Search

The internal defects in rock masses can significantly impact the quality and safety of geotechnical projects. Mechanical waves, as a common nondestructive testing (NDT) method, can reflect the external and internal structures of rock or rock masses. Analyses on the reflected and transmitted waves enable nondestructive identification and assessment of potential defects within rocks. Previous studies mainly focused on the variation of single or limited wave features like main frequency, amplitude and energy between the intact and non‐intact samples. In fact, most information contained in the waveforms is neglected. Techniques of data mining can provide a powerful tool to reveal this information and therefore a more accurate determination of the internal structures. In this study, 995,412 NDT data from 14 types of granite and gypsum samples with different cross‐section shapes and different types of defects are recorded by an ultrasonic wave generation and collection system. This dataset can be used not only as the training data for defect classification in NDT but also as a good reference for conventional NDT analyses. Besides, time‐series data analysis is an opportunity and challenging issue, this dataset holds great potential for broader application in general time‐series classification analysis. [ABSTRACT FROM AUTHOR]

Objectives: Patients with intermediate or advanced hepatocellular carcinoma (HCC) require repeated disease monitoring, prognosis assessment and treatment planning. In 2018, a novel machine learning methodology "survival path" (SP) was developed to facilitate dynamic prognosis prediction and treatment planning. One year after, a deep learning approach called Dynamic Deephit was developed. The performance of the two state-of-art models in dynamic prognostication have not been compared. Methods: We trained and tested the SP and Dynamic DeepHit models in a large cohort of 2511 HCC patients using time-series data. The time-series data were converted into data of time slices, with an interval of three months. The time-dependent c-index for OS at given prediction time (t = 1, 6, 12, 18 months) and evaluation time (∆ t = 3, 6, 9, 12, 18, 24, 36, 48 months) were compared. Results: The comparison between SP model and Dynamic DeepHit-HCC model showed the latter had significant better performance at the time of initial admission. The time-dependent c-index of Dynamic DeepHit-HCC model gradually decreased with the extension of time (from 0.756 to 0.639 in the training set; from 0.787 to 0.661 in internal testing set; from 0.725 to 0.668 in multicenter testing set); while the time-dependent c-index of SP model displayed an increased trend (from 0.665 to 0.748 in the training set; from 0.608 to 0.743 in internal testing set; from 0.643 to 0.720 in multicenter testing set). When the prediction time comes to 6 months or later since initial treatment, the survival path model outperformed the dynamic DeepHit model at late evaluation times (∆ t > 12 months). Conclusions: This research highlighted the unique strengths of both models. The SP model had advantage in long term prediction while the Dynamic DeepHit-HCC model had advantages in prediction at near time points. Fine selection of models is needed in dealing with different scenarios. [ABSTRACT FROM AUTHOR]

Transformer models are widely used in natural language processing (NLP) and time-series data analysis. Applications of these models include prediction systems and hand gesture recognition using electromyogram (EMG) signals. However, in the case of time-series analysis, the models perform similarly to traditional networks, contrary to expectations. This study aimed to compare the performance of the transformer model and its various modified versions in terms of accuracy through a user authentication system using EMG signals, which exhibit significant variability and pose challenges in feature extraction. A Siamese network was employed to distinguish subtle differences in the EMG signals between users, using Euclidean distance. Data from 100 individuals were used to create a challenging scenario while ensuring accuracy. Three scenarios were considered: data preprocessing, integration with existing models, and the modification of the internal structure of the transformer model. The method that achieved the highest accuracy was the bidirectional long short-term memory (BiLSTM)–transformer approach. Based on this, a network was further constructed and optimized, resulting in a user authentication accuracy of 99.7% using EMG data from 100 individuals. [ABSTRACT FROM AUTHOR]

Just as the value of crude oil is unlocked through refining, the true potential of air quality data is realized through systematic processing, analysis, and application. This refined data is critical for making informed decisions that may protect health and the environment. Perhaps ground-based air quality monitoring data often face quality control issues, notably outliers. The outliers in air quality data are reported as error and event-based. The error-based outliers are due to instrument failure, self-calibration, sensor drift over time, and the event based focused on the sudden change in meteorological conditions. The event-based outliers are meaningful while error-based outliers are noise that needs to be eliminated and replaced post-detection. In this study, we address error-based outlier detection in air quality data, particularly targeting particulate pollutants (PM2.5 and PM10) across various monitoring sites in Delhi. Our research specifically examines data from sites with less than 5% missing values and identifies four distinct types of error-based outliers: extreme values due to measurement errors, consecutive constant readings and low variance due to instrument malfunction, periodic outliers from self-calibration exceptions, and anomalies in the PM2.5/PM10 ratio indicative of issues with the instruments' dryer unit. We developed a robust methodology for outlier detection by fitting a non-linear filter to the data, calculating residuals between observed and predicted values, and then assessing these residuals using a standardized Z-score to determine their probability. Outliers are flagged based on a probability threshold established through sensitivity testing. This approach helps distinguish normal data points from suspicious ones, ensuring the refined quality of data necessary for accurate air quality modeling. This method is essential for improving the reliability of statistical and machine learning models that depend on high-quality environmental data. [ABSTRACT FROM AUTHOR]

We proposed a deep learning method using a convolutional neural network on time-series (TS) images to detect and differentiate affected body parts in people with Parkinson's disease (PD) and freezing of gait (FOG) during 360° turning tasks. The 360° turning task was performed by 90 participants (60 people with PD [30 freezers and 30 nonfreezers] and 30 age-matched older adults (controls) at their preferred speed. The position and acceleration underwent preprocessing. The analysis was expanded from temporal to visual data using TS imaging methods. According to the PD vs. controls classification, the right lower third of the lateral shank (RTIB) on the least affected side (LAS) and the right calcaneus (RHEE) on the LAS were the most relevant body segments in the position and acceleration TS images. The RHEE marker exhibited the highest accuracy in the acceleration TS images. The identified markers for the classification of freezers vs. nonfreezers vs. controls were the left lateral humeral epicondyle (LELB) on the more affected side and the left posterior superior iliac spine (LPSI). The LPSI marker in the acceleration TS images displayed the highest accuracy. This approach could be a useful supplementary tool for determining PD severity and FOG. [ABSTRACT FROM AUTHOR]

We obtain the air quality index (AQI) for a descriptive system aimed to communicate pollution risks to the population. The AQI is calculated based on major air pollutants including O3, CO, SO2, NO, NO2, benzene, and particulate matter PM2.5 that should be continuously balanced in clean air. Air pollution is a major limitation for urbanization and population growth in developing countries. Hence, automated AQI prediction by a deep learning method applied to time series may be advantageous. We use a seasonal autoregressive integrated moving average (SARIMA) model for predicting values reflecting past trends considered as seasonal patterns. In addition, a transductive long short‐term memory (TLSTM) model learns dependencies through recurring memory blocks, thus learning long‐term dependencies for AQI prediction. Further, the TLSTM increases the accuracy close to test points, which constitute a validation group. AQI prediction results confirm that the proposed SARIMA–TLSTM model achieves a higher accuracy (93%) than an existing convolutional neural network (87.98%), least absolute shrinkage and selection operator model (78%), and generative adversarial network (89.4%). [ABSTRACT FROM AUTHOR]

This study considers an estimator for the asymptotic variance-covariance matrix in time-series quantile regression models which is robust to the presence of heteroscedasticity and autocorrelation. When regression errors are serially correlated, the conventional quantile regression standard errors are invalid. The proposed solution is a quantile analogue of the Newey-West robust standard errors. We establish the asymptotic properties of the heteroscedasticity and autocorrelation consistent (HAC) covariance matrix estimator and provide an optimal bandwidth selection rule. The quantile sample autocorrelation coefficient is biased toward zero in finite sample which adversely affects the optimal bandwidth estimation. We propose a simple alternative estimator that effectively reduces the finite sample bias. Numerical simulations provide evidence that the proposed HAC covariance matrix estimator significantly improves the size distortion problem. To illustrate the usefulness of the proposed robust standard error, we examine the impacts of the expansion of renewable energy resources on electricity prices. for this article are available online. [ABSTRACT FROM AUTHOR]

Time-series data are prevalent across various fields and present unique challenges for deep learning models due to irregular time intervals and missing records, which hinder the ability to capture temporal information effectively. This study proposes ChronoVectors, a novel temporal representation method that addresses these challenges by enabling a more specialized encoding of temporal relationships through the use of learnable parameters tailored to the dataset's dynamics while maintaining consistent time intervals post-scaling. The theoretical demonstration shows that ChronoVectors allow the transformed encoding tensors to map moments in time to continuous spaces, accommodating potentially infinite extensions of the sequence and preserving temporal consistency. Experimental validation using the Parking Birmingham and Metro Interstate Traffic Volume datasets reveals that ChronoVectors enhanced the predictive capabilities of deep learning models by reducing prediction error for regression tasks compared to conventional time representations, such as vanilla timestamp encoding and Time2Vec. These findings underscore the potential of ChronoVectors in handling irregular time-series data and showcase its ability to improve deep learning model performance in understanding temporal dynamics. [ABSTRACT FROM AUTHOR]

The rapidly growing global energy demand, environmental concerns, and the urgent need to reduce carbon footprints have made sustainable household energy consumption a critical priority. This study aims to analyze household energy data to predict the electricity self-sufficiency rate of households and extract meaningful insights that can enhance it. For this purpose, we use LightGBM (Light Gradient Boosting Machine)-, SHAP (SHapley Additive exPlanations)-, and correlation-heatmap-based approaches to analyze 12 months of energy and questionnaire survey data collected from over 200 smart houses in Kitakyushu, Japan. First, we use LightGBM to predict the ESSR of households and identify the key features that impact the prediction model. By using LightGBM, we demonstrated that the key features are the housing type, average monthly electricity bill, presence of floor heating system, average monthly gas bill, electricity tariff plan, electrical capacity, number of TVs, cooking equipment used, number of washing and drying machines, and the frequency of viewing home energy management systems (HEMSs). Furthermore, we adopted the LightGBM classifier with ℓ 1 regularization to extract the most significant features and established a statistical correlation between these features and the electricity self-sufficiency rate. This LightGBM-based model can also predict the electricity self-sufficiency rate of households that did not participate in the questionnaire survey. The LightGBM-based model offers a global view of feature importance but lacks detailed explanations for individual predictions. For this purpose, we used SHAP analysis to identify the impact-wise order of key features that influence the electricity self-sufficiency rate (ESSR) and evaluated the contribution of each feature to the model's predictions. A heatmap is also used to analyze the correlation among household variables and the ESSR. To evaluate the performance of the classification model, we used a confusion matrix showing a good F1 score (Weighted Avg) of 0.90. The findings discussed in this article offer valuable insights for energy policymakers to achieve the objective of developing energy-self-sufficient houses. [ABSTRACT FROM AUTHOR]

Purpose: This study aims to introduce an innovative approach to predictive maintenance by integrating time-series sensor data with event logs, leveraging the synergistic potential of deep learning models. The primary goal is to enhance the accuracy of equipment failure predictions, thereby minimizing operational downtime. Design/methodology/approach: The methodology uses a dual-model architecture, combining the patch time series transformer (PatchTST) model for analyzing time-series sensor data and bidirectional encoder representations from transformers for processing textual event log data. Two distinct fusion strategies, namely, early and late fusion, are explored to integrate these data sources effectively. The early fusion approach merges data at the initial stages of processing, while late fusion combines model outputs toward the end. This research conducts thorough experiments using real-world data from wind turbines to validate the approach. Findings: The results demonstrate a significant improvement in fault prediction accuracy, with early fusion strategies outperforming traditional methods by 2.6% to 16.9%. Late fusion strategies, while more stable, underscore the benefit of integrating diverse data types for predictive maintenance. The study provides empirical evidence of the superiority of the fusion-based methodology over singular data source approaches. Originality/value: This research is distinguished by its novel fusion-based approach to predictive maintenance, marking a departure from conventional single-source data analysis methods. By incorporating both time-series sensor data and textual event logs, the study unveils a comprehensive and effective strategy for fault prediction, paving the way for future advancements in the field. [ABSTRACT FROM AUTHOR]

While mean-field models of cellular operations have identified dominant processes at the macroscopic scale, stochastic models may provide further insight into mechanisms at the molecular scale. In order to identify plausible stochastic models, quantitative comparisons between the models and the experimental data are required. The data for these systems have small sample sizes and time-evolving distributions. The aim of this study is to identify appropriate distance metrics for the quantitative comparison of stochastic model outputs and time-evolving stochastic measurements of a system. We identify distance metrics with features suitable for driving parameter inference, model comparison, and model validation, constrained by data from multiple experimental protocols. In this study, stochastic model outputs are compared to synthetic data across three scales: that of the data at the points the system is sampled during the time course of each type of experiment; a combined distance across the time course of each experiment; and a combined distance across all the experiments. Two broad categories of comparators at each point were considered, based on the empirical cumulative distribution function (ECDF) of the data and of the model outputs: discrete based measures such as the Kolmogorov–Smirnov distance, and integrated measures such as the Wasserstein-1 distance between the ECDFs. It was found that the discrete based measures were highly sensitive to parameter changes near the synthetic data parameters, but were largely insensitive otherwise, whereas the integrated distances had smoother transitions as the parameters approached the true values. The integrated measures were also found to be robust to noise added to the synthetic data, replicating experimental error. The characteristics of the identified distances provides the basis for the design of an algorithm suitable for fitting stochastic models to real world stochastic data. [ABSTRACT FROM AUTHOR]

The Philippines has had high levels of unemployment for years. During the 2000s, the unemployment rate hovered between seven and ten percent. High unemployment can have adverse effects on individuals and society. The question that this paper analyses is how unanticipated money growth affect the unemployment situation in the Philippines. There has been literature on the relationship between unanticipated growth on the money supply and unemployment. The paper proposes that only unanticipated money movements will affect real economic variables like unemployment and the output level. In order to test our hypothesis, it is important that we need to quantify the concepts of anticipated and unanticipated money movements. This paper uses time-series data on several economic variables as well as a model based on Geetha et al. (2023). Using an error-correction model, the results show that an unanticipated increase in M2 money is a factor that contributes to unemployment in Philippines. [ABSTRACT FROM AUTHOR]

EpiRiskNet combines time-series data with graph and static information to enhance forecasting accuracy. This model features the SCI-Block for improved feature extraction and interaction learning, leveraging the capabilities of SCINet and Triformer to manage diverse feature scales. The model's standout attribute, scalability, is driven by Triformer's Patch Attention mechanism, ensuring efficient processing of large-scale data. EpiRiskNet was tested across several locations, including Liaoning, Chongqing, Heilongjiang, and Guangxi, where it demonstrated greater accuracy than other methods. This accuracy is crucial for effectively forecasting disease risks. The model's adaptability to various regional conditions underscores its significance in public health and epidemiology. Moreover, its modular and flexible design makes EpiRiskNet suitable for a wide range of applications that require advanced data processing and predictive analytics. [ABSTRACT FROM AUTHOR]

With the recent advancements in Internet of Things (IoT) technology, various fields such as manufacturing, environment, and health care generate diverse types of time series data. This data is collected in real-time and is used for anomaly detection and prediction. However, current time series data analysis does not achieve efficient results due to the use of different preprocessing criteria and different types of deep learning algorithms depending on the purpose. This study addresses these limitations by implementing an automated, customized pipeline called the Time-series Anomaly detection Pipeline (TAP), which efficiently performs prediction and anomaly detection. TAP establishes an integrated deep learning pipeline that allows users to preprocess and model time series data according to their specific environments, enabling accurate prediction and anomaly detection. This approach reduces on-site analysis time and improves the accuracy of predictions and anomaly detection tailored to the environment. [ABSTRACT FROM AUTHOR]

We obtain the air quality index (AQI) for a descriptive system aimed to communicate pollution risks to the population. The AQI is calculated based on major air pollutants including O3, CO, SO2, NO, NO2, benzene, and particulate matter PM2.5 that should be continuously balanced in clean air. Air pollution is a major limitation for urbanization and population growth in developing countries. Hence, automated AQI prediction by a deep learning method applied to time series may be advantageous. We use a seasonal autoregressive integrated moving average (SARIMA) model for predicting values reflecting past trends considered as seasonal patterns. In addition, a transductive long short-term memory (TLSTM) model learns dependencies through recurring memory blocks, thus learning long-term dependencies for AQI prediction. Further, the TLSTM increases the accuracy close to test points, which constitute a validation group. AQI prediction results confirm that the proposed SARIMA-TLSTM model achieves a higher accuracy (93%) than an existing convolutional neural network (87.98%), least absolute shrinkage and selection operator model (78%), and generative adversarial network (89.4%).

Abstract We proposed a deep learning method using a convolutional neural network on time-series (TS) images to detect and differentiate affected body parts in people with Parkinson’s disease (PD) and freezing of gait (FOG) during 360° turning tasks. The 360° turning task was performed by 90 participants (60 people with PD [30 freezers and 30 nonfreezers] and 30 age-matched older adults (controls) at their preferred speed. The position and acceleration underwent preprocessing. The analysis was expanded from temporal to visual data using TS imaging methods. According to the PD vs. controls classification, the right lower third of the lateral shank (RTIB) on the least affected side (LAS) and the right calcaneus (RHEE) on the LAS were the most relevant body segments in the position and acceleration TS images. The RHEE marker exhibited the highest accuracy in the acceleration TS images. The identified markers for the classification of freezers vs. nonfreezers vs. controls were the left lateral humeral epicondyle (LELB) on the more affected side and the left posterior superior iliac spine (LPSI). The LPSI marker in the acceleration TS images displayed the highest accuracy. This approach could be a useful supplementary tool for determining PD severity and FOG.

This study introduces an Enhanced Autoregressive Integrated Moving Average (E-ARIMA) model for anomaly detection in time-series data, using vibrations monitored by CA 202 accelerometers at the Kirkuk Gas Power Plant as a case study. The objective is to overcome the limitations of traditional ARIMA models in analyzing the non-linear and dynamic nature of industrial sensory data. The novel proposed methodology includes data preparation through linear interpolation to address dataset gaps, stationarity confirmation via the Augmented Dickey-Fuller Test, and ARIMA model optimization against the Akaike Information Criterion, with a specialized time-series cross-validation technique. The results show that E-ARIMA model has superior performance in anomaly detection compared to conventional Seasonal ARIMA (SARIMA) and Vector Autoregressive models. In this regard, Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE) criteria were utilized for this evaluation. Finally, the most important achievement of this research is that the results highlight the enhanced predictive accuracy of the E-ARIMA model, making it a potent tool for industrial applications such as machinery health monitoring, where early detection of anomalies is crucial to prevent costly downtimes and facilitate maintenance planning. [ABSTRACT FROM AUTHOR]

During the shale gas extraction process, affected by the internal pressure of the geological layer and other factors, the internal pressure will gradually decrease with time, and the production will also decrease, and it is necessary to rely on artificial pressurization and other ways to keep the production stable. Accordingly, we analyzed the high-frequency data of shale gas production obtained from a block in the southwest shale gas field, and proposed a data-driven prediction model combining Principal Component Analysis (PCA), Particle Swarm Optimization (PSO) and Long Short-Term Memory (LSTM), which can determine whether artificial pressurization is needed from the predicted results. The model adopts multi-variate input and uni-variate output, firstly, the PCA algorithm for processing the characteristic parameters (casing pressure, oil pressure, pre-valve temperature) and labeling parameters (instantaneous production), secondly, the PSO algorithm is used to iteratively search for the optimal hyper-parameters of the LSTM to find the most suitable hyper-parameter configuration, and finally, established a data-driven shale gas production prediction model. The combined model is analyzed through an example study, and the accuracy is higher in shale gas production prediction. [ABSTRACT FROM AUTHOR]

Although neural networks have revolutionized various fields, their deployment in mobile environments confronts significant challenges due to limitations in battery and cooling capacity, especially for internet of things devices [1]. A lightweight neural network is urgently needed to address these issues. In this study, we explore the use of the Hadamard product and assess the usefulness of the method to enhance the neural network performance in mobile environments. The method has less computational complexity compared with other matrix multiplication methods [2]. Hadamard product methodologies are applied to the input features to amplify useful data and diminish noise. Our research involved the use of 48 electromyography signals sourced from the calves of three individuals with the signal time frame being iterated from 10 to 990 with a step size of 10. Findings indicate that the utilization of Hadamard products significantly improves the model performance relative to the increase in model size. [ABSTRACT FROM AUTHOR]

The paper "Using Absorption Models for Insulin and Carbohydrates and Deep Leaning to Improve Glucose Level Predictions" (Sensors 2021, 21, 5273) proposes a novel approach to predicting blood glucose levels for people with type 1 diabetes mellitus (T1DM). By building exponential models from raw carbohydrate and insulin data to simulate the absorption in the body, the authors reported a reduction in their model's root-mean-square error (RMSE) from 15.5 mg/dL (raw) to 9.2 mg/dL (exponential) when predicting blood glucose levels one hour into the future. In this comment, we demonstrate that the experimental techniques used in that paper are flawed, which invalidates its results and conclusions. Specifically, after reviewing the authors' code, we found that the model validation scheme was malformed, namely, the training and test data from the same time intervals were mixed. This means that the reported RMSE numbers in the referenced paper did not accurately measure the predictive capabilities of the approaches that were presented. We repaired the measurement technique by appropriately isolating the training and test data, and we discovered that their models actually performed dramatically worse than was reported in the paper. In fact, the models presented in the that paper do not appear to perform any better than a naive model that predicts future glucose levels to be the same as the current ones. [ABSTRACT FROM AUTHOR]

Fuel prices are rising, bringing attention to the utilization of alternative energy sources (RES). Even though load forecasting is more accurate at making predictions than wind power forecasting is. To address the operational challenges with the supply of electricity, wind energy forecasts remain essential. A certain kind of technology has recently been applied to forecast wind energy. On wind farms, a variety of wind power forecasting methods have been developed and used. The main idea underlying recurrent networks is parameter sharing across the multiple layers and neurons, which results in cycles in the network's graph sequence. Recurrent networks are designed to process sequential input. A novel hybrid optimization‐based RNN model for wind power forecasting is proposed in this research. Using the SpCro algorithm, a proposed optimization method, the RNN's weights are adjusted. The Crow Search Optimization (CSA) algorithm and the Sparrow search algorithm are combined to form the SpCro Algorithm (SSA). The suggested Algorithm was developed using the crow's memory traits and the sparrow's detecting traits. The proposed system is simulated in MATLAB, and the usefulness of the suggested approach is verified by comparison with other widely used approaches, such as CNN and DNN, in terms of error metrics. Accordingly, the MAE of the proposed method is 45%, 10.02%, 10.04%, 33.58%, 94.81%, and 10.01% higher than RNN, SOA+RNN, CSO+RNN, SSA+DELM, CFU‐COA, and GWO+RNN method. [ABSTRACT FROM AUTHOR]

The importance of monitoring in assessing structural safety and durability continues to grow. With recent technological advancements, Internet of Things (IoT) sensors have garnered attention for their complex scalability and varied detection capabilities, becoming essential devices for monitoring. However, during the data collection process of IoT sensors, anomalies arise due to network instability, sensor noise, and malfunctions, degrading data quality and compromising monitoring system reliability. In this study, Interquartile Range (IQR), Long Short-Term Memory Autoencoder (LSTM-AE), and time-series decomposition were employed for anomaly detection in Structural Health Monitoring (SHM) processes. IQR and LSTM-AE produce irregular patterns; however, time-series decomposition effectively detects such anomalies. In road monitoring influenced by weather and traffic, the time-series decomposition approach is expected to play a crucial role in enhancing monitoring accuracy. [ABSTRACT FROM AUTHOR]

Given the importance of climate in shaping species' geographic distributions, climate change poses an existential threat to biodiversity. Climate envelope modeling, the predominant approach used to quantify this threat, presumes that individuals in populations respond to climate variability and change according to species-level responses inferred from spatial occurrence data--such that individuals at the cool edge of a species' distribution should benefit from warming (the "leading edge"), whereas individuals at the warm edge should suffer (the "trailing edge"). Using 1,558 tree-ring time series of an aridland pine (Pinus edulis) collected at 977 locations across the species' distribution, we found that trees everywhere grow less in warmer-than-average and drier-than-average years. Ubiquitous negative temperature sensitivity indicates that individuals across the entire distribution should suffer with warming--the entire distribution is a trailing edge. Species-level responses to spatial climate variation are opposite in sign to individual-scale responses to time-varying climate for approximately half the species' distribution with respect to temperature and the majority of the species' distribution with respect to precipitation. These findings, added to evidence from the literature for scale-dependent climate responses in hundreds of species, suggest that correlative, equilibrium-based range forecasts may fail to accurately represent how individuals in populations will be impacted by changing climate. A scale-dependent view of the impact of climate change on biodiversity highlights the transient risk of extinction hidden inside climate envelope forecasts and the importance of evolution in rescuing species from extinction whenever local climate variability and change exceeds individual-scale climate tolerances. [ABSTRACT FROM AUTHOR]

Time-series data collected from a network of random variables are useful for identifying temporal pathways among the network nodes. Observed measurements may contain multiple sources of signals and noises, including Gaussian signals of interest and non-Gaussian noises, including artifacts, structured noise, and other unobserved factors (eg, genetic risk factors, disease susceptibility). Existing methods, including vector autoregression (VAR) and dynamic causal modeling do not account for unobserved non-Gaussian components. Furthermore, existing methods cannot effectively distinguish contemporaneous relationships from temporal relations. In this work, we propose a novel method to identify latent temporal pathways using time-series biomarker data collected from multiple subjects. The model adjusts for the non-Gaussian components and separates the temporal network from the contemporaneous network. Specifically, an independent component analysis (ICA) is used to extract the unobserved non-Gaussian components, and residuals are used to estimate the contemporaneous and temporal networks among the node variables based on method of moments. The algorithm is fast and can easily scale up. We derive the identifiability and the asymptotic properties of the temporal and contemporaneous networks. We demonstrate superior performance of our method by extensive simulations and an application to a study of attention-deficit/hyperactivity disorder (ADHD), where we analyze the temporal relationships between brain regional biomarkers. We find that temporal network edges were across different brain regions, while most contemporaneous network edges were bilateral between the same regions and belong to a subset of the functional connectivity network. [ABSTRACT FROM AUTHOR]

Disengagement of students during online learning significantly impacts the effectiveness of online education. Thus, accurately estimating when students are not engaged is a critical aspect of online-learning research. However, the inherent characteristics of public datasets often lead to issues of class imbalances and data insufficiency. Moreover, the instability of video time-series data further complicates data processing in related research. Our research aims to tackle class imbalances and instability of video time-series data in estimating learner engagement, particularly in scenarios with limited data. In the present paper, we introduce "Skipped Moving Average", an innovative oversampling technique designed to augment video time-series data representing disengaged students. Furthermore, we employ long short-term memory (LSTM) and long short-term memory fully convolutional network (LSTM-FCN) models to evaluate the effectiveness of our method and compare it to the synthetic minority over-sampling technique (SMOTE). This approach ensures a thorough evaluation of our method's effectiveness in addressing video time-series data imbalances and in enhancing the accuracy of engagement estimation. The results demonstrate that our proposed method outperforms others in terms of both performance and stability across sequence deep learning models. [ABSTRACT FROM AUTHOR]

We conducted this study to investigate the relationship between environmental stressors and mesozooplankton fluxes in inner Kongsfjorden, Svalbard. The ongoing Arctic amplification, characterized by phenomena such as increased temperatures, glacial and watershed runoff, and diminishing ice cover, poses significant challenges to marine ecosystems. Our multi-year time-series analysis (2010–2018) of mesozooplankton, collected from a moored automatic sediment trap at approximately 87 m depth, aims to elucidate seasonal and interannual variations in fluxes within this Arctic fjord. We integrate meteorological, hydrological, and chemical datasets to assess their influence on zooplankton populations. Principal component analysis reveals the impact of seawater characteristics on mesozooplankton fluxes and composition, while two-way ANOVA highlights the role of seasonality in driving variations in our dataset. We observe a decrease in swimmer fluxes following the maxima mass flux event (from 2013 onwards), coupled with an increase in community diversity, possibly attributed to copepod decline and functional diversity. Notably, sub-Arctic boreal species such as Limacina retroversa have been detected in the sediment trap since 2016. Our continuous multi-year dataset captures the physical, chemical, and biological dynamics in this extreme environment. With Arctic amplification in Kongsfjorden and increasing submarine and watershed runoff, we anticipate significant shifts in mesozooplankton communities in the medium to long-term. This underscores the urgency for further research on their adaptation to changing environmental conditions and the potential introduction of alien species. [ABSTRACT FROM AUTHOR]

The current lack of harmonized standard test conditions for marine shipping hinders the comparison of performance and compliance assessments for different types of ships. This article puts forward a method for extracting ship loading cycles using machine learning algorithms. Time-series data are extracted from real ships in operation, and a segmented linear approximation method and a data normalization technique are adopted. A hierarchical-clustering type of soft dynamic time-warping similarity analysis method is presented to efficiently analyze the similarity of different time-series data, using soft dynamic time warping (Soft-DTW) combined with hierarchical clustering algorithms from the field of machine learning. The problem of data bias caused by spatial and temporal offset characteristics is effectively solved in marine test condition data. The validity and reliability of the proposed method are validated through the analysis of case data. The results demonstrate that the hierarchically clustered soft dynamic time-warping similarity analysis method can be considered reliable for obtaining test cases with different characteristics. Furthermore, it provides input conditions for effectively identifying the operating conditions of different types of ships with high levels of energy consumption and high emissions, thus allowing for the establishment of energy-saving and emissions-reducing sailing strategies. [ABSTRACT FROM AUTHOR]

Missing data is inevitable in single-case experimental designs (SCEDs) studies due to repeated measures over a period of time. Despite this fact, SCEDs implementers such as researchers, teachers, clinicians, and school psychologists usually ignore missing data in their studies. Performing analyses without considering missing data in an intervention study using SCEDs or a meta-analysis study including SCEDs studies in a topic can lead to biased results and affect the validity of individual or overall results. In addition, missingness can undermine the generalizability of SCEDs studies. Considering these drawbacks, this study aims to give descriptive and advisory information to SCEDs practitioners and researchers about missing data in single-case data. To accomplish this task, the study presents information about missing data mechanisms, item level and unit level missing data, planned missing data designs, drawbacks of ignoring missing data in SCEDs, and missing data handling methods. Since single imputation methods among missing data handling methods do not require complicated statistical knowledge, are easy to use, and hence are more likely to be used by practitioners and researchers, the present study evaluates single imputation methods in terms of intervention effect sizes and missing data rates by using a real and hypothetical data sample. This study encourages SCEDs implementers, and also meta-analysts to use some of the single imputation methods to increase the generalizability and validity of the study results in case they encounter missing data in their studies. [ABSTRACT FROM AUTHOR]

Gyroscopes and camera sensors, widely utilized for motion recognition across industries, are celebrated for their low power consumption and user-friendly interaction. Nevertheless, challenges such as accuracy fluctuations due to calibration methods and computational delays in real-time processing persist. In this innovative study, we introduce ConvIMage, a groundbreaking approach that transforms Inertial Measurement Unit (IMU) sensor time-series data into image data through Convolutional Neural Network (CNN) algorithms, enhancing motion estimation capabilities. ConvIMage ingeniously assembles pattern images by converting IMU-derived time-series data into distinctive color channels, empowering a CNN model to discern intricate movement patterns. Experimental assessments underscore ConvIMage's commendable performance, showcasing accuracies ranging from 83.42% to 85.97%, contingent upon the specific type of motion. This auspicious outcome positions ConvIMage as a robust solution for future IoT service development, leveraging motion data with enhanced accuracy and real-time processing capabilities for a multitude of applications. [ABSTRACT FROM AUTHOR]

Water, a critical resource, suffers from significant losses due to leakages in Water Distribution Networks (WDN). These losses present financial, environmental, and public health challenges. With water utility companies amassing vast amounts of data from enterprise information systems, the opportunity for data-driven leakage detection arises. With the increased use of enterprise information systems, water utility companies are generating vast amounts of data that can be valuable for predicting or detecting water leaks early and also for the development of new, automatic, and effective data-driven leak detection techniques. The presented study utilizes this data, by applying anomaly detection methods to heterogeneous time-series data from various components of the WDN in Slovakia. Our results demonstrate that components of the network, such as measured power consumption, water source temperature, and water source levels show significant positive associations with faults in the Water Distribution Network. [ABSTRACT FROM AUTHOR]

Indoor fires may cause casualties and property damage, so it is important to develop a system that predicts fires in advance. There have been studies to predict potential fires using sensor values, and they mostly exploited machine learning models or recurrent neural networks. In this paper, we propose a stack of Transformer encoders for fire prediction using multiple sensors. Our model takes the time-series values collected from the sensors as input, and predicts the potential fire based on the sequential patterns underlying the time-series data. We compared our model with traditional machine learning models and recurrent neural networks on two datasets. For a simple dataset, we found that the machine learning models are better than ours, whereas our model gave better performance for a complex dataset. This implies that our model has a greater potential for real-world applications that probably have complex patterns and scenarios. [ABSTRACT FROM AUTHOR]

In the face of escalating cyber threats that have contributed significantly to global economic losses, this study presents a comprehensive dataset capturing the multifaceted nature of cyber-attacks across 225 countries over a 14-month period from October 2022 to December 2023. The dataset, comprising 77,623 rows and 18 fields, provides a detailed chronology of cyber-attacks, categorized into eight critical dimensions: spam, ransomware, local infection, exploit, malicious mail, network attack, on-demand scan, and web threat. The dataset also includes ranking data, offering a comparative view of countries' susceptibility to different cyber threats. The results reveal significant variations in the frequency and intensity of cyber-attacks across different countries and attack types. The data were meticulously compiled using modern AI-based data acquisition techniques, ensuring a high degree of accuracy and comprehensiveness. Correlation tests against the eight types of cyber-attacks resulted in the determination that on-demand scan and local infection are highly correlated, with a correlation coefficient of 0.93. Lastly, neural-network-based forecasting of these highly correlated factors (i.e., on-demand scan and local infection) reveals a similar pattern of prediction, with an MSE and an MAPE of 1.616 and 80.13, respectively. The study's conclusions provide critical insights into the global landscape of cyber threats, highlighting the urgent need for robust cybersecurity measures. [ABSTRACT FROM AUTHOR]

Introduction: Carbon neutrality has become a key strategy to combat global climate change. However, current methods for predicting carbon emissions are limited and require the development of more effective strategies to meet this challenge. This is especially true in the field of sports and competitions, where the energy intensity of major events and activities means that time series data is crucial for predicting related carbon emissions, as it can detail the emission patterns over a period of time. Method: In this study, we introduce an artificial intelligence-based method aimed at improving the accuracy and reliability of carbon emission predictions. Specifically, our model integrates an Improved Mahjong Search Algorithm (ISSA) and GRU-Transformer technology, designed to efficiently process and analyze the complex time series data generated by sporting events. These technological components help to capture and parse carbon emission data more accurately. Results: Experimental results have demonstrated the efficiency of our model, which underwent a comprehensive evaluation involving multiple datasets and was benchmarked against competing models. Our model outperformed others across various performance metrics, including lower RMSE and MAE values and higher R2 scores. This underscores the significant potential of our model in enhancing the accuracy of carbon emission predictions. Discussion: By introducing this new AI-based method for predicting carbon emissions, this study not only provides more accurate data support for optimizing and implementing carbon neutrality measures in the sports fi eld but also improves the accuracy of time series data predictions. This enables a deeper understanding of carbon emission trends associated with sports activities. It contributes to the development of more effective mitigation strategies, making a significant contribution to global efforts to reduce carbon emissions. [ABSTRACT FROM AUTHOR]

Summary: Due to the energy crisis and environmental concerns, wind power has seen a considerable increase in use over the past 10 years as a source of renewable energy. Since wind is intermittent and variable, it is obvious that as penetration levels rise, the influence of wind power generation on the electric power system must be considered. Wind power forecasting is essential because large‐scale wind power integration will make it more difficult to plan, operate, and control the power system. An accurate forecast is an efficient way to deal with the operational problems brought on by wind variability. To better utilize wind energy resources, it is essential to increase prediction accuracy. Frequently, the noise in the dataset causes the ramp events to be misclassified or overestimated. The main emphasis of this study is the pre‐processing of wind power data that produces precise time‐series data while reducing noise or artifact content and maintaining the swing feature of the original data. For this task, the data augmentation approach is proposed, where the augmented data (synthetic data) will be added up with the training data, in such a way as to make the strategy useful for real‐time applications. As the next step, the significant features, such as higher‐order statistical features and lower‐order statistical features are extracted. The extracted features act as the input to the recurrent neural network (RNN) classifier, the weights of which are tuned using the proposed honey badger crow (HBCro) optimization algorithm. The proposed HBCro optimization algorithm acts as the major contribution of the proposed model, and it is modeled with the integration of the concepts of the crow search optimization (CSO) algorithm and the honey badger optimization algorithm (HBA). The proposed system is simulated in MATLAB and the effectiveness of the proposed method is validated by comparison with other conventional methods in terms of Error measures. Furthermore, the developed HBCro‐based RNN obtained efficient performance in terms of MSE, MAE, RMSE, RMPSE, MAPE, MARE, MSRE, and RMSRE of 0.1578, 0.0442, 0.2102, 123.238, 124.72, 0.9944, 1.1799, and 1.0732, respectively. [ABSTRACT FROM AUTHOR]

Neural networks inspired by differential equations have proliferated for the past several years, of which neural ordinary differential equations (NODEs) and neural controlled differential equations (NCDEs) are two representative examples. In theory, NCDEs exhibit better representation learning capability for time-series data than NODEs. In particular, it is known that NCDEs are suitable for processing irregular time-series data. Whereas NODEs have been successfully extended to adopt attention, methods to integrate attention into NCDEs have not yet been studied. To this end, we present attentive neural controlled differential equations (ANCDEs) for time-series classification and forecasting, where dual NCDEs are used: one for generating attention values and the other for evolving hidden vectors for a downstream machine learning task. We conduct experiments on 5 real-world time-series datasets and 11 baselines. After dropping some values, we also conduct experiments on irregular time-series. Our method consistently shows the best accuracy in all cases by non-trivial margins. Our visualizations also show that the presented attention mechanism works as intended by focusing on crucial information. [ABSTRACT FROM AUTHOR]

Among the existing prediction methods for strata behaviors law in working faces, the methods based on numerical simulation and statistical regression cannot achieve real-time and precise prediction of strata behaviors law in working faces. Deep learning methods have problems such as a large number of hyperparameters that are difficult to set and slow model training speed. In order to solve the above problems, based on the time-series data of internal stress changes in the coal body monitored during the mining process of the 402102 working face in Hujiahe Coal Mine, the particle swarm optimization based gate recurrent unit (PSO-GRU) is applied to predict the strata behaviors law in the working face. The PSO algorithm is used to optimize GRU. The PSO-GRU model is constructed to achieve automatic optimization of hyperparameters, thereby improving the training speed and prediction precision of GRU. Based on the prediction results, the analytic hierarchy process (AHP) is used to establish the evaluation index system of the main control factors of the strata behaviors of the 402102 mining face. The roof conditions, mining technology, coal seam occurrence, and geological structure are identified as the first level indicators affecting the strata behaviors of the working face. The 14 representative second level indicators are further subdivided. The test results show the following points. ① Compared with the unoptimized GRU model, the mean square error (MSE) of the PSO-GRU model is reduced by 83.9%, the root mean square error (RMSE) is reduced by 59.8%, the mean absolute error (MAE) is reduced by 59.0%, and the coefficient of determination R2 is increased by 28.9%. ② The PSO-GRU model has a fitting degree of over 0.980 for predicting strata behaviors data, demonstrating good nonlinear fitting and generalization capabilities. ③ The occurrence factors of coal seams in geological conditions have the greatest impact on the strata behaviors of the mining face, with a weight of 0.47. Among the factors that can be intervened by humans, the impact of advancing speed on the strata behaviors of the working face is the greatest, with a weight of 0.13.

Objective: Leveraging patient data through machine learning techniques in disease care offers a multitude of substantial benefits. Nonetheless, the inherent nature of patient data poses several challenges. Prevalent cases amass substantial longitudinal data owing to their patient volume and consistent follow-ups, however, longitudinal laboratory data are renowned for their irregularity, temporality, absenteeism, and sparsity; In contrast, recruitment for rare or specific cases is often constrained due to their limited patient size and episodic observations. This study employed self-supervised learning (SSL) to pretrain a generalized laboratory progress (GLP) model that captures the overall progression of six common laboratory markers in prevalent cardiovascular cases, with the intention of transferring this knowledge to aid in the detection of specific cardiovascular event. Methods and procedures: GLP implemented a two-stage training approach, leveraging the information embedded within interpolated data and amplify the performance of SSL. After GLP pretraining, it is transferred for target vessel revascularization (TVR) detection. Results: The proposed two-stage training improved the performance of pure SSL, and the transferability of GLP exhibited distinctiveness. After GLP processing, the classification exhibited a notable enhancement, with averaged accuracy rising from 0.63 to 0.90. All evaluated metrics demonstrated substantial superiority ( ${p} < 0.01$ ) compared to prior GLP processing. Conclusion: Our study effectively engages in translational engineering by transferring patient progression of cardiovascular laboratory parameters from one patient group to another, transcending the limitations of data availability. The transferability of disease progression optimized the strategies of examinations and treatments, and improves patient prognosis while using commonly available laboratory parameters. The potential for expanding this approach to encompass other diseases holds great promise. Clinical impact: Our study effectively transposes patient progression from one cohort to another, surpassing the constraints of episodic observation. The transferability of disease progression contributed to cardiovascular event assessment.

The rapidly growing global energy demand, environmental concerns, and the urgent need to reduce carbon footprints have made sustainable household energy consumption a critical priority. This study aims to analyze household energy data to predict the electricity self-sufficiency rate of households and extract meaningful insights that can enhance it. For this purpose, we use LightGBM (Light Gradient Boosting Machine)-, SHAP (SHapley Additive exPlanations)-, and correlation-heatmap-based approaches to analyze 12 months of energy and questionnaire survey data collected from over 200 smart houses in Kitakyushu, Japan. First, we use LightGBM to predict the ESSR of households and identify the key features that impact the prediction model. By using LightGBM, we demonstrated that the key features are the housing type, average monthly electricity bill, presence of floor heating system, average monthly gas bill, electricity tariff plan, electrical capacity, number of TVs, cooking equipment used, number of washing and drying machines, and the frequency of viewing home energy management systems (HEMSs). Furthermore, we adopted the LightGBM classifier with ℓ1 regularization to extract the most significant features and established a statistical correlation between these features and the electricity self-sufficiency rate. This LightGBM-based model can also predict the electricity self-sufficiency rate of households that did not participate in the questionnaire survey. The LightGBM-based model offers a global view of feature importance but lacks detailed explanations for individual predictions. For this purpose, we used SHAP analysis to identify the impact-wise order of key features that influence the electricity self-sufficiency rate (ESSR) and evaluated the contribution of each feature to the model’s predictions. A heatmap is also used to analyze the correlation among household variables and the ESSR. To evaluate the performance of the classification model, we used a confusion matrix showing a good F1 score (Weighted Avg) of 0.90. The findings discussed in this article offer valuable insights for energy policymakers to achieve the objective of developing energy-self-sufficient houses.