检索结果-内蒙古大学图书馆

Machine learning-based analysis of multi-region bone fracture detection and classification using biomedical images

Alexandria Engineering Journal 2025年 128卷 186-199页

作者： Alla M. Elsheikh Azhari A. Elhag Mathematics Department Faculty of Science and Arts Alkamil University of Jeddah Jeddah Saudi Arabia Department of Mathematics and Statistics College of Science Taif University Taif Saudi Arabia

Bone fractures are a prevalent medical concern that necessitates precise and prompt diagnosis. Interpreting X-ray pictures to detect fractures is a complex and time-intensive task that requires specialized radiological expertise. This process is further complicated in under-resourced or high-demand clinical settings, when access to proficient radiologists is restricted and diagnostic inaccuracies may occur owing to exhaustion or excessive workload. These issues underscore the pressing necessity for automated, intelligent solutions to aid in diagnosing and classifying bone fractures. This study proposes a Deep Learning-Driven Computer Vision Model for Multi-Region Bone Fracture Detection and Classification (DLCVM-MBFDC) technique. The proposed method commences with a Wiener Filtering (WF) preparation phase to diminish image noise. Subsequently, DenseNet201 is utilized to extract deep features from biological pictures. A stacked autoencoder (SAE) model is employed for fracture identification and classification, while the wild gibbon optimizer algorithm (WGOA) model is utilized for hyperparameter optimization of the SAE model. The efficacy of the DLCVM-MBFDC approach is examined under the Kaggle dataset. The comparison study of the DLCVM-MBFDC approach portrayed a superior accuracy value of 97.85 % over existing models.

关键词： Bone Fracture Detection Wild Gibbon Optimization Weiner Filtering DenseNet201 stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

LPItabformer: Enhancing generalization in predicting lncRNA-protein interactions via a tabular Transformer

引用

Computational and Structural Biotechnology Journal 2025年 27卷 2323-2335页

作者： Qin Lin Jie Sheng Chang Zhou Tao Xiao Yilei Meng Mingxin Lu Junfang Zhang Xueyun Yan Luying Peng Huaming Cao Li Li State Key Laboratory of Cardiovascular Diseases and Medical Innovation Center Shanghai East Hospital School of Medicine Tongji University Shanghai 200120 China Shanghai Arrhythmias Research Center Shanghai East Hospital Tongji University School of Medicine Shanghai 200120 China Stem Cell Research Center Medical School Tongji University Shanghai 200120 China Teaching Laboratory Center Tongji University School of Medicine Shanghai 200331 China Department of Cardiology Shibei Hospital Shanghai 200435 China

Long-noncoding RNAs (LncRNAs) play important roles in physiological and pathological processes. Accurately predicting lncRNA-protein interactions (LPIs) is vital strategy for clarify functions and pathogenic mechanisms of lncRNAs. Current computational methods for evaluating LPIs with their utility and generalization have significant room for improvement. In this study, data splitting by incorporating protein clusters as group information reveals that lots of LPI prediction methods suffer from generalization flaws due to data leakage caused by ignoring LPI biological properties. To address the issue, we present LPItabformer, a tabular Transformer framework for predicting LPIs, that incorporates a domain shifts with uncertainty (DSU) module for generalization enhancement. The LPItabformer demonstrates a capacity to alleviate the generalization challenges associated with biases in LPI data and preferences in protein binding patterns. In addition, LPItabformer shows greater robustness and generalization on human and mouse LPI datasets compared to state-of-the-art methods. Ultimately, we have verified that the LPItabformer is capable of predicting novel LPIs. Code is available at https://***/Ci-TJ/LPItabformer.

关键词： NcRNA Noncoding RNA LncRNA Long noncoding RNA RBP RNA-binding protein LPI LncRNA-protein interaction RPI RNA-protein interaction SVM Support Vector Machine RF Random Forest LGBM Light Gradient Boosting Machine CTF Conjoint triad feature CNN Convolutional Neural Network SAE stacked autoencoder CLIP-seq Crosslinking Immunoprecipitation Sequencing 5FCV 5-fold cross validation G5FCV Group 5-fold cross validation DSU Domain Shifts with Uncertainty LR Logistic Regression SGD Stochastic Gradient Descent TEDM Transformer Encoder with DSU Module ACC Accuracy AUC Area under the curve PRE Precision SEN Sensitivity SPE Specificity Long non-coding RNA LncRNA-protein interactions Tabular Transformer Generalization Deep learning

来源：评论

学校读者我要写书评

暂无评论

A novel scalable intrusion detection system based on deep learning

引用

INTERNATIONAL JOURNAL OF INFORMATION SECURITY 2021年第3期20卷 387-403页

作者： Mighan, Soosan Naderi Kahani, Mohsen Ferdowsi Univ Mashhad Fac Engn Comp Dept Mashhad Razavi Khorasan Iran

This paper successfully tackles the problem of processing a vast amount of security related data for the task of network intrusion detection. It employs Apache Spark, as a big data processing tool, for processing a large size of network traffic data. Also, we propose a hybrid scheme that combines the advantages of deep network and machine learning methods. Initially, stacked autoencoder network is used for latent feature extraction, which is followed by several classification-based intrusion detection methods, such as support vector machine, random forest, decision trees, and naive Bayes which are used for fast and efficient detection of intrusion in massive network traffic data. A real time UNB ISCX 2012 dataset is used to validate our proposed method and the performance is evaluated in terms of accuracy, f-measure, sensitivity, precision and time.

关键词： Apache Spark stacked autoencoder Latent Accuracy ISCX Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Adaptive EHTARA: An Energy-Efficient and Trust Aware Secure Routing Algorithm for Big Data Classification in IoT Network

引用

WIRELESS PERSONAL COMMUNICATIONS 2021年第1期121卷 621-646页

作者： Mujeeb, S. Md Sam, R. Praveen Madhavi, K. GITAM Deemed Be Univ Dept CSE SOT Hyderabad 502329 Telangana India G Pulla Reddy Engn Coll Autonomous Dept CSE Kurnool 518007 Andhra Pradesh India JNTUA Coll Engn Ananthapuramu Dept CSE Ananthapuramu 515002 Andhra Pradesh India

Due to rapid growth and tremendous advancement, the Internet of Things (IoT) has been considered as a superior technology in recent years and increased its demand over the internet world because of its smart services. IoT has a wide range of applications over the industry, business, and academia. Still, security and routing remain a huge challenging task because of some reasons, such as heterogeneity issues, large energy consumption, and uncontrollable environment. In order to cope up with such security issues, it is essential to develop an energy-efficient routing protocol. Hence, this article presents an Adaptive energy harvesting and Trust aware routing (EHTARA) algorithm for optimal routing such that it prolongs the lifetime of the network. The optimal secure routing path is chosen to exploit the cost metric function. Moreover, the classification of big data is performed at MapReduce framework using stacked autoencoder, which is trained using the proposed Adaptive E-2-Bat algorithm. Moreover, the proposed Adaptive E-2-Bat algorithm is derived by incorporating adaptive principle with E-2-Bat algorithm. The proposed Adaptive EHTARA achieved an energy of 0.948 J that reveals the superiority of the proposed scheme.

关键词： Internet of Things (IoT) Routing Big data MapReduce framework stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic Window S-Transform Aided Deep Neural Network Model-Based Power Quality Monitoring Framework in Electrical Power System

引用

IEEE SENSORS JOURNAL 2021年第12期21卷 13695-13703页

作者： Nandi, Kiron Das, Arup Kumar Ghosh, Riddhi Dalai, Sovan Chatterjee, Biswendu Jadavpur Univ Dept Elect Engn Kolkata 700032 India Univ Bologna Dept Elect Elect & Informat Engn I-40126 Bologna Italy

With the fast development of power grid the usage of electrical equipments is increased which led to importance of power quality disturbance sensing for reliable and smooth operation. In this paper, a deep neural network has been designed using stacked autoencoder (SAE) for deep feature extraction from time-frequency spectrum of single and combined PQ disturbances in electrical power system network. For this purpose, synthetic PQ signals are analyzed in time-frequency domain through hyperbolic window stockwell transform (HWST). Thereafter, PQ signal converted HWST time-frequency matrix has been grouped into time-frequency blocks and subsequently fed as input to 3-layer stacked autoencoder model (SAE) for deep feature learning. Finally, the extracted deep features are classified through several machine learning classifier. The results indicate that proposed framework using XGboost classifier can classify 18 different single and combined PQ event with a 99.86% accuracy. The proposed framework also yields satisfactory outcome with real life PQ data. Therefore, proposed framework can be implemented for Power quality monitoring in electrical power system.

关键词： Feature extraction Transforms Time-frequency analysis Sensors Transient analysis Reliability Power system reliability Power quality detection hyperbolic window s-transform deep neural network stacked autoencoder classification

来源：评论

学校读者我要写书评

暂无评论

Palmvein Recognition Using Block-Based WLD Histogram of Gabor Feature Maps and Deep Neural Network With Bayesian Optimization

引用

IEEE ACCESS 2021年 9卷 97337-97353页

作者： El-Ghandour, Mohammed Obayya, Marwa Ismael Yousef, Bedir Areed, Nihal Fayez Mansoura Univ Coll Engn Dept Elect & Commun Engn Mansoura 35516 Egypt Princess Nourah Bint Abdulrahman Univ Coll Engn Dept Biomed Engn Riyadh 84428 Saudi Arabia Kafrelsheikh Univ Fac Engn Dept Elect Engn Kafr Al Sheikh 33516 Egypt Onaizah Coll Fac Engn & Informat Technol Dept Elect Engn Al Qassim 51911 Saudi Arabia

The demand on devices and systems empowered by biometric verification and identification mechanisms has been increasing in recent years as they have become a significant part of our lives. Palm vein biometric is an emerging technology that has drawn considerable attention from researchers and scientists over the last decade. In the present work, a novel feature extraction methodology named GPWLD combing the Gabor features with positional Weber's local descriptor (PWLD) features is proposed. WLD is a highly representative micro-pattern descriptor that performs well against noise and illumination changes in images. However, it lacks the ability to capture the vein pattern features at different orientations. Moreover, its descriptor packs the local information content into a single histogram that does not take the spatial locality of micro-patterns into consideration. To solve these two issues, firstly, the palm vein image is passed through Gabor filter with different orientations to capture the salient rotational features found in the output feature maps. Secondly, the spatiality is achieved by uniformly dividing each feature map into several blocks. Next, Weber's law feature descriptor (WLD) histogram is computed for each block in every feature map. Finally, these histograms are concatenated to compose the final feature vector. Due to the high dimensionality of the final feature vector, Principal component analysis (PCA) algorithm is utilized for feature size reduction. In the classification stage, a deep neural network (DNN) comprising an optimized stacked autoencoder (SAE) with Bayesian optimization and a softmax layer is used. Optimization of the SAE is carried out by using Bayesian optimization to find the optimal SAE structure and the options of the training algorithm. The Experimental results verify the discriminative power of the extracted features and the accuracy of the proposed DNN. For both Identification and verification experiments, the proposed method a

关键词： Veins Feature extraction Biometrics (access control) Optimization Histograms Gabor filters Bayes methods WLD descriptor Gabor filter deep neural network stacked autoencoder Bayesian optimization

来源：评论

学校读者我要写书评

暂无评论

Mutual Information-Weighted Principle Components Identified From the Depth Features of stacked autoencoders and Original Variables for Oil Dry Point Soft Sensor

引用

IEEE ACCESS 2019年 7卷 1981-1990页

作者： Wang, Jie Yan, Xuefeng East China Univ Sci & Technol Minist Educ Key Lab Adv Control & Optimizat Chem Proc Shanghai 200237 Peoples R China

In modern chemical process control, the application of data-driven soft sensor has become increasingly extensive. Feature extraction is an important step in soft sensor. A novel feature extraction and integration method based on stacked autoencoders (SAE) and mutual information (MI)-weighted principle component analysis (PCA) was proposed to solve the loss of information on shallow depth features and original variables in neural network models. First, an SAE model was trained to extract the features of the original variables with varying depths. Second, through an MI indicator, the original variables and features with strong dependency on the outputs were selected. Then, MI was used to assign varied weights to the features and original variables, and the PCA method was used to remove any possible redundancy between the original variables and features of varying depths to obtain the principle components. Finally, the principle components were used to construct a regressor, such as a neural network. The model was first tested using the Boston housing dataset as a benchmark and then applied to the soft sensor of a constant top oil dry point. The proposed model achieved optimal results in terms of the root mean squared error and r indicators in the experiments and was thus proved feasible and useful.

关键词： Feature extraction mutual information soft sensor stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

A Passenger Flow Prediction Method Using SAE-GCN-BiLSTM for Urban Rail Transit

引用

INTERNATIONAL JOURNAL OF SWARM INTELLIGENCE RESEARCH 2024年第1期15卷 1页

作者： Liu, Fan Zhengzhou Univ Econ & Business Sch Management Zhengzhou 451191 Henan Peoples R China

To address the problems of existing passenger flow prediction methods such as low accuracy, inadequate learning of spatial features of station topology, and inability to apply to large networks, a SAE-GCN-BiLSTM-based passenger flow forecasting method for urban rail transit is proposed. First, the external features are extracted layer by layer using stacked autoencoder (SAE). Then, graph convolutional network (GCN) is used to capture the spatial features of station topology, and bi-directional long and short-term memory network (BiLSTM) is used to extract the bi-directional temporal features, realizing the extraction of the spatio-temporal features. Finally, external features and spatio-temporal features are fused for accurate prediction of urban rail transit passenger flow. The experimental results show that the proposed method is higher than several other advanced models in the evaluation indexes under different granularities, indicating that the model effectively develops the accuracy and robustness of urban rail transit passenger flow prediction.

关键词： Bi-Directional Long and Short-Term Memory Network External Features Feature Fusion Graph Convolutional Network Passenger Flow Prediction Rail Transit Spatial-Temporal Features stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Identification of Human Breathing-States Using Cardiac-Vibrational Signal for m-Health Applications

引用

IEEE SENSORS JOURNAL 2021年第3期21卷 3463-3470页

作者： Choudhary, Tilendra Sharma, L. N. Bhuyan, M. K. Bora, Kangkana IIT Guwahati Dept Elect & Elect Engn Gauhati 781039 India Cotton Univ Dept Comp Sci & Informat Technol Gauhati 7810001 India

In this work, a seismocardiogram (SCG) based breathing-state measuring method is proposed for m-health applications. The aim of the proposed framework is to assess the human respiratory system by identifying degree-of-breathings, such as breathlessness, normal breathing, and long and labored breathing. For this, it is needed to measure cardiac-induced chest-wall vibrations, reflected in the SCG signal. Orthogonal subspaceprojection is employed to extract the SCG cycles with the help of a concurrent ECG signal. Subsequently, fifteen statistically significant morphological-features are extracted from each of the SCG cycles. These features can efficiently characterize physiological changes due to varying respiratory-rates. stacked autoencoder (SAE) based architecture is employed for the identification of different respiratory-effort levels. The performance of the proposed method is evaluated and compared with other standard classifiers for 1147 analyzed SCG- beats. The proposed method gives an overall average accuracy of 91.45% in recognizing three different breathing states. The quantitative analysis of the performance results clearly shows the effectiveness of the proposed framework. It may be employed in various healthcare applications, such as pre-screening medical sensors and IoT based remote health-monitoring systems.

关键词： Seismocardiogram ECG heart cycle neural networks stacked autoencoder respiratory efforts

来源：评论

学校读者我要写书评

暂无评论

Recurrent-DC: A deep representation clustering model for university profiling based on academic graph

引用

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 2021年 116卷 156-167页

作者： Kong, Xiangjie Li, Jiaxing Wang, Luna Shen, Guojiang Sun, Yiming Lee, Ivan Zhejiang Univ Technol Coll Comp Sci & Technol Hangzhou 310023 Peoples R China Dalian Univ Technol Sch Software Dalian 116620 Peoples R China Dalian Univ Technol Inst Sci & Technol Dalian 116024 Peoples R China Univ South Australia Sch Informat Technol & Math Sci Adelaide SA 5001 Australia

Universities play an important role in exploring new concepts and knowledge transfer. University research naturally forms heterogeneous graphs through all real-life academic communication activities. In recent years, there have been many large scholarly graph datasets containing web-scale nodes and edges. However, so far, for these graph data, characterizing research about university output is focusing on counting the volume or evaluating the excellence of research articles and providing a ranking. This paper proposes a novel University Profiling Framework (UPF) from the production and complexity point of view which is different from other straightforward solutions. The framework includes a novel Recurrent Deep Clustering Model (Recurrent-DC) for the learning of deep representations and clusters. In our model, successive operations in a clustering algorithm are expressed as steps in a recurrent process, stacked on top of representations output by a stacked autoencoder (SAE). Our key idea behind this model is that good representations for university clustering task-specific problem can be learned over multiple timesteps. Experimental results illustrate the stability and effectiveness of the proposed model comparing with the other deep clustering and classical clustering methods. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Academic graph University profiling Deep representation learning Deep clustering stacked autoencoder

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：