Efficient data handling in smart healthcare using Quotient Hash Trees and gaussian hilbert regression
Significant amounts of heterogeneous medical data are developed daily from several medical devices, and sensor data analysis across IoT domains is becoming challenging. The conservative data warehouses possess the potential to integrate data and support interactive data exploration. However, transfe...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-09-01
|
| Series: | Ain Shams Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2090447925002941 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839619710972329984 |
|---|---|
| author | T. Kalai Selvi S. Sasirekha |
| author_facet | T. Kalai Selvi S. Sasirekha |
| author_sort | T. Kalai Selvi |
| collection | DOAJ |
| description | Significant amounts of heterogeneous medical data are developed daily from several medical devices, and sensor data analysis across IoT domains is becoming challenging. The conservative data warehouses possess the potential to integrate data and support interactive data exploration. However, transferring data with minimum loss and storing it in a unified format is arduous and time-consuming. The proposed Gaussian Replicating Hilbert Regression and Quotient Hash Tree (GRHR-QHT) method is introduced to convert heterogeneous data into a unified format with improved accuracy and reduced time. The proposed GRHR-QHT performs three processes: data collection, transfer, and storage. At first, linear acceleration and angular velocity-based vector data collection are transmitted to the data management server. The collected data are stored in the input matrix. The data management server constructs multiple data into a unified format without any loss using GRH-based sequencing. This data management server reduces variance among aspect spaces through minimum distance with empirical organizations of samples. Also, the Polynomial Regression function is used to determine the relationship between the independent parameters. Then, unified data gets stored in the data management server using a Quotient Hash Tree (QHT) for easy access and less space complexity. The experimental assessment of the GRHR-QHT technique and existing methods is compared with different metrics: accuracy, time, error rate, space complexity, throughput, packet delivery ratio, service availability, reliability, response time, and end-to-end delay. The outcome of the suggested method is compared with conventional techniques in terms of improved 11% accuracy and 36% throughput with 33%, 41%, and 20% minimum time, error rate, and space complexity. |
| format | Article |
| id | doaj-art-6afb55f69d9b49a8b4967a93cdf3c0e2 |
| institution | Matheson Library |
| issn | 2090-4479 |
| language | English |
| publishDate | 2025-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ain Shams Engineering Journal |
| spelling | doaj-art-6afb55f69d9b49a8b4967a93cdf3c0e22025-07-23T05:23:59ZengElsevierAin Shams Engineering Journal2090-44792025-09-01169103553Efficient data handling in smart healthcare using Quotient Hash Trees and gaussian hilbert regressionT. Kalai Selvi0S. Sasirekha1Department of Computer Science and Engineering, Erode Sengunthar Engineering College, Erode, Tamilnadu, India; Corresponding author.Department of Computer Science and Engineering, National Institute of Technical Teachers Training and Research, Chennai, Tamilnadu, IndiaSignificant amounts of heterogeneous medical data are developed daily from several medical devices, and sensor data analysis across IoT domains is becoming challenging. The conservative data warehouses possess the potential to integrate data and support interactive data exploration. However, transferring data with minimum loss and storing it in a unified format is arduous and time-consuming. The proposed Gaussian Replicating Hilbert Regression and Quotient Hash Tree (GRHR-QHT) method is introduced to convert heterogeneous data into a unified format with improved accuracy and reduced time. The proposed GRHR-QHT performs three processes: data collection, transfer, and storage. At first, linear acceleration and angular velocity-based vector data collection are transmitted to the data management server. The collected data are stored in the input matrix. The data management server constructs multiple data into a unified format without any loss using GRH-based sequencing. This data management server reduces variance among aspect spaces through minimum distance with empirical organizations of samples. Also, the Polynomial Regression function is used to determine the relationship between the independent parameters. Then, unified data gets stored in the data management server using a Quotient Hash Tree (QHT) for easy access and less space complexity. The experimental assessment of the GRHR-QHT technique and existing methods is compared with different metrics: accuracy, time, error rate, space complexity, throughput, packet delivery ratio, service availability, reliability, response time, and end-to-end delay. The outcome of the suggested method is compared with conventional techniques in terms of improved 11% accuracy and 36% throughput with 33%, 41%, and 20% minimum time, error rate, and space complexity.http://www.sciencedirect.com/science/article/pii/S2090447925002941Heterogeneous Medical DataGaussian ReplicatingKernel HilbertQuotient Hash TreeData Management ServerInternet of Things |
| spellingShingle | T. Kalai Selvi S. Sasirekha Efficient data handling in smart healthcare using Quotient Hash Trees and gaussian hilbert regression Ain Shams Engineering Journal Heterogeneous Medical Data Gaussian Replicating Kernel Hilbert Quotient Hash Tree Data Management Server Internet of Things |
| title | Efficient data handling in smart healthcare using Quotient Hash Trees and gaussian hilbert regression |
| title_full | Efficient data handling in smart healthcare using Quotient Hash Trees and gaussian hilbert regression |
| title_fullStr | Efficient data handling in smart healthcare using Quotient Hash Trees and gaussian hilbert regression |
| title_full_unstemmed | Efficient data handling in smart healthcare using Quotient Hash Trees and gaussian hilbert regression |
| title_short | Efficient data handling in smart healthcare using Quotient Hash Trees and gaussian hilbert regression |
| title_sort | efficient data handling in smart healthcare using quotient hash trees and gaussian hilbert regression |
| topic | Heterogeneous Medical Data Gaussian Replicating Kernel Hilbert Quotient Hash Tree Data Management Server Internet of Things |
| url | http://www.sciencedirect.com/science/article/pii/S2090447925002941 |
| work_keys_str_mv | AT tkalaiselvi efficientdatahandlinginsmarthealthcareusingquotienthashtreesandgaussianhilbertregression AT ssasirekha efficientdatahandlinginsmarthealthcareusingquotienthashtreesandgaussianhilbertregression |