Characteristics Of Time Series Research Articles

ImputeVIS: An Interactive Evaluator to Benchmark Imputation Techniques for Time Series Data

With the emergence of The Internet of Things (IoT), smart sensors have become abundant in our daily lives. Failures are very common in those devices, leaving the recorded time series with missing blocks of consecutive values. A cottage industry of imputation algorithms exists, each with different performance tradeoffs. The diversity in time series features, missingness patterns, and algorithms' categories makes it challenging to select the best algorithm. In this demonstration, we showcase ImputeVIS, an analytical tool for benchmarking imputation algorithms. ImputeVIS provides an optimal configuration of those algorithms by implementing various AutoML parameterization strategies. Moreover, it uncovers the behavior of imputation algorithms by explaining the interplay between time series features and the imputation results. Its interactive web browser interface allows users to simulate real-world sensor malfunctions by contaminating time series with different missing block scenarios, deploy their imputation algorithms, and compare them against various popular imputation families.

Nonlinearity in affect dynamics persists after accounting for the valence of daily-life events.

In recent years, increased attention has gone to studying nonlinear characteristics of affective time series. An example of such nonlinear features is multimodality-the presence of more than one mode in an affective time series-which might mark the presence of discrete-like transitions between one and another affective state. In an attempt to capture these nonlinear features, Loossens et al. (2020) proposed the Affective Ising Model (AIM) as a model of affect dynamics. This model was validated on daily-life data, but these data did not contain any information on potential environmental factors that might have influenced a participant's affective state. Unfortunately, this omission may have led to erroneously concluding that nonlinearity is a defining characteristic of the affective system, even when it is solely driven by extrinsic influences. To accommodate this limitation, we applied the AIM on daily-life data in which the valence of such external events was measured. Overall, we found that nonlinearity persisted after accounting for the valence of daily-life events, suggesting that nonlinearity is a defining characteristic of affect and should thus be accounted for. Interestingly, this effect was more pronounced for composite compared to single-item measures of affect. While in line with previous research, these results should be replicated in a larger, more representative sample. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

An endogenous evolution mechanism model of asset prices based on time-varying risk aversion coefficient

In the traditional heterogeneous agent model, investors are assumed to be risk averse, and the wealth expected utility function maximization principle is used to form the optimal asset quantity demand. In such models, the risk aversion coefficient of investors is often assumed to be constant. This paper considers that the risk aversion coefficient of investors is time-varying and changes with the change of wealth, and establishes an endogenous evolutionary mechanism model formed by fundamental analysts, technical analysts, and market makers. Compared with the fixed risk aversion coefficient model, this paper analyzes the investor’s behavior, the interaction between investor behaviors, and the influence of different types of investors on the stability of the market. At the same time, we test asset price and asset behavior and conclude that investor behavior affects the stability of the system model. The numerical simulation of the corresponding stochastic model shows that the model can simulate the basic characteristics of financial time series, such as the partial peak and thick tail of asset return series, and the long memory of fluctuations.

Multi-scale hierarchical model for long-term time series forecasting

Long-term time series forecasting (LTSF) has become an urgent requirement in many applications, such as wind power supply planning. This is a highly challenging task because it requires considering both the complex frequency-domain and time-domain information in long-term time series simultaneously. However, existing work only considers potential patterns in a single domain (e.g., time or frequency domain), whereas a large amount of time-frequency domain information exists in real-world LTSFs. In this paper, we propose a multi-scale hierarchical network (MHNet) based on time-frequency decomposition to solve the above problem. MHNet first introduces a multi-scale hierarchical representation, extracting and learning features of time series in the time domain, and gradually builds up a global understanding and representation of the time series at different time scales, enabling the model to process time series over lengthy periods of time with lower computational complexity. Then, the robustness to noise is enhanced by employing a transformer that leverages frequency-enhanced decomposition to model global dependencies and integrates attention mechanisms in the frequency domain. Meanwhile, forecasting accuracy is further improved by designing a periodic trend decomposition module for multiple decompositions to reduce input-output fluctuations. Experiments on five real benchmark datasets show that the forecasting accuracy and computational efficiency of MHNet outperform state-of-the-art methods.

SEER: An End-to-End Toolkit for Benchmarking Time Series Database Systems in Monitoring Applications

Time series database systems (TSDBs) are prevalent in many applications ranging from monitoring and IoT devices to scientific research. Those systems are specifically designed to efficiently manage data indexed by time. Because of the variety of workloads, the diversity of time series features, and the sophistication of existing TSDBs, there is no clear way to pick the most suitable system. In this demo, we introduce SEER, an automated, configurable, and interactive toolkit to evaluate TSDBs. SEER is based on TSM-Bench, a benchmark tailored for time series database systems used in monitoring applications. It implements an end-to-end pipeline for database benchmarking from data generation and feature contamination to workload evaluation. Users can define their portfolios by configuring and parameterizing custom queries, specifying their frequencies, controlling the type and level of data features, and indicating the type of workloads. Moreover, they can deploy new systems and/or reconfigure the pre-installed ones. SEER would process users' requests and gracefully recommend the best system on a use-case basis.

Advanced fluid prediction using interpretable spatio-temporal network and sHapley additive exPlanations through well logging data

In the realm of oil and gas exploration, accurately predicting subsurface fluid types is crucial. Traditional techniques such as core sampling, x-ray diffraction, and x-ray fluorescence, despite providing essential data, are hampered by high costs, time consumption, or limited applications. This paper introduces an interpretable spatiotemporal deep learning network, ISTNet, utilizing well log data to predict fluid types. The framework enhances prediction accuracy and model robustness through a dual-branch design integrating spatial and temporal branches. The spatial branch employs graph neural networks to capture spatial features of well log data, while the temporal branch analyzes time series features using bidirectional long short-term memory networks (BiLSTM). Additionally, ISTNet incorporates the SHapley Additive exPlanations (SHAP) model to augment the interpretability of predictions. Empirical studies in the Tarim Basin demonstrated that ISTNet outperforms seven other advanced models, achieving an average accuracy exceeding 97% on datasets from two distinct wells. ISTNet not only improves the accuracy and robustness of fluid predictions in oil and gas exploration but also enhances transparency and interpretability through the SHAP model, providing geologists and engineers with tools to deeply understand subsurface geological processes and refine exploration and development strategies.

Integrative approach to pedobarography and pelvis-trunk motion for knee osteoarthritis detection and exploration of non-radiographic rehabilitation monitoring.

Osteoarthritis (OA) is a highly prevalent global musculoskeletal disorder, and knee OA (KOA) accounts for four-fifths of the cases worldwide. It is a degenerative disorder that greatly affects the quality of life. Thus, it is managed through different methods, such as weight loss, physical therapy, and knee arthroplasty. Physical therapy aims to strengthen the knee periarticular muscles to improve joint stability. Pedobarographic data and pelvis and trunk motion of 56 adults are recorded. Among them, 28 subjects were healthy, and 28 subjects were suffering from varying degrees of KOA. Age, sex, BMI, and the recorded variables are used together to identify subjects with KOA using machine learning (ML) models, namely, logistic regression, SVM, decision tree, and random forest. Surface electromyography (sEMG) signals are also recorded bilaterally from two muscles, the rectus femoris and biceps femoris caput longus, bilaterally during various activities for two healthy and six KOA subjects. Cluster analysis is then performed using the principal components obtained from time-series features, frequency features, and time-frequency features. KOA is successfully identified using the pedobarographic data and the pelvis and trunk motion with the highest accuracy and sensitivity of 89.3% and 85.7%, respectively, using a decision tree classifier. In addition, sEMG data have been successfully used to cluster healthy subjects from KOA subjects, with wavelet analysis features providing the best performance for the standing activity under different conditions. KOA is detected using gait variables not directly related to the knee, such as pedobarographic measurements and pelvis and trunk motion captured by pedobarography mats and wearable sensors, respectively. KOA subjects are also distinguished from healthy individuals through clustering analysis using sEMG data from knee periarticular muscles during walking and standing. Gait data and sEMG complement each other, aiding in KOA identification and rehabilitation monitoring. It is important because wearable sensors simplify data collection, require minimal sample preparation, and offer a non-radiographic, safe method suitable for both laboratory and real-world scenarios. The decision tree classifier, trained with stratified k-fold cross validation (SKCV) data, is observed to be the best for KOA identification using gait data.

Study on lung CT image segmentation algorithm based on threshold-gradient combination and improved convex hull method

Lung images often have the characteristics of strong noise, uneven grayscale distribution, and complex pathological structures, which makes lung image segmentation a challenging task. To solve this problems, this paper proposes an initial lung mask extraction algorithm that combines threshold and gradient. The gradient used in the algorithm is obtained by the time series feature extraction method based on differential memory (TFDM), which is obtained by the grayscale threshold and image grayscale features. At the same time, we also proposed a lung contour repair algorithm based on the improved convex hull method to solve the contour loss caused by solid nodules and other lesions. Experimental results show that on the COVID-19 CT segmentation dataset, the advanced lung segmentation algorithm proposed in this article achieves better segmentation results and greatly improves the consistency and accuracy of lung segmentation. Our method can obtain more lung information, resulting in ideal segmentation effects with improved accuracy and robustness.

Soft sensing of NOx emission from waste incineration process based on data de-noising and bidirectional long short-term memory neural networks.

Continuous emission monitoring system is commonly employed to monitor NOx emissions in municipal solid waste incineration (MSWI) processes. However, it still encounters the challenges of regular maintenance and measurement lag. These issues significantly impact the accurate and stable control of NOx emissions. Therefore, developing a soft NOx emission sensor to complement hardware monitoring becomes imperative. Considering data noise, dynamic nonlinearity, time series characteristics and volatility in the MSWI process, this article introduces a soft sensor model for NOx emission prediction utilizing the complete ensemble empirical mode decomposition adaptive noise (CEEMDAN)-wavelet threshold (WT) method and bidirectional long short-term memory (Bi-LSTM). Firstly, the original data signal is decomposed into a group of intrinsic mode functions (IMFs) using the CEEMDAN. Subsequently, the WT processes the high-frequency IMFs that are noise-dominant. Then, all IMFs are reconstructed to obtain the denoized signal. Finally, the Bi-LSTM model is employed to predict NOx emissions. Compared to conventional modelling approaches, the model proposed in this article demonstrates the best predictive performance. The mean absolute percentage error, root-mean-squared error and average absolute error on the test set of the proposed model are 3.75%, 5.34 mg m-3 and 4.34 mg m-3, respectively. The proposed model provides a new method to soft sensing NOx emissions. It holds significant practical value for precise and stable monitoring of NOx emissions in MSWI processes and provides a reference for research on modelling key process parameters.

Prediction of Network Security Situation Based on Attention Mechanism and Convolutional Neural Network–Gated Recurrent Unit

Network-security situation prediction is a crucial aspect in the field of network security. It is primarily achieved through monitoring network behavior and identifying potential threats to prevent and respond to network attacks. In order to enhance the accuracy of situation prediction, this paper proposes a method that combines a convolutional neural network (CNN) and a gated recurrent unit (GRU), while also incorporating an attention mechanism. The model can simultaneously handle the spatial and temporal features of network behavior and optimize the weight allocation of features through the attention mechanism. Firstly, the CNN’s powerful feature extraction ability is utilized to extract the spatial features of the network behavior. Secondly, time-series features of network behavior are processed through the GRU layer. Finally, to enhance the model’s performance further, we introduce attention mechanisms, which can dynamically adjust the importance of different features based on the current context information; this enables the model to focus more on critical information for accurate predictions. The experimental results show that the network-security situation prediction method, which combines a CNN and a GRU and introduces an attention mechanism, performs well in terms of the fitting effect and can effectively enhance the accuracy of situation prediction.

Time-Series Feature Extraction by Return Map Analysis and Its Application to Bearing-Fault Detection

Developing new features for time-series characterization is a current challenge in data science and machine learning. In this paper, we propose a new metric based on a simple and efficient algorithm, namely, the return map. The return map analysis is well established in the field of non-linear dynamics, in particular, for fitting the parameters of a chaotic system from a waveform, or to attack a chaotic communication channel. We show that our metrics work well for both non-linear dynamics and time-series feature extraction problems in the field of machine learning. In an experiment aiming to classify vibration signals of normal and damaged bearings, we compare our method with two other methods that reported to have excellent accuracy, based on entropy and statistical feature distribution, respectively. We show that our method achieves higher accuracy with almost the lowest time costs, which was confirmed in experiments with two different datasets containing three main classes of bearings: normal, with inner race faults, and with outer race faults, having different damage origins and recorded in various conditions. In particular, for the dataset supplied by Case Western Reserve University, our method reached an accuracy of 100% at signals of 5000 sample points length, with a total time of 0.4 s required for feature estimation, while the entropy-based method reached an accuracy of 95% with a time of 100 s, and a statistical feature distribution method reached an accuracy of 93% with a total time of 1.9 s. Results show that the developed method is better suited to real-time bearing condition monitoring applications than most of the methods reported to date.

Fishing Vessel Type Recognition Based on Semantic Feature Vector

Identifying fishing vessel types with artificial intelligence has become a key technology in marine resource management. However, classical feature modeling lacks the ability to express time series features, and the feature extraction is insufficient. Hence, this work focuses on the identification of trawlers, gillnetters, and purse seiners based on semantic feature vectors. First, we extract trajectories from massive and complex historical Vessel Monitoring System data that contain a large amount of dirty data and then extract the semantic features of fishing vessel trajectories. Finally, we input the semantic feature vectors into the LightGBM classification model for classification of fishing vessel types. In this experiment, the F1 measure of our proposed method on the East China Sea fishing vessel dataset reached 96.25, which was 6.82% higher than that of the classical feature-modeling method based on fishing vessel trajectories. Experiments show that this method is accurate and effective for the classification of fishing vessels.

An offline data-driven dual-surrogate framework considering prediction error for history matching

High computer power has long been a critical ingredient that affects the effectiveness and efficiency of history matching. Data-driven surrogate modeling as an efficient strategy can accelerate the history-matching process by constructing machine learning-based models with high computing speed but reduced accuracy. However, the applicability of surrogate models for different history-matching problems is uncertain due to the influence of data quality and quantity, model architectures, and hyperparameters. To overcome this issue, an offline data-driven dual-surrogate framework (ODDF) that considers the prediction error of surrogate models for history matching is proposed, where one surrogate model predicts the production data of reservoirs and the other one learns the prediction error of the former surrogate. The first surrogate model considers the time-series characteristics of production data using a recurrent neural network, while the second surrogate model regards the two-dimensional spatial correlation characteristics of multivariate prediction error using a fully convolutional neural network. Furthermore, an enhanced error model is applied to incorporate the prediction error into the objective function to reduce the influence of the prediction error on inversion results. Based on this hybrid framework, one can improve the prediction accuracy of surrogate models in history matching when the architectures or hyperparameters of surrogate models are not optimal. Additionally, one can obtain satisfactory results for history matching and uncertainty quantification based on surrogate modeling. The proposed framework is validated on the history matching of two- and three-dimensional reservoir models. The results show that the proposed method is robust in constructing the surrogate models and predicting the production data of reservoirs, which improves the efficiency and reliability of history matching.

Compressed Deep Learning Models for Wearable Atrial Fibrillation Detection through Attention.

Deep learning (DL) models have shown promise for the accurate detection of atrial fibrillation (AF) from electrocardiogram/photoplethysmography (ECG/PPG) data, yet deploying these on resource-constrained wearable devices remains challenging. This study proposes integrating a customized channel attention mechanism to compress DL neural networks for AF detection, allowing the model to focus only on the most salient time-series features. The results demonstrate that applying compression through channel attention significantly reduces the total number of model parameters and file size while minimizing loss in detection accuracy. Notably, after compression, performance increases for certain model variants in key AF databases (ADB and C2017DB). Moreover, analyzing the learned channel attention distributions after training enhances the explainability of the AF detection models by highlighting the salient temporal ECG/PPG features most important for its diagnosis. Overall, this research establishes that integrating attention mechanisms is an effective strategy for compressing large DL models, making them deployable on low-power wearable devices. We show that this approach yields compressed, accurate, and explainable AF detectors ideal for wearables. Incorporating channel attention enables simpler yet more accurate algorithms that have the potential to provide clinicians with valuable insights into the salient temporal biomarkers of AF. Our findings highlight that the use of attention is an important direction for the future development of efficient, high-performing, and interpretable AF screening tools for wearable technology.

Construction of a mental health risk model for college students with long and short-term memory networks and early warning indicators

Abstract With the increasing social pressure and academic competition, the mental health (for convenience, abbreviated as MH) problems of college students are becoming increasingly prominent, but there are often challenges that are difficult to accurately predict and intervene in a timely manner. The aim of this article is to address the early warning needs of college students’ MH problems and construct a model that can timely identify the MH problems of college students. The experiment collected MH related data from college students in S city, and analyzed and trained these data using the Long short-term memory (LSTM) network model. By changing the number of hidden layers, learning rate, batch size, and epoch times, the most suitable training effect was achieved. By using the time-series characteristics of the LSTM model, the selected parameters from the experiment can better capture the changing trends of college students’ MH status, thereby improving prediction accuracy. Finally, three stage indicators of low, medium, and high were set up for early warning of the predicted results, in order to effectively and timely take measures. The research results indicated that the constructed model achieved a minimum regularization loss of 0.0674 after training. Finally, the adjusted model was used to predict the test set, with an average accuracy of 0.852 and an average accuracy of 0.906. The LSTM-based MH risk model performed well in predicting college students’ MH problems and could identify potential risk factors in a timely manner.

A Method for Predicting Transformer Oil-Dissolved Gas Concentration Based on Multi-Window Stepwise Decomposition with HP-SSA-VMD-LSTM

Predicting the concentration of dissolved gases in transformer oil is a critical activity for the early detection of potential faults. To address the prevalent issue of data leakage in current prediction methods, this paper proposes a prediction method that completely avoids data leakage. First, the Hodrick Prescott (HP) filter is used for stepwise decomposition to obtain the long-term trend and high-frequency periodic component. The high-frequency periodic component is further decomposed using singular spectrum analysis (SSA) to extract periodic features. Dispersion entropy (DE) and fuzzy entropy (FE) are utilized alongside the HP and SSA methods to determine the optimal decomposition windows during the process, enhancing the ability of the model to acquire time series features. Then, variational mode decomposition (VMD) is applied to remove noise from the high-frequency component. Finally, the long short-term memory network (LSTM) is employed to predict each decomposed component, and the network parameters undergo optimization through the sparrow search optimization algorithm (SSOA). The two case studies in this work verify that the proposed model excels over other prediction means, providing strong support for subsequent fault prediction.

Spatiotemporal factor models for functional data with application to population map forecast

The proliferation of mobile devices has led to the collection of large amounts of population data. This situation has prompted the need to utilize this rich, multidimensional data in practical applications. In response to this trend, we have integrated functional data analysis (FDA) and factor analysis to address the challenge of predicting hourly population changes across various districts in Tokyo. Specifically, by assuming a Gaussian process, we avoided the large covariance matrix parameters of the multivariate normal distribution. In addition, the data were both time and spatially dependent between districts. To capture various characteristics, a Bayesian factor model was introduced, which modeled the time series of a small number of common factors and expressed the spatial structure through factor loading matrices. Furthermore, the factor loading matrices were made identifiable and sparse to ensure the interpretability of the model. We also proposed a Bayesian shrinkage method as a systematic approach for factor selection. Through numerical experiments and data analysis, we investigated the predictive accuracy and interpretability of our proposed method. We concluded that the flexibility of the method allows for the incorporation of additional time series features, thereby improving its accuracy.

Spatial weighting EMD-LSTM based approach for short-term PM2.5 prediction research

Given the significant health and environmental risks posed by atmospheric PM2.5 pollution, accurately predicting its concentration changes is especially important. Current models fall short in researching time-series feature extraction from pollutants and spatial correlations among monitoring stations. In this study, a spatiotemporal prediction model is introduced to address these issues. The model combines spatial weighting, empirical mode decomposition (EMD), and a long short-term memory (LSTM) network. First, weights are allocated to sites using Pearson correlation analysis and distance weighting methods. Next, the pollutant time series is decomposed using the EMD method. The highly correlated intrinsic mode function (IMF) component is selected for signal reconstruction, enhancing denoising. Finally, the model uses an LSTM network to capture nonlinear and dynamic time series traits, which significantly improves the PM2.5 prediction accuracy. The model utilizes data collected from 10 monitoring stations across Hefei city during 2018-2019, employing the previous 24 h of observations to forecast PM2.5 concentrations for the subsequent hour. By comparing with RNN, HPO-RNN, GRU, LSTM, and CBAM-CNN-Bi LSTM, the results show that our model surpasses five benchmark models in terms of prediction accuracy. Relative to the best-performing CBAM-CNN-Bi LSTM model, our model reduces RMSE and MAE by 73.91% and 72.99%, respectively, and improves R2 by 8.15%. In summary, the proposed spatial weighting EMD-LSTM model offers an efficient new approach for predicting atmospheric PM2.5 pollution. It integrates spatial and time series analysis, significantly enhancing the prediction accuracy.

Application of artificial bee colony algorithm based on homogenization mapping and collaborative acquisition control in network communication security.

In order to optimize the spectrum allocation strategy of existing wireless communication networks and improve information transmission efficiency and data transmission security, this study uses the independent correlation characteristics of chaotic time series to simulate the collection and control strategy of bees, and proposes an artificial bee colony algorithm based on uniform mapping and collaborative collection control. Furthermore, it proposes an artificial bee colony algorithm based on uniform mapping and collaborative collection and control. The method begins by establishing a composite system of uniformly distributed Chebyshev maps. In the neighborhood intervals where the nectar sources are firmly connected and relatively independent, the algorithm then conducts a chaotic traversal search. The research results demonstrated the great performance of the suggested algorithm in each test function as well as the positive effects of the optimization search. The network throughput rate was over 300 kbps, the quantity of security service eavesdropping was below 0.1, and the spectrum utilization rate of the algorithm-based allocation method could be enhanced to 0.8 at the most. Overall, the performance of the proposed algorithm outperformed the comparison algorithm, with high optimization accuracy and a significant amount of optimization. This is favorable for the efficient use of spectrum resources and the secure transmission of communication data, and it encourages the development of spectrum allocation technology in wireless communication networks.

Interpretable and efficient RUL prediction of turbofan engines using EM-enhanced Bi-LSTM with TCN and attention mechanism

Remaining useful life (RUL) prediction for turbofan engines is important in prognostics and health management (PHM) for the maintenance and operation of critical equipment. With continuous innovations in deep learning techniques, the complexity of models continues to increase, but the interpretability and comprehensibility of the prediction results become particularly important in industrial applications. Therefore, in this study, an improved bidirectional long and short-term memory network (Bi-LSTM) based interpretable hybrid deep learning model for RUL prediction of turbofan engines is proposed, which ingeniously integrates time series convolutional networks (TCNs), expectation maximization (EM), Bi-LSTMs, and attention mechanisms. By capturing time-series features at different levels, the model adapts to the complex dynamics of turbofan engine performance evolution in an efficient and cost-effective manner. Experimental validation on the C-MAPSS dataset demonstrated that the model significantly outperforms other methods in terms of RUL prediction performance, especially in improving prediction accuracy and coping with the degradation of complex system dynamics. The largest contribution of key metrics to the model is validated through consistent results from multiple interpretable tools, providing comprehensive and consistent support for understanding and trusting prediction results in industrial applications. This study further enhances the robustness of the model and the reliability of the interpretable results by delving into the dynamic relationships between the properties of the different life stages, which not only reveal the importance of these characteristics in engine life prediction but also provide more comprehensive information about the engine performance variations by observing the dynamic relationships.