Sudden cardiac death (SCD) results in millions of deaths annually; as it is a fatal heart abnormality, early prediction of SCD could save peoples’ lives to the greatest extent. Symmetry and asymmetry play an important role in many fields. Electrocardiograms (ECG) as a noninvasive process for acquiring the electrical activity of the heart, has both asymmetric and non-stationary characteristics; it is frequently employed to diagnose and evaluate the heart’s condition. In this work, we have detected SCD 14 min (separately for each one-minute interval) prior to its occurrence by analyzing ECG signals using discrete wavelet transform (DWT) and locality preserving projection (LPP). In the experiment, we have performed DWT on ECG signals to obtain coefficients, then LPP as a reduction methodology was used to cut down these obtained coefficients. Then, the acquired LPP features were ranked using various methods, including the T-test, Bhattacharyya, Wilcoxon, and entropy. At last, the highly ranked LPP features were subjected to decision tree, k-nearest neighbor (KNN), and support vector machine classifiers for distinguishing normal from SCD ECG signals. Our proposed technique has achieved a highest accuracy of 97.6% for the detection of SCD 14 min prior using the KNN classifier, compared to the existing works. Our proposed method is capable of predicting the people at risk of developing SCD 14 min before its onset, and, hence, clinicians would have enough time to provide treatment in intensive care units (ICU) for a subject at risk of SCD. Thus, this proposed technique as a useful tool can increase the survival rate of many cardiac patients.

To compare multiple genome sequences, we transform each primary genome sequence into corresponding k-mer-based vectors. According to the principle of independent component analysis (ICA), the operation can be regarded as mixing multiple source genomic signals via several sensors, through which we can obtain the mixed vectors with equal-length from the corresponding genome sequences with different length. However, this mixing operation is performed by counting all the k-mer-based frequencies, instead of using real hardware of sensors. Thus, we name this preprocessing operation as virtual mixer (VM). Using ICA-based transformation, we projected all the vectors upon their independent components to capture the coefficients-based feature vector through the projection extractor (PE), which has been proved to have a property of distance preserving. Then, we used the proposed VMPE model upon three representative real datasets of genome sequence to test the efficiency for the model. The contrastive analysis results indicate that the proposed VMPE model performs well in similarity analysis.PeerJ Preprints | https://doi.org/10.7287/peerj.preprints.27333v1 | CC BY 4.0 Open Access | rec:To compare multiple genome sequences, we transform each primary genome sequence into 14corresponding k-mer-based vectors. According to the principle of independent component analysis 15(ICA), the operation can be regarded as mixing multiple source genomic signals via several sensors, 16through which we can obtain the mixed vectors with equal-length from the corresponding genome 17 sequences with different length. However, this mixing operation is performed by counting all the k-mer-18based frequencies, instead of using real hardware of sensors. Thus, we name this preprocessing 19 operation as virtual mixer (VM). Using ICA-based transformation, we projected all the vectors upon 20their independent components to capture the coefficients-based feature vector through the projection 21 extractor (PE), which has been proved to have a property of distance preserving. Then, we used the 22proposed VMPE model upon three representative real datasets of genome sequence to test the efficiency 23for the model. The contrastive analysis results indicate that the proposed VMPE model performs well in 24 similarity analysis. 25 26 41 2009, Sims et al., 2009, Sims & Kim, 2011, which can be used as the comparison of whole 42 genomes or genomic segments that may not be closely related and have latent remarkable 43 rearrangement or have not shared a common set of genes, e.g. regulatory, intronic or nongenic 44 regions. 45As a classical alignment-free method, Blaisdell first introduced k-mer for biological sequence 46 comparison (Blaisdell, 1986). The relative approaches can be found in the reference (Luczak et 47 al., 2017). Vinga reviewed more developments about alignment-free comparison (Vinga & 48 Almeida, 2003), which described many developed approaches to mining data and comparing 49 multiple sequences. As a variation of approach for text comparison, S...