Cooperative learning model based on multi-agent architecture for embedded intelligent systems

Villaverde, Mónica; Pérez, David; Moreno, Félix

doi:10.1109/iecon.2014.7048892

Cited by 4 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, memory requirements have to be considered especially for embedded system developments. Moreover, it is important to mention that the system is not complete yet, since cooperative algorithms are not included although several cooperative algorithms have been studied independently [ 15 , 16 ]. For this reason the current system is able to learn new kind of objects but it is not able to label them.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Self-Learning Embedded System for Object Identification in Intelligent Infrastructure Sensors

Villaverde

Pérez

Moreno

2015

Sensors

Self Cite

View full text Add to dashboard Cite

The emergence of new horizons in the field of travel assistant management leads to the development of cutting-edge systems focused on improving the existing ones. Moreover, new opportunities are being also presented since systems trend to be more reliable and autonomous. In this paper, a self-learning embedded system for object identification based on adaptive-cooperative dynamic approaches is presented for intelligent sensor’s infrastructures. The proposed system is able to detect and identify moving objects using a dynamic decision tree. Consequently, it combines machine learning algorithms and cooperative strategies in order to make the system more adaptive to changing environments. Therefore, the proposed system may be very useful for many applications like shadow tolls since several types of vehicles may be distinguished, parking optimization systems, improved traffic conditions systems, etc.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Different weighting procedures were analyzed in [ 15 ] such as global weighting and conditional weighting. In the first one, each device has its own assigned weight which provides information on how good each device is independently of the category of the detected object.…”

Section: Methodsmentioning

confidence: 99%

Self-Learning Embedded System for Object Identification in Intelligent Infrastructure Sensors

Villaverde

Pérez

Moreno

2015

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to minimize this influence, a combination of several radars working together improve the results. 26 Therefore, in this work, a comparison among different algorithms is analyzed to demonstrate the utility of the cooperation.…”

Section: Pedestrian and Car Detectionmentioning

confidence: 99%

“…Then, the first 128 points of the fast Fourier transform (FFT) of the 512 points signals are introduced as inputs to the first-stage classifiers. In this case, instead of using a classification tree, 24,26 an ANN is used to provide the results of each radar device for this first stage.…”

Section: Pedestrian and Car Detectionmentioning

confidence: 99%

“…In contrast, if both results do not match, the weight of that classifier will be decreased by subtracting a fixed value d À to reduce its influence for the future activity. 26 It means that the algorithm is continuously updating the weights and therefore it can adapt the system to external or internal changes, which affects the reliability of the classifiers. Figure 6 shows the pseudocode of this algorithm.…”

Section: Basic Weighted Voting-based Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

On the adaptability of ensemble methods for distributed classification systems: A comparative analysis

Villaverde

Aledo

Pérez

et al. 2019

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

In this work, a two-stage architecture is used to analyze the information collected from several sensors. The first stage makes classifications from partial information of the entire target (i.e. from different points of view or from different kind of measures) using a simple artificial neural network as a classifier. In addition, the second stage aggregates all the estimations given by the ensemble in order to obtain the final classification. Four different ensembles methods are compared in the second stage: artificial neural network, plurality majority, basic weighted majority, and stochastic weighted majority. However, not only reliability is an important factor but also adaptation is critical when the ensemble is working in changing environments. Therefore, the artificial neural network and the plurality majority algorithm are compared against our two proposed adaptive algorithms. Unlike artificial neural network, majority methods do not require previous training. The effects of improving the first stage and how the system behaves when different perturbations are presented have been measured. Results have been obtained from two applications: a realistic one and another simpler one, with more training examples for a more accurate comparison. These results show that artificial neural network is the most accurate proposal, whereas the most innovative proposed stochastic weighted voting is the most adaptive one.

show abstract

Educational technology: Exploring the convergence of technology and pedagogy through mobility, interactivity, AI, and learning tools

Alam,

Mohanty

2023

Cogent Engineering

View full text Add to dashboard Cite

Cooperative learning model based on multi-agent architecture for embedded intelligent systems

Cited by 4 publications

References 14 publications

Self-Learning Embedded System for Object Identification in Intelligent Infrastructure Sensors

Self-Learning Embedded System for Object Identification in Intelligent Infrastructure Sensors

On the adaptability of ensemble methods for distributed classification systems: A comparative analysis

Educational technology: Exploring the convergence of technology and pedagogy through mobility, interactivity, AI, and learning tools

Contact Info

Product

Resources

About