Wireless Sensor Network Modeling Using Modified Recurrent Neural Networks: Application to Fault Detection

Moustapha, A.I.; Šelmić, Rastko R.

doi:10.1109/icnsc.2007.372797

Cited by 23 publications

(25 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The learning happens in Bayesian methods by adapting the probability distribution to efficiently learn the uncertain labels [15,16]. The important aspect of this learning technique is, it uses the current knowledge (that the collected data samples (D)) to refine values of prior belief into posterior belief values…”

Section: Bayesian Learnersmentioning

confidence: 99%

A Study of Machine Learning in Wireless Sensor Network

Khan¹,

Samad²

2017

ijcna

View full text Add to dashboard Cite

-Within this Paper, a concept of machine learning strategies suggested. In this investigation to address the design issues in WSNs is introduced. As can be viewed within this paper, countless endeavors have induced up to now; several layout issues in wireless sensor networks have been remedied employing numerous machine learning strategies. Utilizing machine learning based algorithms in WSNs need to deem numerous constraints, for instance, minimal sources of the network application that really needs distinct events to be tracked as well as other operational and non-operational aspects.

show abstract

Section: Bayesian Learnersmentioning

confidence: 99%

A Study of Machine Learning in Wireless Sensor Network

Khan¹,

Samad²

2017

ijcna

View full text Add to dashboard Cite

show abstract

“…The Kriging interpolation [10][11], IDW [12] [13], KNN [14], Gaussian Mixture Model [15], or RNN [16] are often used to process the geographic information. These methods are also used to estimate the missing data in WSNs.…”

Section: Introductionmentioning

confidence: 99%

Missing Data Reconstruction Using Adaptively Updated Dictionary in Wireless Sensor Networks

Zhao¹,

Fang²

2017

Proceedings of the 7th International Conference on Computer Engineering and Networks — PoS(CENet2017)

View full text Add to dashboard Cite

Due to external interference or fault, the collected sensor data is often missed or abnormal. It's significant to reconstruct the missing data, especially the large-scale missing data. In this paper, a missing sensor data reconstruction method based on the adaptively updated dictionary is presented. The K-SVD algorithm is used to train the historical data frames which are collected at different time to generate the original dictionary atoms. Moreover, in order to meet the realtime, continuous characteristics of sensor data, an adaptive dictionary update algorithm is studiedwhich. It calculates the correlation between the current reconstructed data frame and the largest weight frame in the training dictionary to update the dictionary. The experimental results are fully analyzed by the open data set. The results show that the proposed method has higher reconstructed precision especially the interval of data frames which is more than 60 minutes compared with other commonly used methods .

show abstract

“…Death of central point is the end of the system. In contrast to it, decentralized architecture needs powerful autonomous entities on one hand, and [44], fault detection [45], self-con�guration [46] Arti�cial immune network [34] Immune system [47] Misbehavior detection [48], image pattern recognition [49] Genetic algorithm [35] Natural evolution system Dynamic shortest path routing [50], lifetime maximization [51] Cellular automata [29] Life Life like/ game of life Large network simulations [52], area coverage scheme [53] Rendering (computer graphics) [30] Patterns of animal skins, birds feathers, mollusk shells, and bacterial colonies [54] Range-free localization [55] Fractal geometry Clouds, river networks, snow�akes, cauli�ower or broccoli, and systems of blood vessels and pulmonary vessels, ocean waves Antenna designing [56] Communication networks and protocols Epidemiology Cross-layer communication protocol [57,58] [61], target tracking [62] then it also re�ects the behavior of adaptation (�exible to changing environment), self-assembly (unit to be one), selforganizing (interaction for the one), and self-regulation, (keeping the process tunably smooth) [25] as in WSN due to the distributed knowledge, distributed control and scalable properties on the other hand. Although the architecture is application dependent, decentralized system has variety of advantages over the centralized system.…”

Section: � �Rom �Eal To �Rti��ialmentioning

confidence: 99%

Intelligent Optimization of Wireless Sensor Networks through Bio-Inspired Computing: Survey and Future Directions

Jabbar

Iram

Minhas

et al. 2013

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

is survey article is a comprehensive discussion on Intelligent Optimization of Wireless Sensor Networks through Bio-Inspired Computing. e marvelous perfection of biological systems and its different aspects for optimized solutions for non-biological problems is presented here in detail. In the current research inclination, hiring of biological solutions to solve and optimize different aspects of arti�cial systems' problems has been shaped into an important �eld with the name of bio-inspired computing. We have tabulated the exploitation of key constituents of biological system for developing bio-inspired systems to represent its importance and emergence in problem solving trends. We have presented how the metaphoric relationship is developed between the two biological and non-biological systems by quoting an example of relationship between prevailing wireless system and the natural system. Interdisciplinary research is playing a splendid contribution for various problems' solving. e process of combining the individuals' output to form a single problem solving solution is depicted in three-stage ensemble design. Also the hybrid solutions from computational intelligence-based optimization are elongated to demonstrate the emergent involvement of these inspired systems with rich references for the interested readers. It is concluded that these perfect creations have remedies for most of the problems in non-biological system.

show abstract

Wireless Sensor Network Modeling Using Modified Recurrent Neural Networks: Application to Fault Detection

Cited by 23 publications

References 18 publications

A Study of Machine Learning in Wireless Sensor Network

A Study of Machine Learning in Wireless Sensor Network

Missing Data Reconstruction Using Adaptively Updated Dictionary in Wireless Sensor Networks

Intelligent Optimization of Wireless Sensor Networks through Bio-Inspired Computing: Survey and Future Directions

Contact Info

Product

Resources

About