“…The experiment results show that the supervised CFA outperforms both linear and kernel versions of CFA without considering class label information. We also plan to explore potential of proposed algorithm using big data analysis and high performance computing [20], [21], [22], [23], [24], [9], [10], [25], [26], [27], [28], [29], [30], [31], [20], for applications of big multimodal data processing [32], [33], [34], [35], [36], [37], information and network security [38], [39], [40], [41], [42], [43], [44], [45], [46], [47], computer vision [48], [49], [50], [51], [52], [53], [54], [55], [56], and bioinformatics [57], [58], [59], [60], [61], [62], [60], [63],…”