A5070495580- Statistical Methods and Bayesian Inference
- Probability and Risk Models
- Bayesian Methods and Mixture Models
- Advanced Adaptive Filtering Techniques
- Insurance, Mortality, Demography, Risk Management
- Insurance and Financial Risk Management
- Cognitive Radio Networks and Spectrum Sensing
- Statistical Methods and Inference
- Speech and Audio Processing
- Data-Driven Disease Surveillance
- Bayesian Modeling and Causal Inference
- Advanced MIMO Systems Optimization
- Advanced Sensor and Control Systems
- Markov Chains and Monte Carlo Methods
- Financial Risk and Volatility Modeling
- Advanced Algorithms and Applications
- Statistical Distribution Estimation and Applications
University College Dublin
2018-2021
Abstract Spatial analysis ranges from simple univariate descriptive statistics to complex multivariate analyses and is typically used investigate spatial patterns or identify spatially linked consumer behaviours in insurance. This paper investigates if the incorporation of publicly available demographic census data at population level useful modelling customers’ lapse behaviour (i.e. stopping payment premiums) life insurance policies, based on provided by an company Ireland. From company’s...
While generalized linear models have become the insurance industry's standard approach for claim modelling, of utilizing a single best model on which predictions are based ignores selection uncertainty. An additional feature data sets is common presence categorical variables, within number levels high, and not all may be statistically significant. In such cases, some subsets merged to give smaller overall improved parsimony interpretability. Hence, clustering poses an uncertainty issue. A...
Sharing of frequency spectrum between licensed primary users and unlicensed secondary (SUs) requires reliable detection occupancy by the SUs. We present a new cooperative sensing in OFDM system based on MIMO cognitive radio (CR) sensor networks. interference temperature estimation approach technique system. Frequency combination observed energy values from different is investigated. Square-law-combining (SLC) theoretically proved to be nearly optimal low signal-to-noise ratio (SNR) region,...
In this paper, we consider that cooperative frequency spectrum sensing based on the spatial spectral estimation in cognitive radio sensor networks. We propose an algorithm estimates interference temperature of model using a generalization DOA (direction arrival) algorithm. From this, find and show it does become smaller. compare our method to conventional (without considering directions) The simulation studies new outperforms by reducing improving efficiency.
Abstract The mvClaim package in R provides flexible modelling frameworks for multivariate insurance claim severity modelling. current version of the implements a parsimonious mixture experts (MoE) model family with bivariate gamma distributions, as introduced Hu et al. , and finite copula regressions within MoE framework & O’Hagan. This paper presents approach theory briefly usage models detail. is hosted on GitHub at https://github.com/senhu/ .
Technique of multiple windows frequency estimation integrating SVD offers a efficient method which estimate interference temperature in radio environment. Since this paper uses way integrate the neural network, complexity tradition arithmetic was predigested and improved nicety estimating temperature. At same time, provides good for real time complex