Adding adaptive intelligence to sensor systems with MASS

Frederickson, Christopher J.; Gracie, Thomas; Portley, Steven; Moore, Michael; Cahall, Daniel E.; Polikar, Robi

doi:10.1109/sas.2017.7894084

Cited by 9 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another framework addressing incremental drift in extreme verification latency has been presented in [9], referred to as Modular Adaptive Sensor System. Here, training data is initially grouped by a clustering algorithm.…”

Section: Related Workmentioning

confidence: 99%

Supporting sensor orchestration in non-stationary environments

Holst

Lohweg

2018

Proceedings of the 15th ACM International Conference on Computing Frontiers

View full text Add to dashboard Cite

The aim of sensor orchestration is to design and organise multisensor systems both to reduce manual design efforts and to facilitate complex sensor systems. A sensor orchestration is required to adapt to non-stationary environments, even if it is applied in streaming data scenarios where labelled data are scarce or not available. Without labels in dynamic environments, it is challenging to determine not only the accuracy of a classifier but also its reliability. This contribution proposes monitoring algorithms intended to support sensor orchestration in classification tasks in non-stationary environments. Proposed measures regard the relevance of features, the separability of classes, and the classifier's reliability. The proposed monitoring algorithms are evaluated regarding their applicability in the scope of a publicly available and synthetically created collection of datasets. It is shown that the approach (i) is able to distinguish relevant from irrelevant features, (ii) measures class separability as class representations drift through feature space, and (iii) marks a classifier as unreliable if errors in the drift-adaptation occur.

show abstract

Section: Related Workmentioning

confidence: 99%

Supporting sensor orchestration in non-stationary environments

Holst

Lohweg

2018

Proceedings of the 15th ACM International Conference on Computing Frontiers

View full text Add to dashboard Cite

show abstract

“…This change could be triggered by specific changes in behavior, such as degradation, extremely common in many industrial environments and helpful for early failure detection. It is also useful for detecting sensor failure and degradation [26]. As data streams and the process dynamics are an important consideration for the industry, the work in this paper is driven by the need for GMM-based probabilistic clustering, which is capable of dealing with the dynamic evolution and drifts of the industrial processes, providing a new analytics tool for IIoT.…”

mentioning

confidence: 99%

Clustering of Data Streams With Dynamic Gaussian Mixture Models: An IoT Application in Industrial Processes

Díaz-Rozo

Bielza

Larrañaga

2018

IEEE Internet Things J.

View full text Add to dashboard Cite

In industrial Internet of Things applications with sensors sending dynamic process data at high speed, producing actionable insights at the right time is challenging. A key problem concerns processing a large amount of data, while the underlying dynamic phenomena related to the machine is possibly evolving over time due to factors, such as degradation. This makes any actionable model become obsolete and necessary to be updated. To cope with this problem, in this paper we propose a new unsupervised learning algorithm based on Gaussian mixture models called Gaussian-based dynamic probabilistic clustering (GDPC) mainly based on integrating and adapting three well known algorithms for use in dynamic scenarios: the expectationmaximization (EM) algorithm to estimate the model parameters and the Page-Hinkley test and Chernoff bound to detect concept drifts. Unlike other unsupervised methods, the model induced by the GDPC provides the membership probabilities of each instance to each cluster. This allows to determine, through a Brier score analysis, the robustness of the instance assignment and its evolution each time a concept drift is detected. Also, the algorithm works with very little data and significantly less computing power being able to decide whether (and when) to change the model. The algorithm is tested using synthetic data and data streams from an industrial testbed, where different operational states are automatically identified, giving good results in terms of classification accuracy, sensitivity, and specificity. I. INTRODUCTION N OWADAYS, Internet of Things (IoT) has opened a wide range of applications, where sensor data and other contextual data combined with computational models are able to produce actionable insights, which can be used as new control or monitoring systems and even new

show abstract