Model Selection Criteria for Model-Based Clustering of Categorical Time Series Data: A Monte Carlo Study

2007 ◽  
pp. 23-30 ◽  
Author(s):  
José G. Dias
Keyword(s):  
Time Series ◽  
Monte Carlo ◽  
Model Selection ◽  
Selection Criteria ◽  
Time Series Data ◽  
Monte Carlo Study ◽  
Series Data ◽  
Model Selection Criteria ◽  
Model Based Clustering ◽  
Categorical Time Series

scholarly journals Ranking Information Extracted from Uncertainty Quantification of the Prediction of a Deep Learning Model on Medical Time Series Data

Mathematics ◽  
2020 ◽  
Vol 8 (7) ◽  
pp. 1078
Author(s):  
Ruxandra Stoean ◽  
Catalin Stoean ◽  
Miguel Atencia ◽  
Roberto Rodríguez-Labrada ◽  
Gonzalo Joya
Keyword(s):  
Time Series ◽  
Monte Carlo ◽  
Deep Learning ◽  
Uncertainty Quantification ◽  
Time Series Data ◽  
Short Term Memory ◽  
Learning Model ◽  
Series Data ◽  
Real World Problem ◽  
Uncertainty Estimates

Uncertainty quantification in deep learning models is especially important for the medical applications of this complex and successful type of neural architectures. One popular technique is Monte Carlo dropout that gives a sample output for a record, which can be measured statistically in terms of average probability and variance for each diagnostic class of the problem. The current paper puts forward a convolutional–long short-term memory network model with a Monte Carlo dropout layer for obtaining information regarding the model uncertainty for saccadic records of all patients. These are next used in assessing the uncertainty of the learning model at the higher level of sets of multiple records (i.e., registers) that are gathered for one patient case by the examining physician towards an accurate diagnosis. Means and standard deviations are additionally calculated for the Monte Carlo uncertainty estimates of groups of predictions. These serve as a new collection where a random forest model can perform both classification and ranking of variable importance. The approach is validated on a real-world problem of classifying electrooculography time series for an early detection of spinocerebellar ataxia 2 and reaches an accuracy of 88.59% in distinguishing between the three classes of patients.

scholarly journals Model selection in the reconstruction of regulatory networks from time-series data

2009 ◽  
Vol 2 (1) ◽  
pp. 68
Author(s):  
Eugene Novikov ◽  
Emmanuel Barillot
Keyword(s):  
Time Series ◽  
Model Selection ◽  
Regulatory Networks ◽  
Time Series Data ◽  
Series Data

scholarly journals PERAMALAN JUMLAH PENUMPANG PESAWAT TERBANG DI PINTU KEDATANGAN BANDAR UDARA INTERNASIONAL PATTIMURA AMBON DENGAN MENGGUNAKAN METODE ARIMA BOX-JENKINS

2019 ◽  
Vol 13 (3) ◽  
pp. 135-144
Author(s):  
Sasmita Hayoto ◽  
Yopi Andry Lesnussa ◽  
Henry W. M. Patty ◽  
Ronald John Djami
Keyword(s):  
Time Series ◽  
Model Selection ◽  
Time Series Data ◽  
Moving Average ◽  
Arima Model ◽  
Series Data ◽  
Autoregressive Integrated Moving Average ◽  
Significant Parameter ◽  
International Airport ◽  
Forecast Time

The Autoregressive Integrated Moving Average (ARIMA) model is often used to forecast time series data. In the era of globalization, rapidly progressing times, one of them in the field of transportation. The aircraft is one of the transportation that the residents can use to support their activities, both in business and tourism. The objective of the research is to know the forecasting of the number of passengers of airplanes at the arrival gate of Pattimura Ambon International Airport using ARIMA Box-Jenkins method. The best model selection is ARIMA (0, 1, 3) because it has significant parameter value and MSE value is smaller.

scholarly journals Bristlecone: An F# library for model-fitting and model-selection of ecological time-series data

2019 ◽  
Author(s):  
Andrew C Martin
Keyword(s):  
Time Series ◽  
Model Selection ◽  
Tree Rings ◽  
Time Series Data ◽  
Sediment Cores ◽  
Model Fitting ◽  
Series Data ◽  
Ecological Problems ◽  
Biodiversity And Ecosystem Function

Environmental archives such as sediment cores and tree rings provide important insights on the timing and rates of change in biodiversity and ecosystem function over the long-term. Such datasets are often analysed using empirical methods, which limits their ability to address ecological questions that seek to understand underlying ecological mechanisms and processes. Top down modelling approaches – where data is confronted with simple ecological models – can be used to infer the presence, form, and strength of mechanisms of interest. To aid adoption of time-series mechanistic modelling for long-term ecology, we created a F# library, Bristlecone, that can be used to apply this approach using a Model- Fitting and Model-Selection workflow. Our objective with Bristlecone was to create a library that could be used to efficiency and effectively conduct a full MFMS analysis for long-term ecological problems. We incorporated techniques to address specific challenges with environmental archives, including uneven time steps from age-depth models (for sediment cores), and allometry and seasonality (for tree rings). We include an example analysis to demonstrate functionality of Bristlecone. Our solution presents a straightforward, repeatable, and highly parallel method for conducting inference for long- term ecological problems.

On the Autoregressive Time Series Model Using Real and Complex Analysis

Forecasting ◽  
2021 ◽  
Vol 3 (4) ◽  
pp. 716-728
Author(s):  
Torsten Ullrich
Keyword(s):  
Time Series ◽  
Model Selection ◽  
Closed Form ◽  
Autoregressive Model ◽  
Complex Analysis ◽  
Time Series Data ◽  
Selection Process ◽  
Global Structure ◽  
Series Data ◽  
Time Step

The autoregressive model is a tool used in time series analysis to describe and model time series data. Its main structure is a linear equation using the previous values to compute the next time step; i.e., the short time relationship is the core component of the autoregressive model. Therefore, short-term effects can be modeled in an easy way, but the global structure of the model is not obvious. However, this global structure is a crucial aid in the model selection process in data analysis. If the global properties are not reflected in the data, a corresponding model is not compatible. This helpful knowledge avoids unsuccessful modeling attempts. This article analyzes the global structure of the autoregressive model through the derivation of a closed form. In detail, the closed form of an autoregressive model consists of the basis functions of a fundamental system of an ordinary differential equation with constant coefficients; i.e., it consists of a combination of polynomial factors with sinusoidal, cosinusoidal, and exponential functions. This new insight supports the model selection process.

Sign in / Sign up

Export Citation Format

Share Document