Cognitive Authentication for Smart Healthcare System
-
R. Babu
Abstract1
For cognitive monitoring, that is, behavioral recognition and intellectual tracking of each individual, safe, and reliable monitoring is critical. In recent years, both industry and academia have become interested in cognitive authentication, often known as biometric recognition. The main purpose of cognitive authentication is to recognize, detect, and monitor dissimilarities in biological signatures, behavioral characteristics including facial gestures, biometrics, voices, eye gaze, mannerisms, and posture, among other things. Numerous developing biometric authentication systems are currently becoming incorporated and developed in multidisciplinary sectors such as personally identifiable information, accessibility, and asset monitoring systems. Whenever it comes to simple legalizing and identification surveillance difficulties, conventional security methods are not up to equivalence. To address these issues, an electroencephalogram-based cardiovascular technology is a promising choice for next-generation mechanisms due to brain signals reflecting/ mimicking cognitive style and behaviors. Data encryption and identification tracking are included in today’s modern advanced authentication systems. Users identify themselves by using words/passwords, yet that alone would be insufficient to adequately protect and secure private data. Because standard password protection lacks cognitive distinctiveness, it could be stolen and hacked by anybody. To improve a bad passcode and maintain it, the user must enhance the difficulty level and that will be extremely difficult to remember.
Abstract1
For cognitive monitoring, that is, behavioral recognition and intellectual tracking of each individual, safe, and reliable monitoring is critical. In recent years, both industry and academia have become interested in cognitive authentication, often known as biometric recognition. The main purpose of cognitive authentication is to recognize, detect, and monitor dissimilarities in biological signatures, behavioral characteristics including facial gestures, biometrics, voices, eye gaze, mannerisms, and posture, among other things. Numerous developing biometric authentication systems are currently becoming incorporated and developed in multidisciplinary sectors such as personally identifiable information, accessibility, and asset monitoring systems. Whenever it comes to simple legalizing and identification surveillance difficulties, conventional security methods are not up to equivalence. To address these issues, an electroencephalogram-based cardiovascular technology is a promising choice for next-generation mechanisms due to brain signals reflecting/ mimicking cognitive style and behaviors. Data encryption and identification tracking are included in today’s modern advanced authentication systems. Users identify themselves by using words/passwords, yet that alone would be insufficient to adequately protect and secure private data. Because standard password protection lacks cognitive distinctiveness, it could be stolen and hacked by anybody. To improve a bad passcode and maintain it, the user must enhance the difficulty level and that will be extremely difficult to remember.
Kapitel in diesem Buch
- Frontmatter I
- Contents V
- List of Authors VII
- The Learning of Deep Learning: Overview, Methods, and Applications 1
- Foundation of Cognitive Computing 19
- Applications and Implications of Artificial Intelligence and Deep Learning in Computer Vision 35
- A Study of Voice Recognition System Using Deep Learning Techniques 53
- Building Machine Learning–Based Prediction System for Critical Diseases 75
- An Overview of Internet of Things and Machine Learning for Smart Healthcare 97
- Nutrition Food Recognition Using Deep Learning Algorithm for Physically Challenged Human Being 113
- Healthcare Data Analysis Using Deep Learning Paradigm 129
- Cognitive Authentication for Smart Healthcare System 149
- Cognitive-Inspired Computer Vision Assist System for Diabetic Retinopathy Detection from Fundus Images 165
- A Novel Deep Belief Neural Network Model for Abstractive Text Summarization 179
- Index 201
Kapitel in diesem Buch
- Frontmatter I
- Contents V
- List of Authors VII
- The Learning of Deep Learning: Overview, Methods, and Applications 1
- Foundation of Cognitive Computing 19
- Applications and Implications of Artificial Intelligence and Deep Learning in Computer Vision 35
- A Study of Voice Recognition System Using Deep Learning Techniques 53
- Building Machine Learning–Based Prediction System for Critical Diseases 75
- An Overview of Internet of Things and Machine Learning for Smart Healthcare 97
- Nutrition Food Recognition Using Deep Learning Algorithm for Physically Challenged Human Being 113
- Healthcare Data Analysis Using Deep Learning Paradigm 129
- Cognitive Authentication for Smart Healthcare System 149
- Cognitive-Inspired Computer Vision Assist System for Diabetic Retinopathy Detection from Fundus Images 165
- A Novel Deep Belief Neural Network Model for Abstractive Text Summarization 179
- Index 201
