Identifying pests in precision agriculture using low-cost image data acquisition.

Unmanned Aerial Vehicles (UAVs), often called drones, have gained progressive prevalence for their swift operational ability as well as their extensive applicability in diverse real-world situations. Of late, UAV usage in precision agriculture has attracted much interest from scientific community. This study will look at drone aid in precise farming. Big data has the ability to analyze enormous amounts of data. Due to this, it is one of the diverse crucial technologies of Information and Communication Technology (ICT) which had applied in precision agriculture for the abstraction of critical information as well as for assisting agricultural practitioners in the comprehension of the most feasible farming practices, and also for better decision-making. This work analyses communication protocols, as well as their application toward the challenge of commanding a drone fleet for protecting crops from infestations of parasites. For computer-vision tasks as well as data-intensive applications, the method of deep learning has shown much potential. Due to its vast potential, it can also be used in the field of agriculture. This research will employ several schemes to assess the efficacy of models includes Visual Geometry Group (VGG-16), the Convolutional Neural Network (CNN) as well as the Fully-Convolutional Network (FCN) in plant disease detection. The methods of Artificial Immune Systems (AIS) can be used in order to adapt deep neural networks to the immediate situation. Simulated outcomes demonstrate that the proposed method is providing superior performance over various other technologically-advanced methods.

Quantifying changes in oxygen saturation of the internal jugular vein in vivo using deep neural networks and subject-specific three-dimensional Monte Carlo models.

Central venous oxygen saturation (ScvO2) is an important parameter for assessing global oxygen usage and guiding clinical interventions. However, measuring ScvO2 requires invasive catheterization. As an alternative, we aim to noninvasively and continuously measure changes in oxygen saturation of the internal jugular vein (SijvO2) by a multi-channel near-infrared spectroscopy system. The relation between the measured reflectance and changes in SijvO2 is modeled by Monte Carlo simulations and used to build a prediction model using deep neural networks (DNNs). The prediction model is tested with simulated data to show robustness to individual variations in tissue optical properties. The proposed technique is promising to provide a noninvasive tool for monitoring the stability of brain oxygenation in broad patient populations.

Rehabilitation Assessment System for Stroke Patients Based on Fusion-Type Optoelectronic Plethysmography Device and Multi-Modality Fusion Model: Design and Validation.

This study aimed to propose a portable and intelligent rehabilitation evaluation system for digital stroke-patient rehabilitation assessment. Specifically, the study designed and developed a fusion device capable of emitting red, green, and infrared lights simultaneously for photoplethysmography (PPG) acquisition. Leveraging the different penetration depths and tissue reflection characteristics of these light wavelengths, the device can provide richer and more comprehensive physiological information. Furthermore, a Multi-Channel Convolutional Neural Network-Long Short-Term Memory-Attention (MCNN-LSTM-Attention) evaluation model was developed. This model, constructed based on multiple convolutional channels, facilitates the feature extraction and fusion of collected multi-modality data. Additionally, it incorporated an attention mechanism module capable of dynamically adjusting the importance weights of input information, thereby enhancing the accuracy of rehabilitation assessment. To validate the effectiveness of the proposed system, sixteen volunteers were recruited for clinical data collection and validation, comprising eight stroke patients and eight healthy subjects. Experimental results demonstrated the system's promising performance metrics (accuracy: 0.9125, precision: 0.8980, recall: 0.8970, F1 score: 0.8949, and loss function: 0.1261). This rehabilitation evaluation system holds the potential for stroke diagnosis and identification, laying a solid foundation for wearable-based stroke risk assessment and stroke rehabilitation assistance.

Interpretable (not just posthoc-explainable) medical claims modeling for discharge placement to reduce preventable all-cause readmissions or death.

We developed an inherently interpretable multilevel Bayesian framework for representing variation in regression coefficients that mimics the piecewise linearity of ReLU-activated deep neural networks. We used the framework to formulate a survival model for using medical claims to predict hospital readmission and death that focuses on discharge placement, adjusting for confounding in estimating causal local average treatment effects. We trained the model on a 5% sample of Medicare beneficiaries from 2008 and 2011, based on their 2009-2011 inpatient episodes (approximately 1.2 million), and then tested the model on 2012 episodes (approximately 400 thousand). The model scored an out-of-sample AUROC of approximately 0.75 on predicting all-cause readmissions-defined using official Centers for Medicare and Medicaid Services (CMS) methodology-or death within 30-days of discharge, being competitive against XGBoost and a Bayesian deep neural network, demonstrating that one need-not sacrifice interpretability for accuracy. Crucially, as a regression model, it provides what blackboxes cannot-its exact gold-standard global interpretation, explicitly defining how the model performs its internal "reasoning" for mapping the input data features to predictions. In doing so, we identify relative risk factors and quantify the effect of discharge placement. We also show that the posthoc explainer SHAP provides explanations that are inconsistent with the ground truth model reasoning that our model readily admits.

An intelligent model to decode students' behavioral states in physical education using back propagation neural network and Hidden Markov Model.

This paper highlights the need for intelligent analysis of students' behavioral states in physical education tasks. The hand-ring inertial data is used to identify students' motion sequence states. First, statistical feature extraction is performed based on the acceleration and angular velocity data collected from the bracelet. After completing the filtering and noise reduction of the data, we perform feature extraction by Back Propagation Neural Network (BPNN) and use the sliding window method for analysis. Finally, the classification capability of the model sequence is enhanced by the Hidden Markov Model (HMM). The experimental results indicate that the classification accuracy of student action sequences in physical education exceeds 96% after optimization by the HMM method. This provides intelligent means and new ideas for future student state recognition in physical education and teaching reform.

Enhancing urban blue-green landscape quality assessment through hybrid genetic algorithm-back propagation (GA-BP) neural network approach: a case study in Fucheng, China.

This study employs an artificial neural network optimization algorithm, enhanced with a Genetic Algorithm-Back Propagation (GA-BP) network, to assess the service quality of urban water bodies and green spaces, aiming to promote healthy urban environments. From an initial set of 95 variables, 29 key variables were selected, including 17 input variables, such as water and green space area, population size, and urbanization rate, six hidden layer neurons, such as patch number, patch density, and average patch size, and one output variable for the comprehensive value of blue-green landscape quality. The results indicate that the GA-BP network achieves an average relative error of 0.94772%, which is superior to the 1.5988% of the traditional BP network. Moreover, it boasts a prediction accuracy of 90% for the comprehensive value of landscape quality from 2015 to 2022, significantly outperforming the BP network's approximate 70% accuracy. This method enhances the accuracy of landscape quality assessment but also aids in identifying crucial factors influencing quality. It provides scientific and objective guidance for future urban landscape structure and layout, contributing to high-quality urban development and the creation of exemplary living areas.

Artificial intelligence in the healthcare sector: comparison of deep learning networks using chest X-ray images.

Purpose: Artificial intelligence has led to significant developments in the healthcare sector, as in other sectors and fields. In light of its significance, the present study delves into exploring deep learning, a branch of artificial intelligence. Methods: In the study, deep learning networks ResNet101, AlexNet, GoogLeNet, and Xception were considered, and it was aimed to determine the success of these networks in disease diagnosis. For this purpose, a dataset of 1,680 chest X-ray images was utilized, consisting of cases of COVID-19, viral pneumonia, and individuals without these diseases. These images were obtained by employing a rotation method to generate replicated data, wherein a split of 70 and 30% was adopted for training and validation, respectively. Results: The analysis findings revealed that the deep learning networks were successful in classifying COVID-19, Viral Pneumonia, and Normal (disease-free) images. Moreover, an examination of the success levels revealed that the ResNet101 deep learning network was more successful than the others with a 96.32% success rate. Conclusion: In the study, it was seen that deep learning can be used in disease diagnosis and can help experts in the relevant field, ultimately contributing to healthcare organizations and the practices of country managers.

The Determining Role of Covariances in Large Networks of Stochastic Neurons.

Biological neural networks are notoriously hard to model due to their stochastic behavior and high dimensionality. We tackle this problem by constructing a dynamical model of both the expectations and covariances of the fractions of active and refractory neurons in the network's populations. We do so by describing the evolution of the states of individual neurons with a continuous-time Markov chain, from which we formally derive a low-dimensional dynamical system. This is done by solving a moment closure problem in a way that is compatible with the nonlinearity and boundedness of the activation function. Our dynamical system captures the behavior of the high-dimensional stochastic model even in cases where the mean-field approximation fails to do so. Taking into account the second-order moments modifies the solutions that would be obtained with the mean-field approximation and can lead to the appearance or disappearance of fixed points and limit cycles. We moreover perform numerical experiments where the mean-field approximation leads to periodically oscillating solutions, while the solutions of the second-order model can be interpreted as an average taken over many realizations of the stochastic model. Altogether, our results highlight the importance of including higher moments when studying stochastic networks and deepen our understanding of correlated neuronal activity.

Bayesian tensor network structure search and its application to tensor completion.

Tensor network (TN) has demonstrated remarkable efficacy in the compact representation of high-order data. In contrast to the TN methods with pre-determined structures, the recently introduced tensor network structure search (TNSS) methods automatically learn a compact TN structure from the data, gaining increasing attention. Nonetheless, TNSS requires time-consuming manual adjustments of the penalty parameters that control the model complexity to achieve better performance, especially in the presence of missing or noisy data. To provide an effective solution to this problem, in this paper, we propose a parameters tuning-free TNSS algorithm based on Bayesian modeling, aiming at conducting TNSS in a fully data-driven manner. Specifically, the uncertainty in the data corruption is well-incorporated in the prior setting of the probabilistic model. For TN structure determination, we reframe it as a rank learning problem of the fully-connected tensor network (FCTN), integrating the generalized inverse Gaussian (GIG) distribution for low-rank promotion. To eliminate the need for hyperparameter tuning, we adopt a fully Bayesian approach and propose an efficient Markov chain Monte Carlo (MCMC) algorithm for posterior distribution sampling. Compared with the previous TNSS method, experiment results demonstrate the proposed algorithm can effectively and efficiently find the latent TN structures of the data under various missing and noise conditions and achieves the best recovery results. Furthermore, our method exhibits superior performance in tensor completion with real-world data compared to other state-of-the-art tensor-decomposition-based completion methods.

Automatic classification of dog barking using deep learning.

Barking and other dog vocalizations have acoustic properties related to emotions, physiological reactions, attitudes, or some particular internal states. In the field of intelligent audio analysis, researchers use methods based on signal processing and machine learning to analyze the digitized acoustic signals' properties and obtain relevant information. The present work describes a method to classify the identity, breed, age, sex, and context associated with each bark. This information can support the decisions of people who regularly interact with animals, such as dog trainers, veterinarians, rescuers, police, people with visual impairment. Our approach uses deep neural networks to generate trained models for each classification task. We worked with 19,643 barks recorded from 113 dogs of different breeds, ages and sexes. Our methodology consists of three stages. First, the pre-processing stage prepares the data and transforms it into the appropriate format for each classification model. Second, the characterization stage evaluates different representation models to identify the most suitable for each task. Third, the classification stage trains each classification model and selects the best hyperparameters. After tuning and training each model, we evaluated its performance. We analyzed the most relevant features extracted from the audio and the most appropriate deep neural network architecture for that feature type. Even if the application of our method is not ready for being used in ethological practice, our evaluation showed an outstanding performance of the proposed method, surpassing previous research results on this topic, providing the basis for further technological development.

The impact of technological innovation on the green digital economy and development strategies.

To investigate the interplay among technological innovation, industrial structure, production methodologies, economic growth, and environmental consequences within the paradigm of a green economy and to put forth strategies for sustainable development, this study scrutinizes the limitations inherent in conventional deep learning networks. Firstly, this study analyzes the limitations and optimization strategies of multi-layer perceptron (MLP) networks under the background of the green economy. Secondly, the MLP network model is optimized, and the dynamic analysis of the impact of technological innovation on the digital economy is discussed. Finally, the effectiveness of the optimization model is verified by experiments. Moreover, a sustainable development strategy based on dynamic analysis is also proposed. The experimental results reveal that, in comparison to traditional Linear Regression (LR), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), and Naive Bayes (NB) models, the optimized model in this study demonstrates improved performance across various metrics. With a sample size of 500, the optimized model achieves a prediction accuracy of 97.2% for forecasting future trends, representing an average increase of 14.6%. Precision reaches 95.4%, reflecting an average enhancement of 19.2%, while sensitivity attains 84.1%, with an average improvement of 11.8%. The mean absolute error is only 1.16, exhibiting a 1.4 reduction compared to traditional models and confirming the effectiveness of the optimized model in prediction. In the examination of changes in industrial structure using 2020 data to forecast the output value of traditional and green industries in 2030, it is observed that the output value of traditional industries is anticipated to decrease, with an average decline of 11.4 billion yuan. Conversely, propelled by the development of the digital economy, the output value of green industries is expected to increase, with an average growth of 23.4 billion yuan. This shift in industrial structure aligns with the principles and trends of the green economy, further promoting sustainable development. In the study of innovative production methods, the green industry has achieved an increase in output and significantly enhanced production efficiency, showing an average growth of 2.135 million tons compared to the average in 2020. Consequently, this study highlights the dynamic impact of technological innovation on the digital economy and its crucial role within the context of a green economy. It holds certain reference significance for research on the dynamic effects of the digital economy under technological innovation.

LightPRA: A Lightweight Temporal Convolutional Network for Automatic Physical Rehabilitation Exercise Assessment.

Research evidence shows that physical rehabilitation exercises prescribed by medical experts can assist in restoring physical function, improving life quality, and promoting independence for physically disabled individuals. In response to the absence of immediate expert feedback on performed actions, developing a Human Action Evaluation (HAE) system emerges as a valuable automated solution, addressing the need for accurate assessment of exercises and guidance during physical rehabilitation. Previous HAE systems developed for the rehabilitation exercises have focused on developing models that utilize skeleton data as input to compute a quality score for each action performed by the patient. However, existing studies have focused on improving scoring performance while often overlooking computational efficiency. In this research, we propose LightPRA (Light Physical Rehabilitation Assessment) system, an innovative architectural solution based on a Temporal Convolutional Network (TCN), which harnesses the capabilities of dilated causal Convolutional Neural Networks (CNNs). This approach efficiently captures complex temporal features and characteristics of the skeleton data with lower computational complexity, making it suitable for real-time feedback provided on resource-constrained devices such as Internet of Things (IoT) devices and Edge computing frameworks. Through empirical analysis performed on the University of Idaho-Physical Rehabilitation Movement Data (UI-PRMD) and KInematic assessment of MOvement for remote monitoring of physical REhabilitation (KIMORE) datasets, our proposed LightPRA model demonstrates superior performance over several state-of-the-art approaches such as Spatial-Temporal Graph Convolutional Network (STGCN) and Long Short-Term Memory (LSTM)-based models in scoring human activity performance, while exhibiting lower computational cost and complexity.

BlazePose-Seq2Seq: Leveraging Regular RGB Cameras for Robust Gait Assessment.

Evaluation of human gait through smartphone-based pose estimation algorithms provides an attractive alternative to costly lab-bound instrumented assessment and offers a paradigm shift with real time gait capture for clinical assessment. Systems based on smart phones, such as OpenPose and BlazePose have demonstrated potential for virtual motion assessment but still lack the accuracy and repeatability standards required for clinical viability. Seq2seq architecture offers an alternative solution to conventional deep learning techniques for predicting joint kinematics during gait. This study introduces a novel enhancement to the low-powered BlazePose algorithm by incorporating a Seq2seq autoencoder deep learning model. To ensure data accuracy and reliability, synchronized motion capture involving an RGB camera and ten Vicon cameras were employed across three distinct self-selected walking speeds. This investigation presents a groundbreaking avenue for remote gait assessment, harnessing the potential of Seq2seq architectures inspired by natural language processing (NLP) to enhance pose estimation accuracy. When comparing BlazePose alone to the combination of BlazePose and 1D convolution Long Short-term Memory Network (1D-LSTM), Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM), the average mean absolute errors decreased from 13.4° to 5.3° for fast gait, from 16.3° to 7.5° for normal gait, and from 15.5° to 7.5° for slow gait at the left ankle joint angle respectively. The strategic utilization of synchronized data and rigorous testing methodologies further bolsters the robustness and credibility of these findings.

A method for managing scientific research project resource conflicts and predicting risks using BP neural networks.

This study begins by considering the resource-sharing characteristics of scientific research projects to address the issues of resource misalignment and conflict in scientific research project management. It comprehensively evaluates the tangible and intangible resources required during project execution and establishes a resource conflict risk index system. Subsequently, a resource conflict risk management model for scientific research projects is developed using Back Propagation (BP) neural networks. This model incorporates the Dropout regularization technique to enhance the generalization capacity of the BP neural network. Leveraging the BP neural network's non-linear fitting capabilities, it captures the intricate relationship between project resource demand and supply. Additionally, the model employs self-learning to continuously adapt to new scenarios based on historical data, enabling more precise resource conflict risk assessments. Finally, the model's performance is analyzed. The results reveal that risks in scientific research project management primarily fall into six categories: material, equipment, personnel, financial, time, and organizational factors. This study's model algorithm exhibits the highest accuracy in predicting time-related risks, achieving 97.21%, surpassing convolutional neural network algorithms. Furthermore, the Root Mean Squared Error of the model algorithm remains stable at approximately 0.03, regardless of the number of hidden layer neurons, demonstrating excellent fitting capabilities. The developed BP neural network risk prediction framework in this study, while not directly influencing resource utilization efficiency or mitigating resource conflicts, aims to offer robust data support for research project managers when making decisions on resource allocation. The framework provides valuable insights through sensitivity analysis of organizational risks and other factors, with their relative importance reaching up to 20%. Further research should focus on defining specific strategies for various risk factors to effectively enhance resource utilization efficiency and manage resource conflicts.

Comparing various AI approaches to traditional quantitative assessment of the myocardial perfusion in [82Rb] PET for MACE prediction.

Assessing the individual risk of Major Adverse Cardiac Events (MACE) is of major importance as cardiovascular diseases remain the leading cause of death worldwide. Quantitative Myocardial Perfusion Imaging (MPI) parameters such as stress Myocardial Blood Flow (sMBF) or Myocardial Flow Reserve (MFR) constitutes the gold standard for prognosis assessment. We propose a systematic investigation of the value of Artificial Intelligence (AI) to leverage [ 82 Rb] Silicon PhotoMultiplier (SiPM) PET MPI for MACE prediction. We establish a general pipeline for AI model validation to assess and compare the performance of global (i.e. average of the entire MPI signal), regional (17 segments), radiomics and Convolutional Neural Network (CNN) models leveraging various MPI signals on a dataset of 234 patients. Results showed that all regional AI models significantly outperformed the global model ( p < 0.001 ), where the best AUC of 73.9% (CI 72.5-75.3) was obtained with a CNN model. A regional AI model based on MBF averages from 17 segments fed to a Logistic Regression (LR) constituted an excellent trade-off between model simplicity and performance, achieving an AUC of 73.4% (CI 72.3-74.7). A radiomics model based on intensity features revealed that the global average was the least important feature when compared to other aggregations of the MPI signal over the myocardium. We conclude that AI models can allow better personalized prognosis assessment for MACE.

Evaluation of water resources security in Anhui Province based on GA-BP model.

Water resources security is an important cornerstone of regional sustainable development, but the current evaluation system of water resources security is not scientific, and the measurement of safety level has not been optimized by combining algorithms. In this paper, indicators are selected according to the actual situation in Anhui Province. Firstly, correlation analysis (CA) and principal component analysis (PCA) are used to reduce the dimensionality of indicators, and then, the scientific evaluation is carried out based on genetic algorithm optimized back propagation neural network (GA-BP). This paper improves the generalization ability of the evaluation model and overcomes the shortcomings of the traditional model, which is slow in convergence and easy to fall into local optimality. The results showed that the water resources security level showed an obvious improvement trend from 2006 to 2020 and stabilized at a relatively safe level from 2014 to 2020. The subsystem of water resources environmental security is the least secure, followed by the subsystem of social and economic security, and the security of water resources regulation and response is basically stable at a relatively safe level. The conclusion of this study can provide decision-making basis for the relevant research of government, society, and scientific community.

A novel decision support system for proactive risk management in healthcare based on fuzzy inference, neural network and support vector machine.

BACKGROUND: The nature of activities practiced in healthcare organizations makes risk management the most crucial issue for decision-makers, especially in developing countries. New technologies provide effective solutions to support engineers in managing risks. PURPOSE: This study aims to develop a Decision Support System (DSS) adapted to the healthcare constraints of developing countries that enables the provision of decisions about risk tolerance classes and prioritizations of risk treatment. METHODS: Failure Modes and Effects Analysis (FMEA) is a popular method for risk assessment and quality improvement. Fuzzy logic theory is combined with this method to provide a robust tool for risk evaluation. The fuzzy FMEA provides fuzzy Risk Priority Number (RPN) values. The artificial neural network is a powerful algorithm used in this study to classify identified risk tolerances. The risk treatment process is taken into consideration in this study by improving FMEA. A new factor is added to evaluate the feasibility of correcting the intolerable risks, named the control factor, to prioritize these risks and start with the easiest. The new factor is combined with the fuzzy RPN to obtain intolerable risk prioritization. This prioritization is classified using the support vector machine. FINDINGS: Results prove that our DSS is effective according to these reasons: (1) The fuzzy-FMEA surmounts classical FMEA drawbacks. (2) The accuracy of the risk tolerance classification is higher than 98%. (3) The second fuzzy inference system developed (the control factor for intolerable risks with the fuzzy RPN) is useful because of the imprecise situation. (4) The accuracy of the fuzzy-priority results is 74% (mean of testing and training data). CONCLUSIONS: Despite the advantages, our DSS also has limitations: There is a need to generalize this support to other healthcare departments rather than one case study (the sterilization unit) in order to confirm its applicability and efficiency in developing countries.

Development of Multimodal Fusion Technology for Tomato Maturity Assessment.

The maturity of fruits and vegetables such as tomatoes significantly impacts indicators of their quality, such as taste, nutritional value, and shelf life, making maturity determination vital in agricultural production and the food processing industry. Tomatoes mature from the inside out, leading to an uneven ripening process inside and outside, and these situations make it very challenging to judge their maturity with the help of a single modality. In this paper, we propose a deep learning-assisted multimodal data fusion technique combining color imaging, spectroscopy, and haptic sensing for the maturity assessment of tomatoes. The method uses feature fusion to integrate feature information from images, near-infrared spectra, and haptic modalities into a unified feature set and then classifies the maturity of tomatoes through deep learning. Each modality independently extracts features, capturing the tomatoes' exterior color from color images, internal and surface spectral features linked to chemical compositions in the visible and near-infrared spectra (350 nm to 1100 nm), and physical firmness using haptic sensing. By combining preprocessed and extracted features from multiple modalities, data fusion creates a comprehensive representation of information from all three modalities using an eigenvector in an eigenspace suitable for tomato maturity assessment. Then, a fully connected neural network is constructed to process these fused data. This neural network model achieves 99.4% accuracy in tomato maturity classification, surpassing single-modal methods (color imaging: 94.2%; spectroscopy: 87.8%; haptics: 87.2%). For internal and external maturity unevenness, the classification accuracy reaches 94.4%, demonstrating effective results. A comparative analysis of performance between multimodal fusion and single-modal methods validates the stability and applicability of the multimodal fusion technique. These findings demonstrate the key benefits of multimodal fusion in terms of improving the accuracy of tomato ripening classification and provide a strong theoretical and practical basis for applying multimodal fusion technology to classify the quality and maturity of other fruits and vegetables. Utilizing deep learning (a fully connected neural network) for processing multimodal data provides a new and efficient non-destructive approach for the massive classification of agricultural and food products.

Energy Expenditure Prediction from Accelerometry Data Using Long Short-Term Memory Recurrent Neural Networks.

The accurate estimation of energy expenditure from simple objective accelerometry measurements provides a valuable method for investigating the effect of physical activity (PA) interventions or population surveillance. Methods have been evaluated previously, but none utilize the temporal aspects of the accelerometry data. In this study, we investigated the energy expenditure prediction from acceleration measured at the subjects' hip, wrist, thigh, and back using recurrent neural networks utilizing temporal elements of the data. The acceleration was measured in children (N = 33) performing a standardized activity protocol in their natural environment. The energy expenditure was modelled using Multiple Linear Regression (MLR), stacked long short-term memory (LSTM) networks, and combined convolutional neural networks (CNN) and LSTM. The correlation and mean absolute percentage error (MAPE) were 0.76 and 19.9% for the MLR, 0.882 and 0.879 and 14.22% for the LSTM, and, with the combined LSTM-CNN, the best performance of 0.883 and 13.9% was achieved. The prediction error for vigorous intensities was significantly different (p < 0.01) from those of the other intensity domains: sedentary, light, and moderate. Utilizing the temporal elements of movement significantly improves energy expenditure prediction accuracy compared to other conventional approaches, but the prediction error for vigorous intensities requires further investigation.

Optimisation and Calibration of Bayesian Neural Network for Probabilistic Prediction of Biogas Performance in an Anaerobic Lagoon.

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.