Bayesian Deep Learning Enabled Sentiment Analysis on Web Intelligence Applications

In recent times,web intelligence(WI)has become a hot research topic,which utilizes Artificial Intelligence(AI)and advanced information technologies on theWeb and Internet.The users post reviews on social media and are employed for sentiment analysis(SA),which acts as feedback to business people and government.Proper SA on the reviews helps to enhance the quality of the services and products,however,web intelligence techniques are needed to raise the company profit and user fulfillment.With this motivation,this article introduces a new modified pigeon inspired optimization based feature selection(MPIO-FS)with Bayesian deep learning(BDL),named MPIOBDL model for SA on WI applications.The presented MPIO-BDL model initially involved preprocessing and feature extraction take place using Term Frequency—Inverse Document Frequency(TF-IDF)technique to derive a useful set of information from the user reviews.Besides,the MPIO-FS model is applied for the selection of optimal feature subsets,which helps to enhance classification accuracy and reduce computation complexity.Moreover,the BDL model is employed to allocate the proper class labels of the applied user review data.A comprehensive experimental results analysis highlighted the improved classification efficiency of the presented model.

A VAE-Bayesian deep learning scheme for solar power generation forecasting based on dimensionality reduction

The advancements in distributed generation(DG)technologies such as solar panels have led to a widespread integration of renewable power generation in modern power systems.However,the intermittent nature of renewable energy poses new challenges to the network operational planning with underlying uncertainties.This paper proposes a novel probabilistic scheme for renewable solar power generation forecasting by addressing data and model parameter uncertainties using Bayesian bidirectional long short-term memory(BiLSTM)neural networks,while handling the high dimensionality in weight parameters using variational auto-encoders(VAE).The forecasting performance of the proposed method is evaluated using various deterministic and probabilistic evaluation metrics such as root-mean square error(RMSE),Pinball loss,etc.Furthermore,reconstruction error and computational time are also monitored to evaluate the dimensionality reduction using the VAE component.When compared with benchmark methods,the proposed method leads to significant improvements in weight reduction,i.e.,from 76,4224 to 2,022 number of weight parameters,quantifying to 97.35%improvement in weight parameters reduction and 37.93%improvement in computational time for 6 months of solar power generation data.

Reliability assessment of engine electronic controllers based on Bayesian deep learning and cloud computing

The reliability of an Engine Electronic Controller(EEC)attracts attention,which has a critical impact on aircraft engine safety.Reliability assessment is an important part of the design phase.However,the complex composition of EEC and the characteristic of the Phased-Mission System(PMS)lead to the difficulty of assessment.This paper puts forward an advanced approach,considering the complex products and uncertain mission profiles to evaluate the Mean Time Between Failures(MTBF)in the design phase.The failure mechanisms of complex components are deduced by Bayesian Deep Learning(BDL)intelligent algorithm.And copious samples of reliability simulation are solved by cloud computing technology.Based on the result of BDL and cloud computing,simulations are conducted with the Physics of Failure(Po F)theory and Failure Behavior Model(FBM).This reliability assessment approach can evaluate MTBF of electronic products without reference to physical tests.Finally,an EEC is applied to verify the effectiveness and accuracy of the method.

Bayesian Deep Learning for Dynamic Power System State Prediction Considering Renewable Energy Uncertainty

Modern power systems are incorporated with distributed energy sources to be environmental-friendly and costeffective.However,due to the uncertainties of the system integrated with renewable energy sources,effective strategies need to be adopted to stabilize the entire power systems.Hence,the system operators need accurate prediction tools to forecast the dynamic system states effectively.In this paper,we propose a Bayesian deep learning approach to predict the dynamic system state in a general power system.First,the input system dataset with multiple system features requires the data pre-processing stage.Second,we obtain the dynamic state matrix of a general power system through the Newton-Raphson power flow model.Third,by incorporating the state matrix with the system features,we propose a Bayesian long short-term memory(BLSTM)network to predict the dynamic system state variables accurately.Simulation results show that the accurate prediction can be achieved at different scales of power systems through the proposed Bayesian deep learning approach.

Using Bayesian deep learning approaches for uncertainty-aware building energy surrogate models

Fast machine learning-based surrogate models are trained to emulate slow,high-fidelity engineering simulation models to accelerate engineering design tasks.This introduces uncertainty as the surrogate is only an approxi-mation of the original model.Bayesian methods can quantify that uncertainty,and deep learning models exist that follow the Bayesian paradigm.These models,namely Bayesian neural networks and Gaussian process models,enable us to give predic-tions together with an estimate of the model’s uncertainty.As a result we can derive uncertainty-aware surrogate models that can automatically identify unseen design samples that may cause large emulation errors.For these samples the high-fidelity model can be queried instead.This paper outlines how the Bayesian paradigm allows us to hybridize fast but approximate and slow but accurate models.In this paper,we train two types of Bayesian models,dropout neural networks and stochastic variational Gaussian Process models,to emulate a complex high dimensional building energy performance simulation problem.The surrogate model processes 35 building design parameters(inputs)to estimate 12 annual building energy perfor-mance metrics(outputs).We benchmark both approaches,prove their accuracy to be competitive,and show that errors can be reduced by up to 30%when the 10%of samples with the highest uncertainty are transferred to the high-fidelity model.