检索结果-内蒙古大学图书馆

30th IEEE international conference on Parallel and Distributed Systems, ICPADS 2024

作者： Zhang, Ronghuan Zhao, Jing Li, Ming Zou, Qingzhi Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China Shandong University of Traditional Chinese Medicine School of Intelligence and Information Engineering Jinan China

ISBN: (纸本)9798331515966

Extracting buildings from remote sensing images using deep learning techniques is a widely applied and crucial task. Convolutional Neural Networks (CNNs) adopt hierarchical feature representation, showcasing powerful capabilities in extracting local information but facing challenges in capturing global features. Transformers can address this limitation, but they perform poorly in extracting local features and significantly increase memory requirements and computational complexity. To overcome these challenges, we propose a method for building extraction from remote sensing images called LGDB-Net (Local-Global Dual-Branch Network), employing a dual-branch approach. Firstly, inspired by Swin Transformer, we designed GB-Former(Global Branch-Former) as the backbone network to model global information. We use a linear multi-head self-attention mechanism to reduce time and memory complexity while maintaining a large global receptive field. Additionally, we replace the traditional multi-layer perceptron with a convolution-enhanced multi-layer perceptron to improve channel feature representation, reduce model parameters, and enhance segmentation performance. Secondly, we use multiple Depth-wise Conv3×3 + LN (Layer Normalization) + GeLU (Gaussian Error Linear Unit) modules as the auxiliary branch for local detailed feature extraction. Finally, we adopt a multi-scale feature fusion strategy to integrate feature information from both branches. We conduct a series of experiments on three datasets: WHU, Massachusetts, and Inria. The experimental results demonstrate that the proposed method not only effectively improves segmentation accuracy with lower building omission and commission rates but also significantly reduces model parameters and computational complexity. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Cotton Leaf Disease Detection Using Deep Learning Models

Performance Evaluation of Cotton Leaf Disease Detection Usin...

引用

2024 international conference on Computational Intelligence and Computing Applications, ICCICA 2024

作者： Singh, Gulbir Aggarwal, Ritu Bhatnagar, Vivek Kumar, Suneet Dhondiyal, Shiv Ashish Graphic Era Hill University Department Of Computer Science And Engineering Haldwani Campus Uttarakhand Nanital India Seth Jai Parkash Mukand Lal Institute Of Engineering And Technology Department Of Computer Science And Engineering Yamunanagar Haryana Radaur India Ambala Haryana Mullana India Department Of Computer Science And Engineering Ambala Haryana Mullana India Department Of Computer Science And Engineering Uttarakhand Dehradun India

ISBN: (纸本)9798350306446

Cotton plant diseases significantly impact developing nations' economies and pose a threat to the textile industry. Detecting these diseases is challenging due to lack of competence and fluctuating disease stages. Recent technology has enabled the use of computer-aided techniques to automatically identify and categorize disorders. This paper proposes various deep learning approaches for identifying and categorizing cotton leaf diseases, focusing on unhealthy and unhealthy areas. The study uses a dataset and various optimization techniques, with the Xception model showing the highest validation accuracy of 98.61% using the Adam optimizer. © 2024 IEEE.

关键词： Cotton

来源：评论

学校读者我要写书评

暂无评论

An Empirical Understanding of Black Screen Abnormality in Android multi-View 6

An Empirical Understanding of Black Screen Abnormality in An...

引用

6th IEEE international conference on computer and Communication engineering Technology, CCET 2023

作者： Zhu, Lu Wang, PeiJie Jaiteh, Ousainou Wang, Qianlu Guo, Chenkai College of Computer Science Nankai University Tianjin China School of Information Communication and Technology University of Gambia Banjul Gambia College of Cyber Science Nankai University Tianjin China

ISBN: (纸本)9798350340686

With the increase of requirements for multi-line operations of users, the multi-view mechanism is gradually developed and supported by recent Android versions. However, the underlying exceptions and bugs raised by such mechanisms tend to be neglected by both the developer and system maintainer. To bridge this gap, in this paper, we first conduct a systematical investigation to explore the defects that are possibly raised by the multi-view. We found the black screen problems are especially prevalent in the multi-view context. Based on this finding, we then analyzed the potential reason behind the problem and developed a detection framework to detect this type of defect in a dynamic way. In the experiments on real-world apps collected from the Android market, we find over 86% of apps can be detected to have the black screen risk in multi-view. The finding is not only detected by our automated framework but also verified manually. © 2023 IEEE.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

Attention Information Fusion Emotion Analysis Model Based on BiLSTM-BERT 4

Attention Information Fusion Emotion Analysis Model Based on...

引用

4th international conference on Consumer Electronics and computer engineering, ICCECE 2024

作者： Cheng, Zhi-Wei Li, Shun-Xin Wuhan University of Science and Technology Department of Computer Science and Technology Wuhan China Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial Wuhan China

ISBN: (纸本)9798350384062

Aiming at the problem that most sentiment analysis methods do not focus on the weight fusion of local context and global context information and the important information in fusion features is not prominent, AIFM-BB (Attention information fusion emotion analysis model based on BiLSTM-BERT) is proposed. The model uses a pre-trained BERT model to process text vectors and a collaborative speech analysis algorithm to process audio vectors, and introduces BiLSTM and Attention mechanisms. The weight of the feature vector is dynamically adjusted by combining the global information and local information of text and audio and the attention information of text and audio modes. The emotion analysis results are obtained through the Softmax layer after the fusion features are self-focused. The experimental results show that the accuracy of the proposed AIFM-BB model on the CMU-MOSI dataset is 85.3%, which is 2.8 percentage points higher than the baseline. In the multi-category emotion classification task, the accuracy of the model is 44.7%, an improvement of 1.1 percentage points compared with baseline. The accuracy is 83.6% on the CMU-MOSEI dataset, an improvement of 1.4 percentage points compared to baseline. © 2024 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

LULC Classification Based on multi-Scale Convolutional Auto Encoder with Artificial Bee Colony 2

LULC Classification Based on Multi-Scale Convolutional Auto ...

引用

2nd IEEE international conference on Data science and Network Security, ICDSNS 2024

作者： Kumar, Bura Vijay Husain, Saif O. Kulkarni, Megha Das, Abhijeet Gurumoorthy, Sasikumar School of Computer Science and Artificial Intelligence Sr University Warangal India College of Technical Engineering The Islamic University Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Department of Civil Engineering Bengaluru India Department of Civil Engineering Odisha Bhubaneswar India School of Engineering and Technology Dhanalakshmi Srinivasan University Computer Science and Engineering Tiruchirappalli India

ISBN: (纸本)9798350373110

Monitoring Land Use and Land Cover (LULC) is beneficial to several applications like non- rural development, planning, agricultural, forest departments etc. which enables for global transformation. In recent years, satellite images have become rapid growth in land surveys and environmental planning's. In this research, for LULC classification introduced a framework called multi-Scale Convolutional Auto Encoder with Artificial Bee Colony (MSCAE). This research is evaluated by images collected from Eurosat dataset. Once dataset is collected preprocessing techniques are employed such as normalization to improve the quality of images. After preprocessing, haralick texture is applied to extract Spatial, texture from preprocessed images. In the next phase, Artificial Bee Colony is implemented to consider optimal features to improve the performance. ABC uses bit vectors to select optimal features and fed to classifier based on fitness function which automatically improves the accuracy. These optimal features are provided to MSCAE classifier to classify LULC classes. The MSCAE incorporates convolutional kernel to understand and classify images effectively. The proposed method outperformed with accuracy of 98.2 % when compared to state-of-art methods such as Densnet-121, CNN and 1D CNN. © 2024 IEEE.

关键词： Environmental management

来源：评论

学校读者我要写书评

暂无评论

Research on computer image recognition and classification algorithms for complex scenes 2

Research on computer image recognition and classification al...

引用

2nd IEEE international conference on Electrical, Automation and computer engineering, ICEACE 2024

作者： Zhou, Ziyao Tianjin University of Science and Technology College of Artificial Intelligence Tianjin China

ISBN: (数字)9798350368208

ISBN: (纸本)9798350368208

Image recognition and classification algorithms are more and more widely used in various complex scenes. However, the problems of diverse visual features, occlusion phenomenon, illumination variation and background interference in complex scenes bring great challenges to the existing algorithms. To address the challenges of image recognition and classification in complex scenarios, this paper thoroughly investigates existing mainstream image processing algorithms and introduces an enhanced model that leverages deep learning and multi-scale feature extraction. By integrating convolutional neural network (CNN) and attention mechanism, the model realizes efficient extraction of detailed features in images and global perception of scene information. Experimental results show that the proposed algorithm is superior to traditional algorithms in image recognition accuracy and classification performance in complex scenes, and has high robustness and generalization ability, providing effective technical support for applications in related fields. © 2024 IEEE.

关键词： Visualization Image recognition Attention mechanisms Accuracy Computational modeling Feature extraction Robustness Classification algorithms Convolutional neural networks Image classification

来源：评论

学校读者我要写书评

暂无评论

Advancing Survey on multi-Tenant Cloud Environments: Challenges and Solutions

Advancing Survey on Multi-Tenant Cloud Environments: Challen...

引用

2024 international conference on Intelligent Systems for Cybersecurity, ISCS 2024

作者： Shanker, Bhawani Tufail, Amina Bhatt, Chandradeep Kaushik, Keshav Sajid, Ahthasham Khan, Inam Ullah Riphah Institute of System Engineering Department of Information Security Islamabad Pakistan Graphic Era Hill University Department of Cse Uttarakhand India Graphic Era Deemed to Be University Uttarakhand Dehradun India School of Computer Science University of Petroleum and Energy Studies Dehradun India Department of Computer Science Szabist Islamabad Pakistan

ISBN: (纸本)9798350375237

This research examines cloud forensic challenges and solutions using quantitative methodologies. Major challenges in cloud forensics, including data dispersion, loss of control, multi-tenancy, and integrity/authenticity, were identified. The effectiveness of cloud forensic tools was evaluated, with Tool 2 identified as the most effective. Factors A and B were found to influence tool adoption. Emerging trends in cloud forensics, such as advancements in cloud technologies and new security threats, were explored. The study provides valuable insights for practitioners and researchers, informing decision-making in addressing challenges, selecting tools, and considering future directions in cloud forensics. © 2024 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Sign Language Recognition and Translation: A multi-Modal Approach using computer Vision and Natural Language Processing

Sign Language Recognition and Translation: A Multi-Modal App...

引用

2023 international conference Recent Advances in Natural Language Processing: Large Language Models for Natural Language Processing, RANLP 2023

作者： Li, Jacky Gerdes, Jaren Gojit, James Tao, Austin Katke, Samyak Nguyen, Kate Ahmadnia, Benyamin Department of Computer Engineering and Computer Science California State University Long Beach United States

ISBN: (纸本)9789544520922

Sign-to-Text (S2T) is a hand gesture recognition program in the American Sign Language (ASL) domain. The primary objective of S2T is to classify standard ASL alphabets and custom signs and convert the classifications into a stream of text using neural networks. This paper addresses the shortcomings of pure computer Vision techniques and applies Natural Language Processing (NLP) as an additional layer of complexity to increase S2T's robustness. © 2023 Incoma Ltd. All rights reserved.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

IoT-based System for multi-Head Dual Attention Generative Adversarial Network-based Soil Nutrition and Plant Disease Detection in Smart Agriculture 8

IoT-based System for Multi-Head Dual Attention Generative Ad...

引用

8th international conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Shukla, Arvind Kumar Krishnaraj, Kowsalyadevi Venkatesh, R.J. Santhanalakshmi, M. Iftm University Department of Computer Applications Uttar Pradesh Moradabad India Sona College of Technology Department of Computer Science and Engineering Tamil Nadu Salem India Sri Venkateswara College of Engineering Department of Eee Tamil Nadu Chennai India Department of Computer Science and Engineering Tamil Nadu Dindigul India

ISBN: (纸本)9798350376425

The Internet of Things (IoT) has been increasingly popular in recent years due to its many uses. Regarding the agricultural industry, automated systems for identifying plant diseases offer mixed benefits and some drawbacks. Hence multi-Head Dual Attention Generative Adversarial Network (MHDAGAN) based plant disease detection in IoT is proposed. In order to address the absence of infrastructure in this area, the proposed approach seeks to identify stress to plants caused by crop diseases, environmental imbalance, and soil fertility. The proposed scheme uses nodes to capture plant leaf images, with a sink node collecting information from an automated module for IoT-based monitoring. The Combined Bilateral Parametric Filtering (CBPF) is used to pre-process the nodes' images so they are appropriate for the plant disease detection. After pre-processing, DenseNet201is proposed for extracting the Statistical features of the images. Then multi-Head Dual Attention Generative Adversarial Network (MHDAGAN) is proposed for segmenting and classifying the plant leaf as healthy and disease. In order to improve the classification accuracy, Humboldt Squid Optimization Algorithm is proposed. Utilizing criteria such as sensitivity, accuracy, energy of nodes and specificity on various IoT environments, the detection performance is verified overall. According to the simulation findings, the suggested strategy performs better in terms of detection, with an accuracy of 99.46%. © 2024 IEEE.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

Machine and deep learning techniques for the prediction of diabetics: a review

引用

multimedia Tools and Applications 2025年第18期84卷 19425-19549页

作者： Modak, Sandip Kumar Singh Jha, Vijay Kumar Department of Computer Science & Engineering Sarala Birla University Jharkhand Ranchi India Department of Computer Science & Engineering Birla Institute of Technology Mesra Ranchi India

Diabetes has become one of the significant reasons for public sickness and death in worldwide. By 2019, diabetes had affected more than 463 million people worldwide. According to the international Diabetes Federation report, this figure is expected to rise to more than 700 million in 2040, so early screening and diagnosis of diabetes patients have great significance in detecting and treating diabetes on time. Diabetes is a multi factorial metabolic disease, its diagnostic criteria are difficult to cover all the ethology, damage degree, pathogenesis and other factors, so there is a situation for uncertainty and imprecision under various aspects of the medical diagnosis process. With the development of Data mining, researchers find that machine learning and deep learning, playing an important role in diabetes prediction research. This paper is an in-depth study on the application of machine learning and deep learning techniques in the prediction of diabetics. In addition, this paper also discusses the different methodology used in machine and deep learning for prediction of diabetics since last two decades and examines the methods used, to explore their successes and failure. This review would help researchers and practitioners understand the current state-of-the-art methods and identify gaps in the literature. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Data mining

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：