2016 International Joint Conference on Neural Networks (IJCNN)最新文献_第10页

An expert disambiguation method based on attributed graph clustering 基于属性图聚类的专家消歧方法

2016 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2016-07-24 DOI: 10.1109/IJCNN.2016.7727706

Shengxiang Gao, Zhuo Wang, Zhengtao Yu, Jin Jiang, Lin Wu

引用次数: 0

Offline Arabic Handwritten recognition system with dropout applied in Deep networks based-SVMs 基于支持向量机的深度网络中带有dropout的离线阿拉伯手写识别系统

2016 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2016-07-24 DOI: 10.1109/IJCNN.2016.7727613

M. Elleuch, Raouia Mokni, M. Kherallah

{"title":"Offline Arabic Handwritten recognition system with dropout applied in Deep networks based-SVMs","authors":"M. Elleuch, Raouia Mokni, M. Kherallah","doi":"10.1109/IJCNN.2016.7727613","DOIUrl":"https://doi.org/10.1109/IJCNN.2016.7727613","url":null,"abstract":"As a machine learning algorithms, deep learning algorithms developed in recent years, have been successfully practiced in many fields of computer vision, like face recognition, object detection and image classification. These Deep algorithms look for drawing out a very performing representation of the data, among which image and speech, through multi-layers in a deep hierarchical structure. In this study, a deep learning model based on Support Vector Machine (SVM) named Deep SVM (DSVM) is represented. We applied the dropout technique on the Deep SVM (DSVM). It is worth noting that this model has an inherent capacity to choose data points crucial to classify good generalization capacities. The deep SVM is built by a stack of SVMs permitting to extracting/learning automatically features from the raw images and to realize classification, too. We chose and tested the Multi-class Support Vector Machine with an RBF kernel, as non-linear discriminative features for classification, on Handwritten Arabic Characters Database (HACDB). Further to these advantages, our model is safeguarded against over-fitting because of strong performance of dropout. Simulation outcomes prove the efficiency of the suggested model.","PeriodicalId":109405,"journal":{"name":"2016 International Joint Conference on Neural Networks (IJCNN)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115640944","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 17

Using Convolutional Neural Network for edge detection in musculoskeletal ultrasound images 基于卷积神经网络的肌肉骨骼超声图像边缘检测

2016 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2016-07-24 DOI: 10.1109/IJCNN.2016.7727805

S. I. Jabbar, C. Day, Nicholas Heinz, E. Chadwick

{"title":"Using Convolutional Neural Network for edge detection in musculoskeletal ultrasound images","authors":"S. I. Jabbar, C. Day, Nicholas Heinz, E. Chadwick","doi":"10.1109/IJCNN.2016.7727805","DOIUrl":"https://doi.org/10.1109/IJCNN.2016.7727805","url":null,"abstract":"Fast and accurate segmentation of musculoskeletal ultrasound images is an on-going challenge. Two principal factors make this task difficult: firstly, the presence of speckle noise arising from the interference that accompanies all coherent imaging approaches; secondly, the sometimes subtle interaction between musculoskeletal components that leads to non-uniformity of the image intensity. Our work presents an investigation of the potential of Convolutional Neural Networks (CNNs) to address both of these problems. CNNs are an effective tool that has previously been used in image processing of several biomedical imaging modalities. However, there is little published material addressing the processing of musculoskeletal ultrasound images. In our work we explore the effectiveness of CNNs when trained to act as a pre-segmentation pixel classifier that determines whether a pixel is an edge or non-edge pixel. Our CNNs are trained using two different ground truth interpretations. The first one uses an automatic Canny edge detector to provide the ground truth image; the second ground truth was obtained using the same image marked-up by an expert anatomist. In this initial study the CNNs have been trained using half of the prepared data from one image, using the other half for testing; validation was also carried out using three unseen ultrasound images. CNN performance was assessed using Mathew's Correlation Coefficient, Sensitivity, Specificity and Accuracy. The results show that CNN performance when using expert ground truth image is better than using Canny ground truth image. Our technique is promising and has the potential to speed-up the image processing pipeline using appropriately trained CNNs.","PeriodicalId":109405,"journal":{"name":"2016 International Joint Conference on Neural Networks (IJCNN)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121028936","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 25

Using a hybrid of fuzzy theory and neural network filter for image dehazing applications 将模糊理论与神经网络滤波相结合，应用于图像去雾

2016 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2016-07-24 DOI: 10.1109/IJCNN.2016.7727267

Jyun-Guo Wang, S. Tai, Chin-Ling Lee, Cheng‐Jian Lin, Tsung-Hung Lin

引用次数: 1

A rule extraction study on a neural network trained by deep learning 基于深度学习训练的神经网络规则提取研究

2016 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2016-07-24 DOI: 10.1109/IJCNN.2016.7727264

G. Bologna, Y. Hayashi

引用次数: 14

Sparse Least squares support vector regression via Multiresponse Sparse Regression 基于多响应稀疏回归的稀疏最小二乘支持向量回归

2016 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2016-07-24 DOI: 10.1109/IJCNN.2016.7727610

David Clifte da S. Vieira, A. Neto, Antonio Wendell De Oliveira Rodrigues

{"title":"Sparse Least squares support vector regression via Multiresponse Sparse Regression","authors":"David Clifte da S. Vieira, A. Neto, Antonio Wendell De Oliveira Rodrigues","doi":"10.1109/IJCNN.2016.7727610","DOIUrl":"https://doi.org/10.1109/IJCNN.2016.7727610","url":null,"abstract":"Least square support vector machines (LSSVMs) are an alternative to SVMs because the training process for LSSVMs is based on solving a linear equation system while the training process for SVMs relies on solving a quadratic programming optimization problem. When LSSVMs are dealing with regression tasks, we refer to them as Least square support vector regressors (LSSVRs). Despite solving a linear system is easier than solving a quadratic programming optimization problem, the absence of sparsity in the Lagrange multiplier vector obtained after training a LSSVR model is an important drawback. To overcome this drawback, we present a new approach for sparse LSSVR called Optimally Pruned LSSVR (OP-LSSVR). Our proposal relies on a ranking method, named Multiresponse Sparse Regression (MRSR), which is used to sort the patterns in terms of relevance. After doing so, the leave-one-out (LOO) criterion is also used in order to select an appropriate number of support vectors. Our proposal was inspired by a recent methodology called OP-ELM, which prunes neurons in the hidden layer of Extreme Learning Machines. Therefore, in this paper, we put LSSVR and MRSR to work together in order to achieve sparse regressors while we achieved equivalent (or even superior) performance for real-world regression tasks.","PeriodicalId":109405,"journal":{"name":"2016 International Joint Conference on Neural Networks (IJCNN)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123741594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Sparsely connected autoencoder 稀疏连接的自动编码器

2016 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2016-07-24 DOI: 10.1109/IJCNN.2016.7727437

Kavya Gupta, A. Majumdar

引用次数: 8

Event identification and assertion from social media using auto-extendable knowledge base 使用自动扩展知识库从社交媒体识别和断言事件

2016 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2016-07-24 DOI: 10.1109/IJCNN.2016.7727781

A. Suliman, Khaled Al Kaabi, Di Wang, Ahmad Al-Rubaie, Ahmed Al Dhanhani, D. Ruta, John Davies, Sandra Stincic

引用次数: 9

An energy efficient decoding scheme for nonlinear MIMO-OFDM network using reservoir computing 一种基于储层计算的非线性MIMO-OFDM网络节能解码方案

2016 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2016-07-24 DOI: 10.1109/IJCNN.2016.7727329

S. Mosleh, Cenk Sahin, Lingjia Liu, R. Zheng, Y. Yi

{"title":"An energy efficient decoding scheme for nonlinear MIMO-OFDM network using reservoir computing","authors":"S. Mosleh, Cenk Sahin, Lingjia Liu, R. Zheng, Y. Yi","doi":"10.1109/IJCNN.2016.7727329","DOIUrl":"https://doi.org/10.1109/IJCNN.2016.7727329","url":null,"abstract":"Reservoir computing (RC) is attracting widespread attention in several signal processing domains owing to its nonlinear stateful computation. It deals particularly well with time-series prediction tasks and reduces training complexity over recurrent neural networks. It is also suitable for hardware implementation whereby device physics are utilized in performing data processing. In this paper, the RC concept is applied to modeling a Multiple-Input Multiple-Output Orthogonal Frequency Division Multiplexing (MIMO-OFDM) system. Due to the harsh propagation environment, the transmitted signal undergoes severe distortion that must be compensated for at the receiver. The nonlinear distortion introduced by the power amplifier at the transmitter further complicates this process. An effective channel estimation scheme is therefore required. In this paper, we introduce a MIMO-OFDM channel estimation scheme utilizing Echo State Network (ESN). Echo State Networks are powerful recurrent neural networks that can predict time-series very well. They acts as a black-box for system modeling purposes and models nonlinear dynamic systems efficiently. Simulation results for the bit error rate of the nonlinear MIMO-OFDM system show that the introduced channel estimator outperforms commonly used channel estimation schemes.","PeriodicalId":109405,"journal":{"name":"2016 International Joint Conference on Neural Networks (IJCNN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122535976","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 14

Nonlinear non-negative matrix factorization using deep learning 基于深度学习的非线性非负矩阵分解

2016 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2016-07-24 DOI: 10.1109/IJCNN.2016.7727237

Hui Zhang, Huaping Liu, Rui Song, F. Sun

引用次数: 7