检索结果-内蒙古大学图书馆

10th Int Conf on Appl Human Factors and Ergon (AHFE) / AHFE Int Conf Human Factors in Artificial Intelligence and Social Comp / AHFE Int Conf on Human Factors, Software, Serv and Syst Engn / AHFE Int Conf of Human Factors in Energy

作者： Yang, Jaemin Lee, Subong Kim, Jonghyun Chosun Univ Dept Nucl Engn 309 Pilmun Daero Gwangju 501709 South Korea

ISBN: (纸本)9783030204549;9783030204532

Diagnosis of the accident or transient at the nuclear power plants is performed under the judgment of operators based on the procedures. Although procedures given to operators, numerous and rapidly changing parameters are generated by measurements from a variety of indicators and alarms, thus, there can be difficulties or delays to interpret a situation. In order to deal with this problem, many approaches have suggested based on computerized algorithms or networks. Although those studies suggested methods to diagnose accidents, if an unknown (or untrained) accident is given, they cannot respond as they do not know about it. In this light, this study aims at developing an algorithm to diagnose the accidents including "don't know" response. Long short term memory recurrent neural network and the auto encoder are applied for implementing the algorithm including novelty detection function. The algorithm is validated with various examples regarding untrained cases to demonstrate its feasibility.

关键词： LSTM auto encoder Accident diagnosis Novelty detection

来源：评论

学校读者我要写书评

暂无评论

Optimizing EEG - based Emotion Recognition with a multi-modal ensemble approach

引用

RESULTS IN ENGINEERING 2025年 26卷

作者： Kavitha, K., V Sudha, L. R. Jayasudha, J. S. Annamalai Univ Deaprtment Comp Sci & Engn Chidambaram India Cent Univ Kerala Dept Comp Sci Kasargod India

Emotions significantly influence human communication and are intricately associated with cerebral activity, as evidenced by EEG data, which enhances human-machinemachine interactions, especially in Brain-Computer Interfaces (BCI). Considering this potential, attaining high precision in emotion recognition from EEG data continues to pose a considerable barrier, but such progress could yield critical insights for diagnosis of mental and behavioural illnesses and facilitate treatment decision-making in clinical environments. Recent advancements in deep learning techniques have established them as formidable instruments for improving classification efficiency in BCI systems. This study presents a novel hybrid model that integrates encoder and Gated Recurrent Unit networks to enhance the accuracy of emotion categorisation using EEG data. The encoder from autoencoder is utilised for dimensionality reduction and feature extraction, generating a compressed latent representation of the input signals. The latent characteristics are subsequently input into the GRU, which captures the temporal dynamics of EEG data to forecast emotional states. The encoder is used for dimensionality reduction and feature extraction, while GRU is used to capture the temporal dynamics of EEG data. This paper introduces an ensemble technique employing Soft Voting, which integrates predictions from three deep learning models: LSTM network, a novel Deep Neural Network, and the hybrid autoencoder-GRU model. This ensemble seeks to enhance classification accuracy by utilizing the complimentary capabilities of each model. The method was validated using the EEG Brainwave Dataset. This approach was validated using the EEG Brainwave Dataset, achieving a superior classification accuracy of 97.42%, surpassing individual model performances (LSTM: 97%, GRU: 97%, autoencoder-GRU: 94%, DNN: 95%). The results confirm that the ensemble model effectively integrates complementary learning patterns from multiple archi

关键词： Long Short-Term Memory Emotion Recognition Electroencephalography Deep Learning auto encoder Gated Recurrent Unit Hybrid Model Soft Voting Ensemble Model

来源：评论

学校读者我要写书评

暂无评论

Bi directional sparse attention recurrent autoencoder based intrusion detection for VANET security with tuna swarm optimization

引用

Scientific reports 2025年第1期15卷 18406页

作者： R Gopi V Thiruppathy Kesavan Md Jakir Hossen Nor Hidayati Binti Abdul Aziz Faculty of Computer Science & Engineering Dhanalakshmi Srinivasan Engineering College Perambalur Tamil Nadu India. Post Doctoral Fellow Department of Engineering and Technology Multimedia University Malaysia Melaka Malaysia. Faculty of Information Technology Dhanalakshmi Srinivasan Engineering College Perambalur India. Faculty of Engineering and Technology (FET) Center for Advanced Analytics (CAA) COE for Artificial Intelligence Multimedia University Melaka Malaysia. jakir.hossen@mmu.edu.my. Faculty of Engineering and Technology (FET) Center for Advanced Analytics (CAA) COE for Artificial Intelligence Multimedia University Melaka Malaysia.

Vehicular Ad-hoc Networks (VANETs) have garnered a lot of consideration and research in last decades. By enhancing safety and comfort, VANETs are essential to the development of self-driving and semi-self-driving cars. Security risks that are specific to VANET or that are observed in ad hoc networks, however, pose significant difficulties. External communication with the situation through data control and Cooperative Awareness Messages (CAMs) exchanges is crucial for these vehicles. Numerous assaults could possibly target VANETs. VANETs may be vulnerable to several types of assaults. The lack of intrusion detection systems, inadequate encryption methods, insecure communication routes, and inadequate authentication processes are some of the technological flaws in VANETs that make smart vehicles vulnerable to attacks. The security and effectiveness of smart vehicle operations suffer because these flaws allow attackers to intercept, change, or interrupt communication between vehicles. Owing to these security concerns, this study introduces a Bi-directional sparse Attention-recurrent auto encoder (BSAR-AE) based Intrusion Detection System (IDS) in VANET. The system uses the Tuna Swarm optimizer (TSO) with the enhancement through the implementation of Deep Neural Network (DNN) based feature selection in VANET. It is a useful technique for resolving issues with deep layer neural networks, like low velocity and overfitting issues in learning. The evolutionary based optimization effectively tuned the hyper parameters of the DL model which will improve the detection accuracy. The system use of the CICIDS2017 dataset, which is associated with actual data and the experimented analysis shows that the proposed model is effectual for detecting the malicious attacks in VANET with improved accuracy of 98.7%.

关键词： Anomaly detection auto encoder Bidirectional long short term memory networks Intrusion detection system Tuna swarm optimization Vehicular Ad-hoc networks

来源：评论

学校读者我要写书评

暂无评论

Deep learning provides a new computed tomography-based prognostic biomarker for recurrence prediction in high-grade serous ovarian cancer

引用

RADIOTHERAPY AND ONCOLOGY 2019年 132卷 171-177页

作者： Wang, Shuo Liu, Zhenyu Rong, Yu Zhou, Bin Bai, Yan Wei, Wei Wei, Wei Wang, Meiyun Guo, Yingkun Tian, Jie Chinese Acad Sci Inst Automat CAS Key Lab Mol Imaging Beijing Peoples R China Sichuan Univ Key Lab Birth Defects & Related Dis Women & Child Dept Radiol Minist EducWest China Univ Hosp 2 Chengdu Sichuan Peoples R China Henan Prov Peoples Hosp Zhengzhou Henan Peoples R China Sichuan Univ West China Univ Hosp 2 Key Lab Birth Defects & Related Dis Women & Child Minist Educ Chengdu Sichuan Peoples R China Guizhou Prov Peoples Hosp Key Lab Intelligent Med Image Anal & Precis Diag Dept Radiol Guiyang Guizhou Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Beihang Univ Beijing Adv Innovat Ctr Big Data Based Precis Med Beijing 100191 Peoples R China

Background and purpose: Recurrence is the main risk for high-grade serous ovarian cancer (HGSOC) and few prognostic biomarkers were reported. In this study, we proposed a novel deep learning (DL) method to extract prognostic biomarkers from preoperative computed tomography (CT) images, aiming at providing a non-invasive recurrence prediction model in HGSOC. Materials and methods: We enrolled 245 patients with HGSOC from two hospitals, which included a feature-learning cohort (n = 102), a primary cohort (n = 49) and two independent validation cohorts from two hospitals (n = 49 and n = 45). We trained a novel DL network in 8917 CT images from the feature-learning cohort to extract the prognostic biomarkers (DL feature) of HGSOC. Afterward, a DL-CPH model incorporating the DL feature and Cox proportional hazard (Cox-PH) regression was developed to predict the individual recurrence risk and 3-year recurrence probability of patients. Results: In the two validation cohorts, the concordance-index of the DL-CPH model was 0.713 and 0.694. Kaplan-Meier's analysis clearly identified two patient groups with high and low recurrence risk (p = 0.0038 and 0.0164). The 3-year recurrence prediction was also effective (AUC = 0.772 and 0.825), which was validated by the good calibration and decision curve analysis. Moreover, the DL feature demonstrated stronger prognostic value than clinical characteristics. Conclusions: The DL method extracts effective CT-based prognostic biomarkers for HGSOC, and provides a non-invasive and preoperative model for individualized recurrence prediction in HGSOC. In addition, the DL-CPH model provides a new prognostic analysis method that can utilize CT data without follow-up for prognostic biomarker extraction. (C) 2018 The Authors. Published by Elsevier B.V.

关键词： Deep learning High-grade serous ovarian cancer Recurrence Prognosis Computed tomography Artificial intelligence Semi-supervised learning auto encoder Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

A novel improved deep convolutional neural network model for medical image fusion

引用

CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS 2019年第1-Sup期22卷 1515-1527页

作者： Xia, Kai-jian Yin, Hong-sheng Wang, Jiang-qiang China Univ Min & Technol Sch Informat & Control Engn Xuzhou 221116 Jiangsu Peoples R China Soochow Univ Changshu Hosp Changshu Peoples Hosp 1 Changshu 215500 Jiangsu Peoples R China

This paper proposed a novel fusion scheme for muti-modal medical images that utilizes both the features of the multi-scale transformation and deep convolutional neural network. Firstly, the source images are decomposed by the Gauss-Laplace filter and Gaussian filter into several sub-images in the first layer of network. Then, HeK-based method is used to initialize the convolution kernel of the rest layers, construct the basic unit, and use the back propagation algorithm to train the basic unit;Train multiple basic units that are sacked with the thought of SAE to get the deep stacked neural network;the proposed network is adopted to decompose the input images to obtain their own high frequency and low frequency images, and combine the our fusion rule to fuse the two high frequency and low frequency images, and put them back to the last layer of the network to get the final fusion images. The performance of our proposed fusion method is evaluated by conducting several experiments on the different medical image datasets. Experimental results demonstrate that our proposed method does not only produce better results by successfully fusing the different images, but also ensures an improvement in the various quantitative parameters as compared to other existing methods. In addition, the speed of our improved CNN method is much faster than that of comparison algorithms which have good fusion quality.

关键词： Image fusion Multi-scale transformation Deep learning Fusion rules auto encoder CNN modal

来源：评论

学校读者我要写书评

暂无评论

Targeted unsupervised features learning for gene expression data analysis to predict cancer stage 10

Targeted unsupervised features learning for gene expression ...

引用

10th International Conference on Computational Systems-Biology and Bioinformatics (CSBio)

作者： Zenbout, Imene Meshoul, Souham Bouramoul, Abdelkrim Abedlhamid Mehri Univ Constantine 2 NTIC Fac Dept Fundamental Informat & Its Applicat Constantine Algeria CERIST CRBT Constantine Algeria Abedlhamid Mehri Univ Constantine 2 NTIC Fac Dept Fundamental Informat & Its Applicat Misc Lab Constantine Algeria Princess Nourah Bint Abdulrahman Univ Riyadh Saudi Arabia

ISBN: (纸本)9781450372152

The intensive explosion in the generation of large scale cancer gene expression data brought several computational challenges, yet opened great opportunities in exploring different pathways in order to improve cancer prognosis, diagnosis and treatment. In this paper, we propose a targeted unsupervised learning model, based on deep autoencoders (TAE) to learn significant cancer representation based on the gene expression omnibus(GEO) integrated expO data set, for the ultimate goal of constructing an accurate cancer stage predictive model. Where, the trained model was tested on two gene expression cancer data sets namely, lung cancer for clinical stage and intensive breast cancer (IBC) for pathological stage. In which, the model extracted new features space for the two cancer type based on the knowledge built from the expO data set. The generated features were used to train classifiers to predict the cancer stage of each sample. We evaluated the effectiveness of our proposal by comparison to the principal component analysis (PCA) unsupervised dimensionality reduction, as well as to the supervised univariate features selection method. The experimental results, show a promising performance of our analysis model to build a collaborative knowledge from different cancer type to enhance the prediction rate of different cancer stage.

关键词： Unsupervised learning Feature selection Gene expression Deep Learning auto encoder Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Cyber Attack Detection by Using Neural Network Approaches: Shallow Neural Network, Deep Neural Network and autoencoder 26th

Cyber Attack Detection by Using Neural Network Approaches: S...

引用

26th International Conference on Computer Networks (CN)

作者： Ustebay, Serpil Turgut, Zeynep Aydin, M. Ali Istanbul Medeniyet Univ Istanbul Turkey Halic Univ Istanbul Turkey Istanbul Univ Cerrahpasa Istanbul Turkey

ISBN: (纸本)9783030219529;9783030219512

As the accuracy rate of artificial intelligence based applications increased, they have started to be used in different areas. Artifical Neural Networks (ANN) can be very successful for extracting meaningful data from features by processing complex data. Well-trained models can solve difficult problems with high a high accuracy rate. In this study, 2 different ANN models have been developed to detect malicious users who want to access high-security servers. These models are tested from simple to complex: Shallow Neural Network (SNN), Deep Neural Network (DNN), and auto encoder are used to reduce features. All models are trained with CICIDS2017 dataset. Server connection requests are classified as normal or malicious (Brute Force, Web Attack, In ltration, Botnet or DDoS) with 98.45% accuracy rate.

关键词： Shallow Neural Network auto encoder Deep Neural Network IDS Cyberattack

来源：评论

学校读者我要写书评

暂无评论

Clean speech AE-DNN PSD constraint for MCLP based reverberant speech enhancement 27

Clean speech AE-DNN PSD constraint for MCLP based reverberan...

引用

27th European Signal Processing Conference (EUSIPCO)

作者： Chetupalli, Srikanth Raj Sreenivas, Thippur, V Indian Inst Sci Dept Elect Commun Engn Bengaluru 560012 India

ISBN: (纸本)9789082797039

Blind inverse filtering using multi-channel linear prediction (MCLP) in short-time Fourier transform (STFT) domain is an effective means to enhance reverberant speech. Traditionally, a speech power spectral density (PSD) weighted prediction error (WPE) minimization approach is used to estimate the prediction filters, independently in each frequency bin. The method is sensitive to the estimation of desired signal PSD. In this paper, we propose an auto-encoder (AE) deep neural network (DNN) based constraint for the estimation of desired signal PSD. An auto encoder trained on clean speech STFT coefficients is used as the prior to non-linearly map the natural speech PSD. We explore two different architectures for the auto-encoder: (i) fully-connected (FC) feed-forward, and (ii) recurrent long short-term memory (LSTM) architecture. Experiments using real room impulse responses show that the LSTM-DNN based PSD estimate performs better than the traditional methods for reverberant signal enhancement.

关键词： Dereverberation Multi channel linear prediction auto encoder Deep neural network prior

来源：评论

学校读者我要写书评

暂无评论

A BASIC STUDY ON RAILWAY FACILITY EXTRACTION USING A SINGLE-SHOT MULTI-BOX DETECTOR 18

A BASIC STUDY ON RAILWAY FACILITY EXTRACTION USING A SINGLE-...

引用

International Conference on Machine Learning and Cybernetics (IMLC)

作者： Nakamura, Masami Aoto, Yuta Maeda, Shunji Hiroshima Inst Technol Dept Elect & Comp Engn Hiroshima Japan

ISBN: (纸本)9781728128160

In railway facilities, there are numerous types and electric train-line facilities. It is difficult to visually inspect all of them, so automatic visual inspection is expected. To achieve automatic inspection, it is important to extract and diagnose the target facilities. This study focuses on facilities extraction by utilizing single-shot multi-box detector (SSD), which can be used as a discriminator for human, car and boat object detection, etc. Diagnosis using Local Subspace Classifier (LSC) is proposed. Herein, we present the evaluation results and the issues applying SSD to the equipment called hangers connecting overhead lines. Some diagnosis results are also explained.

关键词： Railway maintenance Electric train line facilities Single shot multi-box detector Local subspace classifier auto encoder Variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Prediction Based Deep autoencoding Model for Anomaly Detection 14th

Prediction Based Deep Autoencoding Model for Anomaly Detecti...

引用

14th Asian Conference on Computer Vision (ACCV)

作者： Pang, Zhanzhong Yu, Xiaoyi Sun, Jun Hiroya, Inakoshi Fujitsu R&D Ctr Co Ltd Beijing Peoples R China Fujitsu Labs Ltd Kawasaki Kanagawa Japan

ISBN: (纸本)9783030210748

Latent variables and reconstruction error generated from auto encoder are the common means for anomaly detection dealing with high dimensional signals. They are exclusively typical representations of the original input, and a plenty of methods utilizing them for anomaly detection have achieved good results. In this paper, we propose a new method combining these two features together to generate proper scores for anomaly detection. As both these two features contain useful information contributing to anomaly detection, good results can be expected by fusion of those two. The architecture proposed in this paper comprises of two networks, and we only use normal data for training. To compress and rebuild an input, a deep auto encoder (AE) is utilized where low dimensional latent variables and reconstruction error can be obtained, and compactness loss is introduced on latent variables to maintain a low intra-variance. Meanwhile, multi-layer perceptron (MLP) network which takes the generated latent variables as input is established aiming at predicting its corresponding reconstruction error. By introducing MLP network, anomalies sharing similar reconstruction error yet different distribution of latent variables to normal data or vice versa can be separated. These two networks, AE and MLP are trained jointly in our model and the prediction error form MLP network is used as the final score for anomaly detection. Experiments on several benchmarks including image and multivariable datasets demonstrate the effectiveness and practicability of this new approach when comparing with several up-to-data algorithms.

关键词： Anomaly detection auto encoder Prediction mechanism

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：