检索结果-内蒙古大学图书馆

Cryptocurrency Transaction Network Embedding From Static and Dynamic Perspectives: An Overview

IEEE/CAA Journal of Automatica Sinica 2023年第5期10卷 1105-1121页

作者： Yue Zhou Xin Luo MengChu Zhou the School of Computer Science and Technology Chongqing University of Posts and TelecommunicationsChongqing 400065 the Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent TechnologyChinese Academy of SciencesChongqing 400714 the Chongqing School University of Chinese Academy of SciencesChongqing 400714China the College of Computer and Information Science Southwest UniversityChongqing 400715China the School of Information and Electronic Engineering Zhejiang Gongshang UniversityHangzhou 310018China the Helen and John C.Hartmann Department of Electrical and Computer Engineering New Jersey Institute of TechnologyNewark NJ 07102 USA

Cryptocurrency, as a typical application scene of blockchain, has attracted broad interests from both industrial and academic communities. With its rapid development, the cryptocurrency transaction network embedding(CTNE) has become a hot topic. It embeds transaction nodes into low-dimensional feature space while effectively maintaining a network structure,thereby discovering desired patterns demonstrating involved users' normal and abnormal behaviors. Based on a wide investigation into the state-of-the-art CTNE, this survey has made the following efforts: 1) categorizing recent progress of CTNE methods, 2) summarizing the publicly available cryptocurrency transaction network datasets, 3) evaluating several widely-adopted methods to show their performance in several typical evaluation protocols, and 4) discussing the future trends of CTNE. By doing so, it strives to provide a systematic and comprehensive overview of existing CTNE methods from static to dynamic perspectives,thereby promoting further research into this emerging and important field.

关键词： Big data analysis cryptocurrency transaction network embedding(CTNE) dynamic network network embedding network representation static network

来源：评论

学校读者我要写书评

暂无评论

Smart Home Automation with IoT Sensor Systems for Energy Conservation using Zigbee and Wifi 5

Smart Home Automation with IoT Sensor Systems for Energy Con...

引用

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Jagannathan, Srinivasan Deepa, V. Sakthi Karthi Durai, B. Rajan, M. Sundar Celin, J. Jeya A. Dhamodaran, Sasikala Madanapalle Institute of Technology & Science Department of Computer Applications Madanapalle India Tiruppur Kumaran College for Women Pg and Research Department of Computer Science Tamil Nadu Tiruppur India Kalasalingam Academy of Research and Education Computer Science and Engineering India Arbaminch Institute of Technology Arbaminch University Faculty of Electrical and Computer Engineering Ethiopia Kalasalingam Academy of Research and Education Department of Information Technology Viruthunagar Krishnankoil626126 India Rajasthan Jaipur India

ISBN: (纸本)9798350379945

This study presents a comprehensive study on smart home automation systems utilizing Internet of Things (IoT) sensor technology to achieve efficient energy conservation. The proposed system integrates ZigBee and WiFi communication protocols for effective and reliable connectivity across various smart devices within a home. Through the deployment of interconnected sensors and intelligent controllers, the system allows real-time monitoring and management of household energy usage, optimizing energy consumption and reducing waste. The combination of ZigBee for low-power, long-range sensor networks and WiFi for high-speed data transmission enables seamless interaction between smart appliances, lighting, heating, and cooling systems. Proposesd approach offers a scalable, cost-effective solution for enhancing home automation with an emphasis on energy conservation and sustainability. Also discussed the implementation, challenges, and future potential of IoT-based smart home systems for improved energy efficiency. © 2024 IEEE.

关键词： Smart homes

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human-computer Interaction with Hand Gesture Recognition 2

Enhancing Human-Computer Interaction with Hand Gesture Recog...

引用

2nd IEEE International Conference on Networks, Multimedia and Information technology, NMITCON 2024

作者： Pavithra, N. Sapna, R. Aswitha, A. Preethi Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Department of Computer Science and Engineering Manipal India Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Department of Information Technology Manipal India

ISBN: (纸本)9798350372892

A common means of nonverbal expression is realized through a hand gesture recognition system, offering a contemporary and natural mode of communication. This technology finds wide-ranging applications in sign language interpretation and human-computer interaction, bridging the physical and digital realms. Enhancing user-computer interactions by increasing the computer's receptivity to user demands is the fundamental aim of human-computer interaction. Human-computer interaction has grown in significance due to the widespread use of computers in society. It's commonly accepted that when computer, communication, and display technologies advance even more, the current state of HCI practices could eventually impede the efficient use of the information flow that is already accessible. This work aims to explain a new method of hand gesture identification that relies on the detection of certain shape-based elements. Features are extracted using the Histogram of Gradients feature descriptor, and SVMs trained on HOG features provide 87.4 % accurate results. In order to properly evaluate the efficacy of the recommended method, Metrics such as F-Score, Precision, and Recall provide a more nuanced view of the model's performance than merely accuracy. © 2024 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

A neuromorphic core based on threshold switching memristor with asynchronous address event representation circuits

引用

science China(Information sciences) 2022年第2期65卷 211-217页

作者： Jinsong WEI Jilin ZHANG Xumeng ZHANG Zuheng WU Rui WANG Jian LU Tuo SHI Mansun CHAN Qi LIU Hong CHEN School of Microelectronics University of Science and Technology of China Institute of Microelectronics of Chinese Academy of Sciences Zhejiang Lab Department of Microelectronics and Nanoelectronics Tsinghua University Department of Electronic & Computer Engineering The Hong Kong University of Science and Technology

The full memristive network hardware features high density and excellent scalability. However,recent researches on the full memristive network have been limited to a single-layer network, due to the lack of effective and flexible communication between neurons. In this design, we demonstrate a neuromorphic core based on Ag/Si O2/Au threshold switching memristor, which has built-in asynchronous address event representation(AER) circuits to provide flexible communication between neurons. Since temporally sparse spikes are the medium of communication between neurons, the AER circuits are designed to transmit spikes serially which have been encoded with neurons' addresses before transmission. With the asynchronous circuits design, the AER circuits will detect neurons' output in real-time. To test the performance of the neuromorphic core, we designed a behavioral simulator for the neuromporphic core to simulate the liquid state machine(LSM) network, which achieves a 100% recognition rate in the free spoken digital dataset. The simulation results show that the neuromorphic core obtains 35 times higher performance than the CPU and111 times higher energy efficiency than the GPU.

关键词： leaky-integration-and-fire (LIF) memristor threshold switching artificial neuron AER circuits asynchronous circuits on-chip communication

来源：评论

学校读者我要写书评

暂无评论

GS-PT: Exploiting 3D Gaussian Splatting for Comprehensive Point Cloud Understanding via Self-supervised Learning

GS-PT: Exploiting 3D Gaussian Splatting for Comprehensive Po...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Liu, Keyi Luo, Yeqi Yang, Weidong Xu, Jingyi Li, Zhijun Chen, Wen-Ming Fei, Ben School of Computer Science Fudan University China School of Mechanical Engineering Tongji University China Academy for Engineering and Technology Fudan University China

ISBN: (纸本)9798350368741

Self-supervised learning of point cloud aims to leverage unlabeled 3D data to learn meaningful representations without reliance on manual annotations. However, current approaches face challenges such as limited data diversity and inadequate augmentation for effective feature learning. To address these challenges, we propose GS-PT, which integrates 3D Gaussian Splatting (3DGS) into point cloud self-supervised learning for the first time. Our pipeline utilizes transformers as the backbone for self-supervised pre-training and introduces novel contrastive learning tasks through 3DGS. Specifically, the transformers aim to reconstruct the masked point cloud. 3DGS utilizes multi-view rendered images as input to generate enhanced point cloud distributions and novel view images, facilitating data augmentation and cross-modal contrastive learning. Additionally, we incorporate features from depth maps. By optimizing these tasks collectively, our method enriches the tri-modal self-supervised learning process, enabling the model to leverage the correlation across 3D point clouds and 2D images from various modalities. We freeze the encoder after pre-training and test the model's performance on multiple downstream tasks. Experimental results indicate that GS-PT outperforms the off-the-shelf self-supervised learning methods on various downstream tasks including 3D object classification, real-world classifications, and few-shot learning and segmentation. Project page: https://***/Luoyeqi1/***. © 2025 IEEE.

关键词： 3D Gaussian Splatting 3D understanding point clouds pre-training self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Fine classification of rice paddy using multitemporal compact polarimetric SAR C band data based on machine learning methods

引用

Frontiers of Earth science 2024年第1期18卷 30-43页

作者： Xianyu GUO Junjun YIN Kun LI Jian YANG Huimin ZOU Fukun YANG School of Computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China Aerospace Information Research Institute Chinese Academy of SciencesBeijing 100094China Department of Electronic Engineering Tsinghua UniversityBeijing 100084China College of Global Change and Earth System Science Beijing Normal UniversityBeijing 100875China

Rice is an important food crop for human *** distinguishing different varieties and sowing methods of rice on a large scale can provide more accurate information for rice growth monitoring,yield estimation,and phenological monitoring,which has significance for the development of modern *** polarimetric(CP)synthetic aperture radar(SAR)provides multichannel information and shows great potential for rice monitoring and ***,the use of machine learning methods to build classification models is a controversial *** this paper,the advantages of CP SAR data,the powerful learning ability of machine learning,and the important factors of the rice growth cycle were taken into account to achieve high-precision and fine classification of rice ***,CP SAR data were simulated by using the seven temporal RADARSAT-2 C-band data ***,20-two CP SAR parameters were extracted from each of the seven temporal CP SAR data *** addition,we fully considered the change degree of CP SAR parameters on a time scale(ΔCP_(DoY)).Six machine learning methods were employed to carry out the fine classification of rice *** results show that the classification methods of machine learning based on multitemporal CP SAR data can obtain better results in the fine classification of rice paddies by considering the parameters ofΔCP_(DoY).The overall accuracy is greater than 95.05%,and the Kappa coefficient is greater than *** them,the random forest(RF)and support vector machine(SVM)achieve the best results,with an overall accuracy reaching 97.32%and 97.37%,respectively,and Kappa coefficient values reaching 0.965 and 0.966,*** the two types of rice paddies,the average accuracy of the transplant hybrid(T-H)rice paddy is greater than 90.64%,and the highest accuracy is 95.95%.The average accuracy of direct-sown japonica(D-J)rice paddy is greater than 92.57%,and the highest accuracy is 96.13%.

关键词： compact polarimetric(CP)SAR rice paddy machine learning fine classification multitemporal

来源：评论

学校读者我要写书评

暂无评论

An Efficient and Secure Vehicular Networks Based on IoT and Cloud Computing

引用

SN computer science 2022年第3期3卷 1-8页

作者： El Zouka, Hesham A. Computer Engineering Department College of Engineering and Technology Arab Academy for Science Technology and Maritime Transport Alexandria Egypt

Undeniably, the increasing number of vehicles on the roads has automatically led to the unbelievable number of accidents occurring every day and the need for a safe communication system among the vehicles has become quite urgent. Using such systems, vehicles can communicate via wireless communication technologies and protocols like ZigBee, WiMax, Bluetooth, GSM, and RF. This paper introduces a communication system that works on preventing accidents by making all the surrounding vehicles communicate using RF, IoT, and LCD technologies to show all the warnings and the indications sent from other vehicles and a VLC that is connected to every vehicle to detect and send all needed information of occurring accidents on the road to all connected vehicles and to identify the hit or damaged ones. Moreover, the framework proposed in this paper attempts to perform mutual authentication procedures between vehicles and road-side units based on radio frequency identification devices and cloud computing. According to this framework, a low-cost device has been implemented using an LED lamp and an electrical circuit to control the LED luminous flux, and the modulated carrier signal has also been modified to effectively suppress the low-frequency noise. It should be noted that the experiments have shown that vehicular networks must be resilient and self-adapted to failures and potential threats to support coordinated transportation systems. Finally, the security analysis has also shown that the proposed framework is efficient, easily deployed and capable of finding the best routing paths between communicating vehicles. © 2022, The Author(s).

关键词： Anonymity Cloud computing Conditional privacy Identity-based cryptography Internet of things Mutual authentication Vehicular network security

来源：评论

学校读者我要写书评

暂无评论

On the Necessity of Collaboration for Online Model Selection with Decentralized Data 38

On the Necessity of Collaboration for Online Model Selection...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Li, Junfan Wu, Zheshun Xu, Zenglin King, Irwin School of Computer Science and Technology Harbin Institute of Technology Shenzhen China Pengcheng Lab China Institute Fudan University China Shanghai Academy of AI for Science China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong

We consider online model selection with decentralized data over M clients, and study the necessity of collaboration among clients. Previous work proposed various federated algorithms without demonstrating their necessity, while we answer the question from a novel perspective of computational constraints. We prove lower bounds on the regret, and propose a federated algorithm and analyze the upper bound. Our results show (i) collaboration is unnecessary in the absence of computational constraints on clients;(ii) collaboration is necessary if the computational cost on each client is limited to o(K), where K is the number of candidate hypothesis spaces. We clarify the unnecessary nature of collaboration in previous federated algorithms for distributed online multi-kernel learning, and improve the regret bounds at a smaller computational and communication cost. Our algorithm relies on three new techniques including an improved Bernstein's inequality for martingale, a federated online mirror descent framework, and decoupling model selection and prediction, which might be of independent interest. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advanced Knee Osteoarthritis Detection and Severity Prediction 15

Advanced Knee Osteoarthritis Detection and Severity Predicti...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Santosh, B. Rama Sai Reddy, N. Vinay Kumar Krishna, B. Jathin Vadlamudi, Venkata Naveen Jeyaraj, Jane Rubel Angelina Subhashini, S.J. Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Tamilnadu Virudhnagar India Department of IT SRM Madurai College for Engineering and Technology Tamil Nadu India

ISBN: (纸本)9798331300579

Millions of individuals worldwide suffer from knee osteoarthritis (OA), a crippling joint ailment that is marked by joint stiffness, discomfort, and functional impairment. To make a decision severity, physical symptoms, medical history, and further joint screening exams including radiography, MRIs, and CT scans are frequently considered. Unfortunately, the old methods are quite subjective, which makes it difficult to identify early illness development. Worldwide, Osteoarthritis affects close to 240 million individuals. Arthritis's most widespread kind, particularly in older people, is knee OA. Doctors utilize the Kellgren and Lawrence (KL) measure in order to assess the level of severity of knee OA. visually using X-ray or MR imaging. For the intent of detecting and predicting the severity of Knee Osteoarthritis, we are putting forth a model that uses novel Deep Learning models, such as Inception and Exception. By utilizing the KL Grading Scale, we propose ahead a model that can determine the degree of knee osteoarthritis in people. © Grenze Scientific Society, 2024.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

An Efficient Machine Learning-Based Power Management System for Smart Grids Using Renewable Energy Resources 2

An Efficient Machine Learning-Based Power Management System ...

引用

2nd IEEE International Conference on Networks, Multimedia and Information technology, NMITCON 2024

作者： Kavya, B.M. Mallikarjunaswamy, S. Sharmila, N. Shilpa, M. Komala, M. Shivaji, R. Balachandra, P. Sheela, S. Pavithra, G.S. Ks Institute of Technology Dept of Electronics and Communication Engineering Bengaluru India Jss Academy of Technical Eduction Dept of Electronics and Communication Engineering Bengaluru India Jss Science and Technology University Dept of Electronics and Electrical Engineering Mysuru India Bengaluru Institute of Technology Dept of Information Science and Engineering Bengaluru India Sjb Institute of Technology Dept of Electronics and Communication Engineering Bengaluru India Jagadambha college of Engineering & Technology Dept Electronics and Telecommunication Engineering India Sjb Institute of Technology Dept of Mathematics Bengaluru India Global Academy of Technology Dept of Computer Sceinec and Engineering Bengaluru India Jss Academy of Technical Eduction Dept of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350372892

In the dynamic landscape of energy systems, integrating renewable energy resources into smart grids presents substantial challenges, notably due to the inherent variability of wind and solar power. This study unveils an advanced power management system for smart grids that harnesses machine learning algorithms (ApmSGML) to optimize energy distribution and storage, ensuring stability, efficiency, and environmental sustainability. This approach is distinguished from conventional methods such as Fixed Threshold Control and Rule-Based Scheduling, which often struggle to adapt to the unpredictable nature of renewable energy sources. By leveraging predictive models, the proposed system anticipates energy production and consumption patterns, facilitating proactive adjustments to maintain supply and demand equilibrium. Additionally, A comparison of the ApmSGML's performance against traditional power management techniques like Deterministic Load Forecasting and Static Energy Storage Management, underscoring the adaptive and continuous learning advantages offered by machine learning through techniques like deep learning and reinforcement learning. Our findings highlight significant advancements in energy efficiency and cost reduction, demonstrating the transformative potential of integrating machine learning into the energy sector. © 2024 IEEE.

关键词： Internet of things (IoT) Machine learning power management Renewable energy smart grid

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：