Samaneh Soradi-Zeid - Faculty of Industry and Mining, University of Sistan and Baluchestan, Zahedan, Iran
Seyede Toktam Mousavi - Secretary of Education of Khorasan Razavi

This paper improves differential evolution algorithm via combining five keyoperations. This paper employs differential evolution algorithm to optimize parameters ofCNNs for music emotion recognition tasks. The proposed DE-CNN approach effectivelyidentifies optimal parameters and structures for CNNs.

Evolutionary computation, Differential evolution, CNN Music data, Emotionalanalysis