Search

The aim of this study is designed an improved ResNet 50 network to achieve automatic classification model for pain expressions by elderly patients with hip fractures. This study built a dataset by combining the advantages of deep learning in image recognition, using a hybrid of the Multi-Task Cascaded Convolutional Neural Networks (MTCNN). Based on ResNet50 network framework utilized transfer learning to implement model function. This study performed the hyperparameters by Bayesian optimization in the learning process. This study calculated intraclass correlation between visual analog scale scores provided by clinicians independently and those provided by pain expression evaluation assistant(PEEA). The automatic pain expression recognition model in elderly patients with hip fractures, which constructed using the algorithm. The accuracy achieved 99.6% on the training set, 98.7% on the validation set, and 98.2% on the test set. The substantial kappa coefficient of 0.683 confirmed the efficacy of PEEA in clinic. This study demonstrates that the improved ResNet50 network can be used to construct an automatic pain expression recognition model for elderly patients with hip fractures, which has higher accuracy.

Purpose: To develop an algorithm using a residual base network guided by the confidence map and transfer learning for limited dataset size and imbalanced bladder wall segmentation. Methods: The geometric transformation was made to the training data for data augmentation, and a pre-trained Resnet50 model on ImageNet was also adopted for transfer learning. Three loss functions were put into the pre-trained Resnet50 network, they are the cross-entropy loss function (CELF), the generalized Dice loss function (GDLF) and the Tversky loss function (TLF). Three models were obtained through training, and three corresponding confidence maps were output after entering a new image. By selecting the point with the maximum confidence values at the corresponding position, we merged the three images into one figure, performed threshold filtering to avoid external anomalies, and finally obtained the segmentation result. Results: The average Jaccard similarity coefficient of model training based on the CELF, GDLF and TLF is 0.9173, 0.8355, 0.8757, respectively, and the average Jaccard similarity coefficient of our algorithm can be achieved at 0.9282. In contrast, the classical 2D U-Net algorithm can only achieve 0.518. We also qualitatively give the reasons for the improvement of model performance. Conclusion: Our study demonstrates that a confidence map-assisted residual base network can accurately segment bladder walls on a limited-size data set. Compared with the segmentation results of each model alone, our method originally improves the accuracy of the segmentation results by combining confidence map guidance with threshold filtering. [ABSTRACT FROM AUTHOR]

Picture book creation has a rich metaphorical connotation, which is becoming more and more popular along with the development of digitalization. In this paper, the textual metaphors of picture book creation are extracted by combining the textual feature extraction model of the BERT pre-training model and HAN network, the ResNet50 network extracts the illustration metaphors of picture book creation, and the extracted metaphorical features are multimodal fused and recognized with the help of fully connected layer. In addition, a picture book metaphor dataset was constructed, and after analyzing the basic features of picture book metaphors, the effect of the constructed multimodal metaphor recognition was explored, and the recognition and communication of metaphors in picture book creation was studied. The results showed that the recognition accuracy in picture book creation ranged from 0.67 to 0.77, and the high degree of metaphor recognition in picture book creation showed a positive correlation with the average response time of communication, with the regression equation RT=138.45*IdentificationStd+1045.The results of the analysis of the metaphorical picture book creation pictures with textual references showed that the degree of communication comprehension (M=22.38. Std.=3.68), communication liking (M=94.86, Std.=13.58) and reaction time (M=82.44s, Std.=14.15s). Picture books facilitate better interactive communication through their metaphorical expression.

Skin cancer, specifically melanoma, is a serious health issue that arises from the melanocytes, the cells that produce melanin, the pigment responsible for skin color. With skin cancer on the rise, the timely identification of skin lesions is crucial for effective treatment. However, the similarity between some skin lesions can result in misclassification, which is a significant problem. It is important to note that benign skin lesions are more prevalent than malignant ones, which can lead to overly cautious algorithms and incorrect results. As a solution, researchers are developing computer-assisted diagnostic tools to detect malignant tumors early. First, a new model based on the combination of "you only look once" (YOLOv5) and "ResNet50" is proposed for melanoma detection with its degree using humans against a machine with 10,000 training images (HAM10000). Second, feature maps integrate gradient change, which allows rapid inference, boosts precision, and reduces the number of hyperparameters in the model, making it smaller. Finally, the current YOLOv5 model is changed to obtain the desired outcomes by adding new classes for dermatoscopic images of typical lesions with pigmented skin. The proposed approach improves melanoma detection with a real-time speed of 0.4 MS of non-maximum suppression (NMS) per image. The performance metrics average is 99.0%, 98.6%, 98.8%, 99.5, 98.3%, and 98.7% for the precision, recall, dice similarity coefficient (DSC), accuracy, mean average precision (MAP) from 0.0 to 0.5, and MAP from 0.5 to 0.95, respectively. Compared to current melanoma detection approaches, the provided approach is more efficient in using deep features. [ABSTRACT FROM AUTHOR]

To solve the problem that the features of small targets in the image are difficult to extract and lead to missed detection, a small target detection method combining attention mechanism and feature fusion was proposed based on the single shot multi-box detector (SSD) model. Firstly, ResNet50 was used as the feature extraction backbone network to solve the problem of insufficient feature extraction capability caused by the gradient correlation decay of the original network. Then, an attention mechanism module was added to the low-level feature extraction layer information, the learning ability of low-level feature was improved. Finally, the low-level features and high-level semantic information were cascaded and fused to make full use of the correlation information between different feature maps. The experimental results show that the average detection accuracy of the improved model for small targets reaches 51.1%, which is 9.3% higher than that before the improvement. The improved model has higher detection accuracy for small targets.

Copyright of Acta Agriculturae Zhejiangensis is the property of Acta Agriculturae Zhejiangensis Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Xi'an Polytechnic University is the property of Editorial Department of Journal of Xi'an Polytechnic University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

With the massive success of deep networks, there have been significant efforts to analyze cancer diseases, especially skin cancer. For this purpose, this work investigates the capability of deep networks in diagnosing a variety of dermoscopic lesion images. This paper aims to develop and fine-tune a deep learning architecture to diagnose different skin cancer grades based on dermatoscopic images. Fine-tuning is a powerful method to obtain enhanced classification results by the customized pre-trained network. Regularization, batch normalization, and hyperparameter optimization are performed for fine-tuning the proposed deep network. The proposed fine-tuned ResNet50 model successfully classified 7-respective classes of dermoscopic lesions using the publicly available HAM10000 dataset. The developed deep model was compared against two powerful models, i.e., InceptionV3 and VGG16, using the Dice similarity coefficient (DSC) and the area under the curve (AUC). The evaluation results show that the proposed model achieved higher results than some recent and robust models. [ABSTRACT FROM AUTHOR]

In order to reduce the false alarm phenomenon of smoke detection caused by cloud and fog, a smoke detection method based on fusing multiple network models is proposed. On the basis of using VGG16 network to extract the detailed features of smoke, it is fused with the ResNet50 network feature extraction layer to extract more subtle features.The skip connection mechanism is used to transfer the image information to the deeper layer of the neural network, in order to avoid the loss of important features of smoke image and solve the under-fitting problem caused by the gradient disappearance. The training process adopts the feature transfer learning method based on isomorphic space to solve the small sample training problem, retrain in the new target detection field, better integrate the network model, rebuild the output detection structure of the whole connection layer, and adopt the random inactivation method to improve the generalization ability of the model. Experimental results show that, compared with the current popular deep convolutional network, this method has lower false alarm rate and higher accuracy and recall rate. [ABSTRACT FROM AUTHOR]