检索结果-内蒙古大学图书馆

4th International Conference on Natural Language processing, ICNLP 2022

作者： Zhao, Feng Liu, Yu Xi'an China

ISBN: (数字)9781665495448

ISBN: (纸本)9781665495448

Multi-objective evolutionary algorithms (MOEAs)-based fuzzy clustering have been successfully applied to image segmentation problems. However, these MOEAs require a lot of expensive fitness function evaluations. In order to make full use of image prior information and multi-kernel advantages as well as further improve the segmentation performance and time efficiency for image segmentation, a compact fuzzy broad learning system (CFBLS) surrogate-assisted semi-supervised multi-objective evolutionary adaptive multiple-kernel fuzzy clustering (CFBLS-S2AMKFC) algorithm is proposed in this paper. The main contributions of CFBLS-S22AMKFC are described as follows: first, a semi-supervised adaptive multiple-kernel weights fuzzy clustering fitness function is constructed to obtain satisfactory segmentation results;second, using CFBLS model predict the real objective function values in the MOEAS framework, thus reducing the time complexity of the algorithm, and third, constructing a semi-supervised multi-kernel clustering validity index to select the optimal solution from the final nondominated solution set. Experiment results on Berkeley images demonstrate that the proposed algorithm CFBLS-S2AMKFC has good segmentation accuracy and low time cost. © 2022 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

deep learning-Based Architectures For Multimodal Instance Segmentation

Deep Learning-Based Architectures For Multimodal Instance Se...

引用

Workshop on Hyperspectral image and Signal processing: Evolution in Remote Sensing, WHISPERS

作者： Md Omar Faruk Behnood Rasti Margret Fuchs Richard Gloaguen Pedram Ghamisi Technische Universität Dresden Helmholtz-Zentrum Dresden-Rossendorf

We present a novel deep-learning architecture and fusion model as a promising approach to characterize objects in recycling streams, particularly electrolyzer scraps. Electrolyzers are of particular interest due to their complexity and significance for future green tech. By combining RGB and Hyperspectral data, the model enables a comprehensive understanding of the spectral and spatial properties of the materials. To facilitate near real-time hyperspectral feature extraction, we propose an attention-based band selection method. Further-more, a auxiliary loss function is introduced to enhance the learning capability. Leveraging mid-level feature fusion techniques, the model effectively combines modalities, achieving an impressive up to 98.65% mAP on the dataset. Our proposed architecture offers a promising solution for the efficient and accurate detection of electrolyzer materials, and its adaptability to other material streams could significantly improve recycling processes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-frame Video Super-resolution Based on Efficient and Parallel Network 2

Multi-frame Video Super-resolution Based on Efficient and Pa...

引用

2nd IEEE International Conference on Software Engineering and Artificial Intelligence (SEAI) / 7th International Workshop on Pattern Recognition (IWPR)

作者： Yang, Bin Jiang, Juhao Chen, Guannan Fujian Normal Univ Coll Photon & Elect Engn Fuzhou Peoples R China

ISBN: (数字)9781665482233

ISBN: (纸本)9781665482233

Multi-frame video super-resolution(VSR) aims to restore a high-resolution video from both its corresponding low-resolution frame and multiple neighboring frames, in order to make full use of the inter-frame information. However, vast computation complexity hinders the inference speed of video super-resolution. In order to increase the inference speed while ensuring the accuracy of the model, we proposed an efficient and parallel multi-frame VSR network, termed EPVSR. The proposed EPVSR is based on spatio-temporal adversarial learning to achieve temporal consistency and uses TecoGAN as the baseline model. By adding an improved non-deep network, which is composed of parallel subnetworks with multi-resolution streams, these streams are fused together at regular intervals to exchange information. we reduced the number of parameters and make the model lighter. Besides, we implement structural re-parameterization network acceleration technique to optimize the inference process of EPVSR network. Finally, our EPVSR achieves the real-time processing capacity of 4K@36.45FPS. compared with TecoGAN, we achieve 9.75 x performance speedups, but the effect is not reduced. the PSNR of EGVSR are increased by 3.36%. The experimental results show that the nondeep network can effectively speed up the model inference, and the proposed EPVSR has a good super-resolution effect.

关键词： multi-frame video super-resolution TecoGAN PaeNet real-time system non-deep network

来源：评论

学校读者我要写书评

暂无评论

Dynamic image reconstruction and synthesis framework using deep learning algorithm

引用

IET image processing 2020年第7期14卷 1219-1226页

作者： Jeyaraj, Pandia Rajan Nadar, Edward Rajan Samuel Mepco Schlenk Engn Coll Dept Elect & Elect Engn Sivakasi India

This research study shows an effective deformable complex 3D image reconstruction and image synthesis technique by consolidating needed high-level features from a deep convolutional neural network (CNN) system. By recognising the inherent deep features in image patches lead to information discovery in medicinal imaging. Utilising the ADNI and LONI imaging datasets, the performance of the proposed deep learning algorithm image reconstruction and synthesis performance was verified. For validation, various performance indices obtained with the proposed deep learning algorithm were compared with two conventional algorithms namely support vector machine and CNN. Likewise, to reveal the adaptability of the proposed image reconstruction and synthesis system, synthesis and reconstruction experiments were directed on the 7 T cerebrum magnetic resonance image. As presented in the study outcomes, the proposed method can accomplish predominant performance compared with other cutting-edge techniques with either low- or high-level features in terms of the synthesis and reconstruction rate. The proposed algorithm has a training time of 5 s with a structural similarity index of 0.97. In all investigations, the outcome shows that the proposed image reconstruction framework reliably exhibited progressively precise outcomes when contrasted with best in class. Hence, it can be used for possible precise image reconstruction and synthesis related applications.

关键词： biomedical MRI learning (artificial intelligence) neural nets medical image processing image classification brain image reconstruction support vector machines synthesis framework image synthesis technique high-level features deep convolutional neural network system image patches medicinal imaging deep learning algorithm image reconstruction synthesis performance synthesis system reconstruction experiments reconstruction rate image reconstruction framework cerebrum magnetic resonance image LONI imaging dataset ADNI imaging dataset

来源：评论

学校读者我要写书评

暂无评论

Systematic study and design of multimodal MRI image augmentation for brain tumor detection with loss aware exchange and residual networks

引用

INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY 2024年第2期34卷 e22989-e22989页

作者： Bhuyan, Ranadeep Nandi, Gypsy Assam Don Bosco Univ Dept Comp Applicat Gauhati India

One of the most difficult problems that develop when brain cells start to grow out of control is a brain tumor, which is regarded as the most lethal disease of the century. Finding and identifying malignant brain magnetic resonance imaging (MRI) images is the major challenge before therapy. Researchers have been putting a lot of effort into creating the best method for more accurate real-world medical image recognition. For manual categorization, it is quite time-consuming to segment large quantities of MRI data. To mitigate these issues, this paper suggests the information exchange gateway-based residual UNet (IEGResUNet) model, which uses the ResUNet model as a base model. Additionally, including principal component analysis (PCA) data augmentation will increase the model's efficiency while also enhancing its speed. The IEGResUNet model shows an ablation investigation on three Brats datasets, with and without PCA augmentation. The results demonstrate that IEGResUNet will improve segmentation effectiveness and can also manage the imbalance in input data when PCA data augmentation models are included. The dice score on BraTS 2019 for whole tumor, region of core tumor, and region of enhancing tumor were 0.9083, 0.883, and 0.8106 respectively. Also, on BraTS 2020, the dice score for WT, CT, and ET 0.9083, 0.883, and 0.8106 was respectively. Similarly, on BraTS 2021, the dice score for WT, CT, and ET was 0.8737, 0.8866, and 0.7963 respectively. Comparing against baseline models, the IEGResUNet scored well in terms of dice score and intersection over union.

关键词： brain tumor data augmentation deep learning magnetic resonance imaging (MRI) residual learning UNet

来源：评论

学校读者我要写书评

暂无评论

2nd International Conference on Machine learning and Information processing, ICMLIP 2020

2nd International Conference on Machine Learning and Informa...

引用

2nd International Conference on Machine learning and Information processing, ICMLIP 2020

ISBN: (纸本)9789813348585

The proceedings contain 55 papers. The special focus in this conference is on Machine learning and Information processing. The topics include: Performance Analysis of Different Models for Twitter Sentiment;electricity Forecasting Using Machine learning: A Review;end to End learning Human Pose Detection Using Convolutional Neural Networks;conference Paper Acceptance Prediction: Using Machine learning;Object Identification and Tracking Using YOLO Model: A CNN-Based Approach;real-time Hands-Free Mouse Control for Disabled;accounting Fraud Detection Using K-Means Clustering Technique;transforming the Lives of Socially Dependent to Self-dependent Using IoT;enforcement an Evidence and Quality of Query Services in the Cost-Effective Cloud;Prediction and Classification of Biased and Fake News Using NLP and Machine learning Models;a Machine learning Approach Towards Increased Crop Yield in Agriculture;resume Screening Using Natural Language processing and Machine learning: A Systematic Review;assessment of Osteogenic Sarcoma with Histology images Using deep learning;SMDSB: Efficient Off-Chain Storage Model for Data Sharing in Blockchain Environment;ray Tracing Algorithm for Scene Generation in Simulation of Photonic Mixer Device Sensors;a Study of Quality Metrics in Agile Software Development;Optimization of Ray-Tracing Algorithm for Simulation of PMD Sensors;real-time Object Detection for Visually Challenged;reinforcement learning: A Survey;smart Leaf Disease Detection Using image processing;data Encryption on Cloud Database Using Quantum Computing for Key Distribution;prediction and Prevention of Addiction to Social Media Using Machine learning;analysis of Block Matching Algorithms for Motion Estimation in Video Data;information Retrieval Based on Telugu Cross-Language Transliteration;Success of H1-B VISA Using ANN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

JU-VNT: a multi-spectral dataset of indoor object recognition using visible, near-infrared and thermal spectrum

引用

MULtimeDIA TOOLS AND APPLICATIONS 2021年第12期80卷 17807-17826页

作者： Ghosh, Swarnendu Das, Nibaran Sarkar, Priyam Nasipuri, Mita Jadavpur Univ Dept Comp Sci & Engn Kolkata 700032 WB India

Detecting objects in natural scenes can be a very challenging task. In several real-life scenarios it is often found that visible spectrum is not ideal for typical computer vision tasks. Going beyond the range of visible light spectrum, such as the near infrared spectrum or the thermal spectrum allows us to capture many unique properties of objects that normally not captured with a normal camera. In this work we propose two multi-spectral dataset with three different spectrum, namely, the visible, near infrared and thermal spectrum. The first dataset is a single object dataset where we have common desk objects of 25 different categories comprising of various materials. The second dataset comprises of all possible combination using these 25 objects taking a pair at a time. The objects are captured from 8 different angles using the three different cameras. The images are registered and cropped and provided along with classification and localization ground truths. Additionally classification benchmarks have been provided using the ResNet, InceptionNet and DenseNet architectures on both the datasets. The dataset would be publicly available from .

关键词： Multispectral image processing Thermal image Near infrared image deep learning

来源：评论

学校读者我要写书评

暂无评论

Acoustic Signal processing using deep learning for Intelligent Feed Monitoring of Dicentrarchus Labrax

Acoustic Signal Processing using Deep Learning for Intellige...

引用

International IEEE Conference on Signal-image Technologies and Internet-Based System

作者： Laura Bies Shreyas Mysore Guruprasad Mrudula Ingale Dirk Werth August-Wilhelm Scheer Institute Saarbrücken Germany

Acoustic signal processing holds significant promise for real-time fish feeding intensity estimation in aquaculture. Unlike traditional methods reliant on visual cues or sensor data, acoustic analysis provides valuable insights into feeding behavior and demand. By capturing indicators such as water splashing, acoustic techniques can estimate the current feeding demand of fish. Acoustic techniques in aquaculture remain under explored, especially those delving into temporal information within acoustic spectrograms. This paper presents an intelligent monitoring approach using deep learning and acoustic signals. It investigates the perceptual domain of fish feeding acoustic spectrum recognition, extracting insights from Mel Spectrogram feature maps. Employing a supervised machine learning method with a multi-instance multi-label technique, the study classifies audio events during operational scenarios. Furthermore, the research assesses the effectiveness of the proposed neural network (NN) models for multi-label classification by comparing it with established NN architectures like AlexNet, ResNet18, and VGG11, showcasing its superior performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Review on the application of deep learning in network attack detection

引用

JOURNAL OF NETWORK AND COMPUTER APPLICATIONS 2023年第1期212卷 1-15页

作者： Yi, Tao Chen, Xingshu Zhu, Yi Ge, Weijing Han, Zhenhui Sichuan Univ Sch Cyber Sci & Engn Chengdu Peoples R China China Elect Technol Cyber Secur Co Ltd Ind Dev Dept Chengdu Sichuan Peoples R China Sichuan Univ First Ring Rd24 South Sect Chengdu Sichuan Peoples R China

With the development of new technologies such as big data, cloud computing, and the Internet of Things, network attack technology is constantly evolving and upgrading, and network attack detection technology is forced to undergo corresponding iterative evolution. Three main problems are associated with these technologies: the automatic representation of heterogeneous and complex network traffic data, the uneven network attack samples, and the contradiction between the accuracy of the anomaly detection model and the continuous evolution of attacks. Researchers have proposed several network attack detection techniques based on deep learning to address these problems. This study reviews and analyzes the studies aimed at dealing with such problems, considering multiple factors, such as models, traffic representation and feature extraction, threat detection model training, and model robustness improvement. Finally, the existing problems and challenges associated with the current research are analyzed with respect to data category imbalance, high-dimensional massive data processing, concept distribution drift, real-time interpretability of the detection model, and the security of the model.

关键词： Network attack deep learning Flow characterization Detection model Model security

来源：评论

学校读者我要写书评

暂无评论

EventPS: real-time Photometric Stereo Using an Event Camera

EventPS: Real-Time Photometric Stereo Using an Event Camera

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Bohan Yu Jieji Ren Jin Han Feishi Wang Jinxiu Liang Boxin Shi National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University National Engineering Research Center of Visual Technology School of Computer Science Peking University School of Mechanical Engineering Shanghai Jiao Tong University Graduate School of Information Science and Technology The University of Tokyo National Institute of Informatics

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Photometric stereo is a well-established technique to es-timate the surface normal of an object. However, the re-quirement of capturing multiple high dynamic range images under different illumination conditions limits the speed and real-time applications. This paper introduces EventPS, a novel approach to real-time photometric stereo using an event camera. Capitalizing on the exceptional temporal resolution, dynamic range, and low bandwidth character-istics of event cameras, EventPS estimates surface nor-mal only from the radiance changes, significantly enhancing data efficiency. EventPS seamlessly integrates with both optimization-based and deep-learning-based photo-metric stereo techniques to offer a robust solution for non-Lambertian surfaces. Extensive experiments validate the effectiveness and efficiency of EventPS compared to frame-based counterparts. Our algorithm runs at over 30 fps in real-world scenarios, unleashing the potential of EventPS in time-sensitive and high-speed downstream applications. 1 1 Code available: https://***/ybh1998/EventPS

关键词： Computer vision image resolution Lighting Bandwidth Cameras real-time systems Pattern recognition

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：