检索结果-内蒙古大学图书馆

The dynamics of a memristor-based Rulkov neuron with fractional-order difference

Chinese Physics B 2022年第6期31卷 30-38页

作者： Yan-Mei Lu Chun-Hua Wang Quan-Li Deng Cong Xu College of Computer Science and Electronic Engineering Hunan UniversityChangsha 410082China

The exploration of the memristor model in the discrete domain is a fascinating *** electromagnetic induction on neurons has also begun to be simulated by some discrete ***,most of the current investigations are based on the integer-order discrete memristor,and there are relatively few studies on the form of fractional *** this paper,a new fractional-order discrete memristor model with prominent nonlinearity is constructed based on the Caputo fractional-order difference ***,the dynamical behaviors of the Rulkov neuron under electromagnetic radiation are simulated by introducing the proposed discrete *** integer-order and fractional-order peculiarities of the system are analyzed through the bifurcation graph,the Lyapunov exponential spectrum,and the iterative *** results demonstrate that the fractional-order system has more abundant dynamics than the integer one,such as hyper-chaos,multi-stable and transient *** addition,the complexity of the system in the fractional form is evaluated by the means of the spectral entropy complexity algorithm and consequences show that it is affected by the order of the fractional *** feature of fractional difference lays the foundation for further research and application of the discrete memristor and the neuron map in the future.

关键词： discrete memristor Rulkov neuron fractional-order difference dynamics

来源：评论

学校读者我要写书评

暂无评论

A Diagnosis Method of Non-Small Cell Lung Cancer Whole Slide Images Based on Multi-Dimensional Feature Fusion 5

A Diagnosis Method of Non-Small Cell Lung Cancer Whole Slide...

引用

5th International Seminar on Artificial Intelligence, Networking and Information Technology, AINIT 2024

作者： Hua, Jiajun Ding, Guangtai College of Computer Engineering and Science Shanghai University Shanghai China

ISBN: (纸本)9798350385557

The diagnosis of pathological images is the gold standard for lung cancer diagnosis. The pathological image diagnosis method based on deep convolutional neural network has achieved good results. However, for the whole slide image, the vast majority of processing methods are to divide it into small images and predict each small image separately, without considering the global spatial information. Therefore, this paper proposes a whole slice image diagnosis method based on multi-dimensional features fusion. Firstly, the sliding window was used to obtain small images, and the convolutional neural network was used to classify and predict them. Secondly, the prediction result with spatial correlation was formed by the feature fusion of the image patch and the surrounding related image patches, and it was mapped to the global space. On the self-built non-small cell lung cancer whole section image dataset, the performance effects of the three attention mechanisms on the small image classifier are compared, and the constructed feature fusion method is compared with the three feature fusion methods. The results show that the classifier of small images in our proposed method has better performance, with an accuracy of 97.5% and a recall rate of 98.2%. The feature fusion method we designed is more conducive to recognizing the tumor center region and tumor contour in the whole slice image. The proposed method combines image processing methods and deep learning methods, which is helpful to improve the performance of image recognition and provide more effective help for the diagnosis of pathological images. © 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

Edge Based Health Monitoring System: Exploring Architecture, Security Threats and Future Directions 5

Edge Based Health Monitoring System: Exploring Architecture,...

引用

5th IEEE International Conference for Emerging Technology, INCET 2024

作者： Ishika Kumar, Anish Kaur, Rupinder Department of Computer Science & Engineering Chandigarh University Mohali India

ISBN: (纸本)9798350361155

By decentralising data processing and analysis, edge computing has become a significant paradigm for health monitoring systems. Edge computing allows real-time processing of health data, improving efficiency, scalability, and privacy by bringing computational resources closer to the source of data generation. This review paper offers a thorough analysis of edge computing-based health monitoring systems, covering their introduction, architecture, prospective security issues, and future scope. In addition to the security and access control measures implemented to protect sensitive medical data, we look at how these systems make use of a broad range of edge devices, sensors, and gateways. The potential of edge computing to transform healthcare delivery and enhance patient outcomes is highlighted in this paper through an analysis of current research trends and advancements. © 2024 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

FaLa: feature-augmented location-aware transformer network for graph representation learning

引用

Neural Computing and Applications 2025年 1-28页

作者： Morshed, Md Golam Sultana, Tangina Lee, Young-Koo Computer Science and Engineering Kyung Hee University Yongin17104 Korea Republic of Computer Science and Engineering International University of Business Agriculture and Technology Dhaka1230 Bangladesh Electronics and Communication Engineering Hajee Mohammad Danesh Science & Technology University Dinajpur5200 Bangladesh

Data augmentation is a technique that improves the ability of neural networks to make accurate predictions by increasing the size of the training dataset. However, it is still uncertain how to properly use data augmentation on graph data in order to boost the performance of graph neural networks (GNNs). While the majority of current graph regularizers primarily concentrate on modifying the topological structures of graphs by adding or deleting nodes and edges, we propose a technique to augment node and edge features in order to improve efficiency. More precisely, we use cosine similarity to perform cross-functions on the existing features. This allows us to generate new graph features, such as node and edge attributes, as well as new graph structures. We then merge these new features together to provide specific pairs of inputs for graph transformer networks. We next propose feature-augmented location-aware transformer (FaLa) networks that generalize well across several graph learning problems by combining the positional and structural encoding of nodes. Additionally, in order to avoid collecting duplicate data from other features, we apply a disparity restriction during training on these latent node embeddings. Experimental findings across eleven real-world datasets demonstrate that our methodology enhances node classification accuracy by a significant margin of 2.8% to 22.7%, link prediction by 1.6% to 8.5%, and graph classification by 7.0% to 39.8% compared to the state-of-the-art graph convolutional network (GCN) and graph transformer (GT) models. This clearly shows the importance of augmenting graph features and location encoding for efficient graph representation learning. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Analysis of early detection and prediction of diabetic retinopathy by deep learning 4th

Analysis of early detection and prediction of diabetic retin...

引用

4th International Conference on Computational Methods in science and Technology, ICCMST 2024

作者： Shubham Sharma, Geetika Garg, Deepanshu Department of Computer Science and Engineering Chandigarh University Mohali Gharaun India

ISBN: (纸本)9781032911571

Diabetic retinopathy (DR) is a very common ocular complication of diabetes. Failure of its early detection and treatment leads to permanent visual loss. Deep learning methods have been highly advanced in recent times in the field of ophthalmology, very specifically on issues related to the detection and categorization of DR. The current study will try to find the use of deep learning techniques in facing challenges of medical diagnosis, particularly related to diabetic retinopathy (DR). This paper outlines the epi-demiological situation in the DR, with its implications for global public health. It particularly focuses on how to use Convolutional Neural Networks (CNNs) for the assessment of retinal images. The study further asks about the importance of some of the data sets used in building resilient and precise deep-learning models. Recent works have reported that the implemented deep learning models have reached high levels of sensitivity and specificity in the automated detection and classification of DR. The study also reports on the implementation difficulties of DR with deep learning, such as model requirements for diverse and well-annotated datasets, interpretability of models, and ethical concerns. The study, hence, underscores the worldwide impacts whereby deep learning is associated with DR. © 2025 the Author(s).

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

TL-GRN: triplet loss-grouped reversible network 3

TL-GRN: triplet loss-grouped reversible network

引用

3rd International Conference on Electronic Information engineering and Data Processing, EIEDP 2024

作者： Lv, Shaolin Sheng, Bin School of Computer Engineering and Science Shanghai University Shanghai China

ISBN: (纸本)9781510680531

This paper focuses on the problem of node classification on text-attributed graphs (TAGs), for which many techniques and methods have been proposed. Early Graph Neural Network methods often face many challenges when dealing with textual node classification tasks, such as incomplete, inaccurate and unbalanced data. These problems can lead to over-smoothing of the model during training, which in turn affects the ability of the model to capture local features and edge cases, thus reducing the accuracy of prediction and classification. In order to improve the performance of Graph Neural Networks in the textual node classification task, this paper explores a series of improvement and extension strategies, including reversible connection, residual connection, grouped convolution, and loss function design. These strategies are integrated into the GNN to form the model TL-GRN (Triplet Loss-Grouped Reversible Network) in this paper. By combining the advantages of Reversible connection and grouped convolution, we proposed a Grouped Reversible Network (GRN). This network structure aims to reduce the memory requirements of the model through reversibility while improving the representation of graph-structured data through grouped convolution. In addition, a Triplet Loss (TL) component is introduced in the design of the loss function, which is specifically used to define the similarity between groups of nodes of different classes. Experimental results on the ogbn-arxiv dataset show that TL-GRN is not only effective but also outperforms existing baseline models when dealing with textual node classification tasks. © 2024 SPIE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Robust Multi-Agent Pathfinding with Continuous Time 34

Robust Multi-Agent Pathfinding with Continuous Time

引用

34th International Conference on Automated Planning and Scheduling, ICAPS 2024

作者： Tan, Wen Jun Tang, Xueyan Cai, Wentong School of Computer Science and Engineering Nanyang Technological University Singapore

ISBN: (纸本)9781577358893

Multi-Agent Pathfinding (MAPF) is the problem of finding plans for multiple agents such that every agent moves from its start location to its goal location without collisions. If unexpected events delay some agents during plan execution, it may not be possible for the agents to continue following their plans without causing any collision. We define and solve a Trobust MAPF problem that seeks plans that can be followed even if some delays occur, under the generalized MAPFR setting with continuous time notions. The proposed approach is complete and provides provably optimal solutions. We also develop an exact method for collision detection among agents that can be delayed. We experimentally evaluate our proposed approach in terms of efficiency and plan cost. Copyright © 2024, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning for Dyslexia Identification through Heterogeneous Cognitive and Behavioral Data Analysis 15

Hybrid Deep Learning for Dyslexia Identification through Het...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Dewanjee, Swarup Muntaha, Sidratul East Delta University Computer Science & Engineering Chattogram Bangladesh

ISBN: (纸本)9798350370249

Dyslexia is a neurological condition, that involves cognitive challenges in processing written languages, impacting reading, writing and spelling abilities. Given that it affects over 10% of global population, early detection of dyslexia in children is crucial. This research proposes an automated system leveraging multiple modalities of data including Electroencephalography (EEG), Eye Tracking (ET) and Handwriting Text images (HTI) for enhanced generalizability. After rigorous preprocessing of data, clean data were used for feature extraction that led to data splitting. For broader understanding, this study employed both Machine Learning (ML) and Deep Learning (DL) architectures and analyses the outcome. A hybrid CNN-BiLSTM DL model was proposed for early detection of dyslexia as it showcased remarkable performance across all modalities, attaining accuracies of 96.57%, 97.62%, 95.81% on EEG, ET and HTI dataset respectively. The proposed model secured its superiority over traditional ML and DL models after thorough hyper parameter tuning, including assessment of various optimizers. The robustness was validated through cross validation with multiple-folds and inspection of Receiver Operating Characteristic (ROC) curves, Confusion Matrix and Accuracy-Loss curves were accomplished for meticulous evaluation. Furthermore, this research compared the proposed model against various Late fusion techniques and Ensemble Learning techniques, in which the proposed model held its consistent superiority. Consequently, the CNN-BiLSTM hybrid model was proposed as a tool for early detection of dyslexia. © 2024 IEEE.

关键词： Dyslexia Detection EEG Eye Tracking Handwriting Image Hybrid Deep Learning Learning Disability Prediction Multi-Modal

来源：评论

学校读者我要写书评

暂无评论

Dynamic Real-Time Scheduling on Distributed Hierarchical Fog Networks 31

Dynamic Real-Time Scheduling on Distributed Hierarchical Fog...

引用

31st IEEE International Conference on High Performance Computing, Data, and Analytics Workshops, HiPCW 2024

作者： Sharma, Amit Auluck, Nitin Dept. of Computer Science & Engineering IIT Ropar India

ISBN: (纸本)9798331509118

We present a novel approach for efficient task scheduling on hierarchical fog nodes, catering to real-time (RT) and non-real-time (NRT) tasks with varying sizes and deadline constraints. Leveraging machine learning (ML) techniques, our proposed solution autonomously allocates tasks across fog nodes, dynamically adapting to changing workload patterns and system conditions. Our novel methodology integrates supervised learning algorithms to predict workload patterns and resource availability, enabling intelligent decision-making in task assignment. Our findings contribute to advancing the state-of-the-art in fog computing by offering a scalable and adaptive solution for dynamic task scheduling in hierarchical heterogeneous environments. © 2024 IEEE

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

MTPNet: Learning Multiple Twin-support Prototypes for Few-shot Medical Image Segmentation

MTPNet: Learning Multiple Twin-support Prototypes for Few-sh...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Song, Feifan Cheng, Ziming Li, Lunbo Zhang, Haofeng Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798350386226

Given the high annotation costs and ethical considerations associated with medical images, leveraging a limited number of annotated samples for Few-Shot Medical Image Segmentation (FSMIS) has become increasingly prevalent. However, existing models tend to focus on visible foreground support information, often overlooking extreme foreground-background imbalances. In addition, query images sometimes have slight different appearance compared to support images of the same category due to the differences in size as well as slicing angle, thus employing only support images to generate prototypes inevitably leads to matching bias. To address these challenges, we present an innovative approach through learning a Multiple Twin-support Prototypes Network (MTPNet). Our approach includes the design of the Scale Consistent Sampling (SCS) module, which adaptively adjusts the foreground and background points within the support set, thereby balancing the influence of various structural elements in the image. Additionally, the Twin-support Prototypes Extraction (TPE) module facilitates the critical interaction between query and support features to extract twin-support prototypes. This module incorporates a Backtrace Interaction Filter (BIF) to eliminate erroneous interaction prototypes. Extensive experimental validation on three widely used medical image datasets demonstrates that our method surpasses current State-of-the-arts, showcasing its potential to address key limitations in FSMIS. The code is available at https://***/FeifanSong/MTPNet. © 2024 IEEE.

关键词： Image segmentation

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：