检索结果-内蒙古大学图书馆

A deep autoencoder based approach for the inverse design of an acoustic-absorber

ENGINEERING WITH COMPUTERS 2024年第1期40卷 279-300页

作者： Mahesh, K. Ranjith, S. Kumar Mini, R. S. Coll Engn Trivandrum Govt Kerala Dept Mech Engn Thiruvananthapuram 695016 Kerala India Coll Engn Trivandrum Govt Kerala Dept Mech Engn Micro Nanofluid Res Lab Thiruvananthapuram 695016 Kerala India APJ Abdul Kalam Technol Univ Thiruvananthapuram 695016 Kerala India

This paper proposes an algorithm to perform the inverse design of a low-frequency acoustic absorber using a deep convolutional autoencoder network. A hybrid sound-absorber configuration based on Helmholtz resonators with inserted curvy neck and microperforated panel is suggested and its geometrical properties are inversely forecasted from the targeted signal. A mathematical model is put forwarded to evaluate the absorption characteristics of the introduced geometry by employing the effective medium theory and the electro-acoustic analogy. The large dataset required to train, validate and test the deep neural network is extracted through this analytical procedure. Initially, the proposed inverse technique is successfully applied on a standard Helmholtz resonator based absorber setup with great accuracy. This prediction approach is further extended to suit the inverse design of a hybrid sound absorber with complex geometrical attributes. The encoder maps the input acoustic absorption spectrum to geometrical features of the absorber, and the subsequent decoder recreates the absorption characteristics using convolutional layers. Once the training and testing of the neural network are over, the deep autoencoder inversely predicts the geometrical parameters. In comparison with earlier inverse models which employed deep neural networks, the accuracy of the current scheme is very high and no pre-design information on absorber geometry is required as well. Since the relevant learnable parameters involved are very low, the computational load is also very less for this autoencoder based method. Later, using the new inverse scheme, four representative absorber designs with specific acoustic functionality are deduced. Most importantly, these four compact absorber models produce quasi-perfect absorption in the frequency bands 200-315 Hz, 255-400 Hz, 300-530 Hz, and 350-650 Hz. Notably, the developed absorber versions have great potential in noise reduction applications owing to t

关键词： Low frequency sound absorption Helmholtz resonator Analytical modelling Electro-acoustic analogy convolutional autoencoder Inverse design

来源：评论

学校读者我要写书评

暂无评论

A fault diagnosis method for rolling bearings in open-set domain adaptation with adversarial learning

引用

SCIENTIFIC REPORTS 2025年第1期15卷 1-19页

作者： Lei, Tongfei Pan, Feng Hu, Jiabei He, Xu Li, Bing Xijing Univ Sch Mech Engn Xian 710123 Peoples R China Xian Aeronaut Comp Tech Res Inst Xian 710068 Peoples R China Chinese Acad Sci Xian Inst Opt & Precis Mech Xian 710119 Peoples R China Shaanxi Inst Elect Technol Co Ltd Xian 710000 Peoples R China

The closed-set assumption often fails in practical industrial applications, especially considering diverse working conditions where the data distribution may differ significantly. In light of this, a domain adaptation method with adversarial learning is designed for open-set fault diagnosis. Firstly, convolutional autoencoder is developed to distill the fault features;Secondly, an unknown boundary by weighting the similarity between known and unknown classes is established, to ensure shared class alignment between domains while classifying known classes across domains and identifying unknown fault samples. Finally, the diagnostic performance is evaluated using three sets of rolling bearing datasets. The proposed method achieved average diagnostic F1-scores of 96.60%, 96.56%, and 96.62% on these datasets, respectively. The results demonstrate that the method effectively rejects unknown fault data in the target domain while aligning known classes, validating its fault diagnosis capability under the open-world assumption.

关键词： Open-set fault diagnosis Adversarial learning convolutional autoencoder Known classes Unknown classes

来源：评论

学校读者我要写书评

暂无评论

A deep learning approach for spatial error correction of numerical seasonal weather prediction simulation data

引用

Big Earth Data 2023年第2期7卷 231-250页

作者： Stelios Karozis Iraklis A.Klampanos Athanasios Sfetsos Diamando Vlachogiannis Environmental Research Laboratory(EREL) INRaSTESNational Centre for Scientific Research“Demokritos”AthensGreece Institute of Informatics and Telecommunications National Centre for Scientific Research“Demokritos”AthensGreece

Numerical Weather Prediction(NWP)simulations produce meteorological data in various spatial and temporal scales,depending on the application *** the current study,a deep learning approach,based on convolutional autoencoders,is explored to effectively correct the error of the NWP *** undercomplete convolutional autoencoder(CAE)is applied as part of the dynamic error correction of NWP *** work is an attempt to improve the seasonal forecast(3-6 months ahead)data accuracy for Greece using a global reanalysis dataset(that incorporates observations,satellite imaging,etc.)of higher spatial *** specifically,the publically available Meteo France Seasonal(Copernicus platform)and the National Centers for Environmental Prediction(NCEP)Final Analysis(FNL)(NOAA)datasets are *** addition,external information is used as evidence transfer,concerning the time conditions(month,day,and season)and the simulation characteristics(initialization of simulation).It is found that convolutional autoencoders help to improve the resolution of the seasonal data and successfully reduce the error of the NWP data for 6-months ahead ***,the month evidence yields the best agreement indicating a seasonal dependence of the performance.

关键词： Seasonal weather prediction neural networks convolutional autoencoder evidence transfer

来源：评论

学校读者我要写书评

暂无评论

Abnormal Data Detection Model Based on autoencoder and Random Forest Algorithm: Camera Sensor Data in Autonomous Driving Systems

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2025年第3期16卷 222-231页

作者： Shengwen, Geng Osman, Mohd Hafeez Univ Putra Malaysia Fac Comp Sci & Informat Technol Serdang 43400 Malaysia

This project develops an AI-based anomaly detection system. In the field of autonomous driving, abnormal data will directly affect the safety of autonomous driving systems, especially in terms of abnormal camera sensor data. Sensor failure, environmental changes, or bad weather can lead to the emergence of abnormal data, which can affect the decision-making process and may have disastrous consequences. Based on the above problems, this study addresses this challenge by proposing a hybrid anomaly detection model (called CAE-RF) that combines convolutional autoencoders and random forest algorithms to achieve efficient and accurate identification of abnormal data patterns to improve the safety of autonomous driving systems. The proposed method will use convolutional autoencoders to calculate the reconstruction error and combine the hidden features extracted by the encoder as the input of the random forest to distinguish normal data from abnormal data. The key performance indicators such as accuracy, precision, recall, and F1 score are used to evaluate the model, and the robustness is guaranteed by cross-validation. Experimental results show that the CAE-RF model has an accuracy of 92% in distinguishing normal and abnormal data. Compared with traditional methods, the CAE-RF model achieves higher accuracy and reliability. The implementation of this model can timely identify and process abnormal data, reduce the risks brought by sensor failure or external environment changes, prevent potential accidents, and improve the safety and reliability of the autonomous driving system.

关键词： Automatic driving anomaly data detection convolutional autoencoder random forest CAE-RF

来源：评论

学校读者我要写书评

暂无评论

DC4Flood: A Deep Clustering Framework for Rapid Flood Detection Using Sentinel-1 SAR Imagery

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2024年 21卷 1-1页

作者： Shahi, Kasra Rafiezadeh Camero, Andres Eudaric, Jeremy Kreibich, Heidi GFZ German Res Ctr Geosci Sect Hydrol D-14473 Potsdam Brandenburg Germany EO Data Sci Remote Sensing Technol Inst German Aerosp Ctr DLR D-82284 Wessling Bayern Germany

Severe flood losses have been on the rise, and this trend is expected to become increasingly prevalent in the future due to climate and socio-economic changes. Swiftly identifying flooded areas is crucial for mitigating socio-economic losses and facilitating effective recovery. Synthetic aperture radar (SAR) sensors are operational in all-weather, day-and-night conditions and offer a rapid, accurate, and cost-effective means of obtaining information for quick flood mapping. However, the complex nature of SAR images, such as speckle noise, coupled with the often absence of training/labeled samples, presents significant challenges in their processing procedures. To alleviate such hindrances, we can benefit from unsupervised classification approaches (also known as clustering). Clustering methods offer valuable insights into newly acquired datasets without the need for training or labeled samples. However, traditional clustering approaches are predominantly linear-based and overlook the spatial information of neighboring pixels during analysis. Thus, to attenuate these challenges, we propose a deep-learning (DL)-based clustering approach for flood detection (DC4Flood) using SAR images. The primary advantage of DC4Flood over existing DL-based clustering approaches lies in its ability to capture multiscale spatial information. This is achieved using multiple dilated convolutions with varying dilation rates and subsequently fusing the extracted multiscale information to effectively and efficiently analyze SAR images in an unsupervised manner. Extensive experiments conducted on SAR images from six different flood events demonstrate the effectiveness of the proposed DC4Flood. The code of the work will be available at https://***/Kasra2020/DC4Flood.

关键词： Radar polarimetry Floods Feature extraction Synthetic aperture radar Laser radar Radar imaging Training Clustering convolutional autoencoder deep learning (DL) flood detection remote sensing (RS) Sentinel-1 synthetic aperture radar (SAR) unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing LPI Radar Signal Classification Through Patch-Based Noise Reduction

引用

IEEE SIGNAL PROCESSING LETTERS 2024年 31卷 716-720页

作者： Kim, Junseob Cho, Sunghwan Hwang, Sunil Lee, Wonjin Choi, Yeongyoon Korea Mil Acad Seoul 01805 South Korea Def Acquisit Program Adm Gwacheon 13809 South Korea LIG Nex1 Pangyo 13488 South Korea Gwangju Inst Sci & Technol Gwangju 61005 South Korea

This letter presents a novel patch-based noise reduction framework designed to enhance the performance of Low Probability of Intercept (LPI) radar waveform classification. The proposed approach capitalizes on the unique characteristic of the waveform's Time-Frequency Images (TFIs) being concentrated in the central region of the image. By partitioning the noisy image into multiple patches, each patch is independently processed using convolutional autoencoders. This method effectively eliminates noise and restores the signal in low Signal-to-Noise Ratio (SNR) environments, thus mitigating interference between the signal and noise components. Simulation results demonstrate the superior performance of the proposed method, achieving an 11% improvement in accuracy compared to classifying noisy images at a -10 dB SNR.

关键词： Noise reduction Radar Convolution Noise measurement Signal to noise ratio Image reconstruction Time-frequency analysis LPI radar convolutional autoencoder time-frequency image noise reduction signal classification

来源：评论

学校读者我要写书评

暂无评论

Index tracking using shapley additive explanations and one-dimensional pointwise convolutional autoencoders

引用

INTERNATIONAL REVIEW OF FINANCIAL ANALYSIS 2024年第PartC期95卷

作者： Zhang, Yanyi De Smedt, Johannes Res Ctr Informat Syst Engn LIRIS Naamsestr 69 B-3000 Leuven Belgium

The aim of index tracking is to mimic the performance of a benchmark index via minimizing the tracking error between the returns of the market index and the tracking portfolio. Lately, various deep learning solutions have been proposed to perform stock prediction or active investment. However, there remains a gap in literature to explore the application of deep learning to index tracking. In this paper, the one-dimensional Pointwise convolutional autoencoder is proposed to capture the main market characteristics and the Shapley Additive Explanations feature importance ranking is applied to select stocks to implement the partial replication index tracking with and without Covid-19 data. Moreover, portfolios with different holding periods and with different rebalancing frequency are created on different financial markets to check the effectiveness of the proposed strategy. Compared with different benchmark stock selection strategies, including Pearson correlation, mutual information, and Euclidean distance, the proposed strategy achieves state-of-the-art performance on different financial markets.

关键词： Index tracking Deep learning convolutional autoencoder Pointwise convolution Feature importance ranking

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2023年第2期35卷 2118-2132页

作者： Zhang, Yuxin Chen, Yiqiang Wang, Jindong Pan, Zhiwen Global Energy Interconnect Dev & Cooperat Org Beijing 100031 Peoples R China Chinese Acad Sci Inst Comp Technol Beijing Key Lab Mobile Comp & Pervas Device Beijing 100864 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Peng Cheng Lab PCL Shenzhen 518066 Peoples R China Microsoft Res Asia Beijing 100080 Peoples R China

Nowadays, multi-sensor technologies are applied in many fields, e.g., Health Care (HC), Human Activity Recognition (HAR), and Industrial Control System (ICS). These sensors can generate a substantial amount of multivariate time-series data. Unsupervised anomaly detection on multi-sensor time-series data has been proven critical in machine learning researches. The key challenge is to discover generalized normal patterns by capturing spatial-temporal correlation in multi-sensor data. Beyond this challenge, the noisy data is often intertwined with the training data, which is likely to mislead the model by making it hard to distinguish between the normal, abnormal, and noisy data. Few of previous researches can jointly address these two challenges. In this paper, we propose a novel deep learning-based anomaly detection algorithm called Deep convolutional Autoencoding Memory network (CAE-M). We first build a Deep convolutional autoencoder to characterize spatial dependence of multi-sensor data with a Maximum Mean Discrepancy (MMD) to better distinguish between the noisy, normal, and abnormal data. Then, we construct a Memory Network consisting of linear (Autoregressive Model) and non-linear predictions (Bidirectional LSTM with Attention) to capture temporal dependence from time-series data. Finally, CAE-M jointly optimizes these two subnetworks. We empirically compare the proposed approach with several state-of-the-art anomaly detection methods on HAR and HC datasets. Experimental results demonstrate that our proposed model outperforms these existing methods.

关键词： Anomaly detection Predictive models Data models Autoregressive processes Image reconstruction Forecasting Computational modeling Unsupervised anomaly detection multi-sensor time series convolutional autoencoder attention based BiLSTM

来源：评论

学校读者我要写书评

暂无评论

Privacy-protecting behaviours of risk detection in people with dementia using videos

引用

BIOMEDICAL ENGINEERING ONLINE 2023年第1期22卷 1-17页

作者： Mishra, Pratik K. Iaboni, Andrea Ye, Bing Newman, Kristine Mihailidis, Alex Khan, Shehroz S. Univ Toronto Inst Biomed Engn Toronto ON Canada Univ Hlth Network KITE Toronto Rehabil Inst Toronto ON Canada Univ Toronto Temerty Fac Med Dept Psychiat Toronto ON Canada Ryerson Univ Daphne Cockwell Sch Nursing Toronto ON Canada

Background People living with dementia often exhibit behavioural and psychological symptoms of dementia that can put their and others' safety at risk. Existing video surveillance systems in long-term care facilities can be used to monitor such behaviours of risk to alert the staff to prevent potential injuries or death in some cases. However, these behaviours of risk events are heterogeneous and infrequent in comparison to normal events. Moreover, analysing raw videos can also raise privacy concerns. Purpose In this paper, we present two novel privacy-protecting video-based anomaly detection approaches to detect behaviours of risks in people with dementia. Methods We either extracted body pose information as skeletons or used semantic segmentation masks to replace multiple humans in the scene with their semantic boundaries. Our work differs from most existing approaches for video anomaly detection that focus on appearance-based features, which can put the privacy of a person at risk and is also susceptible to pixel-based noise, including illumination and viewing direction. We used anonymized videos of normal activities to train customized spatio-temporal convolutional autoencoders and identify behaviours of risk as anomalies. Results We showed our results on a real-world study conducted in a dementia care unit with patients with dementia, containing approximately 21 h of normal activities data for training and 9 h of data containing normal and behaviours of risk events for testing. We compared our approaches with the original RGB videos and obtained a similar area under the receiver operating characteristic curve performance of 0.807 for the skeleton-based approach and 0.823 for the segmentation mask-based approach. Conclusions This is one of the first studies to incorporate privacy for the detection of behaviours of risks in people with dementia. Our research opens up new avenues to reduce injuries in long-term care homes, improve the quality of life of residents,

关键词： Skeleton Semantic segmentation Behaviours of risk People with dementia convolutional autoencoder Anomaly detection Video

来源：评论

学校读者我要写书评

暂无评论

Classifying and Localizing Abnormalities in Brain MRI Using Channel Attention Based Semi-Bayesian Ensemble Voting Mechanism and convolutional Auto-Encoder

引用

IEEE ACCESS 2023年 11卷 75528-75545页

作者： Shah, Syed Muhammad Ahmed Hassan Ullah, Asad Iqbal, Jawaid Bourouis, Sami Ullah, Syed Sajid Hussain, Saddam Khan, Muhammad Qasim Shah, Yaser Ali Mustafa, Ghulam COMSATS Univ Islamabad Dept Comp Sci Attock Campus Attock 43600 Pakistan Riphah Int Univ Fac Comp Islamabad 45210 Pakistan Taif Univ Coll Comp & Informat Technol Dept Informat Technol Taif 21944 Saudi Arabia Univ Agder UiA Dept Informat & Commun Technol N-4898 Grimstad Norway Univ Brunei Darussalam Sch Digital Sci Jalan Tungku Link Gadong 1410 Brunei Shifa Tameer Emillat Univ Dept Comp Sci Islamabad 44000 Pakistan

Adults who have brain tumors face a serious and potentially fatal challenge since the tumors rapidly growing malignant cells can seriously impair their physiological ability. In clinical practice, imaging techniques such as MRI, PET, and CT scans are widely used to determine the size, kind, and location of tumors. The goal of this research is to create a Computer-Aided Diagnostic (CAD) system that can automatically segment and classify brain tumors utilizing T1W-CE Magnetic Resonance Imaging (MRI) of the brain. The CAD system will involve two primary tasks: tumor classification, which determines the type of tumor depicted in the image, and tumor segmentation, which involves accurately determine the tumor region from the surrounding healthy tissue. By automating these processes, the proposed system aims to enhance the accuracy and effectiveness of brain tumor diagnosis and treatment planning. The classification of brain tumors into multiple classes is recognized as a complex challenge within the field of medical imaging. This research article proposes a model named VS-BEAM that can be used efficiently for clinical decision-making. The proposed VS-BEAM (Voting Based Semi-Supervised Bayesian Ensemble Attention Mechanism) model has been examined for a brain tumor's multi-class classification. The VS-BEAM model achieved the highest level of accuracy possible. The proposed work achieves maximum sensitivity, specificity, and diagnostic accuracy compared to existing models using T1W-CE MRI images. A convolutional autoencoder is utilized for extracting tumors from MRI images. The accuracy obtained from testing data of 264 brain tumors was 98.91%, indicating that the method is effective and can be used in the clinical context to assist in detecting larger or even smaller tumors.

关键词： Magnetic resonance imaging medical imaging squeeze and excitation networks Bayesian learning ensemble learning convolutional autoencoder directed acyclic graph (DAG) network brain tumors

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：