检索结果-内蒙古大学图书馆

Neuro Inspired Computational Elements conference (NICE)

作者： Debus, Jan Debus, Charlotte Dissertori, Guenther Goetz, Markus Swiss Fed Inst Technol Inst Particle Phys & Astrophys Zurich Switzerland Karlsruhe Inst Technol Sci Comp Ctr Karlsruhe Germany Helmholtz AI Munich Germany

ISBN: (纸本)9798350390599;9798350390582

Spiking neural networks (SNN) hold the promise of being a more biologically plausible, low-energy alternative to conventional artificial neural networks. Their time-variant nature makes them particularly suitable for processing time-resolved, sparse binary data. In this paper, we investigate the potential of leveraging SNNs for the detection of photon coincidences in positron emission tomography (PET) data. PET is a medical imaging technique based on injecting a patient with a radioactive tracer and detecting the emitted photons. One central post-processing task for inferring an image of the tracer distribution is the filtering of invalid hits occurring due to e.g. absorption or scattering processes. Our approach, coined PETNet, interprets the detector hits as a binary-valued spike train and learns to identify photon coincidence pairs in a supervised manner. We introduce a dedicated multi-objective loss function and demonstrate the effects of explicitly modeling the detector geometry on simulation data for two use-cases. Our results show that PETNet can outperform the state-of-the-art classical algorithm with a maximal coincidence detection F1 of 95.2%. At the same time, PETNet is able to predict photon coincidences up to 36 times faster than the classical approach, highlighting the great potential of SNNs in particle physics applications.

关键词： Spiking neural networks positron emission tomography particle coincidence detection supervised denoising

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison of Vision Transformer-Based Models in Medical image Classification 31

Performance Comparison of Vision Transformer-Based Models in...

引用

31st IEEE conference on Signal processing and Communications applications (SIU)

作者： Kanca, Elif Ayas, Selen Kablan, Elif Baykal Ekinci, Murat Karadeniz Tech Univ Yazilim Muhendisligi Trabzon Turkiye Karadeniz Tech Univ Bilgisayar Muhendisligi Trabzon Turkiye

ISBN: (纸本)9798350343557

In recent years, convolutional neural networks have shown significant success and are frequently used in medical image analysis applications. However, the convolution process in convolutional neural networks limits learning of long-term pixel dependencies in the local receptive field. Inspired by the success of transformer architectures in encoding long-term dependencies and learning more efficient feature representation in natural language processing, publicly available color fundus retina, skin lesion, chest X-ray, and breast histology images are classified using Vision Transformer (ViT), Data-Efficient Transformer (DeiT), Swin Transformer, and Pyramid Vision Transformer v2 (PVTv2) models and their classification performances are compared in this study. The results show that the highest accuracy values are obtained with the DeiT model at 96.5% in the chest X-ray dataset, the PVTv2 model at 91.6% in the breast histology dataset, the PVTv2 model at 91.3% in the retina fundus dataset, and the Swin model at 91.0% in the skin lesion dataset.

关键词： Vision transformer-based models transformers medical image classification

来源：评论

学校读者我要写书评

暂无评论

An Efficient Knowledge Transfer Strategy for Spiking neural networks from Static to Event Domain 38

An Efficient Knowledge Transfer Strategy for Spiking Neural ...

引用

38th AAAI conference on artificial Intelligence (AAAI) / 36th conference on Innovative applications of artificial Intelligence / 14th Symposium on Educational Advances in artificial Intelligence

作者： He, Xiang Zhao, Dongcheng Li, Yang Shen, Guobin Kong, Qingqun Zeng, Yi Chinese Acad Sci Inst Automat Brain Inspired Cognit Intelligence Lab Beijing Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing Peoples R China Univ Chinese Acad Sci Sch Future Technol Beijing Peoples R China Chinese Acad Sci Ctr Excellence Brain Sci & Intelligence Technol Shanghai Peoples R China

ISBN: (纸本)9781577358879

Spiking neural networks (SNNs) are rich in spatio-temporal dynamics and are suitable for processing event-based neuromorphic data. However, event-based datasets are usually less annotated than static datasets. This small data scale makes SNNs prone to overfitting and limits their performance. In order to improve the generalization ability of SNNs on event-based datasets, we use static images to assist SNN training on event data. In this paper, we first discuss the domain mismatch problem encountered when directly transferring networks trained on static datasets to event data. We argue that the inconsistency of feature distributions becomes a major factor hindering the effective transfer of knowledge from static images to event data. To address this problem, we propose solutions in terms of two aspects: feature distribution and training strategy. Firstly, we propose a knowledge transfer loss, which consists of domain alignment loss and spatio-temporal regularization. The domain alignment loss learns domain-invariant spatial features by reducing the marginal distribution distance between the static image and the event data. Spatio-temporal regularization provides dynamically learnable coefficients for domain alignment loss by using the output features of the event data at each time step as a regularization term. In addition, we propose a sliding training strategy, which gradually replaces static image inputs probabilistically with event data, resulting in a smoother and more stable training for the network. We validate our method on neuromorphic datasets, including N-Caltech101, CEP-DVS, and N-Omniglot. The experimental results show that our proposed method achieves better performance on all datasets compared to the current state-of-the-art methods. Code is available at https://***/Brain-Cog-Lab/Transfer-for-DVS.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Low-dose CT denoising network combined with attention mechanism

Low-dose CT denoising network combined with attention mechan...

引用

2024 International conference on image processing and artificial Intelligence, ICIPAl 2024

作者： Zhan, Xinru North China University of Technology Beijing China

ISBN: (纸本)9781510681514

Computed tomography (CT) technology is widely used, but the X-ray radiation it emits is a concern. As a result, more and more research is focusing on how to maintain the quality of CT images while reducing the X-ray dose. With the advancement of deep learning technology, convolutional neural networks (CNNs) have been extensively applied in the field of CT reconstruction. However, CNNs focus only on local information and do not adequately consider the overall structure of the image. To address this issue, we have introduced an attention mechanism into the convolutional neural network to denoise low-dose CT images. We tested and evaluated the proposed denoising method using the AAPM-Mayo Clinic low-dose CT dataset. The experimental results show that our method can effectively remove stripe artifacts in LDCT images, preserve image details to a certain extent, and improve several metrics such as PSNR, SSIM, and RMSE compared to LDCT images. © 2024 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Exhaustive Survey on the Methods and applications of Graph neural networks 8th

An Exhaustive Survey on the Methods and Applications of Grap...

引用

8th International conference on Information Science, Communication and Computing

作者： Fan, Dong Cheng, Jieren Tang, Xiangyan Lu, Kai Hainan Univ Sch Comp Sci & Technol Haikou 570228 Hainan Peoples R China Hainan Blockchain Technol Engn Res Ctr Haikou 570228 Hainan Peoples R China Sch Cyberspace Secur Sch Cryptol Haikou 570228 Hainan Peoples R China Hainan Vocat Coll Polit & Law Dept Publ Safety Technol Haikou 571100 Hainan Peoples R China

ISBN: (纸本)9789819617838;9789819617814;9789819617807

The widespread use of deep learning has achieved unprecedented success. neural networks have achieved remarkable results in natural language processing, image recognition and other application fields. The key to the success of neural networks lies in its efficient processing of Euclidean space data, but the results obtained when traditional neural networks are used in non-Euclidean spaces are often not satisfactory to researchers. Graph neural network has been widely developed as a neural network that can be used in non-Euclidean space. This paper starts with the basic knowledge of graphs, introduces graph neural networks, and makes a new classification of them. Then it illustrates its application from 18 application areas. Finally, I put forward my own views on the future development and challenges of graph neural networks.

关键词： Graph neural networks Convolution Recurrent Graph Generation Euclidean non-Euclidean

来源：评论

学校读者我要写书评

暂无评论

Seismic-ionospheric Precursor Prediction Using Deep Learning

Seismic-ionospheric Precursor Prediction Using Deep Learning

引用

2024 Asia Pacific Signal and Information processing Association Annual Summit and conference

作者： Pham, Bach-Tung Chang, Pao-Chi Wang, Jia-Ching Natl Cent Univ Taoyuan Taiwan

ISBN: (纸本)9798350367331;9798350367348

Numerous studies have indicated the potential involvement of seismic-ionospheric precursors (SIPs) in catastrophic earthquakes. These SIPs have been extensively analyzed in terms of characteristics such as the degree of decrease or increase, timing of occurrence, and duration, with a specific focus on electron density or total electron content (TEC). While deep neural networks have demonstrated remarkable accuracy in various applications, their capability to estimate SIPs has been severely limited. In this study, we developed a novel AI prediction model for forecasting SIPs based on a six-channel data sequence: TEC, median TEC, lower bound TEC, upper bound TEC, positive polarity, and negative polarity. To leverage the power of deep learning image classification methods, we treated this data as a six-dimensional image. This approach yielded a maximum accuracy of 67.1 percent.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

SVM-based malware classification through deep learning method 5

SVM-based malware classification through deep learning metho...

引用

5th International conference on Signal processing and Computer Science, SPCS 2024

作者： Shi, Jiawei Wang, Wancheng Zhang, Meng Yao, Qinbo Cheng, Shiyuan Zhan, Zhifei College of Artificial Intelligence and Automation Hohai University Nanjing China

ISBN: (数字)9781510686731

ISBN: (纸本)9781510686724

Various daily applications, including image categorization, natural language comprehension, and voice identification, heavily rely on fully connected and convolutional neural networks. When tackling classification problems, conventional deep learning architectures typically employ softmax activation functions to normalize outputs and minimize the model's cross-entropy loss. In this study, we present a novel malware classification model that integrates hybrid support vector machines with neural networks. Notably, this model substitutes the conventional softmax layer in neural networks with a support vector machine, thereby shifting the learning process towards minimizing margin losses instead of cross-entropy losses. This modification enhances the precision of malware classification for both standard machine learning algorithms and several prevalent deep learning models. To validate our proposed model, we employed the Malimg dataset, comprising malware images derived from binary malware samples. Subsequently, we trained an DL-SVM model to assign scores to each distinct malware family. Experimental outcomes revealed that the malware classification model achieved an accuracy of 96.31%, a precision rate of 97.00%, a recall rate of 97.35%, and an F1 score of 97.16%, respectively. © 2025 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Method for training deep neural networks in vehicle detection using drone-captured data and background synthesis 2

Method for training deep neural networks in vehicle detectio...

引用

conference on Synthetic Data for artificial Intelligence and Machine Learning - Tools, Techniques, and applications II

作者： Pichler, Alexander Hueber, Nicolas French German Res Inst St Louis ISL 5 Rue Gen Cassagnou F-68301 St Louis France

ISBN: (纸本)9781510673892;9781510673885

Deep neural network based military vehicle detectors pose particular challenges due to the scarcity of relevant images and limited access to vehicles in this domain, particularly in the infrared spectrum. To address these issues, a novel drone-based bi-modal vehicle acquisition method is proposed, capturing 72 key images from different view angles of a vehicle in a fast and automated way. By overlaying vehicle patches with relevant background images and utilizing data augmentation techniques, synthetic training images are obtained. This study introduces the use of AI-generated synthetic background images compared to real video footage. Several models were trained and their performance compared in real-world situations. Results demonstrate that the combination of data augmentation, context-specific background samples, and synthetic background images significantly improves model precision while maintaining Mean Average Precision, highlighting the potential of utilizing Generative AI (Stable Diffusion) and drones to generate training datasets for object detectors in challenging domains.

关键词： Vehicle detection and recognition Deep neural networks Generative AI Aerial images Dataset generation Data augmentation Object background separation image processing

来源：评论

学校读者我要写书评

暂无评论

Stable Multilevel Deep neural networks for Option Pricing and xVAs Using Forward-Backward Stochastic Differential Equations 24

Stable Multilevel Deep Neural Networks for Option Pricing an...

引用

5th International conference on AI in Finance

作者： Naarayan, Aadhithya Ashok Parpas, Panos Imperial Coll Dept Comp London England Imperial Coll London Dept Comp London England

ISBN: (纸本)9798400710810

Deep learning techniques have significantly impacted fields such as image processing, computer vision, and natural language processing. However, their influence on quantitative finance, particularly in option pricing, hedging, and portfolio management, has been limited. Traditional financial applications rely on rigorous mathematical models and established numerical methods like Monte Carlo and finite difference methods. However, these methods struggle with high-dimensional problems. Recent works propose using Deep neural networks (DNNs) to solve high-dimensional Partial Differential Equations (PDEs) in finance, potentially overcoming the limitations of conventional techniques. Despite the recent progress, DNN methods face high computational costs, stability issues, and generally fail to meet the high accuracy requirements of the financial industry. This paper addresses these challenges. To address the high computational cost of training deep neural networks for financial applications, we propose a multilevel architecture inspired by multilevel Monte Carlo methods. To enhance stability, we adopt a dynamical systems perspective and utilize the NAIS-Net architecture, which ensures global asymptotic stability. For improving accuracy, we leverage the forward and backward systems of stochastic differential equations (FBSDEs) for option pricing problems. We also provide a theoretical argument that suggests that the proposed approach is superior to Physics Informed neural networks. Finally, the proposed methodology is implemented on several option pricing and xVA problems and is shown to achieve higher efficiency and accuracy, notably improving the pricing of options and xVAs by an order of magnitude over state-of-the-art methods.

关键词： Forward-Backward Stochastic Differential Equations Deep neural networks Partial Differential Equations Option Pricing

来源：评论

学校读者我要写书评

暂无评论

Automatic Classification of Liquid Crystal images Based on Topological Analysis

引用

IEEE SENSORS JOURNAL 2023年第2期23卷 1377-1388页

作者： Romanov, Alexey M. MIREA Russian Technol Univ Inst Artificial Intelligence Moscow 119454 Russia

Liquid crystal image classification is a vital part of modern biosensors. Recent studies have shown that this problem can be solved using computationally intensive intelligent analysis tools, such as convolutional neural networks (CNNs) and support vector machines (SVMs). This article proposes a new method of microscopic image classification for liquid crystals-based biosensors with fast response. This method is based on topological analysis and provides 95% accuracy. Moreover, on the same hardware, it reaches eightfold performance compared to CNNs, which are usually used in similar applications. Finally, it has only nine parameters. Most of those parameters are independent and can be easily tuned based on the properties of the liquid crystals suspension and the microscope. This is a significant benefit compared to machine learning approaches that require large training datasets. The proposed solution can be considered a new step toward the creation of fully automatic biosensors for industrial water quality assessment systems.

关键词： Biosensor classification graphics processing unit (GPU) image processing liquid crystal pattern recognition sensor data processing

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：