Search

Solar energy is an important alternative energy source, and it is essential to forecast solar power generation for efficient power management. Due to the seasonal characteristics of weather features, seasonal data partition strategies help develop prediction models that perform better in extreme weather-related situations. Most existing studies rely on fixed season partitions, such as meteorological and astronomical, where the start and end dates are specific. However, even if the countries are in the same Northern or Southern Hemisphere, seasonal changes can occur due to abnormal climates such as global warming. Therefore, we propose a novel unfixed seasonal data partition based on Symbolic Aggregate Approximation (SAX) to forecast solar power generation. Here, symbolic representations generated by SAX are used to select seasonal features and obtain seasonal criteria. We then employ two-layer stacked LSTM and combine predictions from various seasonal features and partitions through ensemble methods. The datasets used in the experiments are from real-world solar panel plants such as in Gyeongju, South Korea; and in California, USA. The results of the experiments show that the proposed methods perform better than non-partitioned or fixed-partitioned solar power generation forecasts. They outperform them by 2.2% to 3.5%; and 1.6% to 6.5% in the Gyeongju and California datasets, respectively. [ABSTRACT FROM AUTHOR]

Accurate wind speed forecasting is crucial for the efficient operation of renewable energy platforms, such as wind turbines, as it facilitates more effective management of power output and maintains grid reliability and stability. However, the inherent variability and intermittency of wind speed present significant challenges for achieving precise forecasts. To address these challenges, this study proposes a novel method based on Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and a deep learning-based Long Short-Term Memory (LSTM) network for wind speed forecasting. In the proposed method, CEEMDAN is utilized to decompose the original wind speed signal into different modes to capture the multiscale temporal properties and patterns of wind speeds. Subsequently, LSTM is employed to predict each subseries derived from the CEEMDAN process. These individual subseries predictions are then combined to generate the overall final forecast. The proposed method is validated using real-world wind speed data from Austria and Almeria. Experimental results indicate that the proposed method achieves minimal mean absolute percentage errors of 0.3285 and 0.1455, outperforming other popular models across multiple performance criteria. [ABSTRACT FROM AUTHOR]

This paper investigates the effectiveness of Neural Circuit Policies (NCPs) compared to Long Short-Term Memory (LSTM) networks in forecasting time series data for energy production and consumption in the context of predictive maintenance. Utilizing a dataset generated from the energy production and consumption data of a Tuscan company specialized in food refrigeration, we simulate a scenario where the company employs a 60 kWh storage system and calculate the battery charge and discharge policies to assess potential cost reductions and increased self-consumption of produced energy. Our findings demonstrate that NCPs outperform LSTM networks by leveraging underlying physical models, offering superior predictive maintenance solutions for energy consumption and production. [ABSTRACT FROM AUTHOR]

In recent years, transformer-based models have gained prominence in multivariate long-term time series forecasting (LTSF), demonstrating significant advancements despite facing challenges such as high computational demands, difficulty in capturing temporal dynamics, and managing long-term dependencies. The emergence of LTSF-Linear, with its straightforward linear architecture, has notably outperformed transformer-based counterparts, prompting a reevaluation of the transformer's utility in time series forecasting. In response, this paper presents an adaptation of a recent architecture, termed extended LSTM (xLSTM), for LTSF. xLSTM incorporates exponential gating and a revised memory structure with higher capacity that has good potential for LTSF. Our adopted architecture for LTSF, termed xLSTMTime, surpasses current approaches. We compare xLSTMTime's performance against various state-of-the-art models across multiple real-world datasets, demonstrating superior forecasting capabilities. Our findings suggest that refined recurrent architectures can offer competitive alternatives to transformer-based models in LTSF tasks, potentially redefining the landscape of time series forecasting. [ABSTRACT FROM AUTHOR]

This work conducts a rigorous examination of the economic influence of tourism in Saudi Arabia, with a particular focus on predicting tourist spending patterns and classifying spending behaviors during the COVID-19 pandemic period and its implications for sustainable development. Utilizing authentic datasets obtained from the Saudi Tourism Authority for the years 2015 to 2021, the research employs a variety of machine learning (ML) algorithms, including Decision Trees, Random Forests, K-Neighbors Classifiers, Gaussian Naive Bayes, and Support Vector Classifiers, all meticulously fine-tuned to optimize model performance. Additionally, the ARIMA model is expertly adjusted to forecast the economic landscape of tourism from 2022 to 2030, providing a robust predictive framework for future trends. The research framework is comprehensive, encompassing diligent data collection and purification, exploratory data analysis (EDA), and extensive calibration of ML algorithms through hyperparameter tuning. This thorough process tailors the predictive models to the unique dynamics of Saudi Arabia's tourism industry, resulting in robust forecasts and insights. The findings reveal the growth trajectory of the tourism sector, highlighted by nearly 965,073 thousand tourist visits and 7,335,538 thousand overnights, with an aggregate tourist expenditure of SAR 2,246,491 million. These figures, coupled with an average expenditure of SAR 89,443 per trip and SAR 9198 per night, form a solid statistical basis for the employed predictive models. Furthermore, this research expands on how ML and AI innovations contribute to sustainable tourism practices, addressing key aspects such as resource management, economic resilience, and environmental stewardship. By integrating predictive analytics and AI-driven operational efficiencies, the study provides strategic insights for future planning and decision-making, aiming to support stakeholders in developing resilient and sustainable strategies for the tourism sector. This approach not only enhances the capacity for navigating economic complexities in a post-pandemic context, but also reinforces Saudi Arabia's position as a premier tourism destination, with a strong emphasis on sustainability leading into 2030 and beyond. [ABSTRACT FROM AUTHOR]

This study investigates the effectiveness of Transformer-based models for retail demand forecasting. We evaluated vanilla Transformer, Informer, Autoformer, PatchTST, and temporal fusion Transformer (TFT) against traditional baselines like AutoARIMA and AutoETS. Model performance was assessed using mean absolute scaled error (MASE) and weighted quantile loss (WQL). The M5 competition dataset, comprising 30,490 time series from 10 stores, served as the evaluation benchmark. The results demonstrate that Transformer-based models significantly outperform traditional baselines, with Transformer, Informer, and TFT leading the performance metrics. These models achieved MASE improvements of 26% to 29% and WQL reductions of up to 34% compared to the seasonal Naïve method, particularly excelling in short-term forecasts. While Autoformer and PatchTST also surpassed traditional methods, their performance was slightly lower, indicating the potential for further tuning. Additionally, this study highlights a trade-off between model complexity and computational efficiency, with Transformer models, though computationally intensive, offering superior forecasting accuracy compared to the significantly slower traditional models like AutoARIMA. These findings underscore the potential of Transformer-based approaches for enhancing retail demand forecasting, provided the computational demands are managed effectively. [ABSTRACT FROM AUTHOR]

Short-term load forecasting is a challenging research problem and has a tremendous impact on electricity generation, transmission, and distribution. A robust forecasting algorithm can help power system operators to better tackle the ever-changing electric power demand. This paper presents a novel deep neural network for short-term electric load forecasting for the St. John's campus of Memorial University of Newfoundland (MUN). The electric load data are obtained from the Memorial University of Newfoundland and combined with metrological data from St. John's. This dataset is used to formulate a multivariate time-series forecasting problem. A novel deep learning algorithm is presented, consisting of a 1D Convolutional Neural Network, which is followed by an encoder–decoder-based network with attention. The input used for this model is the electric load consumption and metrological data, while the output is the hourly prediction of the next day. The model is compared with Gated Recurrent Unit (GRU) and Long Short Term Memory (LSTM)-based Recurrent Neural Network. A CNN-based encoder–decoder model without attention is also tested. The proposed model shows a lower mean absolute error (MAE), mean squared error (MSE), mean absolute percentage error (MAPE), and higher R2 score. These evaluation metrics show an improved performance compared to GRU and LSTM-based RNNs as well as the CNN encoder–decoder model without attention. [ABSTRACT FROM AUTHOR]

Accurately predicting industrial electricity consumption is of paramount importance for optimizing energy management and operational efficiency. Traditional forecasting approaches face significant challenges in capturing the complex factors influencing industrial electricity consumption, often due to the inadequate representation of correlations, thus limiting their predictive capabilities. To overcome these limitations, we propose a novel graph-based forecasting model termed Industry–Geography Time Series Forecasting Model (IG-TFM). Our approach leverages historical electricity consumption data and geographical information relevant to similar industries to construct an industry–geography relationship graph. This graph serves as the foundation of a comprehensive network that encompasses all industries of interest, allowing us to identify sectors closely associated with the target industry. The structured graph data are then processed within a graph convolutional neural network framework, which effectively captures the impact of geographical location, industry similarities, and inter-industry relationships on electricity consumption patterns. Utilizing this enriched representation, we develop our IG-TFM for accurate time series forecasting of industrial electricity consumption. Experiments conducted on real-world data, including 31 industries across 9 cities in a southern province of China, demonstrate the significant advantages of our proposed method across key performance indicators such as the Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE). These findings underscore the importance and efficacy of employing complex networks to encode sequence-related information, thereby substantially improving prediction accuracy in industrial electricity consumption forecasting. [ABSTRACT FROM AUTHOR]

This study harnesses advanced time series models ARIMA, ETS, and SARIMA, coupled with neutrosophic statistics, to forecast unemployment trends through interval-based predictions. Transforming these predictions into neutrosophic forms enables the quantification of indeterminacy, providing a nuanced interpretation of potential economic scenarios. The integration of neutrosophic statistics enhances the interpretative power and accuracy of these models, offering a deeper insight into the inherent uncertainties of economic forecasting. The approach reveals not only the variabilities and potential outcomes within the unemployment rates but also strengthens the decision-making processes by presenting data that encompass both precision and indeterminacy. This paper underscores the importance of advanced statistical methods in economic predictions, suggesting further exploration into other economic metrics and advocating for a broader application of neutrosophic statistics to enhance the reliability of economic forecasting across diverse contexts. [ABSTRACT FROM AUTHOR]

This study addresses the integration of machine learning (ML) with supervisory control and data acquisition (SCADA) systems to enhance predictive maintenance and operational efficiency in oil well monitoring. We investigated the applicability of advanced ML models, including Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and Momentum LSTM (MLSTM), on a dataset of 21,644 operational records. These models were trained to predict a critical operational parameter, FlowRate, which is essential for operational integrity and efficiency. Our results demonstrate substantial improvements in predictive accuracy: the LSTM model achieved an R2 score of 0.9720, the BiLSTM model reached 0.9725, and the MLSTM model topped at 0.9726, all with exceptionally low Mean Absolute Errors (MAEs) around 0.0090 for LSTM and 0.0089 for BiLSTM and MLSTM. These high R2 values indicate that our models can explain over 97% of the variance in the dataset, reflecting significant predictive accuracy. Such performance underscores the potential of integrating ML with SCADA systems for real-time applications in the oil and gas industry. This study quantifies ML's integration benefits and sets the stage for further advancements in autonomous well-monitoring systems. [ABSTRACT FROM AUTHOR]

Accurate aboveground vegetation biomass forecasting is essential for livestock management, climate impact assessments, and ecosystem health. While artificial intelligence (AI) techniques have advanced time series forecasting, a research gap in predicting aboveground biomass time series beyond single values persists. This study introduces RECMO and DirRecMO, two multi-output methods for forecasting aboveground vegetation biomass. Using convolutional neural networks, their efficacy is evaluated across short-, medium-, and long-term horizons on six Kenyan grassland biomass datasets, and compared with that of existing single-output methods (Recursive, Direct, and DirRec) and multi-output methods (MIMO and DIRMO). The results indicate that single-output methods are superior for short-term predictions, while both single-output and multi-output methods exhibit a comparable effectiveness in long-term forecasts. RECMO and DirRecMO outperform established multi-output methods, demonstrating a promising potential for biomass forecasting. This study underscores the significant impact of multi-output size on forecast accuracy, highlighting the need for optimal size adjustments and showcasing the proposed methods' flexibility in long-term forecasts. Short-term predictions show less significant differences among methods, complicating the identification of the best performer. However, clear distinctions emerge in medium- and long-term forecasts, underscoring the greater importance of method choice for long-term predictions. Moreover, as the forecast horizon extends, errors escalate across all methods, reflecting the challenges of predicting distant future periods. This study suggests advancing hybrid models (e.g., RECMO and DirRecMO) to improve extended horizon forecasting. Future research should enhance adaptability, investigate multi-output impacts, and conduct comparative studies across diverse domains, datasets, and AI algorithms for robust insights. [ABSTRACT FROM AUTHOR]

Forecasting nuclear energy production is essential for market operations such as security, economic efficiency, resource optimization, grid stability, and the integration of renewable energy sources. Forecasting approaches allow nuclear power plants to operate consistently, contributing to the overall reliability and long-term viability of the energy system. It is noted that energy systems researchers are increasingly interested in machine learning models used to face the challenge of time series forecasting. This study evaluates a hybrid ensemble learning of three time series forecasting models including least-squares support vector regression, gated recurrent unit, and long short-term memory models applied to nuclear power time series forecasting on the dataset of French power plants from 2009 to 2020. Furthermore, this research evaluates forecasting results in which approaches are directed towards the optimized RreliefF (Robust relief Feature) selection algorithm using a hyperparameter optimization based on tree-structured Parzen estimator and following an ensemble learning approach, showing promising results in terms of performance metrics. The suggested ensemble learning model, which combines deep learning and the RreliefF algorithm using a hold-out, outperforms the other nine forecasting models in this study according to performance criteria such as 75% for the coefficient of determination, a root squared error average of 0.108, and an average absolute error of 0.080. [ABSTRACT FROM AUTHOR]

Time series forecasting is undoubtedly a key area in machine learning due to the numerous fields where it is crucial to estimate future data points of sequences based on a set of previously observed values. Deep learning has been successfully applied to this area. On the other hand, growing concerns about the steady increase in the amount of resources required by deep learning-based tools have made Green AI gain traction as a move towards making machine learning more sustainable. In this paper, we present a deep learning-based time series forecasting methodology called GreeNNTSF, which aims to reduce the size of the resulting model, thereby diminishing the associated computational and energetic costs without giving up adequate forecasting performance. The methodology, based on the ODF2NNA algorithm, produces models that outperform state-of-the-art techniques not only in terms of prediction accuracy but also in terms of computational costs and memory footprint. To prove this claim, after presenting the main state-of-the-art methods that utilize deep learning for time series forecasting and introducing our methodology we test GreeNNTSF on a selection of real-world forecasting problems that are commonly used as benchmarks, such as SARS-CoV-2 and PhysioNet (medicine), Brazilian Weather (climate), WTI and Electricity (economics), and Traffic (smart cities). The results of each experiment conducted objectively demonstrate, rigorously following the experimentation presented in the original papers that addressed these problems, that our method is more competitive than other state-of-the-art approaches, producing more accurate and efficient models. [ABSTRACT FROM AUTHOR]

With growing concerns over climate change, accurately predicting temperature trends is crucial for informed decision-making and policy development. In this study, we perform a comprehensive comparative analysis of four advanced time series forecasting models—Autoregressive Integrated Moving Average (ARIMA), Exponential Smoothing (ETS), Multilayer Perceptron (MLP), and Gaussian Processes (GP)—to assess changes in minimum and maximum temperatures across four key regions in the United States. Our analysis includes hyperparameter optimization for each model to ensure peak performance. The results indicate that the MLP model outperforms the other models in terms of accuracy for temperature forecasting. Utilizing this best-performing model, we conduct temperature projections to evaluate the hypothesis that the rates of change in temperatures are greater than zero. Our findings confirm a positive rate of change in both maximum and minimum temperatures, suggesting a consistent upward trend over time. This research underscores the critical importance of refining time series forecasting models to address the challenges posed by climate change and supporting the development of effective strategies to mitigate the impacts of rising temperatures. The insights gained from this work emphasize the need for continuous advancement in predictive modeling techniques to better understand and respond to the dynamics of climate change. [ABSTRACT FROM AUTHOR]

The widespread adoption of e-commerce has rendered online reviews an indispensable source for acquiring knowledge about product features. The Kano model serves as a classic framework for categorizing customer requirements. It was proposed by the Japanese scholar Noriaki Kano in 1984 as a tool primarily used to help businesses better understand and categorize customer needs, guiding product development and service quality improvement. However, existing research on mining online review information often relies predominantly on static analysis, lacking comprehensive categorization of user demands. To address this gap, this paper introduces an enhanced Kano model for the identification and dynamic analysis of user demands. This model classifies review data based on emotional polarity and user attention, leveraging the characteristics inherent in online reviews. Furthermore, it constructs a user demand evolution model using time series analysis and utilizes SnowNLP for emotional calculations. By conducting word frequency statistics and employing LDA models to analyze product features, this paper identifies the evolving trends in user demands. Additionally, the exponential smoothing method is used to forecast the trend in users’ emotional values towards the product. The findings demonstrate that this model effectively extracts valuable insights regarding product feature information from user reviews, thereby offering novel perspectives and methodologies for related fields. Consequently, this contributes significantly to advancing the identification and dynamic analysis of user demands. [ABSTRACT FROM AUTHOR]

Introduction: Hypoxia is defined as a critically low-oxygen condition of water, which, if prolonged, can be harmful to fish and many other aquatic species. In the context of ocean salmon fish farming, early detection of hypoxia events is critical for farm managers to mitigate these events to reduce fish stress, however in complex natural systems accurate forecasting tools are limited. The goal of this research is to use a machine learning approach to forecast oxygen concentration and predict hypoxia events in marine net-pen salmon farms. Methods: The developed model is based on gradient boosting and works in two stages. First, we apply auto-regression to build a forecasting model that predicts oxygen concentration levels within a cage. We take a global forecasting approach by building a model using the historical data provided by sensors at several marine fish farms located in eastern Canada. Then, the forecasts are transformed into binary probabilities that indicate the likelihood of a low-oxygen event. We leverage the cumulative distribution function to compute these probabilities. Results and discussion: We tested our model in a case study that included several cages across 14 fish farms. The experiments suggest that the model can detect future hypoxic events with a commercially acceptable false alarm rate. The resulting probabilistic predictions and oxygen concentration forecasts can help salmon farmers to prioritize resources, and reduce harm to crops. [ABSTRACT FROM AUTHOR]

Reservoir impoundment significantly impacts the hydrogeological conditions of reservoir bank slopes, and bank slope deformation or destruction occurs frequently under cyclic impoundment conditions. Ground deformation prediction is crucial to the early warning system for slow-moving landslides. Deep learning methods have developed rapidly in recent years, but only a few studies are on combining deep learning and landslide warning. This paper proposes a slow-moving landslide displacement prediction method based on the Informer deep learning model. Firstly, the Sentinel-1 (S1) data are processed to obtain the cumulative displacement time-series image of the bank slope by the Small-BAseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR) method. Then, combining data on rainfall, humidity, and horizontal and vertical distances of pixel points from the water table line, this study created a dataset with landslide displacement as the target feature. After that, this paper improves the Informer model to make it applicable to our dataset. This study chose the Dawanzi landslide in the Baihetan reservoir area, China, for validation. After training with 50-time series deformation data points, the model can predict the displacement results of 12-time series deformation data points using 12-time series multi-feature data, and compared with the monitoring values, its Mean Square Error (MSE) was 11.614. The results show that the multivariate dataset is better than the deformation univariate data in predicting the displacement in the large deformation zone of bank slopes, and our model has better complexity and prediction performance than other deep learning models. The prediction results show that among zones I–IV, where the Dawanzi Tunnel is located, significant deformation with the maximum deformation rate detected exceeding –100mm/year occurs in Zones I and III. In these two zones, the initiation of deformation relates to the drop in water level after water storage, with the deformation rate of Zone III exhibiting a stronger correlation with the change in water level. It is expected that deformation in Zone III will either remain slow or stop, while deformation in Zone I will continue at the same or a decreased rate. Our proposed method for slow-moving landslide displacement forecasting offers fast, intuitive, and economically feasible advantages. It can provide a feasible research idea for future deep learning and landslide warning research. [ABSTRACT FROM AUTHOR]

The maritime industry is integral to global trade and heavily depends on precise forecasting to maintain efficiency, safety, and economic sustainability. Adopting deep learning for predictive analysis has markedly improved operational accuracy, cost efficiency, and decision-making. This technology facilitates advanced time series analysis, vital for optimizing maritime operations. This paper reviews deep learning applications in time series analysis within the maritime industry, focusing on three areas: ship operation-related, port operation-related, and shipping market-related topics. It provides a detailed overview of the existing literature on applications such as ship trajectory prediction, ship fuel consumption prediction, port throughput prediction, and shipping market prediction. The paper comprehensively examines the primary deep learning architectures used for time series forecasting in the maritime industry, categorizing them into four principal types. It systematically analyzes the advantages of deep learning architectures across different application scenarios and explores methodologies for selecting models based on specific requirements. Additionally, it analyzes data sources from the existing literature and suggests future research directions. [ABSTRACT FROM AUTHOR]

Generative artificial intelligence (AI) has developed as an effective tool for time series predicting, revolutionizing the typical methods of prediction. Different classical approaches that depend on existing approaches and assumptions, generative AI controls advanced deep learning (DL) approaches like generative adversarial networks (GANs) and recurrent neural networks (RNNs), to identify designs and connections in time series data. DL has accomplished major success in optimizing performances connected with AI. In the financial area, it can be extremely utilized for the stock market predictive, trade implementation approaches, and set of optimizers. Stock market predictive is the most important use case in this field. GANs with advanced AI approaches have become more significant in recent times. However, it can be utilized in image‐image‐translation and other computer vision (CV) conditions. GANs could not utilized greatly for stock market prediction because of their effort to establish the proper set of hyperparameters. This study develops an integrated spotted hyena optimization algorithm with generative artificial intelligence for time series forecasting (SHOAGAI‐TSF) technique. The purpose of the SHOAGAI‐TSF technique is to accomplish a forecasting process for the utilization of stock price prediction. The SHOAGAI‐TSF technique uses probabilistic forecasting with a conditional GAN (CGAN) approach for the prediction of stock prices. The CGAN model learns the data generation distribution and determines the probabilistic prediction from it. To boost the prediction results of the CGAN approach, the hyperparameter tuning can be performed by the use of the SHOA. The simulation result analysis of the SHOAGAI‐TSF technique takes place on the stock market dataset. The experimental outcomes determine the significant solution of the SHOAGAI‐TSF algorithm with other compared methods in terms of distinct metrics. [ABSTRACT FROM AUTHOR]

This study presents methods to handle deep learning regressions with input and output sequences of different lengths. We discuss the Autoregressive one-step prediction framework and introduce an innovative one-time multi-step (OTMS) prediction approach, based on a custom loss function, that predicts all future steps in a single shot. The presented methodologies are then applied to simultaneously predict the State of Health (SoH) trajectory and estimate the Remaining Useful Life (RUL) of lithium-ion battery cells. Accurate estimates of SoH trajectory and RUL are essential for Battery Management Systems (BMSs), electronic systems that guarantee safety while maximizing performance and extending battery lifespan. In this context, the studied methodologies were compared using a rigorous cross-validation approach. The OTMS model showed better predictions in early cycles, while the Autoregressive model performed better in later cycles, suggesting a hybrid approach between these two methodologies as an optimal solution. [ABSTRACT FROM AUTHOR]

Abstract This paper presents FORSEER (Forecasting by Selective Ensemble Estimation and Reconstruction), a novel methodology designed to address temperature forecasting under the challenges inherent to climate change. FORSEER integrates decomposition, forecasting, and ensemble methods within a modular framework. This methodology decomposes the time series into trend, seasonal, and residual components. Subsequently, multiple optimized forecast models are applied to each component. These component models are then carefully weighted and combined through an ensemble process to generate a final robust forecast. Experimental results demonstrate that FORSEER is an efficient computational forecasting methodology for complex climate time series. Furthermore, we show that FORSEER has an equivalent forecasting performance to the M4 competition champion SMYL method for temperature series. Besides, the proposed methodology has less computational complexity than SMYL, making it a more accessible and scalable option. FORSEER's modular architecture also allows flexibility when substituting techniques depending on the context of the problem, facilitating the parallel execution of independent tasks and resulting in a strategy adaptable to multiple contexts.

With growing concerns over climate change, accurately predicting temperature trends is crucial for informed decision-making and policy development. In this study, we perform a comprehensive comparative analysis of four advanced time series forecasting models—Autoregressive Integrated Moving Average (ARIMA), Exponential Smoothing (ETS), Multilayer Perceptron (MLP), and Gaussian Processes (GP)—to assess changes in minimum and maximum temperatures across four key regions in the United States. Our analysis includes hyperparameter optimization for each model to ensure peak performance. The results indicate that the MLP model outperforms the other models in terms of accuracy for temperature forecasting. Utilizing this best-performing model, we conduct temperature projections to evaluate the hypothesis that the rates of change in temperatures are greater than zero. Our findings confirm a positive rate of change in both maximum and minimum temperatures, suggesting a consistent upward trend over time. This research underscores the critical importance of refining time series forecasting models to address the challenges posed by climate change and supporting the development of effective strategies to mitigate the impacts of rising temperatures. The insights gained from this work emphasize the need for continuous advancement in predictive modeling techniques to better understand and respond to the dynamics of climate change.

Lauded for its capacity to curtail building energy consumption and enhance environmental performance compared to traditional mineral-based materials, wood has gained substantial traction in the construction sector. Timber construction, which is a focal point of growing interest in both industry and academia, warrants a reassessment of its historical trajectory and future prospects. This study examines publications on timber construction from 1990 to 2022 to analyze the growth path, shifting hotspots, and potential research directions in this field. By employing scientometric analysis, influential journals, articles, countries, and keywords are identified. Integration into a logistic growth model (LGM) showcases publication trends, while the Prophet model forecasts global growth. Research frontiers and emerging themes are revealed through keyword bursts surge evolution. This study offers a visualized knowledge framework, bridging current research with future trends and enabling practitioners and researchers to comprehensively grasp the evolution of timber construction.

In recent years, transformer-based models have gained prominence in multivariate long-term time series forecasting (LTSF), demonstrating significant advancements despite facing challenges such as high computational demands, difficulty in capturing temporal dynamics, and managing long-term dependencies. The emergence of LTSF-Linear, with its straightforward linear architecture, has notably outperformed transformer-based counterparts, prompting a reevaluation of the transformer’s utility in time series forecasting. In response, this paper presents an adaptation of a recent architecture, termed extended LSTM (xLSTM), for LTSF. xLSTM incorporates exponential gating and a revised memory structure with higher capacity that has good potential for LTSF. Our adopted architecture for LTSF, termed xLSTMTime, surpasses current approaches. We compare xLSTMTime’s performance against various state-of-the-art models across multiple real-world datasets, demonstrating superior forecasting capabilities. Our findings suggest that refined recurrent architectures can offer competitive alternatives to transformer-based models in LTSF tasks, potentially redefining the landscape of time series forecasting.

Accurate aboveground vegetation biomass forecasting is essential for livestock management, climate impact assessments, and ecosystem health. While artificial intelligence (AI) techniques have advanced time series forecasting, a research gap in predicting aboveground biomass time series beyond single values persists. This study introduces RECMO and DirRecMO, two multi-output methods for forecasting aboveground vegetation biomass. Using convolutional neural networks, their efficacy is evaluated across short-, medium-, and long-term horizons on six Kenyan grassland biomass datasets, and compared with that of existing single-output methods (Recursive, Direct, and DirRec) and multi-output methods (MIMO and DIRMO). The results indicate that single-output methods are superior for short-term predictions, while both single-output and multi-output methods exhibit a comparable effectiveness in long-term forecasts. RECMO and DirRecMO outperform established multi-output methods, demonstrating a promising potential for biomass forecasting. This study underscores the significant impact of multi-output size on forecast accuracy, highlighting the need for optimal size adjustments and showcasing the proposed methods’ flexibility in long-term forecasts. Short-term predictions show less significant differences among methods, complicating the identification of the best performer. However, clear distinctions emerge in medium- and long-term forecasts, underscoring the greater importance of method choice for long-term predictions. Moreover, as the forecast horizon extends, errors escalate across all methods, reflecting the challenges of predicting distant future periods. This study suggests advancing hybrid models (e.g., RECMO and DirRecMO) to improve extended horizon forecasting. Future research should enhance adaptability, investigate multi-output impacts, and conduct comparative studies across diverse domains, datasets, and AI algorithms for robust insights.

Abstract Loop diuretics are prevailing drugs to manage fluid overload in heart failure. However, adjusting to loop diuretic doses is strenuous due to the lack of a diuretic guideline. Accordingly, we developed a novel clinician decision support system for adjusting loop diuretics dosage with a Long Short-Term Memory (LSTM) algorithm using time-series EMRs. Weight measurements were used as the target to estimate fluid loss during diuretic therapy. We designed the TSFD-LSTM, a bi-directional LSTM model with an attention mechanism, to forecast weight change 48 h after heart failure patients were injected with loop diuretics. The model utilized 65 variables, including disease conditions, concurrent medications, laboratory results, vital signs, and physical measurements from EMRs. The framework processed four sequences simultaneously as inputs. An ablation study on attention mechanisms and a comparison with the transformer model as a baseline were conducted. The TSFD-LSTM outperformed the other models, achieving 85% predictive accuracy with MAE and MSE values of 0.56 and 1.45, respectively. Thus, the TSFD-LSTM model can aid in personalized loop diuretic treatment and prevent adverse drug events, contributing to improved healthcare efficacy for heart failure patients.

Abstract Electrical conductivity (EC) is widely recognized as one of the most essential water quality metrics for predicting salinity and mineralization. In the current research, the EC of two Australian rivers (Albert River and Barratta Creek) was forecasted for up to 10 days using a novel deep learning algorithm (Convolutional Neural Network combined with Long Short-Term Memory Model, CNN-LSTM). The Boruta-XGBoost feature selection method was used to determine the significant inputs (time series lagged data) to the model. To compare the performance of Boruta-XGB-CNN-LSTM models, three machine learning approaches—multi-layer perceptron neural network (MLP), K-nearest neighbour (KNN), and extreme gradient boosting (XGBoost) were used. Different statistical metrics, such as correlation coefficient (R), root mean square error (RMSE), and mean absolute percentage error, were used to assess the models' performance. From 10 years of data in both rivers, 7 years (2012–2018) were used as a training set, and 3 years (2019–2021) were used for testing the models. Application of the Boruta-XGB-CNN-LSTM model in forecasting one day ahead of EC showed that in both stations, Boruta-XGB-CNN-LSTM can forecast the EC parameter better than other machine learning models for the test dataset (R = 0.9429, RMSE = 45.6896, MAPE = 5.9749 for Albert River, and R = 0.9215, RMSE = 43.8315, MAPE = 7.6029 for Barratta Creek). Considering the better performance of the Boruta-XGB-CNN-LSTM model in both rivers, this model was used to forecast 3–10 days ahead of EC. The results showed that the Boruta-XGB-CNN-LSTM model is very capable of forecasting the EC for the next 10 days. The results showed that by increasing the forecasting horizon from 3 to 10 days, the performance of the Boruta-XGB-CNN-LSTM model slightly decreased. The results of this study show that the Boruta-XGB-CNN-LSTM model can be used as a good soft computing method for accurately predicting how the EC will change in rivers.

Accurately predicting the concentration trend of dissolved gas in oil has a positive effect on the evaluation of transformer status and life assessment. In order to improve the accuracy of dissolved gas in oil prediction, a dissolved gas in oil prediction method based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and time convolution network (TCN) is proposed in this paper. Firstly, the CEEMDAN method is used to decompose the original sequence of dissolved gas in oil into multiple intrinsic mode functions(IMFs), separating the stable and unstable IMFs. Secondly, TCN are established for IMFs, then predictions based on these trained TCNs are made. Finally, the prediction results of IMFs are overlaid to reconstruct the prediction results of the original sequence. Analysis in this paper shows that the root mean square error, mean absolute error and maximum error of the prediction method are 1.01 μL/L, 1.53 μL/L, 5.54 μL/L respectively, which are reduced by 53.47%, 41.18%, 13.36% compared to the case without using the CEEMDAN. When using CEEMDAN, the three errors are the smallest compared to commonly used recurrent neural networks. The proposed dissolved gas in oil prediction method has higher prediction accuracy and can provide more effective support for condition based maintenance strategy.

Tunnel boring machines (TBMs) have been widely utilised in tunnel construction due to their high efficiency and reliability. Accurately predicting TBM performance can improve project time management, cost control, and risk management. This study aims to use deep learning to develop real-time models for predicting the penetration rate (PR). The models are built using data from the Changsha metro project, and their performances are evaluated using unseen data from the Zhengzhou Metro project. In one-step forecast, the predicted penetration rate follows the trend of the measured penetration rate in both training and testing. The autoregressive integrated moving average (ARIMA) model is compared with the recurrent neural network (RNN) model. The results show that univariate models, which only consider historical penetration rate itself, perform better than multivariate models that take into account multiple geological and operational parameters (GEO and OP). Next, an RNN variant combining time series of penetration rate with the last-step geological and operational parameters is developed, and it performs better than other models. A sensitivity analysis shows that the penetration rate is the most important parameter, while other parameters have a smaller impact on time series forecasting. It is also found that smoothed data are easier to predict with high accuracy. Nevertheless, over-simplified data can lose real characteristics in time series. In conclusion, the RNN variant can accurately predict the next-step penetration rate, and data smoothing is crucial in time series forecasting. This study provides practical guidance for TBM performance forecasting in practical engineering.

Abstract Air pollution poses a significant threat to the health of the environment and human well-being. The air quality index (AQI) is an important measure of air pollution that describes the degree of air pollution and its impact on health. Therefore, accurate and reliable prediction of the AQI is critical but challenging due to the non-linearity and stochastic nature of air particles. This research aims to propose an AQI prediction hybrid deep learning model based on the Attention Convolutional Neural Networks (ACNN), Autoregressive Integrated Moving Average (ARIMA), Quantum Particle Swarm Optimization (QPSO)-enhanced-Long Short-Term Memory (LSTM) and XGBoost modelling techniques. Daily air quality data were collected from the official Seoul Air registry for the period 2021 to 2022. The data were first preprocessed through the ARIMA model to capture and fit the linear part of the data and followed by a hybrid deep learning architecture developed in the pretraining–finetuning framework for the non-linear part of the data. This hybrid model first used convolution to extract the deep features of the original air quality data, and then used the QPSO to optimize the hyperparameter for LSTM network for mining the long-terms time series features, and the XGBoost model was adopted to fine-tune the final AQI prediction model. The robustness and reliability of the resulting model were assessed and compared with other widely used models and across meteorological stations. Our proposed model achieves up to 31.13% reduction in MSE, 19.03% reduction in MAE and 2% improvement in R-squared compared to the best appropriate conventional model, indicating a much stronger magnitude of relationships between predicted and actual values. The overall results show that the attentive hybrid deep Quantum inspired Particle Swarm Optimization model is more feasible and efficient in predicting air quality index at both city-wide and station-specific levels.

Loop diuretics are prevailing drugs to manage fluid overload in heart failure. However, adjusting to loop diuretic doses is strenuous due to the lack of a diuretic guideline. Accordingly, we developed a novel clinician decision support system for adjusting loop diuretics dosage with a Long Short-Term Memory (LSTM) algorithm using time-series EMRs. Weight measurements were used as the target to estimate fluid loss during diuretic therapy. We designed the TSFD-LSTM, a bi-directional LSTM model with an attention mechanism, to forecast weight change 48 h after heart failure patients were injected with loop diuretics. The model utilized 65 variables, including disease conditions, concurrent medications, laboratory results, vital signs, and physical measurements from EMRs. The framework processed four sequences simultaneously as inputs. An ablation study on attention mechanisms and a comparison with the transformer model as a baseline were conducted. The TSFD-LSTM outperformed the other models, achieving 85% predictive accuracy with MAE and MSE values of 0.56 and 1.45, respectively. Thus, the TSFD-LSTM model can aid in personalized loop diuretic treatment and prevent adverse drug events, contributing to improved healthcare efficacy for heart failure patients. [ABSTRACT FROM AUTHOR]

In recent years, the global installed capacity of wind power has grown rapidly. Wind power forecasting, as a key technology in wind turbine systems, has received widespread attention and extensive research. However, existing studies typically focus on the power prediction of individual devices. In the context of multi-turbine scenarios, employing individual models for each device may introduce challenges, encompassing data dilution and a substantial number of model parameters in power generation forecasting tasks. In this paper, a single-model method suitable for multi- device wind power forecasting is proposed. Firstly, this method allocates multidimensional random vectors to each device. Then, it utilizes space embedding techniques to iteratively evolve the random vectors into representative vectors corresponding to each device. Finally, the temporal features are concatenated with the corresponding representative vectors and inputted into the model, enabling the single model to accomplish multi-device wind power forecasting task based on device discrimination. Experimental results demonstrate that our method not only solves the data dilution issue and significantly reduces the number of model parameters but also maintains better predictive performance. Future research could focus on using more interpretable space embedding techniques to observe representation vectors of wind turbine equipment and further explore their semantic features. [ABSTRACT FROM AUTHOR]

This study proposes a hybrid model (Conformer-LSTM) based on Conformer and Long Short-Term Memory networks (LSTM) to overcome the limitations of existing techniques and enhance the accuracy and generalizability of wave height predictions. The model combines the advantages of self-attention mechanisms and convolutional neural networks. It captures global dependencies through multi-head self-attention and utilizes convolutional layers to extract local features, thereby enhancing the model's adaptability to dynamic changes in time series. The LSTM component handles long-term dependencies, optimizing the coherence and stability of predictions. Additionally, an adaptive feature fusion weight network is introduced to further improve the model's recognition and utilization efficiency of key features. Experimental data come from the National Oceanic and Atmospheric Administration buoy data, covering wave height, wind speed, and other data from key maritime areas. Evaluation metrics include Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and Coefficient of Determination (R2), ensuring a comprehensive assessment of model performance. The results show that the Conformer-LSTM model outperforms traditional LSTM, CNN, and CNN-LSTM models at multiple sites, confirming its potential in wave height prediction. [ABSTRACT FROM AUTHOR]

Time series forecasting has played an important role in different industries, including economics, energy, weather, and healthcare. RNN-based methods have shown promising potential due to their strong ability to model the interaction of time and variables. However, they are prone to gradient issues like gradient explosion and vanishing gradients. And the prediction accuracy is not high. To address the above issues, this paper proposes a Fractional-order Lipschitz Recurrent Neural Network with a Frequency-domain Gated Attention mechanism (FLRNN-FGA). There are three major components: the Fractional-order Lipschitz Recurrent Neural Network (FLRNN), frequency module, and gated attention mechanism. In the FLRNN, fractional-order integration is employed to describe the dynamic systems accurately. It can capture long-term dependencies and improve prediction accuracy. Lipschitz weight matrices are applied to alleviate the gradient issues. In the frequency module, temporal data are transformed into the frequency domain by Fourier transform. Frequency domain processing can reduce the computational complexity of the model. In the gated attention mechanism, the gated structure can regulate attention information transmission to reduce the number of model parameters. Extensive experimental results on five real-world benchmark datasets demonstrate the effectiveness of FLRNN-FGA compared with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Transformer-based methods have recently demonstrated their potential in time series forecasting problems. However, the mainstream approach, primarily utilizing attention to model inter-step correlation in the time domain, is constrained by two significant issues that lead to ineffective and inefficient multivariate forecasting. The first is that key representations in the time domain are scattered and sparse, resulting in parameter bloat and increased difficulty in capturing time dependencies. The second is that treating time step points as uniformly embedded tokens leads to the erasure of inter-variate correlations. To address these challenges, we propose a frequency-wise and variables-oriented transformer-based method. This method leverages the intrinsic conjugate symmetry in the frequency domain, enabling compact frequency domain representations that naturally mix information across time points while reducing spatio-temporal costs. Multivariate inter-correlations can also be captured from similar frequency domain components, which enhances the variables-oriented attention mechanism modeling capability. Further, we employ both polar and complex domain perspectives to enrich the frequency domain representations and decode complicated temporal patterns. We propose frequency-enhanced independent representation multi-head attention (FIR-Attention) to leverage these advantages for improved multivariate interaction. Techniques such as cutting-off frequency and equivalent mapping are used to ensure the model's lightweight nature. Extensive experiments on eight mainstream datasets show that our approach achieves first-rate satisfactory results and, importantly, requires only one percent of the spatio-temporal cost of mainstream methods. [ABSTRACT FROM AUTHOR]

The economic time series prediction literature has seen an increase in research leveraging artificial neural networks (ANNs), particularly the multilayer perceptron (MLP) and, more recently, transformer networks. These ANN models have shown superior accuracy compared to traditional techniques such as autoregressive integrated moving average (ARIMA) models. The most recent models in the prediction of this type of neural network, such as recurrent or Transformers models, are composed of complex architectures that require sufficient processing capacity to address the problems, while MLP is based on densely connected layers and supervised learning. A deep understanding of the limitations is necessary to appropriately choose the ideal model for each of the prediction tasks. In this article, we show how a simple architecture such as the MLP allows a better adjustment than other models, including a shorter prediction time. This research is based on the premise that the use of the most recent models will not always allow better results. [ABSTRACT FROM AUTHOR]

Accurate long-term water demand forecasting is beneficial to the sustainable development and management of cities. However, the randomness and nonlinear nature of water demand bring great challenges to accurate long-term water demand forecasting. For accurate long-term water demand forecasting, the models currently in use demand the input of extensive datasets, leading to increased costs for data gathering and higher barriers to entry for predictive projects. This situation underscores the pressing need for an effective forecasting method that can operate with a smaller dataset, making long-term water demand predictions more feasible and economically sensible. This study proposes a framework to delineate and analyze long-term water demand patterns. A forecasting model based on generative adversarial networks and multivariate feature fusion (the water demand forecast-mixer, WDF-mixer) is designed to generate synthetic data, and a gradient constraint is introduced to overcome the problem of overfitting. A multi-feature fusion method based on temporal and channel features is then derived, where a multi-layer perceptron is used to capture temporal dependencies and non-negative matrix decomposition is applied to obtain channel dependencies. After that, an attention layer receives all those features associated with the water demand forecasting, guiding the model to focus on important features and representing correlations across them. Finally, a fully connected network is constructed to improve the modeling efficiency and output the forecasting results. This approach was applied to real-world datasets. Our experimental results on four water demand datasets show that the proposed WDF-mixer model can achieve high forecasting accuracy and robustness. In comparison to the suboptimal models, the method introduced in this study demonstrated a notable enhancement, with a 62.61% reduction in the MSE, a 46.85% decrease in the MAE, and a 69.15% improve in the R 2 score. This research could support decision makers in reducing uncertainty and increasing the quality of water resource planning and management. [ABSTRACT FROM AUTHOR]

Retail demand forecasting is a highly intricate and multilevel problem as it may include numerous products, under multiple categories, and potentially sold in many different stores. Forecasts may also process products in isolation or collectively so as to detect mutual correlations. In technical terms, retail demand forecasting may be broken down to a multivariate time series forecasting problem where the time axis is prevalent and introduces added complexity which necessitates proper usage of advanced methodologies with machine/deep learning backgrounds. Popular boosting regressors, such as XGBoost and LightGBM, are excellent machine learning candidates with extensive bibliographic backgrounds covering multiple scientific fields and applications including generic multivariate time series forecasts. The Temporal Convolutional Network and the Temporal Fusion Transformer are recently proposed deep neural network architectures that found success in specific multivariate scenarios but are yet to be tested in a variety of related fields such as retail demand forecasting. Therefore, within this paper, these novel in-the-field models are compared to the aforementioned boosting approaches alongside popular statistical univariate methods, namely Exponential Smoothing and SARIMA. To properly compare the selected models and attempt to generalize their usability, two separate datasets are analyzed and forecasted; an item sales dataset with 500 time series and a category sales dataset with 540 time series. The findings suggest that the deep learning solutions are the better predictors, with the Transformer model surpassing the Boosting solutions by up to 16.8% sMAPE decrease and the statistical approaches by up to 28.6% decrease, further substantiating the notion that deep learning techniques are exceptionally promising in handling large-scale, non-linear and outlier data whilst suggesting that retail demand forecasting does benefit from multivariate approaches and the application of advanced machine learning methods. [ABSTRACT FROM AUTHOR]

Earth observation imaging technologies, particularly multispectral sensors, produce extensive high-dimensional data over time, thus offering a wealth of information on global dynamics. These data encapsulate crucial information in essential climate variables, such as varying levels of soil moisture and temperature. However, current cutting-edge machine learning models, including deep learning ones, often overlook the treasure trove of multidimensional data, thus analyzing each variable in isolation and losing critical interconnected information. In our study, we enhance conventional convolutional neural network models, specifically those based on the embedded temporal convolutional network framework, thus transforming them into models that inherently understand and interpret multidimensional correlations and dependencies. This transformation involves recasting the existing problem as a generalized case of N-dimensional observation analysis, which is followed by deriving essential forward and backward pass equations through tensor decompositions and compounded convolutions. Consequently, we adapt integral components of established embedded temporal convolutional network models, like encoder and decoder networks, thus enabling them to process 4D spatial time series data that encompass all essential climate variables concurrently. Through the rigorous exploration of diverse model architectures and an extensive evaluation of their forecasting prowess against top-tier methods, we utilize two new, long-term essential climate variables datasets with monthly intervals extending over four decades. Our empirical scrutiny, particularly focusing on soil temperature data, unveils that the innovative high-dimensional embedded temporal convolutional network model-centric approaches markedly excel in forecasting, thus surpassing their low-dimensional counterparts, even under the most challenging conditions characterized by a notable paucity of training data. [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]

This study proposes a new crude oil futures price forecasting model based on Large Language Models. It takes advantage of the modeling capabilities of pretrained transformer models with attention mechanism in the mainstream Large Language Models. Results from empirical studies using INE future price showed that the introduction of LLM to the crude oil futures price forecasting model contributes to the improved forecasting accuracy. The forecasting accuracy of the pretrained transformer based crude oil futures price forecasting model is sensitive to the LLM model types. Llama-2 7b is found to provide the best forecasting accuracy for crude oil futures price forecasting. [ABSTRACT FROM AUTHOR]

Real-life time series datasets exhibit complications that hinder the study of time series forecasting (TSF). These datasets inherently exhibit non-stationarity as their distributions vary over time. Furthermore, the intricate inter- and intra-series relationships among data points pose challenges for modeling. Many existing TSF models overlook one or both of these issues, resulting in inaccurate forecasts. This study proposes a novel TSF model designed to address the challenges posed by real-life data, delivering accurate forecasts in both multivariate and univariate settings. First, we propose methods termed "weak-stationarizing" and "non-stationarity restoring" to mitigate distributional shift. These methods enable the removal and restoration of non-stationary components from individual data points as needed. Second, we utilize the spectral decomposition of weak-stationary time series to extract informative features for forecasting. To learn features from the spectral decomposition of weak-stationary time series, we exploit a mixer architecture to find inter- and intra-series dependencies from the unraveled representation of the overall time series. To ensure the efficacy of our model, we conduct comparative evaluations against state-of-the-art models using six real-world datasets spanning diverse fields. Across each dataset, our model consistently outperforms or yields comparable results to existing models. [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]

Deep learning, a crucial technique for achieving artificial intelligence (AI), has been successfully applied in many fields. The gradual application of the latest architectures of deep learning in the field of time series forecasting (TSF), such as Transformers, has shown excellent performance and results compared to traditional statistical methods. These applications are widely present in academia and in our daily lives, covering many areas including forecasting electricity consumption in power systems, meteorological rainfall, traffic flow, quantitative trading, risk control in finance, sales operations and price predictions for commercial companies, and pandemic prediction in the medical field. Deep learning-based TSF tasks stand out as one of the most valuable AI scenarios for research, playing an important role in explaining complex real-world phenomena. However, deep learning models still face challenges: they need to deal with the challenge of large-scale data in the information age, achieve longer forecasting ranges, reduce excessively high computational complexity, etc. Therefore, novel methods and more effective solutions are essential. In this paper, we review the latest developments in deep learning for TSF. We begin by introducing the recent development trends in the field of TSF and then propose a new taxonomy from the perspective of deep neural network models, comprehensively covering articles published over the past five years. We also organize commonly used experimental evaluation metrics and datasets. Finally, we point out current issues with the existing solutions and suggest promising future directions in the field of deep learning combined with TSF. This paper is the most comprehensive review related to TSF in recent years and will provide a detailed index for researchers in this field and those who are just starting out. [ABSTRACT FROM AUTHOR]

Air pollution poses a significant threat to the health of the environment and human well-being. The air quality index (AQI) is an important measure of air pollution that describes the degree of air pollution and its impact on health. Therefore, accurate and reliable prediction of the AQI is critical but challenging due to the non-linearity and stochastic nature of air particles. This research aims to propose an AQI prediction hybrid deep learning model based on the Attention Convolutional Neural Networks (ACNN), Autoregressive Integrated Moving Average (ARIMA), Quantum Particle Swarm Optimization (QPSO)-enhanced-Long Short-Term Memory (LSTM) and XGBoost modelling techniques. Daily air quality data were collected from the official Seoul Air registry for the period 2021 to 2022. The data were first preprocessed through the ARIMA model to capture and fit the linear part of the data and followed by a hybrid deep learning architecture developed in the pretraining–finetuning framework for the non-linear part of the data. This hybrid model first used convolution to extract the deep features of the original air quality data, and then used the QPSO to optimize the hyperparameter for LSTM network for mining the long-terms time series features, and the XGBoost model was adopted to fine-tune the final AQI prediction model. The robustness and reliability of the resulting model were assessed and compared with other widely used models and across meteorological stations. Our proposed model achieves up to 31.13% reduction in MSE, 19.03% reduction in MAE and 2% improvement in R-squared compared to the best appropriate conventional model, indicating a much stronger magnitude of relationships between predicted and actual values. The overall results show that the attentive hybrid deep Quantum inspired Particle Swarm Optimization model is more feasible and efficient in predicting air quality index at both city-wide and station-specific levels. [ABSTRACT FROM AUTHOR]

Let G = (V,E) be a simple, connected and un-directed graph. We introduce a new notion of rainbow vertex antimagic coloring. This is a natural expansion of rainbow vertex coloring combined with antimagic labeling. For f: E(G) → {1, 2, . . ., |E(G)|}, the weight of a vertex v ∈ V (G) against f is wf (v) = Σe∈E(v)f(e), where E(v) is the set of vertices incident to v. The function f is called vertex antimagic edge labeling if every vertex has distinct weight. A path is considered to be a rainbow path if for each vertex u and v, all internal vertices on the u - v path have different weights. The rainbow vertex antimagic connection number of G, denoted by rvac(G), is the smallest number of colors taken over all rainbow colorings induced by rainbow vertex antimagic labelings of G. In this paper we aim to discover some new lemmas or theorems regarding to rvac(G). Furthermore, to see the robust application of rainbow vertex antimagic coloring, at the end of this paper we will illustrate the implementation of RVAC on spatial temporal graph neural networks (STGNN) multistep time series forecasting on subsidized diesel consumption of some petrol stations. [ABSTRACT FROM AUTHOR]

Copyright of Electric Power Engineering Technology is the property of Editorial Department of Electric Power Engineering Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The geography of the Philippines experiences climate variability thus, providing accurate and timely weather forecasts to the population is crucial. Climate forecasts, which are issued and disseminated by government agencies, serve as essential risk management tools. However, the country faces challenges in forecasting, further exacerbated by climate change. Thus, exploring the use of artificial intelligence has emerged as a strategy to enhance weather prediction accuracy. This research focuses on time series forecasting of rainfall, mean temperature, relative humidity, and wind speed weather data using a machine learning approach. Specifically, it aims to compare and identify the most beneficial forecasting models among autoregressive integrated moving average (ARIMA) boost, Prophet boost, and time series linear model (TSLM). It also seeks to evaluate the performance of these models using mean absolute error (MAE), mean absolute percentage error (MAPE), mean absolute scaled error (MASE), symmetric mean absolute percentage error (SMAPE), root mean squared error (RMSE), and R squared (RSQ) metrics. Results showed that the selection of the forecasting model varies based on the specific parameter under consideration, with no hyperparameter tuning in the analysis. For wind speed, ARIMA boost proves to be a favorable choice. At the same time, TSLM demonstrates effectiveness for relative humidity and mean temperature. Both ARIMA boost and TSLM exhibit strong performance for rainfall. Prophet boost consistently ranks as the least-performing model. [ABSTRACT FROM AUTHOR]

Time series forecasting has been a challenging area in the field of Artificial Intelligence. Various approaches such as linear neural networks, recurrent linear neural networks, Convolutional Neural Networks, and recently transformers have been attempted for the time series forecasting domain. Although transformer-based architectures have been outstanding in the Natural Language Processing domain, especially in autoregressive language modeling, the initial attempts to use transformers in the time series arena have met mixed success. A recent important work indicating simple linear networks outperform transformer-based designs. We investigate this paradox in detail comparing the linear neural network- and transformer-based designs, providing insights into why a certain approach may be better for a particular type of problem. We also improve upon the recently proposed simple linear neural network-based architecture by using dual pipelines with batch normalization and reversible instance normalization. Our enhanced architecture outperforms all existing architectures for time series forecasting on a majority of the popular benchmarks. [ABSTRACT FROM AUTHOR]

In fuzzy time series (FTS) based forecasting models, FTS is utilized to depict the characteristic of time series. In the constructed FTS of the existing models, each moment consists of a fuzzy set to reflect the size range of data and aligns with people's semantic description. However, this FTS ignores some essential fuzzy information, for example the membership degree of data to fuzzy set, and then it fails to describe the feature of time series accurately and limits forecasting performance. To address these issues, ordered pair FTS is proposed in this study. This FTS is consisted of ordered pairs, including two aspects: the fuzzified fuzzy set of data and corresponding membership degree. Worth noting that the ordered pair FTS not only captures the characteristic of data accurately by making use of the information of fuzzy set, but also maintains its interpretability. Following this, ordered pair fuzzy logical relationship (FLR) is derived from antecedent ordered pair(s) to a consequent ordered pair, it describes the association of time series effectively through capturing data information exactly. Based on the ordered pair FLR, a forecasting model is designed. This model applies fuzzy implication to measure the truth degree of FLR and indicate the importance of each fuzzy rule in prediction, ultimately produces reasonable prediction result. The superiorities of the proposed ordered pair FTS and forecasting model are demonstrated in experimental studies, where they are compared with other existing forecasting models. [ABSTRACT FROM AUTHOR]