Search

The traditional method for retrieving cloud optical thickness (COT) is carried out through a Look-Up Table (LUT). Researchers must make a series of idealized assumptions and conduct extensive observations and record features in this scenario, consuming considerable resources. The emergence of deep learning effectively addresses the shortcomings of the traditional approach. In this paper, we first propose a daytime (SOZA < 70°) COT retrieval algorithm based on FY-4A AGRI. We establish and train a Convolutional Neural Network (CNN) model for COT retrieval, CM4CR, with the CALIPSO's COT product spatially and temporally synchronized as the ground truth. Then, a deep learning method extended from video prediction models is adopted to predict COT values based on the retrieval results obtained from CM4CR. The COT prediction model (CPM) consists of an encoder, a predictor, and a decoder. On this basis, we further incorporated a time embedding module to enhance the model's ability to learn from irregular time intervals in the input COT sequence. During the training phase, we employed Charbonnier Loss and Edge Loss to enhance the model's capability to represent COT details. Experiments indicate that our CM4CR outperforms existing COT retrieval methods, with predictions showing better performance across several metrics than other benchmark prediction models. Additionally, this paper also investigates the impact of different lengths of COT input sequences and the time intervals between adjacent frames of COT on prediction performance. [ABSTRACT FROM AUTHOR]

Most of the deep-learning algorithms on stock price volatility prediction in the existing literature use data such as same-frequency market indicators or technical indicators, and less consider mixed-frequency data, such as macro-data. Compared with the traditional model that only inputs the same-frequency data such as technical indicators and market indicators, this study proposes an improved deep-learning model based on mixed-frequency big data. This paper first introduces the reserve restricted mixed-frequency data sampling (RR-MIDAS) model to deal with the mixed-frequency data and, secondly, extracts the temporal and spatial features of volatility series by using the parallel model of CNN-LSTM and LSTM, and finally utilizes the Optuna framework for hyper-parameter optimization to achieve volatility prediction. For the deep-learning model with mixed-frequency data, its RMSE, MAE, MSLE, MAPE, SMAPE, and QLIKE are reduced by 18.25%, 14.91%, 30.00%, 12.85%, 13.74%, and 23.42%, respectively. This paper provides a more accurate and robust method for forecasting the realized volatility of stock prices under mixed-frequency data. [ABSTRACT FROM AUTHOR]

Underwater acoustic (UWA) channel prediction technology, as an important topic in UWA communication, has played an important role in UWA adaptive communication network and underwater target perception. Although many significant advancements have been achieved in underwater acoustic channel prediction over the years, a comprehensive summary and introduction is still lacking. As the first comprehensive overview of UWA channel prediction, this paper introduces past works and algorithm implementation methods of channel prediction from the perspective of linear, kernel-based, and deep learning approaches. Importantly, based on available at-sea experiment datasets, this paper compares the performance of current primary UWA channel prediction algorithms under a unified system framework, providing researchers with a comprehensive and objective understanding of UWA channel prediction. Finally, it discusses the directions and challenges for future research. The survey finds that linear prediction algorithms are the most widely applied, and deep learning, as the most advanced type of algorithm, has moved this field into a new stage. The experimental results show that the linear algorithms have the lowest computational complexity, and when the training samples are sufficient, deep learning algorithms have the best prediction performance. [ABSTRACT FROM AUTHOR]

Deep learning models have a high application value in runoff forecasting, but their prediction mechanism is difficult to interpret and their computational cost is high when dealing with complex hydrological relationships, limiting their feasibility in hydrological process mechanism analysis. To address these concerns, the paper first introduces an attention mechanism (AM) for building a long short-term memory network (LSTM) model with AM in the hidden layer (AM-LSTM). The AM-LSTM model employs attention layers to improve information extraction from hidden layers, resulting in a more accurate representation of the relationships between runoff-related elements. Furthermore, in the hidden layers of the AM-LSTM model, interpretable spatiotemporal attention units are established, which not only improves the model's prediction accuracy but also provides interpretability to the forecasting process. Furthermore, parallelization techniques are used in the paper to address the issue of model runtime cost. Simultaneously, to address the accuracy degradation caused by parallelization, the paper employs wavelet denoising (WD) techniques and builds the WD-AM-LSTM model. This accomplishment enables the runoff forecasting model to predict runoff in real time and with high accuracy. Based on validation using ten-day runoff data from the Huanren Reservoir in the Hun River's middle reaches, the results show that, with two layers and an eight-batch size, the AM-LSTM model outperforms the LSTM model in capturing spatiotemporal runoff features. During the model testing phase, the AM-LSTM model improves the MAE, RMSE, and NSE performance metrics by 8.46%, 13%, and 3.82%, respectively. The WD-AM-LSTM model effectively mitigates the noise impact caused by data parallelization under the conditions of two layers and a batch size of 512, achieving the same level of prediction performance while reducing computational cost by 92.01%. By incorporating attention mechanisms and wavelet denoising techniques, this study obtains high-speed and accurate predictions with interpretable results. It expands the deep learning models' applicability in ten-day runoff forecasting work. [ABSTRACT FROM AUTHOR]

Due to the complexity of the factors influencing membrane fouling in membrane bioreactors (MBR), it is difficult to accurately predict membrane fouling. This paper proposes a multi-strategy of integration aquila optimizer deep belief network (MAO-DBN) based membrane fouling prediction method. The method is developed to improve the accuracy and efficiency of membrane fouling prediction. Firstly, partial least squares (PLS) are used to reduce the dimensionality of many membrane fouling factors to improve the algorithm's generalization ability. Secondly, considering the drawbacks of deep belief network (DBN) such as long training time and easy overfitting, piecewise mapping is introduced in aquila optimizer (AO) to improve the uniformity of population distribution, while adaptive weighting is used to improve the convergence speed and prevent falling into local optimum. Finally, the prediction of membrane fouling is carried out by utilizing membrane fouling data as the research object. The experimental results show that the method proposed in this paper can achieve accurate prediction of membrane fluxes, with an 88.45% reduction in RMSE and 87.53% reduction in MAE compared with the DBN model before improvement. The experimental results show that the model proposed in this paper achieves a prediction accuracy of 98.61%, both higher than other comparative models, which can provide a theoretical basis for membrane fouling prediction in the practical operation of membrane water treatment. [ABSTRACT FROM AUTHOR]

Accurate power load prediction is an important guide for power system planning and operation. High‐ or low‐load prediction results will affect the operation of the power system. In recent years, deep learning technology represented by convolution neural network (CNN) and transformer has been proved to be suitable for power load prediction. This paper proposes a new short‐term power load hybrid forecasting model, called channel enhanced attention (CEA) and temporal convolutional network (TCN)‐based transformer comprehensive forecasting model. This method combines the short‐term feature extraction ability of TCN with the long‐term dependent capture ability of transformer for short‐term load forecasting. And the CEA designed in this study is added to improve the prediction accuracy. On the same dataset, the designed model predicts power load mean square errors of 0.056 and 0.146 for the next 24 h and the next week, respectively, which is 0.002 to 0.073 and 0.012 to 0.024 lower than the baseline model. The experimental results show that the hybrid short‐term power load prediction model proposed in this paper is significantly better than the existing methods. The predicted curve is in agreement with the actual charge change, which provides a good guidance for short‐term power load prediction. [ABSTRACT FROM AUTHOR]

Recently, transfer learning has gained popularity in the machine learning community. Transfer Learning (TL) has emerged as a promising paradigm that leverages knowledge learned from one or more related domains to improve prediction accuracy in a target domain with limited data. However, for time series forecasting (TSF) applications, transfer learning is relatively new. This paper addresses the need for empirical studies as identified in recent reviews advocating the need for practical guidelines for Transfer Learning approaches and method designs for time series forecasting. The main contribution of this paper is the suggestion of a comprehensive framework for Transfer Learning Sensitivity Analysis (SA) for time series forecasting. We achieve this by identifying various parameters seen from various angles of transfer learning applied to time series, aiming to uncover factors and insights that influence the performance of transfer learning in time series forecasting. Undoubtedly, symmetry appears to be a core aspect in the consideration of these factors and insights. A further contribution is the introduction of four TL performance metrics encompassed in our framework. These TL performance metrics provide insight into the extent of the transferability between the source and the target domains. Analyzing whether the benefits of transferred knowledge are equally or unequally accessible and applicable across different domains or tasks speaks to the requirement of symmetry or asymmetry in transfer learning. Moreover, these TL performance metrics inform on the possibility of the occurrence of negative transfers and also provide insight into the possible vulnerability of the network to catastrophic forgetting. Finally, we discuss a sensitivity analysis of an Ensemble TL technique use case (with Multilayer Perceptron models) as a proof of concept to validate the suggested framework. While the results from the experiments offer empirical insights into various parameters that impact the transfer learning gain, they also raise the question of network dimensioning requirements when designing, specifically, a neural network for transfer learning. [ABSTRACT FROM AUTHOR]

The accidental leakage of gaseous hydrogen from hydrogen refueling station facilities has the potential to result in a large fire and explosion catastrophe. The ability to forecast the spatiotemporal evolution of hydrogen plumes in real-time is crucial for monitoring the distribution of plume concentrations and mitigating the risk of fire and explosion. The utilization of deep learning has been extensively employed in a diverse range of spatiotemporal forecasting tasks. However, these approaches encounter limitations in accurately quantifying uncertainty when predicting spatiotemporal concentrations and plume boundaries. This research paper introduces a novel model called DPSTNN_H 2 Evolution, which is a deep probabilistic spatial-temporal neural network designed for forecasting the spatiotemporal evolution of hydrogen plumes. The benchmark dataset is constructed by the implementation of numerical simulations pertaining to the inadvertent leak of hydrogen within a hydrogen refueling station. The findings of the study indicate that incorporating quantified uncertainty information might enhance the precision of plume boundaries and the resilience of plume concentrations when predicting the spatiotemporal development of hydrogen. By employing Monte Carlo sampling with a sample size of m = 100 and a dropout rate of p = 0.1 , the model demonstrates the ability to provide real-time inference for 10 instances of plumes, while maintaining a high level of accuracy with R2 = 0.9829. In comparison to the current state-of-the-art model, the proposed model demonstrates superior accuracy and robustness in forecasting the spatiotemporal evolution of hydrogen plumes. In general, our proposed model has the potential to serve as a dependable option for the development of a digital twin for emergency management of hydrogen refueling stations. • Probabilistic spatial-temporal neural network model for hydrogen plume evolutions is proposed. • Normalized uncertainty contours and uncertainty intervals to improve accuracy and robustness. • Numerical experiment of hydrogen leakage and dispersion in refueling station are conducted. • Optimal hyper-parameters of the proposed model are determined • Comparison between the proposed model with point-estimation based model is conducted [ABSTRACT FROM AUTHOR]

The data-driven modular deep fuzzy model has demonstrated excellent forecasting performance due to its clear architecture and powerful fuzzy inference ability. However, the fixed structure predesigned for specific types of datasets limits the further improvement of generalization ability, especially when facing high-dimensional datasets with the challenging problem of rule explosion, thereby suffering from the time-consuming training process. To overcome these limitations, a novel randomized fuzzy modules (RFMs) stacked residual deep fuzzy system (RFM-RDFS) is proposed in this study. Firstly, to obtain high-precision outputs, this paper presents a residual deep fuzzy framework by stacking RFMs layer by layer, where the modules in the current layer only learn the residual of the previous layer. Secondly, to improve the design freedom for different applications, the RFM with multiple inputs is raised, where the input variables are allocated by a sliding window along the input spaces of the layers, so the number of the parallel modules in the same layer can be flexibly adjusted. Meanwhile, in the RFM, inspired by the extreme learning machine, the centers and widths of Gaussian membership functions are randomly generated, which can greatly accelerate the training speed. Thirdly, to strengthen the approximation performance, the consequent parameters of the fuzzy rules in each RFM are learned by minimizing the loss function with the regularization terms through the ridge regression algorithm. Finally, extensive experiments on various datasets are conducted to compare the proposed RFM-RDFS with several state-of-the-art shallow and deep models. The detailed comparison results clearly show that the proposed RFM-RDFS is more flexible and compact, and has greater advantages in terms of the interpretability, generalization ability and robustness. [ABSTRACT FROM AUTHOR]

With the rapid development of data acquisition and storage technology, spatio-temporal (ST) data in various fields are growing explosively, so many ST prediction methods have emerged. The review presented in this paper mainly studies the prediction of ST series. We propose a new taxonomy organized along three dimensions: ST series prediction methods (focusing on time feature learning, focusing on spatial feature learning, and focusing on spatial–temporal feature learning), techniques of ST series prediction (the RNN-, CNN-, and transformer-based models, as well as the CNN-based-composite model and GNN-based-composite models, and the miscellaneous model) and ST series prediction results (single target and multi-target). We first introduce and explain each dimension of the taxonomy in detail. After providing this three-dimensional view, we comprehensively review and compare the recent related ideas in the literature and analyze their advantages and limitations. Moreover, we summarize the key information of the existing literature and provide guidance for researchers to select suitable models. Second, we summarize the different applications of deep learning models in ST series prediction based on current literature and list relevant datasets and download links per application classifications. Lastly, we comprehensively analyze the current innovation and challenges and suggest future directions for researching ST series prediction after comparing and analyzing the computing performance of these forecasting models. In addition, each method or model solves one aspect of the challenge, which means that two or more methods should be combined to solve more challenges at the same time. We hope this article provides readers a broader and deeper understanding of the field of ST series research. [ABSTRACT FROM AUTHOR]

Accurate power load forecasting is crucial for the sustainable operation of smart grids. However, the complexity and uncertainty of load, along with the large-scale and high-dimensional energy information, present challenges in handling intricate dynamic features and long-term dependencies. This paper proposes a computational approach to address these challenges in short-term power load forecasting and energy information management, with the goal of accurately predicting future load demand. The study introduces a hybrid method that combines multiple deep learning models, the Gated Recurrent Unit (GRU) is employed to capture long-term dependencies in time series data, while the Temporal Convolutional Network (TCN) efficiently learns patterns and features in load data. Additionally, the attention mechanism is incorporated to automatically focus on the input components most relevant to the load prediction task, further enhancing model performance. According to the experimental evaluation conducted on four public datasets, including GEFCom2014, the proposed algorithm outperforms the baseline models on various metrics such as prediction accuracy, efficiency, and stability. Notably, on the GEFCom2014 dataset, FLOP is reduced by over 48.8%, inference time is shortened by more than 46.7%, and MAPE is improved by 39%. The proposed method significantly enhances the reliability, stability, and cost-effectiveness of smart grids, which facilitates risk assessment optimization and operational planning under the context of information management for smart grid systems. [ABSTRACT FROM AUTHOR]

The complexity in stock index futures markets, influenced by the intricate interplay of human behavior, is characterized as nonlinearity and dynamism, contributing to significant uncertainty in long-term price forecasting. While machine learning models have demonstrated their efficacy in stock price forecasting, they rely solely on historical price data, which, given the inherent volatility and dynamic nature of financial markets, are insufficient to address the complexity and uncertainty in long-term forecasting due to the limited connection between historical and forecasting prices. This paper introduces a pioneering approach that integrates financial theory with advanced deep learning methods to enhance predictive accuracy and risk management in China's stock index futures market. The SF-Transformer model, combining spot-forward parity and the Transformer model, is proposed to improve forecasting accuracy across short and long-term horizons. Formulated upon the arbitrage-free futures pricing model, the spot-forward parity model offers variables such as stock index price, risk-free rate, and stock index dividend yield for forecasting. Our insight is that the mutual information generated by these variables has the potential to significantly reduce uncertainty in long-term forecasting. A case study on predicting major stock index futures prices in China demonstrates the superiority of the SF-Transformer model over models based on LSTM, MLP, and the stock index futures arbitrage-free pricing model, covering both short and long-term forecasting up to 28 days. Unlike existing machine learning models, the Transformer processes entire time series concurrently, leveraging its attention mechanism to discern intricate dependencies and capture long-range relationships, thereby offering a holistic understanding of time series data. An enhancement of mutual information is observed after introducing spot-forward parity in the forecasting. The variation of mutual information and ablation study results highlights the significant contributions of spot-forward parity, particularly to the long-term forecasting. Overall, these findings highlight the SF-Transformer model's efficacy in leveraging spot-forward parity for reducing uncertainty and advancing robust and comprehensive approaches in long-term stock index futures price forecasting. [ABSTRACT FROM AUTHOR]

The applications of deep learning and artificial intelligence have permeated daily life, with time series prediction emerging as a focal area of research due to its significance in data analysis. The evolution of deep learning methods for time series prediction has progressed from the Convolutional Neural Network (CNN) and the Recurrent Neural Network (RNN) to the recently popularized Transformer network. However, each of these methods has encountered specific issues. Recent studies have questioned the effectiveness of the self-attention mechanism in Transformers for time series prediction, prompting a reevaluation of approaches to LTSF (Long Time Series Forecasting) problems. To circumvent the limitations present in current models, this paper introduces a novel hybrid network, Temporal Convolutional Network-Linear (TCN-Linear), which leverages the temporal prediction capabilities of the Temporal Convolutional Network (TCN) to enhance the capacity of LSTF-Linear. Time series from three classical chaotic systems (Lorenz, Mackey–Glass, and Rossler) and real-world stock data serve as experimental datasets. Numerical simulation results indicate that, compared to classical networks and novel hybrid models, our model achieves the lowest RMSE, MAE, and MSE with the fewest training parameters, and its R2 value is the closest to 1. [ABSTRACT FROM AUTHOR]

Execution of a marine operation (MO) requires coordinated actions of several vessels conducting simultaneous and sequential offshore activities. These activities have their operational limits given in terms of environmental parameters. Wave parameters are important because of their high energetic level. During the execution of a MO, forecast wave spectral parameters, i.e., significant wave height (Hs), peak period (Tp), and peak direction, are used to make an on-board decision. For critical operations, the use of forecasts can be complemented with buoy measurements. This paper proposes to use synthetic statistics of vessel dynamic responses to predict "real-time" wave spectral parameters using multi-output machine learning (ML) regression algorithms. For a case study of a vessel with no forward speed, it is observed that the random forest model predicts accurate Hs and Tp parameters. The prediction of wave direction is not very accurate but it can be corrected with on-board observations. The random forest model has good performance; it is efficient, useful for practical purposes, and comparable with other deep learning models reported in the scientific literature. Findings from this research can be valuable for real-time assessment of wave spectral parameters, which are necessary to support decision-making during the execution of MOs. [ABSTRACT FROM AUTHOR]

Forecasting solar power production accurately is critical for effectively planning and managing renewable energy systems. This paper introduces and investigates novel hybrid deep learning models for solar power forecasting using time series data. The research analyzes the efficacy of various models for capturing the complex patterns present in solar power data. In this study, all of the possible combinations of convolutional neural network (CNN), long short-term memory (LSTM), and transformer (TF) models are experimented. These hybrid models also compared with the single CNN, LSTM and TF models with respect to different kinds of optimizers. Three different evaluation metrics are also employed for performance analysis. Results show that the CNN–LSTM–TF hybrid model outperforms the other models, with a mean absolute error (MAE) of 0.551% when using the Nadam optimizer. However, the TF–LSTM model has relatively low performance, with an MAE of 16.17%, highlighting the difficulties in making reliable predictions of solar power. This result provides valuable insights for optimizing and planning renewable energy systems, highlighting the significance of selecting appropriate models and optimizers for accurate solar power forecasting. This is the first time such a comprehensive work presented that also involves transformer networks in hybrid models for solar power forecasting. [ABSTRACT FROM AUTHOR]

Visual and audio events simultaneously occur and both attract attention. However, most existing saliency prediction works ignore the influence of audio and only consider vision modality. In this paper, we propose a multi-task learning method for audio–visual saliency prediction and sound source localization on multi-face video by leveraging visual, audio and face information. Specifically, we first introduce a large-scale database of multi-face video in visual-audio condition, containing eye-tracking data and sound source annotations. Using this database, we find that sound influences human attention, and conversely attention offers a cue to determine sound source on multi-face video. Guided by these findings, an audio–visual multi-task network (AVM-Net) is introduced to predict saliency and locate sound source. AVM-Net consists of three branches corresponding to visual, audio and face modalities. The visual branch has a two-stream architecture to capture spatial and temporal information. Face and audio branches encode audio signals and faces, respectively. Finally, a spatio-temporal multi-modal graph is constructed to model the interaction among multiple faces. With joint optimization of these branches, the intrinsic correlation of the tasks of saliency prediction and sound source localization is utilized and their performance is boosted by each other. Experiments show that the proposed method outperforms 12 state-of-the-art saliency prediction methods, and achieves competitive results in sound source localization. [ABSTRACT FROM AUTHOR]

Day-ahead electricity price forecasting (DAEPF) holds critical significance for stakeholders in energy markets, particularly in areas with large amounts of renewable energy sources (RES) integration. In Japan, the proliferation of RES has led to instances wherein day-ahead electricity prices drop to nearly zero JPY/kWh during peak RES production periods, substantially affecting transactions between electricity retailers and consumers. This paper introduces an innovative DAEPF framework employing a Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) model designed to predict day-ahead electricity prices in the Kyushu area of Japan. To mitigate the inherent uncertainties associated with neural networks, a novel ensemble learning approach is implemented to bolster the DAEPF model's robustness and prediction accuracy. The CNN–LSTM model is verified to outperform a standalone LSTM model in both prediction accuracy and computation time. Additionally, applying a natural logarithm transformation to the target day-ahead electricity price as a pre-processing technique has proven necessary for higher prediction accuracy. A novel "policy-versus-policy" strategy is proposed to address the prediction problem of the zero prices, halving the computation time of the traditional two-stage method. The efficacy of incorporating a suite of multimodal features: areal day-ahead electricity price, day-ahead system electricity price, areal actual power generation, areal meteorological forecasts, calendar forecasts, alongside the rolling features of areal day-ahead electricity price, as explanatory variables to significantly enhance DAEPF accuracy has been validated. With the full integration of the proposed features, the CNN–LSTM ensemble model achieves its highest accuracy, reaching performance metrics of R 2 , MAE, and RMSE of 0.787, 1.936 JPY/kWh, and 2.630 JPY/kWh, respectively, during the test range from 1 March 2023 to 31 March 2023, underscoring the advantages of a comprehensive, multi-dimensional approach to DAEPF. [ABSTRACT FROM AUTHOR]

In this paper, we propose a global ionospheric total electron content (TEC) maps (GIM) prediction model based on deep learning methods that is both straightforward and practical, meeting the requirements of various applications. The proposed model utilizes an encoder-decoder structure with a Convolution Long Short-Term Memory (ConvLSTM) network and has a spatial resolution of 5° longitude and 2.5° latitude, with a time resolution of 1 h. We utilized the Center for Orbit Determination in Europe (CODE) GIM dataset for 18 years from 2002 to 2019, without requiring any other external input parameters, to train the ConvLSTM models for forecasting GIM 1, 2, and 3 days in advance. Using the CODE GIM data from 1 January 2020 to 31 December 2023 as the test dataset, the performance evaluation results show that the average root mean square errors (RMSE) for 1, 2 and 3 days of forecasts are 2.81 TECU, 3.16 TECU, and 3.41 TECU, respectively. These results show improved performance compared to the IRI-Plas model and CODE's 1-day forecast product c1pg, and comparable to CODE's 2-day forecast c2pg. The model's predictions get worse as the intensity of the storm increases, and the prediction error of the model increases with the lead time. [ABSTRACT FROM AUTHOR]

Monitoring battery health is critical for electric vehicle maintenance and safety. However, existing research has limited focus on predicting capacity degradation paths for entire battery packs, representing a gap between literature and application. This paper proposes a multi-horizon time series forecasting model (MMRNet, which consists of MOSUM, flash-MUSE attention, and RNN core modules) to predict the capacity degradation paths of battery packs. First, domain knowledge (DK) extracts the features from extensive battery aging datasets. The moving sum (MOSUM) and improved flash multi-scale attention (MUSE) methods are proposed to capture capacity curve mutations and multi-scale trends. Dynamic dropout training, transposition linear architecture, residual connections, and module stacking improve model generalization and accuracy. Experiments on battery pack and cell datasets demonstrate the superior performance of MMRNet over six baseline time series models. The proposed data-driven approach effectively predicts battery degradation trajectories, with implications for condition monitoring and the safety of electric vehicles. [ABSTRACT FROM AUTHOR]

Precisely forecasting the price of crude oil is challenging due to its fundamental properties of nonlinearity, volatility, and stochasticity. This paper introduces a novel hybrid model, namely, the KV-MFSCBA-G model, within the decomposition–integration paradigm. It combines the mixed-frequency convolutional neural network–bidirectional long short-term memory network-attention mechanism (MFCBA) and generalized autoregressive conditional heteroskedasticity (GARCH) models. The MFCBA and GARCH models are employed to respectively forecast the low-frequency and high-frequency components decomposed through variational mode decomposition optimized by Kullback–Leibler divergence (KL-VMD). The classification of these components is performed using the fuzzy entropy (FE) algorithm. Therefore, this model can fully exploit the advantages of deep learning networks in fitting nonlinearities and traditional econometric models in capturing volatilities. Furthermore, the intelligent optimization algorithm and the low-frequency economic variable are introduced to improve forecasting performance. Specifically, the sparrow search algorithm (SSA) is employed to determine the optimal parameter combination of the MFCBA model, which is incorporated with monthly global economic conditions (GECON) data. The empirical findings of West Texas Intermediate (WTI) and Brent crude oil indicate that the proposed approach outperforms other models in evaluation indicators and statistical tests and has good robustness. This model can assist investors and market regulators in making decisions. [ABSTRACT FROM AUTHOR]

Accurate and reliable prediction of Alzheimer's disease (AD) progression is crucial for effective interventions and treatment to delay its onset. Recently, deep learning models for AD progression achieve excellent predictive accuracy. However, their predictions lack reliability due to the non-calibration defects, that affects their recognition and acceptance. To address this issue, this paper proposes a temporal attention-aware evidential recurrent network for trustworthy prediction of AD progression. Specifically, evidential recurrent network explicitly models uncertainty of the output and converts it into a reliability measure for trustworthy AD progression prediction. Furthermore, considering that the actual scenario of AD progression prediction frequently relies on historical longitudinal data, we introduce temporal attention into evidential recurrent network, which improves predictive performance. We demonstrate the proposed model on the TADPOLE dataset. For predictive performance, the proposed model achieves mAUC of 0.943 and BCA of 0.881, which is comparable to the SOTA model MinimalRNN. More importantly, the proposed model provides reliability measures of the predicted results through uncertainty estimation and the ECE of the method on the TADPOLE dataset is 0.101, which is much lower than the SOTA model at 0.147, indicating that the proposed model can provide important decision-making support for risk-sensitive prediction of AD progression. [ABSTRACT FROM AUTHOR]

Assessing the strength of complex networks is crucial for evaluating their functionality and monitoring system security. Two primary perspectives for measuring network robustness are connectivity and controllability, which quantify how well a network maintains connectivity and controllability after experiencing complete attacks. However, conventional robustness calculation methods that use simulation attacks can be impractical for large-scale networks. Recent research has explored the use of deep learning methods for network robustness prediction, including PCR (short for predictor of controllability robustness), which uses a VGG (short for visual geometry group)-based convolutional neural network (CNN) and a linear filter. However, PCR has limitations, including inaccurate edge importance differentiation and fluctuating output curves. This paper presents ATTRP, an attention-based robustness predictor, which addresses these limitations. ATTRP uses a novel convolutional neural network with channel and spatial attention mechanisms to improve prediction accuracy and a robustness filter based on Savitzky–Golay smoothing to rectify the robustness curve. Experimental studies demonstrate that ATTRP outperforms other predictors, with much lower errors, while its computational speed is far superior to that of traditional attacking simulation. Overall, our research provides a more effective and efficient means of predicting network robustness, with potential applications in monitoring system security. [ABSTRACT FROM AUTHOR]

This paper presents a comprehensive study on fall recognition and forecasting for reconfigurable stair-accessing robots by leveraging deep learning techniques. The proposed framework integrates machine learning algorithms and recurrent neural networks (RNNs), specifically Long Short-Term Memory (LSTM) and Bidirectional LSTM (BiLSTM), for fall detection of service robots on staircases. The reconfigurable stair-accessing robot sTetro serves as the platform, and the fall data required for training models are generated in a simulation environment. The two machine learning algorithms are compared and their effectiveness on the fall recognition task is reported. The results indicate that the BiLSTM model effectively classifies falls with a median categorical accuracy of 94.10% in simulation and 90.02% with limited experiments. Additionally, the BiLSTM model can be used for forecasting, which is practically valuable for making decisions well before the onset of a free fall. This study contributes insights into the design and implementation of fall detection systems for service robots used to navigate staircases through deep learning approaches. Our experimental and simulation data, along with the simulation steps, are available for reference and analysis via the shared link. [ABSTRACT FROM AUTHOR]

The existing prediction methods have complex model application, high requirements for data parameters, and are limited to the prediction of a single observation point. To address this problem, this paper proposes a deep learning-based surface subsidence prediction method. Taking Hefei City of China as the research area, the time-series surface deformation results of this area are obtained by using SBAS-InSAR, and then the SFLA intelligent algorithm and Elman neural network model are combined to predict the surface deformation of key urban areas, and the prediction results are compared and analyzed.The experimental results show that the prediction model proposed in this paper can not only accurately predict a single deformation point, but also predict regional land subsidence, and can be used for auxiliary decision-making of urban spatial planning, early warning of geological hazards and hazard mitigation. [ABSTRACT FROM AUTHOR]

Predicting the mesoscale eddies in the ocean is crucial for advancing our understanding of the ocean and climate systems. Establishing spatio-temporal correlation among input data is a significant challenge in mesoscale eddy prediction tasks, especially for deep learning techniques. In this paper, we first present a deep learning solution based on a video prediction model to capture the spatio-temporal correlation and predict future sea surface height data accurately. To enhance the performance of the model, we introduced a novel metadata embedding module that utilizes neural networks to fuse remote sensing metadata with input data, resulting in increased accuracy. To the best of our knowledge, our model outperforms the state-of-the-art method for predicting sea level anomalies. Consequently, a mesoscale eddy detection algorithm will be applied to the predicted sea surface height data to generate mesoscale eddies in future. The proposed solution achieves competitive results, indicating that the prediction error for the eddy center position is 5.6 km for a 3-day prediction and 13.6 km for a 7-day prediction. [ABSTRACT FROM AUTHOR]

Accurate prediction of crude petroleum production in oil fields plays a crucial role in analyzing reservoir dynamics, formulating measures to increase production, and selecting ways to improve recovery factors. Current prediction methods mainly include reservoir engineering methods, numerical simulation methods, and deep learning methods, and the required prerequisite is a large amount of historical data. However, when the data used to train the model are insufficient, the prediction effect will be reduced dramatically. In this paper, a time series-related meta-learning (TsrML) method is proposed that can be applied to the prediction of petroleum time series containing small samples and can address the limitations of traditional deep learning methods for the few-shot problem, thereby supporting the development of production measures. The approach involves an architecture divided into meta-learner and base-learner, which learns initialization parameters from 89 time series datasets. It can be quickly adapted to achieve excellent and accurate predictions with small samples in the oil field. Three case studies were performed using time series from two actual oil fields. For objective evaluation, the proposed method is compared with several traditional methods. Compared to traditional deep learning methods, RMSE is decreased by 0.1766 on average, and MAPE is decreased by 4.8013 on average. The empirical results show that the proposed method outperforms the traditional deep learning methods. [ABSTRACT FROM AUTHOR]

Deep learning methodologies employed for biomass prediction often neglect the intricate relationships between labels and samples, resulting in suboptimal predictive performance. This paper introduces an advanced supervised contrastive learning technique, termed Improved Supervised Contrastive Deep Regression (SCDR), which is adept at effectively capturing the nuanced relationships between samples and labels in the feature space, thereby mitigating this limitation. Simultaneously, we propose the U-like Hierarchical Residual Fusion Network (BioUMixer), a bespoke biomass prediction network tailored for image data. BioUMixer enhances feature extraction from biomass image data, facilitating information exchange and fusion while considering both global and local features within the images. The efficacy of the proposed method is validated on the Pepper_Biomass dataset, which encompasses over 600 original images paired with corresponding biomass labels. The results demonstrate a noteworthy enhancement in deep regression tasks, as evidenced by performance metrics on the Pepper_Biomass dataset, including RMSE = 252.18, MAE = 201.98, and MAPE = 0.107. Additionally, assessment on the publicly accessible GrassClover dataset yields metrics of RMSE = 47.92, MAE = 31.74, and MAPE = 0.192. This study not only introduces a novel approach but also provides compelling empirical evidence supporting the digitization and precision improvement of agricultural technology. The research outcomes align closely with the identified problem and research statement, underscoring the significance of the proposed methodologies in advancing the field of biomass prediction through state-of-the-art deep learning techniques. [ABSTRACT FROM AUTHOR]

Pedestrian trajectory prediction plays a crucial role in autonomous driving, as its accuracy directly affects the autonomous driving system's comprehension of the environment and subsequent decision-making processes. Current trajectory prediction methods tend to oversimplify pedestrians to mere point coordinates, utilizing positional information to infer interactions among individuals while overlooking the temporal correlations between them, thereby excessively simplifying pedestrian characteristics. To address the aforementioned issues, this paper proposes a trajectory prediction model for autonomous driving applications, that takes into account both pedestrian motion characteristics and scene interaction. The model optimizes the LSTM unit structure twice, serving to learn correlations among long trajectories of pedestrians and to integrate multiple forms of information into the neighborhood interaction module. Furthermore, our model introduces dual attention mechanisms for individuals and scenes, focusing on the key motion points of individual pedestrians and their interactive behavior with others in busy scenarios. The efficacy of the model was validated on the MOT16 pedestrian dataset and the Daimler pedestrian path prediction dataset, outperforming mainstream methods with 8% and 10% reductions in Average Displacement Error and Final Displacement Error respectively. [ABSTRACT FROM AUTHOR]

The supply of electric power is vital for the daily lives of people, industrial production, and business services. At present, although enough electric power can be supplied to meet the power demand, there are still some challenges, especially in terms of long-distance power transmissions and long-term power storage. Consequently, if the power production capacity exceeds the immediate consumption requirements, i.e., the produced electric power cannot be consumed in a short period, and much electric power could be wasted. Evidently, to minimize the wastage of electric power, it is necessary to properly plan power production by accurately forecasting the future power load. Therefore, a preferable power load forecasting algorithm is crucial for the planning of power production. This paper proposes a novel deep learning model for the purpose of power load forecasting, termed the SSA-CNN-LSTM-ATT model, which combines the CNN-LSTM model with SSA optimization and attention mechanisms. In this model, the CNN module extracts the features from the sequential data, and then the features are passed to the LSTM module for modeling and capturing the long-term dependencies hidden in the sequences. Subsequently, an attention layer is employed to measure the importance of different features. Finally, the output is obtained through a fully connected layer, yielding the forecasting results of the power load. Extensive experiments have been conducted on a real-world dataset, and the metric R2 can reach 0.998, indicating that our proposed model can accurately forecast the power load. [ABSTRACT FROM AUTHOR]

Renewable energies have become pivotal in the global energy landscape. Their adoption is crucial for phasing out fossil fuels and promoting environmentally friendly energy solutions. In recent years, the energy management system (EMS) concept has emerged to manage the power grid. EMS optimizes electric grid operations through advanced metering, automation, and communication technologies. A critical component of EMS is power forecasting, which facilitates precise energy grid scheduling. This research paper introduces a deep learning hybrid model employing convolutional neural network–long short-term memory (CNN-LSTM) for short-term photovoltaic (PV) solar energy forecasting. The proposed method integrates the variational mode decomposition (VMD) algorithm with the CNN-LSTM model to predict PV power output from a solar farm in Boussada, Algeria, spanning 1 January 2019, to 31 December 2020. The performance of the developed model is benchmarked against other deep learning models across various time horizons (15, 30, and 60 min): variational mode decomposition–convolutional neural network (VMD-CNN), variational mode decomposition–long short-term memory (VMD-LSTM), and convolutional neural network–long short-term memory (CNN-LSTM), which provide a comprehensive evaluation. Our findings demonstrate that the developed model outperforms other methods, offering promising results in solar power forecasting. This research contributes to the primary goal of enhancing EMS by providing accurate solar energy forecasts. [ABSTRACT FROM AUTHOR]

For decades, soft sensors have been extensively renowned for their efficiency in real-time tracking of expensive variables for advanced process control. However, despite the diverse efforts lavished on enhancing their models, the issue of label sparsity when modeling the soft sensors has always posed challenges across various processes. In this paper, a fledgling technique, called co-training, is studied for leveraging only a small ratio of labeled data, to hone and formulate a more advantageous framework in soft sensor modeling. Dissimilar to the conventional routine where only two players are employed, we investigate the efficient number of players in batch processes, making a multiple-player learning scheme to assuage the sparsity issue. Meanwhile, a sliding window spanning across both time and batch direction is used to aggregate the samples for prediction, and account for the unique 2D correlations among the general batch process data. Altogether, the forged framework can outperform the other prevalent methods, especially when the ratio of unlabeled data is climbing up, and two case studies are showcased to demonstrate its effectiveness. [ABSTRACT FROM AUTHOR]

This paper proposes a method for forecasting surface solar irradiance (SSI), the most critical factor in solar photovoltaic (PV) power generation. The proposed method uses 16-channel data obtained by the GEO-KOMPSAT-2A (GK2A) satellite of South Korea as the main data for SSI forecasting. To determine feature variables related to SSI from the 16-channel data, the differences and ratios between the channels were utilized. Additionally, to consider the fundamental characteristics of SSI originating from the sun, solar geometry parameters, such as solar declination (SD), solar elevation angle (SEA), and extraterrestrial solar radiation (ESR), were used. Deep learning-based feature selection (Deep-FS) was employed to select appropriate feature variables that affect SSI from various feature variables extracted from the 16-channel data. Lastly, spatio-temporal deep learning models, such as convolutional neural network–long short-term memory (CNN-LSTM) and CNN–gated recurrent unit (CNN-GRU), which can simultaneously reflect temporal and spatial characteristics, were used to forecast SSI. Experiments conducted to verify the proposed method against conventional methods confirmed that the proposed method delivers superior SSI forecasting performance. [ABSTRACT FROM AUTHOR]

This paper introduces an innovative framework for wind power prediction that focuses on the future of energy forecasting utilizing intelligent deep learning and strategic feature engineering. This research investigates the application of a state-of-the-art deep learning model for wind energy prediction to make extremely short-term forecasts using real-time data on wind generation from New South Wales, Australia. In contrast with typical approaches to wind energy forecasting, this model relies entirely on historical data and strategic feature engineering to make predictions, rather than relying on meteorological parameters. A hybrid feature engineering strategy that integrates features from several feature generation techniques to obtain the optimal input parameters is a significant contribution to this work. The model's performance is assessed using key metrics, yielding optimal results with a Mean Absolute Error (MAE) of 8.76, Mean Squared Error (MSE) of 139.49, Root Mean Squared Error (RMSE) of 11.81, R-squared score of 0.997, and Mean Absolute Percentage Error (MAPE) of 4.85%. Additionally, the proposed framework outperforms six other deep learning and hybrid deep learning models in terms of wind energy prediction accuracy. These findings highlight the importance of advanced data analysis for feature generation in data processing, pointing to its key role in boosting the precision of forecasting applications. [ABSTRACT FROM AUTHOR]

Nonlinear dynamical systems with control parameters may not be well modeled by shallow neural networks. In this paper, the stable fixed-point solutions, periodic and chaotic solutions of the parameter-dependent Lorenz system are learned simultaneously via a very deep neural network. The proposed deep learning model consists of a large number of identical linear layers, which provide excellent nonlinear mapping capability. Residual connections are applied to ease the flow of information and a large training dataset is further utilized. Extensive numerical results show that the chaotic solutions can be accurately forecasted for several Lyapunov times and long-term predictions are achieved for periodic solutions. Additionally, the dynamical characteristics such as bifurcation diagrams and largest Lyapunov exponents can be well recovered from the learned solutions. Finally, the principal factors contributing to the high prediction accuracy are discussed. [ABSTRACT FROM AUTHOR]

Spectrum prediction is a promising technique to release spectrum resources and plays an essential role in cognitive radio networks and spectrum situation generating. Traditional algorithms normally focus on one-dimensional or predict spectrum values in a slot-by-slot manner and thus cannot fully perceive the spectrum states in complex environments and lack timeliness. In this paper, a deep learning-based prediction method with a simple structure is developed for temporal–spectral and multi-slot spectrum prediction simultaneously. Specifically, we first analyze and construct spectrum data suitable for the model to simultaneously achieve long-term and multi-dimensional spectrum prediction. Then, a hierarchical spectrum prediction system is developed that takes advantage of the advanced Bi-ConvLSTM and the seq2seq framework. The Bi-ConvLSTM captures time–frequency characteristics of spectrum data, and the seq2seq framework is used for long-term spectrum prediction. Furthermore, the attention mechanism is used to address the limitations of the seq2seq framework that compresses all inputs into fixed-length vectors, resulting in information loss. Finally, the experimental results have shown that the proposed model has a significant advantage over the benchmark schemes. Especially, the proposed spectrum prediction model achieves 6.15%, 0.7749, 1.0978, and 0.9628 in MAPE, MAE, RMSE, and R 2 , respectively, which is better than all the baseline deep learning models. [ABSTRACT FROM AUTHOR]

With recent developments in cloud computing, massive unplanned traffic loads are submitted to cloud platforms. High traffic load variations lead to uncertainty in resource utilization. Therefore, efficient data-driven mechanisms for automatic resource management become crucial. These mechanisms enable complex and distributed systems to anticipate and efficiently react to workload fluctuations. They rely on accurate resource utilization prediction techniques to satisfy the resource needs, in order to fulfill the service level objective for cloud applications and infrastructures. In this paper, we propose a deep learning model to predict the resource consumption (e.g., CPU, memory) in network function virtualization infrastructures. We model an augmented graphical neural network (GNN) that exploit neighbouring relationships between virtual network functions (VNF) composing various service function chains (SFC), and use an augmented feature vector allowing to capture the consumption evolution of a VNF. The model enables to predict the resource needs of VNFs by identifying the multidimensional dependencies according to the graph structure of an SFC. The proposed GNN model has been compared with MLP, LSTM, hybrid LSTM and CNN models to evaluate its accuracy and efficiency. Real word datasets have been used to evaluate the proposed model using five performance metrics. The performance analysis reveals that our graph-features based GNN model outperforms the other models for SFCs with high traffic load variation. [ABSTRACT FROM AUTHOR]

The household load has high volatility and uncertainty, which plays an increasingly important role in short-term power load forecasting for individual residential customers in the operation and planning of future power grids. There is still room for improvement in the prediction accuracy of traditional machine learning and deep learning models. This paper firstly analyzes the complexity of household load data and formulates forecasting problems. Then, the principle of stochastic configuration network (SCN), stacking algorithm and a stacking integrated stochastic configuration network (Stacking-SCN) is introduced, which constructs a short-term household load forecasting model. By adaptively constraining the output weight distribution of the network model, the prediction accuracy can be improved. To show the prediction performance of the algorithm, the experiment comparing the Stacking-SCN model with incremental random vector functional link network (IRVFLN) models, the traditional SCN, ensemble-SCN (E-SCN), deep neural networks (DNN) and long short-term memory (LSTM), and verify it with RMSE, MAE and APE performance metrics. Experimental results show that Stacking-SCN can more effectively express the time series relationship of household short-term load, has higher prediction accuracy, effectively prevents network over-fitting problems, and improves the accuracy of prediction capabilities. [ABSTRACT FROM AUTHOR]

Accurately predicting drug-target binding affinity (DTA) is crucial for advancements in drug repositioning. In this paper, we present HBDTA, an innovative predictive methodology that harnesses the capabilities of graph deep learning and multi-layer networks for DTA prediction. The HBDTA approach encompasses a comprehensive framework with three distinct graph neural network (GNN) algorithms: multi-head graph attention networks (Multi-head GAT), generalized aggregation networks (GENConv), and graph convolutional networks (GCNConv) designed to extract drug features. Additionally, we employ a multi-layer bi-directional long short-term memory (MBLSTM) with residual blocks to extract protein features. After deriving feature vectors for drugs and proteins, they independently pass through fully connected layers before integration into a self-attention layer. Subsequently, the resulting feature vectors are concatenated and passed through four layers of fully secured networks to facilitate prediction. Finally, we assess our model's performance on the Davis, KIBA, Metz, and DTC datasets. Comparative analysis against state-of-the-art methodologies, such as DeepGLSTM, DeepNC, and GraphDTA, among others, underscores the effectiveness of HBDTA. The results suggest that HBDTA holds significant potential for practical drug discovery and personalized medicine applications. [ABSTRACT FROM AUTHOR]

The open-source software platform hosts a large number of software defects, and the task of relying on administrators to manually assign developers is often time consuming. Thus, it is crucial to determine how to assign software defects to appropriate developers. This paper presents DARIP, a method for assigning developers to address software defects. First, the correlation between software defects and issues is considered, predicting related issues for each defect and comprehensively calculating the textual characteristics of the defect using the BERT model. Second, a heterogeneous collaborative network is constructed based on the three development behaviors of developers: reporting, commenting, and fixing. The meta-paths are defined based on the four collaborative relationships between developers: report–comment, report–fix, comment–comment, and comment–fix. The graph-embedding algorithm metapath2vec extracts developer characteristics from the heterogeneous collaborative network. Then, a classifier based on a deep learning model calculates the probability assigned to each developer category. Finally, the assignment list is obtained according to the probability ranking. Experiments on a dataset of 20,280 defects from 9 popular projects show that the DARIP method improves the average of the Recall@5, the Recall@10, and the MRR by 31.13%, 21.40%, and 25.45%, respectively, compared to the state-of-the-art method. [ABSTRACT FROM AUTHOR]

A large proportion of photovoltaic (PV) power generation is connected to the power grid, and its volatility and stochasticity have significant impacts on the power system. Accurate PV power forecasting is of great significance in optimizing the safe operation of the power grid and power market transactions. In this paper, a novel dual-channel PV power forecasting method based on a temporal convolutional network (TCN) is proposed. The method deeply integrates the PV station feature data with the model computing mechanism through the dual-channel model architecture; utilizes the combination of multihead attention (MHA) and TCN to extract the multidimensional spatio-temporal features between other meteorological variables and the PV power; and utilizes a single TCN to fully extract the temporal constraints of the power sequence elements. The weighted fusion of the dual-channel feature data ultimately yields the ideal forecasting results. The experimental data in this study are from a 26.52 kW PV power plant in central Australia. The experiments were carried out over seven different input window widths, and the two models that currently show superior performance within the field of PV power forecasting: the convolutional neural network (CNN), and the convolutional neural network combined with a long and short-term memory network (CNN_LSTM), are used as the baseline models. The experimental results show that the proposed model and the baseline models both obtained the best forecasting performance over a 1-day input window width, while the proposed model exhibited superior forecasting performance compared to the baseline model. It also shows that designing model architectures that deeply integrate the data input method with the model mechanism has research potential in the field of PV power forecasting. [ABSTRACT FROM AUTHOR]

Photovoltaic (PV) power generation forecasting is an important research topic, aiming to mitigate variability caused by weather conditions and improve power generation planning. Climate factors, including solar irradiance, temperature, and cloud cover, influence the energy conversion achieved by PV systems. Long-term weather forecasting improves PV power generation planning, while short-term forecasting enhances control methods, such as managing ramp rates. The stochastic nature of weather variables poses a challenge for linear regression methods. Consequently, advanced, state-of-the-art machine learning (ML) approaches capable of handling non-linear data, such as long short-term memory (LSTM), have emerged. This paper introduces the implementation of a multivariate machine learning model to forecast PV power generation, considering multiple weather variables. A deep learning solution was implemented to analyze weather variables in a short time horizon. Utilizing a hidden Markov model for data preprocessing, an LSTM model was trained using the Alice Spring dataset provided by DKA Solar Center. The proposed workflow demonstrated superior performance compared to the results obtained by state-of-the-art methods, including support vector machine, radiation classification coordinate with LSTM (RCC-LSTM), and ESNCNN specifically concerning the proposed multi-input single-output LSTM model. This improvement is attributed to incorporating input features such as active power, temperature, humidity, horizontal and diffuse irradiance, and wind direction, with active power serving as the output variable. The proposed workflow achieved a mean square error (MSE) of 2.17 × 10 − 7 , a root mean square error (RMSE) of 4.65 × 10 − 4 , and a mean absolute error (MAE) of 4.04 × 10 − 4 . [ABSTRACT FROM AUTHOR]

The transient responses of distributed energy resources (DERs) in a microgrid are dynamically correlated in spatial and temporal dimensions. Hence, the transient stability prediction in microgrids would require an effective modeling of time-varying correlations and the mining of spatial–temporal features of electrical data. This paper proposes a refined DER-level transient stability prediction method for microgrids considering the time-varying spatial–temporal correlations of DERs. First, the spatial–temporal dynamic correlation of DERs was extracted and modeled by an attention-based mechanism. Then, a spatial–temporal graph convolution network was proposed to predict the dynamics of unstable DERs and the instability severity trend in a microgrid. The TSP model consisted of three parts: (1) several stacked spatial–temporal convolution modules to simultaneously mine the spatial–temporal dynamic features of microgrids, (2) an unstable DER identification module to predict the microgrid system stability and identify unstable DERs, and (3) an instability severity trend prediction module for DERs in a microgrid. The test results on a realistic 16-bus 10-DER microgrid demonstrated that the proposed prediction method possessed the desirable reliability and interpretability and outperformed the state-of-the-art baselines in unstable DER identifications and DER instability severity trend predictions. [ABSTRACT FROM AUTHOR]

Photovoltaic (PV) power prediction plays a critical role amid the accelerating adoption of renewable energy sources. This paper introduces a bidirectional long short-term memory (BiLSTM) deep learning (DL) model designed for forecasting photovoltaic power one hour ahead. The dataset under examination originates from a small PV installation located at the Polytechnic School of the University of Alcala. To improve the quality of historical data and optimize model performance, a robust data preprocessing algorithm is implemented. The BiLSTM model is synergistically combined with a Bayesian optimization algorithm (BOA) to fine-tune its primary hyperparameters, thereby enhancing its predictive efficacy. The performance of the proposed model is evaluated across diverse meteorological and seasonal conditions. In deterministic forecasting, the findings indicate its superiority over alternative models employed in this research domain, specifically a multilayer perceptron (MLP) neural network model and a random forest (RF) ensemble model. Compared with the MLP and RF reference models, the proposed model achieves reductions in the normalized mean absolute error (nMAE) of 75.03% and 77.01%, respectively, demonstrating its effectiveness in this type of prediction. Moreover, interval prediction utilizing the bootstrap resampling method is conducted, with the acquired prediction intervals carefully adjusted to meet the desired confidence levels, thereby enhancing the robustness and flexibility of the predictions. [ABSTRACT FROM AUTHOR]

The long-term prediction of the solar cycle is of great significance for aerospace, communication, and space missions. For a long time, many studies have used relatively primitive deep learning methods to predict the solar cycle, and most of them do not perform well in the long-term prediction. In this paper, we proposed XG-SN ensemble model. The model used extreme gradient boosting (XGBoost) ensemble learning method, combined with sample convolution and interaction net (SCINet), and neural basis expansion analysis for the interpretable time series (N-BEATS) to make predictions for known solar cycles. 13 months of smoothed monthly total sunspot numbers were selected as the data set. The model performance was evaluated by mean absolute error (MAE), root-mean-square error (RMSE), and mean absolute time lag (MATL) between the predicted and actual values. The first two evaluation metrics measured the prediction deviation from the numerical dimension, and the last one measured the prediction deviation from the temporal dimension. The results show that the model achieves the MAE, RMSE, and MATL values of 13.19, 17.13, and 0.08, respectively, in Solar Cycle 13 to 24. Our model is able to better predict in most cycles, ensuring accurate prediction of peaks with little time lag. [ABSTRACT FROM AUTHOR]

Background: The Drug–Target Interaction (DTI) prediction uses a drug molecule and a protein sequence as inputs to predict the binding affinity value. In recent years, deep learning-based models have gotten more attention. These methods have two modules: the feature extraction module and the task prediction module. In most deep learning-based approaches, a simple task prediction loss (i.e., categorical cross entropy for the classification task and mean squared error for the regression task) is used to learn the model. In machine learning, contrastive-based loss functions are developed to learn more discriminative feature space. In a deep learning-based model, extracting more discriminative feature space leads to performance improvement for the task prediction module. Results: In this paper, we have used multimodal knowledge as input and proposed an attention-based fusion technique to combine this knowledge. Also, we investigate how utilizing contrastive loss function along the task prediction loss could help the approach to learn a more powerful model. Four contrastive loss functions are considered: (1) max-margin contrastive loss function, (2) triplet loss function, (3) Multi-class N-pair Loss Objective, and (4) NT-Xent loss function. The proposed model is evaluated using four well-known datasets: Wang et al. dataset, Luo's dataset, Davis, and KIBA datasets. Conclusions: Accordingly, after reviewing the state-of-the-art methods, we developed a multimodal feature extraction network by combining protein sequences and drug molecules, along with protein–protein interaction networks and drug–drug interaction networks. The results show it performs significantly better than the comparable state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

High-precision spatial-temporal wind power prediction technology is of great significance for ensuring the safe and stable operation of power grids. The development of artificial intelligence technology provides a new scheme for modeling with strong spatial-temporal correlation. In addition, the existing prediction models are mostly 'black box' models, lacking interpretability, which may lead to a lack of trust in the model by power grid dispatchers. Therefore, improving the model to obtain interpretability has become an important challenge. In this paper, an interpretable short-term wind power prediction model based on ensemble deep graph neural network is designed. Firstly, the graph network model (GNN) with an attention mechanism is applied to the aggregate and the spatial-temporal features of wind power data are extracted, and the interpretable ability is obtained. Then, the long short-term memory (LSTM) method is used to process the extracted features and establish a wind power prediction model. Finally, the random sampling algorithm is used to optimize the hyperparameters to improve the learning rate and performance of the model. Through multiple comparative experiments and a case analysis, the results show that the proposed model has a higher prediction accuracy than other traditional models and obtains reasonable interpretability in time and space dimensions. [ABSTRACT FROM AUTHOR]

Extracting more information from feature interactions is essential to improve click-through rate (CTR) prediction accuracy. Although deep learning technology can help capture high-order feature interactions, the combination of features lacks interpretability. In this paper, we propose a multi-semantic feature interaction learning network (MeFiNet), which utilizes convolution operations to map feature interactions to multi-semantic spaces to improve their expressive ability and uses an improved Squeeze & Excitation method based on SENet to learn the importance of these interactions in different semantic spaces. The Squeeze operation helps to obtain the global importance distribution of semantic spaces, and the Excitation operation helps to dynamically re-assign the weights of semantic features so that both semantic diversity and feature diversity are considered in the model. The generated multi-semantic feature interactions are concatenated with the original feature embeddings and input into a deep learning network. Experiments on three public datasets demonstrate the effectiveness of the proposed model. Compared with state-of-the-art methods, the model achieves excellent performance (+ 0.18% in AUC and - 0.34% in LogLoss VS DeepFM; + 0.19% in AUC and - 0.33% in LogLoss VS FiBiNet). [ABSTRACT FROM AUTHOR]

In response to the need for multiple complete bearing degradation datasets in traditional deep learning networks to predict the impact on individual bearings, a novel deep learning-based rolling bearing remaining life prediction method is proposed in the absence of fully degraded bearng data. This method involves processing the raw vibration data through Channel-wise Attention Encoder (CAE) from the Encoder-Channel Attention (ECA), extracting features related to mutual correlation and relevance, selecting the desired characteristics, and incorporating the selected features into the constructed Autoformer-based time prediction model to forecast the degradation trend of bearings' remaining time. The feature extraction method proposed in this approach outperforms CAE and multilayer perceptual-Attention Encoder in terms of feature extraction capabilities, resulting in reductions of 0.0059 and 0.0402 in mean square error, respectively. Additionally, the indirect prediction approach for the degradation trend of the target bearing demonstrates higher accuracy compared to Informer and Transformer models, with mean square error reductions of 0.3352 and 0.1174, respectively. This suggests that the combined deep learning model proposed in this paper for predicting rolling bearing life may be a more effective life prediction method deserving further research and application. [ABSTRACT FROM AUTHOR]

The significance of precise gold price forecasting is accentuated by its financial attributes, mirroring global economic conditions, market uncertainties, and investor risk aversion. However, predicting the gold price is challenging due to its inherent volatility, influenced by multiple factors, such as COVID-19, financial crises, geopolitical issues, and fluctuations in other metals and energy prices. These complexities often lead to non-stationary time series, rendering traditional time series modeling methods inadequate. Our paper presents a multi-objective optimization algorithm that refines the interval prediction framework with quantile regression deep learning in response to this issue. This framework comprehensively responds to gold's financial market dynamics and uncertainties with a screening process of various factors, including pandemic-related indices, geopolitical indices, the US dollar index, and prices of various commodities. The quantile regression deep-learning models optimized by multi-objective optimization algorithms deliver robust, interpretable, and highly accurate predictions for handling non-linear relationships and complex data structures and enhance the overall predictive performance. The results demonstrate that the QRBiLSTM model, optimized using the MOALO algorithm, delivers excellent forecasting performance. The composite indicator AIS reaches −15.6240 and −11.5581 at 90% and 95% confidence levels, respectively. This underscores the model's high forecasting accuracy and its potential to provide valuable insights for assessing future trends in gold prices. The deterministic and probabilistic forecasting framework for gold prices captures the market dynamics with the new pandemic index and comprehensively sets a new benchmark for predictive modeling in volatile market commodities like gold. [ABSTRACT FROM AUTHOR]