PDF Publication Title:
Text from PDF Page: 110
Figure 9. Comparison of all prediction methods. We have observed that connectivity times have more structure and less noise than was initially predicted. This can justify the consistent behavior of the different methods and the coherence of the results obtained under the different strategies of validation and test. 6. Conclusion This paper presents results of applying machine learning techniques to forecast the on-off activity state of a big number of IoT mobile devices, using time-series and no-time-series methods. All the results are based on data from real IoT mobile devices. ARIMAX time-series method had the best accuracy (93%), but requires a huge training time. ARIMA and some non-time-series methods (logistic regression and random forest) also shown very good performances. The non-time-series methods require, in general, less training time than the time-series- methods. Considering the higher computational requirements for ARIMAX compared to logistic regression, random forest and ARIMA; the latter methods would be a better choice for a production environment (as they provide similar practical accuracy with less computing time). Independently of the method, the on-off connectivity from IoT devices presents a rich periodic structure, allowing good prediction results, even with short training data. Test results were achieved with a specifically developed cross-validation process, applied to both, time-series and non-time-series methods. From the results obtained, we expect in future works to find additional predictors (covariates) that will probably improve the predicting power of the methods presented. One of these new predictors could be obtained by performing clustering of the signals, trying to use the cluster index as an additional new predictor. The main handicap will be the high Doctoral Thesis: Novel applications of Machine Learning to NTAP - 108PDF Image | Novel applications of Machine Learning to Network Traffic Analysis
PDF Search Title:
Novel applications of Machine Learning to Network Traffic AnalysisOriginal File Name Searched:
456453_1175348.pdfDIY PDF Search: Google It | Yahoo | Bing
Cruise Ship Reviews | Luxury Resort | Jet | Yacht | and Travel Tech More Info
Cruising Review Topics and Articles More Info
Software based on Filemaker for the travel industry More Info
The Burgenstock Resort: Reviews on CruisingReview website... More Info
Resort Reviews: World Class resorts... More Info
The Riffelalp Resort: Reviews on CruisingReview website... More Info
CONTACT TEL: 608-238-6001 Email: greg@cruisingreview.com (Standard Web Page)