scholarly journals Handling Massive Proportion of Missing Labels in Multivariate Long-Term Time Series Forecasting

2021 ◽  
Vol 2090 (1) ◽  
pp. 012170
Author(s):  
Jr Cristovão Iglesias ◽  
Varun Mehta ◽  
Alina Venereo-Sanchez ◽  
Xingge Xu ◽  
Julien Robitaille ◽  
...  
Keyword(s):  
Time Series ◽  
Prediction Model ◽  
Domain Knowledge ◽  
Time Series Forecasting ◽  
Sensor Data ◽  
Adeno Associated Virus ◽  
Imputation Methods ◽  
Missing Labels ◽  
Raav Production

Abstract Training Deep Learning (DL) models with missing labels is a challenge in diverse engineering applications. Missing value imputation methods have been proposed to try to address this problem, but their performance is affected with Massive Proportion of Missing Labels (MPML). This paper presents a approach for handling MPML in Multivariate Long-Term Time Series Forecasting. It is an two-step process where interpolation (using Gaussian Processes Regression (GPR) and domain knowledge from experts) and prediction model are separated to enable the integration of prior domain knowledge. First, a set of samples of the possible interpolation of the missing outputs are generated by the GPR based on the domain knowledge. Second, the observed input sensor data and interpolated labels from GPR are used to train the prediction model. We evaluated our approach with the development of a soft-sensor with one real datasets to forecast the biomass during recombinant adeno-associated virus (rAAV) production in bioreactors. Our experimental results demonstrate the potential of the approach through quantitative evaluation of the generated forecasts in a case that would be extremely difficult to train a DL model due to MPML.

Time Series Forecasting in Retail Sales Using LSTM and Prophet

2021 ◽  
pp. 241-262
Author(s):  
Clony Junior ◽  
Pedro Gusmão ◽  
José Moreira ◽  
Ana Maria M. Tome
Keyword(s):  
Time Series ◽  
Data Science ◽  
Short Term Memory ◽  
Special Kind ◽  
Time Series Forecasting ◽  
Short Term ◽  
Term Memory ◽  
Use Of Time

Data science highlights fields of study and research such as time series, which, although widely explored in the past, gain new perspectives in the context of this discipline. This chapter presents two approaches to time series forecasting, long short-term memory (LSTM), a special kind of recurrent neural network (RNN), and Prophet, an open-source library developed by Facebook for time series forecasting. With a focus on developing forecasting processes by data mining or machine learning experts, LSTM uses gating mechanisms to deal with long-term dependencies, reducing the short-term memory effect inherent to the traditional RNN. On the other hand, Prophet encapsulates statistical and computational complexity to allow broad use of time series forecasting, prioritizing the expert's business knowledge through exploration and experimentation. Both approaches were applied to a retail time series. This case study comprises daily and half-hourly forecasts, and the performance of both methods was measured using the standard metrics.

scholarly journals Potential and Challenges of Harmonizing 40 Years of AVHRR Data: The TIMELINE Experience

2021 ◽  
Vol 13 (18) ◽  
pp. 3618
Author(s):  
Stefan Dech ◽  
Stefanie Holzwarth ◽  
Sarah Asam ◽  
Thorsten Andresen ◽  
Martin Bachmann ◽  
...  
Keyword(s):  
Climate Change ◽  
Time Series ◽  
Observation Time ◽  
Sensor Data ◽  
High Temporal Resolution ◽  
Statistical Parameters ◽  
Medium Resolution ◽  
Long Time ◽  
Earth Observation Satellite

Earth Observation satellite data allows for the monitoring of the surface of our planet at predefined intervals covering large areas. However, there is only one medium resolution sensor family in orbit that enables an observation time span of 40 and more years at a daily repeat interval. This is the AVHRR sensor family. If we want to investigate the long-term impacts of climate change on our environment, we can only do so based on data that remains available for several decades. If we then want to investigate processes with respect to climate change, we need very high temporal resolution enabling the generation of long-term time series and the derivation of related statistical parameters such as mean, variability, anomalies, and trends. The challenges to generating a well calibrated and harmonized 40-year-long time series based on AVHRR sensor data flown on 14 different platforms are enormous. However, only extremely thorough pre-processing and harmonization ensures that trends found in the data are real trends and not sensor-related (or other) artefacts. The generation of European-wide time series as a basis for the derivation of a multitude of parameters is therefore an extremely challenging task, the details of which are presented in this paper.

scholarly journals A Long-Term Prediction Model of Beijing Haze Episodes Using Time Series Analysis

2016 ◽  
Vol 2016 ◽  
pp. 1-7 ◽  
Author(s):  
Xiaoping Yang ◽  
Zhongxia Zhang ◽  
Zhongqiu Zhang ◽  
Liren Sun ◽  
Cui Xu ◽  
...  
Keyword(s):  
Time Series ◽  
Time Series Analysis ◽  
Prediction Model ◽  
Industrial Development ◽  
Measurement Model ◽  
Vector Autoregressive ◽  
Series Analysis ◽  
Term Prediction ◽  
Long Term Prediction

The rapid industrial development has led to the intermittent outbreak of pm2.5 or haze in developing countries, which has brought about great environmental issues, especially in big cities such as Beijing and New Delhi. We investigated the factors and mechanisms of haze change and present a long-term prediction model of Beijing haze episodes using time series analysis. We construct a dynamic structural measurement model of daily haze increment and reduce the model to a vector autoregressive model. Typical case studies on 886 continuous days indicate that our model performs very well on next day’s Air Quality Index (AQI) prediction, and in severely polluted cases (AQI ≥ 300) the accuracy rate of AQI prediction even reaches up to 87.8%. The experiment of one-week prediction shows that our model has excellent sensitivity when a sudden haze burst or dissipation happens, which results in good long-term stability on the accuracy of the next 3–7 days’ AQI prediction.

Building trend fuzzy granulation based LSTM recurrent neural network for long-term time series forecasting

2021 ◽  
pp. 1-1
Author(s):  
Yuqing Tang ◽  
Fusheng Yu ◽  
Witold Pedrycz ◽  
Xiyang Yang ◽  
Jiayin Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Recurrent Neural Network ◽  
Time Series Forecasting

scholarly journals Short-term Time Series Forecasting of Concrete Sewer Pipe Surface Temperature

2020 ◽  
Author(s):  
Karthick Thiyagarajan ◽  
sarath kodagoda ◽  
Nalika Ulapane
Keyword(s):  
Time Series ◽  
Surface Temperature ◽  
Time Series Forecasting ◽  
Sensor Data ◽  
Alternative Measure ◽  
Sewer Pipe ◽  
Short Term ◽  
Pipe Surface ◽  
Forecasting Accuracy ◽  
Short Term Forecasting

Microbial corrosion is considered the main reason for multi-billion dollar sewer asset degradation. Sewer pipe surface temperature is a vital parameter for predicting the micro-biologically induced concrete corrosion. Due to this important measure, a surface temperature sensor suite was recently developed and tested in an aggressive sewer environment. The sensors can fail and they may also put offline during the period of scheduled maintenance. In such situations, time series forecasting of sensor data can be an alternative measure for the operators managing the sewer network. In this regard, this paper focuses on the short-term forecasting of sensor measurements. The evaluation was carried out by forecasting the sensor measurements for different time periods and evaluated with different forecasting models. The ETS model leads to high short-term forecasting accuracy and the ARIMA model leads to high long-term forecasting accuracy. The models were evaluated on real data captured in a Sydney sewer

Sign in / Sign up

Export Citation Format

Share Document