Time Series Forecasting Research Articles

Time series modelling and forecasting of Monkeypox outbreak trends Africa's in most affected countries

BackgroundThe recent outbreak of Monkeypox (Mpox), particularly the clade 1b variant, have shifted the epidemiological landscape, making it a Public Health Emergency of International Concern. Africa remains a hotspot with significant ongoing outbreaks, necessitating a focused study on outbreak trends and forecasting to guide health interventions. MethodsThis study utilizes a comprehensive dataset from the four most affected African countries, covering weekly and cumulative Mpox cases from August 6, 2023, to August 18, 2024. Time series analysis techniques, including ARIMA models and Join Point Regression, were employed to forecast Mpox trends and analyse the annual percentage change in new cases. ResultsDescriptive statistics highlighted significant variability in Mpox cases across the studied regions with the mean cases in Africa at 72.55 and a high standard deviation of 60.885. Forecasting models suggest a continued increase in Mpox cases, with cumulative cases expected to reach 6922.95 by the 65th week (95 % CI: 6158.62 to 7687.27) and new cases projected at 45.93 (95 % CI: −88.17 to 180.04). ConclusionThe study underscores the persistent nature of Mpox outbreaks in Africa and the critical need for continuous surveillance and adaptive public health strategies. The forecasts generated offer valuable insights into potential future trends, aiding in the allocation of resources and the implementation of targeted health interventions to curb the spread of the disease.

Dengue Prediction using Short-Term Memory

Dengue is a severe infectious disease on the rise in Malaysia, and there is a demand for artificial intelligence to support the health system. However, the application of deep learning, specifically Long Short-Term Memory (LSTM) time series forecasting, has not been explored by many in dengue prediction studies. However, considering the availability of daily weather data being collected, the ability of LSTM to capture long term dependencies can be leveraged in forecasting dengue cases. Therefore, this study investigates the performance and viability of LSTM time series forecasting on predicting dengue cases. An LSTM model is developed and evaluated to be compared to a Support Vector Regression (SVR) model by utilising the availability of a dengue dataset consisting of weather and climate data. The results indicated LSTM time series forecasting performed better than SVR, with R2 and MAE scoring 0.75 and 8.76. In short, LSTM has shown better performance and, in addition, capturing trends in the rise and fall of dengue cases. Altogether, this research could contribute to the fight against the increase of dengue cases without relying on forecasted weather data but instead, history.

High-precision non-contact online measurement and predictive analysis of geometric parameters in large industrial components

Obtaining precise geometric parameters is fundamental in industry but often proves challenging, particularly for large-scale and irregularly shaped industrial components. This study introduces an innovative measurement method enabling precise determination of chord length, arc length, and curvature radius in curved sections of such components, even within dynamic industrial environments. Our solution relies on the implementation of a LiDAR sensor and the utilization of data processing techniques, including outlier detection and removal, as well as customized digital filters. Additionally, we incorporate analytic geometry to address specific measurement challenges. Finally, Machine Learning techniques were applied to forecast time series data of the measurements. The proposed system was validated in a real-world wind turbine tower manufacturing environment, comparing them with manual measurements performed by experienced operators. This validation confirms its effectiveness of our approach, achieving the industry-required minimum tolerances of 5 millimeters, where precise geometric data acquisition is crucial to ensure product quality.

What we can do with one qubit in quantum machine learning: ten classical machine learning problems that can be solved with a single qubit

This work focuses on quantum machine learning and analyzes the power of one single qubit to solve classical machine learning problems. We explore possible strategies to address traditional supervised, unsupervised, and reinforcement learning tasks. In particular, we study binary and multinomial classification, regression problems, time series forecasting, clustering, and quantum reinforcement learning. Our results suggest that the same methodology could be used to address all three types of learning with different measurement strategies and, despite the strong limitation of reduced data dimensionality of the candidate problems, a single qubit can achieve similar or even improved performance with respect to state-of-the-art classic machine learning methods in many cases. As simulating the evolution of one qubit state is computationally efficient, our study enables the possibility to use the qubit model as a candidate solution to implement simple decision-making machine learning models in hardware with extremely low memory resources such as embedded systems or edge devices. The outcomes provided could be also of interest in academia and for the construction of demonstrators using low-scale contemporary quantum hardware.

Cyber Attacks Detection And Mitigation Using Machine Learning In Smart Grid Systems

The increasing complexity and interconnectedness of smart grid systems have heightened their vulnerability to cyber threats, necessitating advanced solutions for securing these critical infrastructures. This study aims to explore the potential of AI-driven predictive analytics in enhancing the cybersecurity and operational efficiency of smart grids. By leveraging the systematic approach of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, a comprehensive review of 1,526 initial articles was conducted, which was subsequently narrowed down through rigorous screening and evaluation to a final set of 127 high-quality studies. The review reveals that machine learning models, such as neural networks and time series forecasting, significantly enhance the early detection and mitigation of cyber threats, allowing grid operators to take proactive measures to safeguard against disruptions. Additionally, the integration of AI with real-time data analytics was found to optimize load forecasting, predict equipment failures, and improve overall grid resilience, leading to reduced downtime and operational costs. However, significant challenges related to data privacy, scalability, and integration with legacy systems persist. The findings suggest that techniques like federated learning and blockchain integration could address these challenges, though further research is needed to enhance model robustness and efficiency. This review provides critical insights into the practical applications of AI in smart grid cybersecurity, highlighting both the benefits and the barriers that must be overcome to achieve widespread adoption.

Predictive Modeling for Bike Rental Demand: Enhancing Operational Efficiency and User Satisfaction in Urban Mobility

This project focuses on developing a predictive model to forecast bike rental demand by analyzing historical rental data, weather information, and temporal variables. The model will employ machine learning techniques, such as regression analysis, time series forecasting, and ensemble methods, to capture the complex relationships between these factors and rental demand.

A deep kernel regression-based forecasting framework for temperature-induced strain in large-span bridges

The strain data from health monitoring systems of large-span bridges is influenced by various load effects, with the extraction and forecasting of temperature-induced strain being particularly significant for precise analysis and early warning of monitoring data. This paper presents a forecasting framework for temperature-induced strain in large-span bridges, employing a deep kernel regression (DKR) approach that integrates deep learning with Bayesian regression to enhance accuracy and certainty. Initially, this paper addresses the influence of additional response increment induced by vehicle strain effects and employs a robust data smoothing algorithm to extract temperature-induced effect components from measured strain data offline. Subsequently, a DKR model is proposed, integrating a long short-term memory (LSTM) layer with a fully connected layer. The output of the deep learning module serves as the kernel function parameter for the Gaussian process regression (GPR) module, and the GPR module with updated hyperparameters is used for time series forecasting. This method effectively extracts and utilizes time series features from historical data alongside key environmental factors, enabling real-time forecasting of strain effects and significantly improving the performance and utility of health monitoring systems in large-span bridges. Compared to commonly used time series forecasting algorithms, the algorithm proposed in this paper exhibits significantly improved accuracy, stability, and certainty. Through comparing the inference time, it was verified that the algorithm can meet the performance requirements of real-time inference, which underscores the model's potential as a robust tool in bridge structural health monitoring.

Forecasting economic growth by combining local linear and standard approaches

Today, developing economies are of major importance for global macroeconomic development. However, the empirical analysis and especially the forecasting of macroeconomic time series remain difficult due to a lack of sufficient data, data frequency, high volatility, and non-linear developments. These difficulties require more sophisticated approaches to obtain reliable forecasts. Therefore, we propose an improved forecasting method especially for growth data based on a data-driven local linear trend estimation with an extended iterative plug-in algorithm for determining the bandwidth endogenously. This approach allows a smooth trend estimation that takes care of temporary changes in trend processes. Further, the naïve random walk model is extended for forecasting by including a local linear, time-varying drift. We apply this method to GDP development for six developing and two advanced economies and compare different forecast combinations. The combinations that include the local linear approach and the random walk with a local linear trend improve forecasting accuracy and reduce variance.

Big Data Analytics for Forecasting Tourism Recovery in Bali Island Using Multivariate Time Series

Bali is a famous tourist area and can significantly contribute to the Indonesian tourism sector. The COVID-19 pandemic has made Indonesian tourism, including Bali tourism, experience a decline. In March 2022, COVID-19 cases decreased, and the government began to relax some policies. The tourism sector is vital in economic recovery efforts after the COVID-19 pandemic. Therefore, it is necessary to identify tourism recovery to determine strategies and policies related to Indonesian tourism, especially in Bali. Multivariate time series forecasting of tourism demand can be used to identify tourism recovery using several significant data sources. The methods used are Vector Autoregressive (VAR), Support Vector Regression (SVR), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU). The data used are the monthly official number of tourists, room occupancy rate, Google Trends, number of booking.com user reviews, and nighttime light intensity in Bali Province from January 2019 to December 2022. The results show that the best forecasting method is VAR, and modeling with multivariate time series forecasting can improve the performance of forecasting results. In addition, big data can be used as a source of supporting data that can provide better forecasting results, and the size of the dataset affects the selection of the best model. Furthermore, the descriptive and forecasting analysis results show that Bali tourism has experienced post-pandemic tourism recovery. The strategies and policies of the Bali government to restore Bali tourism faster are good enough.

Optimizing Currency Circulation Forecasts in Indonesia: A Hybrid Prophet- Long Short Term Memory Model with Hyperparameter Tuning

The core problem for decision-makers lies in selecting an effective forecasting method, particularly when faced with the challenges of nonlinearity and nonstationarity in time series data. To address this, hybrid models are increasingly employed to enhance forecasting accuracy. In Indonesia and other Muslim countries, monthly economic and business time series data often include trends, seasonality, and calendar variations. This study compares the performance of the hybrid Prophet-Long Short-Term Memory (LSTM) model with their individual counterparts to forecast such patterned time series. The aim is to identify the best model through a hybrid approach for forecasting time series data exhibitingtrend, seasonality, and calendar variations, using the real-life case of currency circulation in South Sulawesi. The goodness of the models is evaluated using the smallest Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) values. The results indicate that the hybrid Prophet- LSTM model demonstrates superior accuracy, especially for predicting currency outflow, with lower MAPE and RMSE values than standalone models. The LSTM model shows excellent performance for currency inflow, while the Prophet model lags in inflow and outflow accuracy. This insight is valuable for Bank Indonesia’s strategic planning, aiding in better cash flow prediction and currency stock management.

Forecasting techniques based on the use of time series models for forecasting expenditures on social protection and social security

In the context of a military conflict, it is growing the number of people who are in difficult life circumstances and need state assistance. Therefore, the issue of forecasting spending on social protection and social security is becoming increasingly relevant. The aim of the paper is to consider modern methods of analyzing and forecasting time series and propose their application to determine the need for spending on social protection and social security. The article provides a brief overview of regression models, their advantages and features of use for analyzing and predicting nonlinear and linear processes described by time series of statistical indicators used in the population social protection system. The paper offers a combination of predictions that can be made based on locally linear and nonlinear models, such as threshold autoregression (TAR) and exponential autoregression (ExAR), which have known quality characteristics. This approach primarily concerns time series that contain data on structural changes in the analyzed processes. Using combined predictions, it is possible to estimate the contribution of each component for both different and selected time points using variable weights. To build forecasts, depending on the scenario of distribution of social protection and social security expenditures, it is proposed to use Bayes networks. Their advantages are flexibility, high quality of results, the possibility of structural and parametric optimization and adaptation to new data and conditions, support for quality assessment by appropriate sets of statistical criteria, which makes it possible to analyze thoroughly intermediate and final results. It helps to increase the adequacy of models and the high quality of the final result of their application.

IFNN: Intuitionistic Fuzzy Logic Based Neural Network Model for Time Series Forecasting

IFNN: Intuitionistic Fuzzy Logic Based Neural Network Model for Time Series Forecasting

Temporal characteristics-based adversarial attacks on time series forecasting

Currently, deep learning models have gained significant popularity in time series forecasting within industrial systems due to their high accuracy. However, these models exhibit vulnerability to adversarial attacks, posing significant cost and security risks. Existing attack methods for time series, primarily adapted from those developed for image classifiers, fail to effectively explore the vulnerability of time series forecasting models, since they overlook the distinct characteristics and temporal patterns inherent in time series data. To address this challenge and inspire future research aimed at improving the reliability of time series forecasting models, we identify the goals of adversarial attacks for time series forecasting and propose a novel white-box adversarial attack method named TCA. Specifically, TCA exploits gradient information from the target model, iteratively applies perturbations to the original samples, and constrains these perturbations based on the temporal characteristics. Extensive experiments on multiple DL models and real-world time series datasets reveal the shortcomings of existing attacks for time series forecasting and demonstrate the effectiveness, stealthiness, and rationality of TCA attacks in both untargeted and targeted attack scenarios.

FAITH: Frequency-domain Attention In Two Horizons for time series forecasting

Time Series Forecasting (TSF) plays a crucial role in various sectors, including industrial maintenance, weather prediction, energy management, traffic control, and financial planning. Current deep learning-based predictive models often exhibit significant deviations between their forecasting outcomes and the ground truth because they lack an efficient method to extract both the global frequency-domain information of each variable and the relationships between different variables. To tackle this challenge, we introduce an innovative model—Frequency-domain Attention In Two Horizons (FAITH). FAITH decomposes time series into trend and seasonal components using a multi-scale adaptive decomposition and fusion architecture and processes them separately. It utilizes two modules—the Frequency Channel Feature Extraction Module (FCEM) and the Frequency Temporal Feature Extraction Module (FTEM)—to capture inter-channel relationships at a finer granularity and to extract global temporal information from the frequency domain of different variables. This significantly enhances its ability to handle long-term dependencies and complex patterns. Furthermore, FAITH achieves theoretically linear complexity by modifying the time-frequency domain transformation method, effectively reducing computational costs. Extensive experiments across six benchmarks for long-term forecasting and five benchmarks for short-term forecasting demonstrate that FAITH outperforms existing models in various domains, such as electricity, weather, and traffic. These results validate the effectiveness and superiority of FAITH in both long-term and short-term time series forecasting tasks. Our codes and data are available at https://github.com/LRQ577/FAITH

CAST: An innovative framework for Cross-dimensional Attention Structure in Transformers

Dominant Transformer-based approaches rely solely on attention mechanisms and their variations, primarily emphasizing capturing crucial information within the temporal dimension. For enhanced performance, we introduce a novel architecture for Cross-dimensional Attention Structure in Transformers (CAST), which presents an innovative approach in Transformer-based models, emphasizing attention mechanisms across both temporal and spatial dimensions. The core component of CAST, the cross-dimensional attention structure (CAS), captures dependencies among multivariable time series in both temporal and spatial dimensions. The Static Attention Mechanism (SAM) is incorporated to simplify and enhance multivariate time series forecasting performance. This integration effectively reduces complexity, leading to a more efficient model. CAST demonstrates robust and efficient capabilities in predicting multivariate time series, with the simplicity of SAM broadening its applicability to various tasks. Beyond time series forecasting, CAST also shows promise in CV classification tasks. By integrating CAS into pre-trained image models, CAST facilitates spatiotemporal reasoning. Experimental results highlight the superior performance of CAST in time series forecasting and its competitive edge in CV classification tasks.

Improved stochastic configuration network ensemble methods for time-series forecasting

Stochastic configuration network ensemble (SCNE) learning is an effective method for handling large datasets and reducing the number of input window size adjustments. However, this model faces challenges in effectively capturing the temporal features of time-series datasets and is constrained by certain hyperparameters, leading to longer training times. To address these issues, this paper proposes an improved stochastic configuration network ensemble (ISCNE) algorithm. Firstly, this algorithm retains the end data of the original dataset during the dataset partitioning process, effectively reducing prediction errors. Secondly, the direct ensemble algorithm eliminates redundant hyperparameters in SCNE, simplifying the model construction process. Lastly, the use of an improved normal distribution sampling strategy for input weights and biases, which provides values close to the mean and relatively small, reduces errors and further shortens the training time. The method was tested on 8 benchmark time-series forecasting datasets. Experimental results indicate that, it effectively improves the accuracy of time-series forecasting and model training efficiency while having a more streamlined structure.

A shared multi-scale lightweight convolution generative network for few-shot multivariate time series forecasting

Time series forecasting is an important time series data mining technique. Among them, multivariate time series (MTS) forecasting has received extensive attention in many fields. However, many existing MTS forecasting models usually rely on a large amount of labeled data for model training, and data collection and labeling are difficult in real systems. The insufficient amount of data makes it difficult for the model to fully learn the intrinsic patterns and features of the data, which not only increases the prediction error, but also makes it hard to obtain satisfactory prediction results. To address this challenge, we propose a shared multi-scale lightweight convolution generative (SMLCG) network for few-shot multivariate time series forecasting by using samples generation strategy. The overall goal is to design a shared multi-scale feature generation prediction framework that generates data highly similar to the original sample and enriches the training sample to improve prediction accuracy. Specifically, the MTS is divided into different scales, and the multi-scale feature fusion module is utilized to capture and fuse the MTS information in different spatial dimensions to eliminate the heterogeneity among the data. Then, the key information in the multi-scale features is captured by a lightweight convolution generative network, and the feature weights are dynamically assigned to explore the change information. In addition, a spatio-temporal memory module is designed based on the parameter sharing strategy to capture the spatio-temporal dynamic relationship of sequences by learning the common knowledge in multi-scale features, thus improving the robustness and generalization ability. Through comprehensive experiments on four publicly available datasets and comparisons with other reported models, it is demonstrated that the SMLCG model can efficiently generate approximate samples in the few-shot case and provide excellent prediction results. The architecture of SMLCG serves as a valuable reference for practical solutions to address the few-shot problem in multivariate time series.

ATPAM: Adversarial Temporal Pattern Attention Mechanism

Abstract. Time series forecasting has a large number of applications in daily life, for instance the prediction of stock prices, electricity consumption, exchange rate changes etc. However, the existing time series prediction methods have limitations. The most significant one is that when all the prediction models get the predicted value, a new round of iteration starts after the loss function is calculated with the corresponding real data. This may cause the accumulation of errors, since there is only one loss function to measure the difference between the predicted value and the ground truth, it will make the connection weak and mainly depend on the accuracy of the prediction model. Unfortunately, there are few time series prediction models with high accuracy in reality. To solve the issue, in this paper, we propose a new time series forecasting model Adversarial Temporal Pattern Attention Mechanism (ATPAM), which based on Generative Adversarial Nets (GANs). ATPAM adopts a Temporal Pattern Attention model as the generator to learn time-invariant temporal patterns, and use a discriminator to improve the prediction performance and do auxiliary adversarial training. Extensive experiments on several real-world datasets show the effectiveness of our method.

Rates of Extended Oral Antibiotic Prophylaxis After Primary Total Knee Arthroplasty Among High-Risk and Standard-Risk Patients: 2009 to 2022

IntroductionRecent evidence suggests extended courses of oral antibiotics (EOA) after total hip (THA) and knee (TKA) arthroplasty may reduce the risk of periprosthetic joint infection (PJI) in high-risk patients. EOA rates after THA have risen significantly. However, there is a lack of epidemiologic data on EOA prophylaxis following TKA. Therefore, we investigated national trends in EOA prophylaxis for primary TKA and whether these rates were reflective of changes in patient risk or prescribing practices. MethodsAdult patients undergoing TKA between 2009 and 2022 were identified in a national insurance claims database (Merative Marketscan). EOA was defined as a 7-14 day course of a first-generation cephalosporin, cefdinir, clindamycin, doxycycline, or trimethoprim-sulfamethoxazole filled between 5 days preoperatively to 3 days postoperatively. Annual EOA rates were calculated and stratified by preoperative PJI risk. Multivariable logistic regression was used to explore whether rates reflected changing patient characteristics. Future rates were predicted with time-series forecasting. ResultsWe identified 712,212 eligible TKA cases. EOA rates rose from 0.91% in 2009 to 7.95% in 2022. Rates increased by 686% among standard-risk patients and 786% among high-risk patients. Logistic regression models using patient comorbidities could not account for changes in EOA rates. EOA rates were projected to rise to 18.3% (CF: 7.5-29.0%) by 2030. ConclusionRates of EOA prophylaxis after TKA rose significantly from 2009 to 2022. This trend could not be explained by changing patient characteristics, suggesting widespread changes in antibiotic prescribing practices, which may be reflective of recent studies favoring EOA use. There is a need for further high-quality research examining the safety, efficacy, and role of EOA prophylaxis in the primary TKA patient population.

Forecast of consumption of natural gas in U.S. based on time series analysis and ARIMA model

Natural gas is a widely used fossil fuel, playing a vital role in both industrial and economic sectors. As a widely used fossil fuel, the prediction of natural gas consumption is crucial for industrial and economics and hence many scholars have been researched on the topic. Due to the weather variation and the sensitivity of industrial demand, a precise consumption forecast is difficult. In the article, ARIMA model, a widely used model in time series analysis and forecasts would be considered in the prediction for consumption for future one year. It turns out that, in the next year, the consumption of natural gas in the coming year is stable and will stay at a still level and the overall trend of the series is increasing, with no significant short-term fluctuations. Therefore, the article suggested that long-term investment in industries related to natural gas is recommended. Besides, short-term investment is not suggested compared to the long-term due to the still level of the consumption within one year.