检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Hu, Zheng Li, Zhe Jiao, Ziyun Nakagawa, Satoshi Deng, Jiawen Cai, Shimin Zhou, Tao Ren, Fuji School of Computer Science and Engineering University of Electronic Science and Technology of China China Graduate School of Information Science and Technology University of Tokyo Japan Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China China

In recent years, knowledge graphs have been integrated into recommender systems as item-side auxiliary information, enhancing recommendation accuracy. However, constructing and integrating structural user-side knowledge remains a significant challenge due to the improper granularity and inherent scarcity of user-side features. Recent advancements in Large Language Models (LLMs) offer the potential to bridge this gap by leveraging their human behavior understanding and extensive real-world knowledge. Nevertheless, integrating LLM-generated information into recommender systems presents challenges, including the risk of noisy information and the need for additional knowledge transfer. In this paper, we propose an LLM-based user-side knowledge inference method alongside a carefully designed recommendation framework to address these challenges. Our approach employs LLMs to infer user interests based on historical behaviors, integrating this user-side information with item-side and collaborative data to construct a hybrid structure: the Collaborative Interest Knowledge Graph (CIKG). Furthermore, we propose a CIKG-based recommendation framework that includes a user interest reconstruction module and a cross-domain contrastive learning module to mitigate potential noise and facilitate knowledge transfer. We conduct extensive experiments on three real-world datasets to validate the effectiveness of our method. Our approach achieves state-of-the-art performance compared to competitive baselines, particularly for users with sparse interactions. Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional Station Distribution Design for TDOA Positioning System of Sea Launch Site

Three-dimensional Station Distribution Design for TDOA Posit...

引用

第十四届中国卫星导航年会

作者： Maolin Chen Xianglu Li Changjiang Liu Zhengyu Ji Yimao Sun Institute of Electronic Engineering China Academy of Engineering Physics 78090 Troop of PLA School of Computer Science Sichuan University

In recent years, USA, Russia and China have carried out many sea launch and recovery experiments, sea launch site exhibits better safety and economical efficiency compared with land launch site, which can provide launch service for spacecraft with different orbits. GNSS/INS integrated navigation system is adopted by rockets to acquire positioning results, nevertheless, owing to the inherit vulnerability of GNSS and possible INS failure, other navigation system is required to offer independent multi-source positioning data. TDOA positioning system is able to calculate rocket's position utilizing time measurement data from telemetering signals, on one hand, the reliability can be promoted, and on the other hand, real-time central monitoring can be achieved, which aroused an increasing number of interests. However, present TDOA system usually apply land stations to obtain time measurements and localization results, because the characteristics of flat station distribution along the vertical direction, the vertical positioning precision cannot be satisfactory, especially for the need of rocket recovery on the sea launch site. To solve this problem, this work first discusses the precision influence of different surveying ships distribution layouts, "T" shape distribution is recommended for surveying ships according to evaluation results, then introduces airbased surveying station into TDOA positioning system to improve vertical localization accuracy, probes the performance variation utilizing different UAVs, including tethered UAV, multi-rotor UAV, medium-scale vertical takeoff and landing fixed wing UAV and large-scale fixed wing UAV, confirms the optimal UAV height in the rocket recovery key area under 10km height, then researches on surveying station optimal distribution layout strategy according to predefined trajectory. This work can enhance the positioning precision and reliability, and provide three-dimensional surveying station distribution guidance in sea launch

关键词：

来源：评论

学校读者我要写书评

暂无评论

Backdoor-Resistant Public data Integrity Verification Scheme Based on Smart Contracts

Backdoor-Resistant Public Data Integrity Verification Scheme...

引用

作者： Li, Shanshan Xu, Chunxiang Zhang, Yuan Du, Yicong Yang, Anjia Wen, Xinsheng Chen, Kefei Zhongnan University of Economics and Law School of Information and Safety Engineering Wuhan430073 China University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu611731 China University of Electronic Science and Technology of China Yangtze Delta Region Institute Huzhou313001 China Jinan University College of Cyber Security Guangzhou510632 China Hangzhou Normal University Department of Mathematics Hangzhou310030 China

This article analyzes existing smart contract-based public data integrity verification schemes and identifies certain weaknesses. First, the fair arbitration mechanism deployed in these schemes fails to meet the users' requirements as it may not promptly notify users of data corruption or loss. Second, to ensure outsourced data confidentiality, existing data integrity schemes use a conventional encrypted method, where each user randomly selects a key to encrypt the outsourced data. Such a method results in varying ciphertexts for the same data by different users, leading to additional storage costs for the cloud server. Third, users' devices, if poorly designed or even intentionally backdoored, can potentially exfiltrate secrets and compromise the security of schemes. To address these issues, we propose the first backdoor-resistant public data integrity verification scheme based on smart contracts (ASSIST). The key idea is to introduce a new entity (a whistleblower) to periodically monitor the state of verification results recorded in the blockchain. This allows for timely notification of data corruption to users. ASSIST requires users to encrypt their data with a cryptographic primitive called message-locked encryption (MLE), which motivates different users to produce the same ciphertext for the same data and reduces storage costs for cloud servers. We also deploy a cryptographic reverse firewall between users' devices and the external to rerandomize interactive messages, making the exfiltration impossible. We provide rigorous security proofs to demonstrate the security of ASSIST. The performance evaluation shows that ASSIST is efficient regarding computation and communication costs. © 2014 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Clinical Text Classification Using Sequential Forward Selection

Clinical Text Classification Using Sequential Forward Select...

引用

Intelligent and Innovative Technologies in Computing, Electrical and electronics (IITCEE), International Conference

作者： Rajkumar Rajasekaran Veer Sanghavi Rashi Solanki Jolly Masih Department of Analytics Vellore Institute of Technology Vellore India School of Computer Science and Engineering Vellore Institute of Technology Vellore India Department of Business Analytics BML Munjal University Gurugram India

Clinical text classification is a critical undertaking within the realm of Natural Language Processing, holding significant implications for healthcare applications. In this NLP project, our primary objective is the categorization of medical transcripts into their corresponding medical conditions. To accomplish this, we harness the power of Sequential Forward Selection (SFS), a feature selection technique meticulously chosen for its capacity to streamline data dimensions. By employing SFS, our project aspires to not only enhance classification performance but also elevate the efficiency of pattern recognition, ensuring both speed and accuracy in disease identification. This research contribution underscores the pivotal role of Clinical Text Classification, with a specific focus on optimizing the process using SFS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ECIL-MU: Embedding Based Class Incremental Learning and Machine Unlearning

ECIL-MU: Embedding Based Class Incremental Learning and Mach...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhiwei Zuo Zhuo Tang Bin Wang Kenli Li Anwitaman Datta College of Computer Science and Electronic Engineering Hunan University China School of Computer Science and Engineering Nanyang Technological University Singapore Shenzhen Research Institute Hunan University China

New categories may be introduced over time, or existing categories may need to be reclassified. Class incremental learning (CIL) is employed for the gradual acquisition of knowledge about new categories while preserving information about previously learned ones in such dynamic environments. It might also be necessary to also eliminate the influence of related categories on the model to adapt to reclassification. We thus introduce class-level machine unlearning (MU) within CIL. Typically, MU methods tend to be time-consuming and can potentially harm the model’s performance. A continuous stream of unlearning requests could lead to catastrophic forgetting. To address these issues, we propose a non-destructive eCIL-MU framework based on embedding techniques to map data into vectors and then be stored in vector databases. Our approach exploits the overlap between CIL and MU tasks for acceleration. Experiments demonstrate the capability of achieving unlearning effectiveness and orders of magnitude (upto ~ 278×) of acceleration.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cloud-Based AI Solutions for Early Wound Infection Detection and Treatment Recommendations 4

Cloud-Based AI Solutions for Early Wound Infection Detection...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Rajasekaran, Mothiram Ranganathan, Chitra Sabapathy Manikandan, G. Bhuvaneswari, G. Ganeshbabu, T.R. Rajmohan, M. Pine Candle Way Saint AugustineFL United States Mphasis Corporation ChandlerAZ United States Rmk Engineering College Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamil Nadu Chennai India Department of Electronics and Communication Tamil Nadu Namakkal India Hindustan Institute of Technology and Science Department of Electronics and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331540364

Wound infections are a major problem for healthcare systems worldwide. Infections cause patients to remain in the hospital longer., which increases healthcare expenses and negatively impacts their health outcomes. For patient care to be successful, it is crucial to identify these illnesses quickly and treat them appropriately. Recent developments in cloud computing and artificial intelligence (AI) have encouraged optimism for the potential of these technologies to improve wound infection diagnosis and treatment. Within healthcare systems, this research outlines a new method for early wound infection diagnosis and treatment recommendations generation using cloud-based AI algorithms. The proposed method employs machine learning to appropriately detect early indications of infection by analyzing a variety of patient data inputs, such as wound features, vital signs, laboratory findings, and medical history. Also, healthcare practitioners may benefit from real-time monitoring and decision assistance due to cloud-based architecture's easy interaction with existing electronic health record (HER) systems. The system is designed with a dynamic feedback loop that can be updated with fresh data inputs to make it more accurate and flexible. The proposed cloud-based AI system has been thoroughly tested and proven reliable in improving the early diagnosis and treatment of wound infections. This has led to better patient outcomes and more efficient use of healthcare resources. Key challenges include data privacy issues, the integration of diverse technologies, the reliability of precise forecasts, and maintaining system resiliency in changing environments. © 2024 IEEE.

关键词： electronic health record

来源：评论

学校读者我要写书评

暂无评论

Structural plasticity-based hydrogel optical Willshaw model for one-shot on-the-fly edge learning

引用

InfoMat 2023年第4期5卷 48-59页

作者： Dingchen Wang Dingyao Liu Yinan Lin Anran Yuan Woyu Zhang Yaping Zhao Shaocong Wang Xi Chen Hegan Chen Yi Zhang Yang Jiang Shuhui Shi Kam Chi Loong Jia Chen Songrui Wei Qing Wang Hongyu Yu Renjing Xu Dashan Shang Han Zhang Shiming Zhang Zhongrui Wang Department of Electrical and Electronic Engineering The University of Hong KongHong Kongthe People's Republic of China ACCESS-AI Chip Center for Emerging Smart Systems InnoHK CentersHong Kong Science ParkHong Kongthe People's Republic of China School of Computer Science and Engineering Faculty of Innovation EngineeringMacao University of Science and TechnologyMacaothe People's Republic of China Key Laboratory of Microelectronics Devices and Integrated Technology Institute of MicroelectronicsChinese Academy of SciencesBeijingthe People's Republic of China Collaborative Innovation Center for Optoelectronic Science Technology International Collaborative Laboratory of 2D Materials for OptoelectronicsScience and Technology of Ministry of EducationInstitute of Microscale OptoelectronicsShenzhen UniversityShenzhenthe People's Republic of China School of Microelectronics Southern University of Science and TechnologyShenzhenthe People's Republic of China Microelectronics Thrust Function Hub of the Hong Kong University of Science and Technology(Guangzhou)Guagndongthe People's Republic of China

Autonomous one-shot on-the-fly learning copes with the high privacy,small dataset,and in-stream data at the *** such learning on digital hardware suffers from the well-known von-Neumann and scaling *** optical neural networks featuring large parallelism,low latency,and high efficiency offer a promising ***,ex-situ training of conventional optical networks,where optical path configuration and deep learning model optimization are separated,incurs hardware,energy and time overheads,and defeats the advantages in edge ***,we introduced a bio-inspired material-algorithm co-design to construct a hydrogel-based optical Willshaw model(HOWM),manifesting Hebbian-rule-based structural plasticity for simultaneous optical path configuration and deep learning model optimization thanks to the underlying opto-chemical *** first employed the HOWM as an all optical in-sensor AI processor for one-shot pattern classification,association and *** then leveraged HOWM to function as a ternary content addressable memory(TCAM)of an optical memory augmented neural network(MANN)for one-shot learning the Omniglot *** HOWM empowered one-shot on-the-fly edge learning leads to 1000boost of energy efficiency and 10boost of speed,which paves the way for the next-generation autonomous,efficient,and affordable smart edge systems.

关键词： associative memory hydrogel one-shot learning optical neural network structural plasticity Willshaw model

来源：评论

学校读者我要写书评

暂无评论

An Empirical Examination of the Factors of Big data analytics Implementation in Supply Chain Management and Logistics 10

An Empirical Examination of the Factors of Big Data Analytic...

引用

10th IEEE Uttar Pradesh Section International Conference on Electrical, electronics and computer engineering, UPCON 2023

作者： Ravindar, K. Syed, Mohammad Haider Sampath, Bharath Rajalakshmi, B. Reddy, V Venkat Dutt, Amit School of Sciences Sr University Telangana Warangal India Saudi Electronic University Department of Computer Science Saudi Arabia University Karnataka Bangalore India New Horizon College of Engineering Department of Computer Science Bangalore India Institute of Aeronautical Engineering Dundigal Hyderabad India Lovely Professional University Phagwara India

ISBN: (纸本)9798350382471

Numerous companies have effectively exploited Big data analytics (BDA) potential to enhance their effectiveness in the Big data period. Given that big data application in logistics and supply chain management (SCM) is nevertheless in its early stages, assessments of BDA could differ from various viewpoints, producing certain difficulties in comprehending the significance and potential of big data. Based on past research on BDA and SCM, this work examines the factors that influence organizations' willingness to implement BDA in their everyday activities. This research divides potential elements into 4 groups: technical, firm, ecological, and supply chain issues. A framework consisting of direct factors like technical, firm, and mediators was presented based on the technology diffusion hypothesis. The experimental findings demonstrated that anticipated advantages and high-level management assistance might have a considerable impact on intended adoption. Furthermore, ecological variables like competitive adoption, administration legislation, and supply chain connection can greatly alter the direct connections between influencing causes and intended adoption. © 2023 IEEE.

关键词： Big data analytics Logistics Operational efficiency Supply chain management

来源：评论

学校读者我要写书评

暂无评论

Towards Context-aware Support for Color Vision Deficiency: An Approach Integrating LLM and AR 13

Towards Context-aware Support for Color Vision Deficiency: A...

引用

13th IEEE Global Conference on Consumer electronic, GCCE 2024

作者： Morita, Shogo Zhang, Yan Yamauchi, Takuto Chen, Sinan Li, Jialong Tei, Kenji Tokyo Institute of Technology School of Computing Tokyo Japan University of Tokyo International Research Center for Neurointelligence Tokyo Japan Waseda University Department of Computer Science and Engineering Tokyo Japan Kobe University Center of Mathematical and Data Sciences Kobe Japan

ISBN: (纸本)9798350355079

People with color vision deficiency often face challenges in distinguishing colors such as red and green, which can complicate daily tasks and require the use of assistive tools or environmental adjustments. Current support tools mainly focus on presentation-based aids, like the color vision modes found in iPhone accessibility settings. However, offering context-aware support, like indicating the doneness of meat, remains a challenge since task-specific solutions are not cost-effective for all possible scenarios. To address this, our paper proposes an application that provides contextual and autonomous assistance. This application is mainly composed of: (i) an augmented reality interface that efficiently captures context;and (ii) a multi-modal large language model-based reasoner that serves to cognitize the context and then reason about the appropriate support contents. Preliminary user experiments with two color vision deficient users across five different scenarios have demonstrated the effectiveness and universality of our application. © 2024 IEEE.

关键词： Color vision

来源：评论

学校读者我要写书评

暂无评论

A Framework and Environment Design of Human-Machine Cooperations in Junior science Education 8

A Framework and Environment Design of Human-Machine Cooperat...

引用

8th International Symposium on System Security, Safety, and Reliability, ISSSR 2022

作者： Meng, Sa Luo, Liang Liu, Jun Dai, Yuanshun School of Computing and Artificial Intelligence Southwest Jiaotong University Sichuan Chengdu China School of Computer Science and Engineering University of Electronic Science and Technology of China Sichuan Chengdu China Robotics Institute School of Computer Science Carnegie Mellon University PittsburghPA United States

ISBN: (数字)9781665453974

ISBN: (纸本)9781665453974

Human-Machine-Environment (HME) Tri-Co (Coexisting, Cooperative, Cognitive) Education is an indispensable prerequisite and main content of Artificial Intelligence empowering junior science education. Moreover, it is also a critical requirement for improving the quality of education and promoting the high-end development of education information. Building a unique learning environment with scene perception and the intelligent cognitive process is a tremendous challenge for diverse needs in junior scientific learning scenarios. Therefore, it is necessary to design advanced human-computer interaction scenarios and functions. This paper aims to tackle the critical scientific problem of this field for HME Tri-Coeducation, i.e., HME multimodal real-time scene perception and Tri-Co collaborative analysis via Multi-source data, fundamental theories, application method, and verification system, and to build HME Tri-Coeducation environment in 'Perception-Analysis-Interaction' architecture. For the requirements of an education environment empowered by artificial intelligence, this paper will also study critical technologies of human-machine cooperative and education environment building driven by big data. It is significant to promote the cross-integration of multi-disciplines such as pedagogy, intelligent technology, and cognitive science. © 2022 IEEE.

关键词： Human computer interaction

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：