Search

Medical cancer rehabilitation healthcare center data maintenance is a global challenge with increased mortality risk. The Internet of Things (IoT)-based applications in healthcare were implemented through sensors and various connecting devices. The main problem of this procedure is the privacy of data, which is the biggest challenge with IoT, as all the connected devices transfer data in real time, the integration of multiple and other protocols can be hacked by the end-to-end connection, and it is not secure, security issues may crop up due to handling of such massive data in real time. Recent studies showed that a more structured risk assessment is needed to secure the medical cancer rehabilitation healthcare center data maintenance. In this respect, collaborative learning frameworks, such as Deep Federated Collaborative Learning (DFCL), are implemented for the study of medical cancer rehabilitation healthcare center data maintenance based on IoT-based systems and are proposed with smart short-term Bayesian convolution network systems for data analysis. This DFCL approach has been preferred in this context, strengthening privacy by allowing sensitive data to be retained. Experiments on benchmark datasets demonstrate that the federated model balances fairness, privacy, and accuracy. In this paper, we analyze administrative data count by medical stages taken from 2016 to 2022, the administrative data include data for routine operations. It is frequently used to assess by achieving an accuracy range of 19.8%. The leading diagnoses taken as per the patient's cost and stay count identifying a disease, illness, or problem by examining the unusual combination of symptoms made an accurate diagnosis which is 26% more efficient than the leading diagnosis. The hospital dictionary analysis is based on dictionary analysis count and data visualization summary; accuracy is 50% higher than the existing data visualization summary. By comparing the hospital dictionary, home health care analysis shows a 44.5% efficient analysis rate for patient data maintenance. Moreover, the adult day-care centers analyzed 88.6% efficient analysis rate for patient data maintenance with 750 patients. [ABSTRACT FROM AUTHOR]

This paper proposes an innovative global solution which is a pioneering work applying automated machine learning algorithms to remarkable precision sparse underwater direction-of-arrival (DOA) estimation that views the subaquatic sparse-sampling DOA estimation problem as a classification prediction task. The proposed solution, termed automated multi-layer perceptron discriminative neural network (AutoMPDNN), is built upon a Bayesian optimization framework. AutoMPDNN transforms sparsely sampled time-domain signals into the complex domain, preserving essential components in a one-source single-snapshot scenario. Leveraging Bayesian optimization principles, the algorithm embeds necessary hyperparameters into the loss function, effectively defining it as a maximum likelihood problem using the upper confidence bound function and incorporating sparse signal features. We also explore the model space architecture and introduce variants of AutoMPDNN, denoted as AutoMPDNNs_ln (n = 2,3,4). Through a series of plane wave simulation experiments, it is demonstrated that AutoMPDNN achieves the highest prediction performance for one-source single-snapshot scenarios compared to classical DOA estimation algorithms that incorporate sparse representation approaches, as well as contemporary deep learning DOA methods under varying conditions. [ABSTRACT FROM AUTHOR]

This study aims to enhance diagnostic capabilities for optimising the performance of the anaerobic sewage treatment lagoon at Melbourne Water's Western Treatment Plant (WTP) through a novel machine learning (ML)-based monitoring strategy. This strategy employs ML to make accurate probabilistic predictions of biogas performance by leveraging diverse real-life operational and inspection sensor and other measurement data for asset management, decision making, and structural health monitoring (SHM). The paper commences with data analysis and preprocessing of complex irregular datasets to facilitate efficient learning in an artificial neural network. Subsequently, a Bayesian mixture density neural network model incorporating an attention-based mechanism in bidirectional long short-term memory (BiLSTM) was developed. This probabilistic approach uses a distribution output layer based on the Gaussian mixture model and Monte Carlo (MC) dropout technique in estimating data and model uncertainties, respectively. Furthermore, systematic hyperparameter optimisation revealed that the optimised model achieved a negative log-likelihood (NLL) of 0.074, significantly outperforming other configurations. It achieved an accuracy approximately 9 times greater than the average model performance (NLL = 0.753) and 22 times greater than the worst performing model (NLL = 1.677). Key factors influencing the model's accuracy, such as the input window size and the number of hidden units in the BiLSTM layer, were identified, while the number of neurons in the fully connected layer was found to have no significant impact on accuracy. Moreover, model calibration using the expected calibration error was performed to correct the model's predictive uncertainty. The findings suggest that the inherent data significantly contribute to the overall uncertainty of the model, highlighting the need for more high-quality data to enhance learning. This study lays the groundwork for applying ML in transforming high-value assets into intelligent structures and has broader implications for ML in asset management, SHM applications, and renewable energy sectors. [ABSTRACT FROM AUTHOR]

With the widespread use of computer-aided technologies like CAD/CAM/CAPP in the product manufacturing process, a large amount of process data is constantly generated and data-driven process planning has shown promising potentials for effectively reusing the process knowledge. However, a lot of labeled data are needed to train a deep learning model for effectively extracting the embedded knowledge and experiences within these process data and the labeling of process data is quite expensive and time-consuming. This paper proposes a cost-effective process design intents extraction approach for process data by combining active learning (AL) and self-paced learning (SPL). First, the process design intents inference model based on Bi-LSTM is generated by using a few pre-labeled samples. Then, the prediction uncertainty of each unlabeled sample is calculated by using a Bayesian neural network, which can assist in the identification of high confidence samples in SPL and low confidence samples in AL. Finally, the low confidence samples with manual-labels and the high confidence samples with pseudo-labels are incorporated into the training data for retraining the process design intents inference model iteratively until the model attains optimal performance. The experiments demonstrate that our approach can substantially decrease the number of labeled samples required for model training and the design intents in the process data could be inferred effectively with dynamically undated training data. [ABSTRACT FROM AUTHOR]

Bayesian neural networks (BNNs) have recently regained a significant amount of attention in the deep learning community due to the development of scalable approximate Bayesian inference techniques. There are several advantages of using a Bayesian approach: parameter and prediction uncertainties become easily available, facilitating more rigorous statistical analysis. Furthermore, prior knowledge can be incorporated. However, the construction of scalable techniques that combine both structural and parameter uncertainty remains a challenge. In this paper, we apply the concept of model uncertainty as a framework for structural learning in BNNs and, hence, make inferences in the joint space of structures/models and parameters. Moreover, we suggest an adaptation of a scalable variational inference approach with reparametrization of marginal inclusion probabilities to incorporate the model space constraints. Experimental results on a range of benchmark datasets show that we obtain comparable accuracy results with the competing models, but based on methods that are much more sparse than ordinary BNNs. [ABSTRACT FROM AUTHOR]

To enhance RUL prediction accuracy and uncertainty quantification, numerous methods have been developed, including model-based, data-driven, and hybrid approaches. However, model-based approaches struggle with complex relationships and uncertainties. Data-driven methods might overlook prior knowledge and struggle with limited data. Hybrid models for RUL prediction face two key challenges: inadequate use of physical information and difficulty in accurately quantifying uncertainty. Aiming at the problems of non-linearity, small sample sizes, and the absence of uncertainty quantification in RUL prediction, this paper introduces a hybrid method aimed at achieving RUL prediction and uncertainty quantification in few-slot scenarios. In this study, a hybrid approach that combines model-based approach and data-driven approach is proposed to achieve accurate RUL prediction. The uncertainty is measured based on a Bayesian framework. Specifically, the proposed method combines the degradation trend model using a double-exponential degradation model (DEDM), and the degradation fluctuations is predicted by a Gated Recurrent Unit (GRU) network to achieve point estimation of the RUL. Subsequently, an ensemble learning method is adopted to integrate the different modules using a Bayesian neural network (BNN) for uncertainty quantification. The applicability and effectiveness of the proposed method is investigated through case studies conducted on the three lithium battery datasets. The comparative analyses are also conducted with commonly used EMD-based approaches. Experimental results demonstrate that the proposed method has good performance in both data leakage and non-leakage scenarios and is more effective than individual methods to achieve accurate RUL prediction under small sample datasets. Finally, this study dedicates to integrate physical models and data-driven models to address the challenge of data drift in future research. [ABSTRACT FROM AUTHOR]

In this paper, three state-of-the-art deep learning uncertainty quantification (UQ) methods – Flipout probabilistic convolutional neural network (CNN), deep ensemble probabilistic CNN, and Bayesian probabilistic CNN – based on the Visual Geometry Group 13 architecture are proposed. They are compared with a traditional Bayesian inference approach for localizing delamination damage in composite. The law of conditional covariance is used to separate and quantify the predictive variance of the three networks into aleatoric and epistemic uncertainty. The network models' performance is enhanced through hyperparameter optimization using Hyperband and warm-up optimization algorithms. The performance of the three networks in measuring the uncertainty is assessed on an out-of-distribution (OOD) dataset and validated on an in-distribution (ID) dataset for localization of composite delamination damage. Results indicate high accuracy in predicting damage locations for all methods on the ID dataset. On the OOD dataset, the Flipout and deep ensemble network have better performance, stably measuring aleatoric uncertainty in both trained and untrained areas, while the Bayesian network's aleatoric uncertainty shows a discernible change across both areas. All three networks effectively measure epistemic uncertainty. Overall in both ID and OOD datasets, the Flipout network provides an optimal balance among training efficiency, UQ effectiveness and accuracy in predicting damage locations. [ABSTRACT FROM AUTHOR]

Deterministic inversion based on deep learning has been widely utilized in model parameters estimation. Constrained by logging data, seismic data, wavelet and modeling operator, deterministic inversion based on deep learning can establish nonlinear relationships between seismic data and model parameters. However, seismic data lacks low-frequency and contains noise, which increases the non-uniqueness of the solutions. The conventional inversion method based on deep learning can only establish the deterministic relationship between seismic data and parameters, and cannot quantify the uncertainty of inversion. In order to quickly quantify the uncertainty, a physics-guided deep mixture density network (PG-DMDN) is established by combining the mixture density network (MDN) with the deep neural network (DNN). Compared with Bayesian neural network (BNN) and network dropout, PG-DMDN has lower computing cost and shorter training time. A low-frequency model is introduced in the training process of the network to help the network learn the nonlinear relationship between narrowband seismic data and low-frequency impedance. In addition, the block constraints are added to the PG-DMDN framework to improve the horizontal continuity of the inversion results. To illustrate the benefits of proposed method, the PG-DMDN is compared with existing semi-supervised inversion method. Four synthetic data examples of Marmousi II model are utilized to quantify the influence of forward modeling part, low-frequency model, noise and the pseudo-wells number on inversion results, and prove the feasibility and stability of the proposed method. In addition, the robustness and generality of the proposed method are verified by the field seismic data. [ABSTRACT FROM AUTHOR]

Composite plates are susceptible to various damages in complex conditions and working environments, which may reduce the reliability of the structure and threaten equipment and personal safety. Thus, the implementation of a robust online Structural health monitoring (SHM) system for these composite structures becomes imperative. To enhance reliability and safety, we introduce a robust online SHM system anchored by our newly developed damage detection Bayesian neural network (DD-BNN). The main contribution of this study lies in the DD-BNN to perform precise and reliable damage detection and localization in composite plates using only one actuator-receiver pair without any signal/feature pre-processing and human intervention. The proposed DD-BNN model innovatively combines probabilistic modeling with deep learning to address uncertainty in Lamb wave-based damage detection and model performance for composite plates, featuring a specialized probabilistic layer trained through Bayesian inference to efficiently encapsulate and manage uncertainty in model weights and activation. Notably, our method significantly simplifies the SHM system design and manual operation requirements. In addition, this approach not only reduces overfitting but also enhances robustness to noise, as confirmed by experiments on perturbation analysis of Gaussian and Poisson noise. [ABSTRACT FROM AUTHOR]

Accurate traffic congestion estimation and prediction are critical building blocks for smart trip planning and rerouting decisions in transportation systems. Over the decades, there have been many studies focusing on traffic congestion estimation and prediction with different statistical approaches (e.g., Markov chain) and machine learning models (e.g., clustering, Bayesian networks, and artificial neural networks). However, there is a lack of a unified framework to address the mechanisms of different models and integrate the advantages of different methods through combinations. This paper introduces the FD-Markov-LSTM model, a hybrid interpretable approach that combines the fundamental diagram (FD), Markov chain, and long short-term memory (LSTM). The aim is to estimate and predict traffic states by integrating statistical data in both congested and uncongested scenarios. The FD-Markov-LSTM model leverages the FD to identify hierarchical traffic states and utilizes the Markov process to capture the probabilistic transitions between these states. We employ the LSTM model to further capture the residual time series produced by the Markov chain model (assuming a memoryless property) to enhance the estimation and prediction performance. The proposed model's accuracy in estimating and predicting traffic flow is evaluated using empirical data from three case studies conducted in Beijing and Los Angeles. The results highlight a significant improvement in accuracy compared to classical benchmark models such as the Markov model, ARIMA model, k-Nearest Neighbor model, Random Forest model, and LSTM. Specifically, the FD-Markov-LSTM model achieves reductions of over 39% in mean absolute error, 35% in root mean squared error, and 7.4% in mean absolute percentage error. These results clearly demonstrate that the FD-Markov-LSTM model outperforms the benchmark models, enabling more precise predictions of traffic flow. [ABSTRACT FROM AUTHOR]

Background: The willingness to trust predictions formulated by automatic algorithms is key in a wide range of domains. However, a vast number of deep architectures are only able to formulate predictions without associated uncertainty. Purpose: In this study, we propose a method to convert a standard neural network into a Bayesian neural network and estimate the variability of predictions by sampling different networks similar to the original one at each forward pass. Methods: We combine our method with a tunable rejection-based approach that employs only the fraction of the data, i.e., the share that the model can classify with an uncertainty below a user-set threshold. We test our model in a large cohort of brain images from patients with Alzheimer's disease and healthy controls, discriminating the former and latter classes based on morphometric images exclusively. Results: We demonstrate how combining estimated uncertainty with a rejection-based approach increases classification accuracy from 0.86 to 0.95 while retaining 75% of the test set. In addition, the model can select the cases to be recommended for, e.g., expert human evaluation due to excessive uncertainty. Importantly, our framework circumvents additional workload during the training phase by using our network "turned into Bayesian" to implicitly investigate the loss landscape in the neighborhood of each test sample in order to determine the reliability of the predictions. Conclusion: We believe that being able to estimate the uncertainty of a prediction, along with tools that can modulate the behavior of the network to a degree of confidence that the user is informed about (and comfortable with), can represent a crucial step in the direction of user compliance and easier integration of deep learning tools into everyday tasks currently performed by human operators. [ABSTRACT FROM AUTHOR]

With the development of deep learning technology, the problem of data‐driven trajectory prediction and intention recognition has been widely studied. However, the pedestrian trajectory prediction and intention recognition methods based solely on data‐driven have weak data description ability and black‐box characteristics, which cannot reason about pedestrian crossing intention and predict pedestrian crossing trajectory as humans do. To address the above problems, the authors proposed a data and knowledge‐driven pedestrian intention estimation and trajectory prediction method by imitating human cognitive mechanisms. In the pedestrian intention inference process, the authors adopted the knowledge‐driven method. As a first step, the authors built a knowledge graph of pedestrian crossing scenes, and then paired it with a Bayesian network to estimate pedestrian crossing intentions. In the pedestrian trajectory prediction process, the authors used a data‐driven approach, combining pedestrian crossing trajectory features and knowledge‐based pedestrian intentions. Experiments show that all evaluation metrics of pedestrian trajectory prediction were improved after adding pedestrian intentions obtained by knowledge‐driven. [ABSTRACT FROM AUTHOR]