检索结果-内蒙古大学图书馆

A Nature-Inspired AI Framework for Accurate Glaucoma Diagnosis

computer Modeling in engineering & Sciences 2025年第4期143卷 539-567页

作者： Jahanzaib Latif Ahsan Wajahat Alishba Tahir Anas Bilal Mohammed Zakariah Abeer Alnuaim School of Software Northwestern Polytechnical UniversityXi’an710072China Shifa College of Medicine Shifa Tameer-e-millat UniversityIslamabad44000Pakistan College of Information Science and Technology Hainan Normal UniversityHaikou571158China Department of Computer Science and Engineering College of Applied Studies and Community ServiceKing Saud UniversityRiyadh11495Saudi Arabia

Glaucoma,a leading cause of blindness,demands early detection for effective *** AI-based diagnostic systems are gaining traction,their performance is often limited by challenges such as varying image backgrounds,pixel intensity inconsistencies,and object size *** address these limitations,we introduce an innovative,nature-inspired machine learning framework combining feature excitation-based dense segmentation networks(FEDS-Net)and an enhanced gray wolf optimization-supported support vectormachine(IGWO-SVM).This dual-stage approach begins with FEDS-Net,which utilizes a fuzzy integral(FI)technique to accurately segment the optic cup(OC)and optic disk(OD)from retinal images,even in the presence of uncertainty and *** the second stage,the IGWO-SVM model optimizes the SVM classification process,leveraging a gray wolf-inspired optimization strategy to fine-tune the kernel function for superior *** testing on three benchmark glaucoma image databases DRIONS-DB,Drishti-GS,and Rim-One-r3 demonstrates the efficacy of our method,achieving classification accuracies of 97.65%,94.88%,and 93.2%,*** results surpass existing state-of-the-art techniques,offering a promising solution for reliable and early glaucoma detection.

关键词： Glaucoma fundus images machine learning nature-inspired algorithm segmentation classification

来源：评论

学校读者我要写书评

暂无评论

An end-to-end contrastive deep-learning framework for remote physiological signal measurement 3

An end-to-end contrastive deep-learning framework for remote...

引用

3rd Vision-Based Remote Physiological Signal Sensing Challenge and Workshop, RePSS 2024

作者： Wu, Bingjie Zhou, Menghan Liu, Wei Wang, Xingyao Zheng, Xingjian Xie, Yiping Luo, Chaoqi Zhen, Liangli Singapore Singapore College of Computer Science and Software Engineering Shenzhen University Shenzhen China School of Electrical Engineering Southwest Jiaotong University Chengdu China

Heart rate measurements based on remote physiological signals could significantly facilitate health monitoring in daily life. However, the ground-truth labels of the physiological signals are expensive and hard to collect. In this paper, we present a contrastive self-supervised learning framework to extract discriminative remote physiological features by leveraging periodic signal priors without ground-truth labels in the pre-training stage. Specifically, a ranking loss and a contrastive learning loss are constructed to extract knowledge with resampling of the video clips. In addition, data augmentation and ensemble learning strategies are designed to fine-tune the pre-trained model and fuse the results to improve the heart rate measurement. Our final solution achieves the 1st place in track 1 of the 3rd Vision-based Remote Physiological Signal Sensing (RePSS) Challenge. © 2024 Copyright for this paper by its authors.

关键词： contactless heart rate measurement Remote photoplethysmography RePSS self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Foreign Object Recognition Model on Coal Mine Belt Conveyors Based on Improved MobileNetV3 7

Foreign Object Recognition Model on Coal Mine Belt Conveyors...

引用

7th International Conference on Communication and Information Systems, ICCIS 2023

作者： Hu, Yujia Zhang, Zhiwei College of Computer Science Sichuan University Department of Artificial Intelligence Chengdu China College of Computer Science Xi'an Aeronautical Institute Department of Software Engineering Xi'an China

ISBN: (纸本)9798350330540

Coal mine belt conveyors are commonly used equipment in coal mining enterprises which transport coal from the coal faces using belts. Currently, video image monitoring serves as the predominant approach to identify foreign objects within the transported coal, such as large gangue and rock bolts. In recent years, the utilization of Convolutional Neural Networks has become prevalent in automatically recognizing foreign objects within images. Nevertheless, existing models suffer from issues including low recognition accuracy and slow speed. In response to the aforementioned problems, this paper proposes an improved coal foreign object recognition model based on MobileNetV3. Firstly, the Coordinate Attention mechanism is introduced into MobileNetV3 to fully consider both channel and spatial features. Secondly, the ReLU6 activation function in MobileNetV3 is replaced with the ELU activation function to augment the model's capacity to express information within the negative value range. Finally, superfluous network layers are removed to reduce computational complexity and improve recognition speed. Experimental results demonstrate that the proposed improved MobileNetV3 model achieves an accuracy of 90.8% in recognizing foreign object images, which is 2.5 to 4.0 percentage points higher compared to commonly used neural networks including AlexNet and EfficientNet. Moreover, compared with MobileNetV3, the proposed model reduces the number of parameters and computational complexity by 40.3% and 12.0% respectively. These results indicate that the proposed model reaches higher recognition accuracy while reducing network size and computational load. As a result, it provides a feasible approach for enhancing safety in coal mining enterprises. © 2023 IEEE.

关键词： Attention mechanism Image foreign object recognition MobileNetV3

来源：评论

学校读者我要写书评

暂无评论

Spatial-spectral attention state-space fusion network for tree carbon estimation using multi-source data

Spatial-spectral attention state-space fusion network for tr...

引用

2024 International Conference on Remote Sensing and Global Positioning Algorithm, RSGPA 2024

作者： Fu, Yawen Hu, Dong Zhou, Yuxin Sun, Zhixiong Zhang, Shuyu College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen518060 China Beijing Institute of Astronautical Systems Engineering Beijing100076 China

Amid rapid industrialization and urbanization, global warming and the urban heat island effect are intensifying. There is an urgent need for rapid and accurate monitoring of carbon storage in urban vegetation to assess and mitigate these environmental issues. While methods exist for estimating above-ground carbon (AGC) stocks in individual trees using deep learning, fewer studies integrate multi-source remote sensing data with these techniques. This study introduces a network that leverages spatial-spectral attention and state-space models, called the spatial-spectral attention state-space fusion network (S4FNet). S4FNet utilizes UAV hyperspectral imaging (HSI) data, light detection and ranging (LiDAR) data, and RGB data to estimate AGC storage in individual trees. This study conducted experiments at two sites, the South and North areas of Shenzhen University’s Yuehai Campus, Shenzhen City, Guangdong Province, China, and compared S4FNet with eight traditional machine learning methods and a deep learning method. The experimental results demonstrate that S4FNet achieves the best performance across all metrics, confirming its excellent capability in predicting AGC stocks using multi-source remote sensing data. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Carbon sequestration

来源：评论

学校读者我要写书评

暂无评论

Tree Regularization for Visual Explanations of Cancer Cell Classification

Tree Regularization for Visual Explanations of Cancer Cell C...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Raza, Muhammad Umair Chen, Jie Wang, Li Nawaz, Adil Leung, Victor C.M. Li, Jianqiang Shenzhen University College of Computer Science and Software Engineering China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology China

ISBN: (纸本)9798350386226

The challenge of interpretability remains a significant barrier to adopting deep neural networks in healthcare domains. Although tree regularization aims to align a deep neural network's decisions with a single axis-aligned decision tree, however, relying on one tree for all inputs often leads to sub-optimal performance and interoperability. To address this limitation, we propose an enhanced tree regularization method that integrates a post-hoc visual explainable model such as Grad-CAM. This approach guides the deep model to be well-approximated by decision trees tailored to the salient regions identified by Grad-CAM in the input space. We rigorously validate the effectiveness of this framework on two cancer cell datasets: CNMC, which focuses on acute lymphoblastic leukemia cells, and ISBI2016, which comprises benign and malignant skin lesions. The results demonstrate that the proposed method delivers simpler and more interpretable explanations without compromising accuracy, thereby advancing the interpretability of deep learning models in critical healthcare applications. © 2024 IEEE.

关键词： Cancer cells

来源：评论

学校读者我要写书评

暂无评论

Optimisation of sparse deep autoencoders for dynamic network embedding

引用

CAAI Transactions on Intelligence Technology 2024年第6期9卷 1361-1376页

作者： Huimei Tang Yutao Zhang Lijia Ma Qiuzhen Lin Liping Huang Jianqiang Li Maoguo Gong College of Computer Science and Software Engineering Shenzhen UniversityShenzhenChina Institute for Infocomm Research Agency for Science Technology and ResearchSingaporeSingapore Key Laboratory of Collaborative Intelligence Systems Ministry of EducationXidian UniversityXi'anChina

Network embedding(NE)tries to learn the potential properties of complex networks represented in a low-dimensional feature ***,the existing deep learningbased NE methods are time-consuming as they need to train a dense architecture for deep neural networks with extensive unknown weight parameters.A sparse deep autoencoder(called SPDNE)for dynamic NE is proposed,aiming to learn the network structures while preserving the node evolution with a low computational *** tries to use an optimal sparse architecture to replace the fully connected architecture in the deep autoencoder while maintaining the performance of these models in the dynamic ***,an adaptive simulated algorithm to find the optimal sparse architecture for the deep autoencoder is *** performance of SPDNE over three dynamical NE models(*** architecture-based deep autoencoder method,DynGEM,and ElvDNE)is evaluated on three well-known benchmark networks and five real-world *** experimental results demonstrate that SPDNE can reduce about 70%of weight parameters of the architecture for the deep autoencoder during the training process while preserving the performance of these dynamical NE *** results also show that SPDNE achieves the highest accuracy on 72 out of 96 edge prediction and network reconstruction tasks compared with the state-of-the-art dynamical NE algorithms.

关键词： deep autoencoder dynamic networks low-dimensional feature space network embedding sparse structure

来源：评论

学校读者我要写书评

暂无评论

DDPG Based Dynamic Scheduling Optimization Mechanism in Real Switch 15

DDPG Based Dynamic Scheduling Optimization Mechanism in Real...

引用

15th International Conference on Communication software and Networks, ICCSN 2023

作者： Wang, Xue Wang, Xingwei Jia, Jie Lu, Xijia Huang, Min School of Computer Science and Engineering Northeastern University China Software College Northeastern University China College of Information Science and Engineering Northeastern University Shenyang China

ISBN: (纸本)9798350329360

Nowadays, more and more traffic with different service requirements is transmitted simultaneously in the network, resulting in network congestion. In order to improve network Quality of Service (QoS), traffic will be classified and processed according to its requirements. The switch uses fair queuing and its extension schemes to schedule it to reduce the packet loss rate. However, statistical data such as packet arrival rate cannot be accurately obtained in the switches, and discrete reinforcement learning cannot model dynamically changing traffic, making existing dynamic bandwidth allocation solutions challenging to implement. Meanwhile, the same weight configuration will obviously cause the packet loss rate to fluctuate, so it is challenging to design an effective reward function. This paper proposes a dynamic scheduling optimization mechanism based on Deep Deterministic Policy Gradient (DDPG), called DDSO, in an actual switch to schedule flows with different service requirements. Firstly, the flow scheduling problem is modeled as a Markov Decision Process (MDP), and DDPG is used to find the optimal queue weight configuration. Queue weight adjustment is a continuous control problem, and DDPG can solve this problem very well. Secondly, we introduce two one-dimensional arrays to design a new reward function, to reduce the influence of packet loss rate fluctuation on reward determination. At last, this mechanism is evaluated through a hardware testbed in two scenarios. The results show that DDSO can effectively schedule the flows with different service requirements and alleviate network congestion. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning in ChatGPT - A Survey 7

Deep Learning in ChatGPT - A Survey

引用

7th International Conference on Trends in Electronics and Informatics, ICOEI 2023

作者： Hashana, A.M. Jasmine Brundha, P. Ahamed Ayoobkhan, Mohamed Uvaze Fazila, S. Computer Science and Engineering Francis Xavier Engineering College Tirunelveli India Software Engineering New Uzbekistan University Tashkent Uzbekistan

ISBN: (纸本)9798350397284

Abstract-As a subset of machine learning, deep learning makes use of multiple-layer neural networks to learn with available data and make decisions or predictions. A large language model called ChatGPT is based on deep learning, specifically a type of neural network called a transformer. ChatGPT's transformer architecture uses attention mechanisms to focus on the most important parts of the input, allowing it to process and comprehend a large amount of text data. In order for the model to comprehend the context and meaning of natural language text, it is trained on a huge database of text, including articles and books. One of the main importance of using deep learning in ChatGPT is its intelligence to understand relationships and patterns from the input text and generate or predict new text that is homogeneous to the input/training data. Because of this, ChatGPT is able to respond to questions and prompts in a manner that is comparable to that of a human, making it useful for a wide scope of natural language processing missions like translating languages, summarizing texts, and responding to questions. It's worth noting that, while deep learning has been highly effective in ChatGPT, it is not without its limitations. To train, deep learning models can be very complex and require a lot of data and computing power. © 2023 IEEE.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

Injections Attacks Efficient and Secure Techniques Based on Bidirectional Long Short Time Memory Model

引用

computers, Materials & Continua 2023年第9期76卷 3605-3622页

作者： Abdulgbar A.R.Farea Gehad Abdullah Amran Ebraheem Farea Amerah Alabrah Ahmed A.Abdulraheem Muhammad Mursil Mohammed A.A.Al-qaness School of Big Data&Software Engineering Chongqing UniversityChongqing401331China Department of Management Science Engineering Dalian University of TechnologyDalian116024China Software College Northeastern UniversityShenyang110169China Department of Information Systems College of Computer and Information ScienceKing Saud UniversityRiyadh11543Saudi Arabia Department of Management Science and Engineering South China University of TechnologyGuangzhou510641China Department of Computer Engineering and Mathematics University of Rovira i VirgiliTarragonaSpain College of Physics and Electronic Information Engineering Zhejiang Normal UniversityJinhua321004China

E-commerce,online ticketing,online banking,and other web-based applications that handle sensitive data,such as passwords,payment information,and financial information,are widely *** web developers may have varying levels of understanding when it comes to securing an online *** Query language SQL injection and cross-site scripting are the two vulnerabilities defined by the OpenWeb Application Security Project(OWASP)for its 2017 Top Ten List Cross Site Scripting(XSS).An attacker can exploit these two flaws and launch malicious web-based actions as a result of these *** published articles focused on these attacks’binary *** article described a novel deep-learning approach for detecting SQL injection and XSS *** datasets for SQL injection and XSS payloads are combined into a single *** dataset is labeledmanually into three labels,each representing a kind of *** work implements some pre-processing algorithms,including Porter stemming,one-hot encoding,and the word-embedding method to convert a word’s text into a *** model used bidirectional long short-term memory(BiLSTM)to extract features automatically,train,and test the payload *** payloads were classified into three types by BiLSTM:XSS,SQL injection attacks,and *** outcomes demonstrated excellent performance in classifying payloads into XSS attacks,injection attacks,and non-malicious ***’s high performance was demonstrated by its accuracy of 99.26%.

关键词： Web security SQL injection XSS deep learning RNN LSTM BiLSTM

来源：评论

学校读者我要写书评

暂无评论

Demystifying AI Advances in Explainable AI (XAI) 3

Demystifying AI Advances in Explainable AI (XAI)

引用

3rd International Conference on Computational Modelling, Simulation and Optimization, ICCMSO 2024

作者： Kumar Pandiya, Dileep Ramrao Joshi, Vilas Tripathi, Kailash Nath ZoomInfo Technology Inc Principal Software Engineer BostonMA United States ISBM College of Engineering Department of Computer Engineering Maharashtra Pune India

ISBN: (纸本)9798350361391

In today's dynamic landscape, the integration of artificial intelligence (AI) has revolutionized operations across diverse domains. However, the enigmatic nature of many AI algorithms presents formidable obstacles, spanning from a dearth of confidence to potential ethical quandaries. Enter Explainable AI (XAI), a burgeoning field that serves as a beacon of clarity, providing to augment transparency and comprehension. This manuscript embarks on a comprehensive exploration of the strides made in XAI, meticulously dissecting its significance, fundamental methodologies, practical applications, hurdles, ethical dimensions, and trajectories for future advancement. By delving into these multifaceted dimensions, this endeavor aims to illuminate the trajectory towards closing the chasm between intricate AI frameworks and human cognition. © 2024 IEEE.

关键词： Advancements Artificial Intelligence Ethical implications Explainable AI (XAI) Transparency

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：