基于卷积神经网络和循环神经网络的环形RNA剪接位点识别研究

本文提出了一种基于卷积神经网络和循环神经网络的深度学习模型,通过分析基因组序列数据,识别人基因组中环形RNA剪接位点.首先,根据预处理后的核苷酸序列,设计了2种网络深度、8种卷积核大小和3种长短期记忆(long short term memory,LSTM)参数,共8组16个模型;其次,进一步针对池化层进行均值池化和最大池化的测试,并加入GC含量提高模型的预测能力;最后,对已经实验验证过的人类精浆中环形RNA进行了预测.结果表明,卷积核尺寸为32×4、深度为1、LSTM参数为32的模型识别率最高,在训练集上为0.9824,在测试数据集上准确率为0.95,并且在实验验证数据上的正确识别率为83%.该模型在人的环形RNA剪接位点识别方面具有较好的性能.     

基于人工神经网络的昆虫鸣声识别

以常见的7种飞虱雄虫求偶鸣声信号的频率峰值作为输入向量,用人工神经网络来识别它们的鸣声,平均识别率达90．6％。人工神经网络可以用于昆虫鸣声识别。     

DeepMHADTA: Prediction of Drug-Target Binding Affinity Using Multi-Head Self-Attention and Convolutional Neural Network

Drug-target interactions provide insight into the drug-side effects and drug repositioning. However, wet-lab biochemical experiments are time-consuming and labor-intensive, and are insufficient to meet the pressing demand for drug research and development. With the rapid advancement of deep learning, computational methods are increasingly applied to screen drug-target interactions. Many methods consider this problem as a binary classification task (binding or not), but ignore the quantitative binding affinity. In this paper, we propose a new end-to-end deep learning method called DeepMHADTA, which uses the multi-head self-attention mechanism in a deep residual network to predict drug-target binding affinity. On two benchmark datasets, our method outperformed several current state-of-the-art methods in terms of multiple performance measures, including mean square error (MSE), consistency index (CI), rm2, and PR curve area (AUPR). The results demonstrated that our method achieved better performance in predicting the drug–target binding affinity.     

Five-Year Prognosis Model of Esophageal Cancer Based on Genetic Algorithm Improved Deep Neural Network

ObjectivesEsophageal cancer is a high occult malignant tumor. Even with good diagnosis and treatment, the 5-year survival rate of esophageal cancer patients is still less than 30%. Considering the influence of clinical characteristics on postoperative esophageal cancer patients, the construction of a neural network model will help improve the poor prognosis of patients in the five years.Material and methodsIn this study, genetic algorithm optimized deep neural network is exploited to the clinical dataset of esophageal cancer. The independent prognostic factors are screened by Relief algorithm and Cox proportional risk regression. FTD prognostic staging system is established to assess the risk level of esophageal cancer patients.ResultsFTD staging system and independent prognostic factors are integrated into the genetic algorithm optimized deep neural network. The Area Under Curve (AUC) of FTD staging system is 0.802. FTD staging system is verified by the Kaplan-Meier survival curve, and the median survival time is divided for different risk grades. The FTD staging system is superior to the TNM stages in the prognosis effect. The AUC of deep neural network optimized by genetic algorithm is 0.91.ConclusionThe deep neural network optimized by genetic algorithm has good performance in predicting the 5-year survival status of esophageal cancer patients. The FTD staging system has a significant prognostic effect. The FTD staging system and genetic algorithm optimized deep neural network can be successfully availed in clinical diagnosis and treatment.     

Neural hierarchical models of ecological populations

Neural networks are increasingly being used in science to infer hidden dynamics of natural systems from noisy observations, a task typically handled by hierarchical models in ecology. This article describes a class of hierarchical models parameterised by neural networks – neural hierarchical models. The derivation of such models analogises the relationship between regression and neural networks. A case study is developed for a neural dynamic occupancy model of North American bird populations, trained on millions of detection/non‐detection time series for hundreds of species, providing insights into colonisation and extinction at a continental scale. Flexible models are increasingly needed that scale to large data and represent ecological processes. Neural hierarchical models satisfy this need, providing a bridge between deep learning and ecological modelling that combines the function representation power of neural networks with the inferential capacity of hierarchical models.     

Arrhythmic Heartbeat Classification Using 2D Convolutional Neural Networks

BackgroundElectrocardiogram (ECG) is a method of recording the electrical activity of the heart and it provides a diagnostic means for heart-related diseases. Arrhythmia is any irregularity of the heartbeat that causes an abnormality in the heart rhythm. Early detection of arrhythmia has great importance to prevent many diseases. Manual analysis of ECG recordings is not practical for quickly identifying arrhythmias that may cause sudden deaths. Hence, many studies have been presented to develop computer-aided-diagnosis (CAD) systems to automatically identify arrhythmias.MethodsThis paper proposes a novel deep learning approach to identify arrhythmias in ECG signals. The proposed approach identifies arrhythmia classes using Convolutional Neural Network (CNN) trained by two-dimensional (2D) ECG beat images. Firstly, ECG signals, which consist of 5 different arrhythmias, are segmented into heartbeats which are transformed into 2D grayscale images. Afterward, the images are used as input for training a new CNN architecture to classify heartbeats.ResultsThe experimental results show that the classification performance of the proposed approach reaches an overall accuracy of 99.7%, sensitivity of 99.7%, and specificity of 99.22% in the classification of five different ECG arrhythmias. Further, the proposed CNN architecture is compared to other popular CNN architectures such as LeNet and ResNet-50 to evaluate the performance of the study.ConclusionsTest results demonstrate that the deep network trained by ECG images provides outstanding classification performance of arrhythmic ECG signals and outperforms similar network architectures. Moreover, the proposed method has lower computational costs compared to existing methods and is more suitable for mobile device-based diagnosis systems as it does not involve any complex preprocessing process. Hence, the proposed approach provides a simple and robust automatic cardiac arrhythmia detection scheme for the classification of ECG arrhythmias.     

Identification of Indian butterflies using Deep Convolutional Neural Network

The conventional butterfly identification method is based on their different morphological characters namely wing-venation, color, shape, patterns and through the dissection studies and molecular techniques which are tedious, expensive and highly time-consuming. To overcome the above aforesaid challenges, a new butterfly identification system using butterfly images has been designed to instantly identify the butterfly with high accuracy. In this study, we construct a new butterfly dataset with 34,024 butterfly images belonging to 315 species from India. We propose and prove the effectiveness of new data augmentation techniques on our dataset. To identify butterflies using photographic images, we built eleven new Deep Convolutional Neural Network (DCNN) butterfly classifier models using eleven pre-trained architectures namely ResNet-18, ResNet-34, ResNet-50, ResNet-121, ResNet-152, Alex-Net, DenseNet-121, DenseNet-161, VGG-16, VGG-19 and SqueezeNet-v1.1. The different model's classification results were compared and the proposed technique achieved a maximum top-1 accuracy(94.44%), top-3 accuracy(98.46%) and top-5 accuracy(99.09%) using ResNet-152 model, followed by DenseNet-161 model achieved the top-1 accuracy(94.31%), top-3 accuracy (98.07%) and top-5 accuracy (98.66%). The results suggest that models can be assertively used to identify butterflies in India.     

Classification of Motor Imagery EEG Based on Time-Domain and Frequency-Domain Dual-Stream Convolutional Neural Network

Background and objectiveAn important task of the brain-computer interface (BCI) of motor imagery is to extract effective time-domain features, frequency-domain features or time-frequency domain features from the raw electroencephalogram (EEG) signals for classification of motor imagery. However, choosing an appropriate method to combine time domain and frequency domain features to improve the performance of motor imagery recognition is still a research hotspot.MethodsIn order to fully extract and utilize the time-domain and frequency-domain features of EEG in classification tasks, this paper proposed a novel dual-stream convolutional neural network (DCNN), which can use time domain signal and frequency domain signal as the inputs, and the extracted time-domain features and frequency-domain features are fused by linear weighting for classification training. Furthermore, the weight can be learned by the DCNN automatically.ResultsThe experiments based on BCI competition II dataset III and BCI competition IV dataset 2a showed that the model proposed by this study has better performance than other conventional methods. The model used time-frequency signal as the inputs had better performance than the model only used time-domain signals or frequency-domain signals. The accuracy of classification was improved for each subject compared with the models only used one signals as the inputs.ConclusionsFurther analysis shown that the fusion weight of different subject is specifically, adjusting the weight coefficient automatically is helpful to improve the classification accuracy.     

基于卷积神经网络的超声影像肝癌自动分类

目的 针对从原发性肝癌中检测肝细胞癌（HCC）的灵敏度不高和诊断结果高度依赖放射科医生的专业性和临床经验，本文利用深度卷积神经网络（CNN）的方法自动学习B超和超声造影（CEUS）图像中的特征信息，并实现对肝癌的分类。方法 建立并验证基于CNN的多个二维（2D）和三维（3D）分类模型，分别对116例患者（其中100例HCC和16例非HCC）的B超和CEUS影像进行定量分析，并对比分析各个模型的分类性能。结果 实验结果表明，3D-CNN模型的各方面性能指标都优于2D-CNN模型，验证了3D-CNN模型能同时提取肿瘤区域的2D影像特征及血流时间动态变化特征，比2D-CNN模型更适用于HCC与非HCC分类。其中3D-CNN模型的AUC、准确率和敏感度值最高，分别达到了85%、85%和80%。此外，由于HCC和非HCC样本不均衡，通过扩充非HCC样本的数量可以提升网络的分类性能。结论 本文提出的3D-CNN模型能够实现快速、准确的肝癌分类，有望应用于辅助临床医师诊断与治疗肝癌。     

基于树木年轮径切特征的卷积神经网络树种识别

卷积神经网络可以通过树木年轮样本构造特征图像实现物种识别的自动化。本研究通过建立树木年轮样本构造特征图像集,选用LeNet、AlexNet、GoogLeNet和VGGNet 4个卷积神经网络模型,实现基于树木年轮横切面的计算机自动化树种精准识别,进而确定各模型的树种识别准确率,明晰不同树种在自动识别中的混淆情况,探测不同模型识别结果的差异。结果表明: 本研究训练的用于树种识别的卷积神经网络模型具有较好的可信度;4个模型中GoogLeNet模型树种识别准确率最高,为96.7%,LeNet模型识别准确率最低(66.4%);不同模型对于所选树种的识别结果具有一致性,表现为对蒙古栎识别准确率最高(AlexNet模型识别率达到100%),对臭冷杉的识别准确率最低。本研究中也存在类似结构树种的识别混淆情况。模型在科和属水平的识别准确率高于种水平;阔叶树种因其显著的结构差异容易区分,阔叶树树种的识别准确率高于针叶树。总体上,通过卷积神经网络,探测了树木年轮特征的深层信息,达到树种的精准识别,提供了一种快速便捷的自动树种初筛鉴定方法。     

基于人工神经网络的叶脉信息提取--植物活体机器识别研究I

叶片的识别是识别植物的重要组成部分,特别在野外识别植物活体尤其重要.叶脉的脉序是植物的内在特征,包含有重要的遗传信息.但由于叶脉本身的多样性,利用单一特征的图像处理方法难以有效地提取叶脉.为了充分利用图像的信息,本文提出了一种基于人工神经网络的叶脉提取方法.该方法利用边缘梯度、局部对比度和邻域统计特征等10个参数来描述像素的邻域特征,并将其作为神经网络的输入层.实验结果表明,与传统方法相比,经过训练的神经网络能够更准确地提取叶脉图像,为进一步的叶片识别打下了良好的基础.     

基于点云卷积神经网络的蛋白质柔性预测

目的 蛋白质的柔性运动对生物体各种反应有着重要意义,基于蛋白质的空间结构预测其柔性运动是蛋白质结构-功能关系领域的重要问题.卷积神经网络(convolutional neural network,CNN)在蛋白质结构-功能关系研究中已有成功应用.方法 本研究借鉴计算机视觉研究中PointNet方法的思想,提出了一种蛋白...     

基于三维卷积神经网络的肺结节探测与定位方法

提出一种基于三维卷积神经网络对肺部计算机断层扫描图像(CT)进行肺结节自动探测及定位的方法.基于开源数据集LUNA16开展研究,对数据进行像素归一化、坐标转换等预处理,对正样本使用随机平移、旋转和翻转的方式进行扩充,对负样本进行随机采样.搭建了三维卷积神经网络并在训练过程中调整网络参数,直到得到性能最佳的网络.此外还设...     

基于卷积神经网络的无人机遥感影像水鸟自动识别

水鸟监测是了解水鸟种群和分布动态、开展水鸟和湿地保护的基础,但该活动耗时耗力。近年来,随着无人机遥感技术的发展,使用小型无人机获得高分辨率的水鸟遥感影像已经成为可能;与此同时,卷积神经网络提供了一种快速识别无人机遥感图像中的鸟类的方法。我们尝试结合两种技术,使用卷积神经网络Mask R-CNN与YOLOv3识别湖南西洞庭湖国家级自然保护区无人机遥感影像中的大型水鸟,取得了良好的效果：模型检测拍摄到的鸭属鸟类,包括绿翅鸭(Anas crecca)和罗纹鸭(A. falcata)的结果平均精度达到0.93,精度达到90.83%,召回率达到93%;检测小天鹅(Cygnus columbianus)的结果平均精度达到0.91,精度达到84.38%,召回率达到84.00%。结果表明,将无人机遥感技术与卷积神经网络结合,可以快速统计水鸟数量,在种群监测工作中具有应用潜力。     

FT-IR Spectroscopy and Artificial Neural Network Identification of Fusarium Species

A rapid spectroscopic approach for whole‐organism fingerprinting of Fourier transform infrared (FT‐IR) spectroscopy was used to analyse 16 isolates from five closely related species of Fusarium: F. graminearum, F. moniliforme, F. nivale, F. semitectum and F. oxysporum. Principal components analysis and hierarchical cluster analysis were used to study the clusters in the data. On visual inspection of the clusters from both methods, the spectra were not differentiated into five separate clusters corresponding to species and these unsupervised methods failed to identify these fungal strains. When the data were trained by back propagation algorithm of artificial neural networks (ANNs) with principal components scores of spectra used as input modes, the strains were accurately predicted and recognized. The results in this study show that FT‐IR spectroscopy in combination with principal component artificial neural networks (PC‐ANNs) is well suited for identifying Fusarium spp. It would be advantageous to establish a comprehensive database of taxonomically well‐defined Fusarium species to aid the identification of unknown strains.     

基于BP神经网络的siRNA活性预测

RNA干扰(RNAinterference,RNAi)是由双链RNA(dsRNA)引起的基因沉默现象,它通过降解具有同源序列的mRNA来起作用,特殊设计的siRNA能使靶基因发生特异性沉默,起到确定基因功能或沉默致病基因从而治疗疾病的目的。在RNAi技术的应用中,通常采用的是长度为19bp,正、反义链3'端各有2个不配对碱基的双链RNA(siRNA)。但针对靶基因不同位点设计的siRNA作用效果差别很大。影响siRNA效果的因素是多方面的,这些因素的作用又是非线性的。本文在研究影响siRNA作用效果的各种因素的基础上,对已经公开发表的实验数据进行特征提取,作为BP神经网络的训练数据,并将训练好的BP神经网络用于siRNA活性预测。     

Classification of Leukemia and Leukemoid Using VGG-16 Convolutional Neural Network Architecture

Leukemoid reaction like leukemia indicates noticeable increased count of WBCs (White Blood Cells) but the cause of it is due to severe inflammation or infections in other body regions. In automatic diagnosis in classifying leukemia and leukemoid reactions, ALL IDB2 (Acute Lymphoblastic Leukemia-Image Data Base) dataset has been used which comprises 110 training images of blast cells and healthy cells. This paper aimed at an automatic process to distinguish leukemia and leukemoid reactions from blood smear images using Machine Learning. Initially, automatic detection and counting of WBC is done to identify leukocytosis and then an automatic detection of WBC blasts is performed to support classification of leukemia and leukemoid reactions. Leukocytosis is commonly observed both in leukemia and leukemoid hence physicians may have chance of wrong diagnosis of malignant leukemia for the patients with leukemoid reactions. BCCD (blood cell count detection) Dataset has been used which has 364 blood smear images of which 349 are of single WBC type. The Image segmentation algorithm of Hue Saturation Value color based on watershed has been applied. VGG16 (Visual Geometric Group) CNN (Convolution Neural Network) architecture based deep learning technique is being incorporated for classification and counting WBC type from segmented images. The VGG16 architecture based CNN used for classification and segmented images obtained from first part were tested to identify WBC blasts.     

A Review on Convolutional Neural Networks for Brain Tumor Segmentation: Methods,Datasets, Libraries,and Future Directions

ObjectivesAccurate and reliable segmentation of brain tumors from MRI images helps in planning an enhanced treatment and increases the life expectancy of patients. However, the manual segmentation of brain tumors is subjective and more prone to errors. Nonetheless, the recent advances in convolutional neural network (CNN)-based methods have exhibited outstanding potential in robust segmentation of brain tumors. This article comprehensively investigates recent advances in CNN-based methods for automatic segmentation of brain tumors from MRI images. It examines popular deep learning (DL) libraries/tools for an expeditious and effortless implementation of CNN models. Furthermore, a critical assessment of current DL architectures is delineated along with the scope of improvement.MethodsIn this work, more than 50 scientific papers from 2014-2020 are selected using Google Scholar and PubMed. Also, the leading journals related to our work along with proceedings from major conferences such as MICCAI, MIUA and ECCV are retrieved. This research investigated various annual challenges too related to this work including Multimodal Brain Tumor Segmentation Challenge (MICCAI BRATS) and Ischemic Stroke Lesion Segmentation Challenge (ISLES).ResultAfter a systematic literature search pertinent to the theme, we found that principally there exist three variations of CNN architecture for brain tumor segmentation: single-path and multi-path, fully convolutional, and cascaded CNNs. The respective performances of most automated methods based on CNN are appraised on the BraTS dataset, provided as a part of the MICCAI Multimodal Brain Tumor Segmentation challenge held annually since 2012.ConclusionNotwithstanding the remarkable potential of CNN-based methods, reliable and robust segmentation of brain tumors continues to be an intractable challenge. This is due to the intricate anatomy of the brain, variability in its appearance, and imperfection in image acquisition. Moreover, owing to the small size of MRI datasets, CNN-based methods cannot operate with their full capacity, as demonstrated with large scale datasets, such as ImageNet.     

Uterine Synchronization Analysis During Pregnancy and Labor Using Graph Theory,Classification Based on Neural Network and Deep Learning

1) ObjectivesPreterm birth caused by preterm labor is one of the major health problems in the world. In this article, we present a new framework for dealing with this problem through the processing of electrohysterographic signals (EHG) that are recorded during labor and pregnancy. The objective in this research is to improve the classification between labor and pregnancy contractions by using a new approach that focuses on the connectivity analysis based on graph parameters, representative of uterine synchronization, and comparing neural network and machine learning methods in order to classify between labor and pregnancy.2) Material and methodsafter denoising of the 16 EHG signals recorded from pregnant women abdomen, we applied different connectivity methods to obtain connectivity matrices; then by using the graph theory, we extracted some graph parameters from the connectivity matrices; finally, we tested different neural network and machine learning methods on the features obtained from both graph and connectivity methods in order to classify between labor and pregnancy.3) ResultsThe best results were obtained by using the logistic regression method. We also evidence the power of graph parameters extracted from the connectivity matrices to improve the classification results.4) ConclusionThe use of graph analysis associated with machine learning methods can be a powerful tool to improve labor and pregnancy classification based on the analysis of EHG signals.