Double Deep Autoencoder for Heterogeneous Distributed Clustering

Chen, Chin-Yi; Huang, Jih-Jeng

doi:10.3390/info10040144

Cited by 8 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, Convolutional Neural Networks (CNNs) are suggested for fault diagnosis over multi-channel data from sensors with excellent performance and lower computational cost, requiring homogeneity of the multi-channel data [ 27 ]. In order to overcome this problem, a Double Deep Autoencoder structure is proposed in Chen and Huang [ 28 ] for clustering distributed and heterogeneous datasets. Autoencoders consist of exactly one input and output layer and one or more hidden layers.…”

Section: Literature Reviewmentioning

confidence: 99%

A Deep Learning Model for Predictive Maintenance in Cyber-Physical Production Systems Using LSTM Autoencoders

Bampoula

Siaterlis

Nikolakis

et al. 2021

Sensors

View full text Add to dashboard Cite

Condition monitoring of industrial equipment, combined with machine learning algorithms, may significantly improve maintenance activities on modern cyber-physical production systems. However, data of proper quality and of adequate quantity, modeling both good operational conditions as well as abnormal situations throughout the operational lifecycle, are required. Nevertheless, this is difficult to acquire in a non-destructive approach. In this context, this study investigates an approach to enable a transition from preventive maintenance activities, that are scheduled at predetermined time intervals, into predictive ones. In order to enable such approaches in a cyber-physical production system, a deep learning algorithm is used, allowing for maintenance activities to be planned according to the actual operational status of the machine and not in advance. An autoencoder-based methodology is employed for classifying real-world machine and sensor data, into a set of condition-related labels. Real-world data collected from manufacturing operations are used for training and testing a prototype implementation of Long Short-Term Memory autoencoders for estimating the remaining useful life of the monitored equipment. Finally, the proposed approach is evaluated in a use case related to a steel industry production process.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A Deep Learning Model for Predictive Maintenance in Cyber-Physical Production Systems Using LSTM Autoencoders

Bampoula

Siaterlis

Nikolakis

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Communication is the key for agents to share the information they collect, to coordinate their actions, and to increase interoperation. Interactions between the agents can be requests for information, particular services, or an action to be performed by other agents as well as issues that concern cooperation, coordination, and/or negotiation to arrange interdependent activities [9]. MASs frequently handle complex applications that need distributed problem solving.…”

Section: Introductionmentioning

confidence: 99%

Multi-Agent System Combined With Distributed Data Mining for Mutual Collaboration Classification

et al. 2021

View full text Add to dashboard Cite

Distributed Data Mining (DDM) has been proposed as a means to deal with the analysis of distributed data, where DDM discovers patterns and implements prediction based on multiple distributed data sources. However, DDM faces several problems in terms of autonomy, privacy, performance and implementation. DDM requires homogeneity regarding environment, control, administration and the classification algorithm(s), and such that requirements are too strict and inflexible in many applications. In this paper, we propose the employment of a Multi-Agent System (MAS) to be combined with DDM (MAS-DDM). MAS is a mechanism for creating goal-oriented autonomous agents within shared environments with communication and coordination facilities. We shall show that MAS-DDM is both desirable and beneficial. In MAS-DDM, agents could communicate their beliefs (calculated classification) by covering private and non-sharable data, and other agents decide whether the use of such beliefs in classifying instances and adjusting their prior assumptions about each class of data. In MAS-DDM, we will develop and use a modified Naive Bayesian algorithm because (1) Naive Bayesian has been shown to be the most used algorithm to deal with uncertain data, and (2) to show that even if all agents in MAS-DDM use the same algorithm, MAS-DDM preforms better than DDM approaches with non-communicating processes. Point (2) provide an evidence that the exchange of information between agents helps in increasing the accuracy of the classification task significantly.

show abstract