ABSTRACT
A wide range of applications based on sequential data, named time series, have become increasingly popular in recent years, mainly those based on the Internet of Things (IoT). Several different machine learning algorithms exploit the patterns extracted from sequential data to support multiple tasks. However, this data can suffer from unreliable readings that can lead to low accuracy models due to the low-quality training sets available. Detecting the change point between high representative segments is an important ally to find and thread biased subsequences. By constructing a framework based on the Augmented Dickey-Fuller (ADF) test for data stationarity, two proposals to automatically segment subsequences in a time series were developed. The former proposal, called Change Detector segmentation, relies on change detection methods of data stream mining. The latter, called ADF-based segmentation, is constructed on a new change detector derived from the ADF test only. Experiments over real-file IoT databases and benchmarks showed the improvement provided by our proposals for prediction tasks with traditional Autoregressive integrated moving average (ARIMA) and Deep Learning (Long short-term memory and Temporal Convolutional Networks) methods. Results obtained by the Long short-term memory predictive model reduced the relative prediction error from 1 to 0.67, compared to time series without segmentation.
Subject(s)
Machine Learning , Neural Networks, Computer , Algorithms , Data Mining , Databases, FactualABSTRACT
The effect of ultrasound on the photocatalytic oxidation kinetics of elemental sulphur particles catalyzed by titanium dioxide was studied using a conductivity method to follow the reaction. The simultaneous use of photocatalyst and ultrasound have a positive effect on the reaction. The zero-order oxidation rate constant of sulphur, reached after an activation period of approximately 150 min, was about 20 times higher when the reactor was sonicated, using an ultrasonic processor of 30 kHz, compared to the rate found in its absence. Finally, when the amount of sulphur is changed in the reactor, saturation kinetics seems to be the most appropriate model to describe the oxidation process in the presence of ultrasound and, in the other hand, when titanium dioxide was increased, a maximum rate was achieved when 0.56 g/L TiO2 were used.