Diagnostic Classification of Lung Cancer Using Deep Transfer Learning Technology and Multi-Omics Data

In recent years,with the increasing application of highthroughput sequencing technology,researchers have obtained and accumulated a large amount of multi-omics ...     

采用深度学习的多方位角SAR图像目标识别研究

合成孔径雷达（Synthetic Aperture Radar,SAR）在对地面目标进行观测时,可以在多个不同的方位角获取到目标的SAR图像,但这些图像中目标的形态各不相同。考虑到SAR图像对观测方位角极其敏感和SAR图像数据规模小这两个因素,本文设计了一个利用多方位角SAR图像进行目标识别的卷积神经网络（Convolutional Neural Network,CNN）,同一目标的3幅SAR图像被当作一幅伪彩色图像输入到网络中,充分利用了SAR图像数据的获取特点,同时用池化层替代了展平操作,降低了网络参数数量。实验结果表明,即便在小规模SAR数据集上,该卷积网络具有识别精度高的特点,对同类别不同型号的目标也具有出色的识别表现。      

Incident and Problem Ticket Clustering and Classification Using Deep Learning

A holistic analysis of problem and incident tickets in a real production cloud service environment is presented in this paper.By extracting different bags of words,we use principal component analysis(PCA) to examine the clustering characteristics of these tickets.Then K-means and latent Dirichlet allocation(LDA) are applied to show the potential clusters within this Cloud environment.The second part of our study uses a pre-trained bidirectional encoder representation from transformers(BERT) mode...     

Computerized Tomography Using Video Recorded Fluoroscopic Images

In this paper we investigate the possibility of constructing computerized tomograms using data collected from a fluoroscopic system. It is shown that through proper handling of these data, useful images can be obtained. The system offers the advantages of eliminating the need for a highly stabilized, linear translating mechanism, and also of requiring relatively low patient dosage. In addition, the data gathering can be done in essentially real time.     

Terahertz Computed Tomography Using A Continuous-Wave Gas Laser

A 3D continuous-wave (CW) terahertz computed tomography (CT) system employing a gas laser operating at 2.52 THz is presented. To shorten acquisition time on the premise of guaranteeing the image quality, the modified simultaneous algebraic reconstruction technique (MSART) coupled with image processing operations like the Gaussian low-pass filter (GLPF), open operation and close operation has been adopted in the paper. With the 2D results the 3D images of the samples have been also obtained. The reconstruction results illustrate the promising application prospects of this CW THz CT system.     

Multidimensional Characterization of the Perceptual Quality of Noise-Reduced Computed Tomography Images

Judging the perceptual quality of processed images is a cognitive process in which the perception of image attributes such as sharpness and noisiness plays an important role. In this paper, we use multidimensional scaling to study the perceptual factors that influence the quality impression of Computed Tomography (CT) images processed by a noise-reduction technique. We also characterize intersubject differences in the assessment of image attributes. We show that multidimensional scaling can be used reliably for the characterization of the subjective performance of image-processing algorithms. Evaluations using human subjects, such as the ones presented in this paper, will continue to play an important role, since objective measures for perceptual image quality, with proven validity in a broad range of applications, are not expected in the near future.     

Classifying Lung Cancer as Benign and Malignant Nodule Using ANN of Back-Propagation Algorithm and GLCM Feature Extraction on Chest X-Ray Images

Lung cancer is the most suffering disease which is very difficult to identify in advance and it is not easily cure if the stage of cancer becomes more malignant, the lung cancer is similar like other cancers such as breast cancer, colorectal cancer, brain tumour etc. Now-a-days, there are lot of technologies are developed to predict and treating the diseases, but still have some trouble in detecting the cancer nodule more accurately. Due to increasing in number of patients admitted in clinic, hospitals, etc., doctors cannot able to monitor every patient with high care and they failed to guide their patients with greater attention. Accordingly, the radiologists require a technology named Computer Aided Design (CAD) system for precise recognition and classification of lung nodule where the detected node is cancerous or non-cancerous. In the proposed research, the Chest X-Ray (CXR) images are used as an input image for experimenting the research and image processing techniques has been used to classify the nodule as benign or malignant and executed with greater accuracy in prediction and classification level. In this proposed research work, features were extracted from hasil segmentation image by using Grey Level Co- occurrence Matrix (GLCM) method. The extracted features from image are taken as input data and processed with Artificial Neural Network (ANN) Classifier. The classification and training has been done by Artificial Neural Network with back propagation (ANN-BP) method; therefore, the Artificial Neural Network has competitive and greater in executing the results by comparing with the existing methods of Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM). Therefore, the performance evaluation of Artificial Neural Network has less training time with better accuracy of 87.5%, sensitivity of 97.75% and specificity of 89.75% by classifying the detected nodule as benign or malignant.

     

Classification of Breast Abnormalities Using a Deep Convolutional Neural Network and Transfer Learning

Journal of Communications Technology and Electronics - A new algorithm for classification of breast pathologies in digital mammography using a convolutional neural network and transfer learning is...     

图像分类问题的几种深度学习策略

针对图像分类学习不够深入的问题,提出图像分类问题的几种深度学习策略研究。通过分析当前主流的主动深度学习图像、多标签图像和多尺度网络图像三种深度学习方法的工作原理和存在的优势与不足,探讨图像分类问题的优化学习策略。随后采用图像分类问题的几种深度学习策略实验的方式加以对比,实验结果表明,参数共享的深度学习图像分类方法不仅提高了预测速度,而且还能确保模型的准确性。     

Spectrum Sensing Based on Deep Learning Classification for Cognitive Radios

Spectrum sensing is a key technology for cognitive radios.We present spectrum sensing as a classification problem and propose a sensing method based on deep learning classification.We normalize the received signal power to overcome the effects of noise power uncertainty.We train the model with as many types of signals as possible as well as noise data to enable the trained network model to adapt to untrained new signals.We also use transfer learning strategies to improve the performance for real-world signals.Extensive experiments are conducted to evaluate the performance of this method.The simulation results show that the proposed method performs better than two traditional spectrum sensing methods,i.e.,maximum-minimum eigenvalue ratio-based method and frequency domain entropy-based method.In addition,the experimental results of the new untrained signal types show that our method can adapt to the detection of these new signals.Furthermore,the real-world signal detection experiment results show that the detection performance can be further improved by transfer learning.Finally,experiments under colored noise show that our proposed method has superior detection performance under colored noise,while the traditional methods have a significant performance degradation,which further validate the superiority of our method.     

Diagnosing COVID-19 from CT Image of Lung Segmentation & Classification with Deep Learning Based on Convolutional Neural Networks

Wireless Personal Communications - Real-time data transmission is one of the objectives of MANET (mobile ad-hoc network) to handle emergencies like a forest fire, flood, and earthquake. In this...     

一种基于FPGA的计算机层析重建的方法

提出一种基于FPGA的计算机层析重建的方法,即借助FPGA的高速数据处理能力来提高计算机层析重建的速度.采用自顶向下的方法,将FPGA依据功能划分为几个模块,并详细论述了各个模块的设计方法和控制流程.FPGA模块的设计采用VHDL语言编程和内部已有的小模块相结合的方法来实现,并利用时钟信号对模块内部以及模块之间运算和数据流程进行控制.整个软件设计和综合模拟仿真在Quartus ||开发平台中完成,同时也给出了一些模块仿真的波形.     

基于深度学习的SAR图像舰船目标检测综述

近年来,合成孔径雷达成像技术因具备全天时和全天候的目标感测能力,在海洋实时监测和管控等领域发挥着重要作用,特别是高分率SAR图像中的舰船目标检测成为当前的研究热点之一.首先分析基于深度学习的SAR图像舰船目标检测流程,并对样本训练数据集的构建、目标特征的提取和目标框选的设计等关键步骤进行归纳总结.然后对检测流程中的各部...     

Investigating the Effects of Transfer Learning on ROI-based Classification of Chest CT Images: A Case Study on Diffuse Lung Diseases

Research on Computer-Aided Diagnosis (CAD) of medical images has been actively conducted to support decisions of radiologists. Since deep learning has shown distinguished abilities in classification, detection, segmentation, etc. in various problems, many studies on CAD have been using deep learning. One of the reasons behind the success of deep learning is the availability of large application-specific annotated datasets. However, it is quite tough work for radiologists to annotate hundreds or thousands of medical images for deep learning, and thus it is difficult to obtain large scale annotated datasets for various organs and diseases. Therefore, many techniques that effectively train deep neural networks have been proposed, and one of the techniques is transfer learning. This paper focuses on transfer learning and especially conducts a case study on ROI-based opacity classification of diffuse lung diseases in chest CT images. The aim of this paper is to clarify what characteristics of the datasets for pre-training and what kinds of structures of deep neural networks for fine-tuning contribute to enhance the effectiveness of transfer learning. In addition, the numbers of training data are set at various values and the effectiveness of transfer learning is evaluated. In the experiments, nine conditions of transfer learning and a method without transfer learning are compared to analyze the appropriate conditions. From the experimental results, it is clarified that the pre-training dataset with more (various) classes and the compact structure for fine-tuning show the best accuracy in this work.

     

基于半监督学习的SVM-Wishart极化SAR图像分类方法

该文针对极化SAR (Synthetic Aperture Radar)图像分类中的小样本问题,提出了一种新的半监督分类算法。考虑到极化SAR数据反映了地物的散射特性,该方法首先利用目标分解方法提取了多种极化散射特征;其次,在协同训练框架下结合SVM分类器构建了协同半监督模型,该模型可以同时利用有标记和无标记样本对极化SAR图像进行分类,从而在小样本时可以获得更好的分类精度;最后,为进一步改善分类结果,在协同训练分类完成后,该方法又利用Wishart分类器对分类结果进行修正。理论分析与实验表明,该算法在只有少量标记样本的情况下优于传统算法。      

基于深度学习的复杂背景图像分类方法研究

复杂背景图像受背景干扰后不易被识别。针对这一问题,文中提出了基于前景分割机制的卷积神经网络图像分类方法。采用全卷积神经网络对图像前景区域进行自动分割,通过图像中前景区域周围的最小边界框对其进行定位。对于定位的前景区域,构建卷积神经网络对其进行处理以区分不同的类别,从而实现复杂背景图像的分类。将提出方法在公开数据集中提取的单一背景和复杂背景图像数据集上进行对比实验,并使用迁移学习与数据增强等方法优化模型。实验结果表明,所提方法使用前景区域分割相比于仅分类CNN具有更高的准确度,且复杂背景图像上的准确度提升幅度要远大于单一背景图像。该结果说明引入前景区域分割对于复杂背景图像分类模型准确度的提升具有一定帮助,能够显著前景区域特征并减少背景因素的干扰。     

基于多模态深度学习的流量分类识别方法

针对流量分类效果与实际情况存在偏差的问题,首先将多模态深度学习运用在流量分类中,通过利用多模态之间的互补性,剔除模态间的冗余,从而学习到更好的流量数据特征表示.然后,提出了一种基于多模态流量数据的检测和分类方法,对同一流量单位的不同模态输入分别采用卷积神经网络(Convolutional Neural Networks...     

Towards Semi-supervised Classification of Abnormal Spectrum Signals Based on Deep Learning

In order to cope with the heavy labor cost challenge of the manual abnormal spectrum classification and improve the effectiveness of existing machine learning schemes for spectral datasets with interference-to-signal ratios,we proposes a semi-supervised classification of abnormal spectrum signals(SSC-ASS),aimed at addressing some of the challenges in abnormal spectrum signal(ASS)classification tasks.A significant advantage of SSC-ASS is that it does not require manual labeling of every abnormal data,but instead achieves high-precision classification of ASSs using only a small number of labeled data.Furthermore,the method can to some extent avoid the introduc-tion of erroneous information resulting from the complex and variable nature of abnormal signals,thereby improving classification accuracy.Specifically,SSC-ASS uses a memory AutoEncoder module to efficiently extract features from abnormal spectrum signals by learning from the reconstruction error.Additionally,SSC-ASS combines convolutional neural network and the K-means using a DeepCluster framework to fully utilize the unlabeled data.Furthermore,SSC-ASS also utilizes pre-training,category mean memory module and replaces pseudo-labels to further improve the classification accuracy of ASSs.And we verify the classification effectiveness of SSC-ASS on synthetic spectrum datasets and real on-air spectrum dataset.