Bayesian Neural Network Model Research Articles

Monitoring the photosynthetic performance of grape leaves using a hyperspectral-based machine learning model

Photosynthesis is a direct expression of the crop growth status and an important indicator predicting yield and quality. Rapid and accurate monitoring of the dynamics of photosynthetic is key to field management. In this study, we obtained photosynthetic pigments and water status parameters at the leaf scale during different growth periods of grape. The potential maximum quantum yield (Fv/Fm) of photosystem II (PSII) under dark adaptation and the light response curve (LRC) of the PSII electron transfer rate (ETR) under light adaptation were measured using a pulse amplitude modulated (PAM) chlorophyll fluorometer, while leaf spectral information was recorded using a hyperspectral imager. The maximum ETR (ETRmax) and initial quantum efficiency (kα) were calculated using the LRC model. A Bayesian neural network (BNN) model (implemented in Tensorfolw2.8) was developed to predict Fv/Fm, ETRmax and kα by quantifying the spectral response indices of photosynthetic pigments and water status parameters. A comparison was made with the partial least squares (PLS) and photochemical reflectance index (PRI). The results show that BNN, PLS model and PRI have better predictive performance for Fv/Fm than ETRmax and kα. Compared with the PLS and PRI, the BNN model was able to significantly improve the prediction accuracy, where the validation results for Fv/Fm were R2 of 0.78, ETRmax of 0.57 and kα of 0.53. In addition, the importance of the BNN model input features varied with Fv/Fm, ETRmax and kα, with the vegetation index describing the photosynthetic pigments having the highest importance. The PRI had the worst predictive performance probably because the de-epoxidation state of the xanthophyll cycle pigments is strongly influenced by temporal changes. The model developed in this paper for monitoring photosynthetic performance parameters in grape leaves can simplify the complex photosynthetic reaction process, expand the application of PAM technology and provide a method for rapid and accurate monitoring of photosynthetic performance.

Towards safe and collaborative aerodrome operations: Assessing shared situational awareness for adverse weather detection with EEG-enabled Bayesian neural networks

Teams formulated by aviation professionals are essential in maintaining a safe and efficient aerodrome environment. Nonetheless, the shared situational awareness between the flight crews under adverse weather conditions might be impaired. This research aims to evaluate the impact of a proposed enhancement in communication protocol on cognitive workload and develop a human-centred classification model to identify hazardous meteorological conditions. Thirty groups of subjects completed four post-landing taxiing tasks under two visibility conditions (CAVOK/CAT IIIA) while two different communication protocols (presence/absence of turning direction information) were adopted by the air traffic control officer (ATCOs). Electroencephalography (EEG) and the NASA Task Load Index were respectively used to reflect the pilot’s mental state and to evaluate the pilot’s mental workload subjectively. Results indicated that impaired visibility increases the subjective workload significantly, while the inclusion of turning direction information in the ATCO’s instruction would not significantly intensify their cognitive workload. Mutual information was used to quantitatively assess the shared situational awareness between the pilot flying and the pilot monitoring. Finally, this research proposes a human-centred approach to identify potentially hazardous weather conditions from EEG power spectral densities with Bayesian neural networks (BNN). The classification model has outperformed other baseline algorithms with an accuracy of 66.5%, an F1 score of 61.4%, and an area under the ROC of 0.749. Using the concept of explainable AI with Shapley Additive Explanations (SHAP) values, the exploration of latent mental patterns formulates novel knowledge to gain insights into the vital physiological indicators of the pilots in response to different scenarios from the BNN model. In the long term, the model facilitates the decision regarding the necessity of providing automation and decision-making aids to pilots.

Estimation of household characteristics with uncertainties from smart meter data

The knowledge of household characteristics can help energy providers carry out more personalized demand-side management programs. Obtaining such information through surveys is costly and time-consuming in practice. This paper proposes a novel estimation method for household characteristics with uncertainties using the residential electricity consumption data. To alleviate the class imbalance problem in the dataset, a dynamic time warping sampling (DTWS) method is proposed to generate synthetic data for the minority class. To overcome the problem that the existing methods for identifying household characteristics cannot provide the confidence level of the results, a Bayesian convolutional neural network (BCNN) model is developed for feature extraction and characteristic identification with uncertainties. These quantified uncertainties can be regarded as a measure of confidence and can be used to target customers more effectively for energy efficiency and demand response programs. The effectiveness of the proposed model is validated by experiments on ground truth data.

Bayesian evaluation of residual production cross sections in proton-induced nuclear spallation reactions

Residual production cross sections in spallation reactions are key data for nuclear physics and related applications. Spallation reactions are very complex due to the wide range of incident energies and abundant fragments involved. Therefore, it is challenging to obtain accurate and complete energy-dependent residual cross sections. With the guidance of a simplified EPAX formula (sEPAX), the Bayesian neural network (BNN) technique is applied to form a new machine learning model (BNN + sEPAX) for predicting fragment cross sections in proton-induced nuclear spallation reactions. Three types of sample dataset for measured residual production cross sections in proton-induced nuclear spallation reactions are made, i.e. D1 consists of isotopic cross sections in reactions below 1 GeV/u, D2 consists of fragments excitation functions of reactions up to 2.6 GeV/u, and D3 is a hybrid of D1 and D2. With the constructed BNN and BNN + sEPAX models, the isotopic and mass cross section distributions are compared for the 356 MeV/u 40Ca + p and 1 GeV/u 136Xe + p reactions, and fragment excitation functions in 40Ca + p, 56Fe + p, 138Ba + p and 197Au + p reactions. It is found that the BNN model needs sufficient information to achieve good extrapolations, while the BNN + sEPAX model performs better extrapolations based on less information due to the physical guidance of the sEPAX formulas. It is suggested that the BNN + sEPAX model provides a new approach to predict the energy-dependent residual production cross sections produced in proton-induced nuclear spallation reactions of incident energies from tens of MeV/u up to several GeV/u.

Predicting wind-caused floater intrusion risk for overhead contact lines based on Bayesian neural network with spatiotemporal correlation analysis

Wind-caused floater intrusion has posed enormous threats to the safety and resilience of overhead contact lines (OCLs) of electrified railway. In this paper, a Bayesian neural network (BNN) based prediction model is proposed, incorporating spatiotemporal correlations, uncertainty of extreme wind speed and direction, characteristic parameters of OCLs, environmental information and human factors into floater intrusion risk prediction. To select optimal candidates, the spatial-temporal correlation among wind data with respect to different OCL corridors are examined. Then, the probabilistic wind model is developed to capture the stochastic nature of wind events and account for the uncertainty in wind speed and direction. The spatiotemporal correlation-constrained environment sensitive parameter is formulated to investigate the impacts of wind, characteristic parameters of OCLs, environmental information and human factors on floater intrusion of OCLs. A BNN model is implemented into predicting wind-caused floater intrusion risk. Finally, the remarkable effectiveness and robustness of the proposed model are compared with some other advanced prediction methods. The experimental results demonstrate that the proposed model not only has the capability of uncertainty estimation, but also provides the confidence interval of floater intrusion risk prediction, which can play a significant role in preventive operational flexibility and resilience against weather-related risks.

Probabilistic occupancy forecasting for risk-aware optimal ventilation through autoencoder Bayesian deep neural networks

Ventilation plays a noteworthy role in maintaining a healthy, comfortable and energy-efficient indoor environment and mitigating the risk of aerosol transmission and disease infection (e.g., SARS-COV-2). In most commercial and office buildings, demand-controlled ventilation (DCV) systems are widely utilized to conserve energy based on occupancy. However, as the presence of occupants is often inherently stochastic, accurate occupancy prediction is challenging. This study, therefore, proposes an autoencoder Bayesian Long Short-term Memory neural network (LSTM) model for probabilistic occupancy prediction, taking account of model misspecification, epistemic uncertainty, and aleatoric uncertainty. Performances of the proposed models are evaluated using real data in an educational building at the University of Cambridge, UK. The models trained on data of one open-plan space are used to predict occupant numbers for other spaces (with similar layout and function) in the same building. The probabilistic occupant profiles are then used for estimating optimal ventilation rates for two scenarios (i.e., normal DCV mode for energy conservation and anti-infection mode for virus transmission prevention). Results show that, during the test period, for the 1-h ahead prediction, the proposed model achieved better performance with up to 5.8% mean absolute percentage error reduction than the traditional LSTM model. More flexible alternatives for ventilation can be offered by the proposed risk-aware decision-making schemes serving different purposes under real operation. The findings from this study provide new occupancy forecasting solutions and explore the potential of probabilistic decision making for building ventilation optimization.

Precise machine learning models for fragment production in projectile fragmentation reactions using Bayesian neural networks * *Supported by the National Natural Science Foundation of China (11975091), the Program for Innovative Research Team (in Science and Technology) in University of Henan Province (21IRTSTHN011), China

Machine learning models are constructed to predict fragment production cross sections in projectile fragmentation (PF) reactions using Bayesian neural network (BNN) techniques. The massive learning for BNN models is based on 6393 fragments from 53 measured projectile fragmentation reactions. A direct BNN model and physical guiding BNN via FRACS parametrization (BNN + FRACS) model have been constructed to predict the fragment cross section in projectile fragmentation reactions. It is verified that the BNN and BNN + FRACS models can reproduce a wide range of fragment productions in PF reactions with incident energies from 40 MeV/u to 1 GeV/u, reaction systems with projectile nuclei from 40Ar to 208Pb, and various target nuclei. The high precision of the BNN and BNN + FRACS models makes them applicable for the low production rate of extremely rare isotopes in future PF reactions with large projectile nucleus asymmetry in the new generation of radioactive nuclear beam factories.

Machine learning-based self-sensing of the stiffness of shape memory coil actuator.

Self-sensing actuation (SSA) assists in sensing the vital property of the shape memory coil which can be used to monitor and control the actuation in smart equipment as well as robotics. The stiffness characteristic of the shape memory coil (SMC) is sensed during actuation which plays a significant role in development of intelligent robotics in defense systems. The electrical property of SMC such as electrical resistance changes due to martensitic phase transformation which is further used to sense the mechanical properties such as strain, stress, temperature, length, and force of the equipment. Nowadays electrical properties are used to sense the stiffness of the shape memory coil. As of now, there is no well-established analytical model to predict the stiffness of SMC during actuation accurately. Therefore, a soft model based on machine learning is proposed in this paper for autosensing of the stiffness in SMC. The experimental facility has been developed for the collection of data with respect to diverse Joule heating currents. To determine the experimental data values of stiffness and electrical resistance of SMC is a cumbersome task. Hence, we have proposed an automated method to predict the stiffness of the SMC using soft computing-based methods. The Classical Polynomial and Bayesian optimization-based Feedforward Neural Network (FFNN) models are developed for analyzing the stiffness of the SMC. It is found that the hybrid FFNN model outperforms the other ML-based model by attaining 95.2650% accuracy. The FFNN model is also able to explain almost all the predicted stiffness values which are experimentally recorded.

A multi-scale anomaly detection framework for retinal OCT images based on the Bayesian neural network

As a non-contact imaging technology, optical coherence tomography (OCT) is widely used in retinal disease detection. There is a growing interest among researchers for automated detection of retinal diseases using OCT images. With the development of deep learning, convolutional neural network (CNN) enables accurate detection of common retinal diseases. However, large-scale labeled data is necessary for these deep learning methods. It limits the application of these methods in retinal disease detection, especially for diseases with low occurrence. Therefore, we propose an automated anomaly detection method for unspecific retinal disease, and only healthy OCT images are needed for training. The method uses epistemic uncertainty as the criterion of anomaly detection. Our method assumes that the lesion correlates with a high epistemic uncertainty region. We propose a Bayesian neural network (BNN) model, Multi-scale Bayesian U-Net (MBU-Net), to obtain epistemic uncertainty of OCT images. We then design an algorithm to reduce the uncertainty generated by healthy tissue regions. Finally, a threshold-based function is designed to distinguish whether the input data is healthy or not. We evaluate our approach on a public dataset, UCSD dataset, and a private dataset collected by ourselves, named BFHJLU dataset. The experimental results show that the proposed method can achieve 94.9% accuracy, 97.9% sensitivity, and 86.0% specificity on the UCSD dataset. On the BFHJLU dataset, the accuracy, sensitivity, and specificity are 92.1%, 97.3%, and 87.7%. The proposed method outperforms existing anomaly detection methods.

Predictions of component Remaining Useful Lifetime Using Bayesian Neural Network

The Machine Prognostics and Health Management (PHM) are concerned with the prediction of the Remaining Useful Lifetime (RUL) of assets. Accurate real-time RUL predictions are necessary when developing an efficient predictive maintenance (PdM) framework for equipment health assessment. If correctly implemented, a PdM framework can maximize the interval between maintenance operations, minimize the cost and number of unscheduled maintenance operations, and improve overall availability of the large facilities like nuclear power plants (NPPs). This is especially important for nuclear power facilities to maximize capacity factor and reliability. In this work, we propose a data-driven approach to make predictions of both the RUL and its uncertainty using a Bayesian Neural Network (BNN). The BNN utilizes the Bayes by backprop algorithm with variational inference to estimate the posterior distribution for each trainable parameter so that the model output is also a PDF from which one can draw the mean prediction and the associated uncertainty. To learn the correlations between various time-series sensor data measurements, a time window approach is implemented with a two-stage noise filtering process for incoming sensor measurements to enhance the feature extraction and overall model performance. As a proof of concept, the NASA Commercial Modular Aero Propulsion System Simulation (C-MAPPS) datasets are utilized to assess the performance of the BNN model. The modeled system can be treated as a surrogate for turbine generators used in NPPs due to the similar mode of operation, degradation, and measurable variables. Comparisons against other state-of-the-art algorithms on the same datasets indicate that the BNN model can not only make predictions with comparable level of accuracy, but also offer the benefit of estimating uncertainty associated with the prediction. This additional uncertainty, which can be continuously updated as more measurement data are collected, can facilitate the decision-making process with a quantifiable confidence level within a PdM framework. Additional advantages of the BNN are showcased, such as providing component maintenance ranges and model executing frequency, with an example of how the BNN estimated uncertainty can be used to support the continuous predictive maintenance. A PdM framework based on a BNN will allow for utilities to make more informed decisions on the optimal time for maintenance so that the loss of revenue can be minimized from planned and unplanned maintenance outages.

An Advanced Machine Learning Approach to Predicting Pedestrian Fatality Caused by Road Crashes: A Step toward Sustainable Pedestrian Safety

More than 8000 pedestrians were killed due to road crashes in Australia over the last 30 years. Pedestrians are assumed to be the most vulnerable users of roads. This susceptibility of pedestrians to road crashes conflicts with sustainable transportation objectives. It is critical to know the causes of pedestrian injuries in order to enhance the safety of these vulnerable road users. To achieve this, traditional statistical models are used frequently. However, they have been criticized for their inflexibility in handling outliers and missing or noisy data, and their strict pre-assumptions. This study applied an advanced machine learning algorithm, a Bayesian neural network, which has the characters of both Bayesian theory and neural networks. Several structures of this model were built, and the best structure was selected, which included three hidden neuron layers—sixteen hidden nodes in the first layer and eight hidden nodes in the second and third layers. The performance of this model was compared with the performances of some other machine learning techniques, including standard Bayesian networks, a standard neural network, and a random forest model. The Bayesian neural network model outperformed the other models. In addition, a study on the importance of the features showed that the individuals’ characteristics, time, and circumstantial factors were essential. They greatly increased model performance if the model used them. This research lays the groundwork for using machine learning approaches to alleviate pedestrian deaths caused by road accidents.

Multi-Objective Optimization Under Uncertainty of Part Quality in Fused Filament Fabrication

Abstract This work presents a data-driven methodology for multi-objective optimization under uncertainty of process parameters in the fused filament fabrication (FFF) process. The proposed approach optimizes the process parameters with the objectives of minimizing the geometric inaccuracy and maximizing the filament bond quality of the manufactured part. First, experiments are conducted to collect data pertaining to the part quality. Then, Bayesian neural network (BNN) models are constructed to predict the geometric inaccuracy and bond quality as functions of the process parameters. The BNN model captures the model uncertainty caused by the lack of knowledge about model parameters (neuron weights) and the input variability due to the intrinsic randomness in the input parameters. Using the stochastic predictions from these models, different robustness-based design optimization formulations are investigated, wherein process parameters such as nozzle temperature, nozzle speed, and layer thickness are optimized under uncertainty for different multi-objective scenarios. Epistemic uncertainty in the prediction model and the aleatory uncertainty in the input is considered in the optimization. Finally, Pareto surfaces are constructed to estimate the tradeoffs between the objectives. Both the BNN models and the effectiveness of the proposed optimization methodology are validated using the actual manufacturing of the parts.

Bayesian-based optimized deep learning model to detect COVID-19 patients using chest X-ray image data

Coronavirus Disease 2019 (COVID-19) is extremely infectious and rapidly spreading around the globe. As a result, rapid and precise identification of COVID-19 patients is critical. Deep Learning has shown promising performance in a variety of domains and emerged as a key technology in Artificial Intelligence. Recent advances in visual recognition are based on image classification and artefacts detection within these images. The purpose of this study is to classify chest X-ray images of COVID-19 artefacts in changed real-world situations. A novel Bayesian optimization-based convolutional neural network (CNN) model is proposed for the recognition of chest X-ray images. The proposed model has two main components. The first one utilizes CNN to extract and learn deep features. The second component is a Bayesian-based optimizer that is used to tune the CNN hyperparameters according to an objective function. The used large-scale and balanced dataset comprises 10,848 images (i.e., 3616 COVID-19, 3616 normal cases, and 3616 Pneumonia). In the first ablation investigation, we compared Bayesian optimization to three distinct ablation scenarios. We used convergence charts and accuracy to compare the three scenarios. We noticed that the Bayesian search-derived optimal architecture achieved 96% accuracy. To assist qualitative researchers, address their research questions in a methodologically sound manner, a comparison of research method and theme analysis methods was provided. The suggested model is shown to be more trustworthy and accurate in real world.

Development of Bayesian Neural Network Model to Predict the Correlated Color Temperature Using Digital Camera and Macbeth ColorChecker Chart

Information about correlated color temperature influencing the scene due to the surrounding lighting is vital, especially for circadian lighting and photography. This paper proposes a novel image-based machine learning model to predict the correlated color temperature in a scene with the help of the Macbeth ColorChecker color rendition chart and a DSLR camera. In the proposed technique, the researcher fixes the white balance setting in the camera, thereby forcing color difference in the captured image of the Macbeth ColorChecker chart placed in the scene. The Bayesian neural network model considers the color difference values of the six spectrally neutral patches of the Macbeth ColorChecker chart as inputs for CCT prediction. The color differences are calculated using the CIEDE2000 color difference formula. Fours models with white balance settings in the camera as 5000 K, 6500 K, 8000 K, and 10000 K were developed and analyzed. It is experimentally found that the correlated color temperature prediction error is less than five percent by the proposed model with white balance setting in the DSLR camera as 10000 K. The proposed model performed consistently during varied lighting levels and mixed CCT lighting conditions set up with LED, incandescent, and fluorescent lamps.

Forest-Fire Response System Using Deep-Learning-Based Approaches With CCTV Images and Weather Data

An effective forest-fire response is critical for minimizing the losses caused by forest fires. The purpose of this study is to construct a model for early fire detection and damage area estimation for response systems based on deep learning. First, a large-scale fire dataset with approximately 400,000 images is used to train and test object-detection models. The optimal backbone for the faster region-based convolutional neural network (Faster R-CNN) model is determined using a DetNAS-based architecture search algorithm. Then, the searched light-weight backbone is compared with well-known backbones, such as ResNet, VoVNet, and FBNetV3. In addition, data pertaining to six years of historical forest fire events are employed to estimate the damaged area. Subsequently, a weather API is used to match the recorded events. A Bayesian neural network (BNN) model is used as a regression model to estimate the damaged area. Additionally, the trained model is compared with other widely used regression models, such as decision trees and neural networks. The Faster R-CNN with a searched backbone achieves a mean average precision of 27.9 on 40,000 testing images, outperforming existing backbones. Compared with other regression models, the BNN estimates the damage area with less error and increased generalization. Thus, both proposed models demonstrate their robustness and suitability for implementation in real-world systems.

Quantitative Evaluation of Line-Edge Roughness in Various FinFET Structures: Bayesian Neural Network With Automatic Model Selection

To design a device that is robust to process-induced random variation, this study proposes a machine-learning-based predictive model that can simulate the electrical characteristics of FinFETs with process-induced line-edge roughness. This model, i.e., a Bayesian neural network (BNN) model with horseshoe priors (Horseshoe-BNN), can significantly reduce the simulation time (as compared to the conventional technology computer-aided design (TCAD) simulation method) in a sufficiently accurate manner. Moreover, this model can perform autonomous model selection over the most compact layer size, which is necessary when the amount of data must be limited. The mean absolute percentage error for the mean and standard deviation of the drain-to-source current <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\left ({\mathrm {I}_{\mathrm {DS}} }\right)$ </tex-math></inline-formula> were ~0.5% and ~6%, respectively. By estimating the distribution of the current-voltage characteristics, the distributions of the other device metrics, such as off-state leakage current and threshold voltage, can be estimated as well.

A Survey on Bayesian Neural Networks

Bayesian Neural Network is the product of combining Bayesian and neural networks, which is one of the most popular neural network branches in deep learning and is widely used in model building in various fields. Bayesian inference is mainly divided into two types: variational inference and MCMC methods. Variational inference uses a pre-defined simple distribution to approximate the posterior distribution, which is faster and suitable for larger scale data. MCMC approach approaches the posterior distribution by sampling, which is more accurate, but relatively slower. This paper introduces three more representative Bayesian models and briefly introduces the main steps and formulas involved in the models. In addition, a variety of Bayesian neural network models are categorized and organized. Finally, the development of Bayesian is summarized and prospected.

Predicting plastic anisotropy using crystal plasticity and Bayesian neural network surrogate models

This work presents an efficient data-driven protocol to accurately predict plastic anisotropy from initial crystallographic texture. In this work, we integrated feed forward neural networks with Variational Bayesian Inference techniques to establish an accurate low-computational cost surrogate model capable of predicting the anisotropic constants based on the texture of the polycrystalline material with quantifiable uncertainty. The developed model was trained on the results of 54,480 crystal plasticity simulations. The performed simulations parametrized Hill’s anisotropic yield model for single crystals and polycrystalline textures, which were robustly represented using generalized spherical harmonics (GSH). Subsequently, the GSH-based representation of the different textures was linked to its corresponding Hill’s anisotropic coefficients using a variational Bayesian neural network. The efficacy and accuracy of the developed surrogate model were critically validated with the results of 20,000 new textures. The predictions from the Bayesian neural network model showed excellent agreement with results obtained from experiments and high-fidelity crystal plasticity finite element simulations.

Probabilistic electrical load forecasting for buildings using Bayesian deep neural networks

Deep learning techniques are increasingly applied in building electrical load analysis thanks to the enrichment of information-intensive sensory data. However, uncertainty is seldom considered among existing deep learning models. This study proposes three Bayesian deep neural network models for probabilistic building electrical load forecasting. Three prevalent deep neural networks (recurrent neural network (RNN), long short-term memory (LSTM), and gated recurrent unit (GRU)) are utilized for model development. In each model, the dropout technique is implemented as a variational Bayesian approximation to quantify two types of model uncertainties: aleatoric and epistemic uncertainty. Performances of the proposed models are evaluated using real data. The results showed that all the proposed three models achieved satisfactory performances and the Bayesian LSTM (BLSTM) model achieved the best performance with up to 15.4% mean absolute percentage error reduction than the baseline model. It was also found that the weather variables were not necessary inputs for Bayesian deep neural network models. The impacts of the input time lags and forecasting horizons on load forecasting accuracies were also investigated. It was found that the BLSTM model could derive decent model performances with only 10 h lagged electrical loads and achieve satisfactory accuracies for the 1-day ahead load forecasting.

A Bayesian CNN-LSTM Model for Sentiment Analysis in Massive Open Online Courses MOOCs

Massive Open Online Courses (MOOCs) are increasingly used by learn-ers to acquire knowledge and develop new skills. MOOCs provide a trove of data that can be leveraged to better assist learners, including behavioral data from built-in collaborative tools such as discussion boards and course wikis. Data tracing social interactions among learners are especially inter-esting as their analyses help improve MOOCs’ effectiveness. We particular-ly perform sentiment analysis on such data to predict learners at risk of dropping out, measure the success of the MOOC, and personalize the MOOC according to a learner’s behavior and detected emotions. In this pa-per, we propose a novel approach to sentiment analysis that combines the advantages of the deep learning architectures CNN and LSTM. To avoid highly uncertain predictions, we utilize a Bayesian neural network (BNN) model to quantify uncertainty within the sentiment analysis task. Our em-pirical results indicate that: 1) The Bayesian CNN-LSTM model provides interesting performance compared to other models (CNN-LSTM, CNN, LSTM) in terms of accuracy, precision, recall, and F1-Score; and 2) there is a high correlation between the sentiment in forum posts and the dropout rate in MOOCs.