Fuzzy-Neural Network Traffic Prediction Framework with Wavelet Decomposition

2003 ◽  
Vol 1836 (1) ◽  
pp. 16-20 ◽  
Author(s):  
Heng Xiao ◽  
Hongyu Sun ◽  
Bin Ran ◽  
Youngtae Oh
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Fuzzy Logic ◽  
Wavelet Decomposition ◽  
Fuzzy Neural Network ◽  
Wavelet Denoising ◽  
Traffic Prediction ◽  
Denoising Method ◽  
Fuzzy Neural ◽  
Special Factors

The framework of a traffic prediction model that could eliminate noise caused by random travel conditions is investigated. This model also can quantitatively calculate the influence of special factors. The framework combined several artificial intelligence technologies, such as wavelet transform, neural network, and fuzzy logic. The wavelet denoising method is emphasized and analyzed.

Fuzzy neural network based traffic prediction and congestion control in high-speed networks

2000 ◽  
Vol 15 (2) ◽  
pp. 144-149 ◽  
Author(s):  
Xiang Fei ◽  
Xiaoyan He ◽  
Junzhou Luo ◽  
Jieyi Wu ◽  
Guanqun Gu
Keyword(s):  
Neural Network ◽  
Congestion Control ◽  
High Speed ◽  
Fuzzy Neural Network ◽  
Traffic Prediction ◽  
High Speed Networks ◽  
Fuzzy Neural

scholarly journals Fuzzy Neural Network (FNN) Pada Proses Identifikasi Penyakit ISPA

2021 ◽  
Vol 5 (3) ◽  
pp. 870
Author(s):  
Dhio Saputra ◽  
Musli Yanto ◽  
Wifra Safitri ◽  
Liga Mayola
Keyword(s):  
Neural Network ◽  
Fuzzy Logic ◽  
Fuzzy Neural Network ◽  
The Elderly ◽  
Diagnostic Process ◽  
Average Error ◽  
Identification Process ◽  
Runny Nose ◽  
Fuzzy Neural ◽  
Artificial Neural Network Ann

ISPA is a disease that can affect anyone from children, adolescents, adults, and even the elderly. The causes experienced by sufferers of this disease are quite simple, such as fever, runny nose, and cough. The discussion in this paper describes the process of ISPA disease identification by developing a Fuzzy Neural Network (FNN) model. The process will be optimized using Fuzzy Logic to form rules for the diagnostic process, then proceed with an Artificial Neural Network (ANN). This model can maximize the performance of ANN in the identification process so that the output given is quite precise and accurate. The results provided by Fuzzy Logic can describe the clarity of the rules in diagnosis by presenting several rules (rules) that are presented from the Fuzzyfication process to the Defuzzyfication process. The output obtained from the ANN process also shows quite perfect results with an average error value based on MSE of 0.00912 and accuracy value of 91.96%. With these results, it can be stated that the FNN model can be used in the ISPA diagnosis process so that the presentation of this paper aims to provide an alternative in the identification process

scholarly journals Space-Time Effect Prediction of Blasting Vibration Based on Intelligent Automatic Blasting Vibration Monitoring System

2021 ◽  
Vol 12 (1) ◽  
pp. 12
Author(s):  
Fan Chen ◽  
Gengsheng He ◽  
Shun Dong ◽  
Shunjun Zhao ◽  
Lin Shi ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Rough Set ◽  
Significant Influence ◽  
Vibration Frequency ◽  
Fuzzy Neural Network ◽  
Vibration Velocity ◽  
Blasting Vibration ◽  
High Rise ◽  
Fuzzy Neural

The vibration produced by blasting excavation in urban underground engineering has a significant influence on the surrounding environment, and the strength of vibration intensity involves many influencing factors. In order to predict the space-time effects of blasting vibration more accurately, an automatic intelligent monitoring system is constructed based on the rough set fuzzy neural network blasting vibration characteristic parameter prediction model and the network blasting vibrator (TC-6850). By setting up the regional monitoring network of monitoring points, the obtained monitoring data are analyzed. An artificial intelligence model is used to predict the influence of stratum condition, excavation hole, and high-rise building on blasting vibration velocity and frequency propagation. The results show that the artificial intelligence prediction model based on a rough set fuzzy neural network can accurately reflect the formation attenuation effect, hollow effect, and building amplification effect of blasting vibration by effectively fuzzing and standardizing the influencing factors. The propagation of blasting vibration in a soil–rock composite stratum is closely related to the surrounding rock conditions with a noticeable elastic modulus effect. The hollow effect is regional, which has a significant influence on the surrounding ground and buildings. Besides, the blasting vibration of the excavated area is stronger than that of the unexcavated area. The propagation of blasting vibration on high-rise buildings was complicated, of which the peak vibration velocity is maximum at the lower level of the building and decreased with the rise of the floor gradually. The whip sheath effect appears at the top floor, which is related to the blasting vibration frequency and the building’s natural vibration frequency.

A pretreatment method of wastewater based on artificial intelligence and fuzzy neural network system

2020 ◽  
Vol 39 (2) ◽  
pp. 1711-1720
Author(s):  
He Chan ◽  
Yan Nai-He
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Network Model ◽  
Neural Network Model ◽  
Fuzzy Neural Network ◽  
Saline Wastewater ◽  
Pretreatment Method ◽  
Fuzzy Function ◽  
Dissolved Oxygen Control ◽  
Fuzzy Neural

A pretreatment method of industrial saline wastewater based on Artificial Intelligence based fuzzy neural network analysis was proposed to improve the pretreatment accuracy of industrial saline wastewater. This method uses a four-layer AI fuzzy neural network model and proposes a graded fuzzy neural network model for pretreatment method of industrial saline wastewater, it includes input layer, fuzzification layer, fuzzy logical layer and output layer, and designs the framework and calculation mode of the fuzzy function block and the neural network module. Finally, the dynamic simulation experiments of dissolved oxygen control in the fifth zone and nitrate nitrogen control in the second zone are carried out based on the simulation benchmark model (BSM1) platform. The experimental results show that this approach can effectively raise the adaptive control accuracy of the system compared with PID, feed forward neural network and conventional recurrent neural network.

Influence of government subsidy on high-tech enterprise investment based on artificial intelligence and fuzzy neural network

2020 ◽  
pp. 1-11
Author(s):  
Li Ran
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Technological Innovation ◽  
Fuzzy Neural Network ◽  
Sampling Period ◽  
High Tech ◽  
Network Bandwidth ◽  
Dynamic Weight ◽  
Network Utilization ◽  
Fuzzy Neural

Government subsidies have an important impact on the development of high-interest technology companies and technological innovation. In order to study the relationship between government investment and the development of high-tech enterprises and technological innovation, based on artificial intelligence and fuzzy neural network, this paper builds an analysis model based on artificial intelligence and fuzzy neural network. According to the operation of each loop, this study designs a scheduling strategy that dynamically allocates network utilization according to the dynamic weight of the loop, and periodically changes the sampling period of the system, so that the system can not only run stably but also maximize the use of limited bandwidth. The network resource allocation module allocates the available network bandwidth of each control loop according to the dynamic weight of each loop, and the sampling period calculation module calculates a new sampling period based on the allocated network utilization rate. In addition, in this study, the performance of the model constructed in this paper is analyzed through empirical analysis. The results of the study show that the model constructed in this paper is effective.

Sign in / Sign up

Export Citation Format

Share Document