检索结果-内蒙古大学图书馆

Detection of impact on aircraft composite structure using machine learning techniques

MEASUREMENT SCIENCE AND TECHNOLOGY 2021年第8期32卷

作者： Ai, Li Soltangharaei, Vafa Bayat, Mahmoud Van Tooren, Michel Ziehl, Paul Univ South Carolina Dept Civil & Environm Engn Columbia SC 29208 USA Collins Aerostruct Chula Vista CA USA Univ South Carolina Columbia SC 29208 USA

Aircraft structures are exposed to impact damage caused by debris and hail during their service life. One of the design concerns in composite structures is the resistance of layered surfaces to damage, which occurs from impacts with various foreign objects. Therefore, the impact localization and damage quantification of impacts should be studied and considered to address flight safety and to reduce costs associated with a regularly scheduled visual inspection. Since the structural components of the aircraft are large scale, visual inspection and monitoring are challenging and subject to human error. This paper presents a promising solution that can automatically detect and localize an impact that may occur during flight. To achieve this goal, acoustic emission (AE) is employed as an impact monitoring approach. Random forest and deep learning were adopted for training the source location models. An AE dataset was collected by conducting an impact experiment on a full-size thermoplastic aircraft elevator in a laboratory environment. A dataset consisting of AE parametric features and a dataset consisting of AE waveforms were assigned to a random forest classifier and deep learning network for the investigation of their applicability of impact source localization. The results obtained were compared using the source localization approach in previous research using a conventional artificial neural network. The analysis of results shows the random forest and deep learning leads to better event localization performance. In addition, the random forest model can provide the importance of features. By deleting the least important features, the storage required to save the input and the computing time for the random forest is greatly reduced, and an acceptable localization performance can still be obtained.

关键词： impact monitoring acoustic emission artificial neural network random forest stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based retrieval of cyanobacteria pigment in inland water for in-situ and airborne hyperspectral data

引用

ECOLOGICAL INDICATORS 2020年第0期110卷 105879-000页

作者： Yim, Inhyeok Shin, Jihoon Lee, Hyuk Park, Sanghyun Nam, Gibeom Kang, Taegu Cho, Kyung Hwa Cha, YoonKyung Univ Seoul Sch Environm Engn Seoul 130743 South Korea Natl Inst Environm Res Water Qual Assessment Res Div Environm Res Complex Incheon South Korea Ulsan Natl Inst Sci & Technol Sch Urban & Environm Engn Ulsan 689798 South Korea

Worldwide proliferation of cyanobacteria blooms in inland waters not only affects the intended use of water but potentially threatens human and animal health. In this study, a stacked autoencoder-deep neural network (SAE-DNN) was developed to estimate phycocyanin (PC) concentration by using in situ reflectance spectra in productive inland water. The estimated PC using the SAE-DNN was in close agreement with the measured PC, with an R-2 of 0.87, root mean square error (RMSE) of 14.45 mu g/L, and relative RMSE of 86.42%. The performance of the SAE-DNN was superior to that of the DNN and band-ratio algorithms. An analysis on the deep spectral features extracted using the SAE yielded the most useful spectral bands, namely 538, 596, and 735 nm, for the retrieval of PC. The estimation accuracy of the SAE-DNNPeaks, using only the aforementioned spectral bands as input variables, was comparable to that of the SAE-DNN, demonstrating that the high-level of abstraction using the SAE facilitated the improvement in feature learning. The application of the SAE-DNNPeak to airborne hyperspectral image data resulted in an acceptable estimation accuracy, despite a bias toward underestimation, potentially arising from uncertainty associated with atmospheric correction, at high PC concentrations. Our results suggest that simple, empirical-based approaches, such as the SAE-DNNPeak have the potential to serve as a rapid assessment tool for the abundance and spatial distribution of cyanobacteria.

关键词： Cyanobacteria Phycocyanin Hyperspectral imaging Deep learning Deep neural networks stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

An Advertising Fraud Detection Method based on Automatic Feature Mining of Time Series Data

International Core Journal of Engineering

引用

International Core Journal of Engineering 2021年第11期7卷 275-282页

作者： Shuo Wang Kang Yang Tongle Wang

With the continuous development of the mobile Internet, the digital advertising marketing market is also showing a trend of vigorous development. The market scale is increasing year by year, and the subsequent advertising fraud problem has gradually become a stubborn disease in the digital advertising marketing market. The traditional rule-based method does not consider the update speed, complexity and randomness of advertising fraud, while the method based on machine learning often ignores the importance of data form and the timing dependence of fraudulent user behavior. In order to solve the above problems, this paper proposes an advertising fraud detection method based on time series data automatic feature mining. First of all, considering the importance of the data form, we constructed the user behavior time series data based on the original data, and then used the improved LSTM-based autoencoder to extract high-level features for the automatic mining of user fraud characteristics, taking into account the timing dependence of fraudulent user behavior It uses multi-scale convolutional neural network to extract local salient features of different scales. In order to avoid information loss, the residual network idea is used to combine high-level features and local salient features as extracted user fraud features. Finally, a fully connected layer is used to merge Use softmax to map user fraud characteristics to whether a user is fraudulent. This article conducts experiments on real advertising traffic data. The experimental results show that the method in this article has effectively improved the F1 value.

关键词： Advertising anti-fraud Automatic Feature Mining stacked autoencoder Multi-CNN

来源：评论

学校读者我要写书评

暂无评论

Novel PV Fault Diagnoses via SAE and Improved Multi-Grained Cascade Forest With String Voltage and Currents Measures

引用

IEEE ACCESS 2020年 8卷 133144-133160页

作者： Gao, Wei Wai, Rong-Jong Chen, Shi-Qun Natl Taiwan Univ Sci & Technol Dept Elect & Comp Engn Taipei 106 Taiwan Fuzhou Univ Coll Elect Engn & Automat Fuzhou 350108 Peoples R China

The precision of conventional PV fault diagnostic methods faces challenges due to the nonlinear output power characteristics of photovoltaic (PV) arrays and the implementation of the maximum power point tracking (MPPT) algorithm. In severe cases, it may lead to power losses and even arouse safety issues. In this study, the variation characteristics of the sequence waveforms at the moment of failure are investigated and used to develop a novel PV fault diagnostic framework. Firstly, the sequence waveforms of string voltages and currents before and after the fault occurred are collected;the normalized sequence data of voltages, currents, and powers are used as analytic data. Then, the fault feature extraction is realized via a stacked autoencoder (SAE) model. After that, an improved multi-grained cascade forest (IgcForest) is proposed to diagnose faults, e.g., line-to-line (L-L) fault, open-circuit (OC) fault, partial-shading of PV arrays, etc. The advantages of the proposed method are that the SAE method to extract features with higher recognition automatically, and the IgcForest to enhance and exploit fault features. Particularly, the proposed improvements can reduce the feature vector dimension and enhance the information connectivity between forests at all levels for further improving the accuracy of diagnoses. In addition, the validity of the proposed method is verified by numerical simulations and measured data, and the corresponding accuracy of fault diagnoses for single failure reach 99.33% and 98.61%, respectively, which are superior to traditional methods, such as softmax, support vector machines, random forest, gcForest, and daForest. Furthermore, it also has a high accuracy of 98.83% for data sets with the occurrence of multiple faults.

关键词： Feature extraction Circuit faults Fault diagnosis Maximum power point trackers Forestry Arrays Current measurement Photovoltaic fault diagnosis stacked autoencoder improved multi-grained cascade forest

来源：评论

学校读者我要写书评

暂无评论

Robust classification and biomarker discovery of inherited metabolic diseases using GC-MS urinary metabolomics analysis combined with chemometrics

引用

MICROCHEMICAL JOURNAL 2023年 190卷

作者： Chen, Nan Chen, Si Zhang, Qi Wang, Si-Rui Tang, Li-Juan Jiang, Jian-Hui Yu, Ru-Qin Zhou, Yan-Ping Hunan Univ Coll Chem & Chem Engn State Key Lab Chemo Biosensing & Chemometr Changsha 410082 Peoples R China Cent China Normal Univ Coll Chem Key Lab Pesticide & Chem Biol Minist Educ Wuhan 430079 Peoples R China Wuhan Univ Res Ctr Strateg Emerging Ind Wuhan 430071 Peoples R China

Early diagnosis and treatment of inherited metabolic diseases (IMDs) is crucial for reducing neonatal mortality rate and improving quality of life in children. The discovery of disease-related biomarkers that can objectively measure the potential pathophysiological changes is vital to improve the prognosis of IMDs. In this study, we collected 90 clinic urine samples of newborns, including two types of IMDs and healthy samples, glutaric aciduria type I (GA I) and propionic acidemia (PA). And 132 metabolites were identified using gas chromatography-mass spectrometry (GC-MS). Then we proposed an integrated chemometrics strategy of assembling discrete particle swarm optimization (DPSO) into stacked autoencoder (SAE) to form a framework called DPSO-SAE for the study of GC-MS metabolomics data. SAE was known for its excellent non-linear feature learning ability. The intro-duction of DPSO afforded SAE the possibility of biomarker discovery and improving performance on classifi-cation via enabling synergetic optimization of variable combinations and the parameter of neuron numbers for SAE modeling. We then invoked DPSO-SAE for the data analysis as compared with random forest (RF), partial least squares discriminant analysis (PLSDA) and conventional SAE. Superior performance was obtained by DPSO-SAE with high accuracy and good generalization ability on classification. We further demonstrated the robust-ness of DPSO-SAE in variable selection and proofed the statistical significance of identified marker metabolites that account for IMD classification. Six potential biomarkers were proofed, including 3-methylglutaconic, 3-OH-propionic, Methylcitric, Methylmalonic and Uric for PA and Glutaric for GA I. All results indicated that the proposed strategy of DPSO-SAE was feasible for robust classification and biomarker discovery of IMDs. And it may provide a valuable modeling algorithm for metabolomics studies.

关键词： stacked autoencoder Discrete particle swarm optimization GC-MS urinary metabolomics Classification Biomarker discovery Inherited metabolic diseases

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

Accurate Prediction of Earthquake-Induced Landslides Based on Deep Learning Considering Landslide Source Area

引用

REMOTE SENSING 2021年第17期13卷 3436页

作者： Li, Yao Cui, Peng Ye, Chengming Marcato Junior, Jose Zhang, Zhengtao Guo, Jian Li, Jonathan Chinese Acad Sci Inst Mt Hazards & Environm Key Lab Mt Hazards & Earth Surface Proc Chengdu 610041 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Chengdu Univ Technol Key Lab Earth Explorat & Informat Technol Minist Educ Chengdu 610059 Peoples R China Univ Fed Mato Grosso do Sul Fac Engn Architecture & Urbanism & Geog BR-79070900 Campo Grande MS Brazil Beijing Normal Univ Acad Disaster Reduct & Emergency Management Minist Emergency Management Beijing 100875 Peoples R China Beijing Normal Univ Fac Geog Sci Minist Educ Beijing 100875 Peoples R China Changan Univ Dept Geol Engn Xian 710064 Peoples R China Univ Waterloo Dept Geog & Environm Management Waterloo ON N2L 3G1 Canada

An earthquake-induced landslide (EQIL) is a rapidly changing process occurring at the Earth's surface that is strongly controlled by the earthquake in question and predisposing conditions. Predicting locations prone to EQILs on a large scale is significant for managing rescue operations and disaster mitigation. We propose a deep learning framework while considering the source area feature of EQIL to model the complex relationship and enhance spatial prediction accuracy. Initially, we used high-resolution remote sensing images and a digital elevation model (DEM) to extract the source area of an EQIL. Then, 14 controlling factors were input to a stacked autoencoder (SAE) to search for robust features by sparse optimization, and the classifier took advantage of high-level abstract features to identify the EQIL spatially. Finally, the EQIL inventory collected from the Wenchuan earthquake was used to validate the proposed model. The results show that the proposed method significantly outperformed conventional methods, achieving an overall accuracy (OA) of 91.88%, while logistic regression (LR), support vector machine (SVM), and random forest (RF) achieved 80.75%, 82.22%, and 84.16%, respectively. Meanwhile, this study reveals that shallow machine learning models only take advantage of significant factors for EQIL prediction, but deep learning models can extract more effective information related to EQIL distribution from low-value density data, which is why its prediction accuracy is growing with increasing input factors. There is hope that new knowledge of EQILs can be represented by high-level abstract features extracted by hidden layers of the deep learning model, which are typically acquired by statistical methods.

关键词： spatial prediction earthquake-induced landslide source area feature stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Neural network with deep learning architectures

引用

JOURNAL OF INFORMATION & OPTIMIZATION SCIENCES 2018年第1期39卷 31-38页

作者： Patel, Hima Thakkar, Amit Pandya, Mrudang Makwana, Kamlesh Charotar Univ Sci & Technol Changa 388421 Gujarat India

Deep Learning is a field included in to Artificial Intelligence. It allows computational models to learn multiple levels of abstraction with multiple processing layers. This Artificial Neural Networks gives state-of-art performance in various fields like Computer Vision, Speech recognition and different domain like bioinformatics. There are mainly three architectures of Deep Learning Convolution Neural Network, Deep Neural Network and Recurrent Neural Network which provides the higher level of representation of data at each next layer. Deep Learning is required to classify high dimensional data like images, audio, video and biological data.

关键词： Neural Network Deep Learning Deep Neural Network stacked autoencoder Convolution Neural Network Recurrent Neural Network

来源：评论

学校读者我要写书评

暂无评论

Rapid assessment of landslide risk level based on deep learning

引用

ARABIAN JOURNAL OF GEOSCIENCES 2021年第3期14卷 220-220页

作者： Tan, Fei Yu, Jin Jiao, Yu-Yong Lin, Dawei Lv, Jiahe Cheng, Yi China Univ Geosci Fac Engn Wuhan 430074 Hubei Peoples R China

A rapid assessment of landslide risk level is carried out based on deep learning to speed up the process of determining landslide risk level. The problems of current assessment methods include cumbersome data processing, and the time-consuming and labor-intensive evaluation of risk factors. In this paper, 14 risk factors were analyzed, including slope topography, geology, and hydrology. The analysis involves using the stacked autoencoder (SAE) for training and testing based on an error backpropagation algorithm, and the data collected from engineered slopes as samples. Through multiple times of training, an optimized SAE model was obtained. The landslide risk level can be quickly and accurately determined by the SAE model. Then, the generalization tests further illustrate this. The complicated and lengthy data pre-processing process required in the traditional method was eliminated. This enables the risk level to be quickly determined by SAE after the landslide risk factors are identified. Therefore, a lot of time and cost will be saved by applying the proposed SAE to carry out landslide risk assessment. This will be a new direction of engineering risk assessment.

关键词： Slope Landslide risk level Deep learning stacked autoencoder Responsible Editor: Zeynal Abiddin Erguler

来源：评论

学校读者我要写书评

暂无评论

Identifying typical pre-crash scenarios based on in-depth crash data with deep embedded clustering for autonomous vehicle safety testing

引用

ACCIDENT ANALYSIS AND PREVENTION 2023年第1期191卷 107218页

作者： Zhou, Rui Huang, Helai Lee, Jaeyoung Huang, Xiangzhi Chen, Jiguang Zhou, Hanchu Cent South Univ Sch Traff & Transportat Engn Changsha 410075 Peoples R China Univ Cent Florida Dept Civil Environm & Construction Engn Orlando FL 32816 USA Newhood Technol Co Ltd Changsha 410075 Peoples R China City Univ Hong Kong Sch Data Sci Hong Kong 99907 Peoples R China

Choosing appropriate scenarios is critical for autonomous vehicles (AVs) safety testing. Real-world crash scenarios can be used as critical scenarios to test the safety performance of AVs. As one of the dominant types of traffic crashes, the car to powered-two-wheelers (PTWs) crash results in a higher possibility of fatality than ordinary car-to-car crashes. Generally, typical testing scenarios are chosen according to the subjective understanding of the safety experts with limited static features of crashes (e.g., geometric features, weather). This study introduced a novel method to identify typical car-to-PTWs crash scenarios based on real-world crashes with dynamic pre-crash features investigated from the China In-depth Mobility Safety Study-Traffic Accident (CIMSSTA) database. First, we present crash data collection and construction methods of the CIMSS-TA database to construct testing scenarios. Second, the stacked autoencoder methods are used to learn and obtain embedded features from the high-dimensional data. Third, the extracted features are clustered using k-means clustering algorithm, and then the clustering results are interpreted. Six typical car-to-PTWs scenarios are obtained with the proposed processes. This study introduces a typical high-risk scenario construction method based on deep embedded clustering. Unlike existing researches, the proposed method eliminates the negative impacts of manually selecting clustering variables and provides a more detailed scenario description. As a result, the typical scenarios obtained from AV testing are more robust.

关键词： Testing scenarios Clustering analysis Autonomous vehicles 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：