检索结果-内蒙古大学图书馆

Deep Learning for Visual-Features Extraction Based Personalized User Modeling

SN Computer Science 2022年第4期3卷 1-13页

作者： Ben Hassen, Aymen Ben Ticha, Sonia Chaibi, Anja Habacha RIADI Laboratory University of Manouba Manouba 2010 Tunisia

Personalized Recommender Systems help users to choose relevant resources and items from many choices, which is an important challenge that remains actuality today. In recent years, we have witnessed the success of deep learning in several research areas, such as computer vision, natural language processing, and image processing. In this paper, we present a new approach exploiting the images describing items to build a new user’s personalized model. With this aim, we use deep learning to extract and reduction dimensionality of latent features describing images. Then we associate these latents features with user preferences to build the personalized model. This model was used in a Collaborative Filtering (CF) algorithm to make recommendations. Experimentally, to evaluate our approach, we apply our approach on two large real data of differents domains, such as fashion and movies, using fashion data sets from *** and movies data sets from MovieLens, where we show that the best performance of clothing image is more important than the poster of a movie, which explains that the fashion image has an importance in the preferences of the users. Finally, we compare our results to other approaches based on collaborative filtering algorithms. © 2022, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： auto-encoder Deep learning Personalized user modeling Recommender systems Transfer learning Visual features

来源：评论

学校读者我要写书评

暂无评论

Physical Layer Key Generation from Wireless Channels with Non-ideal Channel Reciprocity: A Deep Learning Based Approach 95

Physical Layer Key Generation from Wireless Channels with No...

引用

IEEE 95th Vehicular Technology Conference: (VTC-Spring)

作者： Feng, Cheng Sun, Li Xi An Jiao Tong Univ Sch Informat & Commun Engn Xian 710049 Peoples R China Shaanxi Smart Networks & Ubiquitous Access Res Ct Xian 710049 Peoples R China

ISBN: (数字)9781665482431

ISBN: (纸本)9781665482431

Physical layer encryption is a promising solution to provide transmission security for Internet-of-Things (IoT). To realize physical layer encryption, channel state information (CSI) as a random source to generate secret keys should be exploited. The reciprocity of wireless channel between legitimate communication nodes which is typically assumed for time division duplex (TDD) systems, is of critical importance to ensure the consistency in generated keys at two nodes. However, in practical TDD systems, due to the asynchronous measurement of CSI, the receiver noise and the the difference in hardware, etc., the reciprocity of channel measurements between legitimate parties is hard to be guaranteed, which makes physical layer key generation approach infeasible. To address this issue, we propose a wireless key generation scheme based on deep learning techniques. Firstly, a feature extraction network, which consists of two auto-encoders trained jointly, is developed to extract the common feature from the different yet correlated channel observations at two legitimate nodes, which will be used as the source to generate keys. Then a quantizer with an adaptive guard band width is devised to output a binary secret-key sequence from the feature vector. Numerical results show that the proposed scheme achieves remarkable improvement in terms of key disagreement rate (KDR) and key generation rate (KGR) compared existing counterparts in the literature.

关键词： physical layer key generation CSI feature extraction network auto-encoder

来源：评论

学校读者我要写书评

暂无评论

End-to-End Learning for Integrated Sensing and Communication

End-to-End Learning for Integrated Sensing and Communication

引用

IEEE International Conference on Communications (ICC)

作者： Mateos-Ramos, Jose Miguel Song, Jinxiang Wu, Yibo Hager, Christian Keskin, Musa Furkan Yajnanarayana, Vijaya Wymeersch, Henk Chalmers Univ Technol Dept Elect Engn Gothenburg Sweden Ericsson Res Stockholm Sweden Ericsson Res Gurugram India

ISBN: (纸本)9781538683477

Integrated sensing and communication (ISAC) aims to unify radar and communication systems through a combination of joint hardware, joint waveforms, joint signal design, and joint signal processing. At high carrier frequencies, where ISAC is expected to play a major role, joint designs are challenging due to several hardware limitations. Model-based approaches, while powerful and flexible, are inherently limited by how well the models represent reality. Under model deficit, data-driven methods can provide robust ISAC performance. We present a novel approach for data-driven ISAC using an auto-encoder (AE) structure. The approach includes the proposal of the AE architecture, a novel ISAC loss function, and the training procedure. Numerical results demonstrate the power of the proposed AE, in particular under hardware impairments.

关键词： Integrated sensing and communication Joint radar and communications auto-encoder Machine learning

来源：评论

学校读者我要写书评

暂无评论

CNN Structure Optimization using Differential Evolution with Individual Dependent Mechanism 22

CNN Structure Optimization using Differential Evolution with...

引用

Genetic and Evolutionary Computation Conference (GECCO)

作者： Ikushima, Naoya Ono, Keiko Makihara, Erina Yamakawa, Sohei Shinhama, Ryota Doshisha Univ Grad Sch Sci & Engn Kyoto Japan

ISBN: (纸本)9781450392686

While Convolutional Neural Network (CNN) is known to be a prominent method, there is still a need for appropriate structures to achieve high accuracy. Structure optimization is usually hand-crafted, and there is a raising need for an automated optimization method. In this research, we introduce an auto-encoder to create new structures and apply Differential Evolution with an Individual-Dependent Mechanism (IDE) to a simple CNN Structure optimization problem. Experiments using the proposed framework have been conducted on the Cifar10 dataset. Experimental results showed that the proposed method is fit as a structure optimizer.

关键词： CNN DE Structure Optimization IDE auto-encoder

来源：评论

学校读者我要写书评

暂无评论

基于AEViT与先验知识的胶质瘤IDH1突变状态预测

引用

智能系统学报 2024年第4期19卷 952-960页

作者：徐华畅许倩赵钰琳梁峰宁徐凯朱红徐州医科大学医学信息与工程学院江苏徐州221000 徐州医科大学附属医院医学影像科江苏徐州221000

针对目前预测胶质瘤异柠檬酸脱氢酶1(isocitrate dehydrogenase1,IDH1)突变状态存在的数据不足、准确率较低等问题,提出一种基于AEViT(auto-encoder vision Transformer)与先验知识的胶质瘤IDH1突变状态预测方法。首先使用改进的K-Mean... 详细信息

针对目前预测胶质瘤异柠檬酸脱氢酶1(isocitrate dehydrogenase1,IDH1)突变状态存在的数据不足、准确率较低等问题,提出一种基于AEViT(auto-encoder vision Transformer)与先验知识的胶质瘤IDH1突变状态预测方法。首先使用改进的K-Means聚类算法为无IDH1突变状态标签的胶质瘤磁共振成像(magnetic resonance imaging,MRI)数据标注伪标签,并采用ViT(vision Transformer)网络对伪标签进行修正,得到最终的胶质瘤IDH1突变状态。为避免不准确的伪标签数据影响模型精度,采用果蝇优化算法为伪标签数据赋予最优权重;然后提出基于auto-encoder和ViT的分类模型AEViT,利用auto-encoder提取胶质瘤MRI特征;再将特征输入ViT中对胶质瘤IDH1突变状态进行分类;最后将基于胶质瘤位置信息的先验知识加入模型,达到99.01%的预测准确率。结果表明该方法优于其他现有模型,能够实现胶质瘤数据扩增和术前无创、准确地预测胶质瘤IDH1突变状态,从而辅助诊疗过程。

关键词：胶质瘤异柠檬酸脱氢酶1 K-Means聚类算法伪标签 auto-encoder vision Transformer 果蝇优化算法先验知识

来源：评论

学校读者我要写书评

暂无评论

Attributed network embedding with dual fusion strategies

引用

JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE 2024年第7期36卷 1307-1330页

作者： Dong, Kunjie Zhou, Lihua Huang, Tong Du, Guo Wang Jiang, Yiting Yunnan Univ Kunming Peoples R China Yunnan Normal Univ Kunming Peoples R China Yunnan Univ Sch informat Kunming Peoples R China

Attributed network embedding (ANE) maps nodes in a network into a low-dimensional space while preserving the intrinsic essence of node attribute and network topology. Incorporating node attribute and network topology with more deeply and more harmoniously is a critical and challenging issue in the ANE, because node attribute and network topology are two kinds of heterogeneous information. Existing approaches fuse two kinds of heterogeneous information at different stages: i.e. before, during or after the learning process. In fact, fusions at different stages have their own advantages and disadvantages. To maximise the profit of utilising the attributed and networked information in ANE, we propose an Attributed Network Embedding model with Dual Fusion strategies (abbr. ANEDF), which consists of both mutually beneficial components: early fusion component for capturing the latent complementarity and late fusion component for extracting the unique and distinctive information from node attribute and network topology. The two components are co-trained during the learning process, which promotes information interaction and captures the consensus of heterogeneous information. Extensive experiments with the tasks of node classification, node clustering, link prediction and visualisation on eight publicly available networks have been conducted to evaluate the effectiveness and rationality of the proposed model. The experimental results demonstrate that ANEDF obtains the best classification, clustering and link prediction performance on 6-7 of 8 datasets, respectively.

关键词： Network analysis attributed network embedding fusion strategy auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Distortion Correction and Denoising of Light Sheet Fluorescence Images

引用

SENSORS 2024年第7期24卷 2053页

作者： Julia, Adrien Iguernaissi, Rabah Michel, Francois J. Matarazzo, Valery Merad, Djamal Aix Marseille Univ Ctr Natl Rech Sci Lab Informat & Syst LIS CNRS F-13284 Marseille France Aix Marseille Univ Inst Neurobiol Mediterranee Inst Natl Sante & Rech Medicale INMED INSERM F-13284 Marseille France

Light Sheet Fluorescence Microscopy (LSFM) has emerged as a valuable tool for neurobiologists, enabling the rapid and high-quality volumetric imaging of mice brains. However, inherent artifacts and distortions introduced during the imaging process necessitate careful enhancement of LSFM images for optimal 3D reconstructions. This work aims to correct images slice by slice before reconstructing 3D volumes. Our approach involves a three-step process: firstly, the implementation of a deblurring algorithm using the work of K. Becker;secondly, an automatic contrast enhancement;and thirdly, the development of a convolutional denoising auto-encoder featuring skip connections to effectively address noise introduced by contrast enhancement, particularly excelling in handling mixed Poisson-Gaussian noise. Additionally, we tackle the challenge of axial distortion in LSFM by introducing an approach based on an auto-encoder trained on bead calibration images. The proposed pipeline demonstrates a complete solution, presenting promising results that surpass existing methods in denoising LSFM images. These advancements hold potential to significantly improve the interpretation of biological data.

关键词： light sheet fluorescence microscopy neuroscience preprossessing denoising deconvolution axial distortion deep learning auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Bayesian optimization with enhanced features for adaptively improved glioblastoma partitioning and survival prediction

引用

COMPUTERIZED MEDICAL IMAGING AND GRAPHICS 2024年 116卷 102420-102420页

作者： Li, Yifan Li, Chao Wei, Yiran Price, Stephen Schonlieb, Carola-Bibiane Chen, Xi Univ Bath Dept Comp Sci Bath England Univ Cambridge Dept Clin Neurosci Div Neurosurg Cambridge England Univ Cambridge Dept Appl Math & Theoret Phys Cambridge England

Glioblastoma, an aggressive brain tumor prevalent in adults, exhibits heterogeneity in its microstructures and vascular patterns. The delineation of its subregions could facilitate the development of region-targeted therapies. However, current unsupervised learning techniques for this task face challenges in reliability due to fluctuations of clustering algorithms, particularly when processing data from diverse patient cohorts. Furthermore, stable clustering results do not guarantee clinical meaningfulness. To establish the clinical relevance of these subregions, we will perform survival predictions using radiomic features extracted from them. Following this, achieving a balance between outcome stability and clinical relevance presents a significant challenge, further exacerbated by the extensive time required for hyper-parameter tuning. In this study, we introduce a multi-objective Bayesian optimization (MOBO) framework, which leverages a Feature-enhanced auto-encoder (FAE) and customized losses to assess both the reproducibility of clustering algorithms and the clinical relevance of their outcomes. Specifically, we embed the entirety of these processes within the MOBO framework, modeling both using distinct Gaussian Processes (GPs). The proposed MOBO framework can automatically balance the trade-off between the two criteria by employing bespoke stability and clinical significance losses. Our approach efficiently optimizes all hyper-parameters, including the FAE architecture and clustering parameters, within a few steps. This not only accelerates the process but also consistently yields robust MRI subregion delineations and provides survival predictions with strong statistical validation.

关键词： Glioblastoma MRI Unsupervised learning auto-encoder Bayesian optimization

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Learning for Machinery Adaptive Fault Detection Using Wide-Deep Convolutional autoencoder with Kernelized Attention Mechanism

引用

SENSORS 2024年第24期24卷 8053页

作者： Yan, Hao Si, Xiangfeng Liang, Jianqiang Duan, Jian Shi, Tielin Huazhong Univ Sci & Technol State Key Lab Digital Mfg Equipment & Technol Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Mech Sci & Engn Wuhan 430074 Peoples R China

Applying deep learning to unsupervised bearing fault diagnosis in complex industrial environments is challenging. Traditional fault detection methods rely on labeled data, which is costly and labor-intensive to obtain. This paper proposes a novel unsupervised approach, WDCAE-LKA, combining a wide kernel convolutional autoencoder (WDCAE) with a large kernel attention (LKA) mechanism to improve fault detection under unlabeled conditions, and the adaptive threshold module based on a multi-layer perceptron (MLP) dynamically adjusts thresholds, boosting model robustness in imbalanced scenarios. Experimental validation on two datasets (CWRU and a customized ball screw dataset) demonstrates that the proposed model outperforms both traditional and state-of-the-art methods. Notably, WDCAE-LKA achieved an average diagnostic accuracy of 90.29% in varying fault scenarios on the CWRU dataset and 72.89% in the customized ball screw dataset and showed remarkable robustness under imbalanced conditions;compared with advanced models, it shortens training time by 10-26% and improves average fault diagnosis accuracy by 5-10%. The results underscore the potential of the WDCAE-LKA model as a robust and effective solution for intelligent fault diagnosis in industrial applications.

关键词： unsupervised feature learning machinery fault detection auto-encoder kernelized attention adaptive thresholding

来源：评论

学校读者我要写书评

暂无评论

Facial Anti-Spoofing Using "Clue Maps"

引用

SENSORS 2024年第23期24卷 7635页

作者： Gong, Liang Yu Li, Xue Jun Chong, Peter Han Joo Auckland Univ Technol Dept Elect & Elect Engn Auckland 1010 New Zealand

Spoofing attacks (or Presentation Attacks) are easily accessible to facial recognition systems, making the online financial system vulnerable. Thus, it is urgent to develop an anti-spoofing solution with superior generalization ability due to the high demand for spoofing attack detection. Although multi-modality methods such as combining depth images with RGB images and feature fusion methods could currently perform well with certain datasets, the cost of obtaining the depth information and physiological signals, especially that of the biological signal is relatively high. This paper proposes a representation learning method of an auto-encoder structure based on Swin Transformer and ResNet, then applies cross-entropy loss, semi-hard triplet loss, and Smooth L1 pixel-wise loss to supervise the model training. The architecture contains three parts, namely an encoder, a Decoder, and an auxiliary classifier. The encoder part could effectively extract the features with patches' correlations and the Decoder aims to generate universal "Clue Maps" for further contrastive learning. Finally, the auxiliary classifier is adopted to assist the model in making the decision, which regards this result as one preliminary result. In addition, extensive experiments evaluated Attack Presentation Classification Error Rate (APCER), Bonafide Presentation Classification Error Rate (BPCER) and Average Classification Error Rate (ACER) performances on the popular spoofing databases (CelebA, OULU, and CASIA-MFSD) to compare with several existing anti-spoofing models, and our approach could outperform existing models which reach 1.2% and 1.6% ACER on intra-dataset experiment. In addition, the inter-dataset on CASIA-MFSD (training set) and Replay-attack (Testing set) reaches a new state-of-the-art performance with 23.8% Half Total Error Rate (HTER).

关键词： anti-spoofing detection Swin Transformer ResNet auto-encoder

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：