Multiple-Instance Hidden Markov Models With Applications to Landmine Detection Abstract A novel multiple-instance hidden Markov model (MI-HMM) is introduced for classification of time-series data, and its training is developed using stochastic expectation maximization. The MI-HMM provides a single statistical form… Read More
Landmine Detection
Computational modeling Expectation maximization (EM) expectation-maximisation algorithm Ground penetrating radar ground penetrating radar (GPR) Hidden Markov models hidden Markov models (HMMs) Landmine detection landmine detection problem learning (artificial intelligence) MI-HMM multiple-instance hidden Markov model multiple-instance HMM (MI-HMM) multiple-instance learning (MIL) multiple-instance learning framework Noise measurement sensors Standards statistical analysis stochastic EM stochastic expectation maximization stochastic processes time series time-series data time-series data classification Training training set selection