检索结果-内蒙古大学图书馆

neural network Analysis for the detection of glaucomatous damage

APPLIED SOFT computing 2014年 20卷 66-69页

作者： Yiu, K. F. Cedric Hong Kong Polytech Univ Dept Appl Math Kowloon Hong Kong Peoples R China

Glaucoma is a major cause of blindness and is prevalent among Asian populations. Therefore, early detection is of paramount importance in order to let patients have early treatments. One prominent indicator of glaucomatous damage is the Retinal Nerve Fiber Layer (RNFL) profile. In this paper, the performance of artificial neural network models in identifying RNFL profile of glaucoma suspect and glaucoma subjects is studied. RNFL thickness was measured using optical coherence tomography (Stratus OCT). Inputs to the neural network consisted of regional RNFL thickness measurements over 12 clock hours. Sensitivity and specificity for glaucoma detection will be compared by the area under the Receiver Operating Characteristic Curve (AROC). The results show that artificial neural network coupled with the OCT technology enhances the diagnostic accuracy of optical coherence tomography in differentiating glaucoma suspect and glaucoma from normal individuals. (C) 2013 Elsevier By. All rights reserved.

关键词： neural network Glaucoma optical coherence tomography

来源：评论

学校读者我要写书评

暂无评论

Escherichia coli bacteria detection by using graphene-based biosensor

引用

IET NANOBIOTECHNOLOGY 2015年第5期9卷 273-279页

作者： Akbari, Elnaz Buntat, Zolkafle Afroozeh, Abdolkarim Zeinalinezhad, Alireza Nikoukar, Ali Univ Teknol Malaysia Inst High Voltage & High Current Fac Elect Engn Johor Baharu 81310 Malaysia Islamic Azad Univ Jahrom Branch Young Researchers & Elite Club Jahrom Iran Dept Gen Fars Prov Educ Shiraz Iran Islamic Azad Univ Anar Branch Dept Chem Anar Iran Univ Teknol Malaysia Fac Comp Johor Baharu 81310 Malaysia

Graphene is an allotrope of carbon with two-dimensional (2D) monolayer honeycombs. A larger detection area and higher sensitivity can be provided by graphene-based nanosenor because of its 2D structure. In addition, owing to its special characteristics, including electrical, optical and physical properties, graphene is known as a more suitable candidate compared to other materials used in the sensor application. A novel model employing a field-effect transistor structure using graphene is proposed and the current-voltage (I-V) characteristics of graphene are employed to model the sensing mechanism. This biosensor can detect Escherichia coli (E. coli) bacteria, providing high levels of sensitivity. It is observed that the graphene device experiences a drastic increase in conductance when exposed to E. coli bacteria at 0-10(5) cfu/ml concentration. The simple, fast response and high sensitivity of this nanoelectronic biosensor make it a suitable device in screening and functional studies of antibacterial drugs and an ideal high-throughput platform which can detect any pathogenic bacteria. Artificial neural network and support vector regression algorithms have also been used to provide other models for the I-V characteristic. A satisfactory agreement has been presented by comparison between the proposed models with the experimental data.

关键词： biosensors nanosensors microorganisms drugs neural nets support vector machines regression analysis medical computing 2D monolayer honeycombs 2D nanosensor structure antibacterial drug screening artificial neural network bacteria detection biosensor sensitivity level biosensor-based bacterial detection biosensor-detected E coli bacteria biosensor-detected Escherichia coli carbon allotrope E coli detection Escherichia coli detection field-effect transistor structure graphene current-voltage characteristics graphene device conductance graphene I-V characteristics graphene-based biosensor graphene-based nanosenor ideal high-throughput bacterial detection platform nanoelectronic biosensor sensitivity nanosensor electrical properties nanosensor optical properties nanosensor physical properties nanosensor sensitivity level nanosensor-provided detection area nanosensor-provided sensitivity pathogenic bacteria-detecting biosensor sensing mechanism modeling special nanosensor characteristics support vector regression algorithms two-dimensional monolayer honeycombs

来源：评论

学校读者我要写书评

暂无评论

Study on the Prediction Model Based on a Portable Soil TN Detector

Study on the Prediction Model Based on a Portable Soil TN De...

引用

The 9th International Conference on Computer and computing Technologies in Agriculture (CCTA 2015)

作者： Xiaofei An Guangwei Wu Jianjun Dong Jianhua Guo Zhijun Meng Beijing Research Center for Intelligent Agricultural Equipment National Research Center of Intelligent Equipment for Agriculture

ISBN: (纸本)9783319483535

As the development of precision agriculture, it is necessary to obtain soil total nitrogen(TN) content and other element parametersWith the NIRS technology, a soil detector for soil total nitrogen content was developedIt included two part: optical part and control partThe detector took each lamp-house connected with the incidence of Y type optical fiber in turn by a manual rotation, The different wavelength lamp-house signal was transferred to the surface of soil by the input fibreThe re fl ected signal would be converted by photoelectric sensor, the optical signal was converted to electrical signalAfter the power circuit, amplier circuit, and AD convert circuit, the electrical signal was processed by MCUFinally, the result of soil total nitrogen content could be displayed on LCDWith the forty-eight apple orchard soil samples of Beijing surburb, the predicted models were established by seven different methods(MLR, PLSR, SVM, BPNN, GA + BPNN, GA + SVM and PSO + SVM)The model established by genetic algorithm(GA) optimizing BP neural network was optimal, with R C of 0.94, R V of 0.78, RMSEC and RMSEP of 0.037 and *** results showed that the soil total nitrogen content detector had a stable performanceThe established model had perfect accuracy and strong robustness.

关键词： NIR Soil parameter Modeling method Soil sensor Prediction models Model Laws detector total nitrogen electrical signal Soil Support Vector network control section Gallium NOC2L gene soil sampling precision agriculture LIQUID CRYSTAL DISPLAY

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of offline character recognition using neural network approaches

引用

2014 National Conference on Emerging Trends in computing and Communication, ETCC 2014

作者： Chanda, Pramit Brata Datta, Santanu Mukherjee, Soham Goswami, Subhamoy Bisi, Sritama Computer Science and Engineering Kalyani Government Engineering College Kalyani West Bengal India Computer Science and Engineering Academy of Technology Adisaptagram West Bengal India

ISBN: (纸本)9788132218166

optical Character Recognition is a type of document image analysis where scanned digital image that contains either machine printed or handwritten script given as input into the software and translating it into an editable machine readable digital text format. Today, optical character recognition (OCR) becomes an important area in pattern recognition and image processing. Today neural networks are mostly used for Pattern Recognition task. The paper describes the behaviours of different models of neural network used in OCR. OCR is widespread use of neural network. We have considered parameters like number of Hidden Layer, size of Hidden Layer and epochs. We have used Multilayer Feed Forward network with Back propagation. Here we have done comparative study on character recognition using different neural network algorithm. The results showed that the MLP networks trained by the error back propagation algorithm are more superior in calculating recognition accuracy and also memory usage. The result indicates that the back propagation network provides better recognition accuracy of more than 80 % of for these English characters. © 2014 Springer.

关键词： optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Predicting the performance measures of a message-passing multiprocessor architecture using artificial neural networks

引用

neural computing & APPLICATIONS 2013年第7-8期23卷 2481-2491页

作者： Zayid, Elrasheed Ismail Mohommoud Akay, Mehmet Fatih Cukurova Univ Dept Elect Elect Engn TR-01330 Adana Turkey Cukurova Univ Dept Comp Engn TR-01330 Adana Turkey

In this paper, we develop multi-layer feed-forward artificial neural network (MFANN) models for predicting the performance measures of a message-passing multiprocessor architecture interconnected by the simultaneous optical multiprocessor exchange bus (SOME-Bus), which is a fiber-optic interconnection network. OPNET Modeler is used to simulate the SOME-Bus multiprocessor architecture and to create the training and testing datasets. The performance of the MFANN prediction models is evaluated using standard error of estimate (SEE) and multiple correlation coefficient (R). Also, the results of the MFANN models are compared with the ones obtained by generalized regression neural network (GRNN), support vector regression (SVR), and multiple linear regression (MLR). It is shown that MFANN models perform better (i.e., lower SEE and higher R) than GRNN-based, SVR-based, and MLR-based models for predicting the performance measures of a message-passing multiprocessor architecture.

关键词： Artificial neural networks Multiprocessor architectures Message passing Performance evaluation

来源：评论

学校读者我要写书评

暂无评论

Confusion network Based Recurrent neural network Language Modeling for Chinese OCR Error Detection

Confusion Network Based Recurrent Neural Network Language Mo...

引用

International Conference on Pattern Recognition

作者： Jinying Chen Yue Wu Huaigu Cao Prem Natarajan Department of Speech Language and Multimedia Raytheon BBN Technologies Cambridge MA USA Information Sciences Institute University of Southern California Marina del Rey California USA

This paper presents a new framework for OCR error detection, which uses a conditional random field model to combine rich features from multiple sources, including confusion networks (c-nets), lexical local context and recurrent neural network language model (RNNLM). We propose a novel, efficient method for computing character-level c-net based RNNLM scores by using dynamic programming and c-net partial unfolding. Our experiments show that our error detection model has consistent observable improvements over a high baseline employed by our current OCR demo system, as measured by average precision and detection error trade-off curve on two test sets of Chinese image documents. Both linguistic and recognition features contribute to the high performance, with the former especially informative. In addition, we show that the new feature we proposed, the c-net RNNLM feature, plays a remarkable beneficial role in improving error detection rate. These results suggest that applications on top of image text recognition can benefit substantially from a hybrid strategy that combines techniques from optical character recognition and natural language processing.

关键词： optical character recognition software Feature extraction Hidden Markov models Lattices Speech recognition Pragmatics Character recognition

来源：评论

学校读者我要写书评

暂无评论

Table of contents

Table of contents

引用

Global Summit on Computer & Information Technology (GSCIT)

The following topics are dealt with: cellular automata model; sputum color image segmentation; unsupervised Hopfield neural network classifier; wireless sensor networks; miniaturized tag antenna RFID; WDM all-optical networks; anticultism social education media system; frequency domain periodic noise detection and removal; cache consistency; adaptive page-server database systems; semiautomatic cleaning lexical ontology; video surveillance system; optical flow; stereo vision; software development model selection; medical image crypto-compression; circuit switched networks; DNS-based load balancing; geographically distributed Web server systems; routing protocols; MANETs; split ring resonators; pool based key predistribution scheme; fingerprint recognition; instruction-level parallelism; product feature extraction; electronic implantable devices; radio propagation; WSN; CMT-SCTP; elliptic curve digital signature algorithm; pedestrian detection; medical image watermarking; medical image encryption; mobile device user interface for visually impaired users; hybrid renewable energy; wind systems; pervasive computing; classroom environment; AODV protocol; hash-based message authentication algorithm; smart energy management; fractional integral equation; stereoscopic mobile natural feature tracking; human-machine voice interface based standard Arabic; Landsat images; urban change detection; virtual environment stereo image capture; Web-based decision support system; handwritten object recognition; regularized logistic regression; and feedforward neural networks.

关键词： Predictive models Feature extraction Mobile computing Wireless sensor networks Integrated circuit modeling Load modeling Image segmentation

来源：评论

学校读者我要写书评

暂无评论

neural network rule extraction by a new ensemble concept and its theoretical and historical background: A review

Neural network rule extraction by a new ensemble concept and...

引用

作者： Hayashi, Yoichi Department of Computer Science Meiji University Tama-ku Kawasaki 214-8571 Japan

This paper presents theoretical and historical backgrounds related to neural network rule extraction. It also investigates approaches for neural network rule extraction by ensemble concepts. Bologna pointed out that although many authors had generated comprehensive models from individual networks, much less work had been done to explain ensembles of neural networks. This paper carefully surveyed the previous work on rule extraction from neural network ensembles since 1988. We are aware of three major research groups i.e., Bologna' group, Zhou' group and Hayashi' group. The reason of these situations is obvious. Since the structures of previous neural network ensembles were quite complicated, the research on the efficient rule extraction algorithm from neural network ensembles was few although their learning capability was extremely high. Thus, these issues make rule extraction algorithm for neural network ensemble difficult task. However, there is a practical need for new ideas for neural network ensembles in order to realize the extremely high-performance needs of various rule extraction problems in real life. This paper successively explain nature of artificial neural networks, origin of neural network rule extraction, incorporating fuzziness in neural network rule extraction, theoretical foundation of neural network rule extraction, computational complexity of neural network rule extraction, neuro-fuzzy hybridization, previous rule extraction from neural network ensembles and difficulties of previous neural network ensembles. Next, this paper address three principles of proposed neural network rule extraction: to increase recognition rates, to extract rules from neural network ensembles, and to minimize the use of computing resources. We also propose an ensemble-recursive-rule extraction (E-Re-RX) by two or three standard backpropagation to train multi-layer perceptrons (MLPs), which enabled extremely high recognition accuracy and the extraction of comprehensible

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Cognitive computing Systems: Algorithms and Applications for networks of Neurosynaptic Cores

Cognitive Computing Systems: Algorithms and Applications for...

引用

International Joint Conference on neural networks (IJCNN)

作者： Esser, Steve K. Andreopoulos, Alexander Appuswamy, Rathinakumar Datta, Pallab Barch, Davis Amir, Arnon Arthur, John Cassidy, Andrew Flickner, Myron Merolla, Paul Chandra, Shyamal Basilico, Nicola Carpin, Stefano Zimmerman, Tom Zee, Frank Alvarez-Icaza, Rodrigo Kusnitz, Jeffrey A. Wong, Theodore M. Risk, William P. McQuinn, Emmett Nayak, Tapan K. Singh, Raghavendra Modha, Dharmendra S. IBM Res Almaden Cognit Comp Grp San Jose CA 95120 USA IBM Res New Delhi India Univ Calif Merced Sch Engn Merced CA USA IBM Res Almaden San Jose CA USA

ISBN: (纸本)9781467361293;9781467361286

Marching along the DARPA SyNAPSE roadmap, IBM unveils a trilogy of innovations towards the TrueNorth cognitive computing system inspired by the brain's function and efficiency. The non-von Neumann nature of the TrueNorth architecture necessitates a novel approach to efficient system design. To this end, we have developed a set of abstractions, algorithms, and applications that are natively efficient for TrueNorth. First, we developed repeatedly-used abstractions that span neural codes (such as binary, rate, population, and time-to-spike), long-range connectivity, and short-range connectivity. Second, we implemented ten algorithms that include convolution networks, spectral content estimators, liquid state machines, restricted Boltzmann machines, hidden Markov models, looming detection, temporal pattern matching, and various classifiers. Third, we demonstrate seven applications that include speaker recognition, music composer recognition, digit recognition, sequence prediction, collision avoidance, optical flow, and eye detection. Our results showcase the parallelism, versatility, rich connectivity, spatio-temporality, and multi-modality of the TrueNorth architecture as well as compositionality of the corelet programming paradigm and the flexibility of the underlying neuron model.

关键词： Boltzmann machines brain cognition collision avoidance convolution hidden Markov models image sequences neural chips pattern matching speaker recognition spectral analysis

来源：评论

学校读者我要写书评

暂无评论

Using a multi-port architecture of neural-net associative memory based on the equivalency paradigm for parallel cluster image analysis and self-learning

Using a multi-port architecture of neural-net associative me...

引用

Conference on Intelligent Robots and Computer Vision XXX - Algorithms and Techniques

作者： Krasilenko, Vladimir G. Lazarev, Alexander A. Grabovlyak, Sveta K. Nikitovich, Diana V. Vinnitsa Social Econ Inst Vinnitsa Ukraine Vinnitsa Natl Tech Univ Vinnitsa Ukraine

ISBN: (纸本)9780819494351

We consider equivalency models, including matrix-matrix and matrix-tensor and with the dual adaptive-weighted correlation, multi-port neural-net auto-associative and hetero-associative memory (MP NN AAM and HAP), which are equivalency paradigm and the theoretical basis of our work. We make a brief overview of the possible implementations of the MP NN AAM and of their architectures proposed and investigated earlier by us. The main base unit of such architectures is a matrix-matrix or matrix-tensor equivalentor. We show that the MP NN AAM based on the equivalency paradigm and optoelectronic architectures with space-time integration and parallel-serial 2D images processing have advantages such as increased memory capacity (more than ten times of the number of neurons!), high performance in different modes (10(10) - 10(12) connections per second!) And the ability to process, store and associatively recognize highly correlated images. Next, we show that with minor modifications, such MP NN AAM can be successfully used for high-performance parallel clustering processing of images. We show simulation results of using these modifications for clustering and learning models and algorithms for cluster analysis of specific images and divide them into categories of the array. Show example of a cluster division of 32 images (40x32 pixels) letters and graphics for 12 clusters with simultaneous formation of the output-weighted space allocated images for each cluster. We discuss algorithms for learning and self-learning in such structures and their comparative evaluations based on Mathcad simulations are made. It is shown that, unlike the traditional Kohonen self-organizing maps, time of learning in the proposed structures of multi-port neuronet classifier/clusterizer (MP NN C) on the basis of equivalency paradigm, due to their multi-port, decreases by orders and can be, in some cases, just a few epochs. Estimates show that in the test clustering of 32 1280-element images into 12 gr

关键词： multi-port neural network associative memory optical pattern recognition matrix parallel computing equivalently paradigm equivalence and nonequivalence matrix operations cluster analyses

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：