An HVS-Directed Neural-Network-Based Image Resolution Enhancement Scheme for Image Resizing

In this paper, a novel human visual system (HVS)-directed neural-network-based adaptive interpolation scheme for natural image is proposed. A fuzzy decision system built from the characteristics of the HVS is proposed to classify pixels of the input image into human perception nonsensitive class and sensitive class. Bilinear interpolation is used to interpolate the nonsensitive regions and a neural network is proposed to interpolate the sensitive regions along edge directions. High-resolution digital images along with supervised learning algorithms are used to automatically train the proposed neural network. Simulation results demonstrate that the proposed new resolution enhancement algorithm can produce a higher visual quality for the interpolated image than the conventional interpolation methods.     

深度学习在医学影像中的应用综述

深度学习能自动从大样本数据中学习获得优良的特征表达,有效提升各种机器学习任务的性能,已广泛应用于信号处理、计算机视觉和自然语言处理等诸多领域。基于深度学习的医学影像智能计算是目前智慧医疗领域的研究热点,其中深度学习方法已经应用于医学影像处理、分析的全流程。由于医学影像内在的特殊性、复杂性,特别是考虑到医学影像领域普遍存在的小样本问题,相关学习任务和应用场景对深度学习方法提出了新要求。本文以临床常用的X射线、超声、计算机断层扫描和磁共振等4种影像为例,对深度学习在医学影像中的应用现状进行综述,特别面向图像重建、病灶检测、图像分割、图像配准和计算机辅助诊断这5大任务的主要深度学习方法的进展进行介绍,并对发展趋势进行展望。     

FP-CNNH:一种基于深度卷积神经网络的快速图像哈希算法

在大数据时代,图像检索技术在大规模数据上的应用是一个热门的研究领域。近年来,大规模图像检索系统中, 图像哈希算法 由于具备提高图像的检索效率同时减少储存空间的优点而受到广泛的关注。现有的有监督学习哈希算法存在一些问题,主流的有监督的哈希算法需要通过图像特征提取器获取人为构造的图像特征表示,这种做法带来的图像特征损失影响了哈希算法的效果,也不能较好地处理图像数据集中语义的相似性问题。随着深度学习在大规模数据上研究的兴起,一些相关研究尝试通过深度神经网络进行有监督的哈希函数学习,提升了哈希函数的效果,但这类方法需要针对数据集人为设计复杂的深度神经网络,增大了哈希函数设计的难度,而且深度神经网络的训练需要较多的数据和较长的时间,这些问题影响了基于深度学习的哈希算法在大规模数据集上的应用。针对这些问题,提出了一种基于深度卷积神经网络的快速图像哈希算法,该算法通过设计优化问题的求解方法以及使用预训练的大规模深度神经网络,提高了哈希算法的效果,同时明显地缩短了复杂神经网络的训练时间。根据在不同图像数据集上的实验结果分析可知, 与现有的基准算法相比,提出的算法在哈希函数训练效果和训练时间上都具有较大的提高。     

The influence of the radial basis function training strategy on the performance of a neural gripper

In this article, a neural network-based grasping system that is able to collect objects of arbitrary shape is introduced. The grasping process is split into three functional blocks: image acquisition and processing, contact point estimation, and contact force determination. The paper focuses on the second block, which contains two neural networks. A competitive Hopfield neural network first determines an approximate polygon for an object outline. These polygon edges are the input for a supervised neural network model [radial basis function (RBF) or multilayer perceptions], which then defines the contact points. Tests were conducted with objects of different shapes, and experimental results suggest that the performance of the neural gripper and its learning rate are significantly influenced by the choice of supervised training model and RBF learning algorithm.     

Capture interspeaker information with a neural network for speakeridentification

Model-based approach is one of methods widely used for speaker identification, where a statistical model is used to characterize a specific speaker's voice but no interspeaker information is involved in its parameter estimation. It is observed that interspeaker information is very helpful in discriminating between different speakers. In this paper, we propose a novel method for the use of interspeaker information to improve performance of a model-based speaker identification system. A neural network is employed to capture the interspeaker information from the output space of those statistical models. In order to sufficiently utilize interspeaker information, a rival penalized encoding rule is proposed to design supervised learning pairs. For better generalization, moreover, a query-based learning algorithm is presented to actively select the input data of interest during training of the neural network. Comparative results on the KING speech corpus show that our method leads to a considerable improvement for a model-based speaker identification system.     

Bayesian network model of overall print quality: Construction and structural optimisation

Prediction of overall visual quality based on instrumental measurements is a challenging task. Despite the several proposed models and methods, there exists a gap between the instrumental measurements of print and human visual assessment of natural images. In this work, a computational model for representing and quantifying the overall visual quality of prints is proposed. The computed overall quality should correspond to the human visual quality perception when viewing the printed images. The proposed model is a Bayesian network which connects the objective instrumental measurements to the subjective opinion distribution of human observers. This relationship can be used to score printed images, and additionally, to computationally study the connections of the attributes. A novel graphical learning approach using an iterative evolve-estimate-simulate loop learning the quality model based on psychometric data and instrumental measurements is suggested. The network structure is optimised by applying evolutionary computation (evolve). The estimation of the Bayesian network parameters is within the evolutionary loop. In this loop, the maximum likelihood approach is used (estimate). The stochastic learning process is guided by priors devised from the psychometric subjective experiments (performance through simulation). The model reveals and represents the explanatory factors between its elements providing insight to the psychophysical phenomenon of how observers perceive visual quality and which measurable entities affect the quality perception. By using true data, the design choices are demonstrated. It is also shown that the best-performing network establishes a clear and intuitively correct structure between the objective measurements and psychometric data.     

Phase equilibria prediction of solid solute in supercritical carbon dioxide with and without a cosolvent: The use of artificial neural network

In this study, a back-propagation multi-layer neural network was developed to predict the solubility of solid solute in supercritical carbon dioxide with and without cosolvent. The solubility of anthracene in CO₂ with cosolvents, acetone, ethanol and cyclohexane were employed as model systems to investigate the supercritical carbon dioxide behaviour in ternary systems over a wide range of temperatures. The back-propagation neural network operated in a supervised learning mode. A number of networks were trained and tested with different network parameters using training and testing data sets. To establish the network applicability, a validating data set was used and the predictability of the network was statistically evaluated. Statistical estimations showed that the neural network predictions had an excellent agreement with experimental data. The calculated average relative deviation (ARD) and the root mean squared error (RMSD) for tested ANNs data points were 5.45% and 0.74%, respectively. A minimum number of data points have been employed to train the ANN. The predicted ARD and RMSD for the employed ternary systems were 7.83% and 0.07%, respectively. The results obtained in this work indicate that ANN is a superior technique with high level of accuracy for prediction of solubility of solid solute in ternary systems.     

基于可生长结构的神经网络建模与仿真

构建了用于倒立摆平衡控制的神经网络学习模型。该模型利用可生长结构神经网络的优势,不需要预先规定网络的结构和规模,便可以在学习过程中根据需要生长。基于可生长结构的神经网络将监督与无监督学习结合,能够快速学习刺激与响应之间的潜在关系。该神经网络离线进行监督学习,训练后作为控制器作用于倒立摆系统,构成基于可生长结构的倒立摆控制模型。以Matlab为开发工具进行了仿真实验。仿真结果表明,该模型能够完成一级倒立摆平衡控制任务,并验证了其有效性和抗干扰能力：     

深度学习的研究进展与发展

深度学习是基于数据表示的一类更广的机器学习方法,它的出现不仅推动了机器学习的发展,而且促进了人工智能的革新。对深度学习的几种典型模型进行研究与对比。首先介绍受限玻尔兹曼机、深度置信网络、自编码器等无监督学习模型,对其结构、原理和优缺点进行了详细探讨。讨论卷积神经网络、循环神经网络和深度堆叠网络等监督学习模型,分别从模型架构和工作原理来评价与分析。对深度学习的典型模型进行对比分析,将深度置信网络和卷积神经网络应用在手写体数字识别任务中,结果证实深度学习比传统的神经网络具有更好的识别性能。最后探讨深度学习未来的发展与挑战。     

A new feedback neural network with supervised learning

A model is introduced for continuous-time dynamic feedback neural networks with supervised learning ability. Modifications are introduced to conventional models to guarantee precisely that a given desired vector, and its negative, are indeed stored in the network as asymptotically stable equilibrium points. The modifications entail that the output signal of a neuron is multiplied by the square of its associated weight to supply the signal to an input of another neuron. A simulation of the complete dynamics is then presented for a prototype one neuron with self-feedback and supervised learning; the simulation illustrates the (supervised) learning capability of the network.     

基于三相连接的进化模糊神经网络及应用

介绍了一种新型的进化模糊神经网络,规则节点层融入了三相电路的连接方式,用于在线的监督学习或者无人监督学习。使用进化聚类方法,模糊规则在系统执行过程中进行创建和更新,并且采用遗传算法即时优化进化聚类的结果,通过T-S模型模糊推理系统计算输出。     

深度卷积神经网络图像语义分割研究进展

在计算机视觉领域中,语义分割是场景解析和行为识别的关键任务,基于深度卷积神经网络的图像语义分割方法已经取得突破性进展。语义分割的任务是对图像中的每一个像素分配所属的类别标签,属于像素级的图像理解。目标检测仅定位目标的边界框,而语义分割需要分割出图像中的目标。本文首先分析和描述了语义分割领域存在的困难和挑战,介绍了语义分割算法性能评价的常用数据集和客观评测指标。然后,归纳和总结了现阶段主流的基于深度卷积神经网络的图像语义分割方法的国内外研究现状,依据网络训练是否需要像素级的标注图像,将现有方法分为基于监督学习的语义分割和基于弱监督学习的语义分割两类,详细阐述并分析这两类方法各自的优势和不足。本文在PASCAL VOC（pattern analysis, statistical modelling and computational learning visual object classes）2012数据集上比较了部分监督学习和弱监督学习的语义分割模型,并给出了监督学习模型和弱监督学习模型中的最优方法,以及对应的MIoU（mean intersection-over-union）。最后,指出了图像语义分割领域未来可能的热点方向。     

Learning texture discrimination rules in a multiresolution system

We describe a texture analysis system in which informative discrimination rules are learned from a multiresolution representation of time textured input. The system incorporates unsupervised and supervised learning via statistical machine learning and rule-based neural networks, respectively. The textured input is represented in the frequency-orientation space via a log-Gabor pyramidal decomposition. In the unsupervised learning stage a statistical clustering scheme is used for the quantization of the feature-vector attributes. A supervised stage follows in which labeling of the textured map is achieved using a rule-based network. Simulation results for the texture classification task are given. An application of the system to real-world problems is demonstrated     

基于强化学习的股票预测系统的研究与设计

股票市场是金融分析领域中重要而困难的问题。股票数据的分析和预测具有重大的理论意义和诱人的应用价值。BP神经网络在目前的股票预测系统中应用广泛,但是作为有导师的学习系统,BP神经网络必须要求提供相关的经验数据才能正常运行。对此本文提出了一种基于强化学习BP算法应用于股票预测系统,通过强化学习体系来实现体统的自学习,通过网络集成来达到初始数据的预处理,提高系统的泛化能力,在实际应用中取的较好的效果。     

Fuzzy learning vector quantization for hyperspectral coastal vegetation classification

Artificial neural networks (ANNs) may be of significant value in extracting vegetation type information in complex vegetation mapping problems, particularly in coastal wetland environments. Unsupervised, self-organizing ANNs have not been employed as frequently as supervised ANNs for vegetation mapping tasks, and further remote sensing research involving fuzzy ANNs is also needed. In this research, the utility of a fuzzy unsupervised ANN, specifically a fuzzy learning vector quantization (FLVQ) ANN, was investigated in the context of hyperspectral AVIRIS image classification. One key feature of the neural approach is that unlike conventional hyperspectral data processing methods, endmembers for a given scene, which can be difficult to determine with confidence, are not required for neural analysis. The classification accuracy of FLVQ was comparable to a conventional supervised multi-layer perceptron, trained with backpropagation (MLP) (KHAT (Kˆ) accuracy: 82.82% and 84.66%, respectively; normalized accuracy: 74.60% and 75.85%, respectively), with no significant difference at the 95% confidence level. All neural algorithms in the experiment yielded significantly higher classification accuracies than the conventional endmember-based hyperspectral mapping method assessed (i.e., matched filtering, where Kˆ accuracy = 61.00% and normalized accuracy = 57.96%). FLVQ was also dramatically more computationally efficient than the baseline supervised and unsupervised ANN algorithms tested, including the MLP and the Kohonen self-organizing map (SOM), respectively. The 400-neuron FLVQ network required only 3.6% of the computation time used by the MLP network, and only 5.9% of the MLP time was used by the 588-neuron FLVQ network. In addition, the 400-neuron FLVQ used only 16.7% of the time used by the 400-neuron SOM for model development.     

A neural network model which combines unsupervised and supervisedlearning

A neural network that combines unsupervised and supervised learning for pattern recognition is proposed. The network is a hierarchical self-organization map, which is trained by unsupervised learning at first. When the network fails to recognize similar patterns, supervised learning is applied to teach the network to give different scaling factors for different features so as to discriminate similar patterns. Simulation results show that the model obtains good generalization capability as well as sharp discrimination between similar patterns.     

基于LDA和卷积神经网络的半监督图像标注方法

随着智能设备的不断出现,图像数量急速增加,但是很多图像因为没有被标注所以未被充分利用.为了能够使该问题得到较好解决,提出了基于LDA和卷积神经网络的半监督图像标注方法.首先把图像训练集中的所有文字信息放入LDA中,生成图像的文字标注词;然后使用卷积神经网络获得图像的高层视觉特征,同时用加入注意力机制和修改损失函数的方法...     

深度学习在组织病理学中的应用综述

组织病理学是临床上肿瘤诊断的金标准,直接关系到治疗的开展与预后的评估。来自临床的需求为组织病理诊断提出了质量与效率两个方面的挑战。组织病理诊断涉及大量繁重的病理切片判读任务,高度依赖医生的经验,但病理医生的培养周期长,人才储备缺口巨大,病理科室普遍超负荷工作。近年来出现的基于深度学习的组织病理辅助诊断方法可以帮助医生提高诊断工作的精度与速度,缓解病理诊断资源不足的问题,引起了研究人员的广泛关注。本文初步综述深度学习方法在组织病理学中的相关研究工作。介绍了组织病理诊断的医学背景,整理了组织病理学领域的主要数据集,重点介绍倍受关注的乳腺癌、淋巴结转移癌、结肠癌的病理数据及其分析任务。本文归纳了数据的存储与处理、模型的设计与优化以及小样本与弱标注学习这3项需要解决的技术问题。围绕这些问题,本文介绍了包括数据存储、数据预处理、分类模型、分割模型、迁移学习和多示例学习等相关研究工作。最后总结了面向组织病理学诊断的深度学习方法研究现状,并指出当下研究工作可能的改进方向。     

基于模式识别的传感器故障诊断

为满足模式识别故障诊断算法的鲁棒性要求,在小波包分解提取特征向量的基础上,提出了有监督模式分类与无监督模式分类相结合的故障诊断方法．利用小波包分解提取各个频带的能量作为特征向量;采用LVQ神经网络作为有监督的模式分类器进行故障诊断;运用无监督的减法聚类方法对新型故障模式进行辨识．最后,通过动力系统管路流量传感器数据对算法进行检验,验证了所提出方法的实用性和有效性．     

基于轻量自动残差缩放网络的图像超分辨率重建

近年来,由于深度卷积神经网络的出色性能,深度学习已成为图像超分辨率领域的研究热点,已经有许多具有很深结构的大型模型被提出。而在实际应用中,普通个人计算机或智能终端的硬件显然不适合大规模深度神经网络模型。提出了一种针对单幅图像超分辨率且具有自动残差缩放功能的轻量级网络(ARSN),与许多基于深度学习的方法相比,它的层和参数更少。此外,该网络中有特殊的残差块和跳跃连接用来进行残差缩放以及全局和局部残差学习。根据测试数据集结果,该网络在重建质量和运行速度上都达到了非常优异的性能。所提出的网络在性能、速度和硬件消耗方面均取得了良好的效果,具有较高的实用价值。