检索结果-内蒙古大学图书馆

2024 ieee international conference on computing, applications and systems, COMPAS 2024

作者： Hasan, Md. Nahid Akhi, Amatul Bushra Shaha, Sonjoy Prosad Daffodil International University Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798331529765

Capturing the fundamental qualities and properties of the local spinach variation entails doing a thorough investigation. Examining the spinach variant's unique morphology, nutritional makeup, flavor character, and growing environment is part of this procedure. A thorough comprehension of the variant's unique characteristics is attained, making it easier to identify and distinguish it from other spinach variations. DL algorithms may be utilized to determine the freshness of the local spinach variation. One kind of DL model is the convolutional neural network (CNN), which may be educated on datasets including pictures of spinach at various stages of freshness. These models are trained to extract pertinent characteristics, including color, texture, and leaf shape, that are indicative of freshness. After training, the model can quickly and non-destructively evaluate spinach samples by correctly classifying them according to their freshness status. Using deep learning to detect freshness in the local spinach variety, an extensive framework for quality assurance and evaluation is created. This method guarantees that customers obtain a high-quality product by making it easier to identify and characterize the spinach variation and to assess its freshness in real time. © 2024 ieee.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Modeling and Simulation of an Elastic Passive Joint for Non-flipping Jumping Robot

Modeling and Simulation of an Elastic Passive Joint for Non-...

引用

2024 ieee international conference on real-time computing and Robotics, RCAR 2024

作者： Li, Qi Peng, Liang Wu, Zhiyuan Ye, Pengda Zhang, Weitao Xu, Yi Shi, Qing Beijing Institute of Technology Intelligent Robotics Institute School of Mechatronical Engineering Beijing100081 China Beijing Institute of Technology Ministry of Education Key Laboratory of Biomimetic Robots and Systems Beijing100081 China

ISBN: (纸本)9798350372601

To enhance the environmental adaptability of small-sized robots, jumping is commonly employed to achieve high mobility and obstacle-clearing capabilities. However, the prevalent problem of flipping in jumping robots limits their practical applications. Instead of adding extra control mechanisms and actuators, we propose an elastic passive joint (EPJ) to mitigate flipping. By incorporating a revolute joint, a switch, and a spring at the base of the hindleg, the leg can rotate around the body during the take-off phase, with the spring absorbing angular kinetic energy to reduce excessive angular velocity. We conducted dynamic modeling and a series of simulations to optimize the EPJ's position and stiffness. The simulation results indicate that with the EPJ in operation, adjusting the axis position slightly results in a zero-point for angular velocity. Additionally, the optimal spring stiffness of 1566 N/m ensures a non-flipping jump, which decreases the jumping height but improves the jumping distance. © 2024 ieee.

关键词： Kinetic energy

来源：评论

学校读者我要写书评

暂无评论

Special issue on big data computing service and machine learning applications

引用

FUTURE GENERATION COMPUTER systems-THE international JOURNAL OF ESCIENCE 2025年 171卷

作者： Potika, Katerina Eirinaki, Magdalini Vitali, Monica Bernasconi, Anna Fujioka, Hiroyuki San Jose State Univ San Jose CA 95192 USA Politecn Milan Milan Italy Fukuoka Inst Technol Fukuoka Japan

This Special Issue addresses the evolving landscape of big data generated by sensors, devices, and services. The shift from centralized cloud infrastructures to distributed systems that involve cloud, edge, and Internet of Things (IoT) devices requires innovative approaches to managing and analyzing big data. The key challenges include privacy, security, energy efficiency, data quality, and trust. This Special Issue invited researchers to submit innovative solutions covering topics such as: Big Data Analytics and Machine Learning;Integrated, Heterogeneous, and Distributed Infrastructures for Big Data Management;Big Data Platforms and Technologies;real-time Big Data Services and applications;Big Data Security and Privacy Preservation;Big Data Quality and Trust;Trustworthy data sharing;Sustainability and Energy-Efficiency of Big Data;Storage and Computation;Big Data and Analytics for Healthcare;Big Data applications and Experiences. This initiative expands on discussions from the ieee Big Data Service (BDS) 2023 conference held in Athens Greece, reaching a broader audience of researchers.

关键词： Big Data Service Machine learning Big data applications Big Data Platforms and Technologies

来源：评论

学校读者我要写书评

暂无评论

GPU Acceleration of Multi-object Tracking with Motion Vector interpolation and Affine Transformation 34

GPU Acceleration of Multi-object Tracking with Motion Vector...

引用

34th ieee international conference on Application-Specific systems, Architectures and Processors (ASAP)

作者： Kunimoto, Yoshiki Chang, Qiong Yamaguchi, Yoshiki Maruyama, Tsutomu Univ Tsukuba Grad Sch Sci & Technol Tsukuba Japan Tokyo Inst Technol Sch Comp Tokyo Japan Univ Tsukuba Fac Syst & Informat Engn Tsukuba Japan

ISBN: (纸本)9798350346855

In recent studies of object detection and tracking, neural networks have been widely used, and their accuracy has improved. However, its computational complexity is very high and requires the use of high-end GPUs. In order to achieve real-time inference on edge devices, it is necessary to reduce the computational complexity of the network by scaling it down, but this leads to a loss of accuracy. To avoid this loss of accuracy, a method has been proposed in which object detection is performed using a neural network at regular intervals, and in the frames in between, the detected object positions are interpolated using motion prediction. In this research, we propose a method to improve the accuracy of interpolation even when the camera is moving by using an affine transformation used for image stabilization. We also show its real-time computation method on Jetson TX2, one of the lowest power embedded GPUs. The proposed method enables real-time processing of object detection using Yolov5s and tracking of the detected objects at the edge.

关键词： multi object tracking acceleration embedded GPU

来源：评论

学校读者我要写书评

暂无评论

Rigorous Floating-Point to Fixed-Point Quantization of Deep Neural Networks on STM32 Micro-controllers 10

Rigorous Floating-Point to Fixed-Point Quantization of Deep ...

引用

10th international conference on Control, Decision and Information Technologies (CoDIT)

作者： Ben Khalifa, Dorra Martel, Matthieu Univ Toulouse Federat ENAC ISAE SUPAERO ONERA Toulouse France Univ Perpignan Via Domitia LAMPS Lab Perpignan France Numalis Co 265 Ave Etats Languedoc Montpellier France

ISBN: (纸本)9798350373981;9798350373974

Embedding artificial intelligence onto low-power devices is a challenging task that has been partially overcome by recent advances in machine learning and hardware design. Currently, deep neural networks can be deployed on embedded targets to perform various tasks such as speech recognition, object detection or human activity recognition. However, it is still possible to optimize deep neural networks on embedded devices. These optimizations mainly concern energy consumption, memory and real-time constraints, but also easier deployment at the edge. In addition, there is still a need for a better understanding of what can be achieved for different use cases. This work focuses on the quantization and deployment of deep neural networks on low-power 32-bit microcontrollers. In this article, the quantization method used is based on solving an integer optimization problem derived from the neural network model and concerning the accuracy of the computations and results at each point of the network. We evaluate the performance of our quantization method on a collection of neural networks measuring the analysis time and time-to-solution improvement between the floating- and fixed-point networks, considering a typical embedded platform employing a STM32 Nucleo-144 microcontroller.

关键词： embedded systems artificial intelligence constraint generation quantization power consumption micro-controllers

来源：评论

学校读者我要写书评

暂无评论

PEERNet: An End-to-End Profiling Tool for real-time Networked Robotic systems

PEERNet: An End-to-End Profiling Tool for Real-Time Networke...

引用

2024 international conference on Intelligent Robots and systems

作者： Narayanan, Aditya Kasibhatla, Pranav Choi, Minkyu Li, Po-han Zhao, Ruihan Chinchali, Sandeep Univ Texas Austin Austin TX 78712 USA

ISBN: (纸本)9798350377712;9798350377705

Networked robotic systems balance compute, power, and latency constraints in applications such as self-driving vehicles, drone swarms, and teleoperated surgery. A core problem in this domain is deciding when to offload a computationally expensive task to the cloud, a remote server, at the cost of communication latency. Task offloading algorithms often rely on precise knowledge of system-specific performance metrics, such as sensor data rates, network bandwidth, and machine learning model latency. While these metrics can be modeled during system design, uncertainties in connection quality, server load, and hardware conditions introduce real-time performance variations, hindering overall performance. We introduce PEERNet, an end-to-end and real-time profiling tool for cloud robotics. PEERNet enables performance monitoring on heterogeneous hardware through targeted yet adaptive profiling of system components such as sensors, networks, deep-learning pipelines, and devices. We showcase PEERNet's capabilities through networked robotics tasks, such as image-based teleoperation of a Franka Emika Panda arm and querying vision language models using an Nvidia Jetson Orin. PEERNet reveals non-intuitive behavior in robotic systems, such as asymmetric network transmission and bimodal language model output. Our evaluation underscores the effectiveness and importance of benchmarking in networked robotics, demonstrating PEERNet's adaptability. Our code is open-source and available at ***/UTAustin-SwarmLab/PEERNet.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Context switch reduction for delay tolerant activities 9

Context switch reduction for delay tolerant activities

引用

9th ieee international conference on Electronics, computing and Communication Technologies, CONECCT 2023

作者： Sudarshan Rao, B. Vrind, Tushar Venkata Raju, I. Samsung Semiconductor India Research Bangalore India

ISBN: (纸本)9798350334395

Cyber-Physical systems connect physical infrastructure and things to the internet and to one another by integrating sensing, computation, control, and networking. One of the main optimization objectives for the effective operation of such systems is latency reduction. The key components of Cyber Physical systems, RTOS (real time Operating systems), contribute significantly to the system's latency. Different scheduling strategies may be used by a real-time operating system to schedule the system's task efficiently. One such approach used frequently in contemporary embedded computing is preemptive priority scheduling. The executing component in this sort of scheduling is susceptible to preemption at any time due to the execution of an OS API or the scheduler's inter-core task assignment. Unaffected by whether the execution context is going to end or self-relinquish, a preemptive scheduler preempts a task. The kernel lacks the ability to detect when a job is about to self-relinquish or when an execution context is ready to finish. The number of context transitions in the system rises as a result of such preemption. A context switch is an expensive process from the operating system's perspective since it could involve overheads such as MMU table updates, register store restores, bookkeeping and cache reload overhead. The specifics of how to lessen such context changes are covered in this study. The introduction of threshold is discussed in order to stop the kernel from preempting a job that is about to finish or self-relinquish. Additionally, the multi-core instance illustrates how context transitions can be minimised by implementing unique preemption techniques. Our internal simulation test setting demonstrated that a novel preemption method might reduce processing time for the entire system by 2.3 percent. © 2023 ieee.

关键词： embedded systems

来源：评论

学校读者我要写书评

暂无评论

QR-Based Efficient Waste Management System 4

QR-Based Efficient Waste Management System

引用

4th international conference on Ubiquitous computing and Intelligent Information systems, ICUIS 2024

作者： Anuratha, K. Akshaya, S. Rajaselvi, C. Akshaya, M. Sri Sairam Institute of Technology Department of Information Technology Tamil Nadu Chennai India

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529635

This research study provides an overview of the QR-based Trash Management System, which emerges as a technology- driven process that aims at optimizing processes within the waste management process within urban environments. Traditional waste management systems usually fail on proper tracking, timely collections, and effective communication. Implementation of Quick Response code technology enabled this system to meet its challenges toward an organized and sustainable waste management framework. The basis for this system is in the integration of QR codes and mobile applications, which will enhance segregation practices, community engagement, and so forth. This QR-based Waste Management System is built to increase operational processes, sustainability initiatives, lower costs, and help towards making the cities cleaner and healthier. This scalable solution empowers communities to take active roles in waste management and hence forms a very critical innovation for metropolitan areas. © 2024 ieee.

关键词： Waste management Technological innovation Urban areas QR codes Ubiquitous computing real-time systems Mobile applications Waste disposal Sustainable development Information systems

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Driven Anomaly Detection: A Comprehensive Model for Digital Security 4

Machine Learning-Driven Anomaly Detection: A Comprehensive M...

引用

4th international conference on Ubiquitous computing and Intelligent Information systems, ICUIS 2024

作者： Samarth, S. Sumukha Raghavan, M. Santhosh, T. Kowligi, Sahana J. Pooja, M.R. Department of Computer Science and Engineering Vidyavardhaka College of Engineering Mysuru India

ISBN: (纸本)9798331529635

This research study proposes a novel approach for behavioral tracking and anomaly detection in digital systems by using AI-driven models, particularly for applications in signal processing and digital computer environments. The proposed AI model combines techniques of behavioral tracking, aiming at identifying deviations in the operations of the system, while enhanced monitoring and anomaly identification are the focus. This methodology captures subtle deviations in user behavior and system signals to enhance real-time security and system integrity, thereby reducing the likelihood of unauthorized access and system misuse. © 2024 ieee.

关键词： AI Models Anomaly Detection Behavioral Tracking Digital systems

来源：评论

学校读者我要写书评

暂无评论

Integration of C2000 Microcontrollers with MATLAB Simulink embedded Coder: A real-time Control Application 7

Integration of C2000 Microcontrollers with MATLAB Simulink E...

引用

7th international conference on Electrical Engineering and Green Energy, CEEGE 2024

作者： Rahman, Mohammad Abidur Abushaiba, Ali A. Elrajoubi, Akrem M. University of Arkansas School of Engineering & Engineering Technology Little RockAR United States University of Misurata College of Engineering Misurata Libya

ISBN: (纸本)9798350350623

C2000 TM 32-bit microcontrollers excel in real-time control, optimizing closed-loop performance for various applications such as industrial motor drives, solar inverters, digital power systems, and sensing. The lineup offers Premium and Entry-performance microcontroller units (MCUs). This paper explores the integration process of Texas Instruments text TM (TI) C2000 microcontroller units with MATLAB and Simulink using Code Composer Studio (CCS) and embedded Coder (EC) support package for C2000 microcontrollers. It shows how to set up Simulink to program the Digital Signal Processor (DSP) microcontroller unit and the communication between the host computer and the C2000 target hardware using the LAUNCHXLF28379D launchpad. Basic functions such as Pulse Width Modulation, Analog Digital Conversion, and Proportional-Integral controllers are explained. Finally, a closed-loop control model for a C2000 Digital Power Buck Converter BoosterPack is implemented, showcasing the effective integration of TI C2000 microcontroller units with MATLAB, Simulink, and related tools for real-time control in the power system context. © 2024 ieee.

关键词： Microcontrollers

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：