 The application of intracranial electroencephalogram, EEG, to predict seizures remains challenging. Although channel selection has been utilized in seizure prediction and detection studies, most of them focus on the combination with conventional machine learning methods. Thus, channel selection combined with deep learning methods can be further analyzed in the field of seizure prediction. Given this, in this work, a novel EEG-based deep learning method of one-dimensional convolutional neural networks, 1D-CNN, combined with channel increment strategy was proposed for the effective seizure prediction. First, we used four seconds sliding windows without overlap to segment EEG signals. Then, four seconds EEG segments with an increasing number of channels, channel increment strategy, from one channel to all channels, were sequentially fed into the constructed 1D-CNN model. Next, the patient's specific model was trained for classification. Finally, according to the classification results in different channel cases, the channel case with the best classification rate was selected for each patient. Our method was tested on the Freiburg EEG database, and the system performances were evaluated at two levels, segment and. This article was authored by Xu Shuan Wang, Qi Zhang, Tommy Karkanen, and others. We are article.tv, links in the description below.