检索结果-内蒙古大学图书馆

Skeleton-Aware Graph-Based Adversarial Networks for Human Pose Estimation from Sparse IMUs

ACM Transactions on Multimedia Computing, Communications and Applications 2025年第4期21卷 1-22页

作者： Chen, Kaixin Zhang, Lin Wang, Zhong Zhao, Shengjie Zhou, Yicong School of Software Engineering Tongji University Shanghai China Department of Computer and Information Science University of Macau Macau China

Recently, sparse-inertial human pose estimation (SI-HPE) with only a few IMUs has shown great potential in various fields. The most advanced work in this area achieved fairish results using only six IMUs. However, there are still two major issues that remain to be addressed. First, existing methods typically treat SI-HPE as a temporal sequential learning problem and often ignore the important spatial prior of skeletal topology. Second, there are far more synthetic data in their training data than real data, and the data distribution of synthetic data and real data is quite different, which makes it difficult for the model to be applied to more diverse real data. To address these issues, we propose "Graph-based Adversarial Inertial Poser (GAIP),"which tracks body movements using sparse data from six IMUs. To make full use of the spatial prior, we design a multi-stage pose regressor with graph convolution to explicitly learn the skeletal topology. A joint position loss is also introduced to implicitly mine spatial information. To enhance the generalization ability, we propose supervising the pose regression with an adversarial loss from a discriminator, bringing the ability of adversarial networks to learn implicit constraints into full play. Additionally, we construct a real dataset that includes hip support movements and a synthetic dataset containing various motion categories to enrich the diversity of inertial data for SI-HPE. Extensive experiments demonstrate that GAIP produces results with more precise limb movement amplitudes and relative joint positions, accompanied by smaller joint angle and position errors compared to state-of-the-art counterparts. The datasets and codes are publicly available at https://***/GAIP/. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Network theory (graphs)

来源：评论

学校读者我要写书评

暂无评论

Enhanced Knowledge Extraction using Cutting-Edge Rough and Soft Graph Techniques 5

Enhanced Knowledge Extraction using Cutting-Edge Rough and S...

引用

5th International Conference on Emerging Systems and Intelligent Computing, ESIC 2025

作者： Bhagat, Surendra Nath Sekhar Rath, Premansu Mitra, Anirban Giet University Department of Computer Science and Engineering Gunupur India Amity University Department of Computer Science and Engineering Kolkata India

ISBN: (纸本)9798331522100

Addressing uncertainties in data is crucial for real-world applications, including social networks, where relationships often lack clear definition. Soft and rough graph theories allow for nuanced modeling of such data by extending traditional graph structures with parameters that account for uncertainty. Social networks exhibit complex, often ambiguous relationships that traditional graphs cannot fully represent, especially in dynamic, imprecise settings. This study aims to explore soft and rough graphs as effective tools for extracting knowledge from social networks by modeling vague or partially known relationships. Our rough graph analysis identified strong, definite communication channel between employees sharing dual expertise and different weaker channels based on single expertise, suggesting potential collaboration points. In soft graph analysis, two subgroups were detected around shared interests in Sports and Music, identifying central and bridging users within the network. Soft and rough graphs enhance knowledge extraction from social networks, enabling insights into communities, influencers, and communication channels that reflect the uncertain and dynamic nature of social interactions, which can also be used in data science to evaluate ambiguous or incomplete datasets, find hidden patterns, and enhance decision-making in fields like network optimization, fraud detection, and recommendation systems. This approach is shown to be beneficial in structuring and understanding intricate social data patterns. © 2025 IEEE.

关键词： Network theory (graphs)

来源：评论

学校读者我要写书评

暂无评论

UniManage - An All-in-One Platform for Empowering Businesses 2

UniManage - An All-in-One Platform for Empowering Businesses

引用

2nd International Conference on Computational Intelligence, Communication Technology and Networking, CICTN 2025

作者： Pandey, Geetansh Saxena, Kushagra Tyagi, Simran Singh, Arya Prabha, Sneh Department of Computer Science Inderprastha Engineering College Ghaziabad India

ISBN: (纸本)9798331530389

UniManage is basically all packaged into one, fully-fledged SaaS solution that has been designed to bring together major business functions into one excellent system that optimizes organizational processes. Its modules are flexible and span meetings, collaboration, accounting, finance, and supply chain management. With this, it can attend to many business needs. By being modular, UniManage will allow organizations to create solutions that fit the requirements of their operations and workflows specifically. This has been a major advantage for UniManage. Software laundry will significantly decline, workflows will be optimized and increased overall productivity across organizations will be achieved. Flexibility, robust features, and user-centric design make UniManage certainly an essential tool for businesses intent on streamlining operations. It increases efficiency while also allowing teams to work better, so they stay in sync and can meet their goals. This is how well UniManage is positioned as a solution that is flexible or scalable according to the demands of today's business scenarios: a reliable foundation for growth and innovation. © 2025 IEEE.

关键词： Cost reduction

来源：评论

学校读者我要写书评

暂无评论

Chernobyl-Inspired Optimization for Efficient Wireless Sensor Network Routing 5

Chernobyl-Inspired Optimization for Efficient Wireless Senso...

引用

5th International Conference on Emerging Systems and Intelligent Computing, ESIC 2025

作者： Garima Rani, Amita Kumar, Sanjay Dcrust Computer Science and Engineering Department Murthal Sonepat India Sgt University Computer Science and Engineering Department Gurugram India

ISBN: (纸本)9798331522100

Optimising routing in Wireless Sensor Networks (WSNs) is crucial for enhancing their performance, with a focus on energy conservation, reliable data transmission, and network stability. This research presents a unique approach to WSN routing optimization using Chernobyl Disaster Optimization (CDO), a nature-inspired algorithm modeled on the rehabilitation and ecological restoration efforts following the Chernobyl incident. CDO simulates the process of resource redistribution and recovery after a catastrophic event to identify optimal routing paths in WSNs. The study assesses the CDO algorithm's effectiveness against the traditional Gravitational Search Algorithm (GSA) using key performance indicators such as energy usage, jitter, average end-to-end delay (EED), packet loss, and packet delivery fraction (PFD). Simulation results show that the CDO-based routing optimisation method consistently surpasses GSA, delivering improved end-to-end delay, decreased jitter, reduced packet loss, and enhanced energy efficiency. This investigation highlights CDO's potential as a viable alternative to conventional optimisation techniques, offering a more efficient and adaptable solution for WSN routing optimisation, particularly in dynamic, large-scale scenarios. © 2025 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

A Mini Review on Purchaser Security in the Metaverse: Challenges and Solutions

A Mini Review on Purchaser Security in the Metaverse: Cha...

引用

PhD Symposium, Posters, Demos, and A Web for more inclusive, sustainable and prosperous societies, WEB-for-GOOD 2024 and 1st International Workshop on AI and Web Data Analytics, AIWDA 2024 form the 25th International Conference on Web Information Systems engineering, WISE 2024

作者： Aloudat, Mohammad Barhamgi, Mahmoud Yaacoub, Elias Department of Computer Science and Engineering Qatar University Doha Qatar

ISBN: (纸本)9789819614820

This mini review examines the security challenges faced by purchasers in the metaverse, focusing on issues such as data protection, privacy, identity theft, financial fraud, and software vulnerabilities. The metaverse, characterized by its immersive, decentralized, and interactive nature, presents unique risks due to extensive data collection, real-time user tracking, and the integration of digital and physical worlds. This mini review highlights specific threats such as unauthorized access, exploitation of biometric data, and fraudulent activities involving blockchain-based assets like non-fungible tokens (NFTs). Mitigation strategies, including advanced encryption, multi-factor authentication, decentralized identity solutions, and regulatory frameworks, are discussed as essential to safeguarding purchasers. The paper concludes by identifying gaps in current research and proposing directions for future studies, emphasizing the need for interdisciplinary approaches to enhance metaverse security. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

An optimised AI-driven swarm-based enhanced task scheduling model for cloud computing environment

引用

International Journal of Cloud Computing 2025年第1期14卷 25-53页

作者： Kaur, Surinder Singh, Jaspreet Bharti, Vishal Department of Computer Science and Engineering Chandigarh University Gharuan Punjab Mohali140413 India Mullana Haryana Ambala India

Task scheduling in cloud computing environment becomes difficult when complexity level of dispute, including task count and computing resources, rises with user growth. Solving this, an enhanced task scheduling (ETS) model with optimised artificial intelligence driven by swarm is proposed in paper. In proposed method, supervised machine learning algorithm, artificial neural networks (ANN) with swarm-based moth flame optimisation (MFO) is used to balance scheduling. MFO optimises by separating out virtual machines (VMs) considering basic properties like CPU utilisation, memory and bandwidth. ETS model is optimised based on resource allocation and balancing issues using back-propagation algorithm (BPA) with ANN (ANN-BPA) to analyse scheduling and problem identification mechanism. Efficiency of ETS model is assessed, focusing on aspects such as task allocation, task completion, execution time and energy consumption. The ANN-BPA-based task scheduling model outperforms by present technique and ANN-based model, which enhances resource utilisation by 7.54% and decreases completion time by 0.6 s. Copyright © 2025 Inderscience Enterprises Ltd.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

A Blockchain-Based Land Registration System in the Indian Context Incorporating Mortgage and Legal Aspects 4th

A Blockchain-Based Land Registration System in the Indian ...

引用

4th International Conference on Emerging Trends and Technologies on Intelligent Systems, ETTIS 2024

作者： Parashar, Yugam Pathari, Vinod Department of Computer Science and Engineering NIT Calicut Kozhikode India

ISBN: (纸本)9789819757022

Land is a limited resource that drives the development. The registration process of land ensures the proper recording of its details and ownership. Recently, there have been some attempts at digitalization of the land records. This paper presents the details of our proposed blockchain-based information system for land registration in India. The details of our implementation are also included. The work is in accordance with Torrens system and at the same time incorporates both mortgage and legal aspects from an Indian perspective. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Enhancing Plagiarism Detection in Marathi with a Weighted Ensemble of TF-IDF and BERT Embeddings for Low-Resource Language Processing 1

Enhancing Plagiarism Detection in Marathi with a Weighted En...

引用

1st Workshop on Language Models for Low-Resource Languages, LoResLM 2025 - co-located at the 31st International Conference on Computational Linguistics, COLING 2025

作者： Mutsaddi, Atharva Choudhary, Aditya Department of Computer Science and Engineering COEP Technological University India

ISBN: (纸本)9798891762152

Plagiarism involves using another persons work or concepts without proper attribution, presenting them as original creations. With the growing amount of data communicated in regional languages such as Marathi - one of India’s regional languages - it is crucial to design robust plagiarism detection systems tailored for low-resource languages. Language models like Bidirectional Encoder Representations from Transformers (BERT) have demonstrated exceptional capability in text representation and feature extraction, making them essential tools for semantic analysis and plagiarism detection. However, the application of BERT for low-resource languages remains under-explored, particularly in the context of plagiarism detection. This paper presents a method to enhance the accuracy of plagiarism detection for Marathi texts using BERT sentence embeddings in conjunction with Term Frequency-Inverse Document Frequency (TF-IDF) feature representation. This approach effectively captures statistical, semantic, and syntactic aspects of text features through a weighted voting ensemble of machine learning models. © 2025 Association for Computational Linguistics.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

A Survey on Predicting Depression Among Teachers and Students at Metropolitan University (Sylhet, Bangladesh) Using Machine Learning 3

A Survey on Predicting Depression Among Teachers and Student...

引用

3rd International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, IITCEE 2025

作者： Tabassum, Anika Ema, Yasmin Firuza Rafee, Md. Mushtaq Shahriyar Limon, Md Shamihul Islam Khan Metropolitan University Department of Computer Science and Engineering Sylhet Bangladesh

ISBN: (纸本)9798331515911

Depression, a psychiatric condition marked by profound sadness and apathy, influences cognitive processes, emotions, and behaviors, causing psychological and physiological challenges. Everyday tasks become arduous, life loses vibrancy, and in extreme cases, may lead to suicidal tendencies. University students face unique stressors due to academic, social, and personal pressures, underscoring the need for mental health support. This thesis investigates depression diagnosis among Metropolitan University teachers and students using machine learning techniques. Survey data, comprising 516 anonymized responses covering mental well-being, mood, and behavior, form the basis. The researchers preprocess data, visualize it, and train models to detect depression indicators, evaluating techniques like Logistic Regression, Decision Trees, and Gradient Boosting for effectiveness. The research highlights that the reasons for depression differ between females and males. The aim is to enhance early detection and support mechanisms, fostering proactive intervention within the university community. © 2025 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

An exploration on pattern analysis for bitcoin address behavior 4th

An exploration on pattern analysis for bitcoin address behav...

引用

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

作者： Parihar, Ankita Kumar, Amit Abhishek Department of Computer Science and Engineering Chandigarh University Chandigarh India

ISBN: (纸本)9781032911571

Bitcoin is a sort of money that is entirely virtual and is frequently referred to as a cryptocurrency, digital cash or virtual currency. It resembles a virtual currency although some countries have openly banned it, At first, not many stores used to accept Bitcoin as a mode of payment for goods and services. cryptocurrencies were mainly preferred for illicit activity on darknets, but nowadays it is widely used in mainstream applications. The amount of people who are becoming interested in cryptocurrencies has skyrocketed in recent years, and as a result, daily interactions on the distributed ledgers that underpin them have become more intense. The real Bitcoins you see in pictures are just for show. Without the private codes printed inside them, they would be worthless. In this paper we examine academic works to determine bitcoin address behaviour and pattern analysis. A thorough research of the literature is used to report on the pattern analysis of bitcoin transaction. The paper is based on primary information from published works and secondary information from publicly available case studies that are pertinent. In contrast to previous currencies, Bitcoin seems to have encountered many difficulties and, with its wide range of practical uses, posed particular difficulties for the user community. When Bitcoin first appeared, it appeared to represent optimism for a brighter future, but it is difficult to forecast how bitcoin will develop. © 2025 the Author(s).

关键词： Distributed ledger

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：