检索结果-内蒙古大学图书馆

Hyper-Tuned Convolutional Neural Networks for Authorship Verification in Digital Forensic Investigations

Computers, Materials & Continua 2023年第8期76卷 1947-1976页

作者： Asif Rahim Yanru Zhong Tariq Ahmad Sadique Ahmad Mohammed A.ElAffendi School of Computer and Information Security Guilin University of Electronic TechnologyGuilin541004China Guangxi Key Laboratory of Intelligent Processing of Computer Images and Graphics Guilin University of Electronic TechnologyGuilin541004China School of Information and Communication Guilin University of Electronic TechnologyGuilin541004China EIAS:Data Science and Blockchain Laboratory College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia

Authorship verification is a crucial task in digital forensic investigations,where it is often necessary to determine whether a specific individual wrote a particular piece of *** Neural Networks(CNNs)have shown promise in solving this problem,but their performance highly depends on the choice of *** this paper,we explore the effectiveness of hyperparameter tuning in improving the performance of CNNs for authorship *** conduct experiments using a Hyper Tuned CNN model with three popular optimization algorithms:Adaptive Moment Estimation(ADAM),StochasticGradientDescent(SGD),andRoot Mean Squared Propagation(RMSPROP).The model is trained and tested on a dataset of text samples collected from various authors,and the performance is evaluated using accuracy,precision,recall,and F1 *** compare the performance of the three optimization algorithms and demonstrate the effectiveness of hyperparameter tuning in improving the accuracy of the CNN *** results show that the Hyper Tuned CNN model with ADAM Optimizer achieves the highest accuracy of up to 90%.Furthermore,we demonstrate that hyperparameter tuning can help achieve significant performance improvements,even using a relatively simple model architecture like *** findings suggest that the choice of the optimization algorithm is a crucial factor in the performance of CNNs for authorship verification and that hyperparameter tuning can be an effective way to optimize this ***,this paper demonstrates the effectiveness of hyperparameter tuning in improving the performance of CNNs for authorship verification in digital forensic *** findings have important implications for developing accurate and reliable authorship verification systems,which are crucial for various applications in digital forensics,such as identifying the author of anonymous threatening messages or detecting cases of plagiarism.

关键词： Convolutional Neural Network(CNN) hyper-tuning authorship verification digital forensics

来源：评论

学校读者我要写书评

暂无评论

A Novel Dual-supervised Convolutional Network for Retinal Vessel Segmentation

A Novel Dual-supervised Convolutional Network for Retinal Ve...

引用

image processing, Computer Vision and Machine Learning (ICICML), International Conference on

作者： Zizheng Li Junlin Guan Huadeng Wang Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China

ISBN: (纸本)9781665464697

Retinal vascular images play an essential role in the early diagnosis of ophthalmic diseases. Automatic segmentation of retinal blood vessels is a challenging task due to the complex vascular interlacing of fundus images and the noise problems during acquisition. Because of the above problems, we propose a new network structure, which is effective for vascular tree segmentation and can segment more fine blood vessels. Firstly, to improve the segmentation ability of the network to blood vessels, we design a novel convolutional structure of FMCD from the primary level. Then, to focus on the learning of vascular characteristics from the perspectives of deep segmentation and shallow segmentation, we design a deep-shallow dual-level network from the local level. Finally, to assist in supervising the deep and shallow networks to improve the segmentation accuracy of blood vessels and complement the segmentation output of the deep and shallow networks, to segment more microvessels, we use the multi-level semantic fusion module (MSFM) from the overall level. Our Acc, Sen, and F1 on the DRIVE dataset achieve high accuracy of 0.9706, 0.8404, and 0.8332, respectively, outperforming mainstream methods. The proposed method has important clinical implications.

关键词： image segmentation Computer vision Semantics Machine learning Blood vessels Retinal vessels Task analysis

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation Network with Local Multi-Scale Attention for Locating Traffic Sign

Semantic Segmentation Network with Local Multi-Scale Attenti...

引用

International Conference on intelligent Computation Technology and Automation, ICICTA

作者： Shun Zhong Zhuoyuan Zheng Peipei Yang Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China

ISBN: (数字)9781728142845

ISBN: (纸本)9781728142852

Semantic segmentation network is able to detect multi-scale traffic sign effectively. However, probabilities that different scale features participate in decision are equal in the network. In this work, we propose a local multi-scale attention module based on channel-attention, which extracts local features generated by dilated convolution and weights scale features. We demonstrate that adopting local multi-scale attention module on a semantic segmentation network achieves a better performance for locating multi-scale traffic signs than state-of-art convolutional networks by the experimental results on a Chinese traffic sign dataset.

关键词： Semantics Convolution Feature extraction image segmentation Task analysis Kernel Training

来源：评论

学校读者我要写书评

暂无评论

On the optimization of tolerance synthesis with an ontology-based approach

On the optimization of tolerance synthesis with an ontology-...

引用

Chinese Automation Congress (CAC)

作者： Hongcheng Lu Meifa Huang Yanru Zhong Congwen Zheng Key Laboratory of Intelligent Processing of Computer Image and Graphics Guilin University of Electronic Technology Guilin PR China

ISBN: (纸本)9781467371902

In general, mechanical designers have to manually select assembly tolerance types and values in product design. To reduce the uncertainty in manufacturing process, solve the problem of effectively sharing and smoothly exchange tolerance information among heterogeneous CAD system. On the optimization of tolerance synthesis with an ontology-based approach is proposed, automatically generated the tolerance type, variations of tolerance, cost function and tolerance value. Firstly, ontology contains abundant semantic knowledge and semantic structure. Secondly, the Web Ontology Language (OWL) is used to define the concepts of tolerance synthesis, and Semantic Web Rule Language (SWRL) is used to define the constraint conditions and distribute experience. Thirdly, based on the genetic algorithm, a tolerance values optimization model is established with manufacturing cost functions and assembly stack-up constraint. Finally, the effectiveness of the proposed approach is illustrated by using a practical example of the gear case.

关键词： Assembly Cost function Feature extraction Ontologies Solid modeling

来源：评论

学校读者我要写书评

暂无评论

Research on YOLOv8-Based Household Item Detection for Indoor Scenes

Research on YOLOv8-Based Household Item Detection for Indoor...

引用

Data Intelligence and Innovative Application (DIIA), IEEE International Conference on

作者： Jingwen Wu Xiaonan Luo Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798331504434

ISBN: (纸本)9798331504441

This research is driven by the growing need for efficient, scalable object detection in smart home applications with real-time performance and resource constraints. In this study, we utilize the YOLOv8 deep learning model for household item detection, focusing on its performance in real-time scenarios. We compare different versions of YOLOv8—specifically, YOLOv8n, YOLOv8s, and YOLOv8m—using a preprocessed custom dataset. The results indicate that YOLOv8n stands out due to its lower parameter count and faster inference speed, making it ideal for real-time applications, even though it has slightly lower precision and recall. In contrast, while YOLOv8s and YOLOv8m show improvements in certain metrics, their higher computational demands limit their effectiveness in resource-constrained settings. Overall, YOLOv8n effectively balances speed and accuracy, offering a viable solution for household item detection.

关键词： Training Measurement Analytical models Accuracy Computational modeling Heuristic algorithms Smart homes Object detection Real-time systems Tuning

来源：评论

学校读者我要写书评

暂无评论

EOFD-Net: Edge Optimization and Feature Denoising for Weakly Supervised Deep Nuclei Segmentation with Point Annotations

EOFD-Net: Edge Optimization and Feature Denoising for Weakly...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Xipeng Pan Feihu Hou Zhenbing Liu Siyang Feng Rushi Lan Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China

Nuclei segmentation is a fundamental and critical step in digital pathological image analysis. Fully supervised nuclei segmentation requires a lot of pixel-by-pixel manual annotation by pathologists, which is very time-consuming and laborious. To minimize the labeling burden of pathologists, this paper uses only point annotations of nuclei data for weakly supervised learning. Specifically, a two-stage model named EOFD-Net with feature denoising and edge optimization is proposed. In the first stage, three weak labels (K-means cluster labels, Voronoi labels, and superpixel labels) with complementary information are used to train the encoder-decoder network to achieve coarse segmentation of nuclei. A feature denoising module(FDM) is designed in the encoder part, which can effectively reduce noise interference. In the second stage, we designed an edge optimization strategy using the prior knowledge of the trained model in the first stage. Confident learning is employed to denoise pseudo-label and rectify the mislabel. These optimized labels are input into the second stage to obtain the final segmentation results. The performance of our method outperforms current state-of-the-art methods on two publicly nuclei segmentation datasets, MoNuSeg and TNBC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Application of intelligent Schedule Management in Volunteer Service System

Application of Intelligent Schedule Management in Volunteer ...

引用

Data Intelligence and Innovative Application (DIIA), IEEE International Conference on

作者： Yongxin Li Xiaonan Luo Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798331504434

ISBN: (纸本)9798331504441

As the demand for volunteer services grows, enhancing the efficiency and management of these services has become a key issue. This paper explores methods of integrating intelligent scheduling management functions with volunteer service systems to optimize volunteer time management and task allocation. By analyzing existing volunteer service systems, we propose a novel system framework that integrates intelligent scheduling management. This framework updates volunteer schedules in real- time, automatically matches tasks with volunteers' time windows, and optimizes task distribution using smart algorithms. Experimental results show that volunteer service systems with integrated intelligent scheduling management significantly improve task allocation accuracy and volunteer satisfaction. This research provides new ideas and practical basis for the intelligent development of volunteer services.

关键词： Training Performance evaluation Schedules Data analysis Organizations Scheduling User experience Resource management System analysis and design Testing

来源：评论

学校读者我要写书评

暂无评论

An English Pronunciation Evaluation Model Based on Acoustic Phonetics Features

An English Pronunciation Evaluation Model Based on Acoustic ...

引用

Computer Science and Blockchain (CCSB), International Conference on

作者： Hongkang Wang Qingkai Guo Guimin Huang Ya Zhou Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798350356502

ISBN: (纸本)9798350356519

Oral English practice constitutes a crucial component of English language acquisition for non-native speakers; however, traditional classroom teaching methods are increasingly insufficient to address the diverse needs of learners. This paper enhances the evaluation of pronunciation quality within Computer-Assisted Language Learning (CALL) system. To assess the fluency of English learners' pronunciation, this paper introduces the innovative feature known as wordDurationRatio. Additionally, an intonation evaluation method utilizing dynamic time warping (DTW) algorithms is explored. Finally, this study incorporates support vector regression (SVR) algorithms to effectively fuse features, enhancing the assessment result of pronunciation quality.

关键词： Support vector machines Computer science Acoustic phonetics Fuses Heuristic algorithms Evaluation models Education Quality assessment Blockchains Standards

来源：评论

学校读者我要写书评

暂无评论

SRGNet: A GRU Based Feature Fusion Network for image Denoising

SRGNet: A GRU Based Feature Fusion Network for Image Denoisi...

引用

2019 International Symposium on intelligent Signal processing and Communication Systems, ISPACS 2019

作者： Wang, Wenhao Pang, Cheng Liu, Zhenbing Lan, Rushi Luo, Xiaonan Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China National Local Joint Engineering Research Center of Satellite Navigation and Location Service Guilin University of Electronic Technology Guilin China

ISBN: (纸本)9781728130385

image denoising is an essential pretreatment for most of image processing pipelines, which has been extensively studied for several decades. Recently, convolutional neural networks with skip connections show promising performances on image denoising due to their discriminative feature modeling and utilizing of features from former layers. However, they only apply coarse feature fusion strategies like pixel-wise addition or concatenation which are insufficient in image denoising. In this work, we propose a novel network architecture to exploit finer feature fusion. Specifically, a module based on gate recurrent unit is introduced into the architecture, fusing features from different layers and adopting finer feature selection at the same time. Experiments on multiple challenging datasets show the effectiveness of the proposed network. © 2019 IEEE.

关键词： image denoising

来源：评论

学校读者我要写书评

暂无评论

Gland segmentation based on morphological clues and feature fusion

Gland segmentation based on morphological clues and feature ...

引用

image processing, Computer Vision and Machine Learning (ICICML), International Conference on

作者： Lingqi Zeng Huadeng Wang Junlin Guan Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China

The task of gland segmentation based on deep learning serves as a crucial auxiliary tool for diagnosing cancer. However, existing methods still exhibit shortcomings in handling gland adhesion and scale adaptability. To address these issues, we propose a gland segmentation approach that leverages morphological cues and multi-level feature fusion. By analyzing the morphological and imaging characteristics of glands, we have devised a novel scheme for label generation and loss weighting to guide model training. This scheme helps alleviate the challenge posed by the presence of adjacent glands and their adhesion. Additionally, by exploring the correlation between semantic features at different levels, we have developed a new feature fusion mechanism to mitigate issues related to model inaccuracies arising from variations in gland scales. Through experimental comparisons and discussions with classical and state-of-the-art methods, we demonstrate the effectiveness of our proposed approach.

关键词：

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：