Previous Time Series Research Articles

One-step ahead short-term hourly global solar radiation forecasting with a dynamical system based on classification of days

The data-driven method is a common approach to solar irradiation prediction. However, its weakness is that it is highly dependent on the characteristics of the prior data, which leads to a lag delay in forecasting. Therefore, this paper proposes a prediction model that considers data-driven, data-cycle variations, and statistical information for solving such problems. Firstly, the periodicity of the data is removed using the Fourier transform. Secondly, monthly daily characterization matrices are constructed to predict from a global perspective without including information from previous time series. Finally, the coupled autoregressive and dynamical system (CARDS) model is improved using the identity matrix. Comparing the model proposed in this paper with seven other popular prediction models, the error can be reduced by 30.2 % on average at four locations in the northern and southern hemispheres. Moreover, the proposed model does not increase the computational burden of existing models.

Impact of Long-Term Drought on Surface Water and Water Balance Variations in Iran: Insights from Highland and Lowland Regions

Droughts have a significant impact on surface water resources, especially in arid and semi-arid regions. Computational and data handling limitations have constrained previous time-series analyses. However, advances in cloud computing services and remote sensing technology allow for a more detailed examination. This study integrates multi-source satellite-derived data with a cloud computing platform to assess the impact of long-term drought on surface water and water balance in Iran from 2000 to 2021. Given the varying effects of drought on highlands and lowlands, the analysis was conducted at three levels: the entire country, the highlands, and the lowlands. The results of this study reveal imbalances between water balance from 2000 to 2021, with notable disparities observed during 2000–2007, 2009–2014, and 2016–2019. The results also show varying drought trends (e.g., −1.22 in 2000 and −0.73 in 2021), with severe conditions captured in 2008 (SPI: −1.92). Additionally, our analysis illustrated that lowlands were more impacted by droughts compared to highlands. Long-term drought and permanent surface water had correlation values of 0.33 across the country, 0.33 in the highlands, and 0.31 in the lowlands. For seasonal surface water, coefficients were 0.18 for the entire country, 0.16 for the highlands, and 0.18 for the lowlands. Overall, long-term drought had minimal effect on reducing surface water. These findings show that drought is only part of the explanation for the decrease in surface water resources.

ADAPTATION OF THE ALGORITHM FOR DETECTING ANOMALIES IN TIME SERIES FOR NON-STATIONARY STREAMING DATA

Detection of anomalies in streaming time series data has become an important research topic due to the wide range of possible applications, including the detection of extreme weather conditions, malicious attacks on protected facilities, monitoring unauthorised gas and oil leaks, illegal pipeline connections, power cable faults, and water and other environmental pollution. Rapid detection of abnormal conditions and identifying these critical events is essential to protect lives and assets. Therefore, developing appropriate systems and detection methods is an urgent task. Anomaly detection in streaming data is challenging due to its large volume and high speed, presence of noise, and non-stationarity of the signal (or ‘concept drift’). The latter significantly complicates the identification of differences between new ‘typical’ behaviour and abnormal events. Solving this problem requires the algorithm for processing such data to learn and adapt to changing conditions. The paper proposes a modification of the algorithm for detecting anomalies in time series. This algorithm provides early detection of abnormal series in a massive collection of non-stationary streaming time series data. Anomalies are observations that are highly improbable given the previous time series values. The proposed approach is based on the primary detection of the predictive limit for the typical system behaviour using the theory of extreme values, followed by checking for the abnormality of the following series using the sliding window technique. The time series parameters are used as input data and compared by density distribution to detect any significant changes in the distribution of the characteristics. It allows the decision-making model to automatically adapt to the changing environment according to detected changes. Since anomalies are, by definition, exceptions to the typical behaviour of a system, most of the available stored data should reflect that typical behaviour of the system in question. It is unnecessary to have representative samples of all possible types of the standard behaviour of a given system for the algorithm to work well. The basic idea is to have a warm-up data set to obtain initial values for the decision model parameters. It makes it possible to determine if there is any significant difference between the last typical behaviour and the new typical behaviour. The proposed algorithm demonstrates its performance under conditions of noisy non-stationary data in several time series classes. Keywords: concept drift, extreme value theory, multivariate time series, outlier detection.

County-level intensity of carbon emissions from crop farming in China during 2000–2019

Agriculture is an important contributor to global carbon emissions. With the implementation of the Sustainable Development Goals of the United Nations and China’s carbon neutral strategy, accurate estimation of carbon emissions from crop farming is essential to reduce agricultural carbon emissions and promote sustainable food production systems in China. However, previous long-term time series estimates in China have mainly focused on the national and provincial levels, which are insufficient to characterize regional heterogeneity. Here, we selected the county-level administrative district as the basic geographical unit and then generated a county-level dataset on the intensity of carbon emissions from crop farming in China during 2000–2019, using random forest regression with multi-source data. This dataset can be used to delineate spatio-temporal changes in carbon emissions from crop farming in China, providing an important basis for decision makers and researchers to design agricultural carbon reduction strategies in China.

Implementing lee's model to apply fuzzy time series in forecasting bitcoin price

Over time, cryptocurrencies like Bitcoin have attracted investor's and speculators' interest. Bitcoin's dramatic rise in value in recent years has caught the attention of many who see it as a promising investment asset. After all, Bitcoin investment is inseparable from Bitcoin price volatility that investors must mitigate. This research aims to use Lee's Fuzzy Time Series approach to forecast the price of Bitcoin. A time series analysis method called Lee's Fuzzy Time Series to get around ambiguity and uncertainty in time series data. Ching-Cheng Lee first introduced this approach in his research on time series prediction. This method is a development of several previous fuzzy time series (FTS) models, namely Song and Chissom and Cheng and Chen. According to most previous studies, Lee's model was stated to be able to convey more precise forecasting results than the classic model from the FTS. This study used first and second orders, where researchers obtained error values from the first order of 5.419% and the second order of 4.042%, which means that the forecasting results are excellent. But of both orders, only the first order can be used to predict the next period's Bitcoin price. In the second order, the resulting relations in the next period do not have groups in their fuzzy logical relationship group (FLRG), so they can not predict the price in the next period. This study contributes to considering investors and the general public as a factor in keeping, selling, or purchasing cryptocurrencies.

Implementing lee's model to apply fuzzy time series in forecasting bitcoin price

Over time, cryptocurrencies like Bitcoin have attracted investor's and speculators' interest. Bitcoin's dramatic rise in value in recent years has caught the attention of many who see it as a promising investment asset. After all, Bitcoin investment is inseparable from Bitcoin price volatility that investors must mitigate. This research aims to use Lee's Fuzzy Time Series approach to forecast the price of Bitcoin. A time series analysis method called Lee's Fuzzy Time Series to get around ambiguity and uncertainty in time series data. Ching-Cheng Lee first introduced this approach in his research on time series prediction. This method is a development of several previous fuzzy time series (FTS) models, namely Song and Chissom and Cheng and Chen. According to most previous studies, Lee's model was stated to be able to convey more precise forecasting results than the classic model from the FTS. This study used first and second orders, where researchers obtained error values from the first order of 5.419% and the second order of 4.042%, which means that the forecasting results are excellent. But of both orders, only the first order can be used to predict the next period's Bitcoin price. In the second order, the resulting relations in the next period do not have groups in their fuzzy logical relationship group (FLRG), so they can not predict the price in the next period. This study contributes to considering investors and the general public as a factor in keeping, selling, or purchasing cryptocurrencies.

TIME SERIES OF SURFACE WATER DISSOLVED INORGANIC CARBON ISOTOPES FROM THE SOUTHERN CALIFORNIA BIGHT

ABSTRACT Dissolved inorganic carbon (DIC) in ocean water is a major sink of fossil fuel derived CO2. Carbon isotopes in DIC serve as tracers for oceanic water masses, biogeochemical processes, and air-sea gas exchange. We present a timeseries of surface DIC δ13C and Δ14C values from 2011 to 2022 from Newport Beach, California. This is a continuation of previous timeseries (Hinger et al. 2010; Santos et al. 2011) that together provide an 18-year record. These data show that DIC Δ14C values have declined by 42‰ and that DIC δ13C values have declined by 0.4‰ since 2004. By 2020, DIC Δ14C values were within analytical error of nearby clean atmospheric CO2 Δ14C values. These long-term trends are likely the result of significant fossil fuel derived CO2 in surface DIC from air-sea gas exchange. Seasonally, Δ14C values varied by 3.4‰ between 2011 and 2022, where seasonal δ13C values varied by 0.7‰. The seasonal variation in Δ14C values is likely driven by variations in upwelling, surface eddies, and mixed layer depth. The variation in δ13C values appears to be driven by isotopic fractionation from marine primary producers. The DIC δ13C and Δ14C values record the influence of the drought that began in 2012, and a major upwelling event in 2016.

Pattern-based prediction of population outbreaks

The complexity and practical importance of insect outbreaks have made the problem of predicting outbreaks a focus of recent research. We propose the Pattern-Based Prediction (PBP) method for predicting population outbreaks. It uses information on previous time series values that precede an outbreak event as predictors of future outbreaks, which can be helpful when monitoring pest species. We illustrate the methodology using simulated datasets and an aphid time series obtained in wheat crops in Southern Brazil. We obtained an average test accuracy of 84.6% in the simulation studies implemented with stochastic models and 95.0% for predicting outbreaks using a time series of aphids in wheat crops in Southern Brazil. Our results show the PBP method's feasibility in predicting population outbreaks. We benchmarked our results against established state-of-the-art machine learning methods: Support Vector Machines, Deep Neural Networks, Long Short Term Memory and Random Forests. The PBP method yielded a competitive performance associated with higher true-positive rates in most comparisons while providing interpretability rather than being a black-box method. It is an improvement over current state-of-the-art machine learning tools, especially by non-specialists, such as ecologists aiming to use a quantitative approach for pest monitoring. We provide the implemented PBP method in Python through the pypbp package.

Correction of nonstationary tidal prediction using deep-learning neural network models in tidal estuaries and rivers

An operational tidal prediction method based on a combination of nonstationary harmonic analysis and deep-learning neural network models is described. Nonstationary harmonic analysis (NSHA), which was based on classical harmonic analysis (CHA), has been developed for tidal forecasting in tidal rivers and estuaries. However, the prediction accuracy is poor when the discharge grows very large or changes abruptly. Therefore, in this study, we aimed to combine nonstationary harmonic analysis with a deep-learning neural network model to improve tidal forecasts in tidal rivers and estuaries. The long short-term memory (LSTM) neural network model, which works well for processing long-term time series data, was chosen to correct the errors from NSHA. In addition, the traditional feed-forward neural network (FFNN) model was also applied and compared with LSTM to determine and optimize the structure of the neural network. Through experiments, the results showed that a two-layer network with a fully connected layer on top of an LSTM layer that uses discharge in addition to the previous time series as input data exhibited the best performance in predicting the errors of the NS_TIDE model. After correction by the proposed model at three stations on the West River, a branch river of the Pearl River, the root mean square error (RMSE) at 24 h by the NS_TIDE model can be reduced from approximately 0.3 m to less than 0.1 m. More specifically, the results indicated a significant improvement for extremely high-level prediction, which is crucial for water conservancy administrations. Finally, optimization approaches of the neural network to prevent overfitting and improve efficiency are also discussed.

Cognitive Video Surveillance Management in Hierarchical Edge Computing System with Long Short-Term Memory Model.

Nowadays, deep learning (DL)-based video surveillance services are widely used in smart cities because of their ability to accurately identify and track objects, such as vehicles and pedestrians, in real time. This allows a more efficient traffic management and improved public safety. However, DL-based video surveillance services that require object movement and motion tracking (e.g., for detecting abnormal object behaviors) can consume a substantial amount of computing and memory capacity, such as (i) GPU computing resources for model inference and (ii) GPU memory resources for model loading. This paper presents a novel cognitive video surveillance management with long short-term memory (LSTM) model, denoted as the CogVSM framework. We consider DL-based video surveillance services in a hierarchical edge computing system. The proposed CogVSM forecasts object appearance patterns and smooths out the forecast results needed for an adaptive model release. Here, we aim to reduce standby GPU memory by model release while avoiding unnecessary model reloads for a sudden object appearance. CogVSM hinges on an LSTM-based deep learning architecture explicitly designed for future object appearance pattern prediction by training previous time-series patterns to achieve these objectives. By referring to the result of the LSTM-based prediction, the proposed framework controls the threshold time value in a dynamic manner by using an exponential weighted moving average (EWMA) technique. Comparative evaluations on both simulated and real-world measurement data on the commercial edge devices prove that the LSTM-based model in the CogVSM can achieve a high predictive accuracy, i.e., a root-mean-square error metric of 0.795. In addition, the suggested framework utilizes up to 32.1% less GPU memory than the baseline and 8.9% less than previous work.

A machine learning-based model for the next 3-day geomagnetic index (Kp) forecast

The 3-day Kp forecast product is important and necessary for space weather forecasts. There is some essential information that can be obtained from the 3-day Kp forecast product, such as the start time of the geomagnetic storm, the maximum storm level, and the storm duration. In this study, we aimed to predict the next 3-day Kp index based on the previous Kp time series and SDO/AIA 193 Å images. We prepared datasets from May 2010 to December 2019 for training and datasets from January 2020 to October 2022 for testing. The similarity parameters of the previous and current geomagnetic conditions between the samples are calculated and analyzed. We assumed that the paired samples with high-similarity parameters of the previous and current geomagnetic conditions would also have high-similarity parameters of the next 3-day geomagnetic conditions. Based on the assumption, we selected the three best similarity parameters through the feature selection process and adopted the scalable tree boosting system (XGBoost) to develop a prediction model. It took the similarity parameters of the previous and current geomagnetic conditions as input and provided the best match sample from the training subset as a forecast. For the next 3-day non-storm (maximum Kp < 5) prediction period, our model reached an F1-score of 0.96. For the next 3-day storm (maximum Kp ≥ 5) prediction period, our model reached an F1-score of 0.82, a recall of 0.70, and a precision of 0.98.

A Real-Time C-V2X Beamforming Selector Based on Effective Sequence to Sequence Prediction Model Using Transitional Matrix Hard Attention

For C-V2X systems, the selection of the best beam in a real-time mode becomes an increasingly critical and yet open topic. Most of the existing approaches adopt either conventional ARIMA or ANN. Recently, there has been research on adopting sequence-to-sequence (Seq2Seq) predictors with attentions to extract time series features and emphasis on critical information to achieve data prediction. In this paper, a Seq2Seq predictor integrating with a Transitional Matrix based Hard attention is presented and validated through an artificial test dataset with predefined transitional states. At first, the transition probability matrix is generated from previous time series data and fed into the “hard” attention module of Seq2Seq predictor to determine the weights during the training phase. Secondly, the presented Seq2Seq predictor was implemented and adopted to predict the best beams of a C-V2X beamforming selector built up by the authors. Experiments were conducted and captured data were used to validate the performance of the predictor. When compared with baseline models, the presented predictor can achieve an enhanced prediction accuracy in a gain of 10-12%.

A Time Series Model Based on Deep Learning and Integrated Indicator Selection Method for Forecasting Stock Prices and Evaluating Trading Profits

A stock forecasting and trading system is a complex information system because a stock trading system needs to be analyzed and modeled using data science, machine learning, and artificial intelligence. Previous time series models have been widely used to forecast stock prices, but due to several shortcomings, these models cannot apply all available information to make a forecast. The relationship between stock prices and related factors is nonlinear and involves nonstationary fluctuations, and accurately forecasting stock prices is not an easy task. Therefore, this study used support vector machines (linear and radial basis functions), gene expression programming, multilayer perceptron regression, and generalized regression neural networks to calculate the importance of indicators. We then integrated the five indicator selection methods to find the key indicators. Next, we used long short-term memory (LSTM) and gated recurrent units (GRU) to build time series models for forecasting stock prices and compare them with the listing models. To evaluate the effectiveness of the proposed model, we collected six different stock market data from 2011 to 2019 to evaluate their forecast performance based on RMSE and MAPE metrics. It is worth mentioning that this study proposes two trading policies to evaluate trading profits and compare them with the listing methods, and their profits are pretty good to investors. After the experiments, the proposed time series model (GRU/LSTM combined with the selected key indicators) exhibits better forecast ability in fluctuating and non-fluctuating environments than the listing models, thus presenting an effective reference for stakeholders.

Angular disturbance prediction for countermeasure launcher in active protection system of moving armored vehicle based on an ensemble learning method

The active protection system (APS), usually installed on the turret of armored vehicles, can significantly improve the vehicles’ survivability on the battlefield by launching countermeasure munitions to actively intercept incoming threats. However, uncertainty over the launch angle of the countermeasure is increased due to angular disturbances when the off-road armored vehicle is moving over rough terrain. Therefore, accurate and comprehensive angular disturbance prediction is essential to the real-time monitoring of the countermeasure launch angle. In this paper, a deep ensemble learning (DEL)-based approach is proposed to predict the angular disturbances of the countermeasure launcher in the APS based on previous time-series information. In view of the intricate temporal attribute of angular disturbance prediction, the sampling information of historical time series measured by an inertial navigation device is adopted as the input of the developed DEL model. Then, the recursive multi-step (RMS) prediction strategy and multi-output (MO) prediction strategy are combined with the DEL model to perform the final angular disturbance prediction for the countermeasure launcher in the APS of a moving armored vehicle. The proposed DEL model is validated by using the different datasets from real experiments. The results reveal that this approach can be used to accurately predict angular disturbances, with the maximum absolute error of each DOF less than 0.1°.

Covid19 Information Management and Services App

Abstract: The Corona Virus Disease popularized as COVID-19 is a highly transmissible viral infection and has severe impact on global health. It has impacted the global economy also very badly. To overcome it many vaccines were introduced but the distribution and handling of such information has become necessary to provide a user-friendly interface for the layman in India. The project attempts to address such a problem. Furthermore, the application uses a machine learning model to detect the next number of cases based on the previous data time series data. Although the prediction is based on the time series data it provides a real-world hint into the number of cases. The algorithm is based on a hybrid regression model on top of support vector machines, Polynomial regression, Bayesian Ridge regression. The final predicted cases are presented on the dashboard in a linear graph.

A general framework for spatial GARCH models

In time-series analysis, particularly in finance, generalized autoregressive conditional heteroscedasticity (GARCH) models are widely applied statistical tools for modelling volatility clusters (i.e., periods of increased or decreased risk). In contrast, it has not been considered to be of critical importance until now to model spatial dependence in the conditional second moments. Only a few models have been proposed for modelling local clusters of increased risks. In this paper, we introduce a novel spatial GARCH process in a unified spatial and spatiotemporal GARCH framework, which also covers all previously proposed spatial ARCH models, exponential spatial GARCH, and time-series GARCH models. In contrast to previous spatiotemporal and time series models, this spatial GARCH allows for instantaneous spill-overs across all spatial units. For this common modelling framework, estimators are derived based on a non-linear least-squares approach. Eventually, the use of the model is demonstrated by a Monte Carlo simulation study and by an empirical example that focuses on real estate prices from 1995 to 2014 across the postal code areas of Berlin. A spatial autoregressive model is applied to the data to illustrate how locally varying model uncertainties (e.g., due to latent regressors) can be captured by the spatial GARCH-type models.

Adaptive Industrial Control System Attack Sample Expansion Algorithm Based on Generative Adversarial Network

The scarcity of attack samples is the bottleneck problem of anomaly detection of underlying business data in the industrial control system. Predecessors have done a lot of research on temporal data generation, but most of them are not suitable for industrial control attack sample generation. The change patterns of the characteristics of the underlying business data attack samples can be divided into three types: oscillation type, step type, and pulse type. This paper proposes an adaptive industrial control attack sample expansion algorithm based on GAN, which expands the three types of features in different ways. The basic network structure of data expansion adopts GAN. According to the characteristics of oscillation type changes, momentum is selected as the optimizer. Aiming at the characteristics of step type changes, the Adam optimization method is improved. For pulse type features, attack samples are generated according to the location and length of the pulse. Compared with previous time-series data generation methods, this method is more targeted for each feature and has higher similarities.

STC‐IDS: Spatial–temporal correlation feature analyzing based intrusion detection system for intelligent connected vehicles

Intrusion detection is an important defensive measure for automotive communications security. Accurate frame detection models assist vehicles to avoid malicious attacks. Uncertainty and diversity regarding attack methods make this task challenging. However, the existing works have the limitation of only considering local features or the weak feature mapping of multi-features. To address these limitations, we present a novel model for automotive intrusion detection by spatial-temporal correlation features of in-vehicle communication traffic (STC-IDS). Specifically, the proposed model exploits an encoding-detection architecture. In the encoder part, spatial and temporal relations are encoded simultaneously. To strengthen the relationship between features, the attention-based convolutional network still captures spatial and channel features to increase the receptive field, while attention-LSTM builds meaningful relationships from previous time series or crucial bytes. The encoded information is then passed to detector for generating forceful spatial-temporal attention features and enabling anomaly classification. In particular, single-frame and multi-frame models are constructed to present different advantages respectively. Under automatic hyper-parameter selection based on Bayesian optimization, the model is trained to attain the best performance. Extensive empirical studies based on a real-world vehicle attack dataset demonstrate that STC-IDS has outperformed baseline methods and obtains fewer false-alarm rates while maintaining efficiency.

Taxi Demand Prediction using ML

Abstract: Taxi plays a crucial role in transportation especially in urban areas.Predicting the future demand for taxis in particular geographical location will greatly help internet based transportation companies like Ola, Uber etc. So that we can drastically decrease the waiting time of customers/passengers and also it helps taxi drivers to move to particular location where demand is high eventually making passengers,drivers and companies happy. In this Project we like to predict the demand for taxi in particular location for next 10 min using previous time series data .we want to perform this task of regression using machine learning models with high accuracy and then we would like to apply deep learning models and compare the results.we like to propose the best suited and high accuracy model for the problem.It will greatly help companies in managing the taxi fleet in cities.

A real-time prediction method for tunnel boring machine cutter-head torque using bidirectional long short-term memory networks optimized by multi-algorithm

Based on data from the Jilin Water Diversion Tunnels from the Songhua River (China), an improved and real-time prediction method optimized by multi-algorithm for tunnel boring machine (TBM) cutter-head torque is presented. Firstly, a function excluding invalid and abnormal data is established to distinguish TBM operating state, and a feature selection method based on the SelectKBest algorithm is proposed. Accordingly, ten features that are most closely related to the cutter-head torque are selected as input variables, which, in descending order of influence, include the sum of motor torque, cutter-head power, sum of motor power, sum of motor current, advance rate, cutter-head pressure, total thrust force, penetration rate, cutter-head rotational velocity, and field penetration index. Secondly, a real-time cutter-head torque prediction model's structure is developed, based on the bidirectional long short-term memory (BLSTM) network integrating the dropout algorithm to prevent overfitting. Then, an algorithm to optimize hyperparameters of model based on Bayesian and cross-validation is proposed. Early stopping and checkpoint algorithms are integrated to optimize the training process. Finally, a BLSTM-based real-time cutter-head torque prediction model is developed, which fully utilizes the previous time-series tunneling information. The mean absolute percentage error ( MAPE ) of the model in the verification section is 7.3%, implying that the presented model is suitable for real-time cutter-head torque prediction. Furthermore, an incremental learning method based on the above base model is introduced to improve the adaptability of the model during the TBM tunneling. Comparison of the prediction performance between the base and incremental learning models in the same tunneling section shows that: (1) the MAPE of the predicted results of the BLSTM-based real-time cutter-head torque prediction model remains below 10%, and both the coefficient of determination ( R 2 ) and correlation coefficient ( r ) between measured and predicted values exceed 0.95; and (2) the incremental learning method is suitable for real-time cutter-head torque prediction and can effectively improve the prediction accuracy and generalization capacity of the model during the excavation process. • A torque prediction model based on BLSTM and multi-algorithm fusion is developed. • The Dropout algorithm is integrated to prevent overfitting. • Bayesian and Cross-Validation based hyperparameter optimization method is presented. • EarlyStopping and ModelCheckPoint are integrated to optimize the training process. • An incremental learning method is proposed to improve the model's adaptability.