future research directions are committed to expanding the diversity and scale of datasets, optimizing the efficiency of computing resource utilization and enhancing the inference speed of the model across various devices. Furthermore, integrating environmental sensor data, such as temperature and humidity, is being considered to construct a more comprehensive and precise intelligent pest and disease detection system.

YOLOv8-ACU: improved YOLOv8-pose for facial acupoint detection.

Acupoint localization is integral to Traditional Chinese Medicine (TCM) acupuncture diagnosis and treatment. Employing intelligent detection models for recognizing facial acupoints can substantially enhance localization accuracy. This study introduces an advancement in the YOLOv8-pose keypoint detection algorithm, tailored for facial acupoints, and named YOLOv8-ACU. This model enhances acupoint feature extraction by integrating ECA attention, replaces the original neck module with a lighter Slim-neck module, and improves the loss function for GIoU. The YOLOv8-ACU model achieves impressive accuracy, with an mAP@0.5 of 97.5% and an mAP@0.5-0.95 of 76.9% on our self-constructed datasets. It also marks a reduction in model parameters by 0.44M, model size by 0.82 MB, and GFLOPs by 9.3%. With its enhanced recognition accuracy and efficiency, along with good generalization ability, YOLOv8-ACU provides significant reference value for facial acupoint localization and detection. This is particularly beneficial for Chinese medicine practitioners engaged in facial acupoint research and intelligent detection.

Landscape design of aging rehabilitation in community park based on improved YOLOv4

In the aging rehabilitation landscape design of community parks, the crack detection of landscape architecture is very important, which is related to the beauty and safety of landscape architecture. In order to improve the poor effect of current landscape building crack detection methods, an intelligent landscape building crack detection model based on improved YOLOv4 is proposed. Aiming at the inadequacy of information feature extraction in YOLOv4 algorithm, the coordinate attention module with extended convolution structure optimization is adopted to optimize it. Aiming at the defect that YOLOv4 algorithm has poor information feature utilization rate of shallow position, an improved K-means algorithm is designed to determine the optimal size of prior frame, so as to improve the performance of the algorithm. The performance of the algorithm is improved. Finally, combined with the above content, an intelligent detection model of landscape building cracks based on improved YOLOv4 is constructed. The results verify that the fitting degree of the model is 0.986, which is 0.008 and 0.016 higher than that of the CRF-CNN and Faster-RCNN models, respectively. The F1 value is 0.951, 0.10–0.12 higher than the two models. The accuracy was 98.26%, 0.47%-0.51% higher than the two models. Recall value was 96.44%, which was 0.47%-0.51% higher than that of the two models. The AUC value is 0.988, which is 0.009–0.016 higher than the two models. To sum up, the model built in the study can detect the cracks in landscape architecture with high accuracy and efficiency, and improve the safety and beauty of the landscape. Meanwhile, this model can assist in the design of aging rehabilitation landscape in community parks.

Data-driven intelligent detection model of railway vehicle wheels flat

Data-driven intelligent detection model of railway vehicle wheels flat

Research on Intelligent Inspection Method of Prestressed Bridge Engineering Based on Machine Learning

Abstract As an important engineering structure for national and regional transportation infrastructure construction, bridges have important economic, social, and strategic significance. The research centers on the intelligent detection of prestressed bridge engineering, on the one hand, combined with the finite element analysis of the prestressed beam modal in the obtained area, based on LS-SVM to construct the intelligent detection method of effective prestressing of bridge engineering. On the other hand, the ResNet neural network is selected for feature extraction of bridge characteristic parameters, and LSTM is combined to complete the fusion of bridge spatiotemporal features to construct an intelligent detection model of bridge technical condition based on the ResNet-LSTM joint network. The detection performance of the two methods is evaluated through simulation and experimental tests on the dataset. The analysis shows that the maximum error for effective prestress detection of the LS-SVM model is 15.584%, which is 6.121% lower than that of the BP neural network model. The technical condition detection error of less than 0.1 is basically greater than 90% in both discontinuous and continuous time-span detection. It has been verified that the LS-SVM model has a better identification effect on effective prestressing, while the ResNet-LSTM model has a high accuracy prediction effect on the technical condition of the bridge.

Precision local anomaly positioning technology for large complex electromechanical systems

In recent years, Prognostics Health Management (PHM) technology has become an important reference technology in fields such as avionics and electromechanical systems due to its ability to reduce costs and achieve state based maintenance and autonomous support. However, with the operation of large and complex electromechanical systems (ES), the data generated gradually ages the status of components, and traditional PHM technology is difficult to solve the problem of electromechanical system components becoming more complex. Based on this, this study takes the hydraulic actuator cylinder as an example to construct a local component fault detection model. Firstly, fault data features are extracted using wavelet packet energy spectrum, and then a fault detection model is constructed based on support vector machine (SVM). In response to the shortcomings of SVM, a smooth support vector machine (SSVM) is proposed to replace SVM, and an improved crow search algorithm (ICSA) is used to improve SVM. Finally, an intelligent detection model for hydraulic actuator cylinder faults based on ICSA-SSVM was constructed based on the above algorithms. The experimental results show that the ICSA-SSVM model has the fastest Rate of convergence, among which, the positioning accuracy is 0.96, the fitting degree is 0.984, the fault detection accuracy is 99.16 %, the recall value is 94.52 %, and the AUC value is 0.986, all of which are better than the existing fault detection models. From this, it can be seen that the precise local anomaly localization technology for large-scale complex electromechanical systems based on the ICSA-SSVM algorithm proposed in this study can improve the efficiency and accuracy of fault detection, achieve accurate and intelligent detection of ES local anomalies, and have certain positive significance for the development of China’s industry.

YOLO-G: Improved YOLO for cross-domain object detection.

Cross-domain object detection is a key problem in the research of intelligent detection models. Different from lots of improved algorithms based on two-stage detection models, we try another way. A simple and efficient one-stage model is introduced in this paper, comprehensively considering the inference efficiency and detection precision, and expanding the scope of undertaking cross-domain object detection problems. We name this gradient reverse layer-based model YOLO-G, which greatly improves the object detection precision in cross-domain scenarios. Specifically, we add a feature alignment branch following the backbone, where the gradient reverse layer and a classifier are attached. With only a small increase in computational, the performance is higher enhanced. Experiments such as Cityscapes→Foggy Cityscapes, SIM10k→Cityscape, PASCAL VOC→Clipart, and so on, indicate that compared with most state-of-the-art (SOTA) algorithms, the proposed model achieves much better mean Average Precision (mAP). Furthermore, ablation experiments were also performed on 4 components to confirm the reliability of the model. The project is available at https://github.com/airy975924806/yolo-G.

Gabor wavelet transform combined with area CNN in appearance intelligent detection of stayed cables

The major structure for transmitting forces in a cable-stayed bridge is the stay cable. If the stay cable system fails, the whole bridge will collapse. At present, there is no very mature technical means for the detection of bridge cables. The most common method is for workers to perform regular manual inspection and replacement of cables. Although the defect condition of the cable can be detected to a certain extent, the real-time monitoring of its health cannot be realized. Therefore, the research used the median filter, mean standardization method and Retinex algorithm to preprocess the image data. And after extracting the stay cable picture’s macroscopic characteristics using the Gabor wavelet transform, it implemented image segmentation using the OTSU approach. The obtained feature images were applied to the Faster Regional Convolution Neural Network (RCNN) recognition model to detect microscopic defects. During the research, the training efficiency of traditional Convolution Neural Network (CNN) was not high. Therefore, Faster RCNN built a cable defect recognition model. Based on this, the research built an intelligent detection model for apparent defects of stay cables based on Gabor wavelet transform and improved RCNN. Through the experimental analysis, the model built for the study has a recognition accuracy rate of 94.14 %, which can achieve dynamic bridge health monitoring and instantly identify the condition of the stay cables, and maintain the safety of the bridge.

Substation Safety Awareness Intelligent Model: Fast Personal Protective Equipment Detection Using GNN Approach

Federal regulations require employees to protect themselves from electrical hazards when working at substations. Such protections, commonly called personal protective equipment (PPE), vary with the hazard types and nature of exposure or delivery. Over the past decades, personal injuries and fatalities from electrical hazards have remained relatively common despite regular risk assessments and controls. One reason for this is that adequate PPE is not appropriately used. Easy-to-deploy strategies to detect proper use of PPE for electrical hazards are not available. Here, an intelligent detection model is developed to check whether PPE is appropriately worn or not; warning alarms would be triggered when the usage does not follow safety regulations. Arc-flash analysis is employed to determine a reasonable and safe PPE guideline. Eight types of PPE are considered, which cover the major PPE categories utilized in practice, including medical masks recommended for the Covid-19 pandemic. The model's framework utilizes a few-shot based graph neural network (GNN) technique to detect PPE. In contrast to prior data-driven models, only 50 images were collected for each PPE type, a relatively small number compared with state-of-the-art research. The proposed model was trained with diversified samples within multiple environments, resulting in a robust, efficient, intelligent detection model with probability of similarity in the range of 79% - 100%. To tackle the existing issues of computer-vision based PPE detection models, some technical suggestions on preserving personal privacy and PPE labels are provided.

Study on the Detection Method for Daylily Based on YOLOv5 under Complex Field Environments.

Intelligent detection is vital for achieving the intelligent picking operation of daylily, but complex field environments pose challenges due to branch occlusion, overlapping plants, and uneven lighting. To address these challenges, this study selected an intelligent detection model based on YOLOv5s for daylily, the depth and width parameters of the YOLOv5s network were optimized, with Ghost, Transformer, and MobileNetv3 lightweight networks used to optimize the CSPDarknet backbone network of YOLOv5s, continuously improving the model's performance. The experimental results show that the original YOLOv5s model increased mean average precision (mAP) by 49%, 44%, and 24.9% compared to YOLOv4, SSD, and Faster R-CNN models, optimizing the depth and width parameters of the network increased the mAP of the original YOLOv5s model by 7.7%, and the YOLOv5s model with Transformer as the backbone network increased the mAP by 0.2% and the inference speed by 69% compared to the model after network parameter optimization. The optimized YOLOv5s model provided precision, recall rate, mAP, and inference speed of 81.4%, 74.4%, 78.1%, and 93 frames per second (FPS), which can achieve accurate and fast detection of daylily in complex field environments. The research results can provide data and experimental references for developing intelligent picking equipment for daylily.

A Deep Neural Network-Based Intelligent Detection Model for Manufacturing Defects of Automobile Parts

Image defect detection of casting parts is a key part of the production process in the machinery manufacturing industry. The traditional methods are ineffective because traditional computer image processing methods require a large number of manual features to be set artificially, and the detection time is too long. In order to save human resources and improve the efficiency of image defect detection, this paper proposes a deep learning-based defect detection method for automobile parts. This paper selects EfficientNetB0 as the backbone framework of the target detection network, which significantly reduces the memory usage of the model and shortens the model inference time, while improving the model detection accuracy. Facing the problem of small samples of defect image dataset, we analyze the image characteristics of the dataset and introduce shape transformation and scale scaling as the basic online data enhancement method according to the industrial field image projection law. Then, it is expected to combine the traditional image processing algorithms according to the characteristics of casting parts with different depth distribution and multiple morphological changes, and develop a special image defect data enhancement method. This further improves the performance of the model and increases the detection accuracy of the algorithm by 22.3% without increasing the data.

NIDD: an intelligent network intrusion detection model for nursing homes

AbstractIn nursing homes using technologies such as IoT, big data, cloud computing, and machine learning, there is a constant risk of attacks such as Brute Force FTP, Brute Force SSH, Web Attack, Infiltration, and Botnet during data communication between individual terminals and the cloud server. Therefore, effectively identifying network communication data is essential to protect data communication security between individual terminals and the cloud server. Aiming at the data mentioned above regarding communication security issues, we propose an intelligent intrusion detection model NIDD (Network Intelligent Data Detection) model that combines deep convolution generation adversarial network (DCGAN) with Light Gradient Boosting Machine (LightGBM) and Shapley Additive exPlanations (SHAP). The NIDD model first generates new attack samples by learning the feature distribution of the existing attack sample data and effectively expands the rare attack samples. Secondly, we use the Light Gradient Boosting Machine (LightGBM) algorithm as the base classifier to train the dataset and start to build the intrusion detection model. Then use Shapley Additive exPlanations (SHAP) to analyze the contribution of the classification results, and adjust the model parameters according to the analysis results. Finally, we obtain the optimal model for the intelligent detection model of network intrusion. This paper conducts experimental tests on the NSL-KDD dataset. The experimental results show that the NIDD model built based on Light Gradient Boosting Machine can detect Brute Force FTP, Brute Force SSH, DoS, Heartbleed, Web Attack, Infiltration, Botnet, PROBE, R2L, and U2R attacks with an accuracy of 99.76%. Finally, we re-verified the NIDD model on the CIC-IDC-2018 dataset. The results once again proved that the NIDD model could solve the data communication security between the nursing robot and the cloud server and the data before the IoT terminal and the cloud server. Communication security provides a sufficient guarantee.

An intelligent monitoring system of diseases and pests on rice canopy.

Accurate and timely surveys of rice diseases and pests are important to control them and prevent the reduction of rice yields. The current manual survey method of rice diseases and pests is time-consuming, laborious, highly subjective and difficult to trace historical data. To address these issues, we developed an intelligent monitoring system for detecting and identifying the disease and pest lesions on the rice canopy. The system mainly includes a network camera, an intelligent detection model of diseases and pests on rice canopy, a web client and a server. Each camera of the system can collect rice images in about 310 m2 of paddy fields. An improved model YOLO-Diseases and Pests Detection (YOLO-DPD) was proposed to detect three lesions of Cnaphalocrocis medinalis, Chilo suppressalis, and Ustilaginoidea virens on rice canopy. The residual feature augmentation method was used to narrow the semantic gap between different scale features of rice disease and pest images. The convolution block attention module was added into the backbone network to enhance the regional disease and pest features for suppressing the background noises. Our experiments demonstrated that the improved model YOLO-DPD could detect three species of disease and pest lesions on rice canopy at different image scales with an average precision of 92.24, 87.35 and 90.74%, respectively, and a mean average precision of 90.11%. Compared to RetinaNet, Faster R-CNN and Yolov4 models, the mean average precision of YOLO-DPD increased by 18.20, 6.98, 6.10%, respectively. The average detection time of each image is 47 ms. Our system has the advantages of unattended operation, high detection precision, objective results, and data traceability.

An intelligent leakage detection method for diaphragm wall joints based on fiber Bragg grating sensors and intelligent algorithms

The leakage detection method based on fiber Bragg grating (FBG) sensing technology is an effective method to determine leakage points in diaphragm wall joints. However, the detection method involves cumbersome data processing which causes manual data processing errors and costs time. In this work, an intelligent leakage detection method for diaphragm wall joints based on FBG sensing signals was proposed. Firstly, a field study of the leakage detection method was carried out in a new urban expressway in Hohhot, Inner Mongolia, China. The field monitoring data were compared with test data, and characteristics of the FBG wavelength curve and mechanism of leakage detection were analyzed. In addition, four intelligent detection models including a convolutional neural network, support vector machine (SVM), decision tree, and random forest were established. Results showed that the proposed method is effective and efficient in identifying and locating leakage through diaphragm walls.

Two-Stage Intelligent Model for Detecting Malicious DDoS Behavior.

5G technologies provide ubiquitous connectivity. However, 5G security is a particularly important issue. Moreover, because public datasets are outdated, we need to create a self-generated dataset on the virtual platform. Therefore, we propose a two-stage intelligent detection model to enable 5G networks to withstand security issues and threats. Finally, we define malicious traffic detection capability metrics. We apply the self-generated dataset and metrics to thoroughly evaluate the proposed mechanism. We compare our proposed method with benchmark statistics and neural network algorithms. The experimental results show that the two-stage intelligent detection model can distinguish between benign and abnormal traffic and classify 21 kinds of DDoS. Our analysis also shows that the proposed approach outperforms all the compared approaches in terms of detection rate, malicious traffic detection capability, and response time.

Research on Traffic Detection Method of Secure Transmission Industrial Internet of Things Based on Computer Vision

In recent years, the process of industrial modernization has intensified, traditional industrial control has been improved and rapidly developed, industrial automation and intelligent unmanned production lines have become a new development trend, and the Internet of Things has become the basic direction of industrial development. In order to improve the effect of safe transmission and industrial IoT traffic detection, this study uses a neural network to improve the industrial IoT traffic detection algorithm. In order to improve the visualization effect of monitoring, this study uses computer vision technology to construct a traffic detection system of secure transmission industrial Internet of Things and builds an intelligent detection model. Finally, this study combines experimental research to verify the performance of the system. From the statistical point of view, it can be seen that the system’s security detection and traffic detection effects are very good.