Multi-Biometric Authentication Using Deep Learning Classifier for Securing of Healthcare Data
Gandhimathi Amirthalingam · International Journal of Advanced Trends in Computer Science and Engineering · 2019
Ensuring the security of healthcare data is becoming an increasingly important problem as modern technology is integrated into existing medical services.As a consequence of the adoption of healthcare data in the health care sector, it is becoming more and more common for a health professional to edit and view a patient's record using a tablet PC.To protect the patient's privacy, a secure authentication system to access patient records must be used.Yet, most Health apps used by consumers do not fall under federal or regional health privacy laws, even when the apps are used to manage a chronic illness.To solve this issue multi-biometric authentication is performed in this work via the use of deep learning classifier.This paper analyzes the performance of combining the use of on-line signature and fingerprint authentication to perform robust user authentication.Signatures are verified using the dynamic time warping (DTW) technique of string matching.The proposed minutiae-based matching algorithm, stores merely a small number of minutiae points, which greatly reduces the storage requirement with the help of phase correlation.Here, matching score level fusion is used by applying weighted sum rule for the biometric fusion process.To improve the authentication performance, deep learning classifier is proposed in this work for multi-biometrics authentication.When a biometric authentication request is submitted, the proposed authentication system uses deep learning to automatically select an appropriate matching image.In the experiment, biometric authentication was performed on healthcare in the UCI database.Multi -Biometric Authentication was used during the authentication stage.