检索结果-内蒙古大学图书馆

A Conflict Degree-Guided Quantum Group Consensus Method Based on Graph Convolutional Networks with Enhanced Sentiment Analysis for Consumer Electronics Products

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Zhang, Chao Liang, Xinyu Sangaiah, Arun Kumar Li, Deyu Shanxi University School of Computer and Information Technology Key Laboratory of Computational Intelligence Chinese Information Processing Ministry of Education Taiyuan030006 China National Yunlin University of Science and Technology International Graduate Institute of Artificial Intelligence Douliou64002 Taiwan Sunway University School of Engineering and Technology Petaling Jaya Selangor 47500 Malaysia Chandigarh University University Centre for Research and Development Punjab Mohali140413 India

artificial intelligence-based human-computer interaction (AI-HCI) and consumer electronics (CE) are closely linked, making AI-HCI crucial in e-commerce by providing intelligent and personalized product recommendations. In this context, consumers often select from multiple websites and products when purchasing CE products. This makes CE product selections conflicting and random to reach a consensus, often modeled as a quantum group consensus problem. Therefore, this paper aims to enhance consumer selections via intelligent decision support using online reviews. First, an ensemble technique, multi-objective salp swarm optimization bi-directional long short-term memory (MOSSO-BiLSTM) with gate recurrent unit (GRU), is employed for sentiment analysis (SA). Second, graph convolutional networks (GCN) is used to calculate weights for key indicators. Meanwhile, according to hybrid distances, an improved fuzzy C-means three-way (FCMTW) clustering analysis is explored. Third, a conflict degree-guided quantum two-stage consensus reaching process (CRP) is designed. It includes identification rules determined by quantum frameworks and modification rules determined by regret theory (RT). Fourth, multi-objective optimization by ratio analysis plus the full MULTIplicative form (MULTIMOORA) and RT are combined for stable optimal product selections. Finally, a case study of selecting solar emergency lights verifies the viability of the proposed methodology. © 1975-2011 IEEE.

关键词： Quantum electronics

来源：评论

学校读者我要写书评

暂无评论

An investigation of ensemble learning techniques for obesity risk prediction using lifestyle data

Decision Analytics Journal

引用

Decision Analytics Journal 2025年 14卷

作者： Ganie, Shahid Mohammad Reddy, Bobba Bharath K, Hemachandran Rege, Manjeet AI Research Centre Woxsen University Telangana Hyderabad 502345 India School of Technology Woxsen University Telangana Hyderabad 502345 India Department of Software Engineering and Data Science Director of the Center for Applied Artificial Intelligence University of St. Thomas United States

Obesity disease is a significant health issue and has affected millions of people worldwide. Identifying underlying reasons for the onset of obesity risk in its early stage has become challenging for medical practitioners. The growing volume of lifestyle data related to obesity has made it imperative to employ effective machine-learning algorithms that can gather insights from the underlying data trends and identify critical patient conditions. In this study, an ensemble learning approach including boosting, bagging, and voting techniques was used for obesity risk prediction based on lifestyle dataset. Specifically, XGBoost, Gradient Boosting, and CatBoost models are used for boosting, Bagged Decision Tree, Random Forest, and Extra Tree models are used for bagging, and Logistic Regression, Decision Tree, and Support Vector Machine models are used for voting. Different preprocessing steps were employed to improve the quality assessment of the data. Hyperparameter tuning and feature selection and ranking are also used to achieve better prediction results. The considered models are extensively evaluated and compared using various metrics. Among all the models, XGBoost performed better with an accuracy of 98.10%, precision and recall of 97.50%, f1-score of 96.50%, and AUC-ROC of 100%, respectively. Additionally, weight, height, and age features were identified and ranked as the most significant predictors using the recursive feature elimination method for obesity risk prediction. Our proposed model can be used in the healthcare industry to support healthcare providers in better predicting and detecting multiple stages of obesity diseases. © 2024 The Author(s)

关键词： Bagging Boosting Ensemble learning Machine learning Obesity risk prediction Voting

来源：评论

学校读者我要写书评

暂无评论

Scalable and verifiable quantum secret sharing with photonic efficiency via quasicausal cones in the multiscale entanglement renormalization ansatz framework

引用

Physical Review A 2025年第2期111卷 022603-022603页

作者： Hong Lai Zhongrui Huang Li Ren Josef Pieprzyk Qibin Zhao Leongchuan Kwek School of Computer and Information Science Southwest University Chongqing 400715 China Centre for Quantum Technologies National University of Singapore 3 Science Drive 2 Singapore 117543 Singapore Data61 CSIRO Sydney New South Wales 2122 Australia Institute of Computer Science Polish Academy of Sciences Warsaw 01-248 Poland RIKEN Center for Advanced Intelligence Project Tokyo 103-0027 Japan MajuLab UMI No. 3654 CNRS-UNS-NUS-NTU International Joint Research Unit Singapore 117543 Singapore National Institute of Education Nanyang Technological University Singapore 637616 Singapore Quantum Science and Engineering Centre Nanyang Technological University Singapore 639798 Singapore

Quantum secret sharing (QSS) is set to revolutionize secure communication. However, achieving practical implementations that balance efficiency, security, and flexibility remains a significant challenge. To address this issue, we propose an innovative QSS scheme that integrates a verification mechanism for the distribution process by leveraging quasicausal cones within the multiscale entanglement renormalization ansatz framework. This approach ensures the secure dissemination of entangled photons across a multiuser network while enhancing the integrity of the quantum state against disturbances. A key feature of our scheme is the application of quasicausal cones, which improve the system's fault tolerance and recovery precision, preserving quantum state coherence and stability even in the presence of errors or losses. The recursive and hierarchical design of our framework enables it to dynamically adapt to fluctuations in network size and the number of participants, making it well suited for large-scale quantum networks. Furthermore, our method reduces the costs associated with photon transmission and storage, enhancing resource allocation within expansive quantum networks. The strategic incorporation of quasicausal cones represents a major advancement, streamlining the flow of quantum information and minimizing the overall resource footprint. By flexibly accommodating varying network sizes and configurations, our scheme marks a significant step towards efficient large-scale QSS, underscoring the critical role of quasicausal cones in advancing quantum communication technologies.

关键词： Photons

来源：评论

学校读者我要写书评

暂无评论

High Sensitivity Strain and Temperature Sensing With Cascaded Sagnac Interferometer Based on Harmonic Vernier Effect

引用

Photonic Sensors 2025年第3期15卷 1-14页

作者： Ding, Xin Liu, Shen Wang, Mengjie Chen, Nan Zhang, Weiguan Wang, Yiping Key Laboratory of Optoelectronic Devices and Systems of Ministry of Education/Guangdong Province College of Physics and Optoelectronic Engineering Shenzhen University Shenzhen China Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen) Shenzhen China Guangdong and Hong Kong Joint Research Centre for Optical Fiber Sensors Shenzhen University Shenzhen China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai China School of Electrical Engineering Nantong University Nantong China

To further improve sensor sensitivity, a strain and temperature sensor based on the harmonic Vernier effect with cascaded Sagnac interferometers (SIs) is proposed. Through a combination of simulation and experimentation, it is shown that the basic Vernier effect can be realized when the lengths of the polarization-maintaining fiber (PMF) in two SIs are slightly different. Furthermore, the first-order harmonic Vernier effect can be achieved when the lengths of two PMFs are approximately integer multiples. This sensor, leveraging the harmonic Vernier effect, demonstrates higher sensitivity. Compared to a single SI, the strain sensitivity based on the basic Vernier effect is improved to 61.93 pm/με with a magnification factor of 7.6, and the temperature sensitivity is improved to 14.29 nm/°C with a magnification factor of 9.4. For the first-order harmonic Vernier effect, the strain sensitivity increases to 146.35 pm/με with a magnification factor of 18, and the temperature sensitivity increases to 24.92 nm/°C with a magnification factor of 16.5. Additionally, the sensor based on the harmonic Vernier effect exhibits good stability in strain and temperature measurement. Unlike the basic Vernier effect, the harmonic Vernier effect does not require strict control of the reference and sensing interferometer lengths, further increasing sensitivity. Due to its simple structure and low cost, the proposed sensor shows significant potential for applications in high-precision measurement engineering and medical treatment.

关键词： Cascade Sagnac interferometers harmonic Vernier effect strain and temperature measurement polarization-maintaining fiber

来源：评论

学校读者我要写书评

暂无评论

M-Adapter: Multi-Level Image-to-Video Adaptation for Video Action Recognition

SSRN

引用

SSRN 2023年

作者： Li, Rongchang Xu, Tianyang Wu, Xiao-Jun Li, Linze Yang, Xiao Shen, Zhongwei Kittler, Josef School of Artificial Intelligence and Computer Science Jiangnan University Wuxi214122 China School of Electronic and Information Engineering Suzhou University of Science and Technology Suzhou215009 China Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

With the growing size of visual foundation models, training video models from scratch has become costly and challenging. Recent attempts focus on transferring frozen Pretrained Image Models (PIMs) to video fields by tuning inserted learnable parameters such as adapters and prompts. However, these methods require saving PIM activations for gradient calculations, leading to limited savings of GPU memory. In this paper, we propose a novel parallel branch that adapts the multi-level outputs of the frozen PIM for action recognition. It avoids passing gradients through the PIMs, thus naturally owning much lower GPU memory footprints. The proposed adaptation branch consists of hierarchically combined multi-level output adapters (M-adapters), comprising a fusion module and a temporal module. This design digests the existing discrepancies between the pre-training task and the target task with lower training costs. We show that when using larger models or on scenarios with higher demands for temporal modelling, the proposed method performs better than those with the full-parameter tuning manner. Finally, despite only tuning fewer parameters, our method achieves superior or comparable performance against current SOTA methods. © 2023, The Authors. All rights reserved.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Touchstone benchmark: are we on the right way for evaluating AI algorithms for medical segmentation? 24

Touchstone benchmark: are we on the right way for evaluating...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Pedro R. A. S. Bassi Wenxuan Li Yucheng Tang Fabian Isensee Zifu Wang Jieneng Chen Yu-Cheng Chou Saikat Roy Yannick Kirchhoff Maximilian Rokuss Ziyan Huang Jin Ye Junjun He Tassilo Wald Constantin Ulrich Michael Baumgartner Klaus H. Maier-Hein Paul Jaeger Yiwen Ye Yutong Xie Jianpeng Zhang Ziyang Chen Yong Xia Zhaohu Xing Lei Zhu Yousef Sadegheih Afshin Bozorgpour Pratibha Kumari Reza Azad Dorit Merhof Pengcheng Shi Ting Ma Yuxin Du Fan Bai Tiejun Huang Bo Zhao Haonan Wang Xiaomeng Li Hanxue Gu Haoyu Dong Jichen Yang Maciej A. Mazurowski Saumya Gupta Linshan Wu Jiaxin Zhuang Hao Chen Holger Roth Daguang Xu Matthew B. Blaschko Sergio Decherchi Andrea Cavalli Alan L. Yuille Zongwei Zhou Department of Computer Science Johns Hopkins University and Department of Pharmacy and Biotechnology University of Bologna and Center for Biomolecular Nanotechnologies Istituto Italiano di Tecnologia Department of Computer Science Johns Hopkins University NVIDIA Division of Medical Image Computing German Cancer Research Center (DKFZ) and Helmholtz Imaging German Cancer Research Center (DKFZ) ESAT-PSI KU Leuven Division of Medical Image Computing German Cancer Research Center (DKFZ) and Faculty of Mathematics and Computer Science Heidelberg University Division of Medical Image Computing German Cancer Research Center (DKFZ) and Faculty of Mathematics and Computer Science Heidelberg University and HIDSS4Health - Helmholtz Information and Data Science School for Health Shanghai Jiao Tong University Shanghai Artificial Intelligence Laboratory Division of Medical Image Computing German Cancer Research Center (DKFZ) Division of Medical Image Computing German Cancer Research Center (DKFZ) and Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Helmholtz Imaging German Cancer Research Center (DKFZ) and Interactive Machine Learning Group (IML) DKFZ School of Computer Science and Engineering Northwestern Polytechnical University Australian Institute for Machine Learning The University of Adelaide College of Computer Science and Technology Zhejiang University Hong Kong University of Science and Technology (Guangzhou) Hong Kong University of Science and Technology (Guangzhou) and Hong Kong University of Science and Technology Faculty of Informatics and Data Science University of Regensburg Faculty of Electrical Engineering and Information Technology RWTH Aachen University Faculty of Informatics and Data Science University of Regensburg and Fraunhofer Institute for Digital Medicine MEVIS Electronic & Information Engineering School Harbin Institute of Technology (Shenzhen) Shanghai Jiao Tong University and Beijing Academy of Artificial Intelligence (BAAI) S

ISBN: (纸本)9798331314385

How can we test AI performance? This question seems trivial, but it isn't. Standard benchmarks often have problems such as in-distribution and small-size test sets, oversimplified metrics, unfair comparisons, and short-term outcome pressure. As a consequence, good performance on standard benchmarks does not guarantee success in real-world scenarios. To address these problems, we present Touchstone, a large-scale collaborative segmentation benchmark of 9 types of abdominal organs. This benchmark is based on 5,195 training CT scans from 76 hospitals around the world and 5,903 testing CT scans from 11 additional hospitals. This diverse test set enhances the statistical significance of benchmark results and rigorously evaluates AI algorithms across out-of-distribution scenarios. We invited 14 inventors of 19 AI algorithms to train their algorithms, while our team, as a third party, independently evaluated these algorithms. In addition, we also evaluated pre-existing AI frameworks—which, differing from algorithms, are more flexible and can support different algorithms—including MONAI from NVIDIA, nnU-Net from DKFZ, and numerous other open-source frameworks. We are committed to expanding this benchmark to encourage more innovation of AI algorithms for the medical domain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cloud-Based Road Safety for Real-Time Vehicle Rash Driving Alerts with Random Forest Algorithm

Cloud-Based Road Safety for Real-Time Vehicle Rash Driving A...

引用

Innovation in Technology (INOCON), IEEE International Conference for

作者： Presitha Aarthi M Chilukala Mahender Reddy A. Anbarasi N. Mohankumar Ishwarya M.V S. Murugan Department of Computer Science and Engineering Shree Sathyam College of Engineering and Technology Salem Tamil Nadu India Department of Computer Science and Engineering GITAM University Hyderabad Telangana India Department of Computing Technologies School of Computing SRM Institute of Science and Technology Chennai Tamil Nadu India Department of Electronics and Communication Engineering B.V. Raju Institute of Technology Hyderabad Telangana India Artificial Intelligence and Data Science Department Agni College of Technology Chennai Tamil Nadu India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

The cloud-based road safety technology introduced in this research improves real-time vehicle behavior monitoring and warns for rash driving. It uses cloud computing to gather and interpret data from onboard car sensors and other traffic monitoring equipment. Powerful machine learning technology the Random Forest (RF) algorithm analyses this data intelligently. The RF algorithm is trained on a varied array of driving metrics to detect rash driving tendencies. Real-time data streams may be processed efficiently and scalable on the cloud, enabling speedy decision-making for rash driving detection. A network sends alerts to authorities and nearby vehicles. The system is adaptable to different road conditions, resistant to sensor data noise, and able to enhance rash driving detection accuracy via model updates. Cloud architecture makes the system available worldwide. With its focus on real-time notifications utilizing the RF algorithm, this cloud-based road safety system may reduce the hazards of reckless driving and avoid accidents.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent Approach Integrating Multiagent Systems and Case-Based Reasoning in Brain-computer Interface

Intelligent Approach Integrating Multiagent Systems and Case...

引用

International Conference on Power Energy, Environment and Intelligent Control (PEEIC)

作者： Kiran Malik Jagjit Singh Dhatterwal Kuldeep Singh Kaswan Manish Gupta Jyoti Thakur Department of Computer Science & Engineering MRIEM Rohtak Haryana India Artificial Intelligence and Data Science Koneru Lakshmaiah Education Foundation Guntur AP India School of Computer Science & Engineering Galgotias University Greater Noida UP India Director IQAC Lovely Professional University Punjab India Department of Information Technology GL Bajaj Institute of Technology and Management Greater Noida UP India

In this research paper investigates the integration of Multiagent Systems (MAS) and Case-Based Reasoning (CBR) within Brain-computer Interfaces (BCls). The aim is to enhance decision-making and adaptation in BCls, addressing limitations of standalone approaches. The problem statement revolves around the need for improved BCI performance and adaptability. Methodology involves designing a hybrid MAS-CBR framework and evaluating its performance against traditional BCI systems. MAS enables collaborative decision-making among agents, while CBR facilitates learning from past cases. Integration is achieved by using MAS for agent coordination and CBR for case adaptation. Key findings indicate that the hybrid approach yields improved decision accuracy and adaptation compared to individual systems. The collaborative nature of MAS and the knowledge reuse of CBR synergize effectively, resulting in enhanced BCI performance. This integration showcases the potential to advance BCls beyond their current limitations. Implications of this research are significant, as it offers a novel approach to overcome BCI challenges. The hybrid MAS-CBR framework can be further refined to optimize real-time decision-making and adaptability in various application domains. Ultimately, this research contributes to the evolution of BCls by leveraging the strengths of both MAS and CBR, leading to more efficient and robust brain-computer interaction paradigms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Resource Management and data Security in Cloud Computing Environments

Optimizing Resource Management and Data Security in Cloud Co...

引用

Advancement in Technology (ICONAT), International Conference for

作者： S.Jothi Shri G. Karthiyayini L S Vignesh Talluri Upender D Shobana Ladi Sandip Kumar Patra Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Chennai Department of CSE Ramco Institute of Technology Rajapalayam Tamil Nadu Department of Artificial Intelligence and Data Science Nadar Saraswathi College of Engineering and Technology Theni Department of CSE CMR College of Engineering and Technology Medchal Hyderabad Telangana Department of Mechatronics Engineering Rajalakshmi Engineering College Chennai Department of ECE MLR Institute of Technology Hyderabad

ISBN: (数字)9798350354171

ISBN: (纸本)9798350354188

The quick uptake of cloud computing has completely changed how companies run since it offers flexible and scalable resources that promote productivity and creativity. However, the dynamic and complex nature of cloud environments presents significant challenges in optimizing resource management and ensuring robust data security. This paper investigates advanced strategies and methodologies for enhancing resource allocation, virtualization, and scheduling to maximize performance and cost-efficiency in cloud infrastructures. Key techniques explored include dynamic scaling, load balancing, VM migration, containerization, and cost-effective resource usage through spot and reserved instances. The important facets of cloud computing data security, such as encryption, identity and access management (IAM), data loss prevention (DLP), and intrusion detection and prevention systems (IDPS), are also covered in tandem by this research. The study offers novel approaches for reducing security threats and guaranteeing data integrity by fusing cutting-edge technology like blockchain and machine intelligence. The comprehensive analysis aims to provide actionable insights and practical recommendations for IT professionals and organizations striving to optimize their cloud computing operations. By balancing resource management efficiency with stringent security measures, this research contributes to the development of a more secure and efficient cloud ecosystem. The results emphasise the significance of a comprehensive strategy for managing cloud systems, where data security and performance optimisation work together to provide durable and sustainable cloud computing environments.

关键词： Productivity Cloud computing Processor scheduling data security Prevention and mitigation Dynamic scheduling Resource management Virtualization Optimization Machine intelligence

来源：评论

学校读者我要写书评

暂无评论

Cloud Computing Based POC Diagnostic Device: Rapid Infectious Disease Testing by data Analytics

Cloud Computing Based POC Diagnostic Device: Rapid Infectiou...

引用

artificial intelligence for Innovations in Healthcare Industries (ICAIIHI), International Conference on

作者： H. Anwer Basha L. Ramalingam MD Ashfaqul Hasan M.H Ananda S. Velmurugan S.P. Maniraj Department of Computer Science Saveetha College of Liberal Arts & Sciences SIMATS University Chennai Tamil Nadu India Department of Artificial Intelligence and Data Science Loyola Institute of Technology Chennai Tamil Nadu India Department of Computer Science and Engineering Malla Reddy Institute of Engineering and Technology Hyderabad Telangana India School of Electrical and Electronics Engineering REVA University Bangalore Karnataka India Department of Electronics and Communication Engineering TJS Engineering College Chennai Tamil Nadu India Department of Computer Science and Engineering SRM Institute of Science and Technology Chennai Tamil Nadu India

To meet the growing need for affordable, efficient, and accurate diagnostic tools, the system has developed a Raspberry Pi-based Point-of-Care (POC) gadget for speedy and reliable detection of infectious illnesses. This groundbreaking gadget, built on the flexible and powerful Raspberry Pi computer, ushers in a new era of state-of-the-art POC diagnostics by combining molecular and image analysis methods. Complex testing for pathogens like COVID-19 and malaria may be carried out using this state-of-the-art system, which integrates a camera module and custom biosensors. The device's software parses sensor data, improves diagnostic precision using machine learning techniques, and presents a straightforward interface for clinicians and patients alike. This study takes a holistic approach by considering all relevant factors, including adherence to regulations, user education, upkeep, and data management. Our POC diagnostic gadget driven by a Raspberry Pi provides a low-cost, high-throughput method for diagnosing illness, which may have far-reaching implications for the future of healthcare delivery in both under-resourced and well-endowed regions.

关键词：

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：