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。     

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.     

人工神经网络在蝙蝠回声定位叫声识别方面的应用

近年来,人工神经网络被不断应用于野生动物的声学研究中,本文概括地介绍了人工神经网络的概念以及这项新技术的研究方法,并且重点介绍了它在蝙蝠回声定位叫声识别方面的应用。     

具时滞的Hopfield型神经网络模型的全局渐近稳定性

本文研究了具时滞的Hopfield型神经网络模型平衡点的全局渐近稳定性,获得了一系列充分条件。     

具有时滞的双向联想记忆神经网络的全局渐近稳定性

双向联想记忆模型是两层异联想网络,本文讨论了具有轴突信号传输时滞的双向联想记忆神经网络的全局渐近稳定性,得出了保证神经网络平衡点稳定的几个充分条件,所得到的结论对于具有时滞的连续双向联想记忆神经网络的设计和应用都是很有意义的。     

关于一类具有时滞的双向联想记忆神经网络的收敛性

研究了一类具有时滞的双层双向联想记忆模型的收敛性,给出了平衡点的存在性、唯一性、全局渐近稳定性的充分条件．     

An automatic method for removing empty camera trap images using ensemble learning

Camera traps often produce massive images, and empty images that do not contain animals are usually overwhelming. Deep learning is a machine‐learning algorithm and widely used to identify empty camera trap images automatically. Existing methods with high accuracy are based on millions of training samples (images) and require a lot of time and personnel costs to label the training samples manually. Reducing the number of training samples can save the cost of manually labeling images. However, the deep learning models based on a small dataset produce a large omission error of animal images that many animal images tend to be identified as empty images, which may lead to loss of the opportunities of discovering and observing species. Therefore, it is still a challenge to build the DCNN model with small errors on a small dataset. Using deep convolutional neural networks and a small‐size dataset, we proposed an ensemble learning approach based on conservative strategies to identify and remove empty images automatically. Furthermore, we proposed three automatic identifying schemes of empty images for users who accept different omission errors of animal images. Our experimental results showed that these three schemes automatically identified and removed 50.78%, 58.48%, and 77.51% of the empty images in the dataset when the omission errors were 0.70%, 1.13%, and 2.54%, respectively. The analysis showed that using our scheme to automatically identify empty images did not omit species information. It only slightly changed the frequency of species occurrence. When only a small dataset was available, our approach provided an alternative to users to automatically identify and remove empty images, which can significantly reduce the time and personnel costs required to manually remove empty images. The cost savings were comparable to the percentage of empty images removed by models.     

SPIN2: Predicting sequence profiles from protein structures using deep neural networks

Designing protein sequences that can fold into a given structure is a well‐known inverse protein‐folding problem. One important characteristic to attain for a protein design program is the ability to recover wild‐type sequences given their native backbone structures. The highest average sequence identity accuracy achieved by current protein‐design programs in this problem is around 30%, achieved by our previous system, SPIN. SPIN is a program that predicts sequences compatible with a provided structure using a neural network with fragment‐based local and energy‐based nonlocal profiles. Our new model, SPIN2, uses a deep neural network and additional structural features to improve on SPIN. SPIN2 achieves over 34% in sequence recovery in 10‐fold cross‐validation and independent tests, a 4% improvement over the previous version. The sequence profiles generated from SPIN2 are expected to be useful for improving existing fold recognition and protein design techniques. SPIN2 is available at http://sparks-lab.org .     

Hindmarsh-Rose 神经网络的混沌同步

研究了通过特殊构造的非线性函数耦合连接的神经网络的混沌同步问题。在发展基于稳定性准则的混沌同步方法的基础上,给出了计算同步稳定性的误差发展方程,当耦合强度取参考值时,可实现稳定的混沌同步而不需要计算最大条件Lyapunov指数去判定是否稳定。通过对按照完全连接形式构成的Hindmarsh-Rose神经网络的数值模拟,显示可仅从两个耦合神经的耦合强度的稳定性范围预期到许多耦合神经实现同步的稳定性范围。该方法在噪声影响下,对实现神经元的混沌同步仍具有较强的鲁棒性。此外发现随着耦合神经数的增加,满足同步稳定性的耦合强度减小,与耦合神经的数量成反比。     

New deep learning-based methods for visualizing ecosystem properties using environmental DNA metabarcoding data

Environmental DNA (eDNA) metabarcoding provides an efficient approach for documenting biodiversity patterns in marine and terrestrial ecosystems. The complexity of these data prevents current methods from extracting and analyzing all the relevant ecological information they contain, and new methods may provide better dimensionality reduction and clustering. Here we present two new deep learning-based methods that combine different types of neural networks (NNs) to ordinate eDNA samples and visualize ecosystem properties in a two-dimensional space: the first is based on variational autoencoders and the second on deep metric learning. The strength of our new methods lies in the combination of two inputs: the number of sequences found for each molecular operational taxonomic unit (MOTU) detected and their corresponding nucleotide sequence. Using three different datasets, we show that our methods accurately represent several biodiversity indicators in a two-dimensional latent space: MOTU richness per sample, sequence α-diversity per sample, Jaccard's and sequence β-diversity between samples. We show that our nonlinear methods are better at extracting features from eDNA datasets while avoiding the major biases associated with eDNA. Our methods outperform traditional dimension reduction methods such as Principal Component Analysis, t-distributed Stochastic Neighbour Embedding, Nonmetric Multidimensional Scaling and Uniform Manifold Approximation and Projection for dimension reduction. Our results suggest that NNs provide a more efficient way of extracting structure from eDNA metabarcoding data, thereby improving their ecological interpretation and thus biodiversity monitoring.     

Implementation of Neural Networks to Frontal Electroencephalography for the Identification of the Transition Responsiveness/Unresponsiveness During Induction of General Anesthesia

ObjectiveGeneral anesthesia is a reversible drug-induced state of altered arousal characterized by loss of responsiveness (LOR) due to brainstem inactivation. Precise identification of the LOR during the induction of general anesthesia is extremely important to provide personalized information on anesthetic requirements and could help maintain an adequate level of anesthesia throughout surgery, ensuring safe and effective care and balancing the avoidance of intraoperative awareness and overdose. So, main objective of this paper was to investigate whether a Convolutional Neural Network (CNN) applied to bilateral frontal electroencephalography (EEG) dataset recorded from patients during opioid-propofol anesthetic procedures identified the exact moment of LOR.Material and methodsA clinical protocol was designed to allow for the characterization of different clinical endpoints throughout the transition to unresponsiveness. Fifty (50) patients were enrolled in the study and data from all was included in the final dataset analysis. While under a constant estimated effect-site concentration of 2.5 ng/mL of remifentanil, an 1% propofol infusion was started at 3.3 mL//h until LOR. The level of responsiveness was assessed by an anesthesiologist every six seconds using a modified version of the Richmond Agitation-Sedation Scale (aRASS). The frontal EEG was acquired using a bilateral bispectral (BIS VISTA™ v2.0, Medtronic, Ireland) sensor. EEG data was then split into 5-second epochs, and for each epoch, the anesthesiologist's classification was used to label it as responsiveness (no-LOR) or unresponsiveness (LOR). All 5-second epochs were then used as inputs for the CNN model to classify the untrained segment as no-LOR or LOR.ResultsThe CNN model was able to identify the transition from no-LOR to LOR successfully, achieving 97.90±0.07% accuracy on the cross-validation set.ConclusionThe obtained results showed that the proposed CNN model was quite efficient in the responsiveness/unresponsiveness classification. We consider our approach constitutes an additional technique to the current methods used in the daily clinical setting where LOR is identified by the loss of response to verbal commands or mechanical stimulus. We therefore hypothesized that automated EEG analysis could be a useful tool to detect the moment of LOR, especially using machine learning approaches.     

Wildlife surveillance using deep learning methods

相似文献   

Varieties of Representation in Evolved and Embodied Neural Networks

In this paper I discuss one of the key issuesin the philosophy of neuroscience:neurosemantics. The project of neurosemanticsinvolves explaining what it means for states ofneurons and neural systems to haverepresentational contents. Neurosemantics thusinvolves issues of common concern between thephilosophy of neuroscience and philosophy ofmind. I discuss a problem that arises foraccounts of representational content that Icall ``the economy problem': the problem ofshowing that a candidate theory of mentalrepresentation can bear the work requiredwithin in the causal economy of a mind and anorganism. My approach in the current paper isto explore this and other key themes inneurosemantics through the use of computermodels of neural networks embodied and evolvedin virtual organisms. The models allow for thelaying bare of the causal economies of entireyet simple artificial organisms so that therelations between the neural bases of, forinstance, representation in perception andmemory can be regarded in the context of anentire organism. On the basis of thesesimulations, I argue for an account ofneurosemantics adequate for the solution of theeconomy problem.     

一类BAM随机神经网络的稳定性

对于一类双向联想记忆（BAM）随机神经网络。研究其全局稳定性和指数稳定性,利用Schwarz积分不等式和Ito积分性质,给出其稳定性判定的充分性条件．     

具有变时滞竞争神经网络的指数稳定性

利用微分方程组的基解矩阵及推广的Halanay微分不等式等分析技巧,讨论了一类具有不同时间尺度的变时滞竞争神经网络的平衡点存在和唯一性,并给出指数稳定性判定的充分条件,最后通过数值仿真实例检验结果的正确性.     

Distinguishing Felsenstein Zone from Farris Zone Using Neural Networks

Maximum likelihood and maximum parsimony are two key methods for phylogenetic tree reconstruction. Under certain conditions, each of these two methods can perform more or less efficiently, resulting in unresolved or disputed phylogenies. We show that a neural network can distinguish between four-taxon alignments that were evolved under conditions susceptible to either long-branch attraction or long-branch repulsion. When likelihood and parsimony methods are discordant, the neural network can provide insight as to which tree reconstruction method is best suited to the alignment. When applied to the contentious case of Strepsiptera evolution, our method shows robust support for the current scientific view, that is, it places Strepsiptera with beetles, distant from flies.     

基于神经网络的异位妊娠发病率发展趋势研究

本文阐述了ＢＰ神经网络的基本算法,并根据近十年来搜集整理的异位妊娠发病率的统计资料;采用 ＢＰ神经网络对异位妊娠的发病率的发展趋势进行预测;预测结果和实际结果比较吻合．进一步指出了神经网络可作为一种新的预测方法．