MLP Neural Network Based Gas Classification System on Zynq SoC

Zhai, Xiaojun; Ali, Amine Ait Si; Amira, Abbes; Bensaali, Fayçal

doi:10.1109/access.2016.2619181

Cited by 99 publications

(65 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The Zynq-7000 SoC was introduced to combine the software programmability of an ARM-based dual-core processor with the hardware programmability of an FPGA, which has a good potential to achieve a high performance-per-watt as well as the scalability to meet different application requirements [25]. In this work, we use a Digilent Arty Z7-20 Zynq-7000 development board, equipped with a Zynq-7000 all programmable SoC, with 512 MB DDR3 memory and a 16 GB SD card.…”

Section: A Architecture Of Zynq Implementationmentioning

confidence: 99%

Heterogeneous System-on-Chip-Based Lattice-Boltzmann Visual Simulation System

Zhai

Chen

Esfahani

et al. 2020

IEEE Systems Journal

Self Cite

View full text Add to dashboard Cite

Cerebral aneurysm is a cerebrovascular disorder caused by a weakness in the wall of an artery or vein, that causes a localised dilation or ballooning of the blood vessel. It is life-threatening, hence an early and accurate diagnosis would be a great aid to medical professionals in making the correct choice of treatment. HemeLB is a massively parallel lattice-Boltzmann simulation software which is designed to provide the radiologist with estimates of flow rates, pressures and shear stresses throughout the relevant vascular structures, intended to eventually permit greater precision in the choice of therapeutic intervention. However, in order to allow surgeries and doctors to view and visualise the results in real-time at medical environments, a cost-efficient, practical platform is needed. In this paper, we have developed and evaluated a version of HemeLB on various heterogeneous system-on-chip platforms, allowing users to run HemeLB on a low cost embedded platform and to visualise the simulation results in real-time. A comprehensive evaluation of implementation on the Zynq SoC and Jetson TX1 embedded graphic processing unit platforms are reported. The achieved results show that the proposed Jetson TX1 implementation outperforms the Zynq implementation by a factor of 19 in terms of site updates per second.

show abstract

Section: A Architecture Of Zynq Implementationmentioning

confidence: 99%

Heterogeneous System-on-Chip-Based Lattice-Boltzmann Visual Simulation System

Zhai

Chen

Esfahani

et al. 2020

IEEE Systems Journal

Self Cite

View full text Add to dashboard Cite

show abstract

“…The artificial neural network (ANN) technique was subsequently created, and has widespread use due to its reliable results and active role in solving nonlinear problems. In 1960, Widrow and Hoff conducted the first work on a multi-layered structure [45,46]. In ANN, the neurons within one layer do not have a relationship with each other, and transfer information to the next layer or subsequent output in the system.…”

Section: Machine Learning Algorithmsmentioning

confidence: 99%

Modeling of Heat Transfer Coefficient in Solar Greenhouse Type Drying Systems

Çerçi

Daş

2019

Sustainability

View full text Add to dashboard Cite

As a sustainable energy source, solar energy is used in many applications. A greenhouse type dryer, which is a food drying system, directly benefits from solar energy. Convective heat transfer coefficient (hc) is an important parameter in food drying systems, in terms of system design and performance. Many parameters and equations are used to determine hc. However, as it is difficult to manually process and analyze large amounts of data and different formulations, machine learning algorithms are preferred. In this study, natural and forced convective solar greenhouse type dryers were designed. In a solar greenhouse type dryer, grape is dried in natural (GDNC) and forced convection (GDFC). For convective heat transfer coefficient (hc), predictive models were created using a multilayer perceptron (MLP)—which has many uses in drying applications, as mentioned in the literature—and decision tree (DT), which has not been used before in food drying applications. The machine learning algorithms and results of the estimated models are compared in this study. Error analyses were performed to determine the accuracy rates of the obtained models. As a result, the hc value of the dried grape product in a natural convective solar greenhouse type dryer was 11.3% higher than that of the forced type. The DT algorithm was found to be a more successful model than the MLP algorithm in estimating hc values in HDFC according to Root Mean Square Error. (RMSE = 0.0903). On the contrary, the MLP algorithm was more successful than the DT algorithm in estimating hc values in GDNC (RMSE = 0.0815).

show abstract

“…In general, the software application of MLP neural networks is used in the algorithm development phase, where parallel and low latency approaches are not required. However, in real-world applications, high-speed processing and low latencies are needed to carry out ANN in real-time constraints [27].…”

Section: Multilayer Perceptronmentioning

confidence: 99%

Prediction of Viscosity Values of Nanofluids at Different pH Values by Alternating Decision Tree and Multilayer Perceptron Methods

Demirpolat

Daş

2019

Applied Sciences

View full text Add to dashboard Cite

Due to the poor thermal properties of conventional thermal fluids such as water, oil and ethylene glycol, small solid particles are added to these fluids to enhance heat transfer. Since the viscosity change determines the rheological behavior of a liquid, it is very important to examine the parameters affecting the viscosity. Since the experimental viscosity measurement is expensive and time-consuming, it is more practical to estimate this parameter. In this study, CuO (copper oxide) nanoparticles were produced and then Scanning Electron Microscope (SEM) images analyses of the produced particles were made. Nanofluids were obtained by using pure water, ethanol and ethylene glycol materials together with the produced nanoparticles and the viscosity values were calculated by experimental setups at different density and temperatures. For the viscosity values of nanofluids, predictive models were created by using different computational intelligence methods. Mean square error (MSE), root mean square error (RMSE) and mean absolute percentage error (MAPE) error analyses were used to determine the accuracy of the predictive models. The multilayer perceptron method, which has the least error value in computational methods, was chosen as the best predicting method. The multilayer perceptron method, with an average accuracy of 51%, performed better than the alternating decision tree method. As a result, the viscosity increased with the increase in the pH of the nanofluids produced by adding CuO nanoparticles and decreased with the increase in the temperature of the nanofluids. The importance of this study is to create a predictive model using computational intelligence methods for viscosity values calculated with different pH values.

show abstract

MLP Neural Network Based Gas Classification System on Zynq SoC

Cited by 99 publications

References 23 publications

Heterogeneous System-on-Chip-Based Lattice-Boltzmann Visual Simulation System

Heterogeneous System-on-Chip-Based Lattice-Boltzmann Visual Simulation System

Modeling of Heat Transfer Coefficient in Solar Greenhouse Type Drying Systems

Prediction of Viscosity Values of Nanofluids at Different pH Values by Alternating Decision Tree and Multilayer Perceptron Methods

Contact Info

Product

Resources

About