Data Cleaning Method in Wireless Sensor-Based on Intelligence Technology

Diachok, Roman; Klym, Halyna

doi:10.23939/istcmtm2022.02.005

Cited by 2 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Examples of machine-learning-based data cleaning methods for IoT include: Clustering: This technique involves grouping similar data points together and can be used to identify and correct errors and inconsistencies in the data. For instance, [ 16 ] proposed an algorithm for removing replicated records that were clustered-based, and the effectiveness of data cleaning methods was evaluated. Anomaly detection: This technique involves identifying data points that deviate from the norm and can be used to identify and correct errors and outliers in the data.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Deep-Reinforcement-Learning-Based IoT Sensor Data Cleaning Framework for Enhanced Data Analytics

Mohammed

Sultan²,

Lee

et al. 2023

Sensors

View full text Add to dashboard Cite

The Internet of things (IoT) combines different sources of collected data which are processed and analyzed to support smart city applications. Machine learning and deep learning algorithms play a vital role in edge intelligence by minimizing the amount of irrelevant data collected from multiple sources to facilitate these smart city applications. However, the data collected by IoT sensors can often be noisy, redundant, and even empty, which can negatively impact the performance of these algorithms. To address this issue, it is essential to develop effective methods for detecting and eliminating irrelevant data to improve the performance of intelligent IoT applications. One approach to achieving this goal is using data cleaning techniques, which can help identify and remove noisy, redundant, or empty data from the collected sensor data. This paper proposes a deep reinforcement learning (deep RL) framework for IoT sensor data cleaning. The proposed system utilizes a deep Q-network (DQN) agent to classify sensor data into three categories: empty, garbage, and normal. The DQN agent receives input from three received signal strength (RSS) values, indicating the current and two previous sensor data points, and receives reward feedback based on its predicted actions. Our experiments demonstrate that the proposed system outperforms a common time-series-based fully connected neural network (FCDQN) solution, with an accuracy of around 96% after the exploration mode. The use of deep RL for IoT sensor data cleaning is significant because it has the potential to improve the performance of intelligent IoT applications by eliminating irrelevant and harmful data.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Clustering: This technique involves grouping similar data points together and can be used to identify and correct errors and inconsistencies in the data. For instance, [ 16 ] proposed an algorithm for removing replicated records that were clustered-based, and the effectiveness of data cleaning methods was evaluated.…”

Section: Related Workmentioning

confidence: 99%

Deep-Reinforcement-Learning-Based IoT Sensor Data Cleaning Framework for Enhanced Data Analytics

Mohammed

Sultan²,

Lee

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Due to the rapid growth and diversity of IoTconnected devices, the traditional centralized network architecture must meet new service requirements, and challenges, and effectively identify and provide large amounts of data concerning security, integrity, and privacy. It is important to develop methods for cleaning data in such networks [6]. To solve the mentioned problems and achieve a better quality of service (QoS) and quality of experience (QoE) by performing data storage and processing operations physically near the data source in a distributed infrastructure, Fog/Edge computing is applied [7][8].…”

Section: Disadvantagesmentioning

confidence: 99%

Modified Fog-Based Trust Method of Data Monitoring for Multi-Sensor Configuration Systems

Diachok¹,

Klym²

2022

MEM

Self Cite

View full text Add to dashboard Cite

.A modified Fog-based trust method to prevent third-party interference in establishing trust relationships between sensors and cloud service providers in multi-sensor systems is considered. Trust in behavior between nodes is established at the level of wireless sensor networks; in the nodes and objects data at the Fog layer. With more detailed data analysis of the latter, it becomes possible to monitor the trust status of the entire network, detect data attacks and recover from misjudged nodes. Fog layer can be built as a reliable third party. Experiment results show that the proposed trust mechanism is inherent in advantage due to reducing energy consumption and ensuring the trust state of Edge nodes and whole the network as well as detecting hidden attacks on data and recovering nodes.

show abstract

Data Cleaning Method in Wireless Sensor-Based on Intelligence Technology

Cited by 2 publications

References 10 publications

Deep-Reinforcement-Learning-Based IoT Sensor Data Cleaning Framework for Enhanced Data Analytics

Deep-Reinforcement-Learning-Based IoT Sensor Data Cleaning Framework for Enhanced Data Analytics

Modified Fog-Based Trust Method of Data Monitoring for Multi-Sensor Configuration Systems

Contact Info

Product

Resources

About