检索结果-内蒙古大学图书馆

4th International Conference on Computer Vision, Application, and Algorithm, CVAA 2024

作者： Liu, Lei Yu, Xuexia Hu, Zhiyuan Li, Xiaojie Zhao, Guowen Su, Jun Beijing China-Power Information &. Technology Co. Ltd. State Grid Information & Telcommunication Group Beijing100000 China

ISBN: (数字)9781510687622

ISBN: (纸本)9781510687615

In order to make the scheduling of tasks to be executed by intelligent agents more flexible and reasonable, a method for adjusting intelligent scheduling tasks based on graph neural networks and adaptive weights is proposed. Based on the short-term memory ability of graph neural networks, search for temporary computing tasks received by intelligent agents in the database as the basic data for subsequent arrangement and adjustment. Extracting thematic content features of intelligent tasks based on recurrent neural networks;Identify priority task targets in the scheduled tasks through graph neural network models. Based on adaptive weights and combined with online learning listwise algorithm, intelligent task scheduling adjustment is achieved. The experimental results show that the conflict rate of task scheduling adjustment using this method remains stable within 5%, and the scheduling adjustment effect is more reasonable;The utilization rate of computing resources is higher after task scheduling adjustment, and task scheduling is more flexible;The longest response time for task scheduling adjustment is 29ms, which is more effective. © 2025 SPIE.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Ovarian cancer detection using optical coherence tomography and convolutional neural networks

引用

neural computing & APPLICATIONS 2022年第11期34卷 8977-8987页

作者： Schwartz, David Sawyer, Travis W. Thurston, Noah Barton, Jennifer Ditzler, Gregory Univ Arizona 1230 E Speedway Blvd Tucson AZ 85721 USA

Ovarian cancer has the sixth-largest fatality rate in the United States among all cancers. A non-surgical assay capable of detecting ovarian cancer with acceptable sensitivity and specificity has yet to be developed. However, such a discovery would profoundly impact the pace of the treatment and improvement to patients' quality of life. Achieving such a solution requires high-quality imaging, image processing, and machine learning to support an acceptably robust automated diagnosis. In this work, we propose an automated framework that learns to identify ovarian cancer in transgenic mice from optical coherence tomography (OCT) recordings. Classification is accomplished using a neural network that perceives spatially ordered sequences of tomograms. We present three neural network-based approaches, namely a VGG-supported feed-forward network, a 3D convolutional neural network, and a convolutional LSTM (Long Short-Term Memory) network. Our experimental results show that our models achieve a favorable performance with no manual tuning or feature crafting, despite the challenging noise inherent in OCT images. Specifically, our best performing model, the convolutional LSTM-based neural network, achieves a mean AUC (+/- standard error) of 0.81 +/- 0.037. To the best of the authors' knowledge, no application of machine learning to analyze depth-resolved OCT images of whole ovaries has been documented in the literature. A significant broader impact of this research is the potential transferability of the proposed diagnostic system from transgenic mice to human organs, which would enable medical intervention from early detection of an extremely deadly affliction.

关键词： Deep learning optical coherence tomography Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Failure prediction of weld defects in long distance pipeline 3

Failure prediction of weld defects in long distance pipeline

引用

3rd International Conference on Applied Mathematics, Modelling, and Intelligent computing, CAMMIC 2023

作者： Feng, Xiao-Xing Fan, Ye China National Aviation Fuel Ningxia Branch Ningxia Yinchuan750001 China

ISBN: (数字)9781510667617

ISBN: (纸本)9781510667600

As an important national energy transportation channel, long distance oil and gas pipeline plays a very important role in the industrial development. In order to ensure the safe operation of pipelines, efficient and accurate prediction of the risk level of long-distance pipelines is essential. Aiming at this practical problem, this paper proposes a failure prediction method of girth weld based on neural network on the basis of analyzing the existing failure prediction methods and models of girth weld. Based on the division of pipeline risk prediction in pipeline integrity management standard and the investigation of factors affecting the failure of girth weld, a neural network model of girth weld failure prediction was constructed. In this paper, the training method of neural network is analyzed and the neural network model suitable for failure risk prediction of girth weld is determined theoretically. The proposed neural network model for failure risk prediction is verified by the actual operation data of a pipeline. The actual calculation shows that the prediction accuracy of high and medium risk girth weld failure risk can reach 100%, 94.1% and 85.7%, respectively. © 2023 SPIE.

关键词： neural network models

来源：评论

学校读者我要写书评

暂无评论

Convolutional neural network Compression for Traffic Sign Recognition

Convolutional Neural Network Compression for Traffic Sign Re...

引用

2023 International Conference on Cloud computing, Performance computing, and Deep Learning, CCPCDL 2023

作者： Zhang, Yuchen Zhang, Xuefang Wuhan Research Institute of Posts and Telecommunications Wuhan430074 China

ISBN: (纸本)9781510666474

An important component of intelligent driving technology is the recognition of traffic signs based on convolutional neural networks (CNN). How to design a traffic sign recognition system with high accuracy and good real-time performance is crucial for the safe driving of vehicles. For the current traffic sign detection algorithm, there are high network complexity, large amount of computation, and high difficulty in edge deployment. This paper proposes a deep neural network compression strategy, which skillfully uses model lightweight, pruning, knowledge distillation and quantification methods. The lightweight full connection layer is used to accelerate reasoning, and the knowledge distillation technology is innovatively used to assist the pruned student network to recover the lost accuracy. The teacher network is used to help pruning restore the original accuracy better, improve the generalization ability, and avoid that the small network cannot work after excessive pruning, so as to achieve a higher pruning rate. This experiment shows that knowledge distillation can assist pruning recovery in a more accurate manner than ordinary pruning. On the traffic sign GTSRB dataset, the mainstream network models VGGNet and AlexNet are used for training and testing. The models are compared before and after compression. Based on the results, the model can be compressed to 0.08% and will have a 97.32% accuracy. © 2023 SPIE.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

HYBRID neural AUDIO EFFECTS 21

HYBRID NEURAL AUDIO EFFECTS

引用

21st Sound and Music computing Conference, SMC 2024

作者： Simionato, Riccardo Fasciani, Stefano Department of Musicology University of Oslo Norway

ISBN: (纸本)9789893520758

Machine learning techniques are commonly employed for modeling audio devices, particularly analog audio effects. Conditioned models have been proposed as well. The conditioning mechanism utilizes the control parameters of the modeled device to influence the sound alteration process. neural networks are shown to be capable of interpolating between conditioning parameter values. This paper further investigates the interpolation ability of neural audio effects. In particular, we introduce additional conditioning parameters to instruct the neural network to learn and predict different audio effects using Feature-wise Linear Modulation and the Gated Linear Unit. The resulting model is a hybrid neural effect that can reproduce, depending on the conditioning values, the audio-altering process of a specific audio effect or interpolates between them. We created hybrid audio effects from a preamp circuit, an optical compressor, and a tape recorder. The designed models are able to learn the sound alteration processes for individual effects and their combinations without producing audible artifacts, and users can use the conditioning parameters to navigate in a continuous space where each point represents a different hybrid audio effect. © 2024. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 Unported License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original.

关键词： Tape recorders

来源：评论

学校读者我要写书评

暂无评论

Learning Graph Enhanced Spatial-Temporal Coherence for Video Anomaly Detection

引用

IEEE SIGNAL PROCESSING LETTERS 2023年 30卷 314-318页

作者： Cheng, Kai Liu, Yang Zeng, Xinhua Fudan Univ Acad Engn & Technol Shanghai 200433 Peoples R China

Video Anomaly Detection (VAD) is a critical yet challenging task in the signal processing community. Since part abnormal events cannot be detected by analyzing spatial or temporal information alone, learning spatial-temporal coherence has been proven the key to effective VAD. To this end, we propose a Graph Enhanced Spatial-Temporal Attention (GESTA) to address unsupervised VAD by learning the spatial-temporal coherence of normal events. Firstly, we propose a Dynamic Graph Recurrent neural network (DGRNN) to extract the motion patterns. Then, we propose a Spatial-Temporal Attention Module (STAM) to better model spatial-temporal coherence by integrating the prototypical spatial and temporal information. Finally, the fused spatial-temporal features are fed into the decoder to predict future frames. In testing phase, the anomaly with irregular information will result in poor prediction results. Experiments on three benchmarks demonstrate that our GESTA performs comparably to the state-of-the-art methods, and extensive analysis proves the effectiveness of DGRNN and STAM.

关键词： optical signal processing Decoding Benchmark testing Task analysis optical computing Coherence Predictive models Video anomaly detection unsupervised learning spatial-temporal attention deep auto-encoder graph network

来源：评论

学校读者我要写书评

暂无评论

Estimation of the surface emission spectra from remotely sensed data based on the physics-informed deep neural network 6

Estimation of the surface emission spectra from remotely sen...

引用

6th International Conference on Geoscience and Remote Sensing Mapping, GRSM 2024

作者： He, Jie Li, Keqiu College of Intelligence and Computing Tianjin University 300072 China

ISBN: (纸本)9781510688018

Surface emission spectra reflects the ability of a target to emit radiation of different wavelengths, and plays an important role in multiple fields as an inherent property of the target object. Currently, common methods require input of multiple data, whose acquisition will directly affect the accuracy and the timeliness of the results obtained. This article proposed a new physics-informed deep neural network for estimation of surface emission spectra, which not only utilizes the ability of deep learning models to handle nonlinear relationships and has been successfully applied to the inversion of various environmental parameters, but also combines physical knowledge of the maximum and minimum emissivity differences in multi band emission spectra to guide deep neural network training. The proposed model achieved accurate results in the simulated dataset. Compare the results of this article with ASTER surface emissivity products, which have similar spatial distributions and numerical ranges. However, the input of the new model only requires remotely sensed data, which has stronger robustness and timeliness. © 2025 SPIE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Neuromorphic Silicon Photonics and Hardware-Aware Deep Learning for High-Speed Inference

引用

JOURNAL OF LIGHTWAVE TECHNOLOGY 2022年第10期40卷 3243-3254页

作者： Moralis-Pegios, Miltiadis Mourgias-Alexandris, George Tsakyridis, Apostolos Giamougiannis, George Totovic, Angelina Dabos, George Passalis, Nikolaos Kirtas, Manos Rutirawut, T. Gardes, F. Y. Tefas, Anastasios Pleros, Nikos Aristotle Univ Thessaloniki Dept Informat Thessaloniki 57001 Greece Aristotle Univ Thessaloniki Ctr Interdisciplinary Res & Innovat Thessaloniki 57001 Greece Univ Southampton Optoelect Res Ctr Southampton SO17 1BJ Hants England

The relentless growth of Artificial Intelligence (AI) workloads has fueled the drive towards non-Von Neuman architectures and custom computing hardware. Neuromorphic photonic engines aspire to synergize the low-power and high-bandwidth credentials of light-based deployments with novel architectures, towards surpassing the computing performance of their electronic counterparts. In this paper, we review recent progress in integrated photonic neuromorphic architectures and analyze the architectural and photonic hardware-based factors that limit their performance. Subsequently, we present our approach towards transforming silicon coherent neuromorphic layouts into high-speed and high-accuracy Deep Learning (DL) engines by combining robust architectures with hardware-aware DL training. Circuit robustness is ensured through a crossbar layout that circumvents insertion loss and fidelity constraints of state-of-the-art linear optical designs. Concurrently, we employ DL training models adapted to the underlying photonic hardware, incorporating noise- and bandwidth-limitations together with the supported activation function directly into neural network (NN) training. We validate experimentally the high-speed and high-accuracy advantages of hardware-aware DL models when combined with robust architectures through a SiPho prototype implementing a single column of a 4:4 photonic crossbar. This was utilized as the pen-ultimate hidden layer of a NN, revealing up to 5.93% accuracy improvement at 5GMAC/sec/axon when noise-aware training is enforced and allowing accuracies of 99.15% and 79.8% for the MNIST and CIFAR-10 classification tasks. Channel-aware training was then demonstrated by integrating the frequency response of the photonic hardware in NN training, with its experimental validation with the MNIST dataset revealing an accuracy increase of 12.93% at a record-high rate of 25GMAC/sec/axon.

关键词： Photonics Adaptive optics Neuromorphics optical modulation Layout Computer architecture High-speed optical techniques neural networks neuromorphic computing neuromorphic photonics optical neural network accelerators

来源：评论

学校读者我要写书评

暂无评论

A multiscale feature extraction feedback network for single image super-resolution

A multiscale feature extraction feedback network for single ...

引用

2024 International Conference on Algorithms, High Performance computing, and Artificial Intelligence, AHPCAI 2024

作者： Yang, Dezhi Xie, Qingsong Xiao, Jinjie Dept. School of Computer Science and Technology Shandong Technology and Business University Yantai China

ISBN: (纸本)9781510685840

In conventional single image super-resolution (SISR) models utilizing deep learning, information is generally transmitted in a feedforward fashion. Nonetheless, these models have not fully exploited the feedback mechanism. Drawing inspiration from the feedback process in human vision, we introduce a Multiscale Feature Extraction Feedback network (MFEFN), which utilizes high-level information to enhance low-level details. In particular, we employ the principles of Recurrent neural networks (RNNs) to reintroduce part of the output back into the model as input, thereby optimizing the input feature representations. We design a multiscale feature extraction channel attention feedback module to handle the feedback connections and generate rich detail texture features. Additionally, to address the issue of limited receptive fields and singular convolutional kernels in models, we propose a multiscale feature extraction module to capture detail texture features at different scales. To further enhance the model's cross-channel learning capability, we incorporate a channel attention mechanism. Comprehensive experimental results showcase the proposed MFEFN's superiority over current state-of-the-art methods. © 2024 SPIE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Global optical and SAR Image Registration Method Based on Local Distortion Division

引用

REMOTE SENSING 2025年第9期17卷 1642-1642页

作者： Li, Bangjie Guan, Dongdong Xie, Yuzhen Zheng, Xiaolong Chen, Zhengsheng Pan, Lefei Zhao, Weiheng Xiang, Deliang High Tech Inst Xian Xian 710025 Peoples R China Beijing Univ Chem Technol Coll Informat Sci & Technol Beijing 100029 Peoples R China

Variations in terrain elevation cause images acquired under different imaging modalities to deviate from a linear mapping relationship. This effect is particularly pronounced between optical and SAR images, where the range-based imaging mechanism of SAR sensors leads to significant local geometric distortions, such as perspective shrinkage and occlusion. As a result, it becomes difficult to represent the spatial correspondence between optical and SAR images using a single geometric model. To address this challenge, we propose a global optical-SAR image registration method that leverages local distortion characteristics. Specifically, we introduce a Superpixel-based Local Distortion Division (SLDD) method, which defines superpixel region features and segments the image into local distortion and normal regions by computing the Mahalanobis distance between superpixel features. We further design a Multi-Feature Fusion Capsule network (MFFCN) that integrates shallow salient features with deep structural details, reconstructing the dimensions of digital capsules to generate feature descriptors encompassing texture, phase, structure, and amplitude information. This design effectively mitigates the information loss and feature degradation problems caused by pooling operations in conventional convolutional neural networks (CNNs). Additionally, a hard negative mining loss is incorporated to further enhance feature discriminability. Feature descriptors are extracted separately from regions with different distortion levels, and corresponding transformation models are built for local registration. Finally, the local registration results are fused to generate a globally aligned image. Experimental results on public datasets demonstrate that the proposed method achieves superior performance over state-of-the-art (SOTA) approaches in terms of Root Mean Squared Error (RMSE), Correct Match Number (CMN), Distribution of Matched Points (Scat), Edge Fidelity (EF), and overall visual qua

关键词： synthetic aperture radar local distortion superpixel features digital capsule feature descriptor

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：