检索结果-内蒙古大学图书馆

27th International Conference on Computer Supported Cooperative Work in Design (CSCWD)

作者： Peng, Jun Yuan, Wei Liu, Yongjie Liu, Zheng Li, Heng Cent South Univ Sch Comp Sci & Engn Changsha Peoples R China Cent South Univ Sch Automat Changsha Peoples R China Cent South Univ Sch Elect Informat Changsha Peoples R China

ISBN: (纸本)9798350349184;9798350349191

Thermal runaway of lithium-ion batteries is one of the key challenges hindering the development of electric vehicles. Realizing timely fault detection in battery systems is of great significance for preventing thermal runaways and safeguarding people's lives and properties. As it is difficult to obtain fault battery datasets in the real world, there is a need to develop novel fault detection methods that can operate with normal data. In this paper, we propose an optimized Gated Recurrent Unit autoencoder architecture that integrates the sparse representation technique to detect battery faults in electric vehicles. Firstly, the Gated Recurrent Unit is employed to efficiently learn the information in battery data from normal electric vehicles. Then, the autoencoder utilizes the sparse representation technique to improve its ability to recognize abnormal data by learning a set of basis vectors that can sparsely represent normal data. Finally, the reconstruction errors between the original and reconstructed vectors are calculated in a sliding window and compared to the threshold to detect the fault. The effectiveness of the proposed method is verified on a real operating dataset including two normal electric vehicles and two faulty electric vehicles. The results show that it can provide early alarm time and reduce the probability of false alarms.

关键词： Fault detection autoencoder Data-driven,Thermal runaway

来源：评论

学校读者我要写书评

暂无评论

In-field Fault Detection Framework for Edge Accelerator using autoencoder 8

In-field Fault Detection Framework for Edge Accelerator usin...

引用

8th IEEE International Test Conference India (ITC India)

作者： Haripriya, R. S. Tudu, Jaynarayan T. Indian Inst Technol Tirupati Dept Elect Engn Chindepalle India Indian Inst Technol Tirupati Dept Comp Sci & Engn Chindepalle India

ISBN: (纸本)9798350352603;9798350352597

AI accelerators are ubiquitous across all computational domains, including safety-critical systems such as autonomous driving. However, they are also susceptible to dynamic faults due to aging-related and missed permanent manufacturing defects manifesting during in-field operation. Detecting such faults early during in-field operations is essential, particularly for the processing elements with fewer resources. The fault detection framework should operate at the level of predictions rather than individual neurons to achieve fault detection with minimal resource overhead. The output of the classifier network could have captured the fault effects as they propagate through both hardware and software architecture. In this work, we propose a methodology that uses the input image and the logits (output of the classifier network without softmax function) to predict the correctness of the prediction. The method detects the faults that significantly reduce the top1 accuracy by more than 50%. This methodology necessitates one-time training of the decoder and additional computation of 1904 neurons using a 3-layer lightweight detection network during in-field operation for fault detection. However, traditional redundancy-based methods such as Dual Modular Redundancy require an additional 4950 neuron computation, equivalent to the classifier network. The proposed method results in around 61% lesser neuron computation compared to traditional methods and a 99.99% critical fault detection rate.

关键词： Accelerator Convolutional layer Fully connected Layer autoencoder Decoder Fault model In-field testing

来源：评论

学校读者我要写书评

暂无评论

Enhancing One-Shot Action Recognition from Occluded Skeletons with a Spatial-Temporal Denoising autoencoder 39

Enhancing One-Shot Action Recognition from Occluded Skeleton...

引用

39th Youth Academic Annual Conference of Chinese-Association-of-Automation (YAC)

作者： Liu, Shengyu Liu, Cuiwei Qiu, Huaijun Shenyang Aerosp Univ Shenyang Peoples R China

ISBN: (纸本)9798350390780;9798350379228

In this paper, we tackle the challenge of one-shot action recognition from occluded skeleton data. The task uses limited labeled samples to learn an action recognition model to cope with the time-consuming and laborious problem of annotating a large amount of data. Additionally, the unavoidable occlusion of human joints in real-life scenarios significantly complicates skeleton action recognition efforts. To address these issues, we introduce a novel Spatial-Temporal Denoising autoencoder (ST-DAE) designed for skeleton-based one-shot action recognition. Employing an encoder-decoder architecture, the encoder extracts intrinsic patterns of movements from input occluded skeletons, whereas the decoder learns to reconstruct the skeletons under the supervision of clean skeletons. Then a Spatial-Temporal GCN (ST-GCN) backbone network learns to map the reconstructed skeletons into a high-dimensional feature space to capture their essential characteristics for action recognition. Finally, one-shot action recognition is achieved by a KNN classifier in the learned feature space. Experimental validations on the comprehensive NTU-RGB+D 120 RE occlusion dataset demonstrate the effectiveness of the proposed spatial-temporal denoising autoencoder against noisy skeleton data.

关键词： Skeleton-based one-shot action recognition occluded skeletons autoencoder

来源：评论

学校读者我要写书评

暂无评论

Quantized non-volatile nanomagnetic domain wall synapse based autoencoder for efficient unsupervised network anomaly detection

引用

NEUROMORPHIC COMPUTING AND ENGINEERING 2024年第2期4卷 024012-024012页

作者： Alam, Muhammad Sabbir Al Misba, Walid Atulasimha, Jayasimha Virginia Commonwealth Univ Dept Mech & Nucl Engn Richmond VA 23298 USA Virginia Commonwealth Univ Dept Elect & Comp Engn Richmond VA 23298 USA Lawrence Berkeley Natl Lab Mat Sci Div Berkeley CA 94720 USA Univ Calif Berkeley Dept Elect Engn & Comp Sci Berkeley CA 94720 USA

Anomaly detection in real-time using autoencoders implemented on edge devices is exceedingly challenging due to limited hardware, energy, and computational resources. We show that these limitations can be addressed by designing an autoencoder with low-resolution non-volatile memory-based synapses and employing an effective quantized neural network learning algorithm. We further propose nanoscale ferromagnetic racetracks with engineered notches hosting magnetic domain walls (DW) as exemplary non-volatile memory-based autoencoder synapses, where limited state (5-state) synaptic weights are manipulated by spin orbit torque (SOT) current pulses to write different magnetoresistance states. The performance of anomaly detection of the proposed autoencoder model is evaluated on the NSL-KDD dataset. Limited resolution and DW device stochasticity aware training of the autoencoder is performed, which yields comparable anomaly detection performance to the autoencoder having floating-point precision weights. While the limited number of quantized states and the inherent stochastic nature of DW synaptic weights in nanoscale devices are typically known to negatively impact the performance, our hardware-aware training algorithm is shown to leverage these imperfect device characteristics to generate an improvement in anomaly detection accuracy (90.98%) compared to accuracy obtained with floating-point synaptic weights that are extremely memory intensive. Furthermore, our DW-based approach demonstrates a remarkable reduction of at least three orders of magnitude in weight updates during training compared to the floating-point approach, implying significant reduction in operation energy for our method. This work could stimulate the development of extremely energy efficient non-volatile multi-state synapse-based processors that can perform real-time training and inference on the edge with unsupervised data.

关键词： domain wall autoencoder unsupervised learning anomaly detection NSL-KDD quantized weight magnetic racetrack

来源：评论

学校读者我要写书评

暂无评论

Non-Technical Losses Detection Using autoencoder and Bidirectional Gated Recurrent Unit to Secure Smart Grids

引用

IEEE ACCESS 2022年 10卷 56863-56875页

作者： Pamir Javaid, Nadeem Qasim, Umar Yahaya, Adamu Sani Alkhammash, Eman H. Hadjouni, Myriam COMSATS Univ Islamabad Dept Comp Sci Islamabad 44000 Pakistan Univ Technol Sydney Sch Comp Sci Ultimo NSW 2007 Australia Univ Engn & Technol & Lahore Dept Comp Sci New Campus Lahore 54000 Pakistan Taif Univ Coll Comp & Informat Technol Dept Comp Sci Taif 21944 Saudi Arabia Princess Nourah Bint Abdulrahman Univ Coll Comp & Informat Sci Dept Comp Sci Riyadh 11671 Saudi Arabia

Electricity theft is considered one of the most significant reasons of the non technical losses (NTL). It negatively influences the utilities in terms of the power supply quality, grid's safety, and economic loss. Therefore, it is necessary to effectively deal with the electricity theft problem. For detecting electricity theft in smart grids (SGs), an efficient and state-of-the-art approach is designed in the underlying work based on autoencoder and bidirectional gated recurrent unit (AE-BiGRU). The proposed approach consists of six components: (1) data collection, (2) data preparation, (3) data balancing, (4) feature extraction, (5) classification and (6) performance evaluation. Moreover, bidirectional gated recurrent unit (BiGRU) is used for the identification of the anomalies in electricity consumption (EC) patterns caused due to factors like family formation changes, holidays, parties, and so on, which are referred as non-theft factors. The proposed autoencoder-bidirectional gated recurrent unit (AE-BiGRU) model employs the EC data acquired from state grid corporation of China (SGCC) for simulations. Furthermore, it is visualized from the simulation results that 90.1% accuracy and 10.2% false positive rate (FPR) are obtained by the proposed model. The results are better than different existing classifiers, i.e., logistic regression (LR), decision tree (DT), extreme gradient boosting (XGBoost), gated recurrent unit (GRU), etc.

关键词： Data models Support vector machines Logic gates Hardware Feature extraction Convolutional neural networks Meters autoencoder bidirectional gated recurrent unit deep learning algorithms smart grid electricity theft detection machine learning algorithms synthetic theft attacks

来源：评论

学校读者我要写书评

暂无评论

Network Traffic Examination for Network Intrusion Detection in IOV using autoencoder and Decoder 2

Network Traffic Examination for Network Intrusion Detection ...

引用

2nd International Conference on Intelligent Cyber Physical Systems and Internet of Things (ICoICI)

作者： Vaishnodevi, S. Kumar, Vinod D. Murali, G. Azhagiri, M. Madhuvappan, Arunkumar C. Sathishkumar, K. Vinayaka Missions Res Fdn Deemed Be Univ Vinayaka Missions Kirupananda Variyar Engn Coll Biomed Engn Salem Tamil Nadu India SRM Inst Sci & Technol Comp Sci & Engn Chennai Tamil Nadu India

ISBN: (数字)9798331540661

ISBN: (纸本)9798331540661;9798331540678

The Internet of Vehicles (IoV) refers to a network where vehicles are connected to each other and to the surrounding infrastructure, enabling the exchange of information among vehicles and with the infrastructure to improve safety, efficiency, and overall transportation experience. However, intrusion into IoV systems may compromise the privacy of vehicle owners and occupants, with unauthorized access to personal data collected by vehicles leading to privacy violations and identity theft. Anomaly-based Network Intrusion Detection System (A-NIDS) provides a means to recognize prospective threats by detecting deviations from the normal model. This work introduces an intrusion detection system for vehicles using autoencoder and Decoder for Image-Based detection, offering automated operation without supervision.

关键词： autoencoder Decoder Internet of Vehicles Intrusion Detection Unsupervised

来源：评论

学校读者我要写书评

暂无评论

DEEP NMF AND autoencoder: A COMPARATIVE ANALYSIS FOR HYPERSPECTRAL UNMIXING USING PRISMA REAL IMAGES

DEEP NMF AND AUTOENCODER: A COMPARATIVE ANALYSIS FOR HYPERSP...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Settembre, Gaetano Del Buono, Nicoletta Esposito, Flavin Taggio, Nicolo Univ Bari Aldo Moro Dept Math Bari Italy Planetek Italia Srl Bari Italy

ISBN: (纸本)9798350360332;9798350360325

In hyperspectral data, mixed pixels are frequent due to the low-medium spatial resolution of the imaging spectrometer, or to intimate mixing effects. Hence the process of blind hyperspectral unmixing, which separates the pixel spectra into a collection of spectral signatures and a set of fractional abundances, is a mandatory task in hyperspectral image processing. In this study, among models capable of performing linear spectral unmixing, we present a comparative analysis performed on real data acquired from the PRISMA (PRecursore IperSpettrale della Missione Applicativa) hyperspectral satellite between deep nonnegative matrix factorization and artificial neural network autoencoder based methods.

关键词： Hyperspectral unmixing deep nonnegative matrix factorization autoencoder PRISMA satellite data

来源：评论

学校读者我要写书评

暂无评论

Lower Limb Trajectory Prediction for Exoskeleton with autoencoder-Deep Gaussian Process 19

Lower Limb Trajectory Prediction for Exoskeleton with AutoEn...

引用

IEEE 19th Conference on Industrial Electronics and Applications (ICIEA)

作者： Lv, Pingping Zhang, Chi Yi, Feng Yuan, Ting Li, Shupei Zhang, Meitong Ningbo Univ Fac Elect Engn & Comp Sci Ningbo 315201 Peoples R China Chinese Acad Sci Ningbo Inst Mat Technol & Engn Ningbo 315201 Peoples R China Zhejiang Key Lab Robot & Intelligent Mfg Equipmen Ningbo 315201 Peoples R China Univ Chinese Acad Sci Coll Mat Sci & Optoelect Technol Ningbo 315201 Peoples R China

ISBN: (纸本)9798350360875;9798350360868

Gait trajectory prediction is a crucial component in compensating control system delays, reducing interactive resistance, and achieving real-time assistance in exoskeleton robotics. In this paper, an adaptive gait prediction model based on the autoencoder deep Gaussian process (AE-DGP) is proposed for joint angle estimation using measurement data from inertial measurement units (IMUs). The DGP process involves stochastic gradient Hamiltonian Monte Carlo (SGHMC) calculations and Monte Carlo Expectation-maximization (MCEM) optimization at a lower computational cost. The kernel of the model is the multi-feature fusion input based on autoencoder and the construction of the DGP model with an adaptive sliding window. To suppress spikes in predicted deviations, a weighted averaging strategy is employed to estimate future stable gait trajectories. Benefiting from the design, the proposed model can enhance the accuracy and adaptability of gait prediction at different speeds. Experiments involving four participants at four speeds indicate that the proposed method achieves hip and knee joint prediction with less than 0.16 degrees and 0.35 degrees root mean squared errors respectively. Compared to the Gaussian process (GP) and long short-term memory (LSTM) models, the proposed method exhibits superior performance in adaptive gait trajectory prediction at different speeds.

关键词： autoencoder deep Gaussian process gait trajectory prediction IMUs lower limb exoskeleton

来源：评论

学校读者我要写书评

暂无评论

Robust Features with Convolutional autoencoder Speech Command Recognition 13

Robust Features with Convolutional Autoencoder Speech Comman...

引用

2024 International Conference on Radar Antenna Microwave Electronics and Telecommunications

作者： Zilvan, Vicky Khoirunisa, Awalia Agustina Ramdan, Ade Pratiwi, Hasih Nadirman, Firnas Darwis, Fajri Suryawati, Endang Pardede, Hilman F. Natl Res & Innovat Agcy Res Ctr Artificial Intelligence & Cyber Secur Bandung Indonesia Univ Sebelas Maret Dept Stat Surakarta Indonesia Natl Res & Innovat Agcy Res Ctr Telecommun Bandung Indonesia

ISBN: (纸本)9798350389937;9798350389920

Today, deep learning (DL) has proven to be a prominent method in many recognition tasks. However, deep learning-based Automatic Speech Recognition (ASR) has degraded performance when dealing with noisy data. In this study, we investigate the effectiveness of DL architectures using the autoencoder convolutional neural network (AECNN) combined with traditional feature extraction methods such as Mel-Filter Bank (MFB), Mel Frequency Cepstral Coefficients (MFCC) and Log Mel-Filter Bank (LMFB) to generate robust features for speech command recognition. We implement RMSprop as an optimizer to get optimal models. Based on our experiment results, we found that MFB features perform best in both clean and noisy conditions.

关键词： deep learning autoencoder CNN speech recognition MFCC Mel-Filter Bank Log Mel-Filter Bank speech command

来源：评论

学校读者我要写书评

暂无评论

An autoencoder-Based Approach for Anomaly Detection of Machining Processes Using Acoustic Emission Signals 25th

An Autoencoder-Based Approach for Anomaly Detection of Machi...

引用

25th International Conference on Engineering Applications of Neural Networks (EANN)

作者： Nappa, Antonio Ferrando Chacon, Juan Luis Azpiroz, Izar Jose Arrazola, Pedro Vicomtech Fdn Basque Res & Technol Alliance BRTA Mikeletegi 57 Donostia San Sebastian 20009 Spain Mondragon Univ Fac Engn Arrasate Mondragon 20500 Spain

ISBN: (纸本)9783031624940;9783031624957

In recent years the growing amount of data generated in industrial processes has enabled the development of data-driven decision-making systems, placing strong interest on artificial intelligence, particularly when the world of Internet-of-Things is considered. Managing and monitoring this data flow is crucial in machining processes, where the health of the system is assessed through the analysis of different sources, such as vibration, temperature, electric and acoustic signals. Currently, the main theme in tackling this task is anomaly detection: identifying an anomalous state is equivalent to having adequate control of the process and being able to make decisions accordingly, which, if achieved in the early stages, gives an incredible return, avoiding failures and production interruptions. In this paper an approach combining Wavelet Packet Decomposition and autoencoders for anomaly detection of CNC machining processes is presented. To this end, acoustic emission signals of a real-world use case are considered. To prove the effectiveness of the proposed system, a comparison with an Isolation Forest algorithm, a well-known benchmark in this field, is made. The results show an improvement of nearly 10% in terms of F1-score and accuracy, as well as the advantages of the encoding procedure.

关键词： Machining Process Acoustic Emission Anomaly detection Wavelet Packet Decomposition Multi-Resolution Analysis 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：