为了提高脑电情绪识别分类精度,最大限度利用脑电信号的空间和时间信息,提出一种Inception残差注意力卷积神经网络与双向长短期记忆(bi-directional long short-term memory, BiLSTM)网络相结合的新型架构时空Inception残差注意力网络...为了提高脑电情绪识别分类精度,最大限度利用脑电信号的空间和时间信息,提出一种Inception残差注意力卷积神经网络与双向长短期记忆(bi-directional long short-term memory, BiLSTM)网络相结合的新型架构时空Inception残差注意力网络。将脑电信号采集电极位置映射到二维矩阵中,采集信号作为通道,构成三维数据;将得到的三维数据输入到时空Inception残差注意力卷积网络之中,提取时空信息;将得到的特征输入到全连接层进行分类;将Inception结构引入脑电情绪识别领域,实现多尺度特征提取,并将电极映射到矩阵之中,保留电极位置信息,使用时空Inception残差注意力网络从时空两个维度获取脑电相关信息。实验表明,使用该模型对DEAP数据集进行情绪四分类可得到93.71%的准确度,相较于对比模型,识别精度提高了10%~20%。提出的模型在脑电信号情绪识别领域具有优良性能。展开更多
为更准确鉴别藏柴胡、锥叶柴胡和北柴胡,本文首先对柴胡样本进行太赫兹光谱测定,然后用含Inception块的残差网络对光谱数据进行识别.本文方法将Inception块中的卷积核收缩成一维,通过一维Inception块堆叠及残差连接来构建残差网络的主...为更准确鉴别藏柴胡、锥叶柴胡和北柴胡,本文首先对柴胡样本进行太赫兹光谱测定,然后用含Inception块的残差网络对光谱数据进行识别.本文方法将Inception块中的卷积核收缩成一维,通过一维Inception块堆叠及残差连接来构建残差网络的主干部分.主干部分后面依次是全局平均池化(Global Average Pooling,GAP)层、全连接(Full Connection,FC)层和Softmax层,其中,网络的主干部分用于对输入的太赫兹光谱数据进行多尺度特征提取,GAP层用于汇聚多尺度特征,FC层和Softmax层用于实现最后的分类.本文算法与9种传统模式识别算法进行了对比实验.结果表明,本文算法鉴别精度达88.99%,优于9种传统模式识别算法.本文算法为北柴胡的鉴别提供了新的解决方案.展开更多
Medical images are a critical component of the diagnostic process for clinicians.Although the quality of medical photographs is essential to the accuracy of a physician’s diagnosis,they must be encrypted due to the c...Medical images are a critical component of the diagnostic process for clinicians.Although the quality of medical photographs is essential to the accuracy of a physician’s diagnosis,they must be encrypted due to the characteristics of digital storage and information leakage associated with medical images.Traditional watermark embedding algorithm embeds the watermark information into the medical image,which reduces the quality of the medical image and affects the physicians’judgment of patient diagnosis.In addition,watermarks in this method have weak robustness under high-intensity geometric attacks when the medical image is attacked and the watermarks are destroyed.This paper proposes a novel watermarking algorithm using the convolutional neural networks(CNN)Inception V3 and the discrete cosine transform(DCT)to address above mentioned problems.First,the medical image is input into the Inception V3 network,which has been structured by adjusting parameters,such as the size of the convolution kernels and the typical architecture of the convolution modules.Second,the coefficients extracted from the fully connected layer of the network are transformed by DCT to obtain the feature vector of the medical image.At last,the watermarks are encrypted using the logistic map system and hash function,and the keys are stored by a third party.The encrypted watermarks and the original image features are performed logical operations to realize the embedding of zero-watermark.In the experimental section,multiple watermarking schemes using three different types of watermarks were implemented to verify the effectiveness of the three proposed algorithms.Our NC values for all the images are more than 90%accurate which shows the robustness of the algorithm.Extensive experimental results demonstrate the robustness under both conventional and high-intensity geometric attacks of the proposed algorithm.展开更多
Medical image classification has played an important role in the medical field, and the related method based on deep learning has become an important and powerful technique in medical image classification. In this art...Medical image classification has played an important role in the medical field, and the related method based on deep learning has become an important and powerful technique in medical image classification. In this article, we propose a simplified inception module based Hadamard attention (SI + HA) mechanism for medical image classification. Specifically, we propose a new attention mechanism: Hadamard attention mechanism. It improves the accuracy of medical image classification without greatly increasing the complexity of the model. Meanwhile, we adopt a simplified inception module to improve the utilization of parameters. We use two medical image datasets to prove the superiority of our proposed method. In the BreakHis dataset, the AUCs of our method can reach 98.74%, 98.38%, 98.61% and 97.67% under the magnification factors of 40×, 100×, 200× and 400×, respectively. The accuracies can reach 95.67%, 94.17%, 94.53% and 94.12% under the magnification factors of 40×, 100×, 200× and 400×, respectively. In the KIMIA Path 960 dataset, the AUCs and accuracy of our method can reach 99.91% and 99.03%. It is superior to the currently popular methods and can significantly improve the effectiveness of medical image classification.展开更多
Medical image super-resolution is a fundamental challenge due to absorption and scattering in tissues.These challenges are increasing the interest in the quality of medical images.Recent research has proven that the r...Medical image super-resolution is a fundamental challenge due to absorption and scattering in tissues.These challenges are increasing the interest in the quality of medical images.Recent research has proven that the rapid progress in convolutional neural networks(CNNs)has achieved superior performance in the area of medical image super-resolution.However,the traditional CNN approaches use interpolation techniques as a preprocessing stage to enlarge low-resolution magnetic resonance(MR)images,adding extra noise in the models and more memory consumption.Furthermore,conventional deep CNN approaches used layers in series-wise connection to create the deeper mode,because this later end layer cannot receive complete information and work as a dead layer.In this paper,we propose Inception-ResNet-based Network for MRI Image Super-Resolution known as IRMRIS.In our proposed approach,a bicubic interpolation is replaced with a deconvolution layer to learn the upsampling filters.Furthermore,a residual skip connection with the Inception block is used to reconstruct a high-resolution output image from a low-quality input image.Quantitative and qualitative evaluations of the proposed method are supported through extensive experiments in reconstructing sharper and clean texture details as compared to the state-of-the-art methods.展开更多
文摘为了提高脑电情绪识别分类精度,最大限度利用脑电信号的空间和时间信息,提出一种Inception残差注意力卷积神经网络与双向长短期记忆(bi-directional long short-term memory, BiLSTM)网络相结合的新型架构时空Inception残差注意力网络。将脑电信号采集电极位置映射到二维矩阵中,采集信号作为通道,构成三维数据;将得到的三维数据输入到时空Inception残差注意力卷积网络之中,提取时空信息;将得到的特征输入到全连接层进行分类;将Inception结构引入脑电情绪识别领域,实现多尺度特征提取,并将电极映射到矩阵之中,保留电极位置信息,使用时空Inception残差注意力网络从时空两个维度获取脑电相关信息。实验表明,使用该模型对DEAP数据集进行情绪四分类可得到93.71%的准确度,相较于对比模型,识别精度提高了10%~20%。提出的模型在脑电信号情绪识别领域具有优良性能。
文摘为更准确鉴别藏柴胡、锥叶柴胡和北柴胡,本文首先对柴胡样本进行太赫兹光谱测定,然后用含Inception块的残差网络对光谱数据进行识别.本文方法将Inception块中的卷积核收缩成一维,通过一维Inception块堆叠及残差连接来构建残差网络的主干部分.主干部分后面依次是全局平均池化(Global Average Pooling,GAP)层、全连接(Full Connection,FC)层和Softmax层,其中,网络的主干部分用于对输入的太赫兹光谱数据进行多尺度特征提取,GAP层用于汇聚多尺度特征,FC层和Softmax层用于实现最后的分类.本文算法与9种传统模式识别算法进行了对比实验.结果表明,本文算法鉴别精度达88.99%,优于9种传统模式识别算法.本文算法为北柴胡的鉴别提供了新的解决方案.
基金supported in part by Key Research Project of Hainan Province under Grant ZDYF2021SHFZ093the Natural Science Foundation of China under Grants 62063004 and 62162022+2 种基金the Hainan Provincial Natural Science Foundation of China under Grants 2019RC018,521QN206 and 619QN249the Major Scientific Project of Zhejiang Lab 2020ND8AD01the Scientific Research Foundation for Hainan University(No.KYQD(ZR)-21013).
文摘Medical images are a critical component of the diagnostic process for clinicians.Although the quality of medical photographs is essential to the accuracy of a physician’s diagnosis,they must be encrypted due to the characteristics of digital storage and information leakage associated with medical images.Traditional watermark embedding algorithm embeds the watermark information into the medical image,which reduces the quality of the medical image and affects the physicians’judgment of patient diagnosis.In addition,watermarks in this method have weak robustness under high-intensity geometric attacks when the medical image is attacked and the watermarks are destroyed.This paper proposes a novel watermarking algorithm using the convolutional neural networks(CNN)Inception V3 and the discrete cosine transform(DCT)to address above mentioned problems.First,the medical image is input into the Inception V3 network,which has been structured by adjusting parameters,such as the size of the convolution kernels and the typical architecture of the convolution modules.Second,the coefficients extracted from the fully connected layer of the network are transformed by DCT to obtain the feature vector of the medical image.At last,the watermarks are encrypted using the logistic map system and hash function,and the keys are stored by a third party.The encrypted watermarks and the original image features are performed logical operations to realize the embedding of zero-watermark.In the experimental section,multiple watermarking schemes using three different types of watermarks were implemented to verify the effectiveness of the three proposed algorithms.Our NC values for all the images are more than 90%accurate which shows the robustness of the algorithm.Extensive experimental results demonstrate the robustness under both conventional and high-intensity geometric attacks of the proposed algorithm.
文摘Medical image classification has played an important role in the medical field, and the related method based on deep learning has become an important and powerful technique in medical image classification. In this article, we propose a simplified inception module based Hadamard attention (SI + HA) mechanism for medical image classification. Specifically, we propose a new attention mechanism: Hadamard attention mechanism. It improves the accuracy of medical image classification without greatly increasing the complexity of the model. Meanwhile, we adopt a simplified inception module to improve the utilization of parameters. We use two medical image datasets to prove the superiority of our proposed method. In the BreakHis dataset, the AUCs of our method can reach 98.74%, 98.38%, 98.61% and 97.67% under the magnification factors of 40×, 100×, 200× and 400×, respectively. The accuracies can reach 95.67%, 94.17%, 94.53% and 94.12% under the magnification factors of 40×, 100×, 200× and 400×, respectively. In the KIMIA Path 960 dataset, the AUCs and accuracy of our method can reach 99.91% and 99.03%. It is superior to the currently popular methods and can significantly improve the effectiveness of medical image classification.
基金supported by Balochistan University of Engineering and Technology,Khuzdar,Balochistan,Pakistan.
文摘Medical image super-resolution is a fundamental challenge due to absorption and scattering in tissues.These challenges are increasing the interest in the quality of medical images.Recent research has proven that the rapid progress in convolutional neural networks(CNNs)has achieved superior performance in the area of medical image super-resolution.However,the traditional CNN approaches use interpolation techniques as a preprocessing stage to enlarge low-resolution magnetic resonance(MR)images,adding extra noise in the models and more memory consumption.Furthermore,conventional deep CNN approaches used layers in series-wise connection to create the deeper mode,because this later end layer cannot receive complete information and work as a dead layer.In this paper,we propose Inception-ResNet-based Network for MRI Image Super-Resolution known as IRMRIS.In our proposed approach,a bicubic interpolation is replaced with a deconvolution layer to learn the upsampling filters.Furthermore,a residual skip connection with the Inception block is used to reconstruct a high-resolution output image from a low-quality input image.Quantitative and qualitative evaluations of the proposed method are supported through extensive experiments in reconstructing sharper and clean texture details as compared to the state-of-the-art methods.
