检索结果-内蒙古大学图书馆

Design of Reconfigurable Metasurface Based on Support Vector Machine

Design of Reconfigurable Metasurface Based on Support Vector...

IEEE MTT-S International Microwave Workshop Series on Advanced Materials and Processes for RF and THz Applications (IMWS-AMP)

作者： Lu, Ying Juan Gao, Shang Wang, Zheng Xing Liang, Jing Cheng Cheng, Qiang Southeast Univ State Key Lab Millimeter Waves Nanjing 210018 Peoples R China

ISBN: (纸本)9781665478342

Traditional metasurface design requires strong expert experience and large time cost. To overcome this problem, a fast design method for reconfigurable metasurface based on support vector machine is proposed, which can be divided into four stages: data collection, data preprocessing, model training, and reverse prediction. Based on the improved pixel modeling method, 10,000 groups of data concerning the reflection amplitude for active unit cells with different patterns and excitations are collected as a dataset. denoising autoencoder is used to extract the features of the data, with fitting errors below 0.0053, whose accuracy is an order of magnitude higher than other autoencoders. To reduce the cost of parameter optimization and improve the element performance, particle swarm optimization is introduced into the optimization process of the SVM. The predicted result is in good agreement with the design target, which verifies the accuracy of the rapid design model.

关键词： Support Vector Machine denoising autoencoder Reconfigurable Intelligent Surfaces Particle Swarm Optimization

来源：评论

学校读者我要写书评

暂无评论

Park Group Loss Perception Model Based on XGBoost and denoising Self-encoding Network 8

Park Group Loss Perception Model Based on XGBoost and Denois...

引用

8th International Forum on Electrical Engineering and Automation (IFEEA)

作者： Zhao, Hongshan Cui, Yangyang Song, Wei Qu, Yuehan Sun, Mengxue North China Elect Power Univ Dept Elect Engn Baoding Hebei Peoples R China

ISBN: (纸本)9781665400886

In order to explore the typical characteristics of the outflow and retention of customers in the park, and predict the loss of customers in the park in order to serve the future power supply planning of the power grid. The design is a community loss perception algorithm based on extreme gradient boosting (XGBoost) and denoising auto encoder (DAE). The algorithm consists of two parts. The first part is the feature mining algorithm. It first constructs the loss perception index based on power data, and then obtains the feature importance ranking through the XGBoost model training and compares the accuracy under different feature importance thresholds to obtain typical *** second part is the DAE churn customer prediction algorithm. The reconstruction error of existing customers is obtained through DAE, and the customers who are prone to churn in the park are predicted according to the threshold of reconstruction error. Combined with examples, XGBoost's feature mining capabilities are stronger than other algorithms. DAE trained with a large number of park stock customer samples can more accurately predict customers with a tendency to churn than other algorithms.

关键词： churn perception feature mining xGBoost denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

A Collaborative Framework Using Multimodal Data and Adaptive Noise for Human Behavior Anomaly Detection

A Collaborative Framework Using Multimodal Data and Adaptive...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Yang, Guoqing Gao, Jianzhe Zhang, Kejia He, Yifan Luo, Zhiming Li, Shaozi Xiamen Univ Dept Artif Intelligence Xiamen Peoples R China Wuyi Univ Fujian Key Lab Big Data Applicat & Intellectualiz Wuyishan Peoples R China

ISBN: (纸本)9798350359329;9798350359312

Human behavior anomaly detection in video aims to identify unusual behaviors that are crucial for public safety. Recently, there has been an increase in reconstruction or predictionbased methods that integrate diverse modal features to enhance anomaly detection. However, they use methods that independently or directly fusion multimodal features without fully considering the collaborative potential between multimodal features, which are susceptible to interference from semantic differences, thereby impacting detection performance. In contrast, we design a collaborative framework using multimodal data and adaptive noise for behavior anomaly detection. Our framework detects anomalies by analyzing the contrastive differences between two modalities alongside single-frame reconstruction errors. Specifically, we first learn the correlation between RGB and skeletal modalities for normal behavior through contrastive learning and use inter-modal contrast difference to detect motion anomalies. Additionally, we propose a single-frame reconstruction network that adaptively adds noise based on the importance of foreground features to detect appearance anomalies. Anomalies often occur in the motion foreground, and increasing noise in this area can make it more difficult to reconstruct anomalies. Extensive experiments validate the state-of-the-art performance of our method on three public datasets.

关键词： Human behavior anomaly detection Multimodal feature Contrastive learning denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

3D Reconstruction from 2D Cerebral Angiograms as a Volumetric denoising Problem 18th

3D Reconstruction from 2D Cerebral Angiograms as a Volumetri...

引用

18th International Symposium on Visual Computing (ISVC)

作者： Wu, Sean Kaneko, Naoki Mendoza, Steve Liebeskind, David S. Scalzo, Fabien Pepperdine Univ Keck Data Sci Inst Malibu CA 90265 USA UCLA Dept Intervent Neuroradiol Los Angeles CA 90095 USA UCLA Dept Neurol Los Angeles CA 90095 USA

ISBN: (纸本)9783031479687;9783031479694

Accurately capturing the 3D geometry of the brain's blood vessels is critical in helping neuro-interventionalists to identify and treat neurovascular disorders, such as stroke and aneurysms. Currently, the gold standard for obtaining a 3D representation of angiograms is through the process of 3D rotational angiography, a timely process requiring expensive machinery, which is also associated with high radiation exposure to the patient. In this research, we propose a new technique for reconstructing 3D volumes from 2D angiographic images, thereby reducing harmful X-ray radiation exposure. Our approach involves parameterizing the input data as a back-projected noisy volume from the images, which is then fed into a 3D denoising autoencoder. Through this method, we have achieved clinically relevant reconstructions with varying amounts of 2D projections from 49 patients. Additionally, our 3D denoising autoencoder outperformed previous generative models in biplane reconstruction by 15.51% for intersection over union (IOU) and 3.5% in pixel accuracy due to keeping a semi-accurate input with back projection. This research highlights the significant role of back-projection in achieving relative visual correspondence in the input space to reconstruct 3D volumes from 2D angiograms. This approach has the potential to be deployed in future neurovascular surgery, where 3D volumes of the patient's brain blood vessels can be visualized with less X-ray radiation exposure time.

关键词： 3D Reconstruction Deep Learning denoising autoencoder Rotational Angiography Cerebral Angiograms

来源：评论

学校读者我要写书评

暂无评论

CF-SSDAE:Symmetric SDAE for Collaborative Filtering Algorithm 8

CF-SSDAE:Symmetric SDAE for Collaborative Filtering Algorith...

引用

8th International Conference on Advanced Cloud and Big Data (CBD)

作者： Sun, Jingyu Wang, Xinjuan Ning, Zefei Zhao, Ruijiao Taiyuan Univ Technol Coll Software Taiyuan Peoples R China Taiyuan Univ Technol Coll Informat & Comp Taiyuan Peoples R China

ISBN: (纸本)9781665423137

Collaborative Deep Learning (CDL) uses the stacked denoising autoencoder to encode information matrix of items, which reduces the dimension of the matrix, but the method does not consider the user information. In order to get the user information, a new acquisition method is proposed: the user information matrix is obtained from the item information matrix and the rating matrix, so that the user information matrix and the item information matrix are in the same space. And a symmetric SDAE for collaborative filtering algorithm(CF-SSDAE) is proposed, which uses the two stacked denoising autoencoders to simultaneously train the user information matrix and the item information matrix to obtain the feature matrix of users and items. In order to compare with the state-of-the-art algorithms, experiments show that our algorithm has higher accuracy on the CiteULike dataset.

关键词： recommendation systems collaborative filtering topic model denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

Microscopic biopsy image reconstruction using inception block with denoising auto-encoder approach

引用

International Journal of Information Technology (Singapore) 2024年第4期16卷 2413-2423页

作者： Singh, Shiksha Kumar, Rajesh Department of Electronics & Communication JK Institute of Applied Physics & Technology University of Allahabad UP Prayagraj India

The use of computer-aided image analysis for disease diagnosis and prognosis has dramatically increased during the past 10 years. The introduction of computer-assisted image analysis of images produced by equipment employed in medical science for the prognosis of various diseases has been made possible by the development of digital scanners and high-resolution imaging technologies. Additionally, much like any other digital image, the obtained medical images may become distorted by various distortions and sounds. The noise in histopathology images can be random or have an even frequency distribution;it can be introduced during data acquisition by imaging devices or as a result of signal processing algorithms;either way, the noise appears in the digital image in an uncorrelated way, inevitably lowering the visual quality of the images. In the present article, employed an integrative strategy for the image denoising of the histopathological images of Breast cancer through deep learning (DL) approach. Moreover, some noises remain intact while following the approach due to the direct conduction of the feature map and also the level noise. Henceforth, a denoising model using denoising autoencoder with an Inception network block (InDAENET) has been proposed to deal with the left-out feature maps and high noise signals related to the medical images. The proposed method has been prepared and verified on the publicly available dataset BreakHis. This approach has further been successfully compared with the conventional denoising autoencoder (DAE) method. Henceforth, it paves the way for Histopathological Image Reconstruction using an Inception block with denoising autoencoder for Breast Cancer Detection. © 2024, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management.

关键词： Convolutional neural network denoising autoencoder Histopathological image Inception network Medical image

来源：评论

学校读者我要写书评

暂无评论

SEPARATION MATRIX OPTIMIZATION USING ASSOCIATIVE MEMORY MODEL FOR BLIND SOURCE SEPARATION 23

SEPARATION MATRIX OPTIMIZATION USING ASSOCIATIVE MEMORY MODE...

引用

23rd European Signal Processing Conference (EUSIPCO)

作者： Omachi, Motoi Ogawa, Tetsuji Kobayashi, Tetsunori Fujieda, Masaru Katagiri, Kazuhiro Waseda Univ Dept Comp Sci Tokyo Japan Oki Elect Ind Co Ltd Minato Tokyo Japan

ISBN: (纸本)9780992862633

A source signalis estimated using an associative memory model (AMM) and used for separation matrix optimization in linear blind source separation (BSS) to yield high quality and less distorted speech. Linear-filtering-based BSS, such as independent vector analysis (IVA), has been shown to he effective in sound source separation while avoiding non-linear signal distortion. This technique, however, requires several assumptions of sound sources being independent and generated from non-Gaussian distribution. We propose a method for estimating a linear separation matrix without, any assumptions about the sources by repeating the following two steps: estimating non-distorted reference signals by using an AMM and optimizing the separation matrix to minimize an error between the estimated signal and reference signal. Experimental comparisons carried out in simultaneous speech separation suggest that the proposed method can reduce the residual distortion caused by IVA.

关键词： convolutional neural network denoising autoencoder associative memory model linear filtering blind source separation

来源：评论

学校读者我要写书评

暂无评论

ROBUST AUTOMATIC RECOGNITION OF SPEECH WITH BACKGROUND MUSIC

ROBUST AUTOMATIC RECOGNITION OF SPEECH WITH BACKGROUND MUSIC

引用

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

作者： Malek, Jiri Zdansky, Jindrich Cerva, Petr Tech Univ Liberec Fac Mechatron Informat & Interdisciplinary Studie Studentska 2 Liberec 46117 Czech Republic

ISBN: (纸本)9781509041176

This paper addresses the task of Automatic Speech Recognition (ASR) with music in the background, where the accuracy of recognition may deteriorate significantly. To improve the robustness of ASR in this task, e.g. for broadcast news transcription or subtitles creation, we adopt two approaches: 1) multi-condition training of the acoustic models and 2) denoising autoencoders followed by acoustic model training on the preprocessed data. In the latter case, two types of autoencoders are considered: the fully connected and the convolutional network. Presented experimental results show that all the investigated techniques are able to improve the recognition of speech distorted by music significantly. For example, in the case of artificial mixtures of speech and electronic music (low Signal-to-Noise Ratio (SNR) of 0 dB), we achieved absolute improvement of accuracy by 35.8 %. For real-world broadcast news and a high SNR (about 1 0 dB), we achieved improvement by 2 : 4 %. The important advantage of the studied approaches is that they do not deteriorate the accuracy in scenarios with clean speech (the decrease is about 1%).

关键词： Robust recognition background music feature enhancement denoising autoencoder multi-condition training

来源：评论

学校读者我要写书评

暂无评论

autoencoder based Domain Adaptation for Speaker Recognition under Insufficient Channel Information 18

Autoencoder based Domain Adaptation for Speaker Recognition ...

引用

18th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2017)

作者： Shon, Suwon Mun, Seongkyu Kim, Wooil Ko, Hanseok Korea Univ Sch Elect Engn Seoul South Korea Korea Univ Dept Visual Informat Proc Seoul South Korea Incheon Natl Univ Dept Comp Sci & Engn Incheon South Korea

ISBN: (纸本)9781510848764

In real-life conditions, mismatch between development and test domain degrades speaker recognition performance. To solve the issue, many researchers explored domain adaptation approaches using matched in-domain dataset. However, adaptation would be not effective if the dataset is insufficient to estimate channel variability of the domain. In this paper, we explore the problem of performance degradation under such a situation of insufficient channel information. In order to exploit limited in-domain dataset effectively, we propose an unsupervised domain adaptation approach using autoencoder based Domain Adaptation (AEDA). The proposed approach combines an autoencoder with a denoising autoencoder to adapt resource-rich development dataset to test domain. The proposed technique is evaluated on the Domain Adaptation Challenge 13 experimental protocols that is widely used in speaker recognition for domain mismatched condition. The results show significant improvements over baselines and results from other prior studies.

关键词： unsupervised domain adaptation domain mismatch speaker recognition autoencoder denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

An Effective Deep Learning Based Scheme for Network Intrusion Detection 24

An Effective Deep Learning Based Scheme for Network Intrusio...

引用

24th International Conference on Pattern Recognition (ICPR)

作者： Zhang, Hongpo Wu, Chase Q. Gao, Shan Wang, Zongmin Xu, Yuxiao Liu, Yongpeng State Key Lab Math Engn & Adv Comp Zhengzhou Henan Peoples R China Zhengzhou Univ Cooperat Innovat Ctr Internet Healthcare Zhengzhou Henan Peoples R China New Jersey Inst Technol Dept Comp Sci Newark NJ 07102 USA Hangzhou DPtech Technol Co Ltd Dept Res & Dev Hangzhou Zhejiang Peoples R China

ISBN: (纸本)9781538637883

Intrusion detection systems (IDS) play an important role in the protection of network operations and services. In this paper, we propose an effective network intrusion detection scheme based on deep learning techniques. The proposed scheme employs a denoising autoencoder (DAE) with a weighted loss function for feature selection, which determines a limited number of important features for intrusion detection to reduce feature dimensionality. The selected data is then classified by a compact multilayer perceptron (MLP) for intrusion identification. Extensive experiments are conducted on the UNSW-NB dataset to demonstrate the effectiveness of the proposed scheme. With a small feature selection ratio of 5.9%, the proposed scheme is still able to achieve a superior performance in terms of different evaluation criteria. The strategic selection of a reduced set of features yields satisfactory detection performance with low memory and computing power requirements, making the proposed scheme a promising solution to intrusion detection in high-speed networks.

关键词： Intrusion detection system denoising autoencoder feature selection deep learning

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：