.png){kind=icon}
返回
Effective energy usage and data compression approach using data mining algorithms for IoT data
.png){kind=icon}
PRE
AI
DOI：10.1111/exsy.12997.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The emergence of technology and communication system paved way for the development of the internet of things (IoT). The IoT system generates diversified data and the quantity of the data is also huge. The IoT systems are developed to adhere to the situation and to make intelligent decisions in a specified time. Hence, the IoT system necessitates high processing and storage environment, which makes the effective response in a short-duration. The data transmission across the mobile nodes and cloud service has made huge utilization of energy. The storage and energy consumption are considered as major issues in the IoT system whereas these issues will reflect in the performance of the IoT system. Initiation of edge computing into the IoT system permits the workload to be offloaded from the cloud providers, which is attained from the closer location of the source of data. This improves privacy, minimizes the saving time, and traffic. In this article, an Effective Energy usage and Data Compression Approach using Data Mining proposed for IoT data. The proposed approach is investigated by considering the driving behaviour and it achieves effective compression without influencing the quality of the data. The stress level of the driver is also identified with high accuracy.
Keyword:
backpropagation neural network
classification
data compression
Huffman coding
machine learning
期刊
IF:
2.3
论文数:
2.6K
被引数:
3.8K
机构
引用论文
.png){kind=icon}
An Efficient Technique for Hardware/Software Partitioning Process in Codesign一种针对硬件/软件划分过程的协同设计高效技术
OAAI
OAAI分享收藏A distributed real-time data prediction and adaptive sensing approach for wireless sensor networks
OAAI
OAAI分享收藏分享收藏
查看更多内容