Wearable Bio-Signal(PPG)-Based Personal Authentication Method Using Random Forest and Period Setting Considering the Feature of PPG Signals

A study regarding personal authentication based on PPG has been conducted using the Random Forest algorithm. In order to ensure correct authentication, data features must be consistent. This consistency is provided through the normalization of the PPG signal using maximum-minimum normalization and spline interpolation. The threshold is set by using normalized data and the highest value among the points above the threshold is set as the peak of the period. After establishing candidates of valley with values below the threshold, a shifted period is calculated by designating the last valley next to the following peak to the valley of the period. In order to reduce errors in the one period PPG data, the data is averaged after overlapping. A discrete cosine transform (DCT) is used to extract features from the preprocessed data. Thus, the extracted features are used as the input variables for machine learning techniques such as Decision Tree, KNN, Random Forest. The accuracy of these algorithms is 93%, 98%, and 99% respectively.

[1]  Sang Gi Hong,et al.  ECG-based Biometric Authentication Using Random Forest , 2017 .

[2]  Juan E. Tapiador,et al.  A Survey of Wearable Biometric Recognition Systems , 2016, ACM Comput. Surv..

[3]  A. Lynn Abbott,et al.  Biometric authentication using photoplethysmography signals , 2016, 2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems (BTAS).

[4]  Y. Y. Gu,et al.  Photoplethysmographic authentication through fuzzy logic , 2003, IEEE EMBS Asian-Pacific Conference on Biomedical Engineering, 2003..

[5]  Chao Chen,et al.  Using Random Forest to Learn Imbalanced Data , 2004 .

[6]  Walter Karlen,et al.  Multiparameter Respiratory Rate Estimation From the Photoplethysmogram , 2013, IEEE Transactions on Biomedical Engineering.

[7]  Ahmet Resit Kavsaoglu,et al.  A novel feature ranking algorithm for biometric recognition with PPG signals , 2014, Comput. Biol. Medicine.

[8]  Mark Mohammad Tehranipoor,et al.  Highly Reliable Key Generation From Electrocardiogram (ECG) , 2017, IEEE Transactions on Biomedical Engineering.

[9]  Mark Mohammad Tehranipoor,et al.  Human recognition from photoplethysmography (PPG) based on non-fiducial features , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[10]  Petros Spachos,et al.  Feasibility study of photoplethysmographic signals for biometric identification , 2011, 2011 17th International Conference on Digital Signal Processing (DSP).

[11]  Yuan-Ting Zhang,et al.  A novel biometric approach in human verification by photoplethysmographic signals , 2003, 4th International IEEE EMBS Special Topic Conference on Information Technology Applications in Biomedicine, 2003..

[12]  M. Sabarimalai Manikandan,et al.  Robust photoplethysmographic (PPG) based biometric authentication for wireless body area networks and m-health applications , 2016, 2016 Twenty Second National Conference on Communication (NCC).

[13]  N. Ahmed,et al.  Discrete Cosine Transform , 1996 .

[14]  Khairul Azami Sidek,et al.  Acceleration plethysmogram based biometric identification , 2015, 2015 International Conference on BioSignal Analysis, Processing and Systems (ICBAPS).

[15]  Saurabh Pal,et al.  Photoplethysmogram signal based biometric recognition using linear discriminant classifier , 2016, 2016 2nd International Conference on Control, Instrumentation, Energy & Communication (CIEC).