Feature selection using non-binary decision trees applied to condition monitoring

Ferreira, Bruno; Silva, Rui; Pereira, Vítor

doi:10.1109/etfa.2017.8247642

Cited by 13 publications

(8 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The features that are traditionally used for CM (RMS, crest factor, kurtosis, …, in the time domain; amplitude of power spectra, band power, envelope, …, in the frequency domain) [4,12,13,14,19,20,21,22,23,24,25], and that are considered in this work, are useful in most applications to maintain the relevant information about the process or tool conditions [4].…”

Section: Methodsmentioning

confidence: 99%

“…Trends of the features calculated on the basis of Tracking Deviation (TD), at different jload [22]. Repeatability is shown as error bars.…”

Section: Figurementioning

confidence: 99%

“…A first selection criterion of the features based on their repeatability was proposed [17]. The debate about these topics is very active, with reference to both general approach and specific applications, like, for instance, those related to tool CM in production machine [19,20,21,22] or computer vision applications [23]. How much these methods are of general validity is still an open point for CM of mechatronic systems.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Physical and Metrological Approach for Feature’s Definition and Selection in Condition Monitoring

D’Emilia

Gaspari

Natale

2019

Sensors

View full text Add to dashboard Cite

In this paper, a methodology is described aiming at emphasizing physical and metrological criteria in feature selection for condition monitoring of a real scale mechatronic system. The device is used for packaging applications according to the movements of its end effector, driven by a couple of brushless servomotors and a kinematic mechanical linkage. The approach is hybrid, meaning that the starting feature set is built with reference to both experimental data from different sensors and to the indication of a simplified kinematic and dynamic model of the mechanical linkage itself. A critical comparison and mixing of theoretical and experimental data, based also on a physical interpretation of differences, suggests some more features, with respect to the classical ones, of hybrid type, which could be mostly correlated to the effects of statuses and defects of the system to be identified. The whole procedure is step by step validated, in order to evaluate the variability of features, throughout the whole procedure. The variability is analyzed depending on the actions that are realized in order to define, select, and use the proposed features for data processing by advanced algorithms, like the most typically used classifiers and artificial neural networks. A comparison with the state-of-the-art automatic feature’s selection procedure is also presented. Experimental results show that the proposed methodology is able to classify with high accuracy many statuses of the mechatronic system, which are only slightly different as for set-up settings and/or mechanical wear and lubrication conditions of mechanical parts of the mechatronic system. Issues to be pursued to a more effective generalization of the method are also discussed.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Trends of the features calculated on the basis of Tracking Deviation (TD), at different jload [22]. Repeatability is shown as error bars.…”

Section: Figurementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Physical and Metrological Approach for Feature’s Definition and Selection in Condition Monitoring

D’Emilia

Gaspari

Natale

2019

Sensors

View full text Add to dashboard Cite

show abstract

“…A classification method belongs to supervised learning category, and it is applicable in cases where the overall aim is to accurately assign a datapoint to a class [78][79][80]. There is a broad range of classification methods as presented in Table 2, in the scope of SD, that clearly shows the impact and potential use of these techniques in conjunction with EO data.…”

Section: Classificationmentioning

confidence: 99%

“…Dimension reduction, similar to clustering method, belongs to the unsupervised learning category and typically follow two main approaches: Feature Selection (FS), applicable when there is the necessity to select fewer characteristics [111,112]; and Feature Extraction, when the information needs to be synthesised through transformation. The aim is to create a small set of features covering much of the details in the initial dataset [79,113,114]. Then, these features/characteristics can be fed into other algorithms or otherwise used as an end result [78].…”

Section: Dimension Reductionmentioning

confidence: 99%

Monitoring sustainable development by means of earth observation data and machine learning: a review

2020

View full text Add to dashboard Cite

This paper presents and explores the different Earth Observation approaches and their contribution to the achievement of United Nations Sustainable Development Goals. A review on the Sustainable Development concept and its goals is presented followed by Earth Observation approaches relevant to this field, giving special attention to the contribution of Machine Learning methods and algorithms as well as their potential and capabilities to support the achievement of Sustainable Development Goals. Overall, it is observed that Earth Observation plays a key role in monitoring the Sustainable Development Goals given its cost-effectiveness pertaining to data acquisition on all scales and information richness. Despite the success of Machine Learning upon Earth Observation data analysis, it is observed that performance is heavily dependent on the ability to extract and synthesise characteristics from data. Hence, a deeper and effective analysis of the available data is required to identify the strongest features and, hence, the key factors pertaining to Sustainable Development. Overall, this research provides a deeper understanding on the relation between Sustainable Development, Earth Observation and Machine Learning, and how these can support the Sustainable Development of countries and the means to find their correlations. In pursuing the Sustainable Development Goals, given the relevance and growing amount of data generated through Earth Observation, it is concluded that there is an increased need for new methods and techniques strongly suggesting the use of new Machine Learning techniques.

show abstract

A framework for designing data pipelines for manufacturing systems

Oleghe¹,

Salonitis

2020

Procedia CIRP

View full text Add to dashboard Cite

Feature selection using non-binary decision trees applied to condition monitoring

Cited by 13 publications

References 27 publications

Physical and Metrological Approach for Feature’s Definition and Selection in Condition Monitoring

Physical and Metrological Approach for Feature’s Definition and Selection in Condition Monitoring

Monitoring sustainable development by means of earth observation data and machine learning: a review

A framework for designing data pipelines for manufacturing systems

Contact Info

Product

Resources

About