Early identification and treatment of stroke can greatly improve patient outcomes and quality of life.Although clinical tests such as the Cincinnati Pre-hospital Stroke Scale(CPSS)and the Face Arm Speech Test(FAST)are...Early identification and treatment of stroke can greatly improve patient outcomes and quality of life.Although clinical tests such as the Cincinnati Pre-hospital Stroke Scale(CPSS)and the Face Arm Speech Test(FAST)are commonly used for stroke screening,accurate administration is dependent on specialized training.In this study,we proposed a novel multimodal deep learning approach,based on the FAST,for assessing suspected stroke patients exhibiting symptoms such as limb weakness,facial paresis,and speech disorders in acute settings.We collected a dataset comprising videos and audio recordings of emergency room patients performing designated limb movements,facial expressions,and speech tests based on the FAST.We compared the constructed deep learning model,which was designed to process multi-modal datasets,with six prior models that achieved good action classification performance,including the I3D,SlowFast,X3D,TPN,TimeSformer,and MViT.We found that the findings of our deep learning model had a higher clinical value compared with the other approaches.Moreover,the multi-modal model outperformed its single-module variants,highlighting the benefit of utilizing multiple types of patient data,such as action videos and speech audio.These results indicate that a multi-modal deep learning model combined with the FAST could greatly improve the accuracy and sensitivity of early stroke identification of stroke,thus providing a practical and powerful tool for assessing stroke patients in an emergency clinical setting.展开更多
In intelligent flower thinning robot applications,accurate and efficient apple flower detection is the key to realizing automated fruit tree thinning operations.However,complex orchard environments and diverse flower ...In intelligent flower thinning robot applications,accurate and efficient apple flower detection is the key to realizing automated fruit tree thinning operations.However,complex orchard environments and diverse flower characteristics pose many challenges to apple blossom detection,such as shading,light variations,flower densities,and so on.To address these challenges,this study proposes an improved model based on the YOLO target detection framework which is named the YOLO-FL apple flower detection model.The model enhances the feature extraction capability by optimizing the Backbone part with EC3DFM structure,while introducing MFEM structure in the Neck part to improve the feature fusion effect.In addition,the ABRLoss loss function is used to optimize the prediction results of the prediction frame,and it also adds the SimAM attention mechanism to the middle two detection heads in the Neck part,which further improves the detection performance of the model.The experimental results respectively show that YOLO-FL achieves 74.63%,73.82%,and 79.97%accuracy,recall,and mean average precision on the test set,which shows significant improvement over the benchmark model.Meanwhile,the model size was only 4693 kB,demonstrating high efficiency and storage advantages.After deploying the YOLO-FL model to the intelligent flower thinning robot,the frame rate of the test image was 40.7 FPS,the average missed detection rate was 7.26%,the false detection rate was 6.89%,and the model was able to efficiently complete the apple flower detection in the complex orchard environment.This study provides an effective solution and technical support for the application of image recognition technology in intelligent flower thinning robots.展开更多
In order to realize the intelligent identification of maize leaf diseases for accurate prevention and control,this study proposed a maize disease detection method based on improved MobileNet V3-small,using a UAV to co...In order to realize the intelligent identification of maize leaf diseases for accurate prevention and control,this study proposed a maize disease detection method based on improved MobileNet V3-small,using a UAV to collect maize disease images and establish a maize disease dataset in a complex context,and explored the effects of data expansion and migration learning on model recognition accuracy,recall rate,and F1-score instructive evaluative indexes,and the results show that the two approaches of data expansion and migration learning effectively improved the accuracy of the model.The structured compression of MobileNet V3-small bneck layer retains only 6 layers,the expansion multiplier of each layer was redesigned,32-fold fast downsampling was used in the first layer,and the location of the SE module was optimized.The improved model had an average accuracy of 79.52%in the test set,a recall of 77.91%,an F1-score of 78.62%,a model size of 2.36 MB,and a single image detection speed of 9.02 ms.The detection accuracy and speed of the model can meet the requirements of mobile or embedded devices.This study provides technical support for realizing the intelligent detection of maize leaf diseases.展开更多
基金supported by the Ministry of Science and Technology of China,No.2020AAA0109605(to XL)Meizhou Major Scientific and Technological Innovation PlatformsProjects of Guangdong Provincial Science & Technology Plan Projects,No.2019A0102005(to HW).
文摘Early identification and treatment of stroke can greatly improve patient outcomes and quality of life.Although clinical tests such as the Cincinnati Pre-hospital Stroke Scale(CPSS)and the Face Arm Speech Test(FAST)are commonly used for stroke screening,accurate administration is dependent on specialized training.In this study,we proposed a novel multimodal deep learning approach,based on the FAST,for assessing suspected stroke patients exhibiting symptoms such as limb weakness,facial paresis,and speech disorders in acute settings.We collected a dataset comprising videos and audio recordings of emergency room patients performing designated limb movements,facial expressions,and speech tests based on the FAST.We compared the constructed deep learning model,which was designed to process multi-modal datasets,with six prior models that achieved good action classification performance,including the I3D,SlowFast,X3D,TPN,TimeSformer,and MViT.We found that the findings of our deep learning model had a higher clinical value compared with the other approaches.Moreover,the multi-modal model outperformed its single-module variants,highlighting the benefit of utilizing multiple types of patient data,such as action videos and speech audio.These results indicate that a multi-modal deep learning model combined with the FAST could greatly improve the accuracy and sensitivity of early stroke identification of stroke,thus providing a practical and powerful tool for assessing stroke patients in an emergency clinical setting.
基金supported the Fruit Industry Modern Agricultural Technology System in Shandong Province(SDAIT-06-12)Innovation Team Fund for Key R&D Program of Shandong Province,China(2024TZXD038,2024TZXD045)。
文摘In intelligent flower thinning robot applications,accurate and efficient apple flower detection is the key to realizing automated fruit tree thinning operations.However,complex orchard environments and diverse flower characteristics pose many challenges to apple blossom detection,such as shading,light variations,flower densities,and so on.To address these challenges,this study proposes an improved model based on the YOLO target detection framework which is named the YOLO-FL apple flower detection model.The model enhances the feature extraction capability by optimizing the Backbone part with EC3DFM structure,while introducing MFEM structure in the Neck part to improve the feature fusion effect.In addition,the ABRLoss loss function is used to optimize the prediction results of the prediction frame,and it also adds the SimAM attention mechanism to the middle two detection heads in the Neck part,which further improves the detection performance of the model.The experimental results respectively show that YOLO-FL achieves 74.63%,73.82%,and 79.97%accuracy,recall,and mean average precision on the test set,which shows significant improvement over the benchmark model.Meanwhile,the model size was only 4693 kB,demonstrating high efficiency and storage advantages.After deploying the YOLO-FL model to the intelligent flower thinning robot,the frame rate of the test image was 40.7 FPS,the average missed detection rate was 7.26%,the false detection rate was 6.89%,and the model was able to efficiently complete the apple flower detection in the complex orchard environment.This study provides an effective solution and technical support for the application of image recognition technology in intelligent flower thinning robots.
基金This study was supported by the Fruit Industry Innovation Team Project of the Modern Agricultural Industry Technology System of Shandong Province(SDAIT-06-12)the“Double First-class”Award and subsidy fund project of Shandong Agricultural University(SYL2017X).
文摘In order to realize the intelligent identification of maize leaf diseases for accurate prevention and control,this study proposed a maize disease detection method based on improved MobileNet V3-small,using a UAV to collect maize disease images and establish a maize disease dataset in a complex context,and explored the effects of data expansion and migration learning on model recognition accuracy,recall rate,and F1-score instructive evaluative indexes,and the results show that the two approaches of data expansion and migration learning effectively improved the accuracy of the model.The structured compression of MobileNet V3-small bneck layer retains only 6 layers,the expansion multiplier of each layer was redesigned,32-fold fast downsampling was used in the first layer,and the location of the SE module was optimized.The improved model had an average accuracy of 79.52%in the test set,a recall of 77.91%,an F1-score of 78.62%,a model size of 2.36 MB,and a single image detection speed of 9.02 ms.The detection accuracy and speed of the model can meet the requirements of mobile or embedded devices.This study provides technical support for realizing the intelligent detection of maize leaf diseases.
