检索结果-内蒙古大学图书馆

autoencoder and Partially Impossible Reconstruction Losses

SENSORS 2022年第13期22卷 4862-4862页

作者： Dias Da Cruz, Steve Taetz, Bertram Stifter, Thomas Stricker, Didier IEE SA Basics & Math Models L-7795 Bissen Luxembourg Univ Kaiserslautern Dept Comp Sci D-67653 Kaiserslautern Germany German Res Ctr Artificial Intelligence DFKI Augmented Vis D-67663 Kaiserslautern Germany

The generally unsupervised nature of autoencoder models implies that the main training metric is formulated as the error between input images and their corresponding reconstructions. Different reconstruction loss variations and latent space regularizations have been shown to improve model performances depending on the tasks to solve and to induce new desirable properties such as disentanglement. Nevertheless, measuring the success in, or enforcing properties by, the input pixel space is a challenging endeavour. In this work, we want to make use of the available data more efficiently and provide design choices to be considered in the recording or generation of future datasets to implicitly induce desirable properties during training. To this end, we propose a new sampling technique which matches semantically important parts of the image while randomizing the other parts, leading to salient feature extraction and a neglection of unimportant details. The proposed method can be combined with any existing reconstruction loss and the performance gain is superior to the triplet loss. We analyse the resulting properties on various datasets and show improvements on several computer vision tasks: illumination and unwanted features can be normalized or smoothed out and shadows are removed such that classification or other tasks work more reliably;a better invariances with respect to unwanted features is induced;the generalization capacities from synthetic to real images is improved, such that more of the semantics are preserved;uncertainty estimation is superior to Monte Carlo Dropout and an ensemble of models, particularly for datasets of higher visual complexity. Finally, classification accuracy by means of simple linear classifiers in the latent space is improved compared to the triplet loss. For each task, the improvements are highlighted on several datasets commonly used by the research community, as well as in automotive applications.

关键词： autoencoder generalization Sim2Real illumination reconstruction sampling uncertainty

来源：评论

学校读者我要写书评

暂无评论

Long-term temperature prediction with hybrid autoencoder algorithms

引用

APPLIED COMPUTING AND GEOSCIENCES 2024年 23卷

作者： Perez-Aracil, J. Fister, D. Marina, C. M. Pelaez-Rodriguez, C. Cornejo-Bueno, L. Gutierrez, P. A. Giuliani, M. Castelleti, A. Salcedo-Sanz, S. Univ Alcala Dept Signal Proc & Commun Madrid Spain Univ Maribor Inst Robot Fac Elect Engn & Comp Sci Maribor Slovenia Univ Cordoba Dept Comp Sci & Numer Anal Cordoba Spain Politecn Milan Dept Elect Informat & Bioengn Milan Italy

This paper proposes two hybrid approaches based on autoencoders (AEs) for long-term temperature prediction. The first algorithm comprises an AE trained to learn temperature patterns, which is then linked to a second AE, used to detect possible anomalies and provide a final temperature prediction. The second proposed approach involves training an AE and then using the resulting latent space as input of a neural network, which will provide the final prediction output. Both approaches are tested in long-term air temperature prediction in European cities: seven European locations where major heat waves occurred have been considered. The longterm temperature prediction for the entire year of the heatwave events has been analysed. Results show that the proposed approaches can obtain accurate long-term (up to 4 weeks) temperature prediction, improving Persistence and Climatology in the benchmark models compared. In heatwave periods, where the persistence of the temperature is extremely high, our approach beat the persistence operator in three locations and works similarly in the rest of the cases, showing the potential of this AE-based method for long-term temperature prediction.

关键词： autoencoder Temperature prediction Hybrid models Heatwave

来源：评论

学校读者我要写书评

暂无评论

autoencoder Based PAPR Reduction for OTFS Modulation 94

Autoencoder Based PAPR Reduction for OTFS Modulation

引用

94th IEEE Vehicular Technology Conference (VTC-Fall)

作者： Liu, Mengxue Zhao, Ming-Min Lei, Ming Zhao, Min-Jian Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou 310027 Peoples R China

ISBN: (纸本)9781665413688

Orthogonal time frequency space (OTFS) modulation shows significant advantages over orthogonal frequency division multiplexing (OFDM), specially in environments with high frequency dispersion. However, high peak-to-average power ratio (PAPR) has been one of the major drawbacks of OTFS systems, which impairs the efficiency of the power amplifier. To resolve the problem, we propose a PAPR reduction method based on the autoencoder (AE) architecture through deep learning (DL) techniques, where the encoder is trained to reduce the PAPR and the decoder is trained to reconstruct the original signal. By carefully designing the loss function, the bit error rate (BER) and the PAPR are simultaneously minimized, and a hyper-parameter is introduced to achieve a good compromise between BER and PAPR in the proposed scheme. Simulation results validate the advantages of the proposed scheme as compared to the other conventional schemes.

关键词： OTFS PAPR deep learning autoencoder

来源：评论

学校读者我要写书评

暂无评论

Data-driven system health monitoring technique using autoencoder for the safety management of commercial aircraft

引用

NEURAL COMPUTING & APPLICATIONS 2021年第8期33卷 3235-3250页

作者： Lee, Hyunseong Lim, Hyung Jin Chattopadhyay, Aditi Arizona State Univ Sch Engn Matter Transport & Energy Tempe AZ 85287 USA Arizona State Univ Mech & Aerosp Engn Sch Engn Matter Transport & Energy Tempe AZ 85287 USA

This paper presents the development of a real-time and data-driven aircraft health monitoring technique to monitor in-flight operations by detecting off-nominal flight operation such as aircraft upset, which is strongly related to aviation safety and is a primary contributor to fatal accidents worldwide. A deep autoencoder is adopted to effectively estimate the complex flight responses from historical flight datasets and capture potential upset precursors. Key sensing variables highly relevant to upset primary factors are selected based on aircraft accident reports. The variables are then preprocessed using decimation and Savitzky-Golay filter for sampling frequency synchronization and denoising. Statistical detection baselines are employed to extract statistically unusual operation patterns that highly correlate with upset precursors. The performance of the developed methodology is evaluated by demonstrating real-time detection of upset precursors in flight datasets. An actual accident scenario is introduced to validate detection robustness. The results show that the proposed aircraft upset detector technique can enhance pilots' situational awareness by providing early safety alert for more effective flight safety management.

关键词： Aircraft health monitoring Aircraft upset detection autoencoder Aviation safety

来源：评论

学校读者我要写书评

暂无评论

A Novel Channel Estimation Framework in MIMO Using Serial Cascaded Multiscale autoencoder and Attention LSTM with Hybrid Heuristic Algorithm

引用

SENSORS 2023年第22期23卷 9154-9154页

作者： Manasa, B. M. R. Pakala, Venugopal Chinthaginjala, Ravikumar Ayadi, Manel Hamdi, Monia Ksibi, Amel Vellore Inst Technol Sch Elect Engn Vellore 632014 India Princess Nourah Bint Abdulrahman Univ Coll Comp & Informat Sci Dept Informat Syst POB 84428 Riyadh 11671 Saudi Arabia Princess Nourah Bint Abdulrahman Univ Coll Comp & Informat Sci Dept Informat Technol PO Box 84428 Riyadh 11671 Saudi Arabia

In wireless communication, multiple signals are utilized to receive and send information in the form of signals simultaneously. These signals consume little power and are usually inexpensive, with a high data rate during data transmission. An Multi Input Multi Output (MIMO) system uses numerous antennas to enhance the functionality of the system. Moreover, system intricacy and power utilization are difficult and highly complicated tasks to achieve in an Analog to Digital Converter (ADC) at the receiver side. An infinite number of MIMO channels are used in wireless networks to improve efficiency with Cross Entropy Optimization (CEO). ADC is a serious issue because the data of the accepted signal are completely lost. ADC is used in the MIMO channels to overcome the above issues, but it is very hard to implement and design. So, an efficient way to enhance the estimation of channels in the MIMO system is proposed in this paper with the utilization of the heuristic-based optimization technique. The main task of the implemented channel prediction framework is to predict the channel coefficient of the MIMO system at the transmitter side based on the receiver side error ratio, which is obtained from feedback information using a Hybrid Serial Cascaded Network (HSCN). Then, this multi-scaled cascaded autoencoder is combined with Long Short Term Memory (LSTM) with an attention mechanism. The parameters in the developed Hybrid Serial Cascaded Multi-scale autoencoder and Attention LSTM are optimized using the developed Hybrid Revised Position-based Wild Horse and Energy Valley Optimizer (RP-WHEVO) algorithm for minimizing the "Root Mean Square Error (RMSE), Bit Error Rate (BER) and Mean Square Error (MSE)" of the estimated channel. Various experiments were carried out to analyze the accomplishment of the developed MIMO model. It was visible from the tests that the developed model enhanced the convergence rate and prediction performance along with a reduction in the computational

关键词： channel estimation scheme multiple input multiple output channel hybrid serial cascaded network revised position-based wild horse and energy valley optimizer long short term memory autoencoder

来源：评论

学校读者我要写书评

暂无评论

An intrusion detection method based on stacked sparse autoencoder and improved gaussian mixture model

引用

COMPUTERS & SECURITY 2023年第1期128卷

作者： Zhang, Tianyue Chen, Wei Liu, Yuxiao Wu, Lifa Nanjing Univ Posts & Telecommun 9 Wenyuan Rd Nanjing Jiangsu Peoples R China

The analysis of a substantial portion of network data is a requirement for almost any machine learningbased network intrusion detection method. High dimension features, a lack of labelled datasets, and inflexible feature selection are some of the difficulties it encounters. This paper proposes an intrusion detection method based on stacked sparse autoencoder and improved Gaussian mixture model (SIGMOD). The method utilizes the stacked sparse autoencoder to produce non-linear dimensionality reduction after first using the Pearson correlation coefficient to achieve linear dimensionality reduction. It can lessen redundant data, obtain low-dimensional features and generate reconstruction errors of the samples, which are subsequently fed into the improved Gaussian mixture model. The method finally judges whether it is abnormal according to the output sample energy threshold of the improved Gaussian mixture model. Unlike the traditional anomaly detection technology that performs dimensionality reduction and clustering in two separate steps, SIGMOD jointly optimizes the parameters of the stacked sparse autoencoder and the Gaussian mixture model in an end-to-end manner, avoiding the key feature loss of cluster analysis or probability density estimation in dimensionality reduction by the two-step method. The experiment results on the UNSW-NB15 dataset demonstrate that SIGMOD performs significantly better than the conventional anomaly detection approach.

关键词： Intrusion detection Unsupervised learning autoencoder Gaussian mixture Deep learning

来源：评论

学校读者我要写书评

暂无评论

Developing health indicators and RUL prognostics for systems with few failure instances and varying operating conditions using a LSTM autoencoder

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2023年第PartA期117卷

作者： de Pater, Ingeborg Mitici, Mihaela Delft Univ Technol Fac Aerosp Engn NL-2926 Delft Netherlands Univ Utrecht Fac Sci Heidelberglaan 8 NL-3584 CS Utrecht Netherlands

Most Remaining Useful Life (RUL) prognostics are obtained using supervised learning models trained with many labelled data samples (i.e., the true RUL is known). In aviation, however, aircraft systems are often preventively replaced before failure. There are thus very few labelled data samples available. We therefore propose a Long Short-Term Memory (LSTM) autoencoder with attention to develop health indicators for an aircraft system instead. This autoencoder is trained with unlabelled data samples (i.e., the true RUL is unknown). Since aircraft fly under various operating conditions (varying altitude, speed, etc.), these conditions are also integrated in the autoencoder. We show that the consideration of the operating conditions leads to robust health indicators and improves significantly the monotonicity, trendability and prognosability of these indicators. These health indicators are further used to predict the RUL of the aircraft system using a similarity -based matching approach. We illustrate our approach for turbofan engines. We show that the consideration of the operating conditions improves the monotonicity of the health indicators by 97%. Also, our approach leads to accurate RUL estimates with a Root Mean Square Error (RMSE) of 2.67 flights only. Moreover, a 19% reduction in the RMSE is obtained using our approach in comparison to existing supervised learning models.

关键词： Remaining Useful Life prognostics Health indicators Unlabelled data samples autoencoder Varying operating conditions Attention

来源：评论

学校读者我要写书评

暂无评论

Towards open domain-specific recognition using Quad-Channel Self-Attention Reciprocal Point Learning and autoencoder

引用

KNOWLEDGE-BASED SYSTEMS 2024年 284卷

作者： Alfarisy, Gusti Ahmad Fanshuri Malik, Owais Ahmed Hong, Ong Wee Univ Brunei Darussalam Sch Digital Sci Jalan Tungku Link BE-1410 Bandar Seri Begawan Brunei Inst Teknol Kalimantan Dept Informat Jalan Soekarno Hatta KM 15 Balikpapan 76127 Indonesia

Open-Set recognition (OSR) emphasizes its ability to reject unknown classes and maintain closed-set performance simultaneously. The primary objective of OSR is to minimize the risk of unknown classes being predicted as one of the known classes. OSR operates under the assumption that unknown classes will be present during testing, and it identifies a single distribution for these unknowns. Recognizing unknowns both within and outside the domain of interest can enhance future learning efforts. The rejected unknown samples within the domain of interest can be used to refine deep learning models further. We introduced a new challenge within OSR called Open Domain-Specific Recognition (ODSR). This approach formalizes the risk in the open domain-specific space to address the recognition of two distinct unknown distributions, i.e., in-domain (ID) and out-of-domain (OOD) unknowns. To address this, we proposed an initial baseline that employs Quad -channel Self-attention Reciprocal Point Learning (QSRPL) to mitigate open-space risk. Additionally, we used an autoencoder to handle open domain-specific space risk. We harnessed the knowledge embedded in pre -trained models and optimized the open-set hyperparameters before benchmarking against other methods. We also explored how different pre-trained models influence open-set recognition performance. To validate our method, we tested our model across various domains, including garbage, vehicles, household items, and pets. Experimental results indicate that our approach is effective at rejecting unseen classes while maintaining closed-set accuracy. Furthermore, the autoencoder shows potential in addressing open domain-specific space risks for future development. The choice of pre-trained models significantly affects the performance of open -set recognition in rejecting unknowns. The source code of the project is available at https://***/gusti-alfarisy/QSRPL.

关键词： Deep learning Open-set recognition Open domain-specific recognition Out-of-distribution detection Prototype-based neural networks Prototype learning Reciprocal point learning autoencoder

来源：评论

学校读者我要写书评

暂无评论

A novel battery abnormality detection method using interpretable autoencoder

引用

APPLIED ENERGY 2023年第PartB期330卷

作者： Zhang, Xiang Liu, Peng Lin, Ni Zhang, Zhaosheng Wang, Zhenpo Beijing Inst Technol Beijing 100081 Peoples R China Beijing Inst Technol Adv Technol Res Inst Jinan Jinan 250300 Peoples R China

The abnormality detection of lithium-ion battery pack is crucial to ensure the safety of electric vehicles (EVs). However, the dynamic and complex operating conditions of EVs making it challenging for algorithms designed under laboratory conditions to perform properly. In this study, a novel data-driven framework for abnormality detection is developed through establishment of a neural network with interpretable modules on top of an autoencoder using data from real EVs to recognize abnormality while charging. The encoding guide matrix proposed in this method greatly accelerates the training speed, which also helps retains the learning ability of the neural network with consideration of the influence from each feature to provide supplementary information. The proposed algorithm is validated with data from real EVs. The results show that, compared with most existing algorithms, evidently higher accuracy can be achieved with shorter training time and lower computational cost, where the accuracy remains above 94% for all tested sample and the average root mean square error (RMSE) is as small as 0.03913. The proposed method can be utilized for both cloud-based and vehicle-based battery fault diagnoses.

关键词： Electric vehicles Lithium-ion battery pack Battery abnormal identification autoencoder

来源：评论

学校读者我要写书评

暂无评论

A Novel Shape Retrieval Method for 3D Mechanical Components Based on Object Projection, Pre-Trained Deep Learning Models and autoencoder

引用

COMPUTER-AIDED DESIGN 2023年 154卷

作者： Bickel, S. Schleich, B. Wartzack, S. Friedrich Alexander Univ Erlangen Nurnberg Engn Design Martensstr 9 D-91058 Erlangen Germany

The reuse of existing design models offers great potential in saving resources and generating an efficient workflow. In order to fully benefit from these advantages, it is necessary to develop methods that are able to retrieve mechanical engineering geometry from a query input. This paper aims to address this problem by presenting a method that focuses on the needs of product development to retrieve similar components by comparing the geometrical similarity of existing parts. Therefore, a method is described, which first converts surface meshes into point clouds, rotates them, and then transforms the results into matrices. These are subsequently passed to a pre-trained Deep Learning network to extract the feature vector. A similarity between different geometries is calculated and evaluated based on this vector. The procedure employs a new type of part alignment, especially developed for mechanical engineering geometries. The method is presented in detail and several parameters affecting the accuracy of the retrieval are discussed. This is followed by a critical comparison with other shape retrieval approaches through a mechanical engineering benchmark data set.(c) 2022 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： 3D object retrieval Shape retrieval Projection method Part alignment Deep Learning 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：