Aftab Ali

A cloud-based healthcare framework for security and patients' data privacy using wireless body area networks

Abstract The recent developments in remote healthcare systems have witnessed significant interests from IT industry (Microsoft, Google, VMware etc) that provide ubiquitous and easily deployable healthcare systems. These systems provide a platform to share medical information, applications, and infrastructure in a ubiquitous and fully automated manner. Communication security and patients’ data privacy are the aspects that would increase the confidence of users in such remote healthcare systems. This paper presents a secure cloud-based mobile healthcare framework using wireless body area networks (WBANs). The research work presented here is twofold: first, it attempts to secure the inter-sensor communication by multi-biometric based key generation scheme in WBANs; and secondly, the electronic medical records (EMRs) are securely stored in the hospital community cloud and privacy of the patients’ data is preserved. The evaluation and analysis shows that the proposed multi-biometric based mechanism provides significant security measures due to its highly efficient key generation mechanism.

Energy-efficient cluster-based security mechanism for intra-WBAN and inter-WBAN communications for healthcare applications

Wireless body area networks (WBANs) are formed by using tiny health monitoring sensors on the human body in order to collect and communicate the human personal data. WBANs serve as a solution to facilitate the tasks performed in the medical sector, and minimize the chances of errors during the process of medical diagnosis. Due to the unreliable wireless media, the communication in a WBAN is exposed to a variety of attacks. These attacks pose major threats to WBAN security. In order to overcome these threats, several cryptographic techniques have been proposed in the recent past. Effectiveness of these cryptographic techniques largely depends on a good key management scheme. However, using an expensive key management scheme is not feasible in highly resource-constrained WBANs. Therefore, we propose and evaluate an energy-efficient key management scheme for WBANs that takes into account available resources of a node during the whole life cycle of key management. Our proposed scheme is a cluster-based hybrid security framework that supports both intra-WBAN and inter-WBAN communications. By using multiple clusters, energy-efficiency can be ensured. The cluster formation process itself is secured by using electrocardiogram (EKG)-based key agreement scheme. The proposed technique is hybrid because we use both preloading of keys and physiological value-based generated keys. We use highly dynamic and random EKG values of the human body for pairwise key generation and refreshment. The performance comparison of our proposed cluster-based key management scheme and low-energy adaptive clustering hierarchy (LEACH)-based key agreement scheme shows that the proposed scheme is secure, more energy-efficient, and provides better network lifetime.

A cluster-based key agreement scheme using keyed hashing for Body Area Networks

In recent years, Body Area Networks (BANs) have gained immense popularity in the domain of healthcare as well as monitoring of soldiers in the battlefield. Security of a BAN is inevitable as we secure the lives of soldiers and patients. In this paper, we propose a security framework using Keyed-Hashing Message Authentication Code (HMAC-MD5) to protect the personal information in a BAN. We assume a network in which nodes sense physiological variables such as electrocardiography (EKG), electroencephalography (EEG), pulse oximeter data, blood pressure and cardiac output. Heterogeneous wireless sensor network is considered which consists of a powerful High-end sensor (H-sensor) and several Low-end sensors (L-sensors). EKG is used for secure communication between nodes as it introduces plug and play capability in BANs. The process is made secure by applying HMAC-MD5 on EKG blocks. Key agreement is done by comparing HMAC of feature blocks between sensors resulting in a more secure network. The analysis is done by calculating the entropy of keys and checking the randomness of EKG data using NIST-randomness testing suite.

An Improved EKG-Based Key Agreement Scheme for Body Area Networks

Body area networks (BANs) play an important role in mobile health monitoring such as, monitoring the health of patients in a hospital or physical status of soldiers in a battlefield. By securing the BAN, we actually secure the lives of soldiers or patients. This work presents an electrocardiogram (EKG) based key agreement scheme using discrete wavelet transform (DWT) for the sake of generating a common key in a body area network. The use of EKG brings plug-and-play capability in BANs; i.e., the sensors are just placed on the human body and a secure communication is started among these sensors. The process is made secure by using the iris or fingerprints to lock and then unlock the blocks during exchange between the communicating sensors. The locking and unlocking is done through watermarking. When a watermark is added at the sender side, the block is locked and when it is removed at the receiver side, the block is unlocked. By using iris or fingerprints, the security of the technique improves and its plug-and-play capability is not affected. The analysis is done by using real 2-lead EKG data sampled at a rate of 125 Hz taken from MIT PhysioBank database.

A Hybrid Security Mechanism for Intra-WBAN and Inter-WBAN Communications:

The emerging wireless body area networks (WBANs) have a great potential for the growth and development of future ubiquitous healthcare systems. However, due to the use of unreliable wireless media, WBANs are exposed to a variety of attacks. The prevention of these attacks depends upon the cryptographic techniques. The strength of cryptography is based on the keys used for encryption and decryption in the communication process. Security is still an alarming challenge for WBANs and needs attention of the research community. The proposed work introduces a hybrid key management scheme for both intra-WBAN and inter-WBAN communications. The proposed technique is based on preloaded keys as well as keys automatically generated from biometrics of the human body. The biometric-based calculations are of linear time complexity to cater the strict resource constraints and security requirements of WBANs. The proposed security mechanism provides an efficient solution for the security of both intra-WBAN and inter-WBAN communications. The results of the proposed technique are compared with an existing key management technique known as BARI+. The results show significant improvement over the results produced by BARI+ in terms of storage, communication, energy overhead, and security.

Key Agreement Schemes in Wireless Body Area Networks: Taxonomy and State-of-the-Art

Advances in wearable and implantable biosensors have enabled the applicability and usability of wireless body area networks (WBANs). A WBAN allows biosensors to collect and communicate human physiological data using wireless communication. The communication security of the collected data in WBAN is a major concern. Because of the dependability of cryptographic schemes for key management, these have become an important aspect of this security. However, the extremely constrained nature of biosensors has made designing key management schemes a challenging task. For this reason, many lightweight key management schemes have been proposed to overcome these constraints. In this article, we present a review of the state of the art of these solutions. We classify the WBAN schemes into three classes and evaluate them based on adequate metrics for key management in WBAN.

A Broadcast-Based Key Agreement Scheme Using Set Reconciliation for Wireless Body Area Networks

Information and communication technologies have thrived over the last few years. Healthcare systems have also benefited from this progression. A wireless body area network (WBAN) consists of small, low-power sensors used to monitor human physiological values remotely, which enables physicians to remotely monitor the health of patients. Communication security in WBANs is essential because it involves human physiological data. Key agreement and authentication are the primary issues in the security of WBANs. To agree upon a common key, the nodes exchange information with each other using wireless communication. This information exchange process must be secure enough or the information exchange should be minimized to a certain level so that if information leak occurs, it does not affect the overall system. Most of the existing solutions for this problem exchange too much information for the sake of key agreement; getting this information is sufficient for an attacker to reproduce the key. Set reconciliation is a technique used to reconcile two similar sets held by two different hosts with minimal communication complexity. This paper presents a broadcast-based key agreement scheme using set reconciliation for secure communication in WBANs. The proposed scheme allows the neighboring nodes to agree upon a common key with the personal server (PS), generated from the electrocardiogram (EKG) feature set of the host body. Minimal information is exchanged in a broadcast manner, and even if every node is missing a different subset, by reconciling these feature sets, the whole network will still agree upon a single common key. Because of the limited information exchange, if an attacker gets the information in any way, he/she will not be able to reproduce the key. The proposed scheme mitigates replay, selective forwarding, and denial of service attacks using a challenge-response authentication mechanism. The simulation results show that the proposed scheme has a great deal of adoptability in terms of security, communication overhead, and running time complexity, as compared to the existing EKG-based key agreement scheme.

Arrhythmia classification using Mahalanobis distance based improved Fuzzy C-Means clustering for mobile health monitoring systems

Abstract In this paper, an improved electrocardiogram (ECG) beats classification system is proposed, which is based on Fuzzy C-Means (FCM) clustering algorithm. The classification of ECG beats is necessary in order to diagnose the type of arrhythmia (e.g., Atrial Premature Contraction (APC), Premature Ventricular Contraction (PVC), Right Bundle Branch Block (RBBB) etc.) present in the ECG records. The efficiency of any classification model highly depends on the “most relevant” set of features used. The primary goal of this study is to classify different arrhythmic beats with reduced set of relevant-only ECG attributes. The attribute selection model is based on Mahalanobis-Taguchi System (MTS); a multi-dimensional pattern recognition tool, which can dynamically choose the important set of ECG features. The number of most relevant features can vary from person to person according to the type of arrhythmia present in the respective ECG signals. A traditional Euclidian Distance (ED) based FCM can detect the spherical clusters but it may lead to improper clustering in some cases. As a solution to this problem, Mahalanobis Distance (MD) is used in the proposed model in order to improve the distance measurement procedure. In our proposed system, MD based improved Fuzzy C-Means (FCM-M) clustering is used to classify the arrhythmic beats. Experimental results show that the performance of FCM-M is significantly better than the conventional FCM for arrhythmia classification. Another direction of our proposed research is to use the concept of initial cluster centroid in order to reduce the number of program iterations. In our experiments, the number of program iterations is reduced to an average of 53% when initial centroid is assigned to FCM-M with the same classification results.

A Continuous Change Detection Mechanism to Identify Anomalies in ECG Signals for WBAN-Based Healthcare Environments

The developments and applications of wireless body area networks (WBANs) for healthcare and remote monitoring have brought a revolution in the medical research field. Numerous physiological sensors are integrated in a WBAN architecture in order to monitor any significant changes in normal health conditions. This monitored data are then wirelessly transferred to a centralized personal server (PS). However, this transferred information can be captured and altered by an adversary during communication between the physiological sensors and the PS. Another scenario where changes can occur in the physiological data is an emergency situation, when there is a sudden change in the physiological values, e.g., changes occur in electrocardiogram (ECG) values just before the occurrence of a heart attack. This paper presents a centralized approach for the detection of abnormalities, as well as intrusions, such as forgery, insertions, and modifications in the ECG data. A simplified Markov model-based detection mechanism is used to detect changes in the ECG data. The features are extracted from the ECG data to form a feature set, which is then divided into sequences. The probability of each sequence is calculated, and based on this probability, the system decides whether the change has occurred or not. Our experiments and analyses show that the proposed scheme has a high detection rate for 5% as well as 10% abnormalities in the data set. The proposed scheme also has a higher true negative rate with a significantly reduced running time for both 5% and 10% abnormalities. Similarly, the receiver operating characteristic (ROC) and ROC convex hull have very promising results.

ECG Arrhythmia Classification Using Mahalanobis-Taguchi System in a Body Area Network Environment

Arrhythmia is caused by improper and irregular sinus rhythm or heartbeats. In order to diagnose cardiac arrhyth- mia, electrocardiogram (ECG) beat classification and analysis is very necessary. The efficiency and accuracy of any classification model highly depends on selecting the most relevant features. The aim of this study is to classify different arrhythmic beats with a reduced set of relevant-only ECG features. To optimize the ECG feature selection process and increase the classification accuracy, a Mahalanobis-Taguchi System (MTS) based classifica- tion and analysis scheme is proposed. MTS is a multi-dimensional pattern recognition system which dynamically selects important features for further analysis. Arrhythmia can occur at any time and thus requires proper and continuous monitoring of the patient to reduce sudden heart attacks. The proposed MTS- based classification scheme is integrated with a Wireless Body Area Network (WBAN) for pervasive monitoring. The proposed scheme is analyzed and compared with a state-of-the-art scheme in terms of sensitivity, specificity, and accuracy. The results show that the proposed scheme performs significantly better than the other scheme by achieving high sensitivity, specificity, and classification accuracy for different arrhythmic heartbeats i.e., Left Bundle Branch Block (LBBB), Premature Ventricular Contraction (PVC), Right Bundle Branch Block (RBBB), and Atrial Premature Contraction (APC).