Emphasizing privacy and security of edge intelligence with machine learning for healthcare

Rajendran, Sukumar; Mathivanan, Sandeep Kumar; Jayagopal, Prabhu; Janaki, K.; Bernard, Benjula Anbu Malar Manickam; Suganya, P.; Somanathan, Manivannan Sorakaya

doi:10.1108/ijicc-05-2021-0099

Cited by 33 publications

(14 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e decency of the data portrayal largely a ects the presentation of data by machine learners; an unfortunate data portrayal is probably going to decrease the exhibition of even a propelled machine learner, while a decent data portrayal can prompt superior for a moderately easier machine learner. ese features include designing, which centers on building highlights and data portrayals from actual data [2], which is a significant component of deep learning. Key idea basic deep learning (DL) strategies are dispersed portrayals of the data, in which countless potential arrangements of the theoretical highlights of the information are achievable, taking into consideration a conservative portrayal for each example and prompting a more extravagant generalization.…”

Section: Introductionmentioning

confidence: 99%

Feature Learning-Based Generative Adversarial Network Data Augmentation for Class-Based Few-Shot Learning

Subedi¹,

Sathishkumar

Maheshwari

et al. 2022

Mathematical Problems in Engineering

Self Cite

View full text Add to dashboard Cite

As training deep neural networks enough requires a large amount of data, there have been a lot of studies to deal with this problem. Data augmentation techniques are basic solutions to increase training data using existing data. Geometric transformations and color space augmentations are well-known augmentation techniques, but they still require some manual work and can generate limited types of data only. Therefore, there are many interests in generative-model-based augmentation lately, which can learn the distribution of data. This study proposes a set of GAN-based data augmentation methods that can generate good quality training data. The proposed networks, f-DAGAN (data augmentation generative adversarial networks), have been motivated by the DAGAN that learns data distribution from two real data. The basic f-DAGAN uses dual discriminators handling both generated data and generated feature spaces for better learning the given data. The other versions of f-DAGANs have been proposed for generating hard or easy data that have additional dual classifiers for both generated data and feature spaces to control the generator. Hard data is useful for optimized training to increase the target performance such as classification accuracy. Easy data generation can be used especially in few-shot learning. The quality of generated data has been validated in two ways: using t-SNE visualization of generated data and classification accuracy by training with generated data using the MNIST data set. The t-SNE representations show that data generated by f-DAGAN are evenly distributed for every class better than the exiting generative model-based augmentation methods. The f-DAGAN also shows the best classification accuracy by training with generated data. The f-DAGAN version for easy and hard data generation generates data well from five-shot learning and performs well in sample data generation experiments.

show abstract

Section: Introductionmentioning

confidence: 99%

Feature Learning-Based Generative Adversarial Network Data Augmentation for Class-Based Few-Shot Learning

Subedi¹,

Sathishkumar

Maheshwari

et al. 2022

Mathematical Problems in Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…Salem et al [157] presented an anomaly detection scheme using support vector machine (SVM) and linear regression models on wireless medical sensor networks. Rajendran et al [158] used machine learning approaches for enhancing security and privacy in edge intelligence in healthcare applications. Pirbhulal et al [159] propounded an ML-based biometric security framework on ECG signals.…”

Section: Access Control-based Solutions Unauthorized Access Can Be Re...mentioning

confidence: 99%

A Taxonomy on Smart Healthcare Technologies: Security Framework, Case Study, and Future Directions

et al. 2022

View full text Add to dashboard Cite

There is a massive transformation in the traditional healthcare system from the specialist-centric approach to the patient-centric approach by adopting modern and intelligent healthcare solutions to build a smart healthcare system. It permits patients to directly share their medical data with the specialist for remote diagnosis without any human intervention. Furthermore, the remote monitoring of patients utilizing wearable sensors, Internet of Things (IoT) technologies, and artificial intelligence (AI) has made the treatment readily accessible and affordable. However, the advancement also brings several security and privacy concerns that poorly maneuvered the effective performance of the smart healthcare system. An attacker can exploit the IoT infrastructure, perform an adversarial attack on AI models, and proliferate resource starvation attacks in smart healthcare system. To overcome the aforementioned issues, in this survey, we extensively reviewed and created a comprehensive taxonomy of various smart healthcare technologies such as wearable devices, digital healthcare, and body area networks (BANs), along with their security aspects and solutions for the smart healthcare system. Moreover, we propose an AI-based architecture with the 6G network interface to secure the data exchange between patients and medical practitioners. We have examined our proposed architecture with the case study based on the COVID-19 pandemic by adopting unmanned aerial vehicles (UAVs) for data exchange. The performance of the proposed architecture is evaluated using various machine learning (ML) classification algorithms such as random forest (RF), naive Bayes (NB), logistic regression (LR), linear discriminant analysis (LDA), and perceptron. The RF classification algorithm outperforms the conventional algorithms in terms of accuracy, i.e., 98%. Finally, we present open issues and research challenges associated with smart healthcare technologies.

show abstract

“…Basic image transformations like color, geometric, and mixing of images are discussed in [ 28 ]. New samples were created from an existing dataset by performing translation and rotation as mentioned in [ 29 ].…”

Section: Literature Surveymentioning

confidence: 99%

Investigation of Applying Machine Learning and Hyperparameter Tuned Deep Learning Approaches for Arrhythmia Detection in ECG Images

Kogilavani¹,

Sathishkumar

Kumar

et al. 2022

Computational and Mathematical Methods in Medicine

Self Cite

View full text Add to dashboard Cite

The level of patient’s illness is determined by diagnosing the problem through different methods like physically examining patients, lab test data, and history of patient and by experience. To treat the patient, proper diagnosis is very much important. Arrhythmias are irregular variations in normal heart rhythm, and detecting them manually takes a long time and relies on clinical skill. Currently machine learning and deep learning models are used to automate the diagnosis by capturing unseen patterns from datasets. This research work concentrates on data expansion using augmentation technique which increases the dataset size by generating different images. The proposed system develops a medical diagnosis system which can be used to classify arrhythmia into different categories. Initially, machine learning techniques like Support Vector Machine (SVM), Naïve Bayes (NB), and Logistic Regression (LR) are used for diagnosis. In general deep learning models are used to extract high level features and to provide improved performance over machine learning algorithms. In order to achieve this, the proposed system utilizes a deep learning algorithm known as Convolutional Neural Network-baseline model for arrhythmia detection. The proposed system also adopts a novel hyperparameter tuned CNN model to acquire optimal combination of parameters that minimizes loss function and produces better result. The result shows that the hyper-tuned model outperforms other machine learning models and CNN baseline model for accurate classification of normal and other five different arrhythmia types.

show abstract

Emphasizing privacy and security of edge intelligence with machine learning for healthcare

Cited by 33 publications

References 25 publications

Feature Learning-Based Generative Adversarial Network Data Augmentation for Class-Based Few-Shot Learning

Feature Learning-Based Generative Adversarial Network Data Augmentation for Class-Based Few-Shot Learning

A Taxonomy on Smart Healthcare Technologies: Security Framework, Case Study, and Future Directions

Investigation of Applying Machine Learning and Hyperparameter Tuned Deep Learning Approaches for Arrhythmia Detection in ECG Images

Contact Info

Product

Resources

About