BACKGROUND Early detection of precancerous lesions is of vital importance for reducing the incidence and mortality of upper gastrointestinal(UGI)tract cancer.However,traditional endoscopy has certain limitations in de...BACKGROUND Early detection of precancerous lesions is of vital importance for reducing the incidence and mortality of upper gastrointestinal(UGI)tract cancer.However,traditional endoscopy has certain limitations in detecting precancerous lesions.In contrast,real-time computer-aided detection(CAD)systems enhanced by artificial intelligence(AI)systems,although they may increase unnecessary medical procedures,can provide immediate feedback during examination,thereby improving the accuracy of lesion detection.This article aims to conduct a meta-analysis of the diagnostic performance of CAD systems in identifying precancerous lesions of UGI tract cancer during esophagogastroduodenoscopy(EGD),evaluate their potential clinical application value,and determine the direction for further research.AIM To investigate the improvement of the efficiency of EGD examination by the realtime AI-enabled real-time CAD system(AI-CAD)system.METHODS PubMed,EMBASE,Web of Science and Cochrane Library databases were searched by two independent reviewers to retrieve literature with per-patient analysis with a deadline up until April 2025.A meta-analysis was performed with R Studio software(R4.5.0).A random-effects model was used and subgroup analysis was carried out to identify possible sources of heterogeneity.RESULTS The initial search identified 802 articles.According to the inclusion criteria,2113 patients from 10 studies were included in this meta-analysis.The pooled accuracy difference,logarithmic difference of diagnostic odds ratios,sensitivity,specificity and the area under the summary receiver operating characteristic curve(area under the curve)of both AI group and endoscopist group for detecting precancerous lesion were 0.16(95%CI:0.12-0.20),-0.19(95%CI:-0.75-0.37),0.89(95%CI:0.85-0.92,AI group),0.67(95%CI:0.63-0.71,endoscopist group),0.89(95%CI:0.84-0.93,AI group),0.77(95%CI:0.70-0.83,endoscopist group),0.928(95%CI:0.841-0.948,AI group),0.722(95%CI:0.677-0.821,endoscopist group),respectively.CONCLUSION The present studies further provide evidence that the AI-CAD is a reliable endoscopic diagnostic tool that can be used to assist endoscopists in detection of precancerous lesions in the UGI tract.It may be introduced on a large scale for clinical application to enhance the accuracy of detecting precancerous lesions in the UGI tract.展开更多
BACKGROUND Computer-aided diagnosis(CAD)may assist endoscopists in identifying and classifying polyps during colonoscopy for detecting colorectal cancer.AIM To build a system using CAD to detect and classify polyps ba...BACKGROUND Computer-aided diagnosis(CAD)may assist endoscopists in identifying and classifying polyps during colonoscopy for detecting colorectal cancer.AIM To build a system using CAD to detect and classify polyps based on the Yamada classification.METHODS A total of 24045 polyp and 72367 nonpolyp images were obtained.We established a computer-aided detection and Yamada classification model based on the YOLOv7 neural network algorithm.Frame-based and image-based evaluation metrics were employed to assess the performance.RESULTS Computer-aided detection and Yamada classification screened polyps with a precision of 96.7%,a recall of 95.8%,and an F1-score of 96.2%,outperforming those of all groups of endoscopists.In regard to the Yamada classification of polyps,the CAD system displayed a precision of 82.3%,a recall of 78.5%,and an F1-score of 80.2%,outper-forming all levels of endoscopists.In addition,according to the image-based method,the CAD had an accuracy of 99.2%,a specificity of 99.5%,a sensitivity of 98.5%,a positive predictive value of 99.0%,a negative predictive value of 99.2%for polyp detection and an accuracy of 97.2%,a specificity of 98.4%,a sensitivity of 79.2%,a positive predictive value of 83.0%,and a negative predictive value of 98.4%for poly Yamada classification.CONCLUSION We developed a novel CAD system based on a deep neural network for polyp detection,and the Yamada classi-fication outperformed that of nonexpert endoscopists.This CAD system could help community-based hospitals enhance their effectiveness in polyp detection and classification.展开更多
In the present research,we describe a computer-aided detection(CAD)method aimed at automatic fetal head circumference(HC)measurement in 2D ultrasonography pictures during all trimesters of pregnancy.The HC might be ut...In the present research,we describe a computer-aided detection(CAD)method aimed at automatic fetal head circumference(HC)measurement in 2D ultrasonography pictures during all trimesters of pregnancy.The HC might be utilized toward determining gestational age and tracking fetal development.This automated approach is particularly valuable in low-resource settings where access to trained sonographers is limited.The CAD system is divided into two steps:to begin,Haar-like characteristics were extracted from ultrasound pictures in order to train a classifier using random forests to find the fetal skull.We identified the HC using dynamic programming,an elliptical fit,and a Hough transform.The computer-aided detection(CAD)program was well-trained on 999 pictures(HC18 challenge data source),and then verified on 335 photos from all trimesters in an independent test set.A skilled sonographer and an expert in medicine personally marked the test set.We used the crown-rump length(CRL)measurement to calculate the reference gestational age(GA).In the first,second,and third trimesters,the median difference between the standard GA and the GA calculated by the skilled sonographer stayed at 0.7±2.7,0.0±4.5,and 2.0±12.0 days,respectively.The regular duration variance between the baseline GA and the health investigator’s GA remained 1.5±3.0,1.9±5.0,and 4.0±14 a couple of days.The mean variance between the standard GA and the CAD system’s GA remained between 0.5 and 5.0,with an additional variation of 2.9 to 12.5 days.The outcomes reveal that the computer-aided detection(CAD)program outperforms an expert sonographer.When paired with the classifications reported in the literature,the provided system achieves results that are comparable or even better.We have assessed and scheduled this computerized approach for HC evaluation,which includes information from all trimesters of gestation.展开更多
CT colonography （CTC） is a non-invasive screening technique for the detection of eolorectal polyps, as an alternative to optical colonoscopy in clinical practice. Computer-aided detection （CAD） for CTC refers to a...CT colonography （CTC） is a non-invasive screening technique for the detection of eolorectal polyps, as an alternative to optical colonoscopy in clinical practice. Computer-aided detection （CAD） for CTC refers to a scheme which automatically detects colorectal polyps and masses in CT images of the colon. It has the potential to increase radiologists＇ detection performance and greatly shorten the detection time. Over the years, technical developments have advanced CAD for CTC substantially. In this paper, key techniques used in CAD for polyp detection are reviewed. Illustrations about the performance of existing CAD schemes show their relatively high sensitivity and low false positive rate. However, these CAD schemes are still suffering from technical or clinical problems. Some existing challenges faced by CAD are also pointed out at the end of this paper.展开更多
Computer aided detection(CADe)of pulmonary nodules plays an important role in assisting radiologists’diagnosis and alleviating interpretation burden for lung cancer.Current CADe systems,aiming at simulating radiologi...Computer aided detection(CADe)of pulmonary nodules plays an important role in assisting radiologists’diagnosis and alleviating interpretation burden for lung cancer.Current CADe systems,aiming at simulating radiologists’examination procedure,are built upon computer tomography(CT)images with feature extraction for detection and diagnosis.Human visual perception in CT image is reconstructed from sinogram,which is the original raw data acquired from CT scanner.In this work,different from the conventional image based CADe system,we propose a novel sinogram based CADe system in which the full projection information is used to explore additional effective features of nodules in the sinogram domain.Facing the challenges of limited research in this concept and unknown effective features in the sinogram domain,we design a new CADe system that utilizes the self-learning power of the convolutional neural network to learn and extract effective features from sinogram.The proposed system was validated on 208 patient cases from the publicly available online Lung Image Database Consortium database,with each case having at least one juxtapleural nodule annotation.Experimental results demonstrated that our proposed method obtained a value of 0.91 of the area under the curve(AUC)of receiver operating characteristic based on sinogram alone,comparing to 0.89 based on CT image alone.Moreover,a combination of sinogram and CT image could further improve the value of AUC to 0.92.This study indicates that pulmonary nodule detection in the sinogram domain is feasible with deep learning.展开更多
Background:The main cause of breast cancer is the deterioration of malignant tumor cells in breast tissue.Early diagnosis of tumors has become the most effective way to prevent breast cancer.Method:For distinguishing ...Background:The main cause of breast cancer is the deterioration of malignant tumor cells in breast tissue.Early diagnosis of tumors has become the most effective way to prevent breast cancer.Method:For distinguishing between tumor and non-tumor in MRI,a new type of computer-aided detection CAD system for breast tumors is designed in this paper.The CAD system was constructed using three networks,namely,the VGG16,Inception V3,and ResNet50.Then,the influence of the convolutional neural network second migration on the experimental results was further explored in the VGG16 system.Result:CAD system built based on VGG16,Inception V3,and ResNet50 has higher performance than mainstream CAD systems.Among them,the system built based on VGG16 and ResNet50 has outstanding performance.We further explore the impact of the secondary migration on the experimental results in the VGG16 system,and these results show that the migration can improve system performance of the proposed framework.Conclusion:The accuracy of CNN represented by VGG16 is as high as 91.25%,which is more accurate than traditional machine learningmodels.The F1 score of the three basic networks that join the secondary migration is close to 1.0,and the performance of the VGG16-based breast tumor CAD system is higher than Inception V3,and ResNet50.展开更多
Breast cancer is one of the most common and deadliest types of cancer among women and early detection is of major importance to decrease mortality rates. Microcalcification clusters and masses are two major indicators...Breast cancer is one of the most common and deadliest types of cancer among women and early detection is of major importance to decrease mortality rates. Microcalcification clusters and masses are two major indicators of malignancy in the early stages of this disease, when mammography is typically used as the screening technology. Computer-Aided Diagnosis (CAD) systems can support the radiologists’ work, by performing a double-reading process, which provides a second opinion that the physician can take into account in the detection process. This paper presents a CAD model based on computer vision procedures for locating suspicious regions that are later analyzed by artificial neural networks, support vector machines and linear discriminant analysis, to classify them into benign or malignant, based on a set of features that are extracted from lesions to characterize their visual content. A genetic algorithm is used to find the subset of features that provide the greatest discriminant power. Our results show that the SVM presented the highest overall accuracy and specificity for classifying microcalcification clusters, while the NN outperformed the rest for mass-classification in the same parameters. Overall accuracy, sensitivity and specificity were measured.展开更多
The mechanical-touched detector was used commonly in textile production limes. It has some defect with high false alarm rate, response delay and high maintenance cost. In order to overcome such defects, a new kind dev...The mechanical-touched detector was used commonly in textile production limes. It has some defect with high false alarm rate, response delay and high maintenance cost. In order to overcome such defects, a new kind device was developed and used to detect roller tangled in the production lines. It is based on image processing. The core algorithm was composed of Canny edge detection, removing interference, detection of perpendicularity line and detection of broken tow. After the four steps, the broken tow could be recognized quickly and correctly. The algorithm is robust and high efficiency. So, the detection device has characteristic of stable, quickly-response and low maintains cost. It can keep superiority with long lifespan even in more formidable conditions. It guarantees a safe and stable production condition.展开更多
In this thesis, a strategy realizing the computer-aided detection (CAD) of the epileptic waves in EEG isintroduced. The expert criterion, continuous wavelet transformation, neural networks, and characteristic paramete...In this thesis, a strategy realizing the computer-aided detection (CAD) of the epileptic waves in EEG isintroduced. The expert criterion, continuous wavelet transformation, neural networks, and characteristic parametermeasuremente these modern signa1 processing weapons were synthesized togetLher to form a so-called multi-method.It was estimated that the advantages of all the powerful techniques could be exploited systematically. Therefore, theCAD’s capacities in the long-term monitoring, trCaAnent and control of epilepsy might be enhanced. In this strategy,the raw EEG signals were uniformed and the expelt criterion were applied to discard most of aItifacts in them at first,and then the signals were pre-processed by continuous wavelet transformation. Some characteristic parameters wereextracted from the raw signals and the pre-processed ones. Consequently groups of eighteen parameters were sent totrain or test BP networks. By applying this theme a correct-detection rate of 84.3% for spike and sharp waves, and88.9% for sPike and sharp slow waves were obtained. In the next step, some non-linear tools wtll also be equippedwith the CAD system.展开更多
Background:Computer-aided detection(CAD)software has been introduced to automatically interpret digital chest X-rays.This study aimed to evaluate the performance of CAD software(JF CXR-1 v3.0,which was developed by a ...Background:Computer-aided detection(CAD)software has been introduced to automatically interpret digital chest X-rays.This study aimed to evaluate the performance of CAD software(JF CXR-1 v3.0,which was developed by a domestic Hi-tech enterprise)in tuberculosis(TB)case finding in China.Methods:In 2019,we conducted an internal evaluation of the performance of JF CXR-1 v3.0 by reading standard images annotated by a panel of experts.In 2020,using the reading results of chest X-rays by a panel of experts as the reference standard,we conducted an on-site prospective study to evaluate the performance of JF CXR-1 v3.0 and local radiologists in TB case finding in 13 township health centers in Zhongmu County,Henan Province.Results:Internal assessment results based on 277 standard images showed that JF CXR-1 v3.0 had a sensitivity of 85.94%(95%confidence interval[CI]:77.42%,94.45%)and a specificity of 74.65%(95%CI:68.81%,80.49%)to distinguish active TB from other imaging conditions.In the on-site evaluation phase,images from 3705 outpatients who underwent chest X-ray detection were read by JF CXR-1 v3.0 and local radiologists in parallel.The imaging diagnosis of local radiologists for active TB had a sensitivity of 32.89%(95%CI:22.33%,43.46%)and a specificity of 99.28%(95%CI:99.01%,99.56%),while JF CXR-1 v3.0 showed a significantly higher sensitivity of 92.11%(95%CI:86.04%,98.17%)(p<0.05)and maintained high specificity at 94.54%(95%CI:93.81%,95.28%).Conclusions:CAD software could play a positive role in improving the TB case finding capability of township health centers.展开更多
Jaundice,common condition in newborns,is characterized by yellowing of the skin and eyes due to elevated levels of bilirubin in the blood.Timely detection and management of jaundice are crucial to prevent potential co...Jaundice,common condition in newborns,is characterized by yellowing of the skin and eyes due to elevated levels of bilirubin in the blood.Timely detection and management of jaundice are crucial to prevent potential complications.Traditional jaundice assessment methods rely on visual inspection or invasive blood tests that are subjective and painful for infants,respectively.Although several automated methods for jaundice detection have been developed during the past few years,a limited number of reviews consolidating these developments have been presented till date,making it essential to systematically evaluate and present the existing advancements.This paper fills this gap by providing a thorough survey of automated methods for jaundice detection in neonates.The primary focus of the survey is to review the existing methodologies,techniques,and technologies used for neonatal jaundice detection.The key findings from the review indicate that image-based bilirubinometers and transcutaneous bilirubinometers are promising non-invasive alternatives,and provide a good trade-off between accuracy and ease of use.However,their effectiveness varies with factors like skin pigmentation,gestational age,and measurement site.Spectroscopic and biosensor-based techniques show high sensitivity but need further clinical validation.Despite advancements,several challenges including device calibration,large-scale validation,and regulatory barriers still haunt the researchers.Standardization,regulatory compliances,and seamless integration into healthcare workflows are the key hurdles to be addressed.By consolidating the current knowledge and discussing the challenges and opportunities in this field,this survey aims to contribute to the advancement of automatic jaundice detection and ultimately improve neonatal care.展开更多
Background Colonic polyps are frequently encountered in clinics. Computed tomographic colonography （CTC）, as a painless and quick detection, has high values in clinics. In this study, we evaluated the application va...Background Colonic polyps are frequently encountered in clinics. Computed tomographic colonography （CTC）, as a painless and quick detection, has high values in clinics. In this study, we evaluated the application value of computer-aided detection （CAD） in CTC detection of colonic polyps in the Chinese population.Methods CTC was performed with a GE 64-row multidetector computed tomography （MDCT） scanner. Data of 50 CTC patients （39 patients positive for at least one polyp of ≥0.5 cm in size and the other 11 patients negative by endoscopic detection） were retrospectively reviewed first without computer-aided detection （CAD） and then with CAD by four radiologists （two were experienced and another two inexperienced） blinded to colonoscopy findings. The sensitivity,specificity, positive predictive value, negative predictive value, and accuracy of detected colonic polyps, as well as the areas under the ROC curves （Az value） with and without CAD were calculated.Results CAD increased the overall sensitivity, specificity, positive predictive value, negative predictive value and accuracy of the colonic polyps detected by experienced and inexperienced readers. The sensitivity in detecting small polyps （5-9 mm） with CAD in experienced and inexperienced readers increased from 82% and 44% to 93% and 82%,respectively （P 〉0.05 and P 〈0.001）. With the use of CAD, the overall false positive rate and false negative rate for the detection of polyps by experienced and inexperienced readers decreased in different degrees. Among 13 sessile polyps not detected by CAD, two were 〉1.0 cm, eleven were 5-9 mm in diameter, and nine were fiat-shaped lesions.Conclusions The application of CAD in combination with CTC can increase the ability to detect colonic polyps,particularly for inexperienced readers. However, CAD is of limited value for the detection of flat polyps.展开更多
Traffic sign detection is an important part of autonomous driving,and its recognition accuracy and speed are directly related to road traffic safety.Although convolutional neural networks(CNNs)have made certain breakt...Traffic sign detection is an important part of autonomous driving,and its recognition accuracy and speed are directly related to road traffic safety.Although convolutional neural networks(CNNs)have made certain breakthroughs in this field,in the face of complex scenes,such as image blur and target occlusion,the traffic sign detection continues to exhibit limited accuracy,accompanied by false positives and missed detections.To address the above problems,a traffic sign detection algorithm,You Only Look Once-based Skip Dynamic Way(YOLO-SDW)based on You Only Look Once version 8 small(YOLOv8s),is proposed.Firstly,a Skip Connection Reconstruction(SCR)module is introduced to efficiently integrate fine-grained feature information and enhance the detection accuracy of the algorithm in complex scenes.Secondly,a C2f module based on Dynamic Snake Convolution(C2f-DySnake)is proposed to dynamically adjust the receptive field information,improve the algorithm’s feature extraction ability for blurred or occluded targets,and reduce the occurrence of false detections and missed detections.Finally,the Wise Powerful IoU v2(WPIoUv2)loss function is proposed to further improve the detection accuracy of the algorithm.Experimental results show that the average precision mAP@0.5 of YOLO-SDW on the TT100K dataset is 89.2%,and mAP@0.5:0.95 is 68.5%,which is 4%and 3.3%higher than the YOLOv8s baseline,respectively.YOLO-SDW ensures real-time performance while having higher accuracy.展开更多
In printed circuit board(PCB)manufacturing,surface defects can significantly affect product quality.To address the performance degradation,high false detection rates,and missed detections caused by complex backgrounds...In printed circuit board(PCB)manufacturing,surface defects can significantly affect product quality.To address the performance degradation,high false detection rates,and missed detections caused by complex backgrounds in current intelligent inspection algorithms,this paper proposes CG-YOLOv8,a lightweight and improved model based on YOLOv8n for PCB surface defect detection.The proposed method optimizes the network architecture and compresses parameters to reduce model complexity while maintaining high detection accuracy,thereby enhancing the capability of identifying diverse defects under complex conditions.Specifically,a cascaded multi-receptive field(CMRF)module is adopted to replace the SPPF module in the backbone to improve feature perception,and an inverted residual mobile block(IRMB)is integrated into the C2f module to further enhance performance.Additionally,conventional convolution layers are replaced with GSConv to reduce computational cost,and a lightweight Convolutional Block Attention Module based Convolution(CBAMConv)module is introduced after Grouped Spatial Convolution(GSConv)to preserve accuracy through attention mechanisms.The detection head is also optimized by removing medium and large-scale detection layers,thereby enhancing the model’s ability to detect small-scale defects and further reducing complexity.Experimental results show that,compared to the original YOLOv8n,the proposed CG-YOLOv8 reduces parameter count by 53.9%,improves mAP@0.5 by 2.2%,and increases precision and recall by 2.0%and 1.8%,respectively.These improvements demonstrate that CG-YOLOv8 offers an efficient and lightweight solution for PCB surface defect detection.展开更多
This study proposes a lightweight rice disease detection model optimized for edge computing environments.The goal is to enhance the You Only Look Once(YOLO)v5 architecture to achieve a balance between real-time diagno...This study proposes a lightweight rice disease detection model optimized for edge computing environments.The goal is to enhance the You Only Look Once(YOLO)v5 architecture to achieve a balance between real-time diagnostic performance and computational efficiency.To this end,a total of 3234 high-resolution images(2400×1080)were collected from three major rice diseases Rice Blast,Bacterial Blight,and Brown Spot—frequently found in actual rice cultivation fields.These images served as the training dataset.The proposed YOLOv5-V2 model removes the Focus layer from the original YOLOv5s and integrates ShuffleNet V2 into the backbone,thereby resulting in both model compression and improved inference speed.Additionally,YOLOv5-P,based on PP-PicoDet,was configured as a comparative model to quantitatively evaluate performance.Experimental results demonstrated that YOLOv5-V2 achieved excellent detection performance,with an mAP 0.5 of 89.6%,mAP 0.5–0.95 of 66.7%,precision of 91.3%,and recall of 85.6%,while maintaining a lightweight model size of 6.45 MB.In contrast,YOLOv5-P exhibited a smaller model size of 4.03 MB,but showed lower performance with an mAP 0.5 of 70.3%,mAP 0.5–0.95 of 35.2%,precision of 62.3%,and recall of 74.1%.This study lays a technical foundation for the implementation of smart agriculture and real-time disease diagnosis systems by proposing a model that satisfies both accuracy and lightweight requirements.展开更多
Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone t...Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone to errors and lacks consistency,emphasizing the need for a reliable and automated inspection system.Leveraging both object detection and image segmentation approaches,this research proposes a vision-based solution for the detection of various kinds of tools in the toolkit using deep learning(DL)models.Two Intel RealSense D455f depth cameras were arranged in a top down configuration to capture both RGB and depth images of the toolkits.After applying multiple constraints and enhancing them through preprocessing and augmentation,a dataset consisting of 3300 annotated RGB-D photos was generated.Several DL models were selected through a comprehensive assessment of mean Average Precision(mAP),precision-recall equilibrium,inference latency(target≥30 FPS),and computational burden,resulting in a preference for YOLO and Region-based Convolutional Neural Networks(R-CNN)variants over ViT-based models due to the latter’s increased latency and resource requirements.YOLOV5,YOLOV8,YOLOV11,Faster R-CNN,and Mask R-CNN were trained on the annotated dataset and evaluated using key performance metrics(Recall,Accuracy,F1-score,and Precision).YOLOV11 demonstrated balanced excellence with 93.0%precision,89.9%recall,and a 90.6%F1-score in object detection,as well as 96.9%precision,95.3%recall,and a 96.5%F1-score in instance segmentation with an average inference time of 25 ms per frame(≈40 FPS),demonstrating real-time performance.Leveraging these results,a YOLOV11-based windows application was successfully deployed in a real-time assembly line environment,where it accurately processed live video streams to detect and segment tools within toolkits,demonstrating its practical effectiveness in industrial automation.The application is capable of precisely measuring socket dimensions by utilising edge detection techniques on YOLOv11 segmentation masks,in addition to detection and segmentation.This makes it possible to do specification-level quality control right on the assembly line,which improves the ability to examine things in real time.The implementation is a big step forward for intelligent manufacturing in the Industry 4.0 paradigm.It provides a scalable,efficient,and accurate way to do automated inspection and dimensional verification activities.展开更多
Synthetic speech detection is an essential task in the field of voice security,aimed at identifying deceptive voice attacks generated by text-to-speech(TTS)systems or voice conversion(VC)systems.In this paper,we propo...Synthetic speech detection is an essential task in the field of voice security,aimed at identifying deceptive voice attacks generated by text-to-speech(TTS)systems or voice conversion(VC)systems.In this paper,we propose a synthetic speech detection model called TFTransformer,which integrates both local and global features to enhance detection capabilities by effectively modeling local and global dependencies.Structurally,the model is divided into two main components:a front-end and a back-end.The front-end of the model uses a combination of SincLayer and two-dimensional(2D)convolution to extract high-level feature maps(HFM)containing local dependency of the input speech signals.The back-end uses time-frequency Transformer module to process these feature maps and further capture global dependency.Furthermore,we propose TFTransformer-SE,which incorporates a channel attention mechanism within the 2D convolutional blocks.This enhancement aims to more effectively capture local dependencies,thereby improving the model’s performance.The experiments were conducted on the ASVspoof 2021 LA dataset,and the results showed that the model achieved an equal error rate(EER)of 3.37%without data augmentation.Additionally,we evaluated the model using the ASVspoof 2019 LA dataset,achieving an EER of 0.84%,also without data augmentation.This demonstrates that combining local and global dependencies in the time-frequency domain can significantly improve detection accuracy.展开更多
Aiming at the scale adaptation of automatic driving target detection algorithms in low illumination environments and the shortcomings in target occlusion processing,this paper proposes a YOLO-LKSDS automatic driving d...Aiming at the scale adaptation of automatic driving target detection algorithms in low illumination environments and the shortcomings in target occlusion processing,this paper proposes a YOLO-LKSDS automatic driving detection model.Firstly,the Contrast-Limited Adaptive Histogram Equalisation(CLAHE)image enhancement algorithm is improved to increase the image contrast and enhance the detailed features of the target;then,on the basis of the YOLOv5 model,the Kmeans++clustering algorithm is introduced to obtain a suitable anchor frame,and SPPELAN spatial pyramid pooling is improved to enhance the accuracy and robustness of the model for multi-scale target detection.Finally,an improved SEAM(Separated and Enhancement Attention Module)attention mechanism is combined with the DIOU-NMS algorithm to optimize the model’s performance when dealing with occlusion and dense scenes.Compared with the original model,the improved YOLO-LKSDS model achieves a 13.3%improvement in accuracy,a 1.7%improvement in mAP,and 240,000 fewer parameters on the BDD100K dataset.In order to validate the generalization of the improved algorithm,we selected the KITTI dataset for experimentation,which shows that YOLOv5’s accuracy improves by 21.1%,recall by 36.6%,and mAP50 by 29.5%,respectively,on the KITTI dataset.The deployment of this paper’s algorithm is verified by an edge computing platform,where the average speed of detection reaches 24.4 FPS while power consumption remains below 9 W,demonstrating high real-time capability and energy efficiency.展开更多
Nondestructive measurement technology of phenotype can provide substantial phenotypic data support for applications such as seedling breeding,management,and quality testing.The current method of measuring seedling phe...Nondestructive measurement technology of phenotype can provide substantial phenotypic data support for applications such as seedling breeding,management,and quality testing.The current method of measuring seedling phenotypes mainly relies on manual measurement which is inefficient,subjective and destroys samples.Therefore,the paper proposes a nondestructive measurement method for the canopy phenotype of the watermelon plug seedlings based on deep learning.The Azure Kinect was used to shoot canopy color images,depth images,and RGB-D images of the watermelon plug seedlings.The Mask-RCNN network was used to classify,segment,and count the canopy leaves of the watermelon plug seedlings.To reduce the error of leaf area measurement caused by mutual occlusion of leaves,the leaves were repaired by CycleGAN,and the depth images were restored by image processing.Then,the Delaunay triangulation was adopted to measure the leaf area in the leaf point cloud.The YOLOX target detection network was used to identify the growing point position of each seedling on the plug tray.Then the depth differences between the growing point and the upper surface of the plug tray were calculated to obtain plant height.The experiment results show that the nondestructive measurement algorithm proposed in this paper achieves good measurement performance for the watermelon plug seedlings from the 1 true-leaf to 3 true-leaf stages.The average relative error of measurement is 2.33%for the number of true leaves,4.59%for the number of cotyledons,8.37%for the leaf area,and 3.27%for the plant height.The experiment results demonstrate that the proposed algorithm in this paper provides an effective solution for the nondestructive measurement of the canopy phenotype of the plug seedlings.展开更多
In this study,the dosimetric characteristics(thickness applicability,preheating time,temperature and humidity dependence,in-batch uniformity,readout reproducibility,dose linearity,self-decay,and electron energy respon...In this study,the dosimetric characteristics(thickness applicability,preheating time,temperature and humidity dependence,in-batch uniformity,readout reproducibility,dose linearity,self-decay,and electron energy response)of engineered polycarbonate films irradiated with an electron beam(0–600 kGy)were investigated using photoluminescence spectroscopy.The results show a linear relationship between photoluminescence intensity and radiation dose when the thickness of the polycarbonate film is 0.3 mm.A higher fluorescence intensity can be obtained by preheating at 60℃ for 180 min before photoluminescence spectrum analysis.As the temperature during spectral testing and the ambient humidity(during and after irradiation)increased,the photoluminescence intensity of the polycarbonate films decreased.The photoluminescence intensity deviation of the polycarbonate films produced within the same batch at 100 kGy is 2.73%.After ten times of repeated excitations and readouts,the coefficients of variation in photoluminescence intensity are less than 8.6%,and the linear correlation coefficient between photoluminescence intensity and irradiation dose is 0.965 in the dose capture range of 20–600 kGy.Within 60 days of irradiation,the photoluminescence intensity of the polycarbonate film decreased to 60%of the initial value.The response of the 0.3 mm polycarbonate films to electron beams with energies exceeding 3.5 MeV does not differ significantly.This comprehensive analysis indicates the potential of polycarbonate films as a high-radiation dose detection material.展开更多
文摘BACKGROUND Early detection of precancerous lesions is of vital importance for reducing the incidence and mortality of upper gastrointestinal(UGI)tract cancer.However,traditional endoscopy has certain limitations in detecting precancerous lesions.In contrast,real-time computer-aided detection(CAD)systems enhanced by artificial intelligence(AI)systems,although they may increase unnecessary medical procedures,can provide immediate feedback during examination,thereby improving the accuracy of lesion detection.This article aims to conduct a meta-analysis of the diagnostic performance of CAD systems in identifying precancerous lesions of UGI tract cancer during esophagogastroduodenoscopy(EGD),evaluate their potential clinical application value,and determine the direction for further research.AIM To investigate the improvement of the efficiency of EGD examination by the realtime AI-enabled real-time CAD system(AI-CAD)system.METHODS PubMed,EMBASE,Web of Science and Cochrane Library databases were searched by two independent reviewers to retrieve literature with per-patient analysis with a deadline up until April 2025.A meta-analysis was performed with R Studio software(R4.5.0).A random-effects model was used and subgroup analysis was carried out to identify possible sources of heterogeneity.RESULTS The initial search identified 802 articles.According to the inclusion criteria,2113 patients from 10 studies were included in this meta-analysis.The pooled accuracy difference,logarithmic difference of diagnostic odds ratios,sensitivity,specificity and the area under the summary receiver operating characteristic curve(area under the curve)of both AI group and endoscopist group for detecting precancerous lesion were 0.16(95%CI:0.12-0.20),-0.19(95%CI:-0.75-0.37),0.89(95%CI:0.85-0.92,AI group),0.67(95%CI:0.63-0.71,endoscopist group),0.89(95%CI:0.84-0.93,AI group),0.77(95%CI:0.70-0.83,endoscopist group),0.928(95%CI:0.841-0.948,AI group),0.722(95%CI:0.677-0.821,endoscopist group),respectively.CONCLUSION The present studies further provide evidence that the AI-CAD is a reliable endoscopic diagnostic tool that can be used to assist endoscopists in detection of precancerous lesions in the UGI tract.It may be introduced on a large scale for clinical application to enhance the accuracy of detecting precancerous lesions in the UGI tract.
基金Supported by Science and Technology Projects in Guangzhou,No.2023A04J2282。
文摘BACKGROUND Computer-aided diagnosis(CAD)may assist endoscopists in identifying and classifying polyps during colonoscopy for detecting colorectal cancer.AIM To build a system using CAD to detect and classify polyps based on the Yamada classification.METHODS A total of 24045 polyp and 72367 nonpolyp images were obtained.We established a computer-aided detection and Yamada classification model based on the YOLOv7 neural network algorithm.Frame-based and image-based evaluation metrics were employed to assess the performance.RESULTS Computer-aided detection and Yamada classification screened polyps with a precision of 96.7%,a recall of 95.8%,and an F1-score of 96.2%,outperforming those of all groups of endoscopists.In regard to the Yamada classification of polyps,the CAD system displayed a precision of 82.3%,a recall of 78.5%,and an F1-score of 80.2%,outper-forming all levels of endoscopists.In addition,according to the image-based method,the CAD had an accuracy of 99.2%,a specificity of 99.5%,a sensitivity of 98.5%,a positive predictive value of 99.0%,a negative predictive value of 99.2%for polyp detection and an accuracy of 97.2%,a specificity of 98.4%,a sensitivity of 79.2%,a positive predictive value of 83.0%,and a negative predictive value of 98.4%for poly Yamada classification.CONCLUSION We developed a novel CAD system based on a deep neural network for polyp detection,and the Yamada classi-fication outperformed that of nonexpert endoscopists.This CAD system could help community-based hospitals enhance their effectiveness in polyp detection and classification.
文摘In the present research,we describe a computer-aided detection(CAD)method aimed at automatic fetal head circumference(HC)measurement in 2D ultrasonography pictures during all trimesters of pregnancy.The HC might be utilized toward determining gestational age and tracking fetal development.This automated approach is particularly valuable in low-resource settings where access to trained sonographers is limited.The CAD system is divided into two steps:to begin,Haar-like characteristics were extracted from ultrasound pictures in order to train a classifier using random forests to find the fetal skull.We identified the HC using dynamic programming,an elliptical fit,and a Hough transform.The computer-aided detection(CAD)program was well-trained on 999 pictures(HC18 challenge data source),and then verified on 335 photos from all trimesters in an independent test set.A skilled sonographer and an expert in medicine personally marked the test set.We used the crown-rump length(CRL)measurement to calculate the reference gestational age(GA).In the first,second,and third trimesters,the median difference between the standard GA and the GA calculated by the skilled sonographer stayed at 0.7±2.7,0.0±4.5,and 2.0±12.0 days,respectively.The regular duration variance between the baseline GA and the health investigator’s GA remained 1.5±3.0,1.9±5.0,and 4.0±14 a couple of days.The mean variance between the standard GA and the CAD system’s GA remained between 0.5 and 5.0,with an additional variation of 2.9 to 12.5 days.The outcomes reveal that the computer-aided detection(CAD)program outperforms an expert sonographer.When paired with the classifications reported in the literature,the provided system achieves results that are comparable or even better.We have assessed and scheduled this computerized approach for HC evaluation,which includes information from all trimesters of gestation.
基金the National Natural Science Foundation of China(No.813716234)the National Basic Research Program(973) of China(No.2010CB834302)the Shanghai Jiao Tong University Medical Engineering Cross Research Funds(Nos.YG2013MS30 and YG2011MS51)
文摘CT colonography （CTC） is a non-invasive screening technique for the detection of eolorectal polyps, as an alternative to optical colonoscopy in clinical practice. Computer-aided detection （CAD） for CTC refers to a scheme which automatically detects colorectal polyps and masses in CT images of the colon. It has the potential to increase radiologists＇ detection performance and greatly shorten the detection time. Over the years, technical developments have advanced CAD for CTC substantially. In this paper, key techniques used in CAD for polyp detection are reviewed. Illustrations about the performance of existing CAD schemes show their relatively high sensitivity and low false positive rate. However, these CAD schemes are still suffering from technical or clinical problems. Some existing challenges faced by CAD are also pointed out at the end of this paper.
基金This work was partially supported by the NIH/NCI grant#CA206171 of the National Cancer Institute and the PSC-CUNY award 62310–0050.
文摘Computer aided detection(CADe)of pulmonary nodules plays an important role in assisting radiologists’diagnosis and alleviating interpretation burden for lung cancer.Current CADe systems,aiming at simulating radiologists’examination procedure,are built upon computer tomography(CT)images with feature extraction for detection and diagnosis.Human visual perception in CT image is reconstructed from sinogram,which is the original raw data acquired from CT scanner.In this work,different from the conventional image based CADe system,we propose a novel sinogram based CADe system in which the full projection information is used to explore additional effective features of nodules in the sinogram domain.Facing the challenges of limited research in this concept and unknown effective features in the sinogram domain,we design a new CADe system that utilizes the self-learning power of the convolutional neural network to learn and extract effective features from sinogram.The proposed system was validated on 208 patient cases from the publicly available online Lung Image Database Consortium database,with each case having at least one juxtapleural nodule annotation.Experimental results demonstrated that our proposed method obtained a value of 0.91 of the area under the curve(AUC)of receiver operating characteristic based on sinogram alone,comparing to 0.89 based on CT image alone.Moreover,a combination of sinogram and CT image could further improve the value of AUC to 0.92.This study indicates that pulmonary nodule detection in the sinogram domain is feasible with deep learning.
文摘Background:The main cause of breast cancer is the deterioration of malignant tumor cells in breast tissue.Early diagnosis of tumors has become the most effective way to prevent breast cancer.Method:For distinguishing between tumor and non-tumor in MRI,a new type of computer-aided detection CAD system for breast tumors is designed in this paper.The CAD system was constructed using three networks,namely,the VGG16,Inception V3,and ResNet50.Then,the influence of the convolutional neural network second migration on the experimental results was further explored in the VGG16 system.Result:CAD system built based on VGG16,Inception V3,and ResNet50 has higher performance than mainstream CAD systems.Among them,the system built based on VGG16 and ResNet50 has outstanding performance.We further explore the impact of the secondary migration on the experimental results in the VGG16 system,and these results show that the migration can improve system performance of the proposed framework.Conclusion:The accuracy of CNN represented by VGG16 is as high as 91.25%,which is more accurate than traditional machine learningmodels.The F1 score of the three basic networks that join the secondary migration is close to 1.0,and the performance of the VGG16-based breast tumor CAD system is higher than Inception V3,and ResNet50.
文摘Breast cancer is one of the most common and deadliest types of cancer among women and early detection is of major importance to decrease mortality rates. Microcalcification clusters and masses are two major indicators of malignancy in the early stages of this disease, when mammography is typically used as the screening technology. Computer-Aided Diagnosis (CAD) systems can support the radiologists’ work, by performing a double-reading process, which provides a second opinion that the physician can take into account in the detection process. This paper presents a CAD model based on computer vision procedures for locating suspicious regions that are later analyzed by artificial neural networks, support vector machines and linear discriminant analysis, to classify them into benign or malignant, based on a set of features that are extracted from lesions to characterize their visual content. A genetic algorithm is used to find the subset of features that provide the greatest discriminant power. Our results show that the SVM presented the highest overall accuracy and specificity for classifying microcalcification clusters, while the NN outperformed the rest for mass-classification in the same parameters. Overall accuracy, sensitivity and specificity were measured.
文摘The mechanical-touched detector was used commonly in textile production limes. It has some defect with high false alarm rate, response delay and high maintenance cost. In order to overcome such defects, a new kind device was developed and used to detect roller tangled in the production lines. It is based on image processing. The core algorithm was composed of Canny edge detection, removing interference, detection of perpendicularity line and detection of broken tow. After the four steps, the broken tow could be recognized quickly and correctly. The algorithm is robust and high efficiency. So, the detection device has characteristic of stable, quickly-response and low maintains cost. It can keep superiority with long lifespan even in more formidable conditions. It guarantees a safe and stable production condition.
文摘In this thesis, a strategy realizing the computer-aided detection (CAD) of the epileptic waves in EEG isintroduced. The expert criterion, continuous wavelet transformation, neural networks, and characteristic parametermeasuremente these modern signa1 processing weapons were synthesized togetLher to form a so-called multi-method.It was estimated that the advantages of all the powerful techniques could be exploited systematically. Therefore, theCAD’s capacities in the long-term monitoring, trCaAnent and control of epilepsy might be enhanced. In this strategy,the raw EEG signals were uniformed and the expelt criterion were applied to discard most of aItifacts in them at first,and then the signals were pre-processed by continuous wavelet transformation. Some characteristic parameters wereextracted from the raw signals and the pre-processed ones. Consequently groups of eighteen parameters were sent totrain or test BP networks. By applying this theme a correct-detection rate of 84.3% for spike and sharp waves, and88.9% for sPike and sharp slow waves were obtained. In the next step, some non-linear tools wtll also be equippedwith the CAD system.
基金supported by the National Science and Technology Major Project of China[2017ZX10201302-008]the CAMS Innovation Fund for Medical Sciences[2021-I2M-1-037].
文摘Background:Computer-aided detection(CAD)software has been introduced to automatically interpret digital chest X-rays.This study aimed to evaluate the performance of CAD software(JF CXR-1 v3.0,which was developed by a domestic Hi-tech enterprise)in tuberculosis(TB)case finding in China.Methods:In 2019,we conducted an internal evaluation of the performance of JF CXR-1 v3.0 by reading standard images annotated by a panel of experts.In 2020,using the reading results of chest X-rays by a panel of experts as the reference standard,we conducted an on-site prospective study to evaluate the performance of JF CXR-1 v3.0 and local radiologists in TB case finding in 13 township health centers in Zhongmu County,Henan Province.Results:Internal assessment results based on 277 standard images showed that JF CXR-1 v3.0 had a sensitivity of 85.94%(95%confidence interval[CI]:77.42%,94.45%)and a specificity of 74.65%(95%CI:68.81%,80.49%)to distinguish active TB from other imaging conditions.In the on-site evaluation phase,images from 3705 outpatients who underwent chest X-ray detection were read by JF CXR-1 v3.0 and local radiologists in parallel.The imaging diagnosis of local radiologists for active TB had a sensitivity of 32.89%(95%CI:22.33%,43.46%)and a specificity of 99.28%(95%CI:99.01%,99.56%),while JF CXR-1 v3.0 showed a significantly higher sensitivity of 92.11%(95%CI:86.04%,98.17%)(p<0.05)and maintained high specificity at 94.54%(95%CI:93.81%,95.28%).Conclusions:CAD software could play a positive role in improving the TB case finding capability of township health centers.
基金funded by the Indian Council of Medical Research(ICMR),New Delhi,Government of India under Grant No.EM/SG/Dev.Res/124/0812-2023.
文摘Jaundice,common condition in newborns,is characterized by yellowing of the skin and eyes due to elevated levels of bilirubin in the blood.Timely detection and management of jaundice are crucial to prevent potential complications.Traditional jaundice assessment methods rely on visual inspection or invasive blood tests that are subjective and painful for infants,respectively.Although several automated methods for jaundice detection have been developed during the past few years,a limited number of reviews consolidating these developments have been presented till date,making it essential to systematically evaluate and present the existing advancements.This paper fills this gap by providing a thorough survey of automated methods for jaundice detection in neonates.The primary focus of the survey is to review the existing methodologies,techniques,and technologies used for neonatal jaundice detection.The key findings from the review indicate that image-based bilirubinometers and transcutaneous bilirubinometers are promising non-invasive alternatives,and provide a good trade-off between accuracy and ease of use.However,their effectiveness varies with factors like skin pigmentation,gestational age,and measurement site.Spectroscopic and biosensor-based techniques show high sensitivity but need further clinical validation.Despite advancements,several challenges including device calibration,large-scale validation,and regulatory barriers still haunt the researchers.Standardization,regulatory compliances,and seamless integration into healthcare workflows are the key hurdles to be addressed.By consolidating the current knowledge and discussing the challenges and opportunities in this field,this survey aims to contribute to the advancement of automatic jaundice detection and ultimately improve neonatal care.
文摘Background Colonic polyps are frequently encountered in clinics. Computed tomographic colonography （CTC）, as a painless and quick detection, has high values in clinics. In this study, we evaluated the application value of computer-aided detection （CAD） in CTC detection of colonic polyps in the Chinese population.Methods CTC was performed with a GE 64-row multidetector computed tomography （MDCT） scanner. Data of 50 CTC patients （39 patients positive for at least one polyp of ≥0.5 cm in size and the other 11 patients negative by endoscopic detection） were retrospectively reviewed first without computer-aided detection （CAD） and then with CAD by four radiologists （two were experienced and another two inexperienced） blinded to colonoscopy findings. The sensitivity,specificity, positive predictive value, negative predictive value, and accuracy of detected colonic polyps, as well as the areas under the ROC curves （Az value） with and without CAD were calculated.Results CAD increased the overall sensitivity, specificity, positive predictive value, negative predictive value and accuracy of the colonic polyps detected by experienced and inexperienced readers. The sensitivity in detecting small polyps （5-9 mm） with CAD in experienced and inexperienced readers increased from 82% and 44% to 93% and 82%,respectively （P 〉0.05 and P 〈0.001）. With the use of CAD, the overall false positive rate and false negative rate for the detection of polyps by experienced and inexperienced readers decreased in different degrees. Among 13 sessile polyps not detected by CAD, two were 〉1.0 cm, eleven were 5-9 mm in diameter, and nine were fiat-shaped lesions.Conclusions The application of CAD in combination with CTC can increase the ability to detect colonic polyps,particularly for inexperienced readers. However, CAD is of limited value for the detection of flat polyps.
基金funded by Key research and development Program of Henan Province(No.251111211200)National Natural Science Foundation of China(Grant No.U2004163).
文摘Traffic sign detection is an important part of autonomous driving,and its recognition accuracy and speed are directly related to road traffic safety.Although convolutional neural networks(CNNs)have made certain breakthroughs in this field,in the face of complex scenes,such as image blur and target occlusion,the traffic sign detection continues to exhibit limited accuracy,accompanied by false positives and missed detections.To address the above problems,a traffic sign detection algorithm,You Only Look Once-based Skip Dynamic Way(YOLO-SDW)based on You Only Look Once version 8 small(YOLOv8s),is proposed.Firstly,a Skip Connection Reconstruction(SCR)module is introduced to efficiently integrate fine-grained feature information and enhance the detection accuracy of the algorithm in complex scenes.Secondly,a C2f module based on Dynamic Snake Convolution(C2f-DySnake)is proposed to dynamically adjust the receptive field information,improve the algorithm’s feature extraction ability for blurred or occluded targets,and reduce the occurrence of false detections and missed detections.Finally,the Wise Powerful IoU v2(WPIoUv2)loss function is proposed to further improve the detection accuracy of the algorithm.Experimental results show that the average precision mAP@0.5 of YOLO-SDW on the TT100K dataset is 89.2%,and mAP@0.5:0.95 is 68.5%,which is 4%and 3.3%higher than the YOLOv8s baseline,respectively.YOLO-SDW ensures real-time performance while having higher accuracy.
基金funded by the Joint Funds of the National Natural Science Foundation of China(U2341223)the Beijing Municipal Natural Science Foundation(No.4232067).
文摘In printed circuit board(PCB)manufacturing,surface defects can significantly affect product quality.To address the performance degradation,high false detection rates,and missed detections caused by complex backgrounds in current intelligent inspection algorithms,this paper proposes CG-YOLOv8,a lightweight and improved model based on YOLOv8n for PCB surface defect detection.The proposed method optimizes the network architecture and compresses parameters to reduce model complexity while maintaining high detection accuracy,thereby enhancing the capability of identifying diverse defects under complex conditions.Specifically,a cascaded multi-receptive field(CMRF)module is adopted to replace the SPPF module in the backbone to improve feature perception,and an inverted residual mobile block(IRMB)is integrated into the C2f module to further enhance performance.Additionally,conventional convolution layers are replaced with GSConv to reduce computational cost,and a lightweight Convolutional Block Attention Module based Convolution(CBAMConv)module is introduced after Grouped Spatial Convolution(GSConv)to preserve accuracy through attention mechanisms.The detection head is also optimized by removing medium and large-scale detection layers,thereby enhancing the model’s ability to detect small-scale defects and further reducing complexity.Experimental results show that,compared to the original YOLOv8n,the proposed CG-YOLOv8 reduces parameter count by 53.9%,improves mAP@0.5 by 2.2%,and increases precision and recall by 2.0%and 1.8%,respectively.These improvements demonstrate that CG-YOLOv8 offers an efficient and lightweight solution for PCB surface defect detection.
文摘This study proposes a lightweight rice disease detection model optimized for edge computing environments.The goal is to enhance the You Only Look Once(YOLO)v5 architecture to achieve a balance between real-time diagnostic performance and computational efficiency.To this end,a total of 3234 high-resolution images(2400×1080)were collected from three major rice diseases Rice Blast,Bacterial Blight,and Brown Spot—frequently found in actual rice cultivation fields.These images served as the training dataset.The proposed YOLOv5-V2 model removes the Focus layer from the original YOLOv5s and integrates ShuffleNet V2 into the backbone,thereby resulting in both model compression and improved inference speed.Additionally,YOLOv5-P,based on PP-PicoDet,was configured as a comparative model to quantitatively evaluate performance.Experimental results demonstrated that YOLOv5-V2 achieved excellent detection performance,with an mAP 0.5 of 89.6%,mAP 0.5–0.95 of 66.7%,precision of 91.3%,and recall of 85.6%,while maintaining a lightweight model size of 6.45 MB.In contrast,YOLOv5-P exhibited a smaller model size of 4.03 MB,but showed lower performance with an mAP 0.5 of 70.3%,mAP 0.5–0.95 of 35.2%,precision of 62.3%,and recall of 74.1%.This study lays a technical foundation for the implementation of smart agriculture and real-time disease diagnosis systems by proposing a model that satisfies both accuracy and lightweight requirements.
基金National Science and Technology Council,the Republic of China,under grants NSTC 113-2221-E-194-011-MY3 and Research Center on Artificial Intelligence and Sustainability,National Chung Cheng University under the research project grant titled“Generative Digital Twin System Design for Sustainable Smart City Development in Taiwan.
文摘Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone to errors and lacks consistency,emphasizing the need for a reliable and automated inspection system.Leveraging both object detection and image segmentation approaches,this research proposes a vision-based solution for the detection of various kinds of tools in the toolkit using deep learning(DL)models.Two Intel RealSense D455f depth cameras were arranged in a top down configuration to capture both RGB and depth images of the toolkits.After applying multiple constraints and enhancing them through preprocessing and augmentation,a dataset consisting of 3300 annotated RGB-D photos was generated.Several DL models were selected through a comprehensive assessment of mean Average Precision(mAP),precision-recall equilibrium,inference latency(target≥30 FPS),and computational burden,resulting in a preference for YOLO and Region-based Convolutional Neural Networks(R-CNN)variants over ViT-based models due to the latter’s increased latency and resource requirements.YOLOV5,YOLOV8,YOLOV11,Faster R-CNN,and Mask R-CNN were trained on the annotated dataset and evaluated using key performance metrics(Recall,Accuracy,F1-score,and Precision).YOLOV11 demonstrated balanced excellence with 93.0%precision,89.9%recall,and a 90.6%F1-score in object detection,as well as 96.9%precision,95.3%recall,and a 96.5%F1-score in instance segmentation with an average inference time of 25 ms per frame(≈40 FPS),demonstrating real-time performance.Leveraging these results,a YOLOV11-based windows application was successfully deployed in a real-time assembly line environment,where it accurately processed live video streams to detect and segment tools within toolkits,demonstrating its practical effectiveness in industrial automation.The application is capable of precisely measuring socket dimensions by utilising edge detection techniques on YOLOv11 segmentation masks,in addition to detection and segmentation.This makes it possible to do specification-level quality control right on the assembly line,which improves the ability to examine things in real time.The implementation is a big step forward for intelligent manufacturing in the Industry 4.0 paradigm.It provides a scalable,efficient,and accurate way to do automated inspection and dimensional verification activities.
基金supported by project ZR2022MF330 supported by Shandong Provincial Natural Science Foundationthe National Natural Science Foundation of China under Grant No.61701286.
文摘Synthetic speech detection is an essential task in the field of voice security,aimed at identifying deceptive voice attacks generated by text-to-speech(TTS)systems or voice conversion(VC)systems.In this paper,we propose a synthetic speech detection model called TFTransformer,which integrates both local and global features to enhance detection capabilities by effectively modeling local and global dependencies.Structurally,the model is divided into two main components:a front-end and a back-end.The front-end of the model uses a combination of SincLayer and two-dimensional(2D)convolution to extract high-level feature maps(HFM)containing local dependency of the input speech signals.The back-end uses time-frequency Transformer module to process these feature maps and further capture global dependency.Furthermore,we propose TFTransformer-SE,which incorporates a channel attention mechanism within the 2D convolutional blocks.This enhancement aims to more effectively capture local dependencies,thereby improving the model’s performance.The experiments were conducted on the ASVspoof 2021 LA dataset,and the results showed that the model achieved an equal error rate(EER)of 3.37%without data augmentation.Additionally,we evaluated the model using the ASVspoof 2019 LA dataset,achieving an EER of 0.84%,also without data augmentation.This demonstrates that combining local and global dependencies in the time-frequency domain can significantly improve detection accuracy.
基金supported by the Key R&D Program of Shaanxi Province(No.2025CYYBXM-078).
文摘Aiming at the scale adaptation of automatic driving target detection algorithms in low illumination environments and the shortcomings in target occlusion processing,this paper proposes a YOLO-LKSDS automatic driving detection model.Firstly,the Contrast-Limited Adaptive Histogram Equalisation(CLAHE)image enhancement algorithm is improved to increase the image contrast and enhance the detailed features of the target;then,on the basis of the YOLOv5 model,the Kmeans++clustering algorithm is introduced to obtain a suitable anchor frame,and SPPELAN spatial pyramid pooling is improved to enhance the accuracy and robustness of the model for multi-scale target detection.Finally,an improved SEAM(Separated and Enhancement Attention Module)attention mechanism is combined with the DIOU-NMS algorithm to optimize the model’s performance when dealing with occlusion and dense scenes.Compared with the original model,the improved YOLO-LKSDS model achieves a 13.3%improvement in accuracy,a 1.7%improvement in mAP,and 240,000 fewer parameters on the BDD100K dataset.In order to validate the generalization of the improved algorithm,we selected the KITTI dataset for experimentation,which shows that YOLOv5’s accuracy improves by 21.1%,recall by 36.6%,and mAP50 by 29.5%,respectively,on the KITTI dataset.The deployment of this paper’s algorithm is verified by an edge computing platform,where the average speed of detection reaches 24.4 FPS while power consumption remains below 9 W,demonstrating high real-time capability and energy efficiency.
基金funded by the National Key Research and Development Program of China(Grant No.2019YFD1001900)the HZAU-AGIS Cooperation Fund(Grant No.SZYJY2022006).
文摘Nondestructive measurement technology of phenotype can provide substantial phenotypic data support for applications such as seedling breeding,management,and quality testing.The current method of measuring seedling phenotypes mainly relies on manual measurement which is inefficient,subjective and destroys samples.Therefore,the paper proposes a nondestructive measurement method for the canopy phenotype of the watermelon plug seedlings based on deep learning.The Azure Kinect was used to shoot canopy color images,depth images,and RGB-D images of the watermelon plug seedlings.The Mask-RCNN network was used to classify,segment,and count the canopy leaves of the watermelon plug seedlings.To reduce the error of leaf area measurement caused by mutual occlusion of leaves,the leaves were repaired by CycleGAN,and the depth images were restored by image processing.Then,the Delaunay triangulation was adopted to measure the leaf area in the leaf point cloud.The YOLOX target detection network was used to identify the growing point position of each seedling on the plug tray.Then the depth differences between the growing point and the upper surface of the plug tray were calculated to obtain plant height.The experiment results show that the nondestructive measurement algorithm proposed in this paper achieves good measurement performance for the watermelon plug seedlings from the 1 true-leaf to 3 true-leaf stages.The average relative error of measurement is 2.33%for the number of true leaves,4.59%for the number of cotyledons,8.37%for the leaf area,and 3.27%for the plant height.The experiment results demonstrate that the proposed algorithm in this paper provides an effective solution for the nondestructive measurement of the canopy phenotype of the plug seedlings.
基金supported by the National Natural Science Foundation of China(No.12305385)Key Projects of Scientific Research of the Hunan Provincial Department of Education(22A0310)the Research Startup Project of University of South China(220XQD025).
文摘In this study,the dosimetric characteristics(thickness applicability,preheating time,temperature and humidity dependence,in-batch uniformity,readout reproducibility,dose linearity,self-decay,and electron energy response)of engineered polycarbonate films irradiated with an electron beam(0–600 kGy)were investigated using photoluminescence spectroscopy.The results show a linear relationship between photoluminescence intensity and radiation dose when the thickness of the polycarbonate film is 0.3 mm.A higher fluorescence intensity can be obtained by preheating at 60℃ for 180 min before photoluminescence spectrum analysis.As the temperature during spectral testing and the ambient humidity(during and after irradiation)increased,the photoluminescence intensity of the polycarbonate films decreased.The photoluminescence intensity deviation of the polycarbonate films produced within the same batch at 100 kGy is 2.73%.After ten times of repeated excitations and readouts,the coefficients of variation in photoluminescence intensity are less than 8.6%,and the linear correlation coefficient between photoluminescence intensity and irradiation dose is 0.965 in the dose capture range of 20–600 kGy.Within 60 days of irradiation,the photoluminescence intensity of the polycarbonate film decreased to 60%of the initial value.The response of the 0.3 mm polycarbonate films to electron beams with energies exceeding 3.5 MeV does not differ significantly.This comprehensive analysis indicates the potential of polycarbonate films as a high-radiation dose detection material.
