电子鼻模式识别算法的比较研究

文中比较了k-近邻法、线性判别分析、反向传播人工神经网络、概率神经网、学习向量量化以及自组织映射6种电子鼻模式识别算法的分类能力.采用了1个定量指标(识别精度)和4个定性指标(运算速度、训练速度、内存容量、抗干扰能力)对不同算法进行了系统比较.研究表明基于神经网络的模式识别算法比基于统计理论的模式识别算法具有更高的识别精度.如果同时考虑定性指标,当训练速度要求不高时,宜采用学习向量量化算法;能满足内存需求前提下,优先推荐采用概率神经网算法.对于选择性高的信号,采用线性判别分析可以达到最佳效果.     

结合深度学习与相关反馈的遥感图像检索

目的 针对基于内容的图像检索存在低层视觉特征与用户对图像理解的高层语义不一致、图像检索的精度较低以及传统的分类方法准确度低等问题，提出一种基于卷积神经网络和相关反馈支持向量机的遥感图像检索方法。方法 通过对比度受限直方图均衡化算法对遥感图像进行预处理，限制遥感图像噪声的放大，采用自学习能力良好的卷积神经网络对遥感图像进行多层神经网络的监督学习提取丰富的图像特征，并将支持向量机作为基分类器，根据测试样本数据到分类超平面的距离进行排序得到检索结果，最后采用相关反馈策略对检索结果进行重新调整。结果 在UC Merced Land-Use遥感图像数据集上进行图像检索实验，在mAP（mean average precision）精度指标上，当检索返回图像数为100时，本文方法比LSH（locality sensitive Hashing）方法提高了29.4%，比DSH（density sensitive Hashing）方法提高了37.2%，比EMR（efficient manifold ranking）方法提高了68.8%，比未添加反馈和训练集筛选的SVM（support vector machine）方法提高了3.5%，对于平均检索速度，本文方法比对比方法中mAP精度最高的方法提高了4倍，针对复杂的遥感图像数据，本文方法的检索效果较其他方法表现出色。结论 本文提出了一种以距离评价标准为核心的反馈策略，以提高检索精度，并采用多距离结合的Top-k排序方法合理筛选训练集，以提高检索速度，本文方法可以广泛应用于人脸识别和目标跟踪等领域，对提升检索性能具有重要意义。     

基于Oracle的地震前兆数据库表结构对比

目前,我国地震前兆数据库采用 Oracle 数据库管理系统,每天每种采样类型观测值存储在 Clob 类型字段的一个纪录中.对比了将观测数据存储在 Clob 和 Blob 类型字段中数据的存取速度,发现将观测数据存储在 Blob 类型字段中具有更高的效率.主要有两个原因:一是利用 API 函数 Copymemory 在内存里实现数据传输,二进制数据比字符串型数据存取快;二是数据存储在 Blob 类型中占用更少的空间,网络传输快.     

一种优化的网络爬虫的设计与实现

网络爬虫是搜索引擎的重要组成部分,它在搜索引擎中负责网络信息的采集。详细介绍了Web_Crawler,一种优化的网络爬虫的设计和实现,包括系统框架、主要模块、多线程工作和数据缓冲池的转存技术。Web-Crawler主要从多线程并行下载提高了速度,并利用数据缓冲池转存技术在实现快速检索的同时减少了存储空间需求这两方面来优化网络爬虫。     

Minimal Structure of Self-Organizing HCMAC Neural Network Classifier

The authors previously proposed a self-organizing Hierarchical Cerebellar Model Articulation Controller (HCMAC) neural network containing a hierarchical GCMAC neural network and a self-organizing input space module to solve high-dimensional pattern classification problems. This novel neural network exhibits fast learning, a low memory requirement, automatic memory parameter determination and highly accurate high-dimensional pattern classification. However, the original architecture needs to be hierarchically expanded using a full binary tree topology to solve pattern classification problems according to the dimension of the input vectors. This approach creates many redundant GCMAC nodes when the dimension of the input vectors in the pattern classification problem does not exactly match that in the self-organizing HCMAC neural network. These redundant GCMAC nodes waste memory units and degrade the learning performance of a self-organizing HCMAC neural network. Therefore, this study presents a minimal structure of self-organizing HCMAC (MHCMAC) neural network with the same dimension of input vectors as the pattern classification problem. Additionally, this study compares the learning performance of this novel learning structure with those of the BP neural network,support vector machine (SVM), and original self-organizing HCMAC neural network in terms of ten benchmark pattern classification data sets from the UCI machine learning repository. In particular, the experimental results reveal that the self-organizing MHCMAC neural network handles high-dimensional pattern classification problems better than the BP, SVM or the original self-organizing HCMAC neural network. Moreover, the proposed self-organizing MHCMAC neural network significantly reduces the memory requirement of the original self-organizing HCMAC neural network, and has a high training speed and higher pattern classification accuracy than the original self-organizing HCMAC neural network in most testing benchmark data sets. The experimental results also show that the MHCMAC neural network learns continuous function well and is suitable for Web page classification.     

A comparison of a novel neural spell checker and standard spell checking algorithms

In this paper, we propose a simple and flexible spell checker using efficient associative matching in the AURA modular neural system. Our approach aims to provide a pre-processor for an information retrieval (IR) system allowing the user's query to be checked against a lexicon and any spelling errors corrected, to prevent wasted searching. IR searching is computationally intensive so much so that if we can prevent futile searches we can minimise computational cost. We evaluate our approach against several commonly used spell checking techniques for memory-use, retrieval speed and recall accuracy. The proposed methodology has low memory use, high speed for word presence checking, reasonable speed for spell checking and a high recall rate.     

二值网络的分阶段残差二值化算法

二值网络在速度、能耗、内存占用等方面优势明显，但会对深度网络模型造成较大的精度损失.为了解决上述问题，本文提出了二值网络的"分阶段残差二值化"优化算法，以得到精度更好的二值神经网络模型.本文将随机量化的方法与XNOR-net相结合，提出了两种改进算法"带有近似因子的随机权重二值化"和"确定权重二值化"，以及一种全新的"分阶段残差二值化"的BNN训练优化算法，以得到接近全精度神经网络的识别准确率.实验表明，本文提出的"分阶段残差二值化"算法能够有效提升二值模型的训练精度，而且不会增加相关网络在测试过程中的计算量，从而保持了二值网络速度快、空间小、能耗低的优势.     

Dynamic arrays for fast, efficient, data manipulation during image analysis: a new software tool for exploratory data analysis.

Memory reallocation is used to construct a run-time data structure for fast/efficient storage of information during collection and analysis. The data structure presented uses dynamic memory but does not require the use of pointers to link nodes of information together. It allows for simple and efficient access to data via array indexing rather than through the use of lists or tree structures and it provides flexibility for competing storage requirements that are determined dynamically. The data structure is developed in the C programming language and a suite of ANSI standard C subroutines that make up a run-time data structure management system is provided.     

基于深度哈希网络的车型识别方法

针对车型识别任务的特点,设计了一种基于深度哈希网络的车型识别方法,实现了在类间差异不明显、样本量较少的情况下进行车型检索和分类。对数据增广方法进行研究,针对车型数据集的特点,提出了适用于车型识别的数据增广方法,有效提升了小样本车型识别的准确率。深度哈希网络采用改进的HashNet网络来快速学习车辆的二值特征表达,针对深度哈希网络使用全连接层导致参数过多的问题,提出了HashNet-GAP网络,以全局平均池化层替换了HashNet中的部分全连接层。相对于HashNet网络,大幅度减少了参数数量,提升了前向计算速度和网络性能。实验结果表明,该车型识别方法能够对类间差距很小的不同车型进行有效识别,在小样本数据集上取得80.0%的Top1准确率,并且能够显著降低模型的存储消耗和内存消耗。     

基于Flink的海量医学图像检索系统设计与实现

医学图像检索是有效利用医学资源的基础，而医学图像的海量性和增量性为图像检索带来了新的挑战和要求。为了提高医学图像检索过程的效率，设计并实现一种基于Flink的海量医学图像检索系统。首先，系统通过Web应用作为用户操作入口，在后端搭建数据平台和业务集群；其次，系统通过HBase对医学图像数据进行分布式存储，利用深度卷积神经网络模型提取医学图像特征；然后，将所提取的医学图像特征数据进行乘积量化编码，并通过HBase进行存储；最后，通过基于Flink的内存计算对接Kafka进行实时图像检索，以及对批量导入图像的特征索引编码。系统在4个节点的服务器上部署分布式集群，使用真实医学图像数据集进行测试，通过在MapReduce和Spark两种不同技术模块下的对比实验表明本系统具有更好的检索效率表现。     

A task decomposition approach to using neural networks for the interpretation of bioprocess data

During the course of most bioproccss development programs a large amount of process data is generated and stored. However, while these data records contain important information about the process, little or no use is made of this asset. The work described here uses a neural network approach to “learn” to recognize patterns in fermentation data. Neural networks, trained using fermentation data generated from previous runs, are then used to interpret data from a new fermentation. We propose a task decomposition approach to the problem. The approach involves decomposing the problem of bioprocess data interpretation into specific tasks. Separate neural networks are trained to perform each of these tasks which include fault diagnosis, growth phase determination and metabolic condition evaluation. These trained networks are combined into a multiple neural network hierarchy for the diagnosis of bioprocess data. The methodology is evaluated using experimental data from fed-batch, Saccharomyces cerevisiae fermentations. We argue that the task decomposition approach taken here allows for each network to develop a task specific representation and that this in turn, can lead to network activations and connection weights that are more clearly interpretable. These expert networks can now be pruned to remove nodes that do not contribute significant additional information.     

Associative Neural Network

An associative neural network (ASNN) is a combination of an ensemble of the feed-forward neural networks and the K-nearest neighbor technique. The introduced network uses correlation between ensemble responses as a measure of distance among the analyzed cases for the nearest neighbor technique and provides an improved prediction by the bias correction of the neural network ensemble both for function approximation and classification. Actually, the proposed method corrects a bias of a global model for a considered data case by analyzing the biases of its nearest neighbors determined in the space of calculated models. An associative neural network has a memory that can coincide with the training set. If new data become available the network can provide a reasonable approximation of such data without a need to retrain the neural network ensemble. Applications of ASNN for prediction of lipophilicity of chemical compounds and classification of UCI letter and satellite data set are presented. The developed algorithm is available on-line at http://www.virtuallaboratory.org/lab/asnn.     

A self-organizing HCMAC neural-network classifier

This paper presents a self-organizing hierarchical cerebellar model arithmetic computer (HCMAC) neural-network classifier, which contains a self-organizing input space module and an HCMAC neural network. The conventional CMAC can be viewed as a basis function network (BFN) with supervised learning, and performs well in terms of its fast learning speed and local generalization capability for approximating nonlinear functions. However, the conventional CMAC has an enormous memory requirement for resolving high-dimensional classification problems, and its performance heavily depends on the approach of input space quantization. To solve these problems, this paper presents a novel supervised HCMAC neural network capable of resolving high-dimensional classification problems well. Also, in order to reduce what is often trial-and-error parameter searching for constructing memory allocation automatically, proposed herein is a self-organizing input space module that uses Shannon's entropy measure and the golden-section search method to appropriately determine the input space quantization according to the various distributions of training data sets. Experimental results indicate that the self-organizing HCMAC indeed has a fast learning ability and low memory requirement. It is a better performing network than the conventional CMAC for resolving high-dimensional classification problems. Furthermore, the self-organizing HCMAC classifier has a better classification ability than other compared classifiers.     

Associative Memory Design via Path Embedding into a Graph

A graph theoretical procedure for storing a set of n-dimensional binary vectors as asymptotically stable equilibrium points of a discrete Hopfield neural network is presented. The method gives an auto-associative memory which stores an arbitrary memory set completely. Spurious memories might occur only in a small neighborhood of the original memory vectors, so cause small errors.     

TexNN: Fast Texture Encoding Using Neural Networks

We present a novel deep learning‐based method for fast encoding of textures into current texture compression formats. Our approach uses state‐of‐the‐art neural network methods to compute the appropriate encoding configurations for fast compression. A key bottleneck in the current encoding algorithms is the search step, and we reduce that computation to a classification problem. We use a trained neural network approximation to quickly compute the encoding configuration for a given texture. We have evaluated our approach for compressing the textures for the widely used adaptive scalable texture compression format and evaluate the performance for different block sizes corresponding to 4 × 4, 6 × 6 and 8 × 8. Overall, our method (TexNN) speeds up the encoding computation up to an order of magnitude compared to prior compression algorithms with very little or no loss in the visual quality.     

An Adaptive Opto-electronic Neural Network for Associative Pattern Retrieval

A novel adaptive trinary neural network model is proposed for associative pattern retrieval from incomplete data. Systematic analysis of the convergence mechanism for the character recognition problem is provided to illustrate the derivation of this novel adaptive thresholding scheme. The adaptive scheme with trinary input representation outperforms other associative retrieval schemes in terms of convergence and storage capacity. The inherent parallelism of this neural network architecture is exploited for a parallel optical implementation. The tremendous speed and free-space interconnection capability of optics results in a very efficient real-time character recognition system. The adaptive threshold scheme developed here may have far reaching implications for other neural networks in enhancing their learning and retrieval, speed, and accuracy.     

Self-Tuning of a Neural Network Controller with an Integral Estimate of Contradictions between the Commands of the Learning Algorithm and Memory

We propose an approach to organizing self-tuning for a controller based on an artificial neural network that uses information on the contradictions arising in the creation of the value for the control signal between accumulated memory of the neural network and the learning algorithm based on backpropagation. The activity of neural network memory is estimated as its reaction to changing the state of the control system. Self-tuning is done by controlling the learning rate coefficient with an integral controller in order to stabilize the integral criterion for estimating the contradictions. Based on this modeling, we show a conceptual possibility for the operation of the self-tuning system with constant tuning parameters in a wide range of changes of the control object’s dynamical properties.     

基于点对相似度的深度非松弛哈希算法

哈希学习能够在保持数据之间语义相似性的同时,将高维数据投影到低维的二值空间中以降低数据维度实现快速检索.传统的监督型哈希学习算法主要是将手工设计特征作为模型输入,通过分类和量化生成哈希码.手工设计特征缺乏自适应性且独立于量化过程使得检索的准确率不高.本文提出了一种基于点对相似度的深度非松弛哈希算法,在卷积神经网络的输出...     

Self-adaptation of mobile systems driven by the Common Variability Language

The execution context in which pervasive systems or mobile computing run changes continually. Hence, applications for these systems require support for self-adaptation to the continual context changes. Most of the approaches for self-adaptive systems implement a reconfiguration service that receives as input the list of all possible configurations and the plans to switch between them. In this paper we present an alternative approach for the automatic generation of application configurations and the reconfiguration plans at runtime. With our approach, the generated configurations are optimal as regards different criteria, such as functionality or resource consumption (e.g. battery or memory). This is achieved by: (1) modelling architectural variability at design-time using the Common Variability Language (CVL), and (2) using a genetic algorithm that finds nearly-optimal configurations at run-time using the information provided by the variability model. We also specify a case study and we use it to evaluate our approach, showing that it is efficient and suitable for devices with scarce resources.