Showing items 1 - 5 of 5

Your selections:

A patient centric agent assisted private blockchain on hyperledger fabric for managing remote patient monitoring

  • Authors: Wadud, Md Anwar , Amir-Ul-Haque Bhuiyan, T. , Uddin, Md Ashraf , Rahman, Md Motiur
  • Date: 2020
  • Type: Text , Conference paper
  • Relation: 11th International Conference on Electrical and Computer Engineering, ICECE 2020 p. 194-197
  • Full Text: false
  • Reviewed:
  • Description: Recently, during the COVID-19 situation, the requirement and importance of tracking patients from a remote location have increased significantly. Most patients now prefer to obtain their doctor's care and check their health status through their mobile phone call, Skype, Facebook Messenger, or other online resources. There is, however, a major concern about the privacy of patients when using online resources. Patients usually choose to keep their information confidential, which should be only accessible to authorized individuals. The most current remote patient monitoring system is organization-centric and patient's privacy and security rely on healthcare providers' mercy. Blockchain technologies have attracted the attention of researchers for designing eHealth applications to provide patients with secure and privacy-preserving health services. Blockchain researchers have recently proposed some models for remote patient monitoring systems. However, most of those researchers have applied public blockchains where health data is available to all participants with the property of data tamper-proof. In this paper, we propose a novel remote patient monitoring model using a decentralized private blockchain to protect patient's privacy and increase the system's efficiency. The private blockchain will be implemented on Hyperledger Fabric where a Patient-centric Agents (PCA) manage patient's data and coordinate authorization to form a secure channel to transmit data to the private blockchain. A hybrid consensus by combining Proof of Integrity (PoI) and Proof of Validity (PoV) is used to protect data privacy and integrity when retrieving data from a blockchain-based cloud database. Finally, the Merkle Tree algorithm was used for data processing and authentication when collecting data and uploading it to a cloud database. © 2020 IEEE.

CRICRATE : A cricket match conduction and player evaluation framework

Cyberbullying detection on social networks using machine learning approaches

  • Authors: Islam, Md Manowarul , Uddin, Md Ashraf , Islam, Linta , Akter, Arnisha , Sharmin, Selina , Acharjee, Uzzal
  • Date: 2020
  • Type: Text , Conference paper
  • Relation: 2020 IEEE Asia-Pacific Conference on Computer Science and Data Engineering, CSDE 2020
  • Full Text: false
  • Reviewed:
  • Description: The use of social media has grown exponentially over time with the growth of the Internet and has become the most influential networking platform in the 21st century. However, the enhancement of social connectivity often creates negative impacts on society that contribute to a couple of bad phenomena such as online abuse, harassment cyberbullying, cybercrime and online trolling. Cyberbullying frequently leads to serious mental and physical distress, particularly for women and children, and even sometimes force them to attempt suicide. Online harassment attracts attention due to its strong negative social impact. Many incidents have recently occurred worldwide due to online harassment, such as sharing private chats, rumours, and sexual remarks. Therefore, the identification of bullying text or message on social media has gained a growing amount of attention among researchers. The purpose of this research is to design and develop an effective technique to detect online abusive and bullying messages by merging natural language processing and machine learning. Two distinct freatures, namely Bag-of Words (BoW) and term frequency-inverse text frequency (TFIDF), are used to analyse the accuracy level of four distinct machine learning algorithms. © 2020 IEEE.

A patient agent controlled customized blockchain based framework for internet of things

  • Authors: Uddin, Md Ashraf
  • Date: 2021
  • Type: Text , Thesis , PhD
  • Full Text:
  • Description: Although Blockchain implementations have emerged as revolutionary technologies for various industrial applications including cryptocurrencies, they have not been widely deployed to store data streaming from sensors to remote servers in architectures known as Internet of Things. New Blockchain for the Internet of Things models promise secure solutions for eHealth, smart cities, and other applications. These models pave the way for continuous monitoring of patient’s physiological signs with wearable sensors to augment traditional medical practice without recourse to storing data with a trusted authority. However, existing Blockchain algorithms cannot accommodate the huge volumes, security, and privacy requirements of health data. In this thesis, our first contribution is an End-to-End secure eHealth architecture that introduces an intelligent Patient Centric Agent. The Patient Centric Agent executing on dedicated hardware manages the storage and access of streams of sensors generated health data, into a customized Blockchain and other less secure repositories. As IoT devices cannot host Blockchain technology due to their limited memory, power, and computational resources, the Patient Centric Agent coordinates and communicates with a private customized Blockchain on behalf of the wearable devices. While the adoption of a Patient Centric Agent offers solutions for addressing continuous monitoring of patients’ health, dealing with storage, data privacy and network security issues, the architecture is vulnerable to Denial of Services(DoS) and single point of failure attacks. To address this issue, we advance a second contribution; a decentralised eHealth system in which the Patient Centric Agent is replicated at three levels: Sensing Layer, NEAR Processing Layer and FAR Processing Layer. The functionalities of the Patient Centric Agent are customized to manage the tasks of the three levels. Simulations confirm protection of the architecture against DoS attacks. Few patients require all their health data to be stored in Blockchain repositories but instead need to select an appropriate storage medium for each chunk of data by matching their personal needs and preferences with features of candidate storage mediums. Motivated by this context, we advance third contribution; a recommendation model for health data storage that can accommodate patient preferences and make storage decisions rapidly, in real-time, even with streamed data. The mapping between health data features and characteristics of each repository is learned using machine learning. The Blockchain’s capacity to make transactions and store records without central oversight enables its application for IoT networks outside health such as underwater IoT networks where the unattended nature of the nodes threatens their security and privacy. However, underwater IoT differs from ground IoT as acoustics signals are the communication media leading to high propagation delays, high error rates exacerbated by turbulent water currents. Our fourth contribution is a customized Blockchain leveraged framework with the model of Patient-Centric Agent renamed as Smart Agent for securely monitoring underwater IoT. Finally, the smart Agent has been investigated in developing an IoT smart home or cities monitoring framework. The key algorithms underpinning to each contribution have been implemented and analysed using simulators.
  • Description: Doctor of Philosophy

Dynamically recommending repositories for health data : a machine learning model

  • Authors: Uddin, Md Ashraf , Stranieri, Andrew , Gondal, Iqbal , Balasubramanian, Venki
  • Date: 2020
  • Type: Text , Conference proceedings
  • Relation: 2020 Australasian Computer Science Week Multiconference, ACSW 2020
  • Full Text: false
  • Reviewed:
  • Description: Recently, a wide range of digital health record repositories has emerged. These include Electronic Health record managed by the government, Electronic Medical Record (EMR) managed by healthcare providers, Personal Health Record (PHR) managed directly by the patient and new Blockchain-based systems mainly managed by technologies. Health record repositories differ from one another on the level of security, privacy, and quality of services (QoS) they provide. Health data stored in these repositories also varies from patient to patient in sensitivity, and significance depending on medical, personal preference, and other factors. Decisions regarding which digital record repository is most appropriate for the storage of each data item at every point in time are complex and nuanced. The challenges are exacerbated with health data continuously streamed from wearable sensors. In this paper, we propose a recommendation model for health data storage that can accommodate patient preferences and make storage decisions rapidly, in real-time, even with streamed data. The model maps health data to be stored in the repositories. The mapping between health data features and characteristics of each repository is learned using a machine learning-based classifier mediated through clinical rules. Evaluation results demonstrate the model's feasibility. © 2020 ACM.
  • Description: E1
  • 1