检索结果-南通市图书馆

EG-STC: An Efficient Secure Two-Party Computation Scheme Based on Embedded GPU for Artificial Intelligence Systems

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

computers, Materials & Continua 2024年第6期79卷 4021-4044页

作者： Zhenjiang Dong Xin Ge Yuehua Huang Jiankuo Dong Jiang Xu school of computer science Nanjing University of Posts and TelecommunicationsNanjing210023China school of computer Nanjing University of Information Science and TechnologyNanjing210044China

This paper presents a comprehensive exploration into the integration of Internet of Things(IoT),big data analysis,cloud computing,and Artificial Intelligence(AI),which has led to an unprecedented era of *** delve into the emerging trend of machine learning on embedded devices,enabling tasks in resource-limited ***,the widespread adoption of machine learning raises significant privacy concerns,necessitating the development of privacy-preserving *** such technique,secure multi-party computation(MPC),allows collaborative computations without exposing private *** its potential,complex protocols and communication interactions hinder performance,especially on resource-constrained *** to enhance efficiency have been made,but scalability remains a *** the success of GPUs in deep learning,lever-aging embedded GPUs,such as those offered by NVIDIA,emerges as a promising ***,we propose an Embedded GPU-based Secure Two-party Computation(EG-STC)framework for Artificial Intelligence(AI)*** the best of our knowledge,this work represents the first endeavor to fully implement machine learning model training based on secure two-party computing on the Embedded GPU *** experimental results demonstrate the effectiveness of *** an embedded GPU with a power draw of 5 W,our implementation achieved a secure two-party matrix multiplication throughput of 5881.5 kilo-operations per millisecond(kops/ms),with an energy efficiency ratio of 1176.3 kops/ms/***,leveraging our EG-STC framework,we achieved an overall time acceleration ratio of 5–6 times compared to solutions running on server-grade *** solution also exhibited a reduced runtime,requiring only 60%to 70%of the runtime of previously best-known methods on the same *** summary,our research contributes to the advancement of secure and efficient machine learning implementations on resource-constrained embedded

关键词： Secure two-party computation embedded GPU acceleration privacy-preserving machine learning edge computing

The Squeeze & Excitation Normalization Based nnU-Net for Segmenting Head & Neck Tumors

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2024年第3期33卷 766-775页

作者： Juanying XIE Ying PENG Mingzhao WANG school of computer science Shaanxi Normal University

Head and neck cancer is one of the most common malignancies in the *** propose SE-nnU-Net by adapting SE(squeeze and excitation) normalization into nnU-Net,so as to segment head and neck tumors in PET/CT images by combining advantages of SE capturing features of interest regions and nnU-Net configuring itself for a specific *** basic module referred to convolution-ReLU-SE is designed for *** the encoder it is combined with residual structure while in the decoder without residual *** loss function combines Dice loss and Focal *** specific data preprocessing and augmentation techniques are developed,and specific network architecture is ***,the deep supervised mechanism is introduced to calculate the loss function using the last four layers of the decoder of *** SE-nnU-net is applied to HECKTOR 2020 and HECKTOR 2021 challenges,respectively,using different experimental *** experimental results show that SE-nnU-Net for HECKTOR 2020 obtained 0.745,0.821,and 0.725 in terms of Dice,Precision,and Recall,respectively,while the SE-nnU-Net for HECKTOR 2021 obtains 0.778 and 3.088 in terms of Dice and median HD95,*** SE-nnU-Net for segmenting head and neck tumors can provide auxiliary opinions for doctors diagnoses.

关键词： Image segmentation Head Data preprocessing Artificial neural networks Network architecture Data models Neck

Effect of strain on structure and electronic properties of monolayer C_(4)N_(4)

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Physics B 2024年第5期33卷 595-600页

作者：陈昊徐瑛赵家石周丹 school of Physics Changchun University of Science and TechnologyChangchun 130022China school of computer science and Technology Changchun University of Science and TechnologyChangchun 130022China

The first-principles calculations are performed to examine structural,mechanical,and electronic properties at large strain for a monolayer C_(4)N_(4),which has been predicted as an anchoring promising material to attenuate shuttle effect in Li–S batteries stemming from its large absorption energy and low diffusion energy *** results show that the ideal strengths of C_(4)N_(4)under tension and pure shear deformation conditions reach 13.9 GPa and 12.5 GPa when the strains are 0.07 and 0.28,*** folded five-membered rings and diverse bonding modes between carbon and nitrogen atoms enhance the ability to resist plastic deformation of C_(4)N_(4).The orderly bond-rearranging behaviors under the weak tensile loading path along the[100]direction cause the impressive semiconductor–metal transition and inverse semiconductor–metal *** present results enrich the knowledge of the structure and electronic properties of C_(4)N_(4)under deformations and shed light on exploring other two-dimensional materials under diverse loading conditions.

关键词： two-dimensional materials strain effect structural evolution electronic properties

维普期刊数据库

Enhanced Hybrid Equilibrium Strategy in Fog-Cloud Computing Networks with Optimal Task Scheduling

在线全文

学校读者我要写书评

暂无评论

computers, Materials & Continua 2024年第5期79卷 2647-2672页

作者： Muchang Rao Hang Qin school of computer science Yangtze UniversityJingzhou434000China

More devices in the Intelligent Internet of Things(AIoT)result in an increased number of tasks that require low latency and real-time responsiveness,leading to an increased demand for computational *** computing’s low-latency performance issues in AIoT scenarios have led researchers to explore fog computing as a complementary ***,the effective allocation of resources for task execution within fog environments,characterized by limitations and heterogeneity in computational resources,remains a formidable *** tackle this challenge,in this study,we integrate fog computing and cloud *** begin by establishing a fog-cloud environment framework,followed by the formulation of a mathematical model for task ***,we introduce an enhanced hybrid Equilibrium Optimizer(EHEO)tailored for AIoT task *** overarching objective is to decrease both the makespan and energy consumption of the fog-cloud system while accounting for task *** proposed EHEO method undergoes a thorough evaluation against multiple benchmark algorithms,encompassing metrics likemakespan,total energy consumption,success rate,and average waiting *** experimental results unequivocally demonstrate the superior performance of EHEO across all assessed ***,in the most favorable conditions,EHEO significantly diminishes both the makespan and energy consumption by approximately 50%and 35.5%,respectively,compared to the secondbest performing approach,which affirms its efficacy in advancing the efficiency of AIoT task scheduling within fog-cloud networks.

关键词： Artificial intelligence of things fog computing task scheduling equilibrium optimizer differential evaluation algorithm local search

Dynamical behaviors in discrete memristor-coupled small-world neuronal networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Physics B 2024年第4期33卷 729-734页

作者：鲁婕妤谢小华卢亚平吴亚联李春来马铭磷 school of Automation and Electronic Information Xiangtan UniversityXiangtan 411105China school of computer science school of Cyberspace science Xiangtan UniversityXiangtan 411105China

The brain is a complex network system in which a large number of neurons are widely connected to each other and transmit signals to each *** memory characteristic of memristors makes them suitable for simulating neuronal synapses with *** this paper,a memristor is used to simulate a synapse,a discrete small-world neuronal network is constructed based on Rulkov neurons and its dynamical behavior is *** explore the influence of system parameters on the dynamical behaviors of the discrete small-world network,and the system shows a variety of firing patterns such as spiking firing and triangular burst firing when the neuronal parameterαis *** results of a numerical simulation based on Matlab show that the network topology can affect the synchronous firing behavior of the neuronal network,and the higher the reconnection probability and number of the nearest neurons,the more significant the synchronization state of the *** addition,by increasing the coupling strength of memristor synapses,synchronization performance is *** results of this paper can boost research into complex neuronal networks coupled with memristor synapses and further promote the development of neuroscience.

关键词： small-world networks Rulkov neurons memristor synchronization

维普期刊数据库

Floating Waste Discovery by Request via Object-Centric Learning

在线全文

学校读者我要写书评

暂无评论

computers, Materials & Continua 2024年第7期80卷 1407-1424页

作者： Bingfei Fu school of computer science Fudan UniversityShanghai200438China

Discovering floating wastes,especially bottles on water,is a crucial research problem in environmental ***,real-world applications often face challenges such as interference from irrelevant objects and the high cost associated with data ***,devising algorithms capable of accurately localizing specific objects within a scene in scenarios where annotated data is limited remains a formidable *** solve this problem,this paper proposes an object discovery by request problem setting and a corresponding algorithmic *** proposed problem setting aims to identify specified objects in scenes,and the associated algorithmic framework comprises pseudo data generation and object discovery by request ***-data generation generates images resembling natural scenes through various data augmentation rules,using a small number of object samples and scene *** network structure of object discovery by request utilizes the pre-trained Vision Transformer(ViT)model as the backbone,employs object-centric methods to learn the latent representations of foreground objects,and applies patch-level reconstruction constraints to the *** the validation phase,we use the generated pseudo datasets as training sets and evaluate the performance of our model on the original test *** have proved that our method achieves state-of-the-art performance on Unmanned Aerial Vehicles-Bottle Detection(UAV-BD)dataset and self-constructed dataset Bottle,especially in multi-object scenarios.

关键词： Unsupervised object discovery object-centric learning pseudo data generation real-world object discovery by request

Task-specific Part Discovery for Fine-grained Few-shot Classification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Machine Intelligence Research 2024年第5期21卷 954-965页

作者： Yongxian Wei Xiu-Shen Wei school of computer science and Technology Nanjing University of Science and TechnologyNanjing210094China

Localizing discriminative object parts(e.g.,bird head)is crucial for fine-grained classification tasks,especially for the more challenging fine-grained few-shot *** work always relies on the learned object parts in a unified manner,where they attend the same object parts(even with common attention weights)for different few-shot episodic *** this paper,we propose that it should adaptively capture the task-specific object parts that require attention for each few-shot task,since the parts that can distinguish different tasks are naturally *** for a few-shot task,after obtaining part-level deep features,we learn a task-specific part-based dictionary for both aligning and reweighting part features in an ***,part-level categorical prototypes are generated based on the part features of support data,which are later employed by calculating distances to classify query data for *** retain the discriminative ability of the part-level representations(i.e.,part features and part prototypes),we design an optimal transport solution that also utilizes query data in a transductive way to optimize the aforementioned distance calculation for the final *** experiments on five fine-grained benchmarks show the superiority of our method,especially for the 1-shot setting,gaining 0.12%,8.56%and 5.87%improvements over state-of-the-art methods on CUB,Stanford Dogs,and Stanford Cars,respectively.

关键词： Fine-grained image recognition few-shot learning transductive learning visual dictionary part feature discovery

Multi-scale persistent spatiotemporal transformer for long-term urban traffic flow prediction

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Electronic science and Technology 2024年第1期22卷 53-69页

作者： Jia-Jun Zhong Yong Ma Xin-Zheng Niu Philippe Fournier-Viger Bing Wang Zu-kuan Wei school of computer science and Engineering University of Electronic Science and Technology of ChinaChengdu611731China College of computer science&Software Engineering Shenzhen UniversityShenzhen518060China school of computer science Southwest Petroleum UniversityChengdu610500China

Long-term urban traffic flow prediction is an important task in the field of intelligent transportation,as it can help optimize traffic management and improve travel *** improve prediction accuracy,a crucial issue is how to model spatiotemporal dependency in urban traffic *** recent years,many studies have adopted spatiotemporal neural networks to extract key information from traffic ***,most models ignore the semantic spatial similarity between long-distance areas when mining spatial *** also ignore the impact of predicted time steps on the next unpredicted time step for making long-term ***,these models lack a comprehensive data embedding process to represent complex spatiotemporal *** paper proposes a multi-scale persistent spatiotemporal transformer(MSPSTT)model to perform accurate long-term traffic flow prediction in *** adopts an encoder-decoder structure and incorporates temporal,periodic,and spatial features to fully embed urban traffic data to address these *** model consists of a spatiotemporal encoder and a spatiotemporal decoder,which rely on temporal,geospatial,and semantic space multi-head attention modules to dynamically extract temporal,geospatial,and semantic *** spatiotemporal decoder combines the context information provided by the encoder,integrates the predicted time step information,and is iteratively updated to learn the correlation between different time steps in the broader time range to improve the model’s accuracy for long-term *** on four public transportation datasets demonstrate that MSPSTT outperforms the existing models by up to 9.5%on three common metrics.

关键词： Graph neural network Multi-head attention mechanism Spatio-temporal dependency Traffic flow prediction

Rethinking attribute localization for zero-shot learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

science China(Information sciences) 2024年第7期67卷 184-196页

作者： Shuhuang CHEN Shiming CHEN Guo-Sen XIE Xiangbo SHU Xinge YOU Xuelong LI school of Electronic Information and Communication Huazhong University of Science and Technology school of computer science and Engineering Nanjing University of Science and Technology school of Artificial Intelligence Optics and Electronics Northwestern Polytechnical University

Recent advancements in attribute localization have showcased its potential in discovering the intrinsic semantic knowledge for visual feature representations, thereby facilitating significant visual-semantic interactions essential for zero-shot learning(ZSL). However, the majority of existing attribute localization methods heavily rely on classification constraints, resulting in accurate localization of only a few attributes while neglecting the rest important attributes associated with other classes. This limitation hinders the discovery of the intrinsic semantic relationships between attributes and visual features across all *** address this problem, we propose a novel attribute localization refinement(ALR) module designed to enhance the model's ability to accurately localize all attributes. Essentially, we enhance weak discriminant attributes by grouping them and introduce weighted attribute regression to standardize the mapping values of semantic attributes. This module can be flexibly combined with existing attribute localization *** experiments show that when combined with the ALR module, the localization errors in existing methods are corrected, and state-of-the-art classification performance is achieved.

关键词： zero-shot learning attention mechanism attribute localization image classification