Unsupervised marine vessel trajectory prediction using LSTM network and wild bootstrapping techniques

Increasing intensity in maritime traffic pushes the requirement in better preventionoriented incident management system. Observed regularities in data could help to predict vessel movement from previous vessels trajectory data and make further movement predictions under specific traffic and weather conditions. However, the task is burden by the fact that the vessels behave differently in different geographical sea regions, sea ports, and their trajectories depends on the vessel type as well. The model must learn spatio-temporal patterns representing vessel trajectories and should capture vessel’s position relation to both space and time. The authors of the paper proposes new unsupervised trajectory prediction with prediction regions at arbitrary probabilities using two methods: LSTM prediction region learning and wild bootstrapping. Results depict that both the autoencoder-based and wild bootstrapping region prediction algorithms can predict vessel trajectory and be applied for abnormal marine traffic detection by evaluating obtained prediction region in an unsupervised manner with desired prediction probability.

Prediction region for average claim occurrence rate and average claim size in motor insurance

The third-party motor insurance data from Sweden for 1977 described by Andrews and Herzberg in 1985 contain average claim occurrence rate (Pc) , average claim size (Ca) for category of vehicles specified by the kilometres travelled per year (K), geographical zone (Z), no claims bonus (B) and make of car (M). The categorical variables Z and M may first be represented respectively by the vectors (Z1, Z2, … , Z6) and (M1, M2, … , M8) of binary variables. The variable (Pc, Ca) is next modelled to be dependent on X∗ = (K, Z1, Z2, … , Z6, B, M1, M2, … , M8) via a conditional distribution which is derived from an 18-dimensional powernormal distribution. From the conditional distribution, a prediction region for (Pc, Ca) can be obtained to provide useful information on the possible ranges of average claim occurrence rate and average claim size for a given category of vehicles.

Prediction Regions for Poisson and Over-Dispersed Poisson Regression Models with Applications in Forecasting the Number of Deaths during the COVID-19 Pandemic

Motivated by the Coronavirus Disease (COVID-19) pandemic, which is due to the SARS-CoV-2 virus, and the important problem of forecasting the number of daily deaths and the number of cumulative deaths, this paper examines the construction of prediction regions or intervals under the no-covariate or intercept-only Poisson model, the Poisson regression model, and a new over-dispersed Poisson regression model. These models are useful for settings with events of interest that are rare. For the no-covariate Poisson and the Poisson regression model, several prediction regions are developed and their performances are compared through simulation studies. The methods are applied to the problem of forecasting the number of daily deaths and the number of cumulative deaths in the United States (US) due to COVID-19. To examine their predictive accuracy in light of what actually happened, daily deaths data until May 15, 2020 were used to forecast cumulative deaths by June 1, 2020. It was observed that there is over-dispersion in the observed data relative to the Poisson regression model. A novel over-dispersed Poisson regression model is therefore proposed. This new model, which is distinct from the negative binomial regression (NBR) model, builds on frailty ideas in Survival Analysis and over-dispersion is quantified through an additional parameter. It has the flavor of a discrete measurement error model and with a viable physical interpretation in contrast to the NBR model. The Poisson regression model is a hidden model in this over-dispersed Poisson regression model, obtained as a limiting case when the over-dispersion parameter increases to infinity. A prediction region for the cumulative number of US deaths due to COVID-19 by October 1, 2020, given the data until September 1, 2020, is presented. Realized daily and cumulative deaths values from September 1st until September 25th are compared to the prediction region limits. Finally, the paper discusses limitations of the proposed procedures and mentions open research problems. It also pinpoints dangers and pitfalls when forecasting on a long horizon, especially during a pandemic where events, both foreseen and unforeseen, could impact point predictions and prediction regions.

Applying Mondrian Cross-Conformal Prediction to Estimate Prediction Confidence on Large Imbalanced Bioactivity Datasets

ABSTRACTConformal prediction has been proposed as a more rigorous way to define prediction confidence compared to other application domain concepts that have earlier been used for QSAR modelling. One main advantage of such a method is that it provides a prediction region potentially with multiple predicted labels, which contrasts to the single valued (regression) or single label (classification) output predictions by standard QSAR modelling algorithms. Standard conformal prediction might not be suitable for imbalanced datasets. Therefore, Mondrian cross-conformal prediction (MCCP) which combines the Mondrian inductive conformal prediction with cross-fold calibration sets has been introduced. In this study, the MCCP method was applied to 18 publicly available datasets that have various imbalance levels varying from 1:10 to 1:1000 (ratio of active/inactive compounds). Our results show that MCCP in general performed well on cheminformatics datasets with various imbalance levels. More importantly, the method not only provides confidence of prediction and prediction regions compared to standard machine learning methods, but also produces valid predictions for the minority class. In addition, a compound similarity based nonconformity measure was investigated. Our results demonstrate that although it gives valid predictions, its efficiency is much worse than nonconformity measures obtained from supervised learning.

Parallel Computing for LURR of Earthquake Prediction

The LURR theory is a new approach for earthquake prediction, which achieves a good result within China mainland and some regions in America, Japan, and Australia. However, the expansion of the prediction region leads to the refinement of its longitude and latitude and the increase of the time period. This requires more and more computations and volume of data reaching the order of GB, which will be very difficult for a single CPU. In this paper, adopting the technology of domain decomposition and parallelizing using MPI, we developed a new parallel tempospatial scanning program.