检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Yang, Sze Jue La, Chinh D. Nguyen, Quang H. Wong, Kok-Seng Tran, Anh Tuan Chan, Chee Seng Doan, Khoa D. College of Engineering and Computer Science VinUniversity Viet Nam Center of Image and Signal Processing Universiti Malaya Malaysia VinAI Research Viet Nam

Backdoor attacks, representing an emerging threat to the integrity of deep neural networks, have garnered significant attention due to their ability to compromise deep learning systems clandestinely. While numerous backdoor attacks occur within the digital realm, their practical implementation in real-world prediction systems remains limited and vulnerable to disturbances in the physical world. Consequently, this limitation has given rise to the development of physical backdoor attacks, where trigger objects manifest as physical entities within the real world. However, creating the requisite dataset to train or evaluate a physical backdoor model is a daunting task, limiting the backdoor researchers and practitioners from studying such physical attack scenarios. This paper unleashes a recipe that empowers backdoor researchers to effortlessly create a malicious, physical backdoor dataset based on advances in generative modeling. Particularly, this recipe involves 3 automatic modules: suggesting the suitable physical triggers, generating the poisoned candidate samples (either by synthesizing new samples or editing existing clean samples), and finally refining for the most plausible ones. As such, it effectively mitigates the perceived complexity associated with creating a physical backdoor dataset, transforming it from a daunting task into an attainable objective. Extensive experiment results show that datasets created by our "recipe" enable adversaries to achieve an impressive attack success rate on real physical world data and exhibit similar properties compared to previous physical backdoor attack studies. This paper offers researchers a valuable toolkit for studies of physical backdoors, all within the confines of their laboratories. © 2023, CC BY-NC-ND.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

An Unsupervised Feature Extraction Method based on CLSTM-AE for Accurate P300 Classification in Brain-Computer Interface Systems

引用

Journal of Biomedical Physics and Engineering 2024年第6期14卷 579-592页

作者： Afrah, Ramin Amini, Zahra Kafie, Rahele School of Advanced Technologies in Medi-cine Isfahan University of Medical Sciences Is-fahan Iran Medical Image and Signal Processing Research Center School of Advanced Technologies in Medicine Isfahan University of Medical Sci-ences Isfahan Iran

Background: The P300 signal, an endogenous component of event-related poten-tials, is extracted from an electroencephalography signal and employed in Brain-com-puter Interface (BCI) devices. Objective: The current study aimed to address challenges in extracting useful features from P300 components and detecting P300 through a hybrid unsupervised man-ner based on Convolutional Neural Network (CNN) and Long Short-term Memory (LSTM). Material and Methods: In this cross-sectional study, CNN as a useful method for the P300 classification task emphasizes spatial characteristics of data. However, CNN and LSTM networks are combined to modify the classification system by extracting both spatial and temporal features. Then, the CNN-LSTM network was trained in an unsupervised learning method based on an autoencoder to improve signal-to-noise Ratio (SNR) by extracting main components from latent space. To deal with imbalanced data, an Adaptive Synthetic Sampling Approach (ADASYN) is used and augmented without any duplication. Results: The trained model, tested on the BCI competition III dataset, including two normal subjects, with an accuracy of 95% and 94% for subjects A and B in P300 detection, respectively. Conclusion: CNN-LSTM, was embedded into an autoencoder and introduced to simultaneously extract spatial and temporal features and manage the computational complexity of the method. Further, ADASYN as an augmentation method was proposed to deal with the imbalanced nature of data, which not only maintained feature space as before but also preserved anatomical features of P300. High-quality results highlight the suitable efficiency of the proposed method. © Journal of Biomedical Physics and Engineering.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

New Methodology for Differentiating Noisy signals of Different Colours Using Geometric Features

New Methodology for Differentiating Noisy Signals of Differe...

引用

IEEE Biennial Congress of Argentina (ARGENCON)

作者： Manuel García Blesa Juan Vorobioff Walter Legnani Signal and Image Processing Center Facultad Regional Buenos Aires Universidad Tecnológica Nacional Buenos Aires Argentina Facultad Regional Buenos Aires Universidad Tecnologica Nacional Buenos Aires Argentina

ISBN: (数字)9798350365931

ISBN: (纸本)9798350365948

This work focuses on the differentiation of coloured noise signals such as pink noise, red noise, blue noise, violet noise, white Gaussian noise and uniform white noise. For this purpose, an algorithm based on the sweeping technique has been used, defining two input values: a embedding dimension and a discretisation factor. Classification is performed by extracting geometric features such as amplitude, and two new parameters: Zenit angle and a shape factor. The process creates three-component vectors in a systematic way, reducing redundant information. As a new result, the model generates a reduced feature space containing unique vectors that can be visualised and used for further processing. The cardinal of this space, i.e. the number of vectors it contains, is the main parameter used to perform the classification. The proposed algorithm showed a significant differentiation of the processed signals using this parameter.

关键词： Wavelet transforms Machine learning algorithms Heuristic algorithms Frequency-domain analysis White noise Feature extraction Wavelet analysis Vectors Classification algorithms Time-domain analysis

来源：评论

学校读者我要写书评

暂无评论

Data Imputation by Pursuing Better Classification: A Supervised Kernel-Based Method

arXiv

引用

arXiv 2024年

作者： Yang, Ruikai He, Fan He, Mingzhen Wang, Kaijie Huang, Xiaolin Institute of Image Processing and Pattern Recognition Department of Automation Shanghai Jiao Tong University 800 Dongchuan RD Shanghai200240 China STADIUS Center for Dynamical Systems Signal Processing and Data Analytics KU Leuven Oude Markt 13 Leuven3000 Belgium

Data imputation, the process of filling in missing feature elements for incomplete data sets, plays a crucial role in data-driven learning. A fundamental belief is that data imputation is helpful for learning performance, and it follows that the pursuit of better classification can guide the data imputation process. While some works consider using label information to assist in this task, their simplistic utilization of labels lacks flexibility and may rely on strict assumptions. In this paper, we propose a new framework that effectively leverages supervision information to complete missing data in a manner conducive to classification. Specifically, this framework operates in two stages. Firstly, it leverages labels to supervise the optimization of similarity relationships among data, represented by the kernel matrix, with the goal of enhancing classification accuracy. To mitigate overfitting that may occur during this process, a perturbation variable is introduced to improve the robustness of the framework. Secondly, the learned kernel matrix serves as additional supervision information to guide data imputation through regression, utilizing the block coordinate descent method. The superiority of the proposed method is evaluated on four real-world data sets by comparing it with state-of-the-art imputation methods. Remarkably, our algorithm significantly outperforms other methods when the data is missing more than 60% of the features. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Train rolling stock video segmentation and classification for bogie part inspection automation: a deep learning approach

引用

Journal of Engineering and Applied Science 2022年第1期69卷 1-24页

作者： Krishnamohan, Kaja Prasad, Ch. Raghava Kishore, P.V.V. Department of Electronics and Communications Engineering K.L. University Green Fields Vaddeswaram Andhra Pradesh Guntur DT522 502 India Image Speech and Signal Processing Research Group Department of Electronics and Communications Engineering Biomechanics and Vision Computing Research Center K.L. University Green Fields Vaddeswaram Andhra Pradesh Guntur DT522 502 India

Train rolling stock examination (TRSE) is a physical procedure for inspecting the bogie parts during transit at a little over 30 kmph. Currently, this process is manually performed across many railway networks across the world. This work proposes to automate the process of TRSE using artificial intelligence techniques. The previous works have proposed active contour-based models for the segmentation of bogie parts. Though accurate, the models require manual intervention and are found to be iterative making them unsuitable for real-time operations. In this work, we propose a segmentation model followed by a deep learning classifier that can accurately increase the deployability of such systems in real time. We apply the UNet model for the segmentation of bogie parts which are further classified using an attention-based convolutional neural network (CNN) classifier. In this work, we propose a shape deformable attention model to identify shape variations occurring in the video sequence due to viewpoint changes during the train movement. The TRSNet is trained and tested on the high-speed train bogie videos captured across four different trains. The results of the experimentation have been shown to improve the recognition accuracy of the proposed system by 6% over the state-of-the-art classifiers previously developed for TRSE. © 2022, The Author(s).

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks based Skin Lesion Segmentation

arXiv

引用

arXiv 2023年

作者： Innani, Shubham Dutande, Prasad Baid, Ujjwal Pokuri, Venu Bakas, Spyridon Talbar, Sanjay Baheti, Bhakti Guntuku, Sharath Chandra Center of Excellence in Signal and Image Processing Shri Guru Gobind Singhji Institute of Engineering and Technology Maharashtra Nanded India Center for Biomedical Image Computing and Analytics University of Pennsylvania Philadelphia United States Department of Computer and Information Science University of Pennsylvania Philadelphia United States

Skin cancer is a serious condition that requires accurate diagnosis and treatment. One way to assist clinicians in this task is using computer-aided diagnosis (CAD) tools that automatically segment skin lesions from dermoscopic images. We propose a novel adversarial learning-based framework called Efficient-GAN (EGAN) that uses an unsupervised generative network to generate accurate lesion masks. It consists of a generator module with a top-down squeeze excitation-based compound scaled path, an asymmetric lateral connection-based bottom-up path, and a discriminator module that distinguishes between original and synthetic masks. A morphology-based smoothing loss is also implemented to encourage the network to create smooth semantic boundaries of lesions. The framework is evaluated on the International Skin Imaging Collaboration (ISIC) Lesion Dataset 2018. It outperforms the current state-of-the-art skin lesion segmentation approaches with a Dice coefficient, Jaccard similarity, and Accuracy of 90.1%, 83.6%, and 94.5%, respectively. We also design a lightweight segmentation framework (MGAN) that achieves comparable performance as EGAN but with an order of magnitude lower number of training parameters, thus resulting in faster inference times for low compute resource settings. Copyright © 2023, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

End-to-End Spectral-Temporal Fusion Using Convolutional Neural Network 1

引用

4th Mediterranean Conference on Pattern Recognition and Artificial Intelligence, MedPRAI 2020

作者： Benzenati, Tayeb Kallel, Abdelaziz Kessentini, Yousri Digital Research Center of Sfax Sfax3021 Tunisia Advanced Technologies for Image and Signal Processing University of Sfax Sfax Tunisia MIRACL Laboratory University of Sfax Sfax Tunisia

ISBN: (数字)9783030718046

ISBN: (纸本)9783030718039

In the last few years, Earth Observation sensors received a large development, offering, therefore, various types of data with different temporal, spatial, spectral, and radiometric resolutions. However, due to physical and budget limitations, the acquisition of images with the best characteristics is not feasible. image fusion becomes a valuable technique to deal with some specific applications. In particular, the vegetation area, which needs a high spectral resolution and frequent coverage. In this paper, we present a novel fusion technique based on Convolutional Neural Networks (CNN) to combine two kinds of remote sensing data with different but complement spectral and temporal characteristics, to produce one high spectral and temporal resolution product. To the best of our knowledge, this is the first attempt to deal with the spectral-temporal fusion problem. The feasibility of the proposed method is evaluated via Sentinel-2 data. The experimental results show that the proposed technique can achieve substantial gains in terms of fusion performance. © 2021, Springer Nature Switzerland AG.

关键词： image fusion

来源：评论

学校读者我要写书评

暂无评论

Bag-Level Multiple Instance Learning for Acute Stress Detection from Video Data

Bag-Level Multiple Instance Learning for Acute Stress Detect...

引用

18th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2025

作者： Brügge, Nele Sophie Korda, Alexandra Borgwardt, Stefan Andreou, Christina Giannakakis, Giorgos Handels, Heinz German Research Center for Artificial Intelligence AI in Medical Image and Signal Processing Lübeck Germany Translational Psychiatry Department of Psychiatry and Psychotherapy University of Luebeck Lübeck23562 Germany Heraklion Greece Department of Electronic Engineering Hellenic Mediterranean University Chania Greece Institute of Agri-food and Life Sciences University Research and Innovation Center Hellenic Mediterranean University Heraklion Greece Institute of Medical Informatics University of Luebeck Lübeck Germany

Stress detection is a complex challenge with implications for health and well-being. It often relies on sensors recording biomarkers and biosignals, which can be uncomfortable and alter behaviour. Video-based facial feature analysis offers a noninvasive alternative. This study explores video-level stress detection using top-k Multiple Instance Learning applied to medical videos. The approach is motivated by the assumption that subjects partly show normal behaviour while performing stressful experimental tasks. Our contributions include a tailored temporal feature network and optimised data utilisation by additionally incorporating bottom-k snippets. Leave-five-subjects-out stress detection results of 95.46% accuracy and 95.49% F1 score demonstrate the potential of our approach, outperforming the baseline methods. Additionally, through multiple instance learning, it is possible to show which temporal video segments the network pays particular attention to. © 2025 by SCITEPRESS – Science and Technology Publications, Lda.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Optical Coherence Tomography image Enhancement via Block Hankelization and Low Rank Tensor Network Approximation

arXiv

引用

arXiv 2023年

作者： Sedighin, Farnaz Cichocki, Andrzej Rabbani, Hossein Medical Image and Signal Processing Research Center School of advanced Technologies in Medicine Isfahan University of Medical Sciences Isfahan*** Iran Systems Research Institute PAS Warsaw00-847 Poland

In this paper, the problem of image super-resolution for Optical Coherence Tomography (OCT) has been addressed. Due to the motion artifacts, OCT imaging is usually done with a low sampling rate and the resulting images are often noisy and have low resolution. Therefore, reconstruction of high resolution OCT images from the low resolution versions is an essential step for better OCT based diagnosis. In this paper, we propose a novel OCT super-resolution technique using Tensor Ring decomposition in the embedded space. A new tensorization method based on a block Hankelization approach with overlapped patches, called overlapped patch Hankelization, has been proposed which allows us to employ Tensor Ring decomposition. The Hankelization method enables us to better exploit the inter connection of pixels and consequently achieve better super-resolution of images. The low resolution image was first patch Hankelized and then its Tensor Ring decomposition with rank incremental has been computed. Simulation results confirm that the proposed approach is effective in OCT super-resolution. Copyright © 2023, The Authors. All rights reserved.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

ENHANCING KERNEL FLEXIBILITY VIA LEARNING ASYMMETRIC LOCALLY-ADAPTIVE KERNELS

arXiv

引用

arXiv 2023年

作者： He, Fan He, Mingzhen Shi, Lei Huang, Xiaolin Suykens, Johan A.K. STADIUS Center for Dynamical Systems Signal Processing and Data Analytics KU Leuven Belgium Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China Shanghai Key Laboratory for Contemporary Applied Mathematics School of Mathematical Sciences Fudan University China

The lack of sufficient flexibility is the key bottleneck of kernel-based learning that relies on manually designed, pre-given, and non-trainable kernels. To enhance kernel flexibility, this paper introduces the concept of Locally-Adaptive-Bandwidths (LAB) as trainable parameters to enhance the Radial Basis Function (RBF) kernel, giving rise to the LAB RBF kernel. The parameters in LAB RBF kernels are data-dependent, and its number can increase with the dataset, allowing for better adaptation to diverse data patterns and enhancing the flexibility of the learned function. This newfound flexibility also brings challenges, particularly with regards to asymmetry and the need for an efficient learning algorithm. To address these challenges, this paper for the first time establishes an asymmetric kernel ridge regression framework and introduces an iterative kernel learning algorithm. This novel approach not only reduces the demand for extensive support data but also significantly improves generalization by training bandwidths on the available training data. Experimental results on real datasets underscore the remarkable performance of the proposed algorithm, showcasing its superior capability in handling large-scale datasets compared to Nyström approximation-based algorithms. Moreover, it demonstrates a significant improvement in regression accuracy over existing kernel-based learning methods and even surpasses residual neural networks. Copyright © 2023, The Authors. All rights reserved.

关键词： Bandwidth

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：