EEG-based interfaces are an active area of research that has great potential. We therefore focused on classifying motor imaging (MI) tasks from various problem areas. Because of that, we applied MI patterns to voting ensembles differently and constructed voters. They employ quasi-probabilistic distribution models based sub-classifiers made up of different frequency bands and time segments. Much previous work focused on just a few MI tasks for BCIs. To that end, we constructed a new mobile EEG dataset, abbreviated as MI-BMPI, containing two major gestures for mobile phone interfaces, and thus brain-mobile phone interfaces (BMPI) was added to the problem domain. In the research experiments, a consumer market EEG system, the mobile wireless Emotiv EPOC Flex neuroheadset, was used. Experiments were carried out on the BCI Competition IV Dataset 2a and MI-BMPI. On the BCI and BMPI datasets, promising results were obtained in classifying various MI tasks. In conclusion, new solutions were introduced for tougher EEG-based interfaces, which have potential in the classification of MI tasks and the development of EEG-based interfaces. In addition to the average performance improvements, more stable results were achieved for both subject and task variations.