1-20 of 237

Search Results for neural

Save search
Follow your search
Access your saved searches in your account
Close Modal
Sort by
Images
Hybrid neural network model.

Hybrid neural network model.

Available to Purchase
in Modeling, Order-Reduction, and Controller Design of Hydraulic Fracturing > Energy Systems and ProcessesRecent Advances in Design and Control
Published: March 2023
FIG. 12.8 Hybrid neural network model. More about this image found in Hybrid neural network model.
Book Chapter
Book cover for Energy Systems and Processes: Recent Advances in Design and Control

References

Available to Purchase

Series: AIPP Books, Methods
Published: March 2023
EISBN: 978-0-7354-2574-3
ISBN: 978-0-7354-2572-9
.... , Pixton , D. S. , and Pink , A. P. , “ Multivariate control for managed-pressure-drilling systems by use of high-speed telemetry ,” SPE J.   21 , 459 – 470 ( 2015 ). 10.2118/170962-PA Bangi , M. S. F. , Kao , K. , and Kwon , J. S. I. , “ Physics-informed neural networks...
Book Chapter
Book cover for Energy Systems and Processes: Recent Advances in Design and Control

Modeling, Order-Reduction, and Controller Design of Hydraulic Fracturing

Available to Purchase

Series: AIPP Books, Methods
Published: March 2023
10.1063/9780735425743_012
EISBN: 978-0-7354-2574-3
ISBN: 978-0-7354-2572-9
... model, which is a combination of first-principles models and data-driven models such as neural networks. As a demonstration, here we develop a hybrid model for a hydraulic fracturing process that combines its first-principles model with a deep neural network that estimates its unmeasured process...
Open the PDF for Modeling, Order-Reduction, and Controller Design of Hydraulic Fracturing in another window
Book Chapter
Book cover for Energy Systems and Processes: Recent Advances in Design and Control

References

Available to Purchase

Series: AIPP Books, Methods
Published: March 2023
EISBN: 978-0-7354-2574-3
ISBN: 978-0-7354-2572-9
... , F. , Fung , A. S. , and Raahemifar , K. , “ Artificial neural network (ANN) based model predictive control (MPC) and optimization of HVAC systems: A state of the art review and case study of a residential HVAC system ,” Energy Buildings   141 , 96 – 113 ( 2017 ). 10.1016/j.enbuild...
Book Chapter
Book cover for Energy Systems and Processes: Recent Advances in Design and Control

Control-Oriented Hybrid Modeling Framework for Building Thermal Modeling

Available to Purchase

Series: AIPP Books, Methods
Published: March 2023
10.1063/9780735425743_009
EISBN: 978-0-7354-2574-3
ISBN: 978-0-7354-2572-9
... model was proposed where an artificial neural network (data-driven model) trained with kinetic data was incorporated into a mass balance for modeling the species concentration of a batch reactor ( Galvanauskas et al., 2004 ). In another approach, a hybrid model was developed for batch...
Open the PDF for Control-Oriented Hybrid Modeling Framework for Building Thermal Modeling in another window
Book Chapter

Applications of Neural Network in Rotor Misalignment and Unbalance Detection

Available to Purchase

Series: AIPP Books, Methods
Published: July 2022
10.1063/9780735423596_012
EISBN: 978-0-7354-2359-6
ISBN: 978-0-7354-2356-5
...) was used for pre-processing the extracted features, relating the time-domain six parameters and frequency-domain two parameters. Furthermore, an Artificial Neural Network (ANN) was applied as an automatic classifier on the three considered faults. Multilayer Perceptron (MLP) Neural Network with Back...
Open the PDF for Applications of Neural Network in Rotor Misalignment and Unbalance Detection in another window
Book
Book cover for Energy Systems and Processes: Recent Advances in Design and Control

Energy Systems and Processes: Recent Advances in Design and Control

Available to Purchase

Series: AIPP Books, Methods
Published: March 2023
10.1063/9780735425743
EISBN: 978-0-7354-2574-3
ISBN: 978-0-7354-2572-9
Open the PDF for Energy Systems and Processes: Recent Advances in Design and Control in another window
Book Chapter

Monitoring, Fault Detection and Operations of Photovoltaic Systems

Available to Purchase

Series: AIPP Books, Principles
Published: March 2023
10.1063/9780735425613_006
EISBN: 978-0-7354-2561-3
ISBN: 978-0-7354-2560-6
... advantages and limits, and they vary in terms of accuracy, cost, complexity, the number of faults, required data, and real-time implementation. Methods based on ML and DL require a large amount of data for the training process. In the following example, a deep learning neural network (DCNN) is applied...
Open the PDF for Monitoring, Fault Detection and Operations of Photovoltaic Systems in another window
Book Chapter

Artificial Neural Network for Control of Solar Photovoltaic System

Available to Purchase

Series: AIPP Books, Principles
Published: July 2022
10.1063/9780735424999_003
EISBN: 978-0-7354-2499-9
ISBN: 978-0-7354-2496-8
... by solar irradiation, ambient temperature, and load profiles ( Eltamaly Ali et al., 2019 ). Control of solar PV systems is a wide topic, and it involves the application of artificial intelligence (AI) methods. Artificial neural network (ANN) is considered one of the significant AI methods applied...
Open the PDF for Artificial Neural Network for Control of Solar Photovoltaic System in another window
Book Chapter

Modeling and Simulation of Solar Photovoltaic (PV) System

Available to Purchase

Series: AIPP Books, Principles
Published: March 2023
10.1063/9780735425613_001
EISBN: 978-0-7354-2561-3
ISBN: 978-0-7354-2560-6
... β j e ( t − j ) , where X(t) represents the forecasted PV power, which is the summation of the AR and MA functions. Artificial neural network (ANN) is the most efficient method and has been popular with researchers since 1980. This method has been applied to different...
Open the PDF for Modeling and Simulation of Solar Photovoltaic (PV) System in another window
Images
Graphic illustration of the mapping from the local environment of local atomic energy. Figure adapted from Zhang et al., Proceedings of the 32nd International Conference on Neural Information Processing Systems. NIPS'18 (Association for Computing Machinery, 2018b), pp. 4441–4451. Copyright 2018b Association for Computing Machinery.

Graphic illustration of the mapping from the local environment of local ato...

Available to Purchase
in Learning DeePMD-Kit: A Guide to Building Deep Potential Models > A Practical Guide to Recent Advances in Multiscale Modeling and Simulation of Biomolecules
Published: January 2023
FIG. 6.1 Graphic illustration of the mapping from the local environment of local atomic energy. Figure adapted from Zhang et al., Proceedings of the 32nd International Conference on Neural Information Processing Systems. NIPS'18 (Association for Computing Machinery, 2018b), pp. 4441–4451 More about this image found in Graphic illustration of the mapping from the local environment of local ato...
Book Chapter

References

Available to Purchase

Series: AIPP Books, Principles
Published: March 2023
0
EISBN: 978-0-7354-2561-3
ISBN: 978-0-7354-2560-6
.../j.gloei.2020.10.008 Khatib , T. and Elmenreich , W. , “ An improved method for sizing standalone photovoltaic systems using generalized regression neural network ,” Int. J. Photoenergy   2014 , 748142 ( 2014 ). 10.1155/2014/748142 Khatib , T. , Ibrahim , I...
Book Chapter

Optimal Design of the Stand-Alone and Grid-Connected PV System

Available to Purchase

Series: AIPP Books, Principles
Published: March 2023
10.1063/9780735425613_002
EISBN: 978-0-7354-2561-3
ISBN: 978-0-7354-2560-6
... improved optimization strategy combining analytical solution and machine learning approaches using a generalized artificial neural network, which can accurately predict the sizing curves of the PV system with a prediction error of 0.6%. Youssef et al. (2017) reviewed the recent advances in AI...
Open the PDF for Optimal Design of the Stand-Alone and Grid-Connected PV System in another window
Images
Neural interface electrode materials. (a) TiN electrode used in neuropixel probe. Reprinted with permission from Fiáth et al., Biosens. Bioelectron. 106, 86–92 (2018). Copyright 2018 Elsevier. (b) Microscopy image demonstrating crossover of metal layers (Ti/Au/Ti) and electrode sites. Reprinted with permission from Mercanzini et al., Sens. Actuators A 143, 90–96 (2008). Copyright 2008 Elsevier. (c) Optical images of gold and Ir-plated electrode sites before the pulse test experiment. Reprinted with permission from Fomani and Mansour, Sens. Actuators A 168, 233–241 (2011). Copyright 2011 Elsevier. (d) Electrochemical deposition of conducting polymer (PEDOT) on the electrode sites and around electro-spun PLLA nanofiber templates as a function of deposition time. Reprinted with permission from Abidian et al., Small 6, 421–429 (2010). Copyright 2010 John Wiley and Sons. (e) Photolithographically patterned conducting polymer electrodes. Reprinted with permission from Khodagholy et al., Adv. Mater. 23(36), H268–H272 (2011). Copyright 2011 John Wiley and Sons. (f) High magnification image of a surface array with transparent graphene electrode sites. Reprinted with permission from Park et al., Nat. Commun. 5, 5258 (2014). Copyright 2014 Springer Nature. (g) Optical micrograph of the multi-electrode array device made with carbon nanotube-based pillars. Reprinted with permission from Ben-Jacob and Hanein, J. Mater. Chem. 18, 5181 (2008). Copyright 1991 the Royal Society of Chemistry. (h) SEM image of PPy nanotube outgrowth on silicon dioxide showing a diameter outgrowth of 60 µm. Reprinted with permission from Abidian et al., Small 6, 421–429 (2010). Copyright 2010 John Wiley and Sons.

Neural interface electrode materials. (a) TiN electrode used in neuropixel ...

Available to Purchase
in Translational Neuroelectronics > Introduction to BioelectronicsMaterials, Devices, and Applications
Published: November 2022
FIG. 7.2 Neural interface electrode materials. (a) TiN electrode used in neuropixel probe. Reprinted with permission from Fiáth et al., Biosens. Bioelectron. 106 , 86–92 ( 2018 ). Copyright 2018 Elsevier. (b) Microscopy image demonstrating crossover of metal layers (Ti/Au/Ti More about this image found in Neural interface electrode materials. (a) TiN electrode used in neuropixel ...
Images
Silicon-based neural interface devices. (a) The Utah array placed on top of a penny for scale. (b) The Michigan probe, also known as Si-probe. The image is of an 8-shank, 256-channel probe manufactured by NeuroNexus. (c) Probe tip (left) and packaging (right) of Neuropixel probe capable of recording 384 channels, simultaneously. Reprinted with permission from Jun et al., Nature 551, 232–236 (2017). Copyright 2017 Springer Nature. (d) Flexible Si-based transistor used in a surface array to perform local buffering and multiplexing. Reprinted with permission from Viventi et al., Nat. Neurosci. 14, 1599–1605 (2011). Copyright 2011 Springer Nature. (e) Capacitively coupled silicon nanomembrane transistor as an amplified sensing node. Circuit diagram (left) and optical micrograph (middle) of a node. Mechanism for capacitively coupled sensing through a thermal SiO2 layer (right). Reprinted with permission from Fang et al., Nat. Biomed. Eng. 1, 38 (2017). Copyright 2017 Springer Nature. (f) Steps to thermally grow, transfer, and integrate ultrathin layers of encapsulating SiO2 onto flexible electronic platforms (left). Sample with a 100 nm thick layer of thermal SiO2 on the top surface (right). Reprinted with permission from Fang et al., Proc. Natl. Acad. Sci. U.S.A. 113, 11682–11687 (2016). Copyright 2016 PNAS.

Silicon-based neural interface devices. (a) The Utah array placed on top of...

Available to Purchase
in Translational Neuroelectronics > Introduction to BioelectronicsMaterials, Devices, and Applications
Published: November 2022
FIG. 7.4 Silicon-based neural interface devices. (a) The Utah array placed on top of a penny for scale. (b) The Michigan probe, also known as Si-probe. The image is of an 8-shank, 256-channel probe manufactured by NeuroNexus. (c) Probe tip (left) and packaging (right) of Neuropixel probe capable More about this image found in Silicon-based neural interface devices. (a) The Utah array placed on top of...
Images
Silicon-based neural interface devices. (a) The Utah array placed on top of a penny for scale. (b) The Michigan probe, also known as Si-probe. The image is of an 8-shank, 256-channel probe manufactured by NeuroNexus. (c) Probe tip (left) and packaging (right) of Neuropixel probe capable of recording 384 channels, simultaneously. Reprinted with permission from Jun et al., Nature 551, 232–236 (2017). Copyright 2017 Springer Nature. (d) Flexible Si-based transistor used in a surface array to perform local buffering and multiplexing. Reprinted with permission from Viventi et al., Nat. Neurosci. 14, 1599–1605 (2011). Copyright 2011 Springer Nature. (e) Capacitively coupled silicon nanomembrane transistor as an amplified sensing node. Circuit diagram (left) and optical micrograph (middle) of a node. Mechanism for capacitively coupled sensing through a thermal SiO2 layer (right). Reprinted with permission from Fang et al., Nat. Biomed. Eng. 1, 38 (2017). Copyright 2017 Springer Nature. (f) Steps to thermally grow, transfer, and integrate ultrathin layers of encapsulating SiO2 onto flexible electronic platforms (left). Sample with a 100 nm thick layer of thermal SiO2 on the top surface (right). Reprinted with permission from Fang et al., Proc. Natl. Acad. Sci. U.S.A. 113, 11682–11687 (2016). Copyright 2016 PNAS.

Silicon-based neural interface devices. (a) The Utah array placed on top of...

Available to Purchase
in Translational Neuroelectronics > Introduction to BioelectronicsMaterials, Devices, and Applications
Published: November 2022
FIG. 7.4 Silicon-based neural interface devices. (a) The Utah array placed on top of a penny for scale. (b) The Michigan probe, also known as Si-probe. The image is of an 8-shank, 256-channel probe manufactured by NeuroNexus. (c) Probe tip (left) and packaging (right) of Neuropixel probe capable More about this image found in Silicon-based neural interface devices. (a) The Utah array placed on top of...
Images
Power transmission strategies. (a) Block diagram for a typical neural stimulator. DC/DC converters boost supply voltage to the level required by the output stage. (b) Ultrasound-powered neural dust mote consists of a piezoelectric crystal, a single transistor, and two recording pads. Reprinted with permission from Seo et al., Neuron 91, 529–539 (2016). Copyright 2016 Elsevier. (c) Triboelectric nanogenerator in a compressed or released state (top) generates current (bottom). Reprinted with permission from Lee et al., Nano Energy 114(40), 10554–10559 (2017b). Copyright 2017 Elsevier. (d) Square and circular planar spiral coils for inductive power transmission. (e) Electronic (green box) and injectable modules (yellow) of a wireless oximeter. Loop antenna enables magnetic resonant coupling to an external antenna. Reprinted with permission from Zhang et al., Sci. Adv. 5, eaaw0873 (2019). Copyright 2019 Author(s). (f) Resonant cavity for self-tracking energy transfer. The cavity is excited by a continuous-wave input. Reprinted with permission from Ho et al., Phys. Rev. Appl. 4, 024001 (2015). Copyright 2020 John Wiley and Sons. (g) Optical micrograph of filamentary serpentine silicon solar cell (top) and filamentary serpentine inductors and capacitors for RF operation (bottom). Reprinted with permission from Kim et al., Science 333, 838–843 (2011). Copyright 2011 AAAS. (h) A flexible, highly stable organic solar cell as a power source for heart rate measurements. Reprinted with permission from Park et al., Nature 561, 516–521 (2018). Copyright 2018 Springer Nature. (i) An organic photo-capacitor is used to drive an organic ion pump for local delivery of the drug. Reprinted with permission from Jakešová et al., npj Flex. Electron. 3, 14 (2019). Copyright 2019 Author(s).

Power transmission strategies. (a) Block diagram for a typical neural stimu...

Available to Purchase
in Translational Neuroelectronics > Introduction to BioelectronicsMaterials, Devices, and Applications
Published: November 2022
FIG. 7.8 Power transmission strategies. (a) Block diagram for a typical neural stimulator. DC/DC converters boost supply voltage to the level required by the output stage. (b) Ultrasound-powered neural dust mote consists of a piezoelectric crystal, a single transistor, and two recording pads More about this image found in Power transmission strategies. (a) Block diagram for a typical neural stimu...
Images
(a) Neural membrane response to the stimuli of different amplitudes and durations drawn below, delivering the same charge. Reproduced with permission from Malmivuo and Plonsey, Bioelectromagnetism: Principles and Applications of Bioelectric and Biomagnetic Fields (Oxford University Press, 1995). Copyright 1995 Oxford University Press. (b) The strength–duration curve overlayed on top of the aforementioned pulses. The rheobase corresponds to the lowest amplitude (or “strength”) and longest duration stimulus current that will still just activate the membrane. The chronaxie duration corresponds to an activating pulse of double the rheobase amplitude.

(a) Neural membrane response to the stimuli of different amplitudes and dur...

Available to Purchase
in Nerve Stimulation > Introduction to BioelectronicsMaterials, Devices, and Applications
Published: November 2022
FIG. 8.5 (a) Neural membrane response to the stimuli of different amplitudes and durations drawn below, delivering the same charge. Reproduced with permission from Malmivuo and Plonsey, Bioelectromagnetism: Principles and Applications of Bioelectric and Biomagnetic Fields (Oxford More about this image found in (a) Neural membrane response to the stimuli of different amplitudes and dur...
Book Chapter
Book cover for Energy Systems and Processes: Recent Advances in Design and Control

Data-Driven Adaptive Sparse Modeling of Chemical Process Systems

Available to Purchase

Series: AIPP Books, Methods
Published: March 2023
10.1063/9780735425743_010
EISBN: 978-0-7354-2574-3
ISBN: 978-0-7354-2572-9
... using artificial neural networks, least squares regression, support vector regression, and Gaussian process regression. Also, modal decomposition-based techniques such as proper orthogonal decomposition (POD) and dynamic mode decomposition (DMD) are commonly used for reduced-order modeling and control...
Open the PDF for Data-Driven Adaptive Sparse Modeling of Chemical Process Systems in another window
Book Chapter

Instructional Strategies that Foster Effective Problem-Solving

Available to Purchase

Series: AIPP Books, Professional
Published: March 2023
10.1063/9780735425477_017
EISBN: 978-0-7354-2547-7
ISBN: 978-0-7354-2544-6
... in the neural structure of the brain's prefrontal cortex ( Funahashi, 2017 ). Information processing and the constraint of cognitive load Because the process of problem-solving is a web of decision-making, a proficient problem-solver needs to be in conscious control of what decisions are needed and how...
Open the PDF for Instructional Strategies that Foster Effective Problem-Solving in another window