检索结果-内蒙古大学图书馆

A hybrid machine learning model with attention mechanism and multidimensional multivariate feature coding for essential gene prediction

引用

BMC BIOLOGY 2025年第1期23卷 1-24页

作者： Wu, Yan Fu, Yu Li, Tan Li, Mengshan Xie, Xiaojun Zhou, Weihong Sheng, Sheng Wang, Jun Wu, Fu-an Gannan Normal Univ Ganzhou 341000 Jiangxi Peoples R China Jiangsu Univ Sci & Technol Zhenjiang 212018 Jiangsu Peoples R China Chinese Acad Agr Sci Sericultural Res Inst Zhenjiang 212018 Jiangsu Peoples R China State Grid Jiangxi Elect Power Co Ltd Ganzhou Power Supply Branch Ganzhou 341000 Jiangxi Peoples R China

BackgroundEssential genes are crucial for the development, inheritance, and survival of species. The exploration of these genes can unravel the complex mechanisms and fundamental life processes and identify potential therapeutic targets for various diseases. Therefore, the identification of essential genes is significant. Machine learning has become the mainstream approach for essential gene prediction. However, some key challenges in machine learning need to be addressed, such as the extraction of genetic features, the impact of imbalanced data, and the cross-species generalization ***, we proposed a hybrid machine learning model based on graph convolutional neural networks (GCN) and bi-directional long short-term memory (Bi-LSTM) with attention mechanism and multidimensional multivariate feature coding for essential gene prediction, called EGP Hybrid-ML. In the model, GCN was used to extract feature encoding information from the visualized graphics of gene sequences and the attention mechanism was combined with Bi-LSTM to assess the importance of each feature in gene sequences and analyze the influences of different feature encoding methods and data imbalance. Additionally, the cross-species predictive performance of the model was evaluated through cross-validation. The results indicated that the sensitivity of the EGP Hybrid-ML model reached *** model demonstrated the superior predictive performance and strong generalization capabilities compared to other models. The EGP Hybrid-ML model proposed in this paper has broad application prospects in bioinformatics, chemical information, and pharmaceutical information. The codes, architectures, parameters, and datasets of the proposed model are available free of charge at GitHub (https://***/gnnumsli/EGP-Hybrid-ML).

关键词： Essential gene Machine learning Attention mechanism LSTM CNN feature coding

来源：评论

学校读者我要写书评

暂无评论

feature coding for image classification combining global saliency and local difference

引用

PATTERN RECOGNITION LETTERS 2015年 51卷 44-49页

作者： Chen, Shuhan Shi, Weiren Lv, Xiao Yangzhou Univ Coll Informat Engn Yangzhou 225127 Peoples R China Chongqing Univ Coll Automat Chongqing 400044 Peoples R China Chongqing Special Equipment Inspect & Res Inst Chongqing 401121 Peoples R China

Saliency l based coding proposed recently have been proven to perform well in both performance and efficiency for image classification. However, we find that they are sensitive to unusual features, e.g., noisy features, which we call poor robustness. To address this problem, we propose a novel coding scheme by combining global saliency and local difference together, which are applied for improving stability or robustness and exploring the latent structure information of the codebook respectively. Thorough experiments on various datasets show that our coding consistently performs better than local saliency based coding, in terms of both accuracy and computation cost. Furthermore, it is more robust to unusual features than localized soft-assignment coding. In addition, a combination of our global saliency with local saliency based coding can usually improve both. (C) 2014 Elsevier B.V. All rights reserved.

关键词： Image classification feature coding Global saliency Local difference

来源：评论

学校读者我要写书评

暂无评论

feature coding in Image Classification: A Comprehensive Study

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2014年第3期36卷 493-506页

作者： Huang, Yongzhen Wu, Zifeng Wang, Liang Tan, Tieniu Chinese Acad Sci CASIA Inst Automat Natl Lab Pattern Recognit NLPR CRIPAC 95 ZhongGuanCun East St Beijing 100190 Peoples R China

Image classification is a hot topic in computer vision and pattern recognition. feature coding, as a key component of image classification, has been widely studied over the past several years, and a number of coding algorithms have been proposed. However, there is no comprehensive study concerning the connections between different coding methods, especially how they have evolved. In this paper, we first make a survey on various feature coding methods, including their motivations and mathematical representations, and then exploit their relations, based on which a taxonomy is proposed to reveal their evolution. Further, we summarize the main characteristics of current algorithms, each of which is shared by several coding strategies. Finally, we choose several representatives from different kinds of coding approaches and empirically evaluate them with respect to the size of the codebook and the number of training samples on several widely used databases (15-Scenes, Caltech-256, PASCAL VOC07, and SUN397). Experimental findings firmly justify our theoretical analysis, which is expected to benefit both practical applications and future research.

关键词： Image classification feature coding bag-of-features

来源：评论

学校读者我要写书评

暂无评论

feature coding VIA VECTOR DIFFERENCE FOR IMAGE CLASSIFICATION

FEATURE CODING VIA VECTOR DIFFERENCE FOR IMAGE CLASSIFICATIO...

引用

19th IEEE International Conference on Image Processing (ICIP)

作者： Zhao, Xin Yu, Yinan Huang, Yongzhen Huang, Kaiqi Tan, Tieniu Univ Sci & Technol China Dept Automat Hefei Anhui Peoples R China Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit Beijing Peoples R China

ISBN: (纸本)9781467325332;9781467325349

An effective image representation is important to an image classification task. The most popular image representation framework utilizes a feature coding algorithm to encode the extracted low-level feature descriptors into a vector representation. In this paper, we analyze the recently developed feature coding methods in a general way. According to their common characteristics, we propose a new coding scheme to perform feature coding based on the vector difference in a high-dimensional space which is obtained by explicit feature maps. As we illustrate, our method has promising results with small codebook sizes and generalizes most existing coding methods in a unified form.

关键词： Image classification feature coding Vector difference Additive kernel

来源：评论

学校读者我要写书评

暂无评论

Dependence-Aware feature coding for Person Re-Identification

引用

IEEE SIGNAL PROCESSING LETTERS 2018年第4期25卷 506-510页

作者： Wang, Xiaobo Lei, Zhen Liao, Shengcai Guo, Xiaojie Yang, Yang Li, Stan Z. Chinese Acad Sci CBSR Inst Automat Beijing 100190 Peoples R China Chinese Acad Sci NLPR Inst Automat Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Tianjin Univ Sch Comp Software Tianjin 300350 Peoples R China

In this letter, we focus on how to boost the performance of person re-identification by exploring the discriminative information among person pairs. A novel dependence-aware feature coding framework is proposed for this task. Specifically, we employ theHilbert-Schmidt independence criterion as the discriminative term, which is to explore the dependence between different kinds of person pairs, i.e., the same person pairs should be dependence maximized, while the different ones should be dependence minimized. Theoretical discussion and analysis on the convexity of the proposed constraint, as well as the convergence of our algorithm, are provided. Experimental results on two benchmark datasets have demonstrated the advantages of our method over the state-of-the-art alternatives.

关键词： feature coding Person re-identification

来源：评论

学校读者我要写书评

暂无评论

Multi-Index Image Retrieval Hash Algorithm Based on Multi-View feature coding

引用

Computers, Materials & Continua 2020年第12期65卷 2335-2350页

作者： Rong Duan Junshan Tan Jiaohua Qin Xuyu Xiang Yun Tan N.eal NXiong College of Computer Science and Information Technology Central South University of Forestry&TechnologyChangsha410004China Department of Mathematics and Computer Science Northeastern State UniversityTahlequahOK 74464USA

In recent years,with the massive growth of image data,how to match the image required by users quickly and efficiently becomes a *** with single-view feature,multi-view feature is more accurate to describe image *** advantages of hash method in reducing data storage and improving efficiency also make us study how to effectively apply to large-scale image *** this paper,a hash algorithm of multi-index image retrieval based on multi-view feature coding is *** learning the data correlation between different views,this algorithm uses multi-view data with deeper level image semantics to achieve better retrieval *** algorithm uses a quantitative hash method to generate binary sequences,and uses the hash code generated by the association features to construct database inverted index files,so as to reduce the memory burden and promote the efficient *** order to reduce the matching error of hash code and ensure the retrieval accuracy,this algorithm uses inverted multi-index structure instead of single-index *** with other advanced image retrieval method,this method has better retrieval performance.

关键词： Hashing multi-view feature large-scale image retrieval feature coding feature matching

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving feature coding for Machines

Privacy-Preserving Feature Coding for Machines

引用

Picture coding Symposium (PCS)

作者： Azizian, Bardia Bajic, Ivan, V Simon Fraser Univ Sch Engn Sci Burnaby BC Canada

ISBN: (纸本)9781665492577

Automated machine vision pipelines do not need the exact visual content to perform their tasks. Therefore, there is a potential to remove private information from the data without significantly affecting the machine vision accuracy. We present a novel method to create a privacy-preserving latent representation of an image that could be used by a downstream machine vision model. This latent representation is constructed using adversarial training to prevent accurate reconstruction of the input while preserving the task accuracy. Specifically, we split a Deep Neural Network (DNN) model and insert an autoencoder whose purpose is to both reduce the dimensionality as well as remove information relevant to input reconstruction while minimizing the impact on task accuracy. Our results show that input reconstruction ability can be reduced by about 0.8 dB at the equivalent task accuracy, with degradation concentrated near the edges, which is important for privacy. At the same time, 30% bit savings are achieved compared to coding the features directly.

关键词： Deep neural network coding for machines privacy adversarial training feature coding

来源：评论

学校读者我要写书评

暂无评论

Text Steganography Based on feature coding Method 16

Text Steganography Based on Feature Coding Method

引用

International Conference on Advances in Information Communication Technology and Computing

作者： Chaudhary, Sunita Dave, Meenu Sanghi, Amit Jagannath Univ Dept CS & IT Jaipur Rajasthan India MEC Dept CSE Bikaner India

ISBN: (纸本)9781450342131

Stegnography is a sheltered communication in which information such as text, image, audio and video is kept under shelter of another message. The message providing the shelter can also be text, image, video etc. No one except the dispatcher and projected addressee can have any idea if any sort of hidden writing exists. In this paper, we present and evaluate an approach for text steganography which is hiding text underneath text. The approach is based on feature encoding and random character generation method. Our focus is primarily on the shape of the capital alphabets of the English language and hence the algorithm has been termed as capital alphabet shape encoding method..

关键词： Text steganography feature coding random character cover text

来源：评论

学校读者我要写书评

暂无评论

IMAGE CLASSIFICATION BASED ON DEEP LOCAL feature coding 25

IMAGE CLASSIFICATION BASED ON DEEP LOCAL FEATURE CODING

引用

International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)

作者： Wang, Qian Zhu, Jianqing Shao, Wei Wang, Lei Zhu, Xiaobin Beijing Technol & Business Univ Beijing Peoples R China Huaqiao Univ Coll Engn Quanzhou 362021 Fujian Peoples R China CCTV High Tech Televis Dev CO Ltd Shenzhen Peoples R China SAPPRFT Acad Broadcasting Sci Beijing Peoples R China

ISBN: (纸本)9781538621592

In this paper, we propose an improved locally aggregated descriptor (VLAD) algorithm coded on deep local features for image classification. Firstly, convolutional neural network (CNN) is adopted to extract the dense local features of images. Secondly, a subset of feature, chosen by the criterion of normal distribution, is selected for high quality codebook generation. Finally, the local features are assigned to multi-neighbor visual words instead of the nearest one with different weights, simultaneously, the statistical distribution information about local features is taken into account during VLAD coding process. Extensive experiments on public available datasets demonstrate the promising performance of the proposed method against state-of-the-art methods.

关键词： VLAD CNN image classification feature coding multi-neighbor assignment

来源：评论

学校读者我要写书评

暂无评论

Roof type classification in aerial imagery using convolutional neural networks exploring the exploitation of convolutional features using feature coding and random forests

Roof type classification in aerial imagery using convolution...

引用

作者： Bart van Driel Eindhoven University of Technology

学位级别：硕士

Accurate, up-to-date and complete data is essential for efficient and effective humanitarian aid. For example, building characteristics can be an important variable in damage prediction models. This work investigates the classification of roof types (i. e. shape and material) in aerial imagery of Sint Maarten using Convolutional Neural Networks (CNNs). Additionally, the UC-Merced data set is used as benchmark data set. Two strategies are presented trying to improve the classification performance of fine-tuned CNNs. In the first approach, features are extracted from the last convolutional layer and encoded using four coding algorithms and classification is done by a linear Support Vector Machine. The second approach extracts the features from the last fully connected layer and classification is done by Random Forests. The best performing fine-tuned CNN, VGG-16, achieved an accuracy of 88% and 58% on respectively the roof shape and roof material data sets. None of the feature coding schemes significantly improved the performance of the fine-tuned VGG-16. Only on the roof material data set, Random Forests showed a small improvement over the fine-tuned VGG-16.

关键词： Image Classification Roof Type Remote Sensing Convolutional Neural Networks feature coding Random Forests

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：