检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Gu, Shi Mattar, Marcelo G. Tang, Huajin Pan, Gang School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Shenzhen China Psychology Department New York University United States College of Computer Science and Technology Zhejiang University Hangzhou China State Key Laboratory of Brain Machine Intelligence Zhejiang University Hangzhou China

While advances in artificial intelligence and neuroscience have enabled the emergence of neural networks capable of learning a wide variety of tasks, our understanding of the temporal dynamics of these networks remains limited. Here, we study the temporal dynamics during learning of Hebbian Feedforward (HebbFF) neural networks in tasks of continual familiarity detection. Drawing inspiration from the field of network neuroscience, we examine the network's dynamic reconfiguration, focusing on how network modules evolve throughout learning. Through a comprehensive assessment involving metrics like network accuracy, modular flexibility, and distribution entropy across diverse learning modes, our approach reveals various previously unknown patterns of network reconfiguration. In particular, we find that the emergence of network modularity is a salient predictor of performance, and that modularization strengthens with increasing flexibility throughout learning. These insights not only elucidate the nuanced interplay of network modularity, accuracy, and learning dynamics but also bridge our understanding of learning in artificial and biological realms. © 2023, CC BY.

关键词： Feedforward neural networks

来源：评论

学校读者我要写书评

暂无评论

Security Technique To Prevent Port Knocking And Illegal Access in SDN

Security Technique To Prevent Port Knocking And Illegal Acce...

引用

Electrical engineering and Sustainable Technologies (ICEEST), International Conference on

作者： Uzair Zia Muhammad Asfand Yar Tahir Naeem Monis Amin Muhammad Zeeshan Muhammad Wajeeh Us Sima Institute of Business & Management University of Engineering & Technology Lahore Pakistan Al-Khawarizmi Instituite of Computer Science University of Engineering and Technology Lahore Pakistan Faculty Of Natural Sciences Computing Science And Mathematics University Of Stirling Scotland Uk School Of Computer Science And Technology Chongqing University Chongqing China

The progress of networking technology has led to a new paradigm of network control based on data plane programmability. This allows for flexible packet processing and improved network management, which increases network security. Literature lacks network security methods for authentication and blocking illegal access. In this study, we aim to prevent assaults in a two-level defense. The first level is a dynamic firewall mechanism that stops packets from untrusted sources. The second level is dynamic port banging. Both security levels were evaluated in a simulated P4 environment. The controller receives packets from unknown hosts. The controller uses ACL rules to allow or reject packets. Each new host generates a random sequence for port knocking. Hosts may only connect in the order given. This solution works better than earlier P4-based firewall systems owing to two security layers. Moreover, it blocks unwanted network access to mitigate certain security threats.

关键词： Electrical engineering Firewalls (computing) Authentication Network security Random sequences

来源：评论

学校读者我要写书评

暂无评论

FedCache: A Knowledge Cache-driven Federated Learning Architecture for Personalized Edge Intelligence

arXiv

引用

arXiv 2023年

作者： Wu, Zhiyuan Sun, Sheng Wang, Yuwei Liu, Min Xu, Ke Wang, Wen Jiang, Xuefeng Gao, Bo Lu, Jinda The Institute of Computing Technology Chinese Academy of Sciences Beijing China The University of Chinese Academy of Sciences Beijing China The Zhongguancun Laboratory Beijing China The Department of Computer Science and Technology Tsinghua University Beijing China The School of Computer and Information Technology The Engineering Research Center of Network Management Technology for High-Speed Railway Ministry of Education Beijing Jiaotong University Beijing China The School of Information Science and Technology University of Science and Technology of China Hefei China

Edge Intelligence (EI) allows Artificial Intelligence (AI) applications to run at the edge, where data analysis and decision-making can be performed in real-time and close to data sources. To protect data privacy and unify data silos distributed among end devices in EI, Federated Learning (FL) is proposed for collaborative training of shared AI models across multiple devices without compromising data privacy. However, the prevailing FL approaches cannot guarantee model generalization and adaptation on heterogeneous clients. Recently, Personalized Federated Learning (PFL) has drawn growing awareness in EI, as it enables a productive balance between local-specific training requirements inherent in devices and global-generalized optimization objectives for satisfactory performance. However, most existing PFL methods are based on the Parameters Interaction-based Architecture (PIA) represented by FedAvg, which suffers from unaffordable communication burdens due to large-scale parameters transmission between devices and the edge server. In contrast, Logits Interaction-based Architecture (LIA) allows to update model parameters with logits transfer and gains the advantages of communication lightweight and heterogeneous on-device model allowance compared to PIA. Nevertheless, previous LIA methods attempt to achieve satisfactory performance either relying on unrealistic public datasets or increasing communication overhead for additional information transmission other than logits. To tackle this dilemma, we propose a knowledge cache-driven PFL architecture, named FedCache, which reserves a knowledge cache on the server for fetching personalized knowledge from the samples with similar hashes to each given on-device sample. During the training phase, ensemble distillation is applied to on-device models for constructive optimization with personalized knowledge transferred from the server-side knowledge cache. Empirical experiments on four datasets demonstrate that FedCache achiev

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Hv-Yolov8 by Hdpconv: Better Lightweight Detectors for Small Object Detection

SSRN

引用

SSRN 2023年

作者： Wang, Wei Meng, Yuanze Li, Shun Zhang, Chenghong Shenyang Institute of Computing Technology Chinese Academy of Sciences Donghu Street Shenyang110168 China University of Chinese Academy of Sciences Beijing100049 China School of Computer Science and Engineering Northeastern University Shenyang110169 China

Small object detection is an important challenge in the field of computer vision, whose task is to accurately detect and localise tiny target objects in images or videos. It is mostly applied in scenarios that require high real-time performance, such as pedestrian detection and autonomous driving scenarios. These tiny targets generally include tiny objects, targets at long distances, or objects appearing in low-resolution images, due to which it becomes extremely difficult to extract effective feature information. To address this challenge, we propose a new convolutional method, HDPConv, which can effectively improve the small target detection accuracy as well as reduce the computational effort. A cross-level partial network (VOV-GSCSP) is also utilised to enhance the small target detection performance, reduce the false detection rate, and improve the adaptability to diverse small targets through multi-level feature extraction and information fusion. On this basis we propose a new network lightweighting model HV-YOLOv8. Relative to YOLOv8, the HV-YOLOv8 method is validated and tested on the Swimming Pool And Car dataset, and the results show that the model size is compressed by 15%, and the number of parameters and computation are also reduced dramatically by 7% and 10%, respectively, whereas in the accuracy assessment metrics mAP0.5:0.9 is also improved by 1.4%. © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Reconfiguration System-Friendly Vertical Handover Scheme

An End-to-End Reconfiguration System-Friendly Vertical Hando...

引用

Communications and Information Technologies (GCCIT), Global Conference on

作者： Dharmesh Dhabliya Manoj Chandra Lohani S. Hemelatha Shudhanshu Marwaha S. Yuvaraj Malathi. H Department of Information Technology Vishwakarma Institute of Technology Pune India School of Computing Graphic Era Hill University Haldwani Graphic Era Deemed to be University Dehradun Uttarakhand India Department of Computer Science Engineering Karpagam Academy of Higher Education Coimbatore Chitkara University Institute of Engineering and Technology Chitkara University Rajpura Punjab India Department of Electronics and Communication Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai School of Sciences Biotechnology and Genetics JAIN (Deemed to be University) Bangalore Karnataka

ISBN: (数字)9798350388916

ISBN: (纸本)9798350388923

Relaying information without accurately understanding the resource and service needs of the newly relocated node is a major obstacle to providing a smooth communication system during vertical handover in heterogeneous networks. There may be a lack of study on the topic of smooth vertical handover, according to the literature review. This research proposes a new technique for vertical handover in heterogeneous integrated networks that uses multi-attribute and neural networks. By navigating among UMTS, GPRS, WLAN, 4G, and 5G, we build the algorithm's framework according to the network environment. In order to set the input layer neurons of the BP neural network and train and learn from subsequent data, each network constructs a unique Q-Learning (Reinforcement Learning) model. Reference objects used in this process include the highest possible transmission rate, the minimum delay, SINR (signal to noise and interference ratio), bit error rate, user moving velocity, and packet loss rate, all of which can impact the wireless network's overall performance. In the end, the five wireless connections are evaluated based on the network download rate, which is used as a forecast goal. Then, the algorithm for vertical handover will choose the correct wireless network to make the choice. This research presents a vertical handover method that, according to MATLAB simulation results, enables efficient handover with seamless connection across multi-heterogeneous networks with a handover success rate of up to 90%.

关键词： Wireless LAN Q-learning Simulation Wireless networks Packet loss Interference Handover Biological neural networks Systematic literature review Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Positional Encoding-Guided Transformer-Based Multiple Instance Learning for Histopathology Whole Slide Images Classification

SSRN

引用

SSRN 2024年

作者： Shi, Jun Sun, Dongdong Wu, Kun Jiang, Zhiguo Kong, Xue Wang, Wei Wu, Haibo Zheng, Yushan School of Software Hefei University of Technology Anhui Province Hefei230601 China School of Computer Science and Information Engineering Hefei University of Technology Anhui Province Hefei230601 China Beijing102206 China Department of Pathology the First Affiliated Hospital of USTC Division of Life Sciences and Medicine University of Science and Technology of China Anhui Province Hefei230036 China Intelligent Pathology Institute Division of Life Sciences and Medicine University of Science and Technology of China Anhui Province Hefei230036 China School of Engineering Medicine Beijing Advanced Innovation Center for Biomedical Engineering Beihang University Beijing100191 China Beijing Advanced Innovation Center for Biomedical Engineering China

Whole slide image (WSI) classification is of great clinical significance in computer-aided pathological diagnosis. Due to the high cost of manual annotation, weakly supervised WSI classification methods have gained more attention. As the most representative, multiple instance learning (MIL) generally aggregates the predictions or features of the patches within a WSI to achieve the slidelevel classification under the weak supervision of WSI labels. However, most existing MIL methods ignore spatial position relationships of the patches which is likely to strengthen the discriminative ability of WSI-level features. In this paper, we propose a novel position encoding-guided transformerbased multiple instance learning (PEGTB-MIL) method for histopathology WSI classification. It aims to encode the spatial positional property of the patch into its corresponding semantic features and explore the potential correlation among the patches for improving the WSI classification performance. Concretely, the deep features of the patches in WSI are first extracted and simultaneously a position encoder is used to encode the spatial 2D positional information of the patches into the spatialaware features. After incorporating the semantic features and spatial embeddings, multi-head selfattention (MHSA) is applied to explore the contextual and spatial dependencies of the fused features. Particularly, we introduce an auxiliary reconstruction task to enhance the spatial-semantic consistency and generalization ability of features. The proposed method is evaluated on one public TCGA dataset and two in-house datasets. Experimental results validate it is effective in the tasks of lung cancer subtyping and gene mutation status prediction for lung cancer and gastrointestinal stromal tumor (GIST), and superior to the state-of-the-art MIL-based methods. © 2024, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Trajectory Optimization and Beamforming Design for NOMA-enabled Multi-Objective RIS-aided IS-UAV-TNs with Deep Reinforcement Learning

Trajectory Optimization and Beamforming Design for NOMA-enab...

引用

International Conference on Communication technology (ICCT)

作者： Min Wu Kefeng Guo Haotong Cao Zhi Lin Kang An Jiangzhou Wang School of Space Information Space Engineering University Beijing China Department of Computing Hong Kong Polytechnic University Hong Kong SAR China College of Electronic Engineering National University of Defense Technology Hefei China School of Computer Science and Engineering Macau University of Science and Technology Macau China Sixty-third Research Institute National University of Defense Technology Nanjing China School of Engineering University of Kent Canterbury U.K.

This paper investigates the collaborative optimization performance route on the reconfigurable intelligent surface (RIS)-aided integrated satellite unmanned aerial vehicle-terrestrial network (IS-UAV-TN). It mainly has two primary challenges: long transmission paths with severe signal fading and the presence of obstacles along the wireless environment. To efficiently address above issues, it is assumed that RIS is deployed on the UAV to enable precise control over signal transmission, and non-orthogonal multiple access (NOMA) transmission strategies are employed at the transmitter. Based on the different transmission phases, a multi-vector optimization problem is proposed with the aim of maximizing the system achievable rate by optimizing the UAV path design, transmit beam and RIS passive phase shift. Especially the deep reinforcement learning (DRL)-based multi-vector deep deterministic policy gradient (MV-DDPG) algorithm, is utilized to achieve adaptive decision-making in non-deterministic wireless environments. Experimental results show that the proposed method has the ability to efficiently consider multiple optimization objectives designed compared to traditional comparison schemes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GCRE-GPT: A Generative Model for Comparative Relation Extraction

arXiv

引用

arXiv 2023年

作者： Wang, Yequan Zhang, Hengran Sun, Aixin Meng, Xuying Beijing Academy of Artificial Intelligence Beijing China Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China School of Computer Science and Engineering Nanyang Technological University Singapore

Given comparative text, comparative relation extraction aims to extract two targets (e.g., two cameras) in comparison and the aspect they are compared for (e.g., image quality). The extracted comparative relations form the basis of further opinion analysis. Existing solutions formulate this task as a sequence labeling task, to extract targets and aspects. However, they cannot directly extract comparative relation(s) from text. In this paper, we show that comparative relations can be directly extracted with high accuracy, by generative model. Based on GPT-2, we propose a Generation-based Comparative Relation Extractor (GCRE-GPT). Experiment results show that GCRE-GPT achieves state-of-the-art accuracy on two datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Scalable Electrophysiology of Millimeter-Scale Animals with Electrode Devices

引用

Biomedical engineering Frontiers 2023年第1期4卷 3-20页

作者： Kairu Dong Wen-Che Liu Yuyan Su Yidan Lyu Hao Huang Nenggan Zheng John A.Rogers Kewang Nan College of Pharmaceutical Sciences Zhejiang UniversityHangzhou 310058China National Key Laboratory of Advanced Drug Delivery and Release Systems Zhejiang UniversityHangzhou 310058China College of Biomedical Engineering&Instrument Science Zhejiang UniversityHangzhou310027China Department of Gastroenterology Brigham and Women’s HospitalHarvard Medical SchoolBostonMA 02115USA College of Chemical and Biological Engineering Zhejiang UniversityHangzhou 310058China Qiushi Academy for Advanced Studies Zhejiang UniversityHangzhou 310027China College of Computer Science and Technology Zhejiang UniversityHangzhou 310027China State Key Lab of Brain-Machine Intelligence Zhejiang UniversityHangzhou 310058China CCAI by MOE and Zhejiang Provincial Government(ZJU) Hangzhou 310027China Querrey Simpson Institute for Bioelectronics Northwestern UniversityEvanstonIL 60208USA Department of Biomedical Engineering Northwestern UniversityEvanstonIL 60208USA Department of Materials Science and Engineering Northwestern UniversityEvanstonIL 60208USA Department of Mechanical Engineering Northwestern UniversityEvanstonIL 60208USA Jinhua Institute of Zhejiang University Jinhua 321299China

Millimeter-scale animals such as Caenorhabditis elegans,Drosophila larvae,zebrafish,and bees serve as powerful model organisms in the fields of neurobiology and *** methods exist for recording large-scale electrophysiological signals from these *** approaches often lack,however,real-time,uninterrupted investigations due to their rigid constructs,geometric constraints,and mechanical mismatch in integration with soft *** recent research establishes the foundations for 3-dimensional flexible bioelectronic interfaces that incorporate microfabricated components and nanoelectronic function with adjustable mechanical properties and multidimensional variability,offering unique capabilities for chronic,stable interrogation and stimulation of millimeter-scale animals and miniature tissue *** review summarizes the most advanced technologies for electrophysiological studies,based on methods of 3-dimensional flexible bioelectronics.A concluding section addresses the challenges of these devices in achieving freestanding,robust,and multifunctional biointerfaces.

关键词： offering recording millimeter

来源：评论

学校读者我要写书评

暂无评论

Sentiment analysis of healthcare Tweets using SVM Classifier 2

Sentiment analysis of healthcare Tweets using SVM Classifier

引用

2nd IEEE International Conference on Power, Energy, Control and Transmission Systems, ICPECTS 2020

作者： Saranya, G. Geetha, G. Chakrapani, K. Meenakshi, K. Karpagaselvi, S. School of Computing Srm Institute of Science Technology Chennai603203 India School of Computing Sastra Deemed University India School of Electrical and Computer Engineering Ethiopian Institute of Technology Mekelle Ethiopia

ISBN: (纸本)9781728110844

Web-based social media offers countless opportunities to have their valuable suggestions for experiences. Twitter can be used effectively in current circumstances and with open modern developments to collect data as opposed to social relationship data in traditional techniques. Twitter is perhaps the most loyal member's online large frequency advantage that encourages individuals to communicate and collect data. Here we discuss which country/place frequently speaks about specific diseases. We can forecast where the disease's impact will be important. This system handles the problems that occur during the Sentiment Analysis cycle spent;ongoing tweeting are known to be rich sources of data for evaluation extraction and feeling study. The basic aim of this system is to carry out a continuous sentimental review of the tweets removed by twitter. © 2020 IEEE.

关键词： Sentiment analysis

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：