检索结果-内蒙古大学图书馆

Pre-trained SAM as data augmentation for image segmentation

CAAI Transactions on Intelligence technology 2025年第1期10卷 268-282页

作者： Junjun Wu Yunbo Rao Shaoning Zeng Bob Zhang Yangtze Delta Region Institute(Huzhou) University of Electronic Science and Technology of ChinaHuzhouChina School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengduChina Pattern Analysis and Machine Intelligence Research Group Department of Computer and Information ScienceUniversity of MacaoMacaoChina

Data augmentation plays an important role in training deep neural model by expanding the size and diversity of the ***,data augmentation mainly involved some simple transformations of ***,in order to increase the diversity and complexity of data,more advanced methods appeared and evolved to sophisticated generative ***,these methods required a mass of computation of training or *** this paper,a novel training-free method that utilises the Pre-Trained Segment Anything Model(SAM)model as a data augmentation tool(PTSAM-DA)is proposed to generate the augmented annotations for *** the need for training,it obtains prompt boxes from the original annotations and then feeds the boxes to the pre-trained SAM to generate diverse and improved *** this way,annotations are augmented more ingenious than simple manipulations without incurring huge computation for training a data augmentation *** comparative experiments on three datasets are conducted,including an in-house dataset,ADE20K and *** this in-house dataset,namely Agricultural Plot Segmentation Dataset,maximum improvements of 3.77%and 8.92%are gained in two mainstream metrics,mIoU and mAcc,***,large vision models like SAM are proven to be promising not only in image segmentation but also in data augmentation.

关键词： data augmentation image segmentation large model segment anything model

来源：评论

学校读者我要写书评

暂无评论

Dynamic Routing of Multiple QoS-Required Flows in Cloud-Edge Autonomous Multi-Domain Data Center Networks

引用

computers, Materials & Continua 2024年第2期78卷 2287-2308页

作者： Shiyan Zhang Ruohan Xu Zhangbo Xu Cenhua Yu Yuyang Jiang Yuting Zhao School of Computer Science(National Pilot Software Engineering School) Beijing University of Posts and TelecommunicationsBeijing100876China College of Computer Science and Technology Tianjin UniversityTianjin300072China Institute of Artificial Intelligence Nankai UniversityTianjin300071China College of Information Science and Engineering East China University of Science and TechnologyShanghai200237China

The 6th generation mobile networks(6G)network is a kind of multi-network interconnection and multi-scenario coexistence network,where multiple network domains break the original fixed boundaries to form connections and *** this paper,with the optimization objective of maximizing network utility while ensuring flows performance-centric weighted fairness,this paper designs a reinforcement learning-based cloud-edge autonomous multi-domain data center network architecture that achieves single-domain autonomy and multi-domain *** to the conflict between the utility of different flows,the bandwidth fairness allocation problem for various types of flows is formulated by considering different defined reward *** the tradeoff between fairness and utility,this paper deals with the corresponding reward functions for the cases where the flows undergo abrupt changes and smooth changes in the *** addition,to accommodate the Quality of Service(QoS)requirements for multiple types of flows,this paper proposes a multi-domain autonomous routing algorithm called LSTM+*** a Long Short-Term Memory(LSTM)layer in the actor and critic networks,more information about temporal continuity is added,further enhancing the adaptive ability changes in the dynamic network *** LSTM+MADDPG algorithm is compared with the latest reinforcement learning algorithm by conducting experiments on real network topology and traffic traces,and the experimental results show that LSTM+MADDPG improves the delay convergence speed by 14.6%and delays the start moment of packet loss by 18.2%compared with other algorithms.

关键词： Multi-Domain data center networks autonomous routing

来源：评论

学校读者我要写书评

暂无评论

Ferroelectrically gated two-dimensional bismuth oxyselenides for strain-invariant flexible synaptic thin-film transistors

引用

science China(information sciences) 2025年第5期68卷 396-403页

作者： Jie WEN Fei XIAO Zheng-Dong LUO Dongxin TAN Xuetao GAN Dawei ZHANG Zhufei CHU Yinshui XIA Yan LIU Genquan HAN Hangzhou Institute of Technology Xidian University State Key Discipline Laboratory of Wide Band Gap Semiconductor Technology School of MicroelectronicsXidian University Key Laboratory of Light Field Manipulation and Information Acquisition Ministry of Industry and Information Technology Shaanxi Key Laboratory of Optical Information Technology School of Physical Science and Technology Northwestern Polytechnical University School of Materials Science and Engineering The University of New South Wales ARC Centre of Excellence in Future Low-Energy Electronics Technologies (FLEET) The University of New South Wales Faculty of Electrical Engineering Computer Science Ningbo University

Two-dimensional van der Waals（2D vdW） semiconductors have proven to be of great importance for flexible thinfilm transistors（TFTs） owing to their intrinsic mechanical flexibility and superior electronic *** particular,bismuth oxyselenide（Bi2O2Se）,featuring ultrahigh electron mobility along with facile scalable thin-film growth methods,could offer a new option to deliver massively enhanced potential for flexible ***,it has remained a challenge to achieve nonvolatile flexible memory devices based on Bi2O2Se TFTs,thereby hindering the extension of Bi2O2Se TFTs to storage and emerging neuromorphic computing ***,a flexible synaptic TFT is demonstrated through the creation of a Bi2O2Se-based ferroelectric field-effect transistor（FeFET） structure on the flexible mica *** proposed device exhibits excellent nonvolatile memory characteristics,including a large memory window,excellent current modulation ratio,great retention,and strong ***,the Bi2O2Se-based FeFET can be operated as a synaptic device with analog conductance-modulating *** to the superior mechanical flexibility of the component materials and the mica substrate,the Bi2O2Se-based FeFETs can retain their performance against various bending states,showing a straininvariant electrical *** study marks the advancement of Bi2O2Se-based TFTs toward flexible nonvolatile memories and synaptic devices.

关键词： Bi$_{2}$O$_{2}$Se FeFET nonvolatile memory flexible device synaptic transistor

来源：评论

学校读者我要写书评

暂无评论

An attention-based channel estimation network with residual mechanism for 5G OFDM systems 4

An attention-based channel estimation network with residual ...

引用

4th International Conference on Electronic Communication, computer science and technology, ECCST 2024

作者： Jiang, Jinjing Huang, Weipeng Zhang, Xiao Yang, Kun Peng, Tong School of Information Engineering Zhejiang Ocean University China School of Computer Science and Software Engineering Shenzhen Institute of Information Technology China

Due to the significant increase in data transmission speed and gradual increase in Doppler frequency shift, channel estimation accuracy has become one of the most prioritized considerations in many cases. Specifically, we propose an attention-based channel estimation network with a residual mechanism, named TRCE-Net. In our design, the use of the multi-head attention mechanism at the input of the encoder is to obtain richer feature details. A linear series decoder module is implemented by leveraging multiple residual networks with skip connections. This novel design is capable of improving the channel estimation accuracy after deepening the network while effectively preventing degradation. To lessen the number of parameters that the network needs to learn, we introduce the bi-linear interpolation mechanism to replace the traditional up-sampling layer to mitigate both computational overhead and model complexity. According to the simulation results, our proposed TRCE-Net is superior to other state-of-the-art methods with regard to estimation accuracy and robustness to different maximum Doppler shifts, such as ResNet and InterpolateNet. © Published under licence by IOP Publishing Ltd.

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Medical Plant Detection using Transfer learning Coupled with K-Nearest Neighbour Algorithm 3

Medical Plant Detection using Transfer learning Coupled with...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Srambickal, Sai Subramanian Srivastava, Aman Somasundaram, S.K. School of Computer Science and Engineering Vellore Institute of Technology Department of Computer Science and Engineering Tamil Nadu Vellore India Vellore Institute of Technology School of Computer Science and Engineering Department of Information Security Tamil Nadu Vellore India

ISBN: (纸本)9798350372120

Medical Plants are being used for more than a thousand year, with evidences dating before the Mauryain Era (around 322 BCE), they are widely used in the Ayurvedic school of medicine for therapeutic as well as medicinal purposes, it requires an expert to identify the species as well as the medical property associated with a given plant. This paper aims to use deep learning in order to identify a given plant using the leaves of the plant by using a pretrained Convolutional Neural Network (CNN) model namely ResNet50 and MobileNet to extract the latent vector which will then be passed to K-Nearest Neighbour (KNN) algorithm in order to identify the plant class, the best accuracy of the proposed models comes out to be 97.65%. © 2024 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Leveraging EfficientNetB3 in a Deep Learning Framework for High-Accuracy MRI Tumor Classification

引用

computers, Materials & Continua 2024年第10期81卷 867-883页

作者： Mahesh Thyluru Ramakrishna Kuppusamy Pothanaicker Padma Selvaraj Surbhi Bhatia Khan Vinoth Kumar Venkatesan Saeed Alzahrani Mohammad Alojail Department of Computer Science&Engineering Faculty of Engineering and TechnologyJAIN(Deemed-to-be University)Bengaluru562112India School of Computer Science and Engineering VIT-AP UniversityAmaravati522241India Department of Computer Science&Technology Madanapalle Institute of Technology&ScienceMadanapalle517325India School of Science Engineering and EnvironmentUniversity of SalfordManchesterM54WTUK School of Computer Science Engineering&Information Systems(SCORE) Vellore Institute of Technology(VIT)Vellore632014India Management Information System Department College of Business AdministrationKing Saud UniversityRiyadh11531Saudi Arabia Adjunct Research Faculty Centre for Research Impact&OutcomeChitkara UniversityRajpuraPunjab140401India

Brain tumor is a global issue due to which several people suffer,and its early diagnosis can help in the treatment in a more efficient *** different types of brain tumors,including gliomas,meningiomas,pituitary tumors,as well as confirming the absence of tumors,poses a significant challenge using MRI *** approaches predominantly rely on traditional machine learning and basic deep learning methods for image *** methods often rely on manual feature extraction and basic convolutional neural networks(CNNs).The limitations include inadequate accuracy,poor generalization of new data,and limited ability to manage the high variability in MRI *** the EfficientNetB3 architecture,this study presents a groundbreaking approach in the computational engineering domain,enhancing MRI-based brain tumor *** approach highlights a major advancement in employing sophisticated machine learning techniques within computer science and engineering,showcasing a highly accurate framework with significant potential for healthcare *** model achieves an outstanding 99%accuracy,exhibiting balanced precision,recall,and F1-scores across all tumor types,as detailed in the classification *** successful implementation demonstrates the model’s potential as an essential tool for diagnosing and classifying brain tumors,marking a notable improvement over current *** integration of such advanced computational techniques in medical diagnostics can significantly enhance accuracy and efficiency,paving the way for wider *** research highlights the revolutionary impact of deep learning technologies in improving diagnostic processes and patient outcomes in neuro-oncology.

关键词： Deep learning MRI brain tumor cassification EfficientNetB3 computational engineering healthcare technology artificial intelligence in medical imaging tumor segmentation neuro-oncology

来源：评论

学校读者我要写书评

暂无评论

Deep transfer learning technique to detect white blood cell classification in regular clinical practice using histopathological images

引用

Multimedia Tools and Applications 2025年第9期84卷 5699-5723页

作者： Davamani, K. Anita Jawahar, Malathy Anbarasi, L. Jani Ravi, Vinayakumar Al Mazroa, Alanoud Robin, C. R. Rene Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Leather Process Technology Division CSIR-Central Leather Research Institute Chennai India School of Computing Science and Engineering Vellore Institute of Technology Vellore India Computer Science and Engineering Sri Sairam Engineering College Sirukalathur India Center for Artificial Intelligence Prince Mohammad Bin Fahd University Khobar Saudi Arabia Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh11671 Saudi Arabia

Leukemia, a malignant disease characterized by the rapid proliferation of specific types of white blood cells (WBC), has prompted increased interest in leveraging automatic WBC classification system. This study presents the design of a robust WBC classification system, integrating deep learning with microscopic image analysis. The proposed classification model is designed to categorize blood cells into four distinct groups: eosinophil, lymphocyte, monocyte, and neutrophil. The study employs a Kaggle image dataset for comprehensive learning. The dataset comprises 12,500 microscopic images used to categorize the four blood cell groups. To enhance performance and reduce the likelihood of overfitting, transfer learning techniques are employed. Six deep transfer learning models namely VGG16, ResNet50, AlexNet, MobileNet, GoogLeNet, and EfficientNetBO are used for feature extraction and classification. The results of the experiments show that VGG16 and MobileNet demonstrated enhancements compared to other pre-trained models when evaluated on both augmented and original datasets. A diverse set of evaluation criteria was employed to thoroughly assess the effectiveness of medical image classification. Notably, the VGG16 and MobileNet models accurately predicted Lymphocytes and Monocytes with a 100% accuracy rate, and Eosinophil and Neutrophil with rates of 99.35% and 99.81%, respectively. This research work empower medical practitioners, particularly in the field of pathology and hematology by providing advanced tools for accurate blood cell classification. The proposed VGG16 and MobileNet models hold promise for simplifying WBC classification, improving decision-making processes, and ultimately advancing patient care in the medical domain. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review on Deep Learning Techniques on Cyber Attacks on Cyber Physical Systems

引用

SN computer science 2024年第7期5卷 1-16页

作者： Sagar, Maloth Vanmathi, C. School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore 632014 India

Cyber-Physical Systems (CPSs), which integrate control, computing, and communication, are considered as next-generation intelligent systems.A major concern in CPS is to ensure security. If security is not ensured, then it leads to both property damage and *** CPS is closely associated with real life, it is a hot research area in present security research. Nevertheless, cyber security issues are also raised. More efforts are still required for understanding CPS security from a more comprehensive perspective even though there are several studies on CPS *** identify and detect cyber security in CPS, numerous methods have been applied. The majority of recently published studies focused on Machine Learning (ML) techniques, with little attention paid to the development of Deep Learning (DL). Hence, the analysis of cyber security on CPS utilizing several algorithms of DL techniques is systematically *** appropriate cyber security risk levels and their corresponding detection and mitigation processesare determined. This study could augment the adaptability of the system of CPS data. Also, it could increase the generalization of the models of security attacks in CPS. Using DL algorithms is strongly recommended by most authors as a means to identify cyber security issues in *** CNN-centric LSTM, Deep Multi-architectural Approach, and DL-Meta classifier attained the highest accuracy in the detection rate of cyber security attacks in CPS when analogized with the other algorithms in DL techniques. Hence, for several critical systems in CPSs, the result renders clear guidelines to apply other regularization on DL techniques. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： CPS Cyber security Cyber-attack Cyber-attack detection Deep learning Risk analysis Security threats

来源：评论

学校读者我要写书评

暂无评论

Strategies for classifying water quality in the Cauvery River using a federated learning technique

引用

International Journal of Cognitive Computing in engineering 2023年第1期4卷 187-193页

作者： J, Vellingiri K, Kalaivanan P, Gopinath M C, Gobinath Subramaniam, Prabhakar Rontala Rangarajan, Sarathkumar School of Information Technology and Engineering Vellore Institute of Technology Vellore632014 India School of Computer Science and Engineering Vellore Institute of Technology Vellore632014 India Information System and Technology University of KwaZulu-Natal Durban South Africa Victorian Institute of Technology Melbourne Australia

Artificial intelligence methods are emerging techniques used in the field of environmental protection, especially in the analysis of air, water, and soil quality. AI analyzes vast amounts of environmental data to predict pollution and provide decision-makers with the information they need to develop efficient policies. One of the most important problems in environmental analysis is data security, and many organizations are actively working to ensure the secure collection, storage, and utilization of sensitive environmental data. In addition, organizations are focusing on developing strategies to protect their data from malicious attacks, such as cyber-attacks, as well as from accidental misuses, like unauthorized access. For this purpose, we have introduced a novel water quality prediction using the Federated Learning Technique. Federated learning enables multiple parties to collaborate and train a model on their local data without sharing it with others, thereby preserving data privacy. The proposed method is applied to a Cauvery River dataset of water quality parameters, and the results demonstrate that the PSO-optimized federated learning process achieves better prediction accuracy of 87%, a precision of 85%, a recall of 93%, and an 89% F1 score. © 2023

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A Self-Adapting and Efficient Dandelion Algorithm and Its Application to Feature Selection for Credit Card Fraud Detection

引用

IEEE/CAA Journal of Automatica Sinica 2024年第2期11卷 377-390页

作者： Honghao Zhu MengChu Zhou Yu Xie Aiiad Albeshri IEEE School of Computer and Information Engineering Bengbu UniversityBengbu 233030China School of Information and Electronic Engineering Zhejiang Gongshang UniversityHangzhou 310018China Helen and John C.Hartmann the Department of Electrical and Computer EngineeringNew Jersey Institute of TechnologyNewark NJ 07102 USA College of Information Engineering Shanghai Maritime UniversityShanghai 201306China Department of Computer Science King Abdulaziz UniversityJeddah 21481Saudi Arabia

A dandelion algorithm(DA) is a recently developed intelligent optimization algorithm for function optimization problems. Many of its parameters need to be set by experience in DA,which might not be appropriate for all optimization problems. A self-adapting and efficient dandelion algorithm is proposed in this work to lower the number of DA's parameters and simplify DA's structure. Only the normal sowing operator is retained;while the other operators are discarded. An adaptive seeding radius strategy is designed for the core dandelion. The results show that the proposed algorithm achieves better performance on the standard test functions with less time consumption than its competitive peers. In addition, the proposed algorithm is applied to feature selection for credit card fraud detection(CCFD), and the results indicate that it can obtain higher classification and detection performance than the-state-of-the-art methods.

关键词： Credit card fraud detection(CCFD) dandelion algorithm(DA) feature selection normal sowing operator

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：