Machine Learning based Health Prediction System using IBM Cloud as PaaS

Neloy, Asif Ahmed; Alam, Sazid; Bindu, Rafia Alif; Moni, Nusrat Jahan

doi:10.1109/icoei.2019.8862754

Cited by 19 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The majority of studies related to CIoT were published in non-healthcare fields such as smart cities [100,101], transportation [102], traffic control [103], agriculture [43], smart environments [82], and smart homes [84]. In the healthcare field, the IoT and Cloud have been considered two separate technologies, and few studies have focused on their integration.…”

Section: Main Domains Of the Cloud-based Iot (Crq3)mentioning

confidence: 99%

“…The main reason for using IBM is to upgrade the security services in the Cloud computing environment to provide greater protection from users in Cloud and multiple Cloud spaces. In this regard, Neloy et al [103] proposed a "Machine learning based on health prediction system using IBM Cloud as PaaS" that introduced IBM Cloud and IBM Watson studio as a platform to store and maintain smart healthcare data.…”

Section: Cloud Platforms (Crq7)mentioning

confidence: 99%

See 1 more Smart Citation

Cloud-Based Internet of Things in Healthcare Applications: A Systematic Literature Review

Gholamhosseini

Behmanesh

Nasiri

et al. 2023

Front Health Inform

View full text Add to dashboard Cite

Introduction: The Internet of Things (IoT) and Cloud computing are two recent technological advances whose potential have not been realized in a range of industries. These technologies have been used in healthcare systems to improve their performance. In this regard, the IoT generates a large amount of data; also, cloud computing is a viable option for data storage and complex computing. The purpose of this study is to identify and categorize various aspects of CIoT-based healthcare in terms of main application domains, sensors, wireless communication technologies, messaging protocols, cloud platforms, and artificial intelligence (AI) algorithms.Material and Methods: We conducted a literature systematic review and reported according to the PRISMA guideline. PubMed, IEEE, Scopus, and Web of Science were searched using the related keywords and their synonyms. Two independent authors reviewed the papers' eligibility according to the defined inclusion and exclusion criteria.Results: Of the 2,118 papers retrieved, 61 were eventually selected in the study. Results of the present study revealed that the majority of CIoT research works were applied to patient monitoring systems and cardiovascular patient monitoring systems using Amazon and IBM dominating Cloud platforms. In addition, the most widely used communication technologies for CIoT in healthcare are cellular networks (3G and 4G), Wi-Fi, and Bluetooth. Cardiovascular, environmental, and position sensors are also the most common types of sensors used in healthcare CIoT applications. Among the Cloud platform providers, Amazon and IBM have the highest utility in healthcare systems. The majority of the included studies used Cloud-based AI algorithms to diagnose, classify, and predict diseases.Conclusion: The integration of the Cloud into the IoT can support healthcare systems in terms of processing power, storage capacity, security, privacy, performance, reliability, and scalability. We suggest researchers conduct experimental studies to evaluate the effectiveness of the CIoT approach in healthcare applications.

show abstract

Section: Main Domains Of the Cloud-based Iot (Crq3)mentioning

confidence: 99%

Section: Cloud Platforms (Crq7)mentioning

confidence: 99%

Cloud-Based Internet of Things in Healthcare Applications: A Systematic Literature Review

Gholamhosseini

Behmanesh

Nasiri

et al. 2023

Front Health Inform

View full text Add to dashboard Cite

show abstract

“…For the performance enhancement, further, improvement has been proposed by the researchers based on the machine learning approach. The machine learning approach makes the system more powerful and affectively utilised for WBAN applications [10,[24][25][26][27][28].…”

Section: Literature Studymentioning

confidence: 99%

Energy efficiency based lifetime improvement for wireless body area network

Guo

Syed

2022

IET Communications

View full text Add to dashboard Cite

The efficient selection of cluster head nodes for the transmission of the data to the sink node is the major requirement of the wireless body area network. The present work deals with the efficient selection of the cluster head node and uniform rotation of the cluster head based on the four important parameters, i.e. residual energy of the node, mean value of the Euclidean distance, priority level based on data sensitivity, and device physical capability. The proposed energy‐efficient Bayesian clustering algorithm uses naïve Bayesian approach for the appropriate selection of the cluster head node. The selected cluster head node collects the data from the sensor nodes in each round. The collected data is first aggregated and then transmitted to the base station. In the steady‐state phase, the proposed algorithm follows energy‐analysed‐TDMA based energy‐efficient data transmission method which further reduces the energy consumption as compared to the standard LEACH protocol. The performance of the proposed protocol is compared to the existing protocol on the MATLAB simulator. The proposed scheme increases the overall lifetime of the network by approximately 1.5 times and also reduces the average energy consumption of the network.

show abstract