检索结果-内蒙古大学图书馆

4th International Symposium on Smart and Healthy Cities, ISHC 2022

作者： Mei, Yongbiao Zhang, Zhourong Yu, Fang Jiang, Liang Liu, Zicong Chen, Junjie Xiangnan University School of Computer and Artificial Intelligence Xiangnan University Hunan Engineering Research Center of Advanced Embedded Computing Intelligent Medical Systems Hunan Chenzhou China

ISBN: (纸本)9781665491808

Aiming at the requirements of safety production, this paper designs an Intelligent Safety Early Warning System for High-Risk Areas based on BeiDou and STM32. The system utilizes the high-precision positioning of the BeiDou Navigation Satellite System, combined with an electronic fence and a sensing technology, to limit the safety grade of different areas for all personnel in high-risk areas, and meanwhile, the surrounding environment, the posture of workers and the like are intelligently detected by using an Internet of Things technology such as a sensor, achieving the role of timely supervision and safety warning, effectively improving the safety of operations in high-risk areas, and enhancing management efficiency. © 2022 IEEE.

关键词： Human resource management

来源：评论

学校读者我要写书评

暂无评论

Integrating digital twins and deep learning for medical image analysis in the era of COVID-19

引用

Virtual Reality & Intelligent Hardware 2022年第4期4卷 292-305页

作者： Imran AHMED Misbah AHMAD Gwanggil JEON School of Computing and Information Science Faculty of Science and EngineeringAnglia Ruskin UniversityEast RoadCambridgeEnglandUK Center of Excellence in IT Institute of Management SciencesHayatabadPeshawarPakistan Department of Embedded Systems Engineering Incheon National UniversityIncheonKorea

Background Digital twins are virtual representations of devices and processes that capture the physical properties of the environment and operational algorithms/techniques in the context of medical devices and *** twins may allow healthcare organizations to determine methods of improving medical processes,enhancing patient experience,lowering operating expenses,and extending the value of *** the present COVID-19 pandemic,various medical devices,such as X-rays and CT scan machines and processes,are constantly being used to collect and analyze medical *** collecting and processing an extensive volume of data in the form of images,machines and processes sometimes suffer from system failures,creating critical issues for hospitals and *** To address this,we introduce a digital-twin-based smart healthcare system in-tegrated with medical devices to collect information regarding the current health condition,configuration,and maintenance history of the device/machine/***,medical images,that is,X-rays,are analyzed by using a deep-learning model to detect the infection of *** designed system is based on the cascade recurrent convolution neural network(RCNN)*** this architecture,the detector stages are deeper and more sequentially selective against small and close false *** architecture is a multi-stage extension of the RCNN model and sequentially trained using the output of one stage for training the *** each stage,the bounding boxes are adjusted to locate a suitable value of the nearest false positives during the training of the different *** this manner,the arrangement of detectors is adjusted to increase the intersection over union,overcoming the problem of *** train the model by using X-ray images as the model was previously trained on another *** The developed system achieves good accuracy during the detection phase of *** experimental o

关键词： Digital twins Deep learning Healthcare COVID-19 Chest X-rays Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Optimization Mechanism of Virtualized Database Log System Under the Background of Intelligent Technology

Optimization Mechanism of Virtualized Database Log System Un...

引用

作者： Xie, Hui Wei, Li Kumar, Aditya School of Computer and Artificial Intelligence Xiangnan University Hunan Chenzhou China Hunan Engineering Research Center of Advanced Embedded Computing and Intelligent Medical Systems Xiangnan University Hunan Chenzhou China Gachon University Seongnam Incheon Korea Republic of

With the development of industrial science and technology, all walks of life are developing in the direction of intelligence, integration and datamation. Under the background of intelligent technology development, big data will become one of the main directions of the development of industrial data information integration in the future. While the log system as the data behavior recording terminal in the database, it makes node records on the behavior of the huge data stream terminal users. But, the existing database log system cannot accurately reflect the "activity" of the data in the real world, and there may be the problem of inconsistency in granularity between the users’ actual operation behavior and the log node in the database. Therefore, this study will propose specific optimization measures based on the Oracle database log system so as to make the nodes of the database log system more accurate and improve the efficiency and security of the system. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Incremental Learning with Repetition via Pseudo-Feature Projection

arXiv

引用

arXiv 2025年

作者： Tscheschner, Benedikt Veas, Eduardo Masana, Marc Know-Center Research GmbH Austria Institute of Visual Computing TU Graz Austria SAL Dependable Embedded Systems Silicon Austria Labs Austria

Incremental Learning scenarios do not always represent real-world inference use-cases, which tend to have less strict task boundaries, and exhibit repetition of common classes and concepts in their continual data stream. To better represent these use-cases, new scenarios with partial repetition and mixing of tasks are proposed, where the repetition patterns are innate to the scenario and unknown to the strategy. We investigate how exemplar-free incremental learning strategies are affected by data repetition, and we adapt a series of state-of-the-art approaches to analyse and fairly compare them under both settings. Further, we also propose a novel method (Horde), able to dynamically adjust an ensemble of self-reliant feature extractors, and align them by exploiting class repetition. Our proposed exemplar-free method achieves competitive results in the classic scenario without repetition, and state-of-the-art performance in the one with repetition. © 2025, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Asynchronous Continuous Time Pipeline Analog-to-Digital Converter

Asynchronous Continuous Time Pipeline Analog-to-Digital Conv...

引用

IEEE National Conference on Radar

作者： Patrick Jungwirth W. Michael Crowe Advanced Computing Branch DEVCOM Army Research Lab Aberdeen MD Embedded Systems DEVCOM Aviation and Missile Center Redstone Arsenal AL

ISBN: (数字)9798350329209

ISBN: (纸本)9798350329216

Continuous time systems offer a number of advantages over conventional digital signal processing. Conventional digital signal processing is limited by quantization error, frequency aliasing, and discrete time lag. Continuous time systems have no inherent quantization error, are free of frequency aliasing, free from discrete time lag, and provide a form of compressive sensing. For a 4-bit equivalent analog-digital-converter (ADC), Vezyrtzis and Tsividis demonstrated offline reconstruction of a continuous time signal with > 100 dB signal-to-noise-and-distortion (SINAD) ratio. Conventional Shannon sampling pipeline analog-to-digital converters are limited by (1) aperture jitter (sample timing jitter) (2) overlapping pipeline stage voltage levels, (3) multiple voltage reference stages, (4) multiple bit changes in multiple pipeline stages, and (5) complex amplitude and timing error correction. Conventional pipeline analog-to-digital converters are not designed to guarantee only one state change occurs a time. A patent pending continuous time pipeline analog-to-digital converter is presented that overcomes many of the limitations present in conventional analog-to-digital converters. A continuous time ADC is not based on Shannon sampling, and it does not have the extremely low aperture jitter requirements found in conventional GHz speed ADCs. Continuous time pipeline analog-to-digital converters can potentially achieve 10 plus equivalent number of bits (ENOB) at greater than 10 GHz speeds.

关键词： Timing jitter Time-frequency analysis Quantization (signal) Pipelines Voltage Digital signal processing Apertures

来源：评论

学校读者我要写书评

暂无评论

Research and Implementation of Network Security Deployment Based on Private Cloud Security Platform 7

Research and Implementation of Network Security Deployment B...

引用

7th International Conference on Intelligent, Interactive systems and Applications, IISA2022

作者： Min, Xiao Mei, Guo Weiping, Zhu School of Computer and Artificial Intelligence XiangNan University Hunan Chenzhou423000 China Advanced Embedded Computing and Intelligent Medical Systems Hunan Engineering Research Center Hunan Chenzhou423000 China

With the development of science and technology, the computer age has *** a new type of computer network application technology, cloud computing technology is of great significance to promote China's economic ***, in the development of cloud technology, it faces serious security *** cloud providers all claim that their services are very secure in all aspects, especially in data ***, for large enterprises, business-related data is their *** enterprises will not put their important applications on the public cloud for operation, and private cloud has great advantages in this *** paper introduces the relevant concepts and network security deployment methods of cloud technology and private cloud security *** research on private cloud security platform is to better resist the next generation of security *** network security on private cloud security platform can reduce the informatization cost of enterprises, public institutions and government departments and improve work efficiency. © 2022 The Authors. Published by Elsevier B.V.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence for Wireless Communications: The InSecTT perspective

IEEE Open Journal of the Industrial Electronics Society

引用

IEEE Open Journal of the Industrial Electronics Society 2025年 6卷 802-819页

作者： Robles, Ramiro Samano Javanmardi, Gowhar Pilz, Christoph Kwapisiewicz, Przemyslaw Rzymowski, Mateusz Kulas, Lukasz Davoli, Luca Belli, Laura Ferrari, Gianluigi Wenning, Bernd-Ludwig Gonca, Bugra Prasad, R. Venkatesha Simha, Ashutosh Kiviranta, Markku Moilanen, Ilkka Robinson, Sean Cirill, Gennaro Soyturk, Mujdat Bostanci, Yavuz Selim Hormann, Leander B. Research Centre in Real-time and Embedded Computing Systems Porto Portugal University of Porto Faculty of Engineering Portugal Virtual Vehicle Research GmbH Graz Austria Gdansk University of Technology Poland Lab Department of Engineering and Architecture Parma Italy Rome Italy Munster Technological University Cork Ireland NuRD Innovation Center Turkey Technical University of Delft Netherlands VTT Research Corporation Finland F-Secure Corporation Finland Marmara University Istanbul Turkey 1Linz Center of Mechatronics GmbH Linz Austria

This paper presents an overview of how Artificial Intelligence (AI) and edge technology have been used to improve wireless connectivity in multiple industrial Use Cases (UCs) of the EU project "Intelligent Secure Trustable Things"(InSecTT). We present a brief introduction of the InSecTT framework for crossdomain architecture design, which targets UCs assisted by reusable and-or interoperable technical Building Blocks (BBs). These BBs constitute the construction bricks containing AI and supporting components that were used to build different UCs. The framework consists of multiple stages based on the processing of UC-BB requirements (RQs). These stages include: i) collection, ii) harmonization, iii) refinement, iv) classification, v) architecture alignment, and vi) functionality modeling of RQs. The most relevant results of these stages are discussed here, with emphasis on the need for a refined granularity of technical components with common functionalities named sub-building blocks (SBBs), where collaboration and cross-domain reusability were optimized. The design process shed light on how AI and SBBs were implemented across different layers and entities of our reference architecture for the Internet-of-Things (IoT), including the interfaces used for information exchange. This detailed interface analysis is expected to reveal issues such as bottlenecks, constraints, vulnerabilities, scalability problems, security threats, etc. This will, in turn, contribute to identifying design gaps in AI-enabled IoT systems. The paper summarizes the SBBs related to wireless connectivity, including a general description, implementation issues, comparison of results, adopted interfaces, and conclusions across domains. © 2020 IEEE.

关键词： Reusability

来源：评论

学校读者我要写书评

暂无评论

Research on the Classification Method of Urolithiasis Composition Based on Machine Learning

Research on the Classification Method of Urolithiasis Compos...

引用

2022 IEEE International Conference on Advances in Electrical Engineering and Computer Applications, AEECA 2022

作者： Liao, Xingjiao Liu, Yaohui Guo, Mei Yu, Fang Xiangnan University Hunan Engineering Research Center of Advanced Embedded Computing and Intelligent Medical Systems Hunan Chenzhou China Xiangnan University School of Computer and Artificial Intelligence Hunan Chenzhou China

ISBN: (数字)9781665480901

ISBN: (纸本)9781665480901

This paper aims to investigate how to accurately classify urinary calculi components by CT images. The image segmentation is completed by grayscale adjustment of the two-dimensional image and region growth of the three-dimensional image. Grayscale and energy features of the region of interest are extracted in three dimensions. In this paper, the three different models trained by the EasyEnsemble ensemble algorithm are connected in series to achieve layer-by-layer classification of unbalanced samples. The experimental results show that this method can effectively analyze the components of simple calcium oxalate monohydrate, anhydrous uric acid, carbonated apatite and dihydrate calcium oxalate in urinary tract stones, and the AUCs reach AUC=0.93, AUC=1.00, AUC= 0.86, AUC=0.76, respectively, indicating that this method can better perform multi-classification of unbalanced samples. © 2022 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Home Medicine Box AI System

Design and Implementation of Home Medicine Box AI System

引用

Computer, Vision and Intelligent Technology (ICCVIT), International Conference on

作者： Xia Zhang Wenfen Zhang College of Computer and Artificial Intelligence Xiangnan University Chenzhou China The Hunan Engineering Researcher Center of Advanced Embedded Computing and Intelligent Medical Systems Chenzhou China

ISBN: (数字)9798331540043

ISBN: (纸本)9798331540050

In order to solve the problems of daily medication and health and safety care for the elderly, this paper uses the Internet of Things technology to design and implement a home medicine box AI system based on Raspberry PI, which is composed of three parts: medicine cabinet management system, electronic bracelet system and wechat mini program. The medicine cabinet control system utilizes Raspberry PI 4b as the central processing unit, incorporating a timing sensor, voice sensor, and temperature and humidity sensor. The electronic bracelet's control system utilizes STM32 as the primary control board, while the development board incorporates a dual-mode positioning sensor, cardiovascular oxygen sensor, voice module, network module, and six-axis acceleration sensor interconnected with dupont wires. The electronic bracelet control system facilitates functions such as positioning, heart rate acquisition, voice broadcasting, wireless communication, and attitude acquisition. The mobile WeChat mini program enables remote monitoring and control of medicine cabinets and the health status of elderly individuals, providing functions such as temperature and humidity monitoring, timed voice medication reminders, heart rate monitoring, posture monitoring, and positioning. The test results demonstrate the system's stability and reliability, thereby providing robust technical support for home monitoring.

关键词： Temperature sensors Temperature measurement Heart rate Social networking (online) Humidity Message services Control systems Real-time systems Older adults Monitoring

来源：评论

学校读者我要写书评

暂无评论

Digital Twin Ancient Architecture: The Exploration of the Digital Protection of Ancient Architecture

Digital Twin Ancient Architecture: The Exploration of the Di...

引用

作者： Li, Shanglin Lin, Anping School of Computer Science and Artificial Intelligence Xiangnan University Hunan Chenzhou423000 China Hunan Engineering Research Center of Advanced Embedded Computing and Intelligent Medical Systems Hunan Chenzhou China School of Physics and Electronic Electrical Engineering Xiangnan University Hunan Chenzhou China

The digital protection of ancient architectures has achieved important achievements. However, technology development has encountered a bottleneck. The main problem is that the digitization of ancient buildings is limited to building static and isolated three-dimensional models, which cannot meet the increasing professional requirements of digital protection. To solve the above problems, the concept of digital twin ancient architecture (DTAA) is proposed, focusing on the high-dimensional data integration method of the DTAA, as well as the construction method and technical route. Finally, the development and application of digital twin ancient architecture are discussed. The proposed method can bring new ideas to the field of digital protection of ancient architectures. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： 3D modeling

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：