Scheduling IDK classifiers with arbitrary dependences to minimize the expected time to successful classification
Scheduling IDK classifiers with arbitrary dependences to minimize the expected time to successful classification
复制标题
调度具有任意依赖性的 IDK 分类器，以最大限度地缩短成功分类的预期时间
DOI：
10.1007/s11241-023-09395-0
复制
发表时间：
2023
影响因子：
1.3
通讯作者：
Hu, Yigong
中科院分区：
文献类型：
--
作者：
Abdelzaher, Tarek;Agrawal, Kunal;Baruah, Sanjoy;Burns, Alan;Davis, Robert I.;Guo, Zhishan;Hu, Yigong
本文介绍并评估了在基于分类的机器感知问题中权衡准确性和总体执行时间的一般结构-即广义IDK分类器级联。其目的是选择最优的分类器序列，以最小化实现成功分类所需的预期（即平均）执行时间，同时受质量约束，以及可选的最坏情况执行时间的延迟约束。IDK分类器是一种软件组件，它试图将提供给它的每个输入分类为一组固定的类之一，如果无法以所需的置信度这样做，则返回“我不知道”（IDK）。对于相同的分类问题，可以使用几个不同的IDK分类器的集合，在有效性（即分类成功的概率）和时效性（即执行持续时间）之间提供不同的权衡。定义了一个表示这些特征的模型，并提出了一种确定给定IDK分类器集合的模型参数值的方法。为将IDK分类器按顺序排列到IDK级联中开发了最优算法，这样，成功对输入进行分类的预期持续时间被最小化，可选地服从对IDK级联的最坏情况总体执行持续时间的延迟约束。整个方法应用于两个现实世界的案例研究。与之前的工作相比，本文开发的方法迎合了不同IDK分类器成功分类概率之间的任意依赖关系。考虑到单处理器和多处理器，开发了有效的实用解决方案。
This paper introduces and evaluates a general construct for trading off accuracy and overall execution duration in classification-based machine perception problems—namely, thegeneralized IDK classifier cascade. The aim is to select the optimal sequence of classifiers required to minimize the expected (i.e. average) execution duration needed to achieve successful classification, subject to a constraint on quality, and optionally a latency constraint on the worst-case execution duration. An IDK classifier is a software component that attempts to categorize each input provided to it into one of a fixed set of classes, returning “I Don’t Know” (IDK) if it is unable to do so with the required level of confidence. An ensemble of several different IDK classifiers may be available for the same classification problem, offering different trade-offs between effectiveness (i.e. the probability of successful classification) and timeliness (i.e. execution duration). A model for representing such characteristics is defined, and a method is proposed for determining the values of the model parameters for a given ensemble of IDK classifiers. Optimal algorithms are developed for sequentially ordering IDK classifiers into an IDK cascade, such that the expected duration to successfully classify an input is minimized, optionally subject to a latency constraint on the worst-case overall execution duration of the IDK cascade. The entire methodology is applied to two real-world case studies. In contrast to prior work, the methodology developed in this paper caters for arbitrary dependences between the probabilities of successful classification for different IDK classifiers. Effective practical solutions are developed considering both single and multiple processors.
登录
查看更多内容
IDK-Cascades 的优化合成
DOI：
10.1145/3453417.3453425
发表时间：
2021
期刊：
Proceedings of the 29th International Conference on Real-Time and Network Systems (RTNS
影响因子：
--
作者：
Baruah, Sanjoy;Burns, Alan;Wu, Yue
通讯作者：
Wu, Yue
具有模糊数据的应用程序的分类方案
DOI：
10.1109/ijcnn.2000.859412
发表时间：
2000
期刊：
Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium
影响因子：
--
作者：
T. Trappenberg;A. Back
通讯作者：
A. Back
具有多路径神经网络的实时物体检测系统
DOI：
10.1109/rtas48715.2020.000-8
发表时间：
2020
期刊：
2020 IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS)
影响因子：
--
作者：
Seonyeong Heo;Sungjun Cho;Youngsok Kim;Hanjun Kim
通讯作者：
Hanjun Kim
探索图像大小调整以优化基于关键性的机器感知
DOI：
10.1109/rtcsa52859.2021.00027
发表时间：
2021
期刊：
2021 IEEE 27th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA)
影响因子：
--
作者：
Yigong Hu;Shengzhong Liu;T. Abdelzaher;Maggie B. Wigness;P. David
通讯作者：
P. David
DOI：
10.1109/rtcsa50079.2020.9203676
发表时间：
2020-08
期刊：
2020 IEEE 26th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA)
影响因子：
--
作者：
Shuochao Yao;Yifan Hao;Yiran Zhao;Huajie Shao;Dongxin Liu;Shengzhong Liu;Tianshi Wang;Jinyang Li;T. Abdelzaher
通讯作者：
Shuochao Yao;Yifan Hao;Yiran Zhao;Huajie Shao;Dongxin Liu;Shengzhong Liu;Tianshi Wang;Jinyang Li;T. Abdelzaher