Outlier Detection Technique for Wireless Sensor  Network Using GAN with Autoencoder to Increase the Network Lifetime

Sarangi, Biswaranjan; Tripathy, Biswajit

doi:10.5815/ijcnis.2023.01.03

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[28], a technique is presented that combines time series analysis, entropy, and classification using random forests. Finally, the technique in [52] uses Generative Adversarial Networks (GANs), an unsupervised learning approach, to detect outliers in WSNs, implementing two neural networks and autoencoders trained through the Adam optimizer.…”

Section: A Characteristics Of Proposals For Outlier Detection In Wsnsmentioning

confidence: 99%

See 1 more Smart Citation

A Literature Review on Outlier Detection in Wireless Sensor Networks

García,

Rivera,

Perez

2024

JAIT

View full text Add to dashboard Cite

Wireless sensor networks have become an important element of technologies such as the Internet ofThings due to their ability to obtain sensory data from the physical world in tracking and monitoring applications. However, such networks are susceptible to the presence of outliers mainly due to errors or failures in the sensor nodes or the presence of events that alter the reading patterns. To address this problem, many researchers have turned their efforts to the development of outlier detection techniques that achieve maximum detection rate with the highest possible efficiency, given the limited resources typical of this type of networks. In this study, 33 papers on outlier detection techniques in wireless sensor networks between 2018 and 2023 were analyzed with the aim of describing the characteristics of these techniques, their metrics and test conditions, application areas, and possible limitations. The results showed mostly hybrid, distributed, online and multivariate sensing proposals in addition to the exploitation of spatiotemporal correlations of the data. In terms of efficiency, almost all of them reported detection rates above 85% and in several cases up to 100% but in specific conditions; with application areas especially related to environmental monitoring and care. Finally, the most relevant limitations encountered include high computational complexity and high resource consumption, sensitivity to parameters, lack of scalability, and dependence on specific assumptions about data distribution.

show abstract

Section: A Characteristics Of Proposals For Outlier Detection In Wsnsmentioning

confidence: 99%

“…Finally, potential limitations of the proposed GAN method [52] could include the computational complexity involved in implementing the GAN, the processing time required, and the possibility of obtaining false positives or negatives in outlier detection.…”

Section: Detection Techniques Limitationsmentioning

confidence: 99%

A Literature Review on Outlier Detection in Wireless Sensor Networks

García,

Rivera,

Perez

2024

JAIT

View full text Add to dashboard Cite

show abstract

“…The GAN is an unsupervised learning method, consisting of two modules, generator G and discriminator D [24][25][26][27]. Its main purpose is to conduct game training between the generator and discriminator to find the Nash balance.…”

Section: Improved Ganmentioning

confidence: 99%

Optimal Scheduling of Virtual Power Plant Considering Revenue Risk with High-Proportion Renewable Energy Penetration

Zhang,

Zhao,

et al. 2023

Electronics

View full text Add to dashboard Cite

Distributed power supplies have gradually become a new trend in power supply development, but access to a large number of distributed energy sources has a certain impact on the stable operation of the power grid. A virtual power plant (VPP) can integrate a variety of distributed power sources for coordination and optimization; thus, it can effectively solve the difficulties faced by a distributed energy grid connection and promote the complementarity of energy sources. However, renewable energy often has a degree of volatility and randomness when distributed, which can bring certain risks to the operation of the VPP. In order to consider the risks brought by renewable energy, an optimal scheduling model of the VPP, based on an improved generative adversarial network (GAN) and the conditional value at risk (CVaR), was proposed to measure the relationship between the benefits and risks. Firstly, the uncertainty of new energy is analyzed, and wind power and photovoltaic scenarios are generated by the improved GAN; then, typical scenarios are generated by the k-medoids method. Finally, based on the CVaR, the optimal scheduling model of the VPP is established to study the effect of risk weight on VPP revenue. The results show that the model can effectively measure the relationship between the benefits and risks and can provide some references for the VPP to make reasonable operational decisions with different risk preferences.

show abstract

Deep Learning-Based Approach for Outlier Detection in Wireless Sensor Network

Sarangi

Tripathy²

2023

Algorithms for Intelligent Systems

View full text Add to dashboard Cite

Outlier Detection Technique for Wireless Sensor Network Using GAN with Autoencoder to Increase the Network Lifetime

Cited by 3 publications

References 0 publications

A Literature Review on Outlier Detection in Wireless Sensor Networks

A Literature Review on Outlier Detection in Wireless Sensor Networks

Optimal Scheduling of Virtual Power Plant Considering Revenue Risk with High-Proportion Renewable Energy Penetration

Deep Learning-Based Approach for Outlier Detection in Wireless Sensor Network

Contact Info

Product

Resources

About