A time series clustering approach for Building Automation and Control Systems

Bode, Gerrit; Schreiber, Thomas; Baranski, Marc; Müller, Dirk

doi:10.1016/j.apenergy.2019.01.196

Cited by 33 publications

(18 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the most tackling part in the machine learning and deep learning projects is the feature listing and extraction that would require advanced techniques to be implemented in order go over such issue (Najafabadi et al, 2015;Bode et al, 2019), many approaches where followed through the literature in order to minimize the time required to handle such type of data curation on IoT streams and data in motion. Banerjee et al (2018) conduct a very rich survey on people involved in IoT analytic application development in order to identify the analysis pain areas related to IoT analytic tasks, the survey analysis shows that, domain knowledge and technical knowledge are required at the maximum limit when it comes to feature listing, selection and reduction, authors continue in identifying the steps involved in IoT applications processing and analytic, finally they propose and test a feature recommendation architecture to tackle the IoT analytic related to feature engineering.…”

Section: Feature Engineeringmentioning

confidence: 99%

“…Supervised Machine algorithms require labeled data set, but when it comes for data on streams curation in terms of features extraction and selection as a preprocessing step for the automated machine learning, unsupervised machine learning techniques show better results in improving the classification process for the time series data. Bode et al (2019) shows a detailed comparison for the accuracies gained for some selective unsupervised machine learning techniques in regards to unsupervised feature extraction and clustering against the normal supervised approaches for the statistical feature selection Fig. 3.…”

Section: Feature Engineeringmentioning

confidence: 99%

“…(Sowe and Zettsu, 2013) Sowe and Zettsu, 2013) IoT Data and 1. Minimizing the time of features listing, extraction, selection and reduction using machine Najafabadi et al (2015;Streams learning and deep learning (Najafabadi et al, 2015;Bode et al, 2019;Banerjee et al, Bode et al, 2019;Engineering 2018) Banerjee et al, 2018). .…”

Section: Comparative Studymentioning

confidence: 99%

“…Miller et al (2017;Machine Learning 2. Phenomena that evolve over time: Second-Order Autoregressive Time-Series Modeling, Fujisawa et al, 2016; Functional Data analysis and Ordinary Differential Equation (ODE) (Miller et al, 2017;Bode et al, 2019;Theodore, 2003).…”

Section: Comparative Studymentioning

confidence: 99%

“…6. Classification process for time series data: Unsupervised learning (Bode et al, 2019). IoT Data and Streams 1.…”

Section: Comparative Studymentioning

confidence: 99%

See 4 more Smart Citations

Data Streams Curation for Better Machine Learning Functionality and Result to Serve IoT and other Applications: A Survey

Salah¹,

Al-Omari²,

Alwidian³

et al. 2019

Journal of Computer Science

View full text Add to dashboard Cite

Data Curation on data streams is effective in operating and reducing costs of BIG DATA analytic. Basically, analytic preparation requires data curation of available heterogeneous data sets available in big data clusters and such analytic process becomes harder when it comes to the concept of conducting the curation process on Data-on-Motion, in order to come at actionable insights and valuable analytic on a real-time basis including the Machine Learning further analytic and processing. In our paper, we identified and surveyed the different issues and challenges among different areas that are related to the big data. In addition to investigate, the most common techniques and methods followed through the implementations including Streams Curation, the Machine Learning Different Algorithms used in such implementations and the Feature Engineering different techniques that can be considered as curation pre-processing paradigm for data streams analytic. Furthermore, our paper shows the different application areas were data curation concept plays a critical role. Finally, we draw the map between the techniques and methods that are related to the data curation field to emphasize on its main critical role among Business, Retails, Culture, Arts, Health, Medicine, Social Media, Wireless Sensor Networks, Natural Language Processing (NLP) and Automated Feature Engineering (FE). On other hand, we identified the different issues and challenges among different areas including the IoT and Media Streams Curation to help the scholars in this region accordingly.

show abstract

Section: Feature Engineeringmentioning

confidence: 99%

Section: Feature Engineeringmentioning

confidence: 99%

Section: Comparative Studymentioning

confidence: 99%

Section: Comparative Studymentioning

confidence: 99%

“…6. Classification process for time series data: Unsupervised learning (Bode et al, 2019). IoT Data and Streams 1.…”

Section: Comparative Studymentioning

confidence: 99%

See 3 more Smart Citations

Data Streams Curation for Better Machine Learning Functionality and Result to Serve IoT and other Applications: A Survey

Salah¹,

Al-Omari²,

Alwidian³

et al. 2019

Journal of Computer Science

View full text Add to dashboard Cite

show abstract

A Preliminary Study on Multivariate Time Series Clustering

Váquez

Villar

Sedano

et al. 2019

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

A Proof of Concept in Multivariate Time Series Clustering Using Recurrent Neural Networks and SP-Lines

Vázquez

Villar

Sedano

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Big Data and the IoT explosion has made clustering multivariate Time Series (TS) one of the most effervescent research fields. From Bio-informatics to Business and Management, multivariate TS are becoming more and more interesting as they allow to match events the co-occur in time but that is hardly noticeable. This study represents a step forward in our research. We firstly made use of Recurrent Neural Networks and transfer learning to analyze each example, measuring similarities between variables. All the results are finally aggregated to create an adjacency matrix that allows extracting the groups. In this second approach, splines are introduced to smooth the TS before modeling; also, this step avoid to learn from data with high variation or with noise. In the experiments, the two solutions are compared suing the same proof-of-concept experimentation.

show abstract

A time series clustering approach for Building Automation and Control Systems

Cited by 33 publications

References 21 publications

Data Streams Curation for Better Machine Learning Functionality and Result to Serve IoT and other Applications: A Survey

Data Streams Curation for Better Machine Learning Functionality and Result to Serve IoT and other Applications: A Survey

A Preliminary Study on Multivariate Time Series Clustering

A Proof of Concept in Multivariate Time Series Clustering Using Recurrent Neural Networks and SP-Lines

Contact Info

Product

Resources

About