检索结果-内蒙古大学图书馆

3rd International Conference on Bio-engineering for Smart Technologies (BioSMART)

作者： Daoud, Mohammad I. Saleh, Amro Hababeh, Ismail Alazrai, Rami German Jordanian Univ Sch Elect Engn & Informat Technol Amman Jordan

ISBN: (纸本)9781728135786

Ultrasound imaging is one of the most widely used medical imaging modalities for detecting breast cancer. However, the accuracy of diagnosing the tumors in breast ultrasound (BUS) images might vary based on the experience level of the radiologist. Content-based image retrieval (CBIR) systems can be employed to improve the diagnosis accuracy by providing the radiologist with BUS images of previous, clinically relevant cases. In this study, a CBIR system is developed based on deep learning technology to support the diagnosis of BUS images. In particular, each query BUS image submitted to the system is analyzed using a custom-made convolutional autoencoder (CAE) to extract a latent features vector that represents the image. An important advantage of the proposed CAE is its ability to extract the latent features vector without the need to localize or outline the tumor. The latent features vector of the query image is analyzed using a similarity measure to identify and retrieve the most relevant BUS images from a reference BUS image database. Finally, the retrieved BUS images are displayed to the radiologist. The performance of the proposed CBIR system has been evaluated using a set of BUS images that includes benign and malignant breast tumors. The results reported in this study suggest the feasibility of employing the proposed CBIR system to improve the diagnosis of BUS images.

关键词： Ultrasound imaging breast cancer content-based image retrieval convolutional autoencoder

来源：评论

学校读者我要写书评

暂无评论

A snapshot neural ensemble method for cancer-type prediction based on copy number variations

引用

NEURAL COMPUTING & APPLICATIONS 2020年第19期32卷 15281-15299页

作者： Karim, Md Rezaul Rahman, Ashiqur Jares, Joao Bosco Decker, Stefan Beyan, Oya Fraunhofer Inst Appl Informat Technol FIT St Augustin Germany Rhein Westfal TH Aachen Aachen Germany

An accurate diagnosis and prognosis for cancer are specific to patients with particular cancer types and molecular traits, which needs to address carefully. The discovery of important biomarkers is becoming an important step toward understanding the molecular mechanisms of carcinogenesis in which genomics data and clinical outcomes need to be analyzed before making any clinical decision. Copy number variations (CNVs) are found to be associated with the risk of individual cancers and hence can be used to reveal genetic predispositions before cancer develops. In this paper, we collect the CNVs data about 8000 cancer patients covering 14 different cancer types from The Cancer Genome Atlas. Then, two different sparse representations of CNVs based on 578 oncogenes and 20,308 protein-coding genes, including genomic deletions and duplication across the samples, are prepared. Then, we train Conv-LSTM and convolutional autoencoder (CAE) networks using both representations and create snapshot models. While the Conv-LSTM can capture locally and globally important features, CAE can utilize unsupervised pretraining to initialize the weights in the subsequent convolutional layers against the sparsity. Model averaging ensemble (MAE) is then applied to combine the snapshot models in order to make a single prediction. Finally, we identify most significant CNVs biomarkers using guided-gradient class activation map plus (GradCAM++) and rank top genes for different cancer types. Results covering several experiments show fairly high prediction accuracies for the majority of cancer types. In particular, using protein-coding genes, Conv-LSTM and CAE networks can predict cancer types correctly at least 72.96% and 76.77% of the cases, respectively. Contrarily, using oncogenes gives moderately higher accuracies of 74.25% and 78.32%, whereas the snapshot model based on MAE shows overall 2.5% of accuracy improvement.

关键词： Cancer prediction Copy number variation Conv-LSTM network convolutional autoencoder Interpretability Snapshot ensemble

来源：评论

学校读者我要写书评

暂无评论

A robust hybrid digital watermarking technique against a powerful CNN-based adversarial attack

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2020年第43-44期79卷 32769-32790页

作者： Sharma, Sai Shyam Chandrasekaran, V Sri Sathya Sai Inst Higher Learning Anantapur Andhra Pradesh India

Digital watermarking techniques are valuable tools to embed digital signatures on multimedia content to establish the legal ownership and authenticity claims by the owners. Firstly this paper investigates the robustness of popular transform domain-based digital image watermarking schemes such as DCT, SVD, DWT, and their hybrid combinations against known image processing type attacks such as image blurring, compression, noise addition, rotation and cropping. Then, an enhanced hybrid scheme using DWT and SVD methods is proposed and its improved performance is demonstrated in terms of the quality of the extracted watermarks measured in terms of PSNR, SSIM and NCC values. This paper then proposes a novel adversarial attack based on a powerful Deep convolutional Neural Network based autoencoder(CAE) scheme. The CAE is specifically chosen to exploit its intrinsic capability to represent the image content (spatial and structural) through lower dimensional projections in the intermediate layers. The CAE is trained and tested on the entire image repository of the CIFAR10 data set. Once CAE is trained on a class of images and the parameters are frozen, it will serve as a system to produce a perceptually close image for any unseen input image belonging to the same class. The power of the proposed adversarial attack scheme is shown in terms of the quality of extracted watermarks against popular water mark embedding schemes. Finally the proposed enhanced hybrid strategy of DWT+SVD is shown to be robust against the new form of attack and outperforms all other techniques measured in terms of its high quality watermark extraction.

关键词： Digital watermarking convolutional autoencoder Copyright protection Adversarial attacks Hybrid transforms

来源：评论

学校读者我要写书评

暂无评论

A Learning-Based Framework for Identifying MicroRNA Regulatory Module

引用

INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS 2020年第1期13卷 1598-1607页

作者： Yang, Yi Hunan Womens Univ Coll Informat Sci & Engn 160 Zhongyi First Rd Changsha 410004 Peoples R China

Accurate identification of microRNA regulatory modules can give insights to understand microRNA synergistical regulatory mechanism. However, the identification accuracy suffers from incomplete biological data. In this paper, we proposed a learning based framework called MicroRNA regulatory module dentification with convolutional autoencoders (MICA). Firstly, the framework applied convolutional autoencoders to extract significant features of microRNA and their target-genes. Then they were clustered into microRNA clusters and target-gene clusters. Finally, the two types of clusters were combined into modules by known microRNA-target interactions. Compared with three existing methods on three cancer data sets, the modules detected by the proposed method exhibited better overall performance. (C) 2020 The Authors. Published by Atlantis Press B.V.

关键词： MicroRNA regulatory module convolutional autoencoder K-means MicroRNA-target interaction

来源：评论

学校读者我要写书评

暂无评论

Identification of MicroRNA Regulatory Modules by Clustering MicroRNA-Target Interactions

引用

IEEE ACCESS 2020年 8卷 154133-154142页

作者： Yang, Yi Wan, Xuting Hunan Womens Univ Coll Informat Sci & Engn Changsha 410004 Peoples R China

Identification of microRNA regulatory modules can help decipher microRNA synergistic regulatory mechanism in the development and progression of complex diseases, especially cancers. Experimentally validated microRNA-target interactions provide strong direct evidence for the analysis of microRNA regulatory functions. We here developed a novel computational framework named CMIN to identify microRNA regulatory modules by performing link clustering on such experimentally verified microRNA-target interactions. CMIN runs in two main steps: it first utilizes convolutional autoencoders to extract high-level microRNA-target interaction features from the expression profile data, and then applied affinity propagation clustering algorithm to interaction feature to obtain overlapping microRNA-target clusters. Clusters with significant synergy correlations are considered as microRNA regulatory modules. We tested the proposed framework and other three existing methods on three types of cancer data sets from TCGA (The Cancer Genome Atlas). The results showed that the microRNA regulatory modules detected by CMIN exhibit stronger topological correlation and more functional enrichment compared with other methods. Availability: The supplementary files of CMIN are available at https://***/snryou/CMIN.

关键词： MicroRNA regulatory module MicroRNA-target interaction convolutional autoencoder affinity propagation link clustering

来源：评论

学校读者我要写书评

暂无评论

Improving model robustness for soybean iron deficiency chlorosis rating by unsupervised pre-training on unmanned aircraft system derived images

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2020年 175卷 105557-105557页

作者： Li, Jiating Oswald, Cody Graef, George L. Shi, Yeyin Univ Nebraska Dept Biol Syst Engn Lincoln NE 68583 USA Univ Nebraska Dept Agron & Hort Lincoln NE 68583 USA

Iron deficiency chlorosis (IDC) is a major yield-limiting factor for soybean production in the mid-western USA. The most practical solution in mitigating losses due to IDC is the development and characterization of IDC tolerant varieties. Leveraging the advanced technique of unmanned aircraft system (UAS) and the thriving deep learning methodology, a convolutional neural network (CNN) could be trained to assist breeders with IDC resistance selection. However, a known difficulty in IDC screening is that the symptoms often vary across diverse genetic backgrounds and spatial or temporal soil heterogeneities. A robust CNN model is desired to mitigate such difficulty. While high robustness usually relies on a sufficiently large labeled training data, the available labeled samples in most breeding programs are normally not enough. Under this limitation, it is critical to find an alternative way to train a robust model. The solution proposed in this study was to apply unsupervised pretraining on the unlabeled aerial images that are much easier to obtain by the UAS. Specifically, a convolutional autoencoder (CAE) was pre-trained on unlabeled sub-images clipped from aerial RGB images;then, the pretrained weights were reused to initialize the CNN model that was trained on labeled plot-wise sub-images clipped from stitched RGB maps. To WA the robustness of this CAE initialized model (CAE1 -CNN), two baseline models were equally trained: the first was CAE2-CNN, where the CAE2 was pre-trained with three times of unlabeled data as that of CAE1, by adding wniter wheat and sorghum aerial images;the second was Ran-CNN where the CNN was randomly initialized. Three conditions were considered for testing model robustness: different soybean trials, field locations and vegetative growth stages. Results revealed that both the CAE1-CNN and the CAE2-CNN had relatively better robustness than the Ran-CNN model, i.e., higher R-2 and lower RMSE values, especially on different soybean trials and

关键词： Plant stress phenotyping Remote sensing convolutional neural network convolutional autoencoder Unlabeled data

来源：评论

学校读者我要写书评

暂无评论

Unsupervised noise-robust feature extraction for aerial image classification

引用

Science China(Technological Sciences) 2020年第8期63卷 1406-1415页

作者： LIANG Ye LU Shuai WENG Rui HAN ChengZhe LIU Ming School of Astronautics Harbin Institute of TechnologyHarbin 150001China Academy of Art Harbin University of Science and TechnologyHarbin 150001China Academy of Software and Microelectronics Harbin University of Science and TechnologyHarbin 150001China

The rich data provided by satellites and unmanned aerial vehicles bring opportunities to directly model aerial image features by extracting their spatial and structural *** convolutional autoencoders(CAEs)have been attained a remarkable performance in ideal aerial image feature extraction,they are still challenging to extract information from noisy images which are generated from capture and *** this paper,a novel CAE-based noise-robust unsupervised learning method is proposed for extracting high-level features accurately from aerial images and mitigating the effect of *** from conventional CAEs,the proposed method introduces the noise-robust module between the encoder and the ***,several pooling layers in CAEs are replaced by convolutional layers with stride=*** performance of feature extraction is evaluated by the prediction accuracy and the accuracy loss in image classification experiments.A 5-classes aerial optical scene and a 9-classes hyperspectral image(HSI)data set are utilized for optical image and HSI feature extraction,*** features extracted from aerial images are utilized for image classification by a linear support vector machine(SVM)*** results indicate that the proposed method improves the classification accuracy for noisy images(Gaussian noise 2Dσ=0.1,3Dσ=60)in both optical images(2D 87.5%)and HSIs(3D 85.6%)compared with the traditional CAE(2D 78.6%,3D 84.2%).The accuracy loss in classification experiments increases with the increment of *** with the traditional CAE(2D 15.7%,3D 11.8%),the proposed method shows the lower classification accuracy loss in experiments(2D 0.3%,3D 6.3%).The proposed unsupervised noise-robust feature extraction method attains desirable classification accuracy in ideal input and enhances the feature extraction capability from noisy input.

关键词： aerial image classification convolutional autoencoder feature extraction noise-robust

来源：评论

学校读者我要写书评

暂无评论

Kick: Shift-N-Overlap Cascades of Transposed convolutional Layer for Better Autoencoding Reconstruction on Remote Sensing Imagery

引用

IEEE ACCESS 2020年 8卷 107244-107259页

作者： Hong, Seungkyun Song, Sa-Kwang Korea Univ Sci & Technol UST Dept Data & HPC Sci Daejeon 34113 South Korea Korea Inst Sci & Technol Informat KISTI Res Data Sharing Ctr Daejeon 34141 South Korea

A convolutional autoencoder is an essential deep neural model architecture for understanding and predicting large-scale and widespread multi-dimensional information such as remote sensing imagery. To training a convolutional autoencoder, an automatic image reconstruction from input data and evaluation is repeatedly performed to achieve optimal reconstruction performance. Checkerboard artifacts, which are frequently produced on output images and lead to degraded image quality, are a significant issue during image reconstruction using a convolutional autoencoder. To remedy this coarse visual saliency issue during model training, we propose the & x2018;Kick& x2019;deconvolutional layer - a cascaded transposed convolutional layer with pixel shifting and overlapping for checkerboard pattern smoothing. By using pixel-shifted identity convolutional layers, we improved image reconstruction performance using fewer trainable decoder parameters than previously suggested models without losing reconstruction capability. Moreover, our proposed layer can be used with any type of convolutional autoencoder, including typical convolutional autoencoders and adversarial autoencoders. To evaluate an image reconstruction performance of our suggested deconvolutional layer, we used a dataset containing 12 years of geostationary satellite observation data of East Asia.

关键词： Meteorology Tensors Image reconstruction Visualization Decoding Computational modeling Convolution Deconvolutional layer convolutional autoencoder adversarial autoencoder image reconstruction checkerboard artifact satellite observation

来源：评论

学校读者我要写书评

暂无评论

A Two Consequent Multi-layers Deep Discriminative Approach for Classifying fMRI Images

引用

INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS 2020年第6期29卷

作者： Mahmoud, Abeer M. Karamti, Hanen Alrowais, Fadwa Ain Shams Univ Fac Comp & Informat Sci Comp Sci Dept Cairo Egypt Princess Nourah Bint Abdulrahman Univ Coll Comp & Informat Sci Comp Sci Dept POB 84428 Riyadh Saudi Arabia Univ Sfax ISIMS MIRACL Lab BP 242 Sfax 3021 Tunisia

Functional Magnetic Resonance Imaging (fMRI), for many decades acts as a potential aiding method for diagnosing medical problems. Several successful machine learning algorithms have been proposed in literature to extract valuable knowledge from fMRI. One of these algorithms is the convolutional neural network (CNN) that competent with high capabilities for learning optimal abstractions of fMRI. This is because the CNN learns features similarly to human brain where it preserves local structure and avoids distortion of the global feature space. Focusing on the achievements of using the CNN for the fMRI, and accordingly, the Deep convolutional Auto-Encoder (DCAE) benefits from the datadriven approach with CNN's optimal features to strengthen the fMRI classification. In this paper, a new two consequent multi-layers DCAE deep discriminative approach for classifying fMRI Images is proposed. The first DCAE is unsupervised sub-model that is composed of four CNN. It focuses on learning weights to utilize discriminative characteristics of the extracted features for robust reconstruction of fMRI with lower dimensional considering tiny details and refining by its deep multiple layers. Then the second DCAE is a supervised sub-model that focuses on training labels to reach an outperformed results. The proposed approach proved its effectiveness and improved literately reported results on a large brain disorder fMRI dataset.

关键词： Deep learning CNN convolutional autoencoder fMRI ASD

来源：评论

学校读者我要写书评

暂无评论

Perceptual autoencoder for Compressive Sensing Image Reconstruction

引用

INFORMATICA 2020年第3期31卷 561-578页

作者： Ralasic, Ivan Sersic, Damir Segvic, Sinisa Univ Zagreb Fac Elect Engn & Comp Unska 3 HR-10000 Zagreb Croatia

This paper presents a non-iterative deep learning approach to compressive sensing (CS) image reconstruction using a convolutional autoencoder and a residual learning network. An efficient measurement design is proposed in order to enable training of the compressive sensing models on normalized and mean-centred measurements, along with a practical network initialization method based on principal component analysis (PCA). Finally, perceptual residual learning is proposed in order to obtain semantically informative image reconstructions along with high pixel-wise reconstruction accuracy at low measurement rates.

关键词： compressive sensing convolutional autoencoder deep learning image reconstruction perceptual loss principal component analysis

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：