Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

PD Controller: Design01:26

PD Controller: Design

227
In automotive engineering, car suspension systems often employ Proportional Derivative (PD) controllers to enhance performance. PD controllers are utilized to adjust the damping force in response to road conditions. A controller, acting as an amplifier with a constant gain, demonstrates proportional control, with output directly mirroring input.
Designing a continuous-data controller requires selecting and linking components like adders and integrators, which are fundamental in Proportional,...
227

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same authorSame journal

Narrow Spectrum Software Testing Addressing Complexity and Trust.

Computer·2026
Same author

It Doesn't Have to Be Like This: Cybersecurity Vulnerability Trends.

IT professional·2020
Same journal

Input Space Coverage Matters.

Computer·2025
Same journal

Using Smart Homes to Detect and Analyze Health Events.

Computer·2025
Same journal

A Trusted Federated System to Share Granular Data Among Disparate Database Resources.

Computer·2024
Same journal

Combinatorial Methods in Security Testing.

Computer·2024
Same journal

Cybertrust in the IoT Age.

Computer·2024
查看所有相关文章

相关实验视频

Updated: Jul 1, 2025

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research
07:15

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Published on: December 18, 2020

4.5K

从神经元覆盖到转向角度:有效测试自动驾驶汽车

Jack Toohey1, M S Raunak2, Dave Binkley1

  • 1Loyola University Maryland.

Computer
|March 7, 2024
PubMed
概括
此摘要是机器生成的。

本研究探讨了用于测试自动驾驶汽车深度神经网络 (DNN) 的现实的图像转换. 研究结果揭示了这些转变如何影响神经元覆盖和模型输出,这对于提高DNN可靠性和信任至关重要.

更多相关视频

An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces
10:51

An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces

Published on: March 10, 2011

13.7K
Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.3K

相关实验视频

Last Updated: Jul 1, 2025

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research
07:15

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Published on: December 18, 2020

4.5K
An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces
10:51

An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces

Published on: March 10, 2011

13.7K
Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.3K

科学领域:

  • 人工智能的人工智能
  • 计算机视觉 计算机视觉
  • 软件工程 软件工程 软件工程

背景情况:

  • 自动驾驶汽车中的深度神经网络 (DNN) 作为复杂的"黑子"运作,需要确保其可靠性和可信度的方法.
  • 传统的软件测试技术正在适应DNN,神经元覆盖率被提议作为评估测试套件在检测故障中的有效性的关键指标.

研究的目的:

  • 调查现实的图像转换对自动驾驶汽车DNN的神经元覆盖率的影响.
  • 评估这些转变如何影响训练自动驾驶汽车DNN的输出.
  • 为提高DNN模型的可靠性和信任度的方法做出贡献.

主要方法:

  • 利用现实的图像转换来生成用于测试的新型数据集.
  • 将这些转换应用于训练有素的自动驾驶汽车DNN.
  • 测量了由此产生的神经元覆盖范围,并分析了模型输出中的变化.

主要成果:

  • 逼真的图像转换显著改变神经元覆盖度量.
  • 选择的转换显然会影响DNN的分类或预测输出.
  • 神经元覆盖水平因应用的特定图像转换而有所不同.

结论:

  • 现实的转换对于发现自动驾驶汽车DNN中的潜在故障是有价值的.
  • 该研究提供了关于DNN对输入变化的敏感性的见解.
  • 结果支持使用基于输入转换的测试来提高DNN的稳定性和可靠性.