检索结果-内蒙古大学图书馆

22nd International Conference on Pattern Recognition (ICPR)

作者： Wang, Meng Chen, Youbin Wang, Xingjun Tsinghua Univ Grad Sch Shenzhen Shenzhen 518057 Peoples R China

ISBN: (纸本)9781479952083

Handwritten Characters Recognition has long been a tough problem in pattern recognition and machine learning. Some special tasks, such as automatic check preprocessing, require Handwritten Chinese Legal Amounts recognition as a prerequisite. Since we expect to utilize machine instead of human to process bank checks, the recognition rate in such task must reach a relatively high rate. This paper proposes to use deep learning, auto-encoder as an effective approach for obtaining hierarchical representations of Isolated Handwritten Chinese Legal Amounts. Experiments show such representations are highly abstractive and can be used in character recognition. Meanwhile, a novel way by combining multiple Neural Networks in doing the work is proposed which proves to be able to improve the recognition rate significantly. This method reports a 0.64% error rate on a large test set over 10,000 samples and outperforms traditional methods using hand-crafted features and convolutional neural network committees (another deep learning model), narrowing the gap to human performance.

关键词： Chinese Legal Amount Isolated Character Recognition sparse auto-encoder Elastic Meshing Committee

来源：评论

学校读者我要写书评

暂无评论

SAE-RNN Deep Learning for RGB-D Based Object Recognition

SAE-RNN Deep Learning for RGB-D Based Object Recognition

引用

10th International Conference on Intelligent Computing (ICIC)

作者： Bai, Jing Wu, Yan Tongji Univ Coll Elect & Informat Engn Shanghai 201804 Peoples R China

ISBN: (纸本)9783319093338;9783319093321

RGB-D image is a multimodal data. Previous works have proved that using color and depth images together can dramatically increase the RGB-D based object recognition accuracy, but most of them either simply take all modalities as input, ignoring information about specific modalities, or train a first layer representation for each modality separately and concatenate them ignoring correlated modality information. In this paper, we use a variant of the sparse auto-encoder (SAE) which can specify how mode-sparse or mode-dense the features should be. A new deep learning network combining the variant SAE with the recursive neural networks (RNNs) was proposed. Through it, we got very discriminating features and obtained state of the art performance on a standard RGB-D object dataset.

关键词： RGB-D Based Object Recognition sparse auto-encoder Recursive Neural Networks Feature Extracting Deep Learning

来源：评论

学校读者我要写书评

暂无评论

A stacked auto-encoder with scaled conjugate gradient algorithm for Malayalam ASR

引用

International Journal of Information Technology (Singapore) 2021年第4期13卷 1473-1479页

作者： Pillai, Leena G. Mubarak, D. Muhammad Noorul Department of Computer Science University of Kerala Thiruvananthapuram India

automatic speech recognition (ASR) is entitled to automate natural speech perception and the processing mechanism through analysis in the linguistic and acoustic features of the speech signal. ASR for children is highly challenging due to their developing physical aspects and rapidly changing articulation features. Therefore, ASR for children is still at its infant level. In this work, a stacked multilayer auto-encoder (AE) network is designed for ASR of the Malayalam vowel, articulated by children in the age group of five to ten. The proposed network structured with an unsupervised pre-training followed by supervised training. The pre-training coupled with two layers of sparse auto-encoders and scaled conjugate gradient (SCG) algorithm used for back-propagation. The auto-encoders are used to pre-train the network in an unsupervised (self- supervised) manner with 40,500 features that include Mel frequency cepstral coefficients (MFCC) and its derivatives, spectrogram formants and zero crossing rate (ZCR). In the softmax layer, the pre-trained network retrained in a supervised manner with bottleneck features. Fine-tuning has been applied in the trained network to enhance its performance. The unsupervised and supervised layers are stacked together to form a comprehensive network. The designed network has shown an average accuracy of 97% in training and 89.5% accuracy in the test data-set. © 2021, Bharati Vidyapeeth's Institute of Computer Applications and Management.

关键词： automatic speech recognition (ASR) Deep neural network Mel frequency cepstral coefficients (MFCC) Scaled conjugate gradient (SCG) sparse auto-encoder Spectrogram Unsupervised learning Zero crossing rate (ZCR)

来源：评论

学校读者我要写书评

暂无评论

Feature Selection using Multiple auto-encoders

Feature Selection using Multiple Auto-Encoders

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Guo, Xinyu Minai, Ali A. Lu, Long J. Univ Cincinnati Dept Elect Engn & Comp Syst Cincinnati OH 45220 USA Univ Cincinnati Dept Elect Engn & Comp Syst Cincinnati OH USA Cincinnati Childrens Hosp Res Fdn Div Biomed Informat Cincinnati OH USA

ISBN: (纸本)9781509061822

Real-world data such as medical images and sensor measurements is usually high-dimensional and limited. Using such datasets directly in machine learning tasks can lead to poor generalization. Feature learning is a general approach for transforming high-dimensional data points to a representational space with lower dimensionality. Machine learning models can be trained efficiently with such representations. In this paper, a novel feature selection method based on multiple trained sparse auto-encoders (SAEs) is described. It works by selecting diverse, non-redundant features from multiple pinched SAEs with very narrow hidden layers, and then using these features in a more appropriately sized classifier without further feature tuning. The feature learning ability of the method is evaluated in a handwritten digits recognition task. Results show that this type of feature selection provides improved representations for a softmax classifier, and that using pinched SAEs produces results equal to or better than regular SAEs.

关键词： Machine learning feature learning handwritten digits recognition sparse auto-encoder feature diversity feature selection

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection Method based on Deep Learning 19

Intrusion Detection Method based on Deep Learning

引用

19th IEEE International Symposium on Parallel and Distributed Processing with Applications (IEEE ISPA)

作者： Wu, Zhijun Liang, Cheng Li, Yuqi Civil Aviat Univ China Sch Safety Sci & Technol Tianjin Peoples R China Civil Aviat Univ China Sch Elect & Informat & Automat Tianjin Peoples R China

ISBN: (纸本)9781665435741

In response to the issue that the classification accuracy of small proportion attack data is low due to the imbalance of classification in existing intrusion detection methods, this paper mainly focuses on two aspects. First, we put forward a hybrid intrusion detection method founded on AdaBoost algorithm and convolutional neural network (CNN). It utilizes CNN to extract network traffic data, and utilizes AdaBoost algorithm to classify network attack data;Second, the improved sparse autoencoder is combined with softmax classifier to increase the classification preciseness of the model by continuously adjusting the parameters of the sparse autoencoder. This method uses KDD99 data set to test the code in pycharm environment. The test results show that this method has advantages over the existing methods in the detection rate (DR) and false positive rate (FPR) of small proportion attack data. This method is suitable for the analysis of continuous and classified attack data, improves the detection effect of imbalanced data classification, and solves the defects of existing intrusion detection models with large classification error and slow calculation speed.

关键词： Intrusion detection deep learning CNN AdaBoost sparse auto-encoder KDD99 dataset component

来源：评论

学校读者我要写书评

暂无评论

Classifying aircraft based on sparse recovery and deep-learning

引用

JOURNAL OF ENGINEERING-JOE 2019年第21期2019卷 7464-7468页

作者： Wang Wenying Wei Yao Zhen Xuanxuan Yu Hui Wang Ruqi Nanjing Res Inst Elect Technol Nanjing 210039 Jiangsu Peoples R China

A hybrid CS-DL method for aircraft classification in complex electromagnetic environment is introduced. To classify aircraft from interfered radar echoes, the authors propose a novel classification method based on compressed sensing (CS) and deep-learning (DL). After recovering the spectrum polluted by jamming signals by using CS, they exploit sparse auto-encoder (SAE) to extract modulation features and then classify aircraft. The method is tested by 536 flights of three types of airplanes, and the results show that the correct classification rate reaches 75% even when 41% of the pulses are interfered.

关键词： jamming signal classification learning (artificial intelligence) feature extraction neural nets radar cross-sections aerospace computing interference (signal) deep-learning sparse auto-encoder correct classification rate sparse recovery hybrid CS-DL aircraft classification complex electromagnetic environment interfered radar echoes novel classification method compressed sensing jamming signals modulation feature extraction

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Prediction in Mammogram Images using EfficientNet Based Hybrid Deep Learning Model

Breast Cancer Prediction in Mammogram Images using Efficient...

引用

2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023

作者： Sharma, Lakshith Dileep, R.M. Kumar Bhardwaj, Arvind Navaneeth, A.V. Nitte Meenakshi Institute of Technology Department of Master of Computer Applications Bengaluru India Capgemini Houston Texas United States

ISBN: (纸本)9798350313413

Scientists are interested in this area since many women with breast cancer do not seek medical attention until the disease has progressed. Genetics, hereditary factors, and inactivity are all contributors to the development of breast cancer. Breast cancer is death in women in India, and its incidence is rising across the country. Women over the age of 45 have an increased risk of contracting this illness. When compared to prose, pictures tell a thousand words. As computing power has increased, a number of methods have emerged for automatically gleaning previously undetectable details from photographs. Among the many fields where the processed photos have been put to use is medicine. The presence of breast lumps in the breast area is a necessary and sufficient factor in the progression of breast cancer in women. Therefore, a more trustworthy method is required to lessen the amount of pointless biopsies performed while diagnosing breast cancer. Doctors can make better judgements and reduce the number of needless biopsies with the use of computer-aided diagnostic technologies. For this purpose, the study applied the deep learning-based model for classification. Initially, three various steps such as normalization, contrast enhancement and noise removal during pre-processing. K-means clustering algorithm is used for segmentation, then the features are extracted by using pre-trained model called EfficientNet. The hybrid model called sparse auto-encoder based Long-short Term Memory (SAE-LSTM) is used. The proposed model efficiency is tested on mammographic image analysis society (MIAS) in terms of various metrics. The results indicated that the projected model is achieved a better performance than other counterparts. © 2023 IEEE.

关键词： Breast Cancer Analysis Computer-aided diagnostic models EfficientNet Long-short Term Memory Mammogram Images sparse auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Research on Target Object Recognition Based on Transfer-Learning Convolutional SAE in Intelligent Urban Construction

引用

IEEE ACCESS 2019年 7卷 125357-125368页

作者： Xie, Bing Duan, Zhemin Zheng, Bin Liu, Liping Northwestern Polytech Univ Sch Elect & Informat Xian 710072 Shaanxi Peoples R China North Univ China Sch Elect & Control Engn Taiyuan 030051 Shanxi Peoples R China

With the development of society, intelligent urban construction is drawing attention globally. It embed sensors and equipment into various environmental monitoring target objects to achieve environmental management and decision-making wisdom in a more granular and dynamic manner. However, how to achieve target objects' recognition in the dynamic environment is of essential importance for intelligent urban construction. Due to the shape, color and other characteristics for target objects are more similar, which make it difficult to identify the target types based on the low-level features such as color, shape, etc. In this paper, we attempt to apply the deep neural network composed of sparse autoencoders based unsupervised feature learning to identify the various types of target objects. On the other hand, due to the fact that the quantities of target objects which are obtained by environmental monitor may be not sufficient, cannot get more high-level visual feature through feature training, which affects the accuracy of the subsequent target recognition. A cross-domain feature learning scheme for target objects recognition using convolutional sparse auto-encoder has been presented. In order to improve the recognition speed, feature weights selection method based on a correlation analysis is further proposed for the purpose of reducing the amount of global features which are taken from target-domain images. Experimental results show that compared with non-transfer feature learning algorithm and underlying visual feature recognition algorithm, the new algorithm proposed in this paper has higher accuracy and robustness. Feature selection can reduce the computational time of global feature extraction and recognition by about 30% while improving recognition performance.

关键词： Target objects recognition sparse auto-encoder transfer learning intelligent urban

来源：评论

学校读者我要写书评

暂无评论

automatic Modulation Classification for Short Burst Underwater Acoustic Communication Signals Based on Hybrid Neural Networks

引用

IEEE ACCESS 2020年 8卷 227793-227809页

作者： Li, Yongbin Wang, Bin Shao, Gaoping Shao, Shuai PLA Strateg Support Force Informat Engn Univ Zhengzhou 450001 Peoples R China

automatic modulation classification (AMC) is challenging for short burst underwater acoustic (UWA) communication signals. Difficulties include but are not limited to the poor UWA channels, impulsive noise, and data scarcity. To address these problems, a method based on hybrid neural networks (HNNs) is proposed in this paper. First, an impulsive noise preprocessor is adopted to mitigate the impulse in the received signals. Subsequently, an HNN consisting of an attention aided convolutional neural network (Att-CNN) and a sparse auto-encoder is built to extract features from the temporal waveforms and square spectra of the preprocessed signals after burst detection. Finally, a late fusion is made to combine the prediction results of the two sub-networks. To overcome the variable signal duration relative to the fixed input size of the Att-CNN, a data-reusing approach is proposed to perform dimension preprocessing on the waveforms. Moreover, a transfer learning strategy is introduced to resolve the issue of insufficient training data from the testing channel. The results of simulation experiments and practical signal tests both demonstrate that the proposed method is robust against UWA channels and ambient noise. Our approach significantly outperforms existing deep learning-based methods in dealing with short and weak signal bursts, while requiring less training data from the testing channel.

关键词： Testing Feature extraction Training data Phase shift keying Modulation Frequency shift keying Data models automatic modulation classification hybrid neural networks attention aided convolutional neural networks sparse auto-encoder data-reusing transfer learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent classification model of land resource use using deep learning in remote sensing images

引用

ECOLOGICAL MODELLING 2023年 475卷

作者： Liao, Qingtao Chongqing Ind Polytech Coll Inst Elect & Internet things Engn Chongqing 401120 Peoples R China

Accurate and effective remote sensing image classification and analysis methods can provide reliable support for the sustainable development of land resources, but the current methods can't support the precise processing of complex images. To solve this problem, this paper proposes a new classification and analysis method of remote sensing image land resources based on deep learning. Firstly, this method first uses ENVI software to realize image preprocessing on the collected data set, and realizes reliable data set;At the same time, based on the sparse auto-encoder network model, the sample features of the image data set are deeply mined to make a better reference for category determination;And based on ELM classifier network, convolution layer and sub sampling layer are alternately connected to extract the depth feature of remote sensing image, which can greatly reduce the number of network parameters and improve the computational. Finally, the actual collected data set is used for simulation verification, and the experimental results show that the accuracy of complex image analysis reaches 98.15%, which shows excellent performance of image feature classification and analysis.

关键词： Remote sensing image Classification of land resources Ecological environment sparse auto-encoder ELM classifier Data preprocessing

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：