检索结果-内蒙古大学图书馆

Improving the generalization of unsupervised feature learning by using data from different sources on gene expression data for cancer diagnosis

引用

MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING 2022年第4期60卷 1055-1073页

作者： Liu, Zhen Wang, Ruoyu Zhang, Wenbin Guangdong Univ Foreign Studies Sch Informat Sci & Technol Sch Cyber Secur Guangzhou 510006 Peoples R China Guangdong Pharmaceut Univ Sch Med Informat Engn Guangzhou 510006 Peoples R China South China Univ Technol Informat & Network Engn Res Ctr Guangzhou 510041 Peoples R China Univ Maryland Baltimore MD 21250 USA

Machine learning techniques have been utilized on gene expression profiling for cancer diagnosis. However, the gene expression data suffer from the curse of high dimensionality. Different kinds of feature reduction methods have been proposed to decrease the features for specific cancer diagnosis. However, with the difficulty of obtaining the samples of a particular tumor, the lack of training samples may lead to the overfitting problem. In addition, the feature reduction model on a specific tumor may lead to the problem that the model is not scalable and cannot be generalized to new cancer types. To handle these problems, this paper proposes an unsupervised feature learning method to reduce the data dimensionality of gene expression data. This method amplifies the training samples of feature learning by utilizing the unlabeled samples from different sources. Two heuristic rules are devised to check if the unlabeled samples could be used for amplifying the training set. The amplified training set is used to train the feature learning model based on sparse autoencoder. Since the method leverages the knowledge among the expression data from different sources, it improves the generalization of unsupervised feature learning and further boosts the cancer diagnosis performance. A series of experiments are carried out on the gene expression datasets from TCGA and other sources. Experimental results prove that our method improves the generalization of cancer diagnosis when unlabeled data are used for latent feature learning.

关键词： Unsupervised feature learning Generalization Gene expression data Cancer diagnosis Unlabeled data sparse autoencoder

来源：评论

学校读者我要写书评

暂无评论

Heart disease prediction using autoencoder and DenseNet architecture

引用

EGYPTIAN INFORMATICS JOURNAL 2024年 28卷

作者： Alghamdi, Norah Saleh Zakariah, Mohammed Shankar, Achyut Viriyasitavat, Wattana Princess Nourah bint Abdulrahman Univ Coll Comp & Informat Sci Dept Comp Sci POB 84428 Riyadh 11671 Saudi Arabia King Saud Univ Coll Comp & Informat Sci Riyadh 11362 Saudi Arabia Univ Warwick Dept Cyber Syst Engn WMG Coventry CV74AL England Chandigarh Univ Univ Ctr Res & Dev Mohali 140413 Punjab India Lovely Profess Univ Sch Comp Sci & Engn Phagwara 144411 Punjab India Graphic Era Univ Dept Comp Sci & Engn Dehra Dun India Chitkara Univ Ctr Res Impact & Outcome Rajpura Punjab India Chulalongkorn Univ Fac Commerce & Accountancy Chulalongkorn Business Sch Bangkok Thailand

Heart disease continues to be a prominent cause of death globally, emphasizing the critical requirement for precise prediction techniques and prompt therapies. This research presents a new method that utilizes the collective capabilities of autoencoder and DenseNet architectures to predict heart illness. Our study is based on the Heart Disease UCI Cleveland dataset, which includes 13 variables that cover clinical and demographic parameters such as age, sex, cholesterol levels, and exercise-induced angina. The dataset presents issues due to its varied attribute types, including category and numerical variables. Furthermore, our approach tackles these difficulties by utilizing a dense autoencoder model, which produced exceptional outcomes. The Model attained a mean accuracy of 99.67% on the Heart Disease UCI Cleveland dataset. Further testing showed it was resilient, with a test accuracy of 99.99%. In addition, the Model demonstrated outstanding macro precision, macro recall, and macro F1 score, with percentages of 99.98%, 99.97%, and 99.96%, respectively. In addition, our results indicate that combining autoencoder and DenseNet designs shows potential for predicting cardiac disease, with substantial enhancements in accuracy and performance metrics compared to current approaches. This methodology can improve clinical decision-making and patient outcomes in cardiovascular care by accurately finding and defining complex patterns within the data. Notwithstanding these encouraging outcomes, our investigation has constraints. The specific attributes of the dataset utilized may limit the applicability of our findings. Subsequent studies could examine the suitability of our method for various datasets and analyze supplementary variables that may improve forecast precision. Furthermore, it is necessary to conduct prospective validation studies to evaluate our strategy's practical effectiveness in clinical environments.

关键词： Heart Disease Heart Disease Cleveland dataset Machine-Learning sparse autoencoder DenseNet

来源：评论

学校读者我要写书评

暂无评论

A random deep neural system for heartbeat classification

引用

EVOLVING SYSTEMS 2023年第1期14卷 37-48页

作者： Siouda, Roguia Nemissi, Mohamed Seridi, Hamid Univ 8 Mai 1945 Dept Comp Sci LabSTIC Lab PB 401 Guelma Algeria Univ 8 Mai 1945 Dept Elect & Telecommun LabSTIC Lab PB 401 Guelma Algeria

This paper introduces a heartbeat classification system that combines three types of neural networks: random neural networks, deep autoencoders and RBF neural networks. The aim is to make use of the advantages of these neural networks in order to introduce a model with simpler architecture than the state-of-the-art deep models. Indeed, the advantages of the three combined networks, briefly, are these: (i) autoencoders provide high level features without pre-processing;(ii) Random neural networks provide good generalisation and very fast training;(iii) RBF neural networks provide high coverage of the input space and allow using prior knowledge. On the other hand, two types of features are used: coded features (obtained from the autoencoder) and RR interval based-features. To evaluate the performance of the proposed system, we conduct experiments on the MIT-BIH arrhythmia dataset and we consider the recommendations of the association for the advancement of medical instrumentation, which defines five classes of interest. Furthermore, the experiments are based on an inter-patient paradigm and the obtained results are compared with some of the state-of-the-art methods.

关键词： ECG arrhythmia Radial basis function neural network Random vector functional link neural network sparse autoencoder Multi-class classification

来源：评论

学校读者我要写书评

暂无评论

An SAE -based resampling SVM ensemble learning paradigm for pipeline leakage detection

引用

NEUROCOMPUTING 2020年 403卷 237-246页

作者： Wang, Chuang Han, Fei Zhang, Yong Lu, Jingyi Northeast Petr Univ Inst Complex Syst & Adv Control Daqing 163318 Peoples R China Northeast Petr Univ Heilongjiang Prov Key Lab Networking & Intelligen Daqing 163318 Peoples R China Northeast Petr Univ Coll Elect Sci Daqing 163318 Peoples R China

In this paper, an ensemble learning framework combining the sparse autoencoder (SAE) network with an improved support vector machine (SVM) is established to enhance the accuracy of classification in detecting the pipeline leakage. First of all, the SAE network is introduced to extract the discriminative and robust features of the pipeline leakage data. Then, a kind of leader-follower particle swarm optimization (LFPSO) algorithm is put forward to optimize the parameters of the SVM algorithm such that the probability trapping into the local optimum is effectively reduced. Next, the proposed LFPSO-SVM approach is employed to further classify and recognize the features extracted from the pipeline leakage data via the SAE network. Moreover, the performance of the SAE-LFPSO-SVM approach is quantitatively evaluated by three performance indicators, i.e., sensitivity, positive predictive value and total classification accuracy. Finally, some simulation examples are given to demonstrate the effectiveness of the proposed SAE-LFPSO-SVM approach, which exhibits a higher classification accuracy than that of the other traditional classification algorithms. (C) 2020 Published by Elsevier B.V.

关键词： Deep learning Pipeline leakage detection sparse autoencoder Leader-follower Particle swarm optimization Support vector machine

来源：评论

学校读者我要写书评

暂无评论

A deep learning based trust- and tag-aware recommender system

引用

NEUROCOMPUTING 2022年第0期488卷 557-571页

作者： Ahmadian, Sajad Ahmadian, Milad Jalili, Mahdi Kermanshah Univ Technol Fac Informat Technol Kermanshah Iran Razi Univ Dept Comp Engn Kermanshah Iran RMIT Univ Sch Engn Melbourne Vic Australia

Recommender systems are popular tools used in many applications, such as e-commerce, e-learning, and social networks to help users select their desired items. Collaborative filtering is a widely used recommendation technique that employs previous ratings of users to predict their future interests. Lack of sufficient ratings often reduces the performance of collaborative filtering recommendation methods. Additional side resources, such as trust relationships and tag information can be employed to enhance the recommendation accuracy. However, trust and tag data are often heavily sparse as users mainly provide insufficient information about these side resources. Moreover, such additional resources have generally large dimensions which result in increasing the computational complexity of recommendation models in calculating similarity values. To cope with these problems, a new recommendation model is proposed that utilizes deep neural networks to model the representation of trust relationships and tag information. To this end, a sparse autoencoder is used to extract latent features from user-user trust relationships and user-tag matrices. Then, the extracted latent features are utilized to calculate similarity values between users, which are then used to form the nearest neighbors of the target user and predict unseen items. The proposed method can tackle the data sparsity problem and reduce the computational complexity of recommender systems as the extracted latent features have smaller dimensions in comparison to the original data. Experimental results on two benchmark datasets reveal the effectiveness of the proposed method and show its outperformance over state-of-the-art recommender systems. (C) 2021 Elsevier B.V. All rights reserved.

关键词： Recommender systems Collaborative filtering Deep neural networks sparse autoencoder Trust Tag

来源：评论

学校读者我要写书评

暂无评论

Damage assessment of laminated composites using unsupervised autonomous features

引用

JOURNAL OF THERMOPLASTIC COMPOSITE MATERIALS 2024年第6期37卷 2123-2148页

作者： Khan, Asif Kim, Heung Soo Ghulam Ishaq Khan Inst Engn Sci & Technol Fac Mech Engn Topi Khyber Pakhtunk Pakistan Dongguk Univ Dept Mech Robot & Energy Engn Seoul 04620 South Korea Dongguk Univ Dept Mech Robot & Energy Engn Seoul 04620 South Korea

This article proposes a framework for the damage assessment of and effect of temperature variations in laminated composites using Lamb waves and unsupervised autonomous features. A network of piezoelectric transducers is employed to generate data for 18 health states of a laminated composite plate. The data is processed with sparse autoencoder (SAE) for unsupervised autonomous features. The discriminative capabilities of the extracted features are confirmed by processing the feature space in the supervised and unsupervised frameworks of machine learning. The confusion matrices of supervised learning provided physical insights into the problem. The feature space was also visualized in two dimensions in an unsupervised manner through principal component analysis (PCA), which revealed physically consistent results for the effect of temperature variations, damage of different severity levels, and the undamaged paths between the actuator and sensors. The healthy state data and information on the paths between the actuator and sensors was processed via SAE for damage localization. The proposed approach can be employed for the autonomous assessment of composite structures for the presence of damage and variations of operating temperatures while using both supervised and unsupervised machine learning algorithms.

关键词： Laminated composites lamb waves damage assessment sparse autoencoder autonomous features

来源：评论

学校读者我要写书评

暂无评论

An Improved Approach to Audio Segmentation and Classification in Broadcasting Industries

引用

JOURNAL OF DATABASE MANAGEMENT 2019年第2期30卷 44-66页

作者： Sun, Jingzhou Wang, Yongbin Commun China Sch Comp Sci & Cybersecur Beijing Peoples R China

Audio segmentation and classification are the basis of audio processing in broadcasting industries. A Dual-CNN (Dual-Convolutional Neural Network) method is proposed in this article in which it is possible to pre-train a CNN with unlabeled audio data so as to deal with the scarcity of labeled data. Auto-encoders (including an encoder and a decoder) are utilized, thus the name "Dual." In the first place, audio sampling points and the derived STFT (Short-Time Fourier Transform) spectrograms pass through their own CNNs. Fusion of the extracted features is then performed. Finally, the merged features are sent to a fully connected network and the classification results are produced via Softmax. Being one of the segmentation-by-classification approaches, our solution also presents a novel smoothing method (SEG-smoothing) in order to deliver the best result of segmentation. A series of experiments have been conducted and their result verifies that the proposed approach for segmentation and classification outperforms alternative solutions.

关键词： Classification-Oriented Audio Processing Dual-CNN Smoothing sparse autoencoder

来源：评论

学校读者我要写书评

暂无评论

Heart disease risk prediction using deep learning techniques with feature augmentation

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第20期82卷 31759-31773页

作者： Teresa Garcia-Ordas, Maria Bayon-Gutierrez, Martin Benavides, Carmen Aveleira-Mata, Jose Alberto Benitez-Andrades, Jose Univ Leon Escuela Ingn Ind & Informat SECOMUCI Res Grp Campus Vegazana s-n Leon 24071 Leon Spain Univ Leon Dept Elect Syst & Automat Engn SALBIS Res Grp Campus Vegazana s-n Leon 24071 Leon Spain

Cardiovascular diseases state as one of the greatest risks of death for the general population. Late detection in heart diseases highly conditions the chances of survival for patients. Age, sex, cholesterol level, sugar level, heart rate, among other factors, are known to have an influence on life-threatening heart problems, but, due to the high amount of variables, it is often difficult for an expert to evaluate each patient taking this information into account. In this manuscript, the authors propose using deep learning methods, combined with feature augmentation techniques for evaluating whether patients are at risk of suffering cardiovascular disease. The results of the proposed methods outperform other state of the art methods by 4.4%, leading to a precision of a 90%, which presents a significant improvement, even more so when it comes to an affliction that affects a large population.

关键词： Deep learning sparse autoencoder Convolutional neural network Heart disease

来源：评论

学校读者我要写书评

暂无评论

Classification of Power Quality Disturbances via Deep Learning

引用

IETE TECHNICAL REVIEW 2017年第4期34卷 408-415页

作者： Ma, Jian Zhang, Jun Xiao, Luxin Chen, Kexu Wu, Jianhua State Grid Corp China Jiangxi Elect Power Res Inst Ctr Metrol Nanchang Jiangxi Peoples R China Nanchang Univ Dept Elect Informat Engn Nanchang Jiangxi Peoples R China

In this paper, a deep learning-based method is introduced into the classification of power quality disturbances (PQDs). Stacked autoencoder, as a deep learning framework, is employed to extract high-level features of PQDs for classification. In this context, a previously unsolved issue regarding optimal features' selection for PQDs can be addressed. Besides, variances of signals and a particle swarm optimization algorithm are applied to assist classification of the PQDs. To sufficiently validate the effectiveness of the proposed classification scheme, a 10-fold cross-validation has been done. Experimental results indicate that the proposed approach is robust against noise and reaches a desirable classification accuracy rate.

关键词： Deep learning Power quality disturbances (PQDs) sparse autoencoder Stacked autoencoder (SAE)

来源：评论

学校读者我要写书评

暂无评论

A novel adaptive fault diagnosis algorithm for multi-machine equipment: application in bearing and diesel engine

引用

STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL 2023年第3期22卷 1677-1707页

作者： Liu, Yangshuo Kang, Jianshe Bai, Yunjie Guo, Chiming Army Engn Univ PLA Shijiazhuang 050003 Hebei Peoples R China Chinese Peoples Liberat Army Unit 66029 Xilinguolemeng Peoples R China

This paper proposes an adaptive fault diagnosis algorithm based on vibration signals for fault diagnosis of bearings and diesel engines. First, the improved nonlinear gray wolf optimization algorithm (NGWO) is adopted to optimize the key parameter for variational mode decomposition (VMD) with the power spectral entropy as the fitness value. Meanwhile, adaptive noise reduction of the signal is realized. Then, sensitive fault features of bearings and diesel engines are selected through a feature sensitivity analysis on the vibration signals. Also, a single-layer sparse autoencoder is used to align the feature dimensions of each type of data to construct feature matrix samples. Subsequently, a deep neural network (DNN) consisting of a two-layer stacked sparse autoencoder (SSAE) and a Softmax classification layer is constructed to realize failure mode recognition. During the training process of DNN, a surrogate model formed by NGWO and a back propagation neural network is employed to optimize the hyperparameters of SSAE. Finally, to verify the effectiveness of the proposed fault diagnosis algorithm, fault diagnosis experiments are conducted on the fault data set of bearings and diesel engines. The diagnosis results show that the proposed method achieves high-precision fault diagnosis for bearings and diesel engines and performs stably for small samples.

关键词： Fault diagnosis condition monitoring model adaptability adaptive noise reduction feature sensitivity analysis feature alignment sparse autoencoder surrogate model hyperparameter optimization

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：