检索结果-内蒙古大学图书馆

16th International Audio Mostly Conference (AM)

作者： Gordan Kreković Visage Technologies

ISBN: (纸本)9781450385695

Inspired by the recently regained popularity of wavetable synthesis and rapid developments of neural networks, this study introduces a wavetable oscillator based on a standard autoencoder. The purpose of such a neural network is to generate diverse and novel single-cycle waveforms based on a small number of input parameters with sufficient computational efficiency. A consequence of using latent variables directly as input parameters is a smooth transition between the generated waveforms when changes of input parameters are small. To investigate the influence of datasets and hyperparameters on the output distribution, we conducted a set of experiments. The results suggest that even small and efficient generative models can successfully perform this task and produce an interestingly wide range of waveforms. Influence on possible shapes and sonic characteristics of the generated waveforms can be achieved using a specifically designed, synthetic dataset for model training.

关键词： Sound synthesis wavetable synthesis deep learning autoencoder generative neural network

来源：评论

学校读者我要写书评

暂无评论

Efficient Data Compression for 3D Sparse TPC via Bicephalous Convolutional autoencoder 20

Efficient Data Compression for 3D Sparse TPC via Bicephalous...

引用

20th IEEE International Conference on Machine Learning and Applications (ICMLA)

作者： Huang, Yi Ren, Yihui Yoo, Shinjae Huang, Jin Brookhaven Natl Lab Computat Sci Initiat Upton NY 11973 USA Brookhaven Natl Lab Phys Dept Upton NY 11973 USA

ISBN: (纸本)9781665443371

Real-time data collection and analysis in large experimental facilities present a great challenge across multiple domains, including high energy physics, nuclear physics, and cosmology. To address this, machine learning (ML)-based methods for real-time data compression have drawn significant attention. However, unlike natural image data, such as CIFAR and ImageNet that are relatively small-sized and continuous, scientific data often come in as three-dimensional (3D) data volumes at high rates with high sparsity (many zeros) and nonGaussian value distribution. This makes direct application of popular ML compression methods, as well as conventional data compression methods, suboptimal. To address these obstacles, this work introduces a dual-head autoencoder to resolve sparsity and regression simultaneously, called Bicephalous Convolutional autoencoder (BCAE). This method shows advantages both in compression fidelity and ratio compared to traditional data compression methods, such as MGARD, SZ, and ZFP. To achieve similar fidelity, the best performer among the traditional methods can reach only half the compression ratio of BCAE. Moreover, a thorough ablation study of the BCAE method shows that a dedicated segmentation decoder improves the reconstruction.

关键词： Deep Learning autoencoder Data Compression Sparse Data High-energy and Nuclear Physics

来源：评论

学校读者我要写书评

暂无评论

Network intrusion detection based on Contractive Sparse Stacked Denoising autoencoder 16

Network intrusion detection based on Contractive Sparse Stac...

引用

16th IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (IEEE BMSB)

作者： Lu, Jizhao Meng, Huiping Li, Wencui Liu, Yue Guo, Yihao Yang, Yang State Grid Henan Informat & Telecommun Co Zhengzhou 450000 Peoples R China Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China

ISBN: (纸本)9781665449083

The rapid growth of network scale leads to the increasingly prominent network security problems. Intrusion detection is an important method to resist complex and growing network attacks. For traditional shallow intrusion detection methods can not effectively identify and classify network intrusion data, this paper proposes a Contractive Sparse Stack Denoising autoencoder(CSSDAE), which cascades multiple traditional autoencoders, and introduces noise, sparse constraint and contractive penalty term on this basis, so as to improve the robustness of the model, enhance decoding ability of the deep network and promote intrusion detection performance. In addition, this paper improves the softmax classifier to make the feature vectors as compact as possible within the class and separate as much as possible between classes, and solves the problem of uneven number of sample classes by weighting. The experimental results show that compared with traditional AE, the CSSDAE's accuracy of network intrusion detection is effectively improved.

关键词： autoencoder characteristic dimension reduction sparse denoising softmax intrusion detection

来源：评论

学校读者我要写书评

暂无评论

rcCAE: a convolutional autoencoder method for detecting intra-tumor heterogeneity and single-cell copy number alterations

引用

BRIEFINGS IN BIOINFORMATICS 2023年第3期24卷 bbad108-bbad108页

作者： Yu, Zhenhua Liu, Furui Shi, Fangyuan Du, Fang Ningxia Univ Sch Informat Engn Yinchuan 750021 Ningxia Peoples R China

Intra-tumor heterogeneity (ITH) is one of the major confounding factors that result in cancer relapse, and deciphering ITH is essential for personalized therapy. Single-cell DNA sequencing (scDNA-seq) now enables profiling of single-cell copy number alterations (CNAs) and thus aids in high-resolution inference of ITH. Here, we introduce an integrated framework called rcCAE to accurately infer cell subpopulations and single-cell CNAs from scDNA-seq data. A convolutional autoencoder (CAE) is employed in rcCAE to learn latent representation of the cells as well as distill copy number information from noisy read counts data. This unsupervised representation learning via the CAE model makes it convenient to accurately cluster cells over the low-dimensional latent space, and detect single-cell CNAs from enhanced read counts data. Extensive performance evaluations on simulated datasets show that rcCAE outperforms the existing CNA calling methods, and is highly effective in inferring clonal architecture. Furthermore, evaluations of rcCAE on two real datasets demonstrate that it is able to provide a more refined clonal structure, of which some details are lost in clonal inference based on integer copy numbers.

关键词： autoencoder Hidden Markov model Copy number alteration Single-cell sequencing

来源：评论

学校读者我要写书评

暂无评论

A Prediction-Augmented autoencoder for Multivariate Time Series Anomaly Detection 28th

A Prediction-Augmented AutoEncoder for Multivariate Time Ser...

引用

28th International Conference on Neural Information Processing

作者： Gong, Sawenbo Wu, Zhihao Liu, Yunxiao Lin, Youfang Wang, Jing Beijing Jiaotong Univ Sch Comp & Informat Technol Beijing Peoples R China Beijing Key Lab Traff Data Anal & Min Beijing Peoples R China CAAC Key Lab Intelligent Passenger Serv Civil Avi Beijing Peoples R China Key Lab Transport Ind Big Data Applicat Technol C Beijing Peoples R China

ISBN: (纸本)9783030921842;9783030921859

To ensure the normal running of IT systems, multivariate time series changing constantly related to system states need to be monitored to detect unexpected events and anomalies and further prevent adverse effects on the systems. With the rapid increase of complexity and scales of the systems, a more automated and accurate anomaly detection method becomes crucial. In this paper, we propose a new framework called Prediction-Augmented autoencoder (PAAE) for multivariate time series anomaly detection, which learns a better representation of normal data from the perspective of reconstruction and prediction. Predictive augmentation is introduced to constrain the latent space to improve the ability of the model to recognize anomalies. And a novel anomaly score is developed considering both the reconstruction errors and prediction errors to reduce false negatives. Extensive experiments prove that the introduction of prediction is effective and show the superiority and robustness of PAAE. Particularly, PAAE obtains at best 7.9% performance improvement on the SMAP dataset.

关键词： Anomaly detection Time series autoencoder Reconstruction Prediction

来源：评论

学校读者我要写书评

暂无评论

One-class autoencoder approach for optimal electrode set identification in wearable EEG event monitoring 43

One-class autoencoder approach for optimal electrode set ide...

引用

43rd Annual International Conference of the IEEE-Engineering-in-Medicine-and-Biology-Society (IEEE EMBC)

作者： Ferrari, Laura M. Hanna, Guy Abi Volpe, Paolo Ismailova, Esma Bremond, Francois Zuluaga, Maria A. INRIA Stars Team F-06902 Sophia Antipolis France EURECOM Data Sci Dept F-06410 Sophia Antipolis France Mines St Etienne Dept Bioelect F-13541 Gardanne France

ISBN: (纸本)9781728111797

A limiting factor towards the wide use of wearable devices for continuous healthcare monitoring is their cumbersome and obtrusive nature. This is particularly true in electroencephalography (EEG), where numerous electrodes are placed in contact with the scalp to perform brain activity recordings. In this work, we propose to identify the optimal wearable EEG electrode set, in terms of minimal number of electrodes, comfortable location and performance, for EEG-based event detection and monitoring. By relying on the demonstrated power of autoencoder (AE) networks to learn latent representations from high-dimensional data, our proposed strategy trains an AE architecture in a one-class classification setup with different electrode combinations as input data. The model performance is assessed using the F-score. Alpha waves detection is the use case through which we demonstrate that the proposed method allows to detect a brain state from an optimal set of electrodes. The so-called wearable configuration, consisting of electrodes in the forehead and behind the ear, is the chosen optimal set, with an average F-score of 0.78. This study highlights the beneficial impact of a learning-based approach in the design of wearable devices for real-life event-related monitoring.

关键词： wearables EEG autoencoder optimal electrode set tattoo electrodes

来源：评论

学校读者我要写书评

暂无评论

A DNN autoencoder FOR AUTOMOTIVE RADAR INTERFERENCE MITIGATION

A DNN AUTOENCODER FOR AUTOMOTIVE RADAR INTERFERENCE MITIGATI...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Chen, Shengyi Taghia, Jalal Fei, Tai Kuehnau, Uwe Pohl, Nils Martin, Rainer HELLA GmbH & Co KGaA Lippstadt Germany Ruhr Univ Bochum Bochum Germany

ISBN: (纸本)9781728176055

In this paper, a novel interference mitigation approach using an autoencoder in combination with a traditional interference detection filter is introduced. It is shown that by employing the gated convolution, the encoder has the ability to learn the signal pattern from the remaining interference-free signal. The decoder can recover the interference-contaminated signal segments from the bottleneck representation as computed by the encoder. Experimental results show that the proposed method can provide a remarkable improvement in signal-to-interference-plus-noise ratio (SINR) and preserves its robustness on real radar measurements in severely disturbed scenarios that are more complex than the training dataset.

关键词： automotive radar interference mitigation autoencoder deep learning

来源：评论

学校读者我要写书评

暂无评论

Enhancement of Fall Detection Algorithm Using Convolutional autoencoder and Personalized Threshold

Enhancement of Fall Detection Algorithm Using Convolutional ...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Iguchi, Yohsuke Lee, Jae Hoon Okamoto, Shingo Ehime Univ Grad Sch Sci & Engn Dept Mech Engn Matsuyama Ehime Japan

ISBN: (纸本)9781728197661

Falling is a hazardous situation for elderly people living alone and labor workers as they are easy to happen and can lead to serious injuries. Hence, a fall detection mechanism is an indispensable way to rescue victims without a delay. Various fall detection systems detect falling by using supervised deep-learning algorithms. However, labeling training data and collecting various falling motions data large enough for deep-learning is time-consuming and tiresome. Therefore, this study aims to develop a fall detection system utilizing the data not from falling but from usual motions of daily life. In this paper, an unsupervised learning method, convolutional autoencoder, and a wearable sensor, inertial measurement unit (IMU), were employed. The motion data from the IMU is converted to monochrome images for training and evaluating the developed fall detection algorithm. Falling is determined by comparing the input and output images of the model and a method for setting a threshold was investigated. After confirming the accuracy of the proposed method using a publicly available dataset and our dataset, the proposed method to train the model and to determine the threshold were addressed. Finally, the fall detection result with a sensitivity and a specificity of 100% and 99% was obtained.

关键词： fall detection deep-learning autoencoder

来源：评论

学校读者我要写书评

暂无评论

Deep Classified autoencoder for Lithofacies Identification

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2022年 60卷 1页

作者： Liu, Xingye Shao, Guangzhou Liu, Yuwei Liu, Xiwu Li, Jingye Chen, Xiaohong Chen, Yangkang Chengdu Univ Technol Coll Geophys Key Lab Earth Explorat & Informat Technol Minist Educ Chengdu 610059 Peoples R China Changan Univ Key Lab Western Chinas Mineral Resources & Geol E Minist Educ Xian 710054 Peoples R China SinoPEC Petr Explorat & Prod Res Inst Natl Key Lab Corp Shale Oil Gas Enrichment Mech & Beijing 102206 Peoples R China China Univ Petr Coll Geophys Beijing 102249 Peoples R China Univ Texas Austin Jackson Sch Geosci Bur Econ Geol Austin TX 78713 USA

Lithofacies classification is an indispensable procedure in well logging and seismic data interpretation. We propose a novel deep classified autoencoder learning approach to identify lithofacies for high-dimensional data and complex problems. Deep autoencoder (DAE) is an unsupervised learning method via layerwise pretraining multiple autoencoders. It can learn deep data features automatically and reconstruct the original data with a small error. Introducing sparse constraint (i.e., sparse autoencoder) potentiates the learning ability of autoencoder. On this foundation, additional regularization terms constructed by labeled samples are considered in the new DAE approach in order to boost the performance. The new method can adaptively preserve the most significant input features and remove insensitive properties to decrease computational complexity. At the same time, we embed the class information into the loss function of autoencoder to measure intraclass similarity and improve the classification accuracy. Several experiments on well data and seismic data show that the proposed method achieves promising results. Compared with the traditional deep autoencoder (DAE), the proposed method is more competitive in terms of classification accuracy and robustness.

关键词： Feature extraction Training Predictive models Decoding Data models Unsupervised learning Reservoirs autoencoder deep learning lithofacies identification reservoir prediction

来源：评论

学校读者我要写书评

暂无评论

Automated spectral decomposition and reconstruction of optical properties using a mixed autoencoder approach

引用

Journal of Biomedical Optics 2025年第4期30卷 047001-047001页

作者： Ni, Dongqin Amouroux, Marine Blondel, Walter Hohmann, Martin Institute of Photonic Technologies Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany Erlangen Graduate School in Advanced Optical Technologies Erlangen Germany CNRS CRAN UMR 7039 Vandoeuvre-Lès-Nancy Université de Lorraine France

Significance: Investigating optical properties (OPs) is crucial in the field of biophotonics, as it has a broad impact on understanding light-tissue interactions. However, current techniques, such as inverse Monte Carlo simulations (IMCS), have limitations in extracting detailed information about the spectral behavior of microscopic absorbers and scatterers. Aim: We aim to develop a customized autoencoder neural network (ANN) that can automatically identify the spectral behavior of each microscopic absorber and scatterer responsible for generating OP. Approach: The ANN is designed to compute OP from measurements, in which the bottleneck corresponds to the number of absorbers and scatterers. The presented ANN functions asymmetrically and computes the OP using a linear combination of absorbers and scatterers. Validation was conducted using intralipid as a scatterer and ink as an absorber. Results: The employment of the decoder weights facilitated the successful extraction of the spectral shape of every constituent, demonstrating the effectiveness of the ANN in extracting detailed information about the spectral behavior of absorbers and scatterers. At the same time, the OP can be predicted with high precision. Conclusions: The presented ANN is a viable tool for extracting the spectral behavior of absorbers and scatterers without the need for prior knowledge of these components in the test and training data. Potential future applications could include the extraction of relative concentrations of constituents in tissue. © 2025 SPIE. All rights reserved.

关键词： autoencoder explainable neural networks machine learning optical properties

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：