arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2001.09636cs.LGstat.ML
收藏

机器学习和深度学习算法在IoT数据分类中的性能分析与比较

Performance Analysis and Comparison of Machine and Deep Learning Algorithms for IoT Data Classification

University of Science and Culture(科学与文化大学);Sharif University of Technology(谢里夫理工大学);Khorasan Institute of Higher Education(霍拉桑高等教育学院)

Meysam Vakili, Mohammad Ghamsari, Masoumeh Rezaei

摘要:

近年来,物联网(IoT)作为一种新兴技术的增长令人难以置信。物联网领域中支持网络的设备数量正在急剧增加,导致电子数据的大量产生。这些数据包含有价值的信息,可用于各个领域,如科学,工业,商业甚至社会生活。要提取和分析这些信息并使物联网系统变得智能,唯一的选择就是进入人工智能(AI)世界,利用机器学习和深度学习技术的力量。本文使用六个物联网相关数据集评估了11种流行的机器和深度学习算法在分类任务中的性能。根据精确度、召回率、f1分数、准确度、执行时间、ROC-AUC分数和混淆矩阵等几个性能评估指标对这些算法进行了比较。还进行了一个具体的实验,以评估所开发的模型的收敛速度。综合实验表明,考虑到所有性能指标,随机森林的表现优于其他机器学习模型,而在深度学习模型中,ANN和CNN取得了更有趣的结果。

英文摘要:

In recent years, the growth of Internet of Things (IoT) as an emerging technology has been unbelievable. The number of networkenabled devices in IoT domains is increasing dramatically, leading to the massive production of electronic data. These data contain valuable information which can be used in various areas, such as science, industry, business and even social life. To extract and analyze this information and make IoT systems smart, the only choice is entering artificial intelligence (AI) world and leveraging the power of machine learning and deep learning techniques. This paper evaluates the performance of 11 popular machine and deep learning algorithms for classification task using six IoT-related datasets. These algorithms are compared according to several performance evaluation metrics including precision, recall, f1-score, accuracy, execution time, ROC-AUC score and confusion matrix. A specific experiment is also conducted to assess the convergence speed of developed models. The comprehensive experiments indicated that, considering all performance metrics, Random Forests performed better than other machine learning models, while among deep learning models, ANN and CNN achieved more interesting results.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑