0531046 20240103224239.520200720235959.9 85089213321 10.1007/978-981-15-4917-5_22 13 s. P cav_un_epca*0531043978-981-15-4916-8vol. 176Smart Innovation, Systems and Technologies283-295SingaporeSpringer2021PengSheng-LungFavorskayaMargarita N.ChaoHan-Chieh Compositional models Artificial neural network Model comparison Taiwanese ecotourism data set cav_un_auth*0393863 Bína Vladislav UTIA-B Matematická teorie rozhodování Department of Decision Making Theory MTR MTR CZ Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0216188 Kratochvíl Václav UTIA-B Matematická teorie rozhodování Department of Decision Making Theory MTR MTR Department of Decision Making Theory CZ Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0261750 Váchová L. CZ cav_un_auth*0101118 Jiroušek Radim UTIA-B Matematická teorie rozhodování Department of Decision Making Theory MTR MTR Department of Decision Making Theory Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0368377 Lee T. R. TW http://library.utia.cas.cz/separaty/2020/MTR/kratochvil-0531046.pdf GA19-06569S GA ČR CZ cav_un_auth*0379647 MOST-04-18 Akademie věd - GA AV ČR CZ cav_un_auth*0393867 This paper aims to perform modeling of Taiwanese farm and ecotourism data using compositional models as a probabilistic approach and to compare its results with the performance of an artificial neural network approach. Authors use probabilistic compositional models together with the artificial neural network as a classifier and compare the accuracy of both approaches. The probabilistic model structure is learned using hill climbing algorithm, and the weights of multilayer feedforward artificial neural network are learned using an R implementation of H2O library for deep learning. In case of both approaches, we employ a non-exhaustive cross-validation method and compare the models. The comparison is augmented by the structure of the compositional model and basic characterization of artificial neural network. As expected, the compositional models show significant advantages in interpretability of results and (probabilistic) relations between variables, whereas the artificial neural network provides more accurate yet “black-box” model. cav_un_auth*0393865 Sensor Networks and Signal Processing (SNSP 2019) /2./ 20191119 20191122 Hualien TW IN 10000 10100 10103 2021 5 PR RVO:67985556 http://hdl.handle.net/11104/0310092 S 2021 85089213321 SCOPUS PUBMED WOS cav_un_epca*0531043 Sensor Networks and Signal Processing Smart Innovation, Systems and Technologies vol. 176 978-981-15-4916-8 283 295 Singapore Springer 2021 2190-3018 Peng Sheng-Lung 340 Favorskaya Margarita N. 340 Chao Han-Chieh 340