Near field acoustic localization under unfavorable conditions using feedforward neural network for processing time difference of arrival

Kovandžić, Marko; Nikolić, Vlastimir; Al-Noori, Abdulathim; źirić, Ivan; Simonović, Miloš

doi:10.1016/j.eswa.2016.11.030

Cited by 16 publications

(14 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The procedure is well established in the conventional robotics [19][20][21][22]. Neural networks are proven approximators distinguished by simple implementation and excellent speed of performance [23]. They are employed as a black box, which means that a certain input produces a desired output, but how the network achieves the result is left to a self-organizing (artificial intelligence) algorithm [24].…”

Section: Fig 2 Tensile Modulus (Young's Modulus) Of Engineering and mentioning

confidence: 99%

“…Neural networks are proven approximators distinguished by simple implementation and excellent speed of performance [23]. They are employed as a black box, which means that a certain input produces a desired output, but how the network achieves the result is left to a self-organizing (artificial intelligence) algorithm [24]. The last property makes them suitable for a broad range of users, who are not necessarily familiar with the control theory, robotics or mechanics at all.…”

Section: Fig 2 Tensile Modulus (Young's Modulus) Of Engineering and mentioning

confidence: 99%

“…The results were evaluated for the range of different configurations and training parameters, in order to find an optimal solution. Both the training and the testing were performed by software designed for the purpose of the previous experiment [23]. The experiment started with the structure of a neural network.…”

Section: Fig 5 An Appearance Of the Employed Soft Robotmentioning

confidence: 99%

“…The testing error decreases up to some value and then stagnates or even increases. Such a case is known as over-trained neural network [24]. The approximations were performed using two term exponential function.…”

Section: Fig 5 An Appearance Of the Employed Soft Robotmentioning

confidence: 99%

See 3 more Smart Citations

Soft Robot Positioning Using Artificial Neural Network

et al. 2019

Self Cite

View full text Add to dashboard Cite

The experiment investigated the performance of an artificial neural network in solving the inverse kinematic problem of a soft robot. For this purpose, a simple soft robot was designed of building blocks, stringed on three rubber hoses, and an actuating system, to provide the hydraulic pressure. An axial extending of a hose, while the others are in the relaxed state, results in bending of the robot. The network was employed, as a black box, to approximate the behavior of the system. In accordance with the purpose, the input consisted of the desired spatial coordinates and the output of the step motor angular displacements. The network was trained and tested using records collected at 200 randomly chosen robot positions. The relative testing error of positioning, about 5%, confirmed a predictable robot behavior. The solution proposed is competitive in terms of simplicity, safety and price of realization. The experiment provided basics for the future research of the design of modular soft robots.

show abstract

Section: Fig 2 Tensile Modulus (Young's Modulus) Of Engineering and mentioning

confidence: 99%

Section: Fig 2 Tensile Modulus (Young's Modulus) Of Engineering and mentioning

confidence: 99%

Section: Fig 5 An Appearance Of the Employed Soft Robotmentioning

confidence: 99%

Section: Fig 5 An Appearance Of the Employed Soft Robotmentioning

confidence: 99%

See 2 more Smart Citations

Soft Robot Positioning Using Artificial Neural Network

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Compared to other nondestructive techniques, AE technique can determine the position of the cracks or monitor the entire structure without damaging the structure [2][3][4]. e advantages of AE method also include real-time capability, high sensitivity, and global monitoring capability [5][6][7][8][9]. In the past few decades, the AE technique had a rapid development.…”

Section: Introductionmentioning

confidence: 99%

Study on Acoustic Emission Localization of Concrete Using Modified Velocity

Qin

2019

Advances in Civil Engineering

View full text Add to dashboard Cite

To improve the accuracy of the acoustic emission (AE) source localization, a new 3D AE source localization method was investigated which used a combination of the modified velocity and the 3D localization algorithm based on the exhaustive method. The wave speed has a significant effect on the AE location results. With the increase of distance, the AE signal seriously attenuated due to the anisotropy of concrete, and the measured velocity changed for various distances. The velocity-distance curves were obtained when employing different water-cement ratios (W/C) and aggregate sizes. However, the current AE location system adopted constant wave velocity. As a result, the error was tremendous. The accuracy of the localization before and after the modified velocity was compared. The 3D localization results showed that compared with the constant wave velocity, the position deviation of the modified velocity was smaller and the localization results with the modified velocity were more accurate.

show abstract