Search

An editorial is presented on exploring the tendency and development of intelligent-optimization-based hybrid methodologies. Topics include precise resources and energy forecasting being important for facilitating the decision-making process in order to achieve higher efficiency and reliability in energy system planning; and providing effective indoor tracking for the movement of people.

Deep Neural Networks (DNN's) present some of the leading applications of Artificial Intelligence (AI) which have proven suitability on various machine-learning use cases. Forecasting demand of intermittent on-line sales is a task which needs to be carried out automatically for a large number of Stock Keeping Units (SKU's). This paper discusses the intermittent online sales and proposes an AI-based model for forecasting demand. We provide empirical evidence by utilizing data from 17 different sellers with approximately 3000 orders in total. Our findings indicate that thanks to their multi-layered learning structure, the DNN's can provide up to 35% better accuracy than the classic models such as Moving Average, Exponential Smoothing, Croston's method and ARIMA. Also, it was revealed that the time between orders' arrivals follow Exponential distribution and the order sizes also generally follow Exponential distribution. Thus, most of the time, Poisson Exponential distribution can be used for modelling intermittent sales process through online platforms. The analyses show that Poisson Exponential distribution can generate values close to real sales with less than 7% error margin with real data. [ABSTRACT FROM AUTHOR]

The accurate prediction of sea surface temperature (SST) is the basis for our understanding of local and global climate characteristics. At present, the existing sea temperature prediction methods fail to take full advantage of the potential spatial dependence between variables. Among them, graph neural networks (GNNs) modeled on the relationships between variables can better deal with space–time dependency issues. However, most of the current graph neural networks are applied to data that already have a good graph structure, while in SST data, the dependency relationship between spatial points needs to be excavated rather than existing as prior knowledge. In order to predict SST more accurately and break through the bottleneck of existing SST prediction methods, we urgently need to develop an adaptive SST prediction method that is independent of predefined graph structures and can take full advantage of the real temporal and spatial correlations hidden indata sets. Therefore, this paper presents a graph neural network model designed specifically for space–time sequence prediction that can automatically learn the relationships between variables and model them. The model automatically extracts the dependencies between sea temperature multi-variates by embedding the nodes of the adaptive graph learning module, so that the fine-grained spatial correlations hidden in the sequence data can be accurately captured. Figure learning modules, graph convolution modules, and time convolution modules are integrated into a unified end-to-end framework for learning. Experiments were carried out on the Bohai Sea surface temperature data set and the South China Sea surface temperature data set, and the results show that the model presented in this paper is significantly better than other sea temperature model predictions in two remote-sensing sea temperature data sets and the surface temperature of the South China Sea is easier to predict than the surface temperature of the Bohai Sea. [ABSTRACT FROM AUTHOR]

To enhance the safety of grid operations, this paper proposes a high-precision short-term photovoltaic (PV) power forecasting method that integrates information from surrounding PV stations and deep learning prediction models. The proposed method utilizes numerical weather prediction (NWP) data of the target PV station and highly correlated features from nearby stations as inputs. This study first analyzes the correlation between irradiance and power sequences and calculates a comprehensive similarity index based on distance factors. Stations with high-similarity indices are selected as data sources. Subsequently, Bayesian optimization is employed to determine the optimal data fusion ratio. The selected data are then used to model power predictions through the convolutional long short-term memory with attention (Conv-LSTM-ATT) deep neural network. Experimental results show that the proposed model significantly outperforms three classical models in terms of forecasting accuracy. The data fusion strategy determined by Bayesian optimization reduces the root mean square error (RMSE) of the test set by 20.04%, 28.24%, and 30.94% under sunny, cloudy, and rainy conditions, respectively. [ABSTRACT FROM AUTHOR]

Diabetes is caused by insulin deficiency or impaired biological action, and long-term hyperglycemia leads to a variety of tissue damage and dysfunction. Therefore, the early prediction of diabetes and timely intervention and treatment are crucial. This paper proposes a robust framework for the prediction and diagnosis of type 2 diabetes (T2DM) to aid in diabetes applications in clinical diagnosis. The data-preprocessing stage includes steps such as outlier removal, missing value filling, data standardization, and assigning class weights to ensure the quality and consistency of the data, thereby improving the performance and stability of the model. This experiment used the National Health and Nutrition Examination Survey (NHANES) dataset and the publicly available PIMA Indian dataset (PID). For T2DM classification, we designed a convolutional neural network (CNN) and proposed a novel attention-oriented convolutional neural network (SECNN) through the channel attention mechanism. To optimize the hyperparameters of the model, we used grid search and K-fold cross-validation methods. In addition, we also comparatively analyzed various machine learning (ML) models such as support vector machine (SVM), logistic regression (LR), decision tree (DT), random forest (RF), and artificial neural network (ANN). Finally, we evaluated the performance of the model using performance evaluation metrics such as precision, recall, F1-Score, accuracy, and AUC. Experimental results show that the SECNN model has an accuracy of 94.12% on the NHANES dataset and an accuracy of 89.47% on the PIMA Indian dataset. SECNN models and CNN models show significant improvements in diabetes prediction performance compared to traditional ML models. The comparative analysis of the SECNN model and the CNN model has significantly improved performance, further verifying the advantages of introducing the channel attention mechanism. The robust diabetes prediction framework proposed in this article establishes an effective foundation for diabetes diagnosis and prediction, and has a positive impact on the development of health management and medical industries. [ABSTRACT FROM AUTHOR]

The Special Issue is completed with two review articles: the first one [[12]] presents a classification of STLF state-of-the-art methods based on four categories, and the second one [[13]] compares criteria used to tune and assess STLF methods with estimated costs caused by the forecasting errors. The 11 research papers published in the Special Issue and in the book attempt to solve some of the STLF limitations, mainly by proposing new methods that improve the forecasting results with respect to those published in previous works. Consequently, STLF methods aimed at DR actions should explore new explanatory variables such as the electricity price forecasts for the next hours or DR event signals triggered by operators. As a result, adapting successful forecasting methods from those fields, the proposal of new ANN architectures and the development of new approaches (beyond current hybrid models) will be crucial to achieving significant progress in STLF. [Extracted from the article]

With the vast popularity of the deep learning models in the engineering and mathematical fields, Artificial Neural Networks (ANN) have recently attracted significant research applications in agriculture, economics, informatics and finance. In this paper, we use a deep learning method to capture and predict the unknown complex nonlinear characteristics of agricultural output based on autoregressive artificial neural network, using Nigeria as a case study. Using the proposed model, shocks in agricultural output is analyzed and modeled using data obtained for a period of forty years (1980-2019), and compared with analyses obtained from the autoregressive integrated moving average model (ARIMA). This result is significant because it justifies the superiority of the hybrid ANN model over the traditional Box-Jenkins methodology for forecasting non-stationary time series. The empirical results show that the proposed autoregressive ANN model achieves an improved forecasting accuracy over the traditional Box-Jenkins ARIMA method. It is further proposed that various types of artificial neural networks would be useful in forecasting and solving relevant tasks and problems widely defined in global agricultural production. [ABSTRACT FROM AUTHOR]

With the increasing proportion of solar energy in the energy system, accurate solar irradiance forecast is of great significance for low-cost energy scheduling. This paper proposes a new forecasting idea for day-ahead solar irradiance forecast on the day-ahead scale: Firstly, based on formula derivation and big data correlation analysis, this paper finds out multiple parameters related to GHI, and jointly uses these parameters to forecast GHI. Error revision during morning period (ERDMP) is innovatively proposed on this basis, towards a more accurate daytime forecast. In order to prove the reliability and universality of the method, relevant data from five different-climatic regions are respectively used in the experiment. The multi-variable historical data-based day-ahead solar irradiance forecast uses deep neural networks, including Recurrent Neural Network (RNN), Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) network. ERDMP uses a linear AutoRegressive (AR) model to predict the daytime error coefficients based on the morning error coefficients. According to the results, through the proposed ERDMP, Mean Absolute Error (MAE) decreases by about 25% to 30%, Root Mean Squared Error (RMSE) decreases by about 20%, and R2 increases by about 5% to 10% when compared with the initial error of multi-parameter prediction models and other advanced models. [ABSTRACT FROM AUTHOR]

Short-term load forecasting is the guarantee for the safe, stable, and economical operation of power systems. Deep learning methods have been proven effective in obtaining accurate forecasting results. However, in recent years, the large-scale integration of distributed photovoltaic systems (DPVS) has caused changes in load curve fluctuations. Current deep learning models generally train with historical load series and load-related meteorological data series as input features, which limits the model's ability to recognize the load fluctuations caused by DPVS. In order to further improve the accuracy of load forecasting models, this paper proposes an input feature reconstruction method based on the maximum information coefficient (MIC). Firstly, the load curves with DPVS are classified by Gaussian mixture model (GMM) clustering. Then, considering the coupling relationship between the load and input features at different times, the load data and input features are reordered. Finally, the MIC between different features and loads at different times is calculated to select the relevant features at those different times and construct new input features. The case analysis shows that the feature reconstruction strategy proposed in this paper effectively improves the prediction performance of deep neural networks. [ABSTRACT FROM AUTHOR]

To aid cocrystal screening, a deep forest-based cocrystal prediction model was developed in this study using data from the Cambridge Structural Database (CSD). The positive samples in the experiment came from the CSD. The negative samples were partly from the failure records in other papers, and some were randomly generated according to specific rules, resulting in a total of 8576 pairs. Compared with the models of traditional machine learning methods and simple deep neural networks models, the deep forest model has better performance and faster training speed. The accuracy is about 95% on the test set. Febuxostat cocrystal screening was also tested to verify the validity of the model. Our model correctly predicted the formation of cocrystal. It shows that our model is practically useful in practice. [ABSTRACT FROM AUTHOR]

Introduction: The characteristics of intermittency and volatility brought by a high proportion of renewable energy impose higher requirements on load forecasting in modern power system. Currently, load forecasting methods mainly include statistical models and machine learning methods, but they exhibit relative rigidity in handling the uncertainty, volatility, and nonlinear relationships of new energy, making it difficult to adapt to instantaneous load changes and the complex impact of meteorological factors. The Transformer model, as an algorithm used in natural language processing, with its self-attention mechanism and powerful nonlinear modeling capability, can help address the aforementioned issues. Methods: However, its current performance in time series processing is suboptimal. Therefore, this paper improves the Transformer model through two steps, namely, Data-Slicing and Channel-independence, enhancing its adaptability in load forecasting. Results: By using load data from Northern Ireland as an example, we compared GRU, CNN, and traditional Transformer models. We validated the effectiveness of this algorithm in short-term load forecasting using MAPE and MSE as indicators. Discussion: The results indicate that, in short-term load forecasting, the MDS method, compared to GRU, CNN, and traditional Transformer methods, has generally reduced the MSE by over 48%, and achieved a reduction of over 47.6% in MAPE, demonstrating excellent performance. [ABSTRACT FROM AUTHOR]

The accuracy of short-term traffic flow prediction is one of the important issues in the construction of smart cities, and it is an effective way to solve the problem of traffic congestion. Most previous studies could not effectively mine the potential relationship between the temporal and spatial dimensions of traffic data flow. Due to the large variability in the traffic flow data of road conditions, we analyzed it with "dynamic", using a dynamic-aware graph neural network model for the hidden relationships between space-time in the deep learning segment. In this paper, we propose a dynamic perceptual graph neural network model for the temporal and spatial hidden relationships of deep learning segments. This model mixes temporal features and spatial features with graphs and expresses them. The temporal features and spatial features are connected to each other to learn potential relationships, so as to more accurately predict the traffic speed in the future time period, we performed experiments on real data sets and compared with some baseline models. The experiments show that the method proposed in this paper has certain advantages. [ABSTRACT FROM AUTHOR]

Short-term load forecasting (STLF) is critical for the energy industry. Accurate predictions of future electricity demand are necessary to ensure power systems' reliable and efficient operation. Various STLF models have been proposed in recent years, each with strengths and weaknesses. This paper comprehensively reviews some STLF models, including time series, artificial neural networks (ANNs), regression-based, and hybrid models. It first introduces the fundamental concepts and challenges of STLF, then discusses each model class's main features and assumptions. The paper compares the models in terms of their accuracy, robustness, computational efficiency, scalability, and adaptability and identifies each approach's advantages and limitations. Although this study suggests that ANNs and hybrid models may be the most promising ways to achieve accurate and reliable STLF, additional research is required to handle multiple input features, manage massive data sets, and adjust to shifting energy conditions. [ABSTRACT FROM AUTHOR]

This paper investigates the effect of the architectural design of deep learning models in combination with a feature engineering approach considering the temporal variation in the features in the case of tropospheric ozone forecasting. Although deep neural network models have shown successful results by extracting features automatically from raw data, their performance in the domain of air quality forecasting is influenced by different feature analysis approaches and model architectures. This paper proposes a simple but effective analysis of tropospheric ozone time series data that can reveal temporal phases of the ozone evolution process and assist neural network models to reflect these temporal variations. We demonstrate that addressing the ozone evolution phases when developing the model architecture improves the performance of deep neural network models. As a result, we evaluated our approach on the CNN model and showed that not only does it improve the performance of the CNN model, but also that the CNN model in combination with our approach boosts the performance of the other deep neural network models such as LSTM. The development of the CNN, LSTM-CNN, and CNN-LSTM models using the proposed approach improved the prediction performance of the models by 3.58%, 1.68%, and 3.37%, respectively. [ABSTRACT FROM AUTHOR]

In this paper, we survey the most recent advances in supervised machine learning (ML) and high‐dimensional models for time‐series forecasting. We consider both linear and nonlinear alternatives. Among the linear methods, we pay special attention to penalized regressions and ensemble of models. The nonlinear methods considered in the paper include shallow and deep neural networks, in their feedforward and recurrent versions, and tree‐based methods, such as random forests and boosted trees. We also consider ensemble and hybrid models by combining ingredients from different alternatives. Tests for superior predictive ability are briefly reviewed. Finally, we discuss application of ML in economics and finance and provide an illustration with high‐frequency financial data. [ABSTRACT FROM AUTHOR]

Economic growth and prosperity of a nation are inextricably linked to the agricultural sector. In the compass of agriculture, climate and other environmental changes are one of the main challenges. The present study attempts to predict crop yield for the Jaipur district which is an important region in the semi-arid eastern plain of Rajasthan (India). Machine learning (ML) techniques are used in forecasting and developing practical solutions for numerous challenges such as climate change with other environmental factors. Crop yield prediction is the process of predicting yield using historical data through meteorological parameters and past yield records. This paper used the agrometeorological time-series data from the year 1991 to 2020 for optimal yield forecasting. There have been numerous attempts to improve crop yield prediction by employing machine learning techniques. However, in this study, fusing the intelligence of reinforcement with deep learning, we got a comprehensive framework for mapping raw data to crop prediction values, allowing an optimal estimation of crop yields with higher accuracy. Upon comparative analysis of numerous ML algorithms, Random Forest is found the best-performing algorithm with an accuracy of 92.3% using supervised machine learning methods. With an accuracy of 92.3%, the proposed Random Forest-based model outperforms other techniques that are currently being used to predict crop yields. The study predictions could significantly help in choosing the best cropping pattern and planning for action accordingly. The results provide the best ways to solve environmental and agricultural problems in this semi-arid region of the specified Rajasthan state facing climate change issues. [ABSTRACT FROM AUTHOR]

Geological hazard is an adverse geological condition that can cause loss of life and property. Accurate prediction and analysis of geological hazards is an important and challenging task. In the past decade, there has been a great expansion of geohazard detection data and advancement in data-driven simulation techniques. In particular, great efforts have been made in applying deep learning to predict geohazards. To understand the recent progress in this field, this paper provides an overview of the commonly used data sources and deep neural networks in the prediction of a variety of geological hazards. [ABSTRACT FROM AUTHOR]

Summary: Globally, the water‐level fluctuations in lakes are a dynamic and complex process. The fluctuation is characterized by higher non‐linearity and stochasticity, making it quite hard to forecast for future planning. However, the advent of machine learning algorithms in recent decades provides significant improvement in forecasting such fluctuations. This work provides a systematic review of the machine learning algorithms (ML) used for characterizing lake‐water level dynamics. Among those ML algorithms, the paper reviews seven distinct as well as popular algorithms namely, neural network model, support vector machines, extreme learning machine, artificial neuro‐fuzzy inference systems, evolutionary and hybrid algorithms, and deep learning models. The sample inputs, splitting of data, performance metrics, and its comparison are discussed with future scope. Moreover, the strength and limitations of those algorithms are also examined. Finally, the review in this paper gives a newer vision for water resource planners and hydrologists for sustainable lake management. [ABSTRACT FROM AUTHOR]

The focus of this paper is on application of advance data analytics and deep machine learning methods for time series forecasting of injection/production data from subsurface hydrocarbon recovery processes. Injection and production data, from subsurface reservoir developed though implementation of water flooding recovery mechanism, is used with aim of developing a machine learning based forecasting methodology to eventually replace numerical simulation-based forecasting methods. Different machine learning algorithms exists for single- and multi-step time series forecasting, e.g., nonlinear regression, artificial neural network (ANN) and long-short-term-memory (LSTM) based recurrent neural networks (RNN). In this paper, RNN-LSTM algorithm is tested on real field data, comprising of a number of injection and production well patterns, and results of RNN-LSTM forecasting model are presented. Complexities related to data acquisition, analysis, and processing are also discussed in detail. The results presented in this paper are unique as it is for the first time that ML model is applied to forecast production from a tight carbonate hydrocarbon reservoir, which is developed through water flooding with help of long horizontal wells. Such an application for time series forecasting using RNN-LSTM model has never been presented, before in literature, to the best of author's knowledge. [ABSTRACT FROM AUTHOR]

Despite advancements in smart grid (SG) technology, effective load forecasting utilizing big data or large-scale datasets remains a complex task for energy management, planning, and control. The Saudi SGs, in alignment with the Saudi Vision 2030, have been envisioned as future electrical grids with a bidirectional flow of power and data. To that end, data analysis and predictive models can enhance Saudi SG planning and control via artificial intelligence (AI). Recently, many AI methods including deep learning (DL) algorithms for SG applications have been published in the literature and have shown superior time series predictions compared with conventional prediction models. Current load-prediction research for the Saudi grid focuses on identifying anticipated loads and consumptions, on utilizing limited historical data and the behavior of the load's consumption, and on conducting shallow forecasting models. However, little scientific proof on complex DL models or real-life application has been conducted by researchers; few articles have studied sophisticated large-scale prediction models for Saudi grids. This paper proposes hybrid DL methods to enhance the outcomes in Saudi SG load forecasting, to improve problem-relevant features, and to accurately predict complicated power consumption, with the goal of developing reliable forecasting models and of obtaining knowledge of the relationships between the various features and attributes in the Saudi SGs. The model in this paper utilizes a real dataset from the Jeddah and Medinah grids in Saudi Arabia for a full year, 2021, with a one-hour time resolution. A benchmark strategy using different conventional DL methods including artificial neural network, recurrent neural network (RNN), conventional neural networks (CNN), long short-term memory (LSTM), gated recurrent unit (GRU), and different real datasets is used to verify the proposed models. The prediction results demonstrate the effectiveness of the proposed hybrid DL models, with CNN–GRU and CNN–RNN with NRMSE obtaining 1.4673% and 1.222% improvements, respectively, in load forecasting accuracy. [ABSTRACT FROM AUTHOR]

With the widespread adoption of service-oriented architectures (SOA), services with the same functionality but the different Quality of Service (QoS) are proliferating, which is challenging the ability of users to build high-quality services. It is often costly for users to evaluate the QoS of all feasible services; therefore, it is necessary to investigate QoS prediction algorithms to help users find services that meet their needs. In this paper, we propose a QoS prediction algorithm called the MFDK model, which is able to fill in historical sparse QoS values by a non-negative matrix decomposition algorithm and predict future QoS values by a deep neural network. In addition, this model uses a Kalman filter algorithm to correct the model prediction values with real-time QoS observations to reduce its prediction error. Through extensive simulation experiments on the WS-DREAM dataset, we analytically validate that the MFDK model has better prediction accuracy compared to the baseline model, and it can maintain good prediction results under different tensor densities and observation densities. We further demonstrate the rationality of our proposed model and its prediction performance through model ablation experiments and parameter tuning experiments. [ABSTRACT FROM AUTHOR]

This paper enters the ongoing volatility forecasting debate by examining the ability of a wide range of Machine Learning methods (ML), and specifically Artificial Neural Network (ANN) models. The ANN models are compared against traditional econometric models for ten Asian markets using daily data for the time period from 12 September 1994 to 05 March 2018. The empirical results indicate that ML algorithms, across the range of countries, can better approximate dependencies compared to traditional benchmark models. Notably, the predictive performance of such deep learning models is superior perhaps due to its ability in capturing long-range dependencies. For example, the Neuro Fuzzy models of ANFIS and CANFIS, which outperform the EGARCH model, are more flexible in modelling both asymmetry and long memory properties. This offers new insights for Asian markets. In addition to standard statistics forecast metrics, we also consider risk management measures including the value-at-risk (VaR) average failure rate, the Kupiec LR test, the Christoffersen independence test, the expected shortfall (ES) and the dynamic quantile test. The study concludes that ML algorithms provide improving volatility forecasts in the stock markets of Asia and suggest that this may be a fruitful approach for risk management. [ABSTRACT FROM AUTHOR]

An automated diagnosis system is crucial for helping radiologists identify brain abnormalities efficiently. The convolutional neural network (CNN) algorithm of deep learning has the advantage of automated feature extraction beneficial for an automated diagnosis system. However, several challenges in the CNN-based classifiers of medical images, such as a lack of labeled data and class imbalance problems, can significantly hinder the performance. Meanwhile, the expertise of multiple clinicians may be required to achieve accurate diagnoses, which can be reflected in the use of multiple algorithms. In this paper, we present Deep-Stacked CNN, a deep heterogeneous model based on stacked generalization to harness the advantages of different CNN-based classifiers. The model aims to improve robustness in the task of multi-class brain disease classification when we have no opportunity to train single CNNs on sufficient data. We propose two levels of learning processes to obtain the desired model. At the first level, different pre-trained CNNs fine-tuned via transfer learning will be selected as the base classifiers through several procedures. Each base classifier has a unique expert-like character, which provides diversity to the diagnosis outcomes. At the second level, the base classifiers are stacked together through neural network, representing the meta-learner that best combines their outputs and generates the final prediction. The proposed Deep-Stacked CNN obtained an accuracy of 99.14% when evaluated on the untouched dataset. This model shows its superiority over existing methods in the same domain. It also requires fewer parameters and computations while maintaining outstanding performance. [ABSTRACT FROM AUTHOR]

Breast Cancer diagnosis is one of the most studied problems in the medical domain. Cancer diagnosis has been studied extensively, which instantiates the need for early prediction of cancer disease. To obtain advance prediction, health records are exploited and given as input to an automated system. The paper focuses on constructing an automated system by employing deep learning based recurrent neural network models. A stacked GRU-LSTM-BRNN is proposed in this paper that accepts health records of a patient for determining the possibility of being affected by breast cancer. The proposed model is compared against other baseline classifiers such as stacked simple-RNN model, stacked LSTM-RNN model, stacked GRU-RNN model. Comparative results obtained in this study indicate that the stacked GRU-LSTM-BRNN model yields better classification performance for predictions related to breast cancer disease. [ABSTRACT FROM AUTHOR]

Sea surface temperature (SST) forecasting is the task of predicting future values of a given sequence using historical SST data, which is beneficial for observing and studying hydroclimatic variability. Most previous studies ignore the spatial information in SST prediction and the forecasting models have limitations to process the large-scale SST data. A novel model of SST prediction integrated Deep Gated Recurrent Unit and Convolutional Neural Network (DGCnetwork) is proposed in this paper. The DGCnetwork has a compact structure and focuses on learning deep long-term dependencies in SST time series. Temporal information and spatial information are all included in our procedure. Differential Evolution algorithm is applied in order to configure DGCnetwork's optimum architecture. Optimum Interpolation Sea Surface Temperature (OISST) data is selected to conduct experiments in this paper, which has good temporal homogeneity and feature resolution. The experiments demonstrate that the DGCnetwork significantly obtains excellent forecasting result, predicting SST by different lengths flexibly and accurately. On the East China Sea dataset and the Yellow Sea dataset, the accuracy of the prediction results is above 98% on the whole and all mean absolute error (MAE) values are lower than 0.33°C. Compared with the other models, root mean square error (RMSE), root mean square percentage error (RMSPE), and mean absolute percentage Error (MAPE) of the proposed approach reduce at least 0.1154, 0.2594, and 0.3938. The experiments of SST time series show that the DGCnetwork model maintains good prediction results, better performance, and stronger stability, which has reached the most advanced level internationally. [ABSTRACT FROM AUTHOR]

Machine learning algorithms and artificial neural networks promise a new and powerful approach for making better and more transferable predictions in global conflict research. In this paper, a novel conflict dataset for the prediction of conflict intensity is introduced. It includes seven socio-economic and political indicators spanning a set of 851 country-years. This set of indicators is combined with conflict intensity data covering the timeframe of 2009–2015 to build a viable predictor framework. With this dataset as a foundation, a wide range of different predictive methods are tested, including linear discriminant analysis, classification and regression trees, k-nearest neighbor, random forest and several series of advanced artificial neural networks including a novel non-sequential long-short-term memory setup. Acknowledging the potential of deep learning techniques for many disciplines and projects, this paper shows, that for this type of assembled medium sized data, resembling many common research frameworks in Social and Political Sciences, using neural networks as singular approach might not be fruitful. The advantages of neural networks do not always outweigh their practical and technical disadvantages in small or medium data settings. The argument derived from this study is that researchers should combine Supervised Learning Algorithms and Deep Learning Networks as a general approach in similar predictive setups, or carefully evaluate for each dataset and project if the added complexity accompanied with using networks is indeed translating into better predictive performance. [ABSTRACT FROM AUTHOR]

Inter prediction is a crucial part of hybrid video coding frameworks, utilized to exploit the temporal redundancy in video sequences and improve the coding performance. During inter prediction, a predicted block is typically derived from reference pictures using motion estimation and motion compensation. To improve the coding performance of inter prediction, a neural network based enhancement to inter prediction (NNIP) is proposed in this paper. NNIP is composed of three networks, namely residue estimation network, combination network, and deep refinement network. Specifically, first, a residue estimation network is designed to estimate the residue between current block and its predicted block using their available spatial neighbors. Second, the feature maps of the estimated residue and the predicted block are extracted and concatenated in a combination network. Finally, the concatenated feature maps are fed into a deep refinement network to generate a refined residue, which is added back to the predicted block to derive a more accurate predicted block. NNIP is integrated in HEVC to evaluate its efficiency. The experimental results demonstrate that NNIP can achieve 4.6%, 3.0%, and 2.7% BD-rate reduction on average under LDP, LDB, and RA configurations compared to HEVC. [ABSTRACT FROM AUTHOR]

Intelligent forecasting of economic indexes has been an important demand for sustainable management of smart cities. Existing methods for this purpose were mostly established upon the basis of economic mechanism. Econometric models are the most general technical means in this area. However, in era of digital economy, increasing amount of big data has brought great change to traditional production. It is becoming more difficult for conventional technological forecasting methods to deal with multi-dimensional economic indexes. To deal with such challenge, this paper introduces the artificial intelligence algorithms to implement automatic information processing, and proposes a deep neural network-based intelligent forecasting method for multi-dimensional economic indexes in smart cities. Specifically, a deep neural network with three-layer structure is developed as the backbone methodology. For empirical analysis, the real-world data from "Chengdu–Chongqing Economic Circle" in China from 2012 to 2022 are selected as the main simulation scenario. Four major indexes are selected as the main research object: gross product (GDP), per capita GDP, GDP growth rate and the proportion of tertiary industry in GDP. The experimental results show that the proposal can well deal with such forecasting problem from a data-driven perspective, with a proper forecasting effect on historical data. [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]

Nucleic-acid G-quadruplexes (G4s) play vital roles in many cellular processes. Due to their importance, researchers have developed experimental assays to measure nucleic-acid G4s in high throughput. The generated high-throughput datasets gave rise to unique opportunities to develop machine-learning-based methods, and in particular deep neural networks, to predict G4s in any given nucleic-acid sequence and any species. In this paper, we review the success stories of deep-neural-network applications for G4 prediction. We first cover the experimental technologies that generated the most comprehensive nucleic-acid G4 high-throughput datasets in recent years. We then review classic rule-based methods for G4 prediction. We proceed by reviewing the major machine-learning and deep-neural-network applications to nucleic-acid G4 datasets and report a novel comparison between them. Next, we present the interpretability techniques used on the trained neural networks to learn key molecular principles underlying nucleic-acid G4 folding. As a new result, we calculate the overlap between measured DNA and RNA G4s and compare the performance of DNA- and RNA-G4 predictors on RNA- and DNA-G4 datasets, respectively, to demonstrate the potential of transfer learning from DNA G4s to RNA G4s. Last, we conclude with open questions in the field of nucleic-acid G4 prediction and computational modeling. [ABSTRACT FROM AUTHOR]

Financial time series have been extensively studied within the past decades; however, the advent of machine learning and deep neural networks opened new horizons to apply supercomputing techniques to extract more insights from the underlying patterns of price data. This paper presents a tri-state labeling approach to classify the underlying patterns in price data into up, down and no-action classes. The introduction of a no-action state in our novel approach alleviates the burden of denoising the dataset as a preprocessing task. The performance of our labeling algorithm is experimented with using machine learning and deep learning models. The framework is augmented by applying the Bayesian optimization technique for the selection of the best tuning values of the hyperparameters. The price trend prediction module generates the required trading signals. The results show that the average annualized Sharpe ratio as the trading performance metric is about 2.823, indicating the framework produces excellent cumulative returns. [ABSTRACT FROM AUTHOR]

In this paper, we investigate two types of photovoltaic (PV) systems (on-grid and off-grid) of different sizes and propose a reliable PV forecasting method. The novelty of our research consists in a weather data-driven feature engineering considering the operation of the PV systems in similar conditions and merging the results of deterministic and stochastic models, namely Machine Learning algorithms (Random Forest—RF, eXtreme Gradient Boost—XGB) and Deep Learning algorithms (Deep Neural Networks—DNN, Gated Recurrent Unit—GRU) into a Hybrid Meta-learning Forecasting method. It combines the estimations of the above-mentioned algorithms with relevant features to predict the PV output using a Long Short-Term Memory model. To design the PV forecast for off-grid systems, that are equally important for prosumers, and approximate the potential power of these systems, the level of load and charging state of the batteries are considered. In this context, feature engineering using the weather and PV output data, including PV characteristics, is relevant to obtaining a performant and robust PV forecast for various use cases taking into account the size and connectivity of the PV systems. On average, the Mean Absolute Error and Mean Absolute Percentage Error have halved compared to values obtained with deterministic methods and are 25% lower than the stochastic models. [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]

Load Forecast (LF) is an important task in the planning, control and application of public power systems. Accurate Short Term Load Forecast (STLF) is the premise of safe and economical operation of a power system. In the research of short-term power load forecasting, machine learning and deep learning are the most popular methods at present, but there still exists a problem that the single and simple structure of power load forecasting model leads to low accuracy of load forecasting. In order to improve the accuracy of STLF, a Gated Cycle Unit (GRU)-Transformer combined neural network model is proposed. Transformer encoder structure is used as feature extractor to mine the complex mapping relationships between the input features and load. The advantage of self-attention mechanism is used to solve the problem of information loss of long sequences in short-term power load forecasting. At the same time, the multivariate time series model of GRU is used for model training. The experimental results on the power load data set of a certain region in southwest China and Panama City show that the proposed combined model prediction method has higher accuracy than those proposed in other literatures, which further proves its feasibility and superiority. [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]

Solar irradiation data are imperatively required for any solar energy-based project. The non-accessibility and uncertainty of these data can greatly affect the implementation, management, and performance of photovoltaic or thermal systems. Developing solar irradiation estimation and forecasting approaches is an effective way to overcome these issues. Practically, prediction approaches can help anticipate events by ensuring good operation of the power network and maintaining a precise balance between the demand and supply of the power at every moment. In the literature, various estimation and forecasting methods have been developed. Artificial Neural Network (ANN) models are the most commonly used methods in solar irradiation prediction. This paper aims to firstly review, analyze, and provide an overview of different aspects required to develop an ANN model for solar irradiation prediction, such as data types, data horizon, data preprocessing, forecasting horizon, feature selection, and model type. Secondly, a highly detailed state of the art of ANN-based approaches including deep learning and hybrid ANN models for solar irradiation estimation and forecasting is presented. Finally, the factors influencing prediction model performances are discussed in order to propose recommendations, trends, and outlooks for future research in this field. [ABSTRACT FROM AUTHOR]

The intelligent monitoring of tool wear status and wear prediction are important factors affecting the intelligent development of the modern machinery industry. Many scholars have used deep learning methods to achieve certain results in tool wear prediction. However, due to the instability and variability of the signal data, some neural network models may have gradient decay between layers. Most methods mainly focus on feature selection of the input data but ignore the influence degree of different features to tool wear. In order to solve these problems, this paper proposes a dual-stage attention model for tool wear prediction. A CNN-BiGRU-attention network model is designed, which introduces the self-attention to extract deep features and embody more important features. The IndyLSTM is used to construct a stable network to solve the gradient decay problem between layers. Moreover, the attention mechanism is added to the network to obtain the important information of output sequence, which can improve the accuracy of the prediction. Experimental study is carried out for tool wear prediction in a dry milling operation to demonstrate the viability of this method. Through the experimental comparison and analysis with regression prediction evaluation indexes, it proves the proposed method can effectively characterize the degree of tool wear, reduce the prediction errors, and achieve good prediction results. [ABSTRACT FROM AUTHOR]

This paper investigates a deep learning‐based wind‐forecasting model to establish an accurate forecasting model which can support the increasing growth of wind power generation. The wind forecasting means wind speed and direction forecasting at the same time. Proposed forecasting model consists of three‐dimensional convolutional neural network and deep convolutional long short‐term memory (3DCNN‐DConvLSTM), and forecasts the wind vector which expressed as time‐sequential images. DConvLSTM model learns spatiotemporal features from time‐series image data that represent a spatial and temporal change of wind speed and direction. The forecasting model combined of 3DCNN and DConvLSTM is effective to decrease training time, and forecasting error in comparison to the DConvLSTM model. Input of the forecasting model is wind speed and direction that is expressed as an image on 2D coordinate and uses the measured data by the Automated Meteorological Data Acquisition System (AMeDAS), Japan. Forecasting accuracy with one‐hour ahead and its usefulness of the proposed forecasting model is evaluated with simulation results for four seasons that is typical of Japan climate, and demonstrated by comparison with fully connected‐LSTM (FC‐LSTM), encoder‐decoder based 3DCNN (ED‐3DCNN), DConvLSTM, and persistent models. © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

This paper presents an overview of the procedures that are involved in prediction with machine learning models with special emphasis on deep learning. We study suitable objective functions for prediction in high-dimensional settings and discuss the role of regularization methods in order to alleviate the problem of over fitting. We also review other features of machine learning methods, such as the selection of hyper parameters, the role of the architecture of a deep neural network for model prediction, or the importance of using different optimization routines for model selection. The review also considers the issue of model uncertainty and presents state-of-the-art methods for constructing prediction intervals using ensemble methods, such as bootstrap and Monte Carlo dropout. These methods are illustrated in an out-of-sample empirical forecasting exercise that compares the performance of machine learning methods against conventional time series models for different financial indices. These results are confirmed in an asset allocation context. [ABSTRACT FROM AUTHOR]

Molecular property prediction (MPP) is vital in drug discovery and drug reposition. Deep learning-based MPP models capture molecular property-related features from various molecule representations. In this paper, we propose a molecule sequence embedding and prediction model facing with MPP task. We pre-trained a bi-directional encoder representations from Transformers (BERT) encoder to obtain the semantic representation of compound fingerprints, called Fingerprints-BERT (FP-BERT), in a self-supervised learning manner. Then, the encoded molecular representation by the FP-BERT is input to the convolutional neural network (CNN) to extract higher-level abstract features, and the predicted properties of the molecule are finally obtained through fully connected layer for distinct classification or regression MPP tasks. Comparison with the baselines shows that the proposed model achieves high prediction performance on all of the classification tasks and regression tasks. [ABSTRACT FROM AUTHOR]

Short-term load forecasting (STLF) has a significant role in reliable operation and efficient scheduling of power systems. However, it is still a major challenge to accurately predict power load due to social and natural factors, such as temperature, humidity, holidays and weekends, etc. Therefore, it is very important for the efficient feature selection and extraction of input data to improve the accuracy of STLF. In this paper, a novel hybrid model based on empirical mode decomposition (EMD), a one-dimensional convolutional neural network (1D-CNN), a temporal convolutional network (TCN), a self-attention mechanism (SAM), and a long short-term memory network (LSTM) is proposed to fully decompose the input data and mine the in-depth features to improve the accuracy of load forecasting. Firstly, the original load sequence was decomposed into a number of sub-series by the EMD, and the Pearson correlation coefficient method (PCC) was applied for analyzing the correlation between the sub-series with the original load data. Secondly, to achieve the relationships between load series and external factors during an hour scale and the correlations among these data points, a strategy based on the 1D-CNN and TCN is proposed to comprehensively refine the feature extraction. The SAM was introduced to further enhance the key feature information. Finally, the feature matrix was fed into the long short-term memory (LSTM) for STLF. According to experimental results employing the North American New England Control Area (ISO-NE-CA) dataset, the proposed model is more accurate than 1D-CNN, LSTM, TCN, 1D-CNN–LSTM, and TCN–LSTM models. The proposed model outperforms the 1D-CNN, LSTM, TCN, 1D-CNN–LSTM, and TCN–LSTM by 21.88%, 51.62%, 36.44%, 42.75%, 16.67% and 40.48%, respectively, in terms of the mean absolute percentage error. [ABSTRACT FROM AUTHOR]

Forecasting electricity load demand is critical for power system planning and energy management. In particular, accurate short-term load forecasting (STLF), which focuses on the lead time horizon of few minutes to one week ahead, can help in better load scheduling, unit commitment, and cost-effective operation of smart power grids. In the last decade, different artificial intelligence (AI)-based techniques and metaheuristic algorithms have been utilized for STLF by the researchers and scientists with varying degrees of accuracy and efficacy. Despite the benefits of implemented methods for STLF, many drawbacks and associated problems have also been observed and reported by the researchers. This paper provides a comprehensive review of hybrid deep learning models based on nature-inspired metaheuristic techniques for STLF with respect to the analysis of the results and accuracy. Moreover, it also provides the research findings and gaps that will assist the researchers to have an early awareness of all important benefits and drawbacks of these integrated STLF methods scientifically and systematically. Especially, the hybrid forecast models using artificial intelligence-based methods for smart grids are focused. Several performance indices are used to compare and report the accuracy of these techniques including mean absolute percentage error (MAPE). Multiple other parametric and exogenous variable details have also been focused to figure out the potential of the intelligent load forecasting techniques from the perspective of smart power grids. [ABSTRACT FROM AUTHOR]

Forecasting the aggregate charging load of a fleet of electric vehicles (EVs) plays an important role in the energy management of the future power system. Therefore, accurate charging load forecasting is necessary for reliable and efficient power system operation. A hybrid method that is a combination of the similar day (SD) selection, complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), and deep neural networks is proposed and explored in this paper. For the SD selection, an extreme gradient boosting (XGB)-based weighted k-means method is chosen and applied to evaluate the similarity between the prediction and historical days. The CEEMDAN algorithm, which is an advanced method of empirical mode decomposition (EMD), is used to decompose original data, to acquire intrinsic mode functions (IMFs) and residuals, and to improve the noise reduction effect. Three popular deep neural networks that have been utilized for load predictions are gated recurrent units (GRUs), long short-term memory (LSTM), and bidirectional long short-term memory (BiLSTM). The developed models were assessed on a real-life charging load dataset that was collected from 1000 EVs in nine provinces in Canada from 2017 to 2019. The obtained numerical results of six predictive combination models show that the proposed hybrid SD-CEEMDAN-BiLSTM model outperformed the single and other hybrid models with the smallest forecasting mean absolute percentage error (MAPE) of 2.63% Canada-wide. [ABSTRACT FROM AUTHOR]

In metal cutting processing, prediction of the tool wear or VB value can help early warning and timely tool replacement before the tool reaches the service life. Although the deep neural network is an effective method to predict the tool wear, the existing research predicts the tool wear only at its next time moment without considering the tool states at different time points. It ignores important information of the tool wear. In this paper, we propose a comprehensive model, which consists of a monitoring module and a prediction module, to monitor and predict the tool wear for the first time. In the monitoring module, a DenseNet model is constructed to monitor the tool wear via sensor signals. In addition, the prediction module based on attention mechanism is developed by simulating the human brain attention to selectively focus on the important part of processing sequence information. An encoder-decoder structure is introduced for a multi-step prediction of the tool wear. Several VB values in the nearest future are predicted by using sequential VB values monitored in the latest past. Experimental studies show that the short-term information has more influence on the tool wear prediction than the long-term information. The proposed method has been used to predict multi-step VB values in milling operations. [ABSTRACT FROM AUTHOR]

Power system demand forecasting is a crucial task in the power system engineering field. This is due to the fact that most system planning and operation activities basically rely on proper forecasting models. Entire power infrastructures are built essentially to provide and serve the consumption of energy. Therefore, it is very necessary to construct robust and efficient predictive models in order to provide accurate load forecasting. In this paper, three techniques are utilized for short-term load forecasting. These techniques are deep neural network (DNN), multilayer perceptron-based artificial neural network (ANN), and decision tree-based prediction (DR). New predictive variables are included to enhance the overall forecasting and handle the difficulties caused by some categorical predictors. The comparison among these three techniques is executed based on coefficients of determination R2 and mean absolute error (MAE). Statistical tests are performed in order to verify the results and examine whether these models are statistically different or not. The results reveal that the DNN model outperformed the other models and was statistically different from them. [ABSTRACT FROM AUTHOR]

Rain attenuation events are one of the foremost drawbacks in satellite communications, impairing satellite link availability. For this reason, it is necessary to foresee rain events to avoid an outage of the satellite link. In this paper, we propose and develop a method based on Machine Learning to predict events of rain attenuation without appealing to complex mathematical models. To be specific, we implement a Long–short term memory architecture that is a Deep Learning algorithm based on an artificial recurrent neural network. Furthermore, supervised learning is the learning task for our algorithms. For this purpose, rain attenuation time-series feed the Long–short term memory network at the input to train it. However, the lack of a rainfall database hinders the development of a reliable prediction method. Therefore, we generate a synthetic rain attenuation database by using the recommendations of the International Telecommunication Union. Each model is trained and validated by computational experiments, employing statistical metrics to find the most accurate and reliable models. Thus, the accuracy metric compares the outcomes of the proposal with other related methods and models. As a result, our best model reaches an accuracy of 91.88 % versus 87.99 % from the external best model, demonstrating superiority over other models/methods. On average, our proposal accuracy reaches a value of 88.08 % . Finally, we find out that this proposal can contribute efficiently to improving the performance of satellite system networks by re-routing data traffic or increasing link availabilities, taking advantage of the prediction of rain attenuation events. [ABSTRACT FROM AUTHOR]

Carbon emission trading market promotes carbon emission reduction effectively. Accurate carbon price forecasting is crucial for relevant policy makers and investors. However, due to the non-linearity, uncertainty, and complexity of carbon prices, the current predication models fail to predict carbon prices accurately. In this paper, an advanced deep neural network model named TCN-Seq2Seq is proposed to forecast carbon prices. The novelty of the proposed model focuses on the "sequence to sequence" layout to learn temporal data dependencies using only fully convolutional layers. Being provided with parallel training for fewer parameters, TCN-Seq2Seq forecasting model is more suitable for small carbon price dataset in few-shot learning way. Qualitatively and quantitatively, we find that the proposed framework consistently and significantly outperforms traditional statistical forecasting models and state-of-the-art deep learning prediction model with respect to predictive ability and robustness. Particularly, our proposed model achieves forecasting accuracy with the highest DA value (0.9697), the lowest MAPE value (0.0027), and the lowest RMSE value (0.0149), showing superior prediction performance compared with the traditional statistical forecasting models. The accuracy of carbon price forecasting gives insight to policy makers and carbon market investors. [ABSTRACT FROM AUTHOR]

Rear-end collision prediction has gained an increasing attention for safety improvement in smart cities. It is urgent to design efficient warning strategies for rear-end collisions which is one of the main causes of traffic accidents. The existing researches have been conducted to predict the collisions. Learning-based methods are proposed to solve this complicated issue, which the traditional methods are difficult to solve. However, due to some limitations in terms of the feature extraction and prediction performance, back-propagation learning methods are facing challenge. In this paper, we proposed a novel Rear-end Collision Prediction Mechanism with deep learning method (RCPM), in which a convolutional neural network model is established. In RCPM, the dataset is smoothed and expanded based on genetic theory to alleviate the class imbalance problem. The preprocessed dataset is divided into training and testing sets as the input to train our convolutional neural network model. The experimental results show that compared with the Honda, Berkeley and multi-layer perception neural-network-based algorithms, RCPM effectively improves performance to predict rear-end collisions. [ABSTRACT FROM AUTHOR]

This paper develops a hierarchical deep learning machine (HDLM) to efficiently achieve both quantitative and qualitative online transient stability prediction (TSP). For the sake of improving its online efficiency, multiple generators’ fault-on trajectories as well as the two closest data-points in pre-/post-fault stages are acquired by PMUs to form its raw inputs. An anti-noise graphical transient characterization technique is tactfully designed to transform multiplex trajectories into 2-D images, within which system-wide transients are concisely described. Then, following the divide-and-conquer philosophy, the HDLM trains a two-level convolutional neural network (CNN) based regression model. With stability margin regressions hierarchically refined, it manages to perform reliable and adaptive online TSP almost immediately after fault clearance. Test results on the IEEE 39-bus test system and the real-world Guangdong Power Grid in South China demonstrate the HDLM's superior performances on both stability status and stability margin predictions. [ABSTRACT FROM AUTHOR]