检索结果-内蒙古大学图书馆

18th Annual ieee International Systems Conference (SysCon)

作者： Priyanta, Irfan Fachrudin Krieger, Cedrik Freytag, Julia Teper, Harun Schulte, Philipp Wietfeld, Christian Chen, Jian-Jia Roidl, Moritz TU Dortmund Univ Chair Mat Handling & Warehousing D-44227 Dortmund Germany TU Dortmund Univ Commun Networks Inst D-44227 Dortmund Germany Fraunhofer Inst Mat Flow & Logist D-44227 Dortmund Germany TU Dortmund Univ Design Automat Embedded Syst D-44227 Dortmund Germany

ISBN: (纸本)9798350358810;9798350358803

The rapidly evolving new concepts of the 6G technology raise the challenge of assessing how well 6G-enabled system-of-systems architectures perform in real-life situations beyond theories and simulations. To facilitate this, a new Visual Metaphor layer is presented in this paper to add the visualization feature for a system-of-systems Digital Twin (DT). Visual metaphor plays a crucial role in assisting network engineers to comprehend complex 6G concepts through intuitive visual representations. Powered by an immersive Augmented reality (AR) based on laser projection system, the metaphor framework seamlessly projects the simulated environments into reality and vice versa. Thus, it bridges the gap between theoretical development and practical implementation. Furthermore, it features a plug-andplay solution to accommodate the validation of integrated systems and applications easily. To validate the performance and show the flexibility of the visual metaphor layer, we perform three case studies from the application contexts of teleoperation, platooning, and intralogistics. The results show that the visual metaphor can visualize internal network states, such as communication links, as well as virtual objects and other environmental features. The metaphor can accomplish these diverse and modular tasks while preserving an overall system response time of 55 ms in large-scale scenarios with up to 40 robots.

关键词： System-of-Systems Architecture Digital Twin 6G Testbed Mobile Robots Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Long Short-Term Memory Network Assisted Evolutionary Algorithm for Computationally Expensive Multiobjective Optimization

Long Short-Term Memory Network Assisted Evolutionary Algorit...

引用

2023 ieee symposium Series on Computational Intelligence, SSCI 2023

作者： He, Cheng Li, Hongbin Lin, Jianqing Lu, Zhichao School of Electrical and Electronic Engineering Huazhong University of Science and Technology Wuhan China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China City University Department of Computer Science Hong Kong Hong Kong

ISBN: (纸本)9781665430654

Computationally expensive multiobjective optimization problems (EMOPs) that require significant computational resources are commonly encountered in realworld applications. To address the challenges associated with such problems, using computationally inexpensive surrogate models to approximate objectives has emerged as an effective approach to handle EMOPs. However, the current collaboration between evolutionary algorithms (EAs) and surrogate models is limited, relying on static regression or classification methods that do not fully capture the dynamic evolution process of EAs. This study aims to advance the integration of surrogateassisted multiobjective optimization by incorporating time-series prediction models. The target is to track the evolutionary trajectory of an EA and enhance its search capability. Specifically, long short-term memory (LSTM) networks are embedded into an EA for surrogateassisted optimization (SAO). The role of LSTM networks in SAO is thoroughly investigated through ablation studies. Experimental results on six EMOPs demonstrate the potential of using LSTM networks in SAO. The results are compared with those obtained from four representative surrogateassisted EAs, providing insights into the effectiveness of LSTM-based approaches in addressing EMOPs. © 2023 ieee.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Homecare-Oriented ECG Diagnosis With Large-Scale Deep Neural Network for Continuous Monitoring on embedded Devices

引用

ieee TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2022年 71卷

作者： Ran, Shaolin Yang, Xiaoyun Liu, Ming Zhang, Yong Cheng, Cheng Zhu, Hongling Yuan, Ye Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Intelligent Control & Image Proc Minist Educ Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Tongji Med Coll Tongji Hosp Div CardiolDept Internal Med Wuhan 430030 Peoples R China Wuhan Univ Sci & Technol Sch Informat Sci & Engn Wuhan 430081 Peoples R China

The accurate electrocardiogram (ECG) interpretation is important for several potentially life-threatening cardiac diseases. Recently developed deep learning methods show their ability to distinguish some severe heart diseases. However, since deep neural network requires a high cost on memory consumption and computation, implementation scenarios of these interpretation methods are constrained to nonportable devices. Few commercial portable devices only have heartbeat detection ability, and therefore, only a few simple cardiac diseases can be diagnosed. In this article, to achieve diagnosing a wide range of cardiac diseases and continuous monitoring, a homecare-oriented ECG diagnosis platform is designed based on a large-scale multilabel deep conventional neural network. The accuracy of the proposed neural network model is guaranteed by our constructed large-scale ECG dataset, which is comprised of 206 468 standard 12-lead ECG recordings from 89 488 patients, with respect to 26 types of most common heart rhythms and conduction abnormalities. Meanwhile, targeting lightweight homecare or wearable applications, algorithm-hardware co-optimization is conducted to accelerate the model computation on an embedded platform with field-programmable gate array (FPGA) for continuous monitoring. Channel-level pruning and parameters quantization strategy are employed to optimize the network, and a reconfigurable accelerator hardware architecture is designed to accelerate the convolution computation on FPGA. The final quantified model achieved a promising score of 0.913 & x0025;and 86.7 & x0025;exact match ratio, in which parameters and floating-point operations per second (FLOPs) are significantly penalized compared to the original large-scale model. real-time analysis is performed. Specifically, the average processing time for each ECG record is 2.895 s, and it can be applied to homecare or portable ECG diagnosis devices for continuous monitoring.

关键词： Electrocardiography Computational modeling Diseases Monitoring Heart beat Rhythm real-time systems Deep learning electrocardiogram (ECG) classification embedded platform field-programmable gate array (FPGA) homecare-oriented diagnosis multilabel diagnosis

来源：评论

学校读者我要写书评

暂无评论

Efficient real-time Task-Based Scheduling Algorithms for IoT-Fog-Cloud Architecture 14

Efficient Real-Time Task-Based Scheduling Algorithms for IoT...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Panda, Sanjaya Kumar Dhiman, Akshat Bhuriya, Pushpraj National Institute of Technology Warangal Department of Computer Science and Engineering Telangana Warangal506004 India

ISBN: (纸本)9798350335095

Integrating the Internet of things (IoT), fog computing, and cloud computing (called IoT-fog-cloud) brings a new direction to solve the problems related to real-life applications, such as self-driving cars, health care, autopilot aircraft, traffic management, fire detection and fighting, and many more. Such applications and their associated tasks are time-sensitive and deadline-oriented. However, executing these tasks in the cloud processors, irrespective of the requirements, cause enormous delay and performance degradation. Therefore, these tasks are categorized into hard, firm and soft;and executed on IoT devices or embedded processors, fog processors and cloud processors, respectively, based on their requirements. But, the execution order of these tasks on different processors is challenging and not emphasized in the literature. Recently, a variant of the earliest deadline first (EDF) has been used to determine the execution order. In this paper, we present three different real-time task scheduling algorithms, namely first come, first served (FCFS), EDF shortest job first (EDF-SJF) and FCFS-SJF for IoT-fog-cloud architecture to determine an efficient ordering of the real-time tasks. These algorithms find the assignment test to allot each task to one of the processors. Then each processor uses min-heap to select a task from its queue in order to execute the same. These algorithms are tested using 100 to 1000 tasks (1000 to 10000 tasks) in a uniprocessor (multi-processor) environment and compared using three performance metrics: success ratio, response time and throughput. We found that FCFS-SJF performs better in most cases than other algorithms. © 2023 ieee.

关键词： Cloud computing architecture

来源：评论

学校读者我要写书评

暂无评论

Demonstrating BrightMarkers: Fluorescent Tracking Markers embedded in 3D Printed Objects 36

Demonstrating BrightMarkers: Fluorescent Tracking Markers Em...

引用

36th Annual ACM symposium on User Interface Software and technology (UIST)

作者： Dogan, Mustafa Doga Garcia-Martin, Raul Haertel, Patrick William O'Keefe, Jamison John Sanchez-Reillo, Raul Mueller, Stefanie MIT CSAIL 77 Massachusetts Ave Cambridge MA 02139 USA Univ Carlos III Madrid Madrid Spain

ISBN: (纸本)9798400700965

In this demonstration, we showcase BrightMarker, a fabrication method that uses fuorescent flaments to embed easily trackable markers in 3D printed color objects. By employing an infrared-fuorescent flament that emits light at a wavelength higher than the incident light, our optical detection setup flters out all the noise to only have the markers present in the infrared camera image. The high contrast of the markers allows us to robustly track them when objects are in motion. We also demonstrate a software interface for automatically embedding these markers for the input object geometry, and a hardware module with a high-speed camera that can be attached to existing AR/VR headsets. We developed an image processing pipeline to robustly localize the markers real-time from the captured images. We illustrate applications for fabricating wearables for motion capture, tangible interfaces for AR/VR, and enabling rapid product tracking, as well as privacy-preserving night vision.

关键词： 3D printing digital fabrication fuorescence infrared imaging marker tracking invisible markers object tracking

来源：评论

学校读者我要写书评

暂无评论

An embedded Multi-Die Active Bridge (EMAB) Chip for Rapid-Prototype Programmable 2.5D/3D Packaging technology

An Embedded Multi-Die Active Bridge (EMAB) Chip for Rapid-Pr...

引用

2022 ieee symposium on VLSI technology and Circuits, VLSI technology and Circuits 2022

作者： Zhang, Jie Lu, Wei Huang, Po-Tsang Li, Sih-Han Hung, Tsung-Yi Wu, Shih-Hsien Dai, Ming-Ji Chung, I-Shan Chen, Wen-Chao Wang, Chin-Hung Sheu, Shyh-Shyuan Chen, Hung-Ming Chen, Kuan-Neng Lo, Wei-Chung Wu, Chih-I Industrial Technology Research Institute Electronic and Optoelectronic System Research Laboratories Hsinchu Taiwan National Yang Ming Chiao Tung University Hsinchu Taiwan

ISBN: (纸本)9781665497725

2.5D/3D integration combines multiple dies or chiplets into a single package through a silicon interposer and through-silicon-vias (TSVs). However, the wire routing of redistribution layer (RDL) on an interposer is time-consuming and expensive. Therefore, this work demonstrates the first programmable 2.5D/3D integration by an embedded multi-die active bridge (EMAB) chip for fast 2.5D/3D prototype proof. The EMAB chip is a programmable bridge and realized by a checkboard and super highways to connect I/Os of multiple dies. The control of programmable switches in EMAB is based on the information stored in the one-time programming (OTP) memory. To further improving the data rates of switches in the checkboard and super highway, a forward body-bias control is utilized to reduce the turn-on resistance. The maximum data rate of the super highway is up to 1Gbps and the data rate of the checkboard is 100Mbps through 20 I/O blocks. The proposed programmable advanced package technology is a fast time-to-market and low-cost 2.5D/3D integration solution for various IoT applications. © 2022 ieee.

关键词： Dies

来源：评论

学校读者我要写书评

暂无评论

A study on real-time image processing applications with edge computing support for mobile devices 25

A study on real-time image processing applications with edge...

引用

25th ieee/ACM International symposium on Distributed Simulation and real time applications (DS-RT)

作者： Mattia, Gabriele Proietti Beraldi, Roberto Sapienza Univ Rome Dept Comp Control & Management Engn Antonio Ruber Rome Italy

ISBN: (纸本)9781665433266

Different libraries allow performing computer vision tasks, e.g., object recognition, in almost every mobile device that has a computing capability. In modern smartphones, such tasks are compute-intensive, energy hungry computation running on the GPU or the particular Machine Learning (ML) processor embedded in the device. Task offloading is a strategy adopted to move compute-intensive tasks and hence their energy consumption to external computers, in the edge network or in the cloud. In this paper, we report an experimental study that measure under different mobile computer vision set-ups the energy reduction when the inference of an image processing is moved to an edge node, and the capability to still meet real-time requirements. In particular, our experiments show that offloading the task - in our case real-time object recognition - to a possible next-to-the-user node allows saving about the 70% of battery consumption while maintaining the same frame rate (fps) that local processing can achieve.

关键词： Performance evaluation Computer vision Image processing Image edge detection Machine learning Particle measurements real-time systems

来源：评论

学校读者我要写书评

暂无评论

Data Vertical Decoupling Digital Twin Aggregation technology in the Energy Efficiency Internet of Things in Small and Micro Parks

Data Vertical Decoupling Digital Twin Aggregation Technology...

引用

2022 ieee International Conference on Advances in Electrical Engineering and Computer applications, AEECA 2022

作者： Gu, Jiting Economic and Technical Research Institute of State Grid Zhejiang Electric Power Co. Ltd. Zhejiang310018 China

ISBN: (数字)9781665480901

ISBN: (纸本)9781665480901

Aiming at the energy efficiency Internet of Things problem in small and micro parks, we build a digital model of energy efficiency Internet of Things in small and micro parks based on the digital twin theory. This paper adopts the embedded cyber-physical fusion system (CPS) for seamless integration and synchronization and uses the twin support vector machine algorithm to predict and manage the energy consumption in real-time operation, and feed it back to the model to form a digital twin framework system. We interpret twin synchronization in terms of behavior real-time mapping, state real-time mapping, and action real-time mapping. The operation of the actual industrial big data platform shows that the use of twin machine learning algorithms can improve the efficiency of fault discrimination and the digital twin system can ensure energy efficiency. © 2022 ieee.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Brief Industry Paper: real-time Image Dehazing for Automated Vehicles 44

Brief Industry Paper: Real-Time Image Dehazing for Automated...

引用

44th ieee real-time Systems symposium, RTSS 2023

作者： Tan, Yanjie Zhu, Yifu Huang, Zhaoyang Tan, Huailiang Chang, Wanli Hunan University The College of Computer Science and Electronic Engineering China Hanbowei Microelectronics Technology Co. Ltd China

ISBN: (纸本)9798350328578

Autonomous vehicles at L2 and above are increasingly relying on stereo vision systems, where haze removal is critical to detect obstacles hidden in fog. Existing image dehazing techniques have low processing speed and high resource consumption, restricting their application scope in practice. In this work, we propose a hardware-software co-design solution for haze removal. It fully decouples calculation of the two main parameters, i.e., atmospheric light and transmittance, in the dehazing process. By eliminating the data dependency, parallelism in hardware acceleration is enhanced. Furthermore, in replacement of the conventional global homogeneous atmospheric light computation, we report a chunk-based heterogeneous method to reduce cache overhead. Our approach is implemented on FPGA, compared against five state-of-the-art (SOTA) works for image haze removal. Evaluation using test sets of real-world foggy driving scenarios shows that our object detection accuracy is over 88%, 9.5%-47.4% better than the SOTA works with neural networks (NN) on GPU, and 25.9%-52.2 % better than the SOTA works on FPGA. The processing speed varies with image resolution and our improvement is generally even more at higher resolution, which is 29.7% faster than the fastest SOTA. We have the lowest overall resource consumption, where the bottleneck BRAM usage is reduced by over 70%. The FPGA solution has circuit-level timing determinism at nanosecond, hence suitable for hard real-time applications. © 2023 ieee.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

real-time Locality Measurement and Monitoring on Cycling Activity Among Adolescents 9

Real-Time Locality Measurement and Monitoring on Cycling Act...

引用

9th ieee International Conference on Smart Instrumentation, Measurement and applications, ICSIMA 2023

作者： Maharum, Siti Marwangi Mohamad Ahmad, Izanoordina Ruslan, Nur Farhanah Mohd Mansor, Zuhanis Universiti Kuala Lumpur British Malaysian Institute Advanced Telecommunication Technology Research Cluster Electronics Technology Section Selangor Gombak Malaysia Universiti Kuala Lumpur British Malaysian Institute Intelligent Embedded Research Lab Electronics Technology Section Selangor Gombak Malaysia Universiti Kuala Lumpur British Malaysian Institute Electronics Technology Section Selangor Gombak Malaysia Universiti Kuala Lumpur British Malaysian Institute Advanced Telecommunication Technology Research Cluster Communication Technology Section Selangor Gombak Malaysia

ISBN: (纸本)9798350343380

The illegally modified speed bicycle known as the Basikal Lajak, which is becoming increasingly popular among teenagers in Malaysia, poses a serious threat to road safety. This group is willing to spend money on illegal modifications to the bicycle frame, brakes, sport rims, fork, and handle. They compete in races featuring risky stunts in small groups, preferably going downhill to gain speed and continue cycling dangerously on the public roads, including highways. Therefore, the aim of this work is to develop a proof of concept (PoC) for a real-time locality measurement and monitoring device through hardware and software integration. A vibration sensor is used to detect the cycling activity in which this input is processed by an ESP8266 microcontroller to relay the information on the cyclist's current location that is detected by an installed Global Positioning System (GPS) module to a monitoring application platform called Blynk. A precautionary notification is sent via Blynk application to the cyclist's parents or guardians when their children ride their bikes outside the safe radius set in this location monitoring device. As a result, parents and guardians are able to monitor their children's whereabouts while they are biking for leisure activities with friends or on their way to and from school. Therefore, this PoC development can assist parents and guardians in preventing their children from loitering outside the house such as engaging in immoral modified speed bicycle races that could endanger their safety and other road users. © 2023 ieee.

关键词： Internet of things

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：