Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
Simplicity is Best: Addressing the Computational Cost of Machine Learning Classifiers in Constrained Edge Devices
Gómez-Carmona O., Gómez-Carmona O., Casado-Mansilla D., Casado-Mansilla D., López-de-Ipiña D., López-de-Ipiña D., García-Zubia J., García-Zubia J.  Proceedings of the 9th International Conference on the Internet of Things (Proceedings of the 9th International Conference on the Internet of Things, Bilbao, Spain, Oct 22-25, 2019)1-8.2019.Type:Proceedings
Date Reviewed: Jul 7 2021

Implementing data processing toward the edge of the Internet of Things (IoT) is an important requirement in order to produce real-time feedback according to some decision-based approach.

The authors aim to experimentally prove that “simplicity is best.” Their experiment-based paper considers three platforms (Notebook i7-7500U, Raspberry PI 3 model B+, Raspberry Zero W) and seven machine learning algorithms for classification (logistic regression, random forest, k-nearest neighbors, naive Bayes, linear support vector machine, multilayer perceptron, and decision trees). They use the Scikit-learn Python library and a dataset for ADL recognition with wrist-worn accelerometer measurements with 839 instances and 14 classes (available on the UCI repository). All results were obtained by training with over 80 percent of data along a five-step cross-validation process. The applied methodology deals with the signals generated by a three-axial inertial sensor (X,Y,Z). After preprocessing, for every component of the signal, five segments are considered. Nine features are computed for each segment, as well for the entire sequence: min, max, average, median, kurtosis, skewness, standard deviation, variance, and mean absolute deviation. Dimension reduction processes, based on chi scores, are used to select first the top ten features and then the top three features.

The reported experiments address classification accuracy and computational cost. It is shown that: 1) it is feasible to implement machine learning projects in the Raspberry Pi and Raspberry Zero platforms; 2) the feature selection step is important for complexity reduction; and 3) the proposed strategy assures detection rates over 90 percent, even for a small number of top features, while the processing time can be reduced by four times.

Finally, I appreciate that this conference paper is well structured. The presentation invites readers to discover how IoT-based applications may benefit from simplicity.

Reviewer:  G. Albeanu Review #: CR147302 (2111-0276)
Bookmark and Share
  Featured Reviewer  
 
Learning (I.2.6 )
 
 
Real-Time And Embedded Systems (C.3 ... )
 
 
General (I.0 )
 
 
General (C.0 )
 
Would you recommend this review?
yes
no
Other reviews under "Learning": Date
Learning in parallel networks: simulating learning in a probabilistic system
Hinton G. (ed) BYTE 10(4): 265-273, 1985. Type: Article
Nov 1 1985
Macro-operators: a weak method for learning
Korf R. Artificial Intelligence 26(1): 35-77, 1985. Type: Article
Feb 1 1986
Inferring (mal) rules from pupils’ protocols
Sleeman D.  Progress in artificial intelligence (, Orsay, France,391985. Type: Proceedings
Dec 1 1985
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy